Commit | Line | Data |
---|---|---|
4e10a221 | 1 | ;;; GNU Guix --- Functional package management for GNU |
c3b2ab9d | 2 | ;;; Copyright © 2014, 2015, 2016, 2017, 2018 Ricardo Wurmus <rekado@elephly.net> |
7502badb | 3 | ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com> |
8921841d | 4 | ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl> |
a5002ae7 | 5 | ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr> |
a0a71439 | 6 | ;;; Copyright © 2016 Roel Janssen <roel@gnu.org> |
3df57b3a | 7 | ;;; Copyright © 2016, 2017, 2018 Efraim Flashner <efraim@flashner.co.il> |
318c0aee | 8 | ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com> |
658ab21d | 9 | ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com> |
ddf38ece | 10 | ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr> |
9364a520 | 11 | ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net> |
32cbbac1 | 12 | ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com> |
4e10a221 RW |
13 | ;;; |
14 | ;;; This file is part of GNU Guix. | |
15 | ;;; | |
16 | ;;; GNU Guix is free software; you can redistribute it and/or modify it | |
17 | ;;; under the terms of the GNU General Public License as published by | |
18 | ;;; the Free Software Foundation; either version 3 of the License, or (at | |
19 | ;;; your option) any later version. | |
20 | ;;; | |
21 | ;;; GNU Guix is distributed in the hope that it will be useful, but | |
22 | ;;; WITHOUT ANY WARRANTY; without even the implied warranty of | |
23 | ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
24 | ;;; GNU General Public License for more details. | |
25 | ;;; | |
26 | ;;; You should have received a copy of the GNU General Public License | |
27 | ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>. | |
28 | ||
29 | (define-module (gnu packages bioinformatics) | |
30 | #:use-module ((guix licenses) #:prefix license:) | |
31 | #:use-module (guix packages) | |
8e913213 | 32 | #:use-module (guix utils) |
4e10a221 | 33 | #:use-module (guix download) |
2c16316e | 34 | #:use-module (guix git-download) |
ec946638 | 35 | #:use-module (guix hg-download) |
10b4a969 | 36 | #:use-module (guix build-system ant) |
4e10a221 | 37 | #:use-module (guix build-system gnu) |
d7678942 | 38 | #:use-module (guix build-system cmake) |
c033f5d6 | 39 | #:use-module (guix build-system ocaml) |
365c8153 | 40 | #:use-module (guix build-system perl) |
8622a072 | 41 | #:use-module (guix build-system python) |
a5002ae7 | 42 | #:use-module (guix build-system r) |
9c38b540 | 43 | #:use-module (guix build-system ruby) |
9364a520 | 44 | #:use-module (guix build-system scons) |
d3517eda | 45 | #:use-module (guix build-system trivial) |
4e10a221 | 46 | #:use-module (gnu packages) |
a2950fa4 | 47 | #:use-module (gnu packages autotools) |
684bf7c7 | 48 | #:use-module (gnu packages algebra) |
d3517eda | 49 | #:use-module (gnu packages base) |
318c0aee | 50 | #:use-module (gnu packages bash) |
a0a71439 | 51 | #:use-module (gnu packages bison) |
e4e5a4d8 | 52 | #:use-module (gnu packages boost) |
ac257f12 | 53 | #:use-module (gnu packages check) |
4e10a221 | 54 | #:use-module (gnu packages compression) |
82c370de | 55 | #:use-module (gnu packages cpio) |
7cb61550 | 56 | #:use-module (gnu packages cran) |
1baee943 | 57 | #:use-module (gnu packages curl) |
99828fa7 | 58 | #:use-module (gnu packages documentation) |
94820951 | 59 | #:use-module (gnu packages databases) |
d29150b5 | 60 | #:use-module (gnu packages datastructures) |
75dd2424 | 61 | #:use-module (gnu packages file) |
99268755 | 62 | #:use-module (gnu packages flex) |
02f35bb5 | 63 | #:use-module (gnu packages gawk) |
2409f37f | 64 | #:use-module (gnu packages gcc) |
66e40e00 | 65 | #:use-module (gnu packages gd) |
97b9da68 | 66 | #:use-module (gnu packages gtk) |
b16728b0 | 67 | #:use-module (gnu packages glib) |
18f5d2a7 | 68 | #:use-module (gnu packages graph) |
db7a3444 | 69 | #:use-module (gnu packages groff) |
50937297 | 70 | #:use-module (gnu packages guile) |
89984be4 | 71 | #:use-module (gnu packages haskell) |
66e40e00 | 72 | #:use-module (gnu packages image) |
97b9da68 | 73 | #:use-module (gnu packages imagemagick) |
15a3c3d4 | 74 | #:use-module (gnu packages java) |
8d77a085 | 75 | #:use-module (gnu packages jemalloc) |
5ded35d8 | 76 | #:use-module (gnu packages ldc) |
51c64999 | 77 | #:use-module (gnu packages linux) |
ec946638 | 78 | #:use-module (gnu packages logging) |
36742f43 | 79 | #:use-module (gnu packages machine-learning) |
db7a3444 | 80 | #:use-module (gnu packages man) |
c833ab55 | 81 | #:use-module (gnu packages maths) |
6c2b26e2 | 82 | #:use-module (gnu packages mpi) |
4e10a221 | 83 | #:use-module (gnu packages ncurses) |
c033f5d6 | 84 | #:use-module (gnu packages ocaml) |
81f3e0c1 | 85 | #:use-module (gnu packages pcre) |
ceb62d54 | 86 | #:use-module (gnu packages parallel) |
66e40e00 | 87 | #:use-module (gnu packages pdf) |
4e10a221 | 88 | #:use-module (gnu packages perl) |
5ccde207 | 89 | #:use-module (gnu packages perl-check) |
4e10a221 | 90 | #:use-module (gnu packages pkg-config) |
bfe3c685 | 91 | #:use-module (gnu packages popt) |
e4e5a4d8 | 92 | #:use-module (gnu packages protobuf) |
346a829a | 93 | #:use-module (gnu packages python) |
589e3f4e | 94 | #:use-module (gnu packages python-web) |
ec946638 | 95 | #:use-module (gnu packages readline) |
9c38b540 | 96 | #:use-module (gnu packages ruby) |
84be3b99 | 97 | #:use-module (gnu packages serialization) |
94820951 | 98 | #:use-module (gnu packages shells) |
c833ab55 | 99 | #:use-module (gnu packages statistics) |
aa163424 | 100 | #:use-module (gnu packages swig) |
d7678942 | 101 | #:use-module (gnu packages tbb) |
97b9da68 | 102 | #:use-module (gnu packages tex) |
db7a3444 | 103 | #:use-module (gnu packages texinfo) |
2127cedb | 104 | #:use-module (gnu packages textutils) |
43c565d2 | 105 | #:use-module (gnu packages time) |
a2950fa4 | 106 | #:use-module (gnu packages tls) |
ce7155d5 | 107 | #:use-module (gnu packages vim) |
365c8153 | 108 | #:use-module (gnu packages web) |
c833ab55 | 109 | #:use-module (gnu packages xml) |
66e40e00 | 110 | #:use-module (gnu packages xorg) |
2c9232ae | 111 | #:use-module (srfi srfi-1) |
ce7e361f | 112 | #:use-module (ice-9 match)) |
4e10a221 | 113 | |
8dc797fa BW |
114 | (define-public aragorn |
115 | (package | |
116 | (name "aragorn") | |
e990c81d | 117 | (version "1.2.38") |
8dc797fa BW |
118 | (source (origin |
119 | (method url-fetch) | |
120 | (uri (string-append | |
121 | "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn" | |
122 | version ".tgz")) | |
123 | (sha256 | |
124 | (base32 | |
e990c81d | 125 | "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b")))) |
8dc797fa BW |
126 | (build-system gnu-build-system) |
127 | (arguments | |
128 | `(#:tests? #f ; there are no tests | |
129 | #:phases | |
130 | (modify-phases %standard-phases | |
131 | (delete 'configure) | |
132 | (replace 'build | |
133 | (lambda _ | |
134 | (zero? (system* "gcc" | |
135 | "-O3" | |
136 | "-ffast-math" | |
137 | "-finline-functions" | |
138 | "-o" | |
139 | "aragorn" | |
140 | (string-append "aragorn" ,version ".c"))))) | |
141 | (replace 'install | |
142 | (lambda* (#:key outputs #:allow-other-keys) | |
143 | (let* ((out (assoc-ref outputs "out")) | |
144 | (bin (string-append out "/bin")) | |
145 | (man (string-append out "/share/man/man1"))) | |
146 | (mkdir-p bin) | |
f3860753 | 147 | (install-file "aragorn" bin) |
8dc797fa | 148 | (mkdir-p man) |
f3860753 | 149 | (install-file "aragorn.1" man)) |
8dc797fa BW |
150 | #t))))) |
151 | (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN") | |
152 | (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences") | |
153 | (description | |
154 | "Aragorn identifies transfer RNA, mitochondrial RNA and | |
155 | transfer-messenger RNA from nucleotide sequences, based on homology to known | |
156 | tRNA consensus sequences and RNA structure. It also outputs the secondary | |
157 | structure of the predicted RNA.") | |
158 | (license license:gpl2))) | |
159 | ||
a12ba6e8 BW |
160 | (define-public bamm |
161 | (package | |
162 | (name "bamm") | |
4b6da268 | 163 | (version "1.7.3") |
a12ba6e8 BW |
164 | (source (origin |
165 | (method url-fetch) | |
166 | ;; BamM is not available on pypi. | |
167 | (uri (string-append | |
4b6da268 | 168 | "https://github.com/Ecogenomics/BamM/archive/" |
a12ba6e8 BW |
169 | version ".tar.gz")) |
170 | (file-name (string-append name "-" version ".tar.gz")) | |
171 | (sha256 | |
172 | (base32 | |
4b6da268 | 173 | "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s")) |
a12ba6e8 BW |
174 | (modules '((guix build utils))) |
175 | (snippet | |
176 | `(begin | |
177 | ;; Delete bundled htslib. | |
178 | (delete-file-recursively "c/htslib-1.3.1") | |
179 | #t)))) | |
180 | (build-system python-build-system) | |
181 | (arguments | |
182 | `(#:python ,python-2 ; BamM is Python 2 only. | |
183 | ;; Do not use bundled libhts. Do use the bundled libcfu because it has | |
184 | ;; been modified from its original form. | |
185 | #:configure-flags | |
186 | (let ((htslib (assoc-ref %build-inputs "htslib"))) | |
187 | (list "--with-libhts-lib" (string-append htslib "/lib") | |
188 | "--with-libhts-inc" (string-append htslib "/include/htslib"))) | |
189 | #:phases | |
190 | (modify-phases %standard-phases | |
191 | (add-after 'unpack 'autogen | |
192 | (lambda _ | |
193 | (with-directory-excursion "c" | |
194 | (let ((sh (which "sh"))) | |
195 | ;; Use autogen so that 'configure' works. | |
196 | (substitute* "autogen.sh" (("/bin/sh") sh)) | |
197 | (setenv "CONFIG_SHELL" sh) | |
198 | (substitute* "configure" (("/bin/sh") sh)) | |
199 | (zero? (system* "./autogen.sh")))))) | |
200 | (delete 'build) | |
201 | ;; Run tests after installation so compilation only happens once. | |
202 | (delete 'check) | |
203 | (add-after 'install 'wrap-executable | |
204 | (lambda* (#:key outputs #:allow-other-keys) | |
205 | (let* ((out (assoc-ref outputs "out")) | |
206 | (path (getenv "PATH"))) | |
207 | (wrap-program (string-append out "/bin/bamm") | |
208 | `("PATH" ":" prefix (,path)))) | |
209 | #t)) | |
210 | (add-after 'wrap-executable 'post-install-check | |
211 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
212 | (setenv "PATH" | |
213 | (string-append (assoc-ref outputs "out") | |
214 | "/bin:" | |
215 | (getenv "PATH"))) | |
216 | (setenv "PYTHONPATH" | |
217 | (string-append | |
218 | (assoc-ref outputs "out") | |
219 | "/lib/python" | |
220 | (string-take (string-take-right | |
221 | (assoc-ref inputs "python") 5) 3) | |
222 | "/site-packages:" | |
223 | (getenv "PYTHONPATH"))) | |
224 | ;; There are 2 errors printed, but they are safe to ignore: | |
225 | ;; 1) [E::hts_open_format] fail to open file ... | |
226 | ;; 2) samtools view: failed to open ... | |
227 | (zero? (system* "nosetests"))))))) | |
228 | (native-inputs | |
229 | `(("autoconf" ,autoconf) | |
230 | ("automake" ,automake) | |
231 | ("libtool" ,libtool) | |
232 | ("zlib" ,zlib) | |
233 | ("python-nose" ,python2-nose) | |
f3b98f4f | 234 | ("python-pysam" ,python2-pysam))) |
a12ba6e8 | 235 | (inputs |
bca2c576 | 236 | `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+. |
a12ba6e8 BW |
237 | ("samtools" ,samtools) |
238 | ("bwa" ,bwa) | |
239 | ("grep" ,grep) | |
240 | ("sed" ,sed) | |
241 | ("coreutils" ,coreutils))) | |
242 | (propagated-inputs | |
243 | `(("python-numpy" ,python2-numpy))) | |
244 | (home-page "http://ecogenomics.github.io/BamM/") | |
245 | (synopsis "Metagenomics-focused BAM file manipulator") | |
246 | (description | |
247 | "BamM is a C library, wrapped in python, to efficiently generate and | |
248 | parse BAM files, specifically for the analysis of metagenomic data. For | |
249 | instance, it implements several methods to assess contig-wise read coverage.") | |
250 | (license license:lgpl3+))) | |
251 | ||
9794180d RW |
252 | (define-public bamtools |
253 | (package | |
254 | (name "bamtools") | |
4ffa0858 | 255 | (version "2.5.1") |
9794180d RW |
256 | (source (origin |
257 | (method url-fetch) | |
258 | (uri (string-append | |
259 | "https://github.com/pezmaster31/bamtools/archive/v" | |
260 | version ".tar.gz")) | |
261 | (file-name (string-append name "-" version ".tar.gz")) | |
262 | (sha256 | |
263 | (base32 | |
4ffa0858 | 264 | "1z3kg24qrwq13a88n9d86izngrar4fll7gr6phddb2faw75pdgaa")))) |
9794180d | 265 | (build-system cmake-build-system) |
4702cec2 RW |
266 | (arguments |
267 | `(#:tests? #f ;no "check" target | |
268 | #:phases | |
269 | (modify-phases %standard-phases | |
270 | (add-before | |
271 | 'configure 'set-ldflags | |
272 | (lambda* (#:key outputs #:allow-other-keys) | |
273 | (setenv "LDFLAGS" | |
274 | (string-append | |
275 | "-Wl,-rpath=" | |
276 | (assoc-ref outputs "out") "/lib/bamtools"))))))) | |
9794180d RW |
277 | (inputs `(("zlib" ,zlib))) |
278 | (home-page "https://github.com/pezmaster31/bamtools") | |
279 | (synopsis "C++ API and command-line toolkit for working with BAM data") | |
280 | (description | |
281 | "BamTools provides both a C++ API and a command-line toolkit for handling | |
282 | BAM files.") | |
283 | (license license:expat))) | |
284 | ||
bdc7be59 MB |
285 | (define-public bcftools |
286 | (package | |
287 | (name "bcftools") | |
cbd9f91c | 288 | (version "1.8") |
bdc7be59 MB |
289 | (source (origin |
290 | (method url-fetch) | |
291 | (uri (string-append | |
292 | "https://github.com/samtools/bcftools/releases/download/" | |
293 | version "/bcftools-" version ".tar.bz2")) | |
294 | (sha256 | |
295 | (base32 | |
cbd9f91c | 296 | "1vgw2mwngq20c530zim52zvgmw1lci8rzl33pvh44xqk3xlzvjsa")) |
bdc7be59 MB |
297 | (modules '((guix build utils))) |
298 | (snippet | |
299 | ;; Delete bundled htslib. | |
cbd9f91c | 300 | '(delete-file-recursively "htslib-1.8")))) |
bdc7be59 MB |
301 | (build-system gnu-build-system) |
302 | (arguments | |
303 | `(#:test-target "test" | |
0620387a | 304 | #:configure-flags (list "--with-htslib=system") |
bdc7be59 MB |
305 | #:make-flags |
306 | (list | |
307 | "USE_GPL=1" | |
0620387a | 308 | "LIBS=-lgsl -lgslcblas" |
bdc7be59 MB |
309 | (string-append "prefix=" (assoc-ref %outputs "out")) |
310 | (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include") | |
98593f9f | 311 | (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so") |
bdc7be59 | 312 | (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip") |
98593f9f BW |
313 | (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix") |
314 | (string-append "PACKAGE_VERSION=" ,version)) | |
bdc7be59 MB |
315 | #:phases |
316 | (modify-phases %standard-phases | |
bdc7be59 MB |
317 | (add-before 'check 'patch-tests |
318 | (lambda _ | |
319 | (substitute* "test/test.pl" | |
320 | (("/bin/bash") (which "bash"))) | |
321 | #t))))) | |
322 | (native-inputs | |
323 | `(("htslib" ,htslib) | |
324 | ("perl" ,perl))) | |
325 | (inputs | |
326 | `(("gsl" ,gsl) | |
327 | ("zlib" ,zlib))) | |
328 | (home-page "https://samtools.github.io/bcftools/") | |
329 | (synopsis "Utilities for variant calling and manipulating VCFs and BCFs") | |
330 | (description | |
331 | "BCFtools is a set of utilities that manipulate variant calls in the | |
332 | Variant Call Format (VCF) and its binary counterpart BCF. All commands work | |
333 | transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.") | |
334 | ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1. | |
335 | (license (list license:gpl3+ license:expat)))) | |
336 | ||
8dd4ff11 RW |
337 | (define-public bedops |
338 | (package | |
339 | (name "bedops") | |
b43a9eb3 | 340 | (version "2.4.33") |
8dd4ff11 RW |
341 | (source (origin |
342 | (method url-fetch) | |
343 | (uri (string-append "https://github.com/bedops/bedops/archive/v" | |
344 | version ".tar.gz")) | |
f586c877 | 345 | (file-name (string-append name "-" version ".tar.gz")) |
8dd4ff11 RW |
346 | (sha256 |
347 | (base32 | |
b43a9eb3 | 348 | "0kx4awrwby8f33wqyx8w7ms7v25xhf0d421csgf96a3hfzn2mb0m")))) |
8dd4ff11 RW |
349 | (build-system gnu-build-system) |
350 | (arguments | |
351 | '(#:tests? #f | |
352 | #:make-flags (list (string-append "BINDIR=" %output "/bin")) | |
353 | #:phases | |
dc1d3cde KK |
354 | (modify-phases %standard-phases |
355 | (add-after 'unpack 'unpack-tarballs | |
356 | (lambda _ | |
357 | ;; FIXME: Bedops includes tarballs of minimally patched upstream | |
358 | ;; libraries jansson, zlib, and bzip2. We cannot just use stock | |
359 | ;; libraries because at least one of the libraries (zlib) is | |
360 | ;; patched to add a C++ function definition (deflateInit2cpp). | |
361 | ;; Until the Bedops developers offer a way to link against system | |
362 | ;; libraries we have to build the in-tree copies of these three | |
363 | ;; libraries. | |
364 | ||
365 | ;; See upstream discussion: | |
366 | ;; https://github.com/bedops/bedops/issues/124 | |
367 | ||
368 | ;; Unpack the tarballs to benefit from shebang patching. | |
369 | (with-directory-excursion "third-party" | |
370 | (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2")) | |
371 | (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2")) | |
372 | (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2")))) | |
373 | ;; Disable unpacking of tarballs in Makefile. | |
374 | (substitute* "system.mk/Makefile.linux" | |
375 | (("^\tbzcat .*") "\t@echo \"not unpacking\"\n") | |
376 | (("\\./configure") "CONFIG_SHELL=bash ./configure")) | |
377 | (substitute* "third-party/zlib-1.2.7/Makefile.in" | |
378 | (("^SHELL=.*$") "SHELL=bash\n")) | |
379 | #t)) | |
380 | (delete 'configure)))) | |
8dd4ff11 RW |
381 | (home-page "https://github.com/bedops/bedops") |
382 | (synopsis "Tools for high-performance genomic feature operations") | |
383 | (description | |
384 | "BEDOPS is a suite of tools to address common questions raised in genomic | |
385 | studies---mostly with regard to overlap and proximity relationships between | |
386 | data sets. It aims to be scalable and flexible, facilitating the efficient | |
387 | and accurate analysis and management of large-scale genomic data. | |
388 | ||
389 | BEDOPS provides tools that perform highly efficient and scalable Boolean and | |
390 | other set operations, statistical calculations, archiving, conversion and | |
391 | other management of genomic data of arbitrary scale. Tasks can be easily | |
392 | split by chromosome for distributing whole-genome analyses across a | |
393 | computational cluster.") | |
394 | (license license:gpl2+))) | |
395 | ||
81de5647 RW |
396 | (define-public bedtools |
397 | (package | |
398 | (name "bedtools") | |
6098a386 | 399 | (version "2.27.1") |
81de5647 RW |
400 | (source (origin |
401 | (method url-fetch) | |
0d9824cc RW |
402 | (uri (string-append "https://github.com/arq5x/bedtools2/releases/" |
403 | "download/v" version "/" | |
404 | "bedtools-" version ".tar.gz")) | |
81de5647 RW |
405 | (sha256 |
406 | (base32 | |
6098a386 | 407 | "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8")))) |
81de5647 | 408 | (build-system gnu-build-system) |
81de5647 RW |
409 | (arguments |
410 | '(#:test-target "test" | |
0d9824cc RW |
411 | #:make-flags |
412 | (list (string-append "prefix=" (assoc-ref %outputs "out"))) | |
81de5647 | 413 | #:phases |
6573ac82 | 414 | (modify-phases %standard-phases |
0d9824cc RW |
415 | (delete 'configure)))) |
416 | (native-inputs `(("python" ,python-2))) | |
417 | (inputs | |
418 | `(("samtools" ,samtools) | |
419 | ("zlib" ,zlib))) | |
81de5647 RW |
420 | (home-page "https://github.com/arq5x/bedtools2") |
421 | (synopsis "Tools for genome analysis and arithmetic") | |
422 | (description | |
423 | "Collectively, the bedtools utilities are a swiss-army knife of tools for | |
424 | a wide-range of genomics analysis tasks. The most widely-used tools enable | |
425 | genome arithmetic: that is, set theory on the genome. For example, bedtools | |
426 | allows one to intersect, merge, count, complement, and shuffle genomic | |
427 | intervals from multiple files in widely-used genomic file formats such as BAM, | |
428 | BED, GFF/GTF, VCF.") | |
429 | (license license:gpl2))) | |
430 | ||
9a8f309c RW |
431 | ;; Later releases of bedtools produce files with more columns than |
432 | ;; what Ribotaper expects. | |
433 | (define-public bedtools-2.18 | |
434 | (package (inherit bedtools) | |
435 | (name "bedtools") | |
436 | (version "2.18.0") | |
437 | (source (origin | |
438 | (method url-fetch) | |
439 | (uri (string-append "https://github.com/arq5x/bedtools2/" | |
440 | "archive/v" version ".tar.gz")) | |
441 | (file-name (string-append name "-" version ".tar.gz")) | |
442 | (sha256 | |
443 | (base32 | |
83b9d121 RW |
444 | "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf")))) |
445 | (arguments | |
446 | '(#:test-target "test" | |
447 | #:phases | |
448 | (modify-phases %standard-phases | |
449 | (delete 'configure) | |
450 | (replace 'install | |
451 | (lambda* (#:key outputs #:allow-other-keys) | |
452 | (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) | |
453 | (for-each (lambda (file) | |
454 | (install-file file bin)) | |
455 | (find-files "bin" ".*"))) | |
456 | #t))))))) | |
9a8f309c | 457 | |
17dc32a4 RW |
458 | (define-public ribotaper |
459 | (package | |
460 | (name "ribotaper") | |
461 | (version "1.3.1") | |
462 | (source (origin | |
463 | (method url-fetch) | |
464 | (uri (string-append "https://ohlerlab.mdc-berlin.de/" | |
465 | "files/RiboTaper/RiboTaper_Version_" | |
466 | version ".tar.gz")) | |
467 | (sha256 | |
468 | (base32 | |
469 | "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv")))) | |
470 | (build-system gnu-build-system) | |
7edee344 RW |
471 | (arguments |
472 | `(#:phases | |
473 | (modify-phases %standard-phases | |
474 | (add-after 'install 'wrap-executables | |
475 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
476 | (let* ((out (assoc-ref outputs "out"))) | |
477 | (for-each | |
478 | (lambda (script) | |
479 | (wrap-program (string-append out "/bin/" script) | |
480 | `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE"))))) | |
481 | '("create_annotations_files.bash" | |
482 | "create_metaplots.bash" | |
483 | "Ribotaper_ORF_find.sh" | |
484 | "Ribotaper.sh")))))))) | |
17dc32a4 RW |
485 | (inputs |
486 | `(("bedtools" ,bedtools-2.18) | |
487 | ("samtools" ,samtools-0.1) | |
2d7c4ae3 | 488 | ("r-minimal" ,r-minimal) |
17dc32a4 RW |
489 | ("r-foreach" ,r-foreach) |
490 | ("r-xnomial" ,r-xnomial) | |
491 | ("r-domc" ,r-domc) | |
492 | ("r-multitaper" ,r-multitaper) | |
493 | ("r-seqinr" ,r-seqinr))) | |
494 | (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/") | |
495 | (synopsis "Define translated ORFs using ribosome profiling data") | |
496 | (description | |
497 | "Ribotaper is a method for defining translated @dfn{open reading | |
498 | frames} (ORFs) using ribosome profiling (ribo-seq) data. This package | |
499 | provides the Ribotaper pipeline.") | |
500 | (license license:gpl3+))) | |
501 | ||
769fc6bb RW |
502 | (define-public ribodiff |
503 | (package | |
504 | (name "ribodiff") | |
505 | (version "0.2.2") | |
506 | (source | |
507 | (origin | |
508 | (method url-fetch) | |
509 | (uri (string-append "https://github.com/ratschlab/RiboDiff/" | |
510 | "archive/v" version ".tar.gz")) | |
511 | (file-name (string-append name "-" version ".tar.gz")) | |
512 | (sha256 | |
513 | (base32 | |
514 | "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj")))) | |
515 | (build-system python-build-system) | |
516 | (arguments | |
517 | `(#:python ,python-2 | |
518 | #:phases | |
519 | (modify-phases %standard-phases | |
520 | ;; Generate an installable executable script wrapper. | |
521 | (add-after 'unpack 'patch-setup.py | |
522 | (lambda _ | |
523 | (substitute* "setup.py" | |
524 | (("^(.*)packages=.*" line prefix) | |
525 | (string-append line "\n" | |
526 | prefix "scripts=['scripts/TE.py'],\n"))) | |
527 | #t))))) | |
528 | (inputs | |
529 | `(("python-numpy" ,python2-numpy) | |
530 | ("python-matplotlib" ,python2-matplotlib) | |
531 | ("python-scipy" ,python2-scipy) | |
532 | ("python-statsmodels" ,python2-statsmodels))) | |
2bb12f5a MB |
533 | (native-inputs |
534 | `(("python-mock" ,python2-mock) | |
535 | ("python-nose" ,python2-nose))) | |
769fc6bb RW |
536 | (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/") |
537 | (synopsis "Detect translation efficiency changes from ribosome footprints") | |
538 | (description "RiboDiff is a statistical tool that detects the protein | |
539 | translational efficiency change from Ribo-Seq (ribosome footprinting) and | |
540 | RNA-Seq data. It uses a generalized linear model to detect genes showing | |
541 | difference in translational profile taking mRNA abundance into account. It | |
542 | facilitates us to decipher the translational regulation that behave | |
543 | independently with transcriptional regulation.") | |
544 | (license license:gpl3+))) | |
545 | ||
a0a71439 RJ |
546 | (define-public bioawk |
547 | (package | |
548 | (name "bioawk") | |
549 | (version "1.0") | |
550 | (source (origin | |
551 | (method url-fetch) | |
552 | (uri (string-append "https://github.com/lh3/bioawk/archive/v" | |
553 | version ".tar.gz")) | |
554 | (file-name (string-append name "-" version ".tar.gz")) | |
555 | (sha256 | |
556 | (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw")))) | |
557 | (build-system gnu-build-system) | |
558 | (inputs | |
559 | `(("zlib" ,zlib))) | |
560 | (native-inputs | |
561 | `(("bison" ,bison))) | |
562 | (arguments | |
563 | `(#:tests? #f ; There are no tests to run. | |
564 | ;; Bison must generate files, before other targets can build. | |
565 | #:parallel-build? #f | |
566 | #:phases | |
567 | (modify-phases %standard-phases | |
568 | (delete 'configure) ; There is no configure phase. | |
569 | (replace 'install | |
570 | (lambda* (#:key outputs #:allow-other-keys) | |
571 | (let* ((out (assoc-ref outputs "out")) | |
572 | (bin (string-append out "/bin")) | |
573 | (man (string-append out "/share/man/man1"))) | |
574 | (mkdir-p man) | |
575 | (copy-file "awk.1" (string-append man "/bioawk.1")) | |
576 | (install-file "bioawk" bin))))))) | |
577 | (home-page "https://github.com/lh3/bioawk") | |
578 | (synopsis "AWK with bioinformatics extensions") | |
579 | (description "Bioawk is an extension to Brian Kernighan's awk, adding the | |
580 | support of several common biological data formats, including optionally gzip'ed | |
581 | BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It | |
582 | also adds a few built-in functions and a command line option to use TAB as the | |
583 | input/output delimiter. When the new functionality is not used, bioawk is | |
584 | intended to behave exactly the same as the original BWK awk.") | |
585 | (license license:x11))) | |
586 | ||
a2fb1492 RW |
587 | (define-public python2-pybedtools |
588 | (package | |
589 | (name "python2-pybedtools") | |
590 | (version "0.6.9") | |
591 | (source (origin | |
592 | (method url-fetch) | |
593 | (uri (string-append | |
594 | "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-" | |
595 | version ".tar.gz")) | |
596 | (sha256 | |
597 | (base32 | |
598 | "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an")))) | |
599 | (build-system python-build-system) | |
600 | (arguments `(#:python ,python-2)) ; no Python 3 support | |
601 | (inputs | |
f2516de2 | 602 | `(("python-matplotlib" ,python2-matplotlib))) |
a2fb1492 RW |
603 | (propagated-inputs |
604 | `(("bedtools" ,bedtools) | |
605 | ("samtools" ,samtools))) | |
606 | (native-inputs | |
f2516de2 HG |
607 | `(("python-cython" ,python2-cython) |
608 | ("python-pyyaml" ,python2-pyyaml) | |
f3b98f4f | 609 | ("python-nose" ,python2-nose))) |
a2fb1492 RW |
610 | (home-page "https://pythonhosted.org/pybedtools/") |
611 | (synopsis "Python wrapper for BEDtools programs") | |
612 | (description | |
613 | "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs, | |
614 | which are widely used for genomic interval manipulation or \"genome algebra\". | |
615 | pybedtools extends BEDTools by offering feature-level manipulations from with | |
616 | Python.") | |
617 | (license license:gpl2+))) | |
618 | ||
9e12eba8 BW |
619 | (define-public python-biom-format |
620 | (package | |
621 | (name "python-biom-format") | |
abc08cba | 622 | (version "2.1.6") |
9e12eba8 BW |
623 | (source |
624 | (origin | |
625 | (method url-fetch) | |
626 | ;; Use GitHub as source because PyPI distribution does not contain | |
627 | ;; test data: https://github.com/biocore/biom-format/issues/693 | |
628 | (uri (string-append "https://github.com/biocore/biom-format/archive/" | |
629 | version ".tar.gz")) | |
630 | (file-name (string-append name "-" version ".tar.gz")) | |
631 | (sha256 | |
632 | (base32 | |
abc08cba | 633 | "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj")))) |
9e12eba8 | 634 | (build-system python-build-system) |
de96ea28 | 635 | (propagated-inputs |
9e12eba8 BW |
636 | `(("python-numpy" ,python-numpy) |
637 | ("python-scipy" ,python-scipy) | |
638 | ("python-future" ,python-future) | |
639 | ("python-click" ,python-click) | |
abc08cba BW |
640 | ("python-h5py" ,python-h5py) |
641 | ("python-pandas" ,python-pandas))) | |
da5ebd10 MB |
642 | (native-inputs |
643 | `(("python-nose" ,python-nose))) | |
9e12eba8 BW |
644 | (home-page "http://www.biom-format.org") |
645 | (synopsis "Biological Observation Matrix (BIOM) format utilities") | |
646 | (description | |
647 | "The BIOM file format is designed to be a general-use format for | |
648 | representing counts of observations e.g. operational taxonomic units, KEGG | |
649 | orthology groups or lipid types, in one or more biological samples | |
650 | e.g. microbiome samples, genomes, metagenomes.") | |
651 | (license license:bsd-3) | |
652 | (properties `((python2-variant . ,(delay python2-biom-format)))))) | |
653 | ||
654 | (define-public python2-biom-format | |
655 | (let ((base (package-with-python2 (strip-python2-variant python-biom-format)))) | |
656 | (package | |
657 | (inherit base) | |
658 | (arguments | |
659 | `(#:phases | |
660 | (modify-phases %standard-phases | |
661 | ;; Do not require the unmaintained pyqi library. | |
662 | (add-after 'unpack 'remove-pyqi | |
663 | (lambda _ | |
664 | (substitute* "setup.py" | |
665 | (("install_requires.append\\(\"pyqi\"\\)") "pass")) | |
666 | #t))) | |
00e10c6e | 667 | ,@(package-arguments base)))))) |
9e12eba8 | 668 | |
f7283db3 RW |
669 | (define-public bioperl-minimal |
670 | (let* ((inputs `(("perl-module-build" ,perl-module-build) | |
671 | ("perl-data-stag" ,perl-data-stag) | |
672 | ("perl-libwww" ,perl-libwww) | |
673 | ("perl-uri" ,perl-uri))) | |
674 | (transitive-inputs | |
675 | (map (compose package-name cadr) | |
676 | (delete-duplicates | |
677 | (concatenate | |
678 | (map (compose package-transitive-target-inputs cadr) inputs)))))) | |
679 | (package | |
680 | (name "bioperl-minimal") | |
c70271ec | 681 | (version "1.7.0") |
f7283db3 RW |
682 | (source |
683 | (origin | |
684 | (method url-fetch) | |
c70271ec RW |
685 | (uri (string-append "https://github.com/bioperl/bioperl-live/" |
686 | "archive/release-" | |
687 | (string-map (lambda (c) | |
688 | (if (char=? c #\.) | |
689 | #\- c)) version) | |
690 | ".tar.gz")) | |
f7283db3 RW |
691 | (sha256 |
692 | (base32 | |
c70271ec | 693 | "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06")))) |
f7283db3 RW |
694 | (build-system perl-build-system) |
695 | (arguments | |
696 | `(#:phases | |
697 | (modify-phases %standard-phases | |
698 | (add-after | |
699 | 'install 'wrap-programs | |
700 | (lambda* (#:key outputs #:allow-other-keys) | |
701 | ;; Make sure all executables in "bin" find the required Perl | |
702 | ;; modules at runtime. As the PERL5LIB variable contains also | |
703 | ;; the paths of native inputs, we pick the transitive target | |
704 | ;; inputs from %build-inputs. | |
705 | (let* ((out (assoc-ref outputs "out")) | |
706 | (bin (string-append out "/bin/")) | |
707 | (path (string-join | |
708 | (cons (string-append out "/lib/perl5/site_perl") | |
709 | (map (lambda (name) | |
710 | (assoc-ref %build-inputs name)) | |
711 | ',transitive-inputs)) | |
712 | ":"))) | |
713 | (for-each (lambda (file) | |
714 | (wrap-program file | |
715 | `("PERL5LIB" ":" prefix (,path)))) | |
716 | (find-files bin "\\.pl$")) | |
717 | #t)))))) | |
718 | (inputs inputs) | |
719 | (native-inputs | |
720 | `(("perl-test-most" ,perl-test-most))) | |
721 | (home-page "http://search.cpan.org/dist/BioPerl") | |
722 | (synopsis "Bioinformatics toolkit") | |
723 | (description | |
724 | "BioPerl is the product of a community effort to produce Perl code which | |
725 | is useful in biology. Examples include Sequence objects, Alignment objects | |
726 | and database searching objects. These objects not only do what they are | |
727 | advertised to do in the documentation, but they also interact - Alignment | |
728 | objects are made from the Sequence objects, Sequence objects have access to | |
729 | Annotation and SeqFeature objects and databases, Blast objects can be | |
730 | converted to Alignment objects, and so on. This means that the objects | |
731 | provide a coordinated and extensible framework to do computational biology.") | |
2f3108ad | 732 | (license license:perl-license)))) |
f7283db3 | 733 | |
85c37e29 RW |
734 | (define-public python-biopython |
735 | (package | |
736 | (name "python-biopython") | |
af6ce610 | 737 | (version "1.70") |
85c37e29 RW |
738 | (source (origin |
739 | (method url-fetch) | |
e815c094 BW |
740 | ;; use PyPi rather than biopython.org to ease updating |
741 | (uri (pypi-uri "biopython" version)) | |
85c37e29 RW |
742 | (sha256 |
743 | (base32 | |
af6ce610 | 744 | "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a")))) |
85c37e29 | 745 | (build-system python-build-system) |
4ce60305 BW |
746 | (arguments |
747 | `(#:phases | |
748 | (modify-phases %standard-phases | |
749 | (add-before 'check 'set-home | |
750 | ;; Some tests require a home directory to be set. | |
751 | (lambda _ (setenv "HOME" "/tmp") #t))))) | |
f22efa01 | 752 | (propagated-inputs |
85c37e29 | 753 | `(("python-numpy" ,python-numpy))) |
85c37e29 RW |
754 | (home-page "http://biopython.org/") |
755 | (synopsis "Tools for biological computation in Python") | |
756 | (description | |
757 | "Biopython is a set of tools for biological computation including parsers | |
758 | for bioinformatics files into Python data structures; interfaces to common | |
759 | bioinformatics programs; a standard sequence class and tools for performing | |
760 | common operations on them; code to perform data classification; code for | |
761 | dealing with alignments; code making it easy to split up parallelizable tasks | |
762 | into separate processes; and more.") | |
5c31f4aa | 763 | (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE")))) |
85c37e29 RW |
764 | |
765 | (define-public python2-biopython | |
5c31f4aa | 766 | (package-with-python2 python-biopython)) |
85c37e29 | 767 | |
985d8411 BW |
768 | (define-public bpp-core |
769 | ;; The last release was in 2014 and the recommended way to install from source | |
770 | ;; is to clone the git repository, so we do this. | |
771 | ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page | |
772 | (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582")) | |
773 | (package | |
774 | (name "bpp-core") | |
775 | (version (string-append "2.2.0-1." (string-take commit 7))) | |
776 | (source (origin | |
777 | (method git-fetch) | |
778 | (uri (git-reference | |
779 | (url "http://biopp.univ-montp2.fr/git/bpp-core") | |
780 | (commit commit))) | |
781 | (file-name (string-append name "-" version "-checkout")) | |
782 | (sha256 | |
783 | (base32 | |
784 | "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j")))) | |
785 | (build-system cmake-build-system) | |
786 | (arguments | |
787 | `(#:parallel-build? #f)) | |
788 | (inputs | |
789 | `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we | |
790 | ; compile all of the bpp packages with GCC 5. | |
791 | (home-page "http://biopp.univ-montp2.fr") | |
792 | (synopsis "C++ libraries for Bioinformatics") | |
793 | (description | |
794 | "Bio++ is a set of C++ libraries for Bioinformatics, including sequence | |
795 | analysis, phylogenetics, molecular evolution and population genetics. It is | |
796 | Object Oriented and is designed to be both easy to use and computer efficient. | |
797 | Bio++ intends to help programmers to write computer expensive programs, by | |
798 | providing them a set of re-usable tools.") | |
799 | (license license:cecill-c)))) | |
800 | ||
8b5f4d57 BW |
801 | (define-public bpp-phyl |
802 | ;; The last release was in 2014 and the recommended way to install from source | |
803 | ;; is to clone the git repository, so we do this. | |
804 | ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page | |
805 | (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2")) | |
806 | (package | |
807 | (name "bpp-phyl") | |
808 | (version (string-append "2.2.0-1." (string-take commit 7))) | |
809 | (source (origin | |
810 | (method git-fetch) | |
811 | (uri (git-reference | |
812 | (url "http://biopp.univ-montp2.fr/git/bpp-phyl") | |
813 | (commit commit))) | |
814 | (file-name (string-append name "-" version "-checkout")) | |
815 | (sha256 | |
816 | (base32 | |
817 | "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh")))) | |
818 | (build-system cmake-build-system) | |
819 | (arguments | |
820 | `(#:parallel-build? #f | |
821 | ;; If out-of-source, test data is not copied into the build directory | |
822 | ;; so the tests fail. | |
823 | #:out-of-source? #f)) | |
824 | (inputs | |
825 | `(("bpp-core" ,bpp-core) | |
826 | ("bpp-seq" ,bpp-seq) | |
827 | ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more | |
828 | ;; modern GCC. | |
829 | ("gcc" ,gcc-5))) | |
830 | (home-page "http://biopp.univ-montp2.fr") | |
831 | (synopsis "Bio++ phylogenetic Library") | |
832 | (description | |
833 | "Bio++ is a set of C++ libraries for Bioinformatics, including sequence | |
834 | analysis, phylogenetics, molecular evolution and population genetics. This | |
835 | library provides phylogenetics-related modules.") | |
836 | (license license:cecill-c)))) | |
837 | ||
159a7016 BW |
838 | (define-public bpp-popgen |
839 | ;; The last release was in 2014 and the recommended way to install from source | |
840 | ;; is to clone the git repository, so we do this. | |
841 | ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page | |
842 | (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f")) | |
843 | (package | |
844 | (name "bpp-popgen") | |
845 | (version (string-append "2.2.0-1." (string-take commit 7))) | |
846 | (source (origin | |
847 | (method git-fetch) | |
848 | (uri (git-reference | |
849 | (url "http://biopp.univ-montp2.fr/git/bpp-popgen") | |
850 | (commit commit))) | |
851 | (file-name (string-append name "-" version "-checkout")) | |
852 | (sha256 | |
853 | (base32 | |
854 | "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5")))) | |
855 | (build-system cmake-build-system) | |
856 | (arguments | |
857 | `(#:parallel-build? #f | |
858 | #:tests? #f)) ; There are no tests. | |
859 | (inputs | |
860 | `(("bpp-core" ,bpp-core) | |
861 | ("bpp-seq" ,bpp-seq) | |
862 | ("gcc" ,gcc-5))) | |
863 | (home-page "http://biopp.univ-montp2.fr") | |
864 | (synopsis "Bio++ population genetics library") | |
865 | (description | |
866 | "Bio++ is a set of C++ libraries for Bioinformatics, including sequence | |
867 | analysis, phylogenetics, molecular evolution and population genetics. This | |
868 | library provides population genetics-related modules.") | |
869 | (license license:cecill-c)))) | |
870 | ||
70f1bc05 BW |
871 | (define-public bpp-seq |
872 | ;; The last release was in 2014 and the recommended way to install from source | |
873 | ;; is to clone the git repository, so we do this. | |
874 | ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page | |
875 | (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33")) | |
876 | (package | |
877 | (name "bpp-seq") | |
878 | (version (string-append "2.2.0-1." (string-take commit 7))) | |
879 | (source (origin | |
880 | (method git-fetch) | |
881 | (uri (git-reference | |
882 | (url "http://biopp.univ-montp2.fr/git/bpp-seq") | |
883 | (commit commit))) | |
884 | (file-name (string-append name "-" version "-checkout")) | |
885 | (sha256 | |
886 | (base32 | |
887 | "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2")))) | |
888 | (build-system cmake-build-system) | |
889 | (arguments | |
890 | `(#:parallel-build? #f | |
891 | ;; If out-of-source, test data is not copied into the build directory | |
892 | ;; so the tests fail. | |
893 | #:out-of-source? #f)) | |
894 | (inputs | |
895 | `(("bpp-core" ,bpp-core) | |
896 | ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'. | |
897 | (home-page "http://biopp.univ-montp2.fr") | |
898 | (synopsis "Bio++ sequence library") | |
899 | (description | |
900 | "Bio++ is a set of C++ libraries for Bioinformatics, including sequence | |
901 | analysis, phylogenetics, molecular evolution and population genetics. This | |
902 | library provides sequence-related modules.") | |
903 | (license license:cecill-c)))) | |
904 | ||
db7a3444 BW |
905 | (define-public bppsuite |
906 | ;; The last release was in 2014 and the recommended way to install from source | |
907 | ;; is to clone the git repository, so we do this. | |
908 | ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page | |
909 | (let ((commit "c516147f57aa50961121cd505bed52cd7603698b")) | |
910 | (package | |
911 | (name "bppsuite") | |
912 | (version (string-append "2.2.0-1." (string-take commit 7))) | |
913 | (source (origin | |
914 | (method git-fetch) | |
915 | (uri (git-reference | |
916 | (url "http://biopp.univ-montp2.fr/git/bppsuite") | |
917 | (commit commit))) | |
918 | (file-name (string-append name "-" version "-checkout")) | |
919 | (sha256 | |
920 | (base32 | |
921 | "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb")))) | |
922 | (build-system cmake-build-system) | |
923 | (arguments | |
924 | `(#:parallel-build? #f | |
925 | #:tests? #f)) ; There are no tests. | |
926 | (native-inputs | |
927 | `(("groff" ,groff) | |
928 | ("man-db" ,man-db) | |
929 | ("texinfo" ,texinfo))) | |
930 | (inputs | |
931 | `(("bpp-core" ,bpp-core) | |
932 | ("bpp-seq" ,bpp-seq) | |
933 | ("bpp-phyl" ,bpp-phyl) | |
934 | ("bpp-phyl" ,bpp-popgen) | |
935 | ("gcc" ,gcc-5))) | |
936 | (home-page "http://biopp.univ-montp2.fr") | |
937 | (synopsis "Bioinformatics tools written with the Bio++ libraries") | |
938 | (description | |
939 | "Bio++ is a set of C++ libraries for Bioinformatics, including sequence | |
940 | analysis, phylogenetics, molecular evolution and population genetics. This | |
941 | package provides command line tools using the Bio++ library.") | |
942 | (license license:cecill-c)))) | |
943 | ||
82c370de RW |
944 | (define-public blast+ |
945 | (package | |
946 | (name "blast+") | |
4732e6ee | 947 | (version "2.6.0") |
82c370de RW |
948 | (source (origin |
949 | (method url-fetch) | |
950 | (uri (string-append | |
951 | "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/" | |
952 | version "/ncbi-blast-" version "+-src.tar.gz")) | |
953 | (sha256 | |
954 | (base32 | |
4732e6ee BW |
955 | "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405")) |
956 | (patches (search-patches "blast+-fix-makefile.patch")) | |
82c370de RW |
957 | (modules '((guix build utils))) |
958 | (snippet | |
959 | '(begin | |
4732e6ee | 960 | ;; Remove bundled bzip2, zlib and pcre. |
82c370de RW |
961 | (delete-file-recursively "c++/src/util/compress/bzip2") |
962 | (delete-file-recursively "c++/src/util/compress/zlib") | |
4732e6ee | 963 | (delete-file-recursively "c++/src/util/regexp") |
82c370de RW |
964 | (substitute* "c++/src/util/compress/Makefile.in" |
965 | (("bzip2 zlib api") "api")) | |
966 | ;; Remove useless msbuild directory | |
967 | (delete-file-recursively | |
968 | "c++/src/build-system/project_tree_builder/msbuild") | |
969 | #t)))) | |
970 | (build-system gnu-build-system) | |
971 | (arguments | |
4732e6ee | 972 | `(;; There are two(!) tests for this massive library, and both fail with |
82c370de | 973 | ;; "unparsable timing stats". |
82c370de RW |
974 | ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats) |
975 | ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats) | |
976 | #:tests? #f | |
977 | #:out-of-source? #t | |
978 | #:parallel-build? #f ; not supported | |
979 | #:phases | |
980 | (modify-phases %standard-phases | |
981 | (add-before | |
982 | 'configure 'set-HOME | |
983 | ;; $HOME needs to be set at some point during the configure phase | |
984 | (lambda _ (setenv "HOME" "/tmp") #t)) | |
985 | (add-after | |
986 | 'unpack 'enter-dir | |
987 | (lambda _ (chdir "c++") #t)) | |
988 | (add-after | |
989 | 'enter-dir 'fix-build-system | |
990 | (lambda _ | |
991 | (define (which* cmd) | |
992 | (cond ((string=? cmd "date") | |
993 | ;; make call to "date" deterministic | |
994 | "date -d @0") | |
995 | ((which cmd) | |
996 | => identity) | |
997 | (else | |
998 | (format (current-error-port) | |
999 | "WARNING: Unable to find absolute path for ~s~%" | |
1000 | cmd) | |
1001 | #f))) | |
1002 | ||
1003 | ;; Rewrite hardcoded paths to various tools | |
1004 | (substitute* (append '("src/build-system/configure.ac" | |
1005 | "src/build-system/configure" | |
4732e6ee | 1006 | "src/build-system/helpers/run_with_lock.c" |
82c370de RW |
1007 | "scripts/common/impl/if_diff.sh" |
1008 | "scripts/common/impl/run_with_lock.sh" | |
1009 | "src/build-system/Makefile.configurables.real" | |
1010 | "src/build-system/Makefile.in.top" | |
1011 | "src/build-system/Makefile.meta.gmake=no" | |
1012 | "src/build-system/Makefile.meta.in" | |
1013 | "src/build-system/Makefile.meta_l" | |
1014 | "src/build-system/Makefile.meta_p" | |
1015 | "src/build-system/Makefile.meta_r" | |
1016 | "src/build-system/Makefile.mk.in" | |
1017 | "src/build-system/Makefile.requirements" | |
1018 | "src/build-system/Makefile.rules_with_autodep.in") | |
1019 | (find-files "scripts/common/check" "\\.sh$")) | |
1020 | (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd) | |
1021 | (or (which* cmd) all))) | |
1022 | ||
1023 | (substitute* (find-files "src/build-system" "^config.*") | |
1024 | (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln"))) | |
1025 | (("^PATH=.*") "")) | |
1026 | ||
1027 | ;; rewrite "/var/tmp" in check script | |
1028 | (substitute* "scripts/common/check/check_make_unix.sh" | |
1029 | (("/var/tmp") "/tmp")) | |
1030 | ||
1031 | ;; do not reset PATH | |
1032 | (substitute* (find-files "scripts/common/impl/" "\\.sh$") | |
1033 | (("^ *PATH=.*") "") | |
1034 | (("action=/bin/") "action=") | |
1035 | (("export PATH") ":")) | |
1036 | #t)) | |
1037 | (replace | |
1038 | 'configure | |
1039 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
1040 | (let ((out (assoc-ref outputs "out")) | |
1041 | (lib (string-append (assoc-ref outputs "lib") "/lib")) | |
1042 | (include (string-append (assoc-ref outputs "include") | |
1043 | "/include/ncbi-tools++"))) | |
1044 | ;; The 'configure' script doesn't recognize things like | |
1045 | ;; '--enable-fast-install'. | |
1046 | (zero? (system* "./configure.orig" | |
1047 | (string-append "--with-build-root=" (getcwd) "/build") | |
1048 | (string-append "--prefix=" out) | |
1049 | (string-append "--libdir=" lib) | |
1050 | (string-append "--includedir=" include) | |
1051 | (string-append "--with-bz2=" | |
1052 | (assoc-ref inputs "bzip2")) | |
1053 | (string-append "--with-z=" | |
1054 | (assoc-ref inputs "zlib")) | |
4732e6ee BW |
1055 | (string-append "--with-pcre=" |
1056 | (assoc-ref inputs "pcre")) | |
82c370de RW |
1057 | ;; Each library is built twice by default, once |
1058 | ;; with "-static" in its name, and again | |
1059 | ;; without. | |
1060 | "--without-static" | |
1061 | "--with-dll")))))))) | |
4732e6ee BW |
1062 | (outputs '("out" ; 21 MB |
1063 | "lib" ; 226 MB | |
1064 | "include")) ; 33 MB | |
82c370de RW |
1065 | (inputs |
1066 | `(("bzip2" ,bzip2) | |
4732e6ee BW |
1067 | ("zlib" ,zlib) |
1068 | ("pcre" ,pcre) | |
1069 | ("perl" ,perl) | |
1070 | ("python" ,python-wrapper))) | |
82c370de RW |
1071 | (native-inputs |
1072 | `(("cpio" ,cpio))) | |
1073 | (home-page "http://blast.ncbi.nlm.nih.gov") | |
1074 | (synopsis "Basic local alignment search tool") | |
1075 | (description | |
1076 | "BLAST is a popular method of performing a DNA or protein sequence | |
1077 | similarity search, using heuristics to produce results quickly. It also | |
1078 | calculates an “expect value” that estimates how many matches would have | |
1079 | occurred at a given score by chance, which can aid a user in judging how much | |
1080 | confidence to have in an alignment.") | |
1081 | ;; Most of the sources are in the public domain, with the following | |
1082 | ;; exceptions: | |
1083 | ;; * Expat: | |
1084 | ;; * ./c++/include/util/bitset/ | |
1085 | ;; * ./c++/src/html/ncbi_menu*.js | |
1086 | ;; * Boost license: | |
1087 | ;; * ./c++/include/util/impl/floating_point_comparison.hpp | |
1088 | ;; * LGPL 2+: | |
1089 | ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/ | |
1090 | ;; * ASL 2.0: | |
1091 | ;; * ./c++/src/corelib/teamcity_* | |
1092 | (license (list license:public-domain | |
1093 | license:expat | |
1094 | license:boost1.0 | |
1095 | license:lgpl2.0+ | |
1096 | license:asl2.0)))) | |
1097 | ||
6c2b26e2 RW |
1098 | (define-public bless |
1099 | (package | |
1100 | (name "bless") | |
1101 | (version "1p02") | |
1102 | (source (origin | |
1103 | (method url-fetch) | |
1104 | (uri (string-append "mirror://sourceforge/bless-ec/bless.v" | |
1105 | version ".tgz")) | |
1106 | (sha256 | |
1107 | (base32 | |
4d75e03a RW |
1108 | "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd")) |
1109 | (modules '((guix build utils))) | |
6c2b26e2 RW |
1110 | (snippet |
1111 | `(begin | |
1112 | ;; Remove bundled boost, pigz, zlib, and .git directory | |
953c1223 RW |
1113 | ;; FIXME: also remove bundled sources for murmurhash3 and |
1114 | ;; kmc once packaged. | |
6c2b26e2 RW |
1115 | (delete-file-recursively "boost") |
1116 | (delete-file-recursively "pigz") | |
953c1223 | 1117 | (delete-file-recursively "google-sparsehash") |
6c2b26e2 RW |
1118 | (delete-file-recursively "zlib") |
1119 | (delete-file-recursively ".git") | |
1120 | #t)))) | |
1121 | (build-system gnu-build-system) | |
1122 | (arguments | |
1123 | '(#:tests? #f ;no "check" target | |
1124 | #:make-flags | |
1125 | (list (string-append "ZLIB=" | |
1126 | (assoc-ref %build-inputs "zlib") | |
1127 | "/lib/libz.a") | |
1128 | (string-append "LDFLAGS=" | |
1129 | (string-join '("-lboost_filesystem" | |
1130 | "-lboost_system" | |
1131 | "-lboost_iostreams" | |
1132 | "-lz" | |
1133 | "-fopenmp" | |
1134 | "-std=c++11")))) | |
1135 | #:phases | |
1136 | (modify-phases %standard-phases | |
1137 | (add-after 'unpack 'do-not-build-bundled-pigz | |
1138 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
1139 | (substitute* "Makefile" | |
1140 | (("cd pigz/pigz-2.3.3; make") "")) | |
1141 | #t)) | |
1142 | (add-after 'unpack 'patch-paths-to-executables | |
1143 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
1144 | (substitute* "parse_args.cpp" | |
1145 | (("kmc_binary = .*") | |
1146 | (string-append "kmc_binary = \"" | |
1147 | (assoc-ref outputs "out") | |
1148 | "/bin/kmc\";")) | |
1149 | (("pigz_binary = .*") | |
1150 | (string-append "pigz_binary = \"" | |
1151 | (assoc-ref inputs "pigz") | |
1152 | "/bin/pigz\";"))) | |
1153 | #t)) | |
1154 | (replace 'install | |
1155 | (lambda* (#:key outputs #:allow-other-keys) | |
1156 | (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) | |
1157 | (for-each (lambda (file) | |
1158 | (install-file file bin)) | |
1159 | '("bless" "kmc/bin/kmc")) | |
1160 | #t))) | |
1161 | (delete 'configure)))) | |
1162 | (native-inputs | |
1163 | `(("perl" ,perl))) | |
1164 | (inputs | |
1165 | `(("openmpi" ,openmpi) | |
1166 | ("boost" ,boost) | |
953c1223 | 1167 | ("sparsehash" ,sparsehash) |
6c2b26e2 RW |
1168 | ("pigz" ,pigz) |
1169 | ("zlib" ,zlib))) | |
9641a899 | 1170 | (supported-systems '("x86_64-linux")) |
3b3b60d0 | 1171 | (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/") |
6c2b26e2 RW |
1172 | (synopsis "Bloom-filter-based error correction tool for NGS reads") |
1173 | (description | |
1174 | "@dfn{Bloom-filter-based error correction solution for high-throughput | |
1175 | sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a | |
1176 | correction tool for genomic reads produced by @dfn{Next-generation | |
1177 | sequencing} (NGS). BLESS produces accurate correction results with much less | |
1178 | memory compared with previous solutions and is also able to tolerate a higher | |
1179 | false-positive rate. BLESS can extend reads like DNA assemblers to correct | |
1180 | errors at the end of reads.") | |
1181 | (license license:gpl3+))) | |
1182 | ||
2c7ee167 RW |
1183 | (define-public bowtie |
1184 | (package | |
1185 | (name "bowtie") | |
d6e63cf3 | 1186 | (version "2.3.2") |
2c7ee167 RW |
1187 | (source (origin |
1188 | (method url-fetch) | |
1189 | (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v" | |
1190 | version ".tar.gz")) | |
f586c877 | 1191 | (file-name (string-append name "-" version ".tar.gz")) |
2c7ee167 RW |
1192 | (sha256 |
1193 | (base32 | |
d6e63cf3 | 1194 | "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90")) |
2c7ee167 RW |
1195 | (modules '((guix build utils))) |
1196 | (snippet | |
1197 | '(substitute* "Makefile" | |
2c7ee167 RW |
1198 | ;; replace BUILD_HOST and BUILD_TIME for deterministic build |
1199 | (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"") | |
0047d26a | 1200 | (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))))) |
2c7ee167 | 1201 | (build-system gnu-build-system) |
d6e63cf3 BW |
1202 | (inputs |
1203 | `(("perl" ,perl) | |
1204 | ("perl-clone" ,perl-clone) | |
1205 | ("perl-test-deep" ,perl-test-deep) | |
1206 | ("perl-test-simple" ,perl-test-simple) | |
1207 | ("python" ,python-2) | |
1208 | ("tbb" ,tbb) | |
1209 | ("zlib" ,zlib))) | |
2c7ee167 | 1210 | (arguments |
0047d26a RW |
1211 | '(#:make-flags |
1212 | (list "allall" | |
1213 | "WITH_TBB=1" | |
1214 | (string-append "prefix=" (assoc-ref %outputs "out"))) | |
2c7ee167 | 1215 | #:phases |
06e37236 BW |
1216 | (modify-phases %standard-phases |
1217 | (delete 'configure) | |
1218 | (replace 'check | |
1219 | (lambda* (#:key outputs #:allow-other-keys) | |
1220 | (zero? (system* "perl" | |
1221 | "scripts/test/simple_tests.pl" | |
1222 | "--bowtie2=./bowtie2" | |
1223 | "--bowtie2-build=./bowtie2-build"))))))) | |
2c7ee167 RW |
1224 | (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml") |
1225 | (synopsis "Fast and sensitive nucleotide sequence read aligner") | |
1226 | (description | |
1227 | "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing | |
1228 | reads to long reference sequences. It is particularly good at aligning reads | |
1229 | of about 50 up to 100s or 1,000s of characters, and particularly good at | |
1230 | aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the | |
1231 | genome with an FM Index to keep its memory footprint small: for the human | |
1232 | genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports | |
1233 | gapped, local, and paired-end alignment modes.") | |
241e1221 | 1234 | (supported-systems '("x86_64-linux")) |
2c7ee167 RW |
1235 | (license license:gpl3+))) |
1236 | ||
94ce537e RW |
1237 | (define-public tophat |
1238 | (package | |
1239 | (name "tophat") | |
1240 | (version "2.1.0") | |
1241 | (source (origin | |
1242 | (method url-fetch) | |
1243 | (uri (string-append | |
1244 | "http://ccb.jhu.edu/software/tophat/downloads/tophat-" | |
1245 | version ".tar.gz")) | |
1246 | (sha256 | |
1247 | (base32 | |
1248 | "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7")) | |
fc1adab1 | 1249 | (patches (search-patches "tophat-build-with-later-seqan.patch")) |
94ce537e RW |
1250 | (modules '((guix build utils))) |
1251 | (snippet | |
1252 | '(begin | |
1253 | ;; Remove bundled SeqAn and samtools | |
1254 | (delete-file-recursively "src/SeqAn-1.3") | |
1255 | (delete-file-recursively "src/samtools-0.1.18") | |
1256 | #t)))) | |
1257 | (build-system gnu-build-system) | |
1258 | (arguments | |
1259 | '(#:parallel-build? #f ; not supported | |
1260 | #:phases | |
1261 | (modify-phases %standard-phases | |
1262 | (add-after 'unpack 'use-system-samtools | |
1263 | (lambda* (#:key inputs #:allow-other-keys) | |
1264 | (substitute* "src/Makefile.in" | |
1265 | (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix) | |
1266 | (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "") | |
1267 | (("SAMPROG = samtools_0\\.1\\.18") "") | |
1268 | (("\\$\\(samtools_0_1_18_SOURCES\\)") "") | |
1269 | (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") "")) | |
1270 | (substitute* '("src/common.cpp" | |
1271 | "src/tophat.py") | |
1272 | (("samtools_0.1.18") (which "samtools"))) | |
1273 | (substitute* '("src/common.h" | |
1274 | "src/bam2fastx.cpp") | |
1275 | (("#include \"bam.h\"") "#include <samtools/bam.h>") | |
1276 | (("#include \"sam.h\"") "#include <samtools/sam.h>")) | |
1277 | (substitute* '("src/bwt_map.h" | |
1278 | "src/map2gtf.h" | |
1279 | "src/align_status.h") | |
1280 | (("#include <bam.h>") "#include <samtools/bam.h>") | |
1281 | (("#include <sam.h>") "#include <samtools/sam.h>")) | |
1282 | #t))))) | |
1283 | (inputs | |
1284 | `(("boost" ,boost) | |
1285 | ("bowtie" ,bowtie) | |
1286 | ("samtools" ,samtools-0.1) | |
1287 | ("ncurses" ,ncurses) | |
1288 | ("python" ,python-2) | |
1289 | ("perl" ,perl) | |
1290 | ("zlib" ,zlib) | |
1291 | ("seqan" ,seqan))) | |
1292 | (home-page "http://ccb.jhu.edu/software/tophat/index.shtml") | |
1293 | (synopsis "Spliced read mapper for RNA-Seq data") | |
1294 | (description | |
1295 | "TopHat is a fast splice junction mapper for nucleotide sequence | |
1296 | reads produced by the RNA-Seq method. It aligns RNA-Seq reads to | |
1297 | mammalian-sized genomes using the ultra high-throughput short read | |
1298 | aligner Bowtie, and then analyzes the mapping results to identify | |
1299 | splice junctions between exons.") | |
1300 | ;; TopHat is released under the Boost Software License, Version 1.0 | |
1301 | ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893 | |
1302 | (license license:boost1.0))) | |
1303 | ||
9a8336d8 RW |
1304 | (define-public bwa |
1305 | (package | |
1306 | (name "bwa") | |
6f141eff | 1307 | (version "0.7.17") |
9a8336d8 RW |
1308 | (source (origin |
1309 | (method url-fetch) | |
ae6e00f6 BW |
1310 | (uri (string-append |
1311 | "https://github.com/lh3/bwa/releases/download/v" | |
1312 | version "/bwa-" version ".tar.bz2")) | |
9a8336d8 RW |
1313 | (sha256 |
1314 | (base32 | |
6f141eff | 1315 | "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy")))) |
9a8336d8 RW |
1316 | (build-system gnu-build-system) |
1317 | (arguments | |
1318 | '(#:tests? #f ;no "check" target | |
1319 | #:phases | |
dc1d3cde KK |
1320 | (modify-phases %standard-phases |
1321 | (replace 'install | |
1322 | (lambda* (#:key outputs #:allow-other-keys) | |
1323 | (let ((bin (string-append | |
1324 | (assoc-ref outputs "out") "/bin")) | |
1325 | (doc (string-append | |
1326 | (assoc-ref outputs "out") "/share/doc/bwa")) | |
1327 | (man (string-append | |
1328 | (assoc-ref outputs "out") "/share/man/man1"))) | |
1329 | (install-file "bwa" bin) | |
1330 | (install-file "README.md" doc) | |
1331 | (install-file "bwa.1" man)) | |
1332 | #t)) | |
1333 | ;; no "configure" script | |
1334 | (delete 'configure)))) | |
9a8336d8 | 1335 | (inputs `(("zlib" ,zlib))) |
db94f8c7 RW |
1336 | ;; Non-portable SSE instructions are used so building fails on platforms |
1337 | ;; other than x86_64. | |
1338 | (supported-systems '("x86_64-linux")) | |
9a8336d8 RW |
1339 | (home-page "http://bio-bwa.sourceforge.net/") |
1340 | (synopsis "Burrows-Wheeler sequence aligner") | |
1341 | (description | |
1342 | "BWA is a software package for mapping low-divergent sequences against a | |
1343 | large reference genome, such as the human genome. It consists of three | |
1344 | algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is | |
1345 | designed for Illumina sequence reads up to 100bp, while the rest two for | |
1346 | longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar | |
1347 | features such as long-read support and split alignment, but BWA-MEM, which is | |
1348 | the latest, is generally recommended for high-quality queries as it is faster | |
1349 | and more accurate. BWA-MEM also has better performance than BWA-backtrack for | |
1350 | 70-100bp Illumina reads.") | |
1351 | (license license:gpl3+))) | |
1352 | ||
d29150b5 RW |
1353 | (define-public bwa-pssm |
1354 | (package (inherit bwa) | |
1355 | (name "bwa-pssm") | |
1356 | (version "0.5.11") | |
1357 | (source (origin | |
1358 | (method url-fetch) | |
1359 | (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/" | |
1360 | "archive/" version ".tar.gz")) | |
1361 | (file-name (string-append name "-" version ".tar.gz")) | |
1362 | (sha256 | |
1363 | (base32 | |
1364 | "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg")))) | |
1365 | (build-system gnu-build-system) | |
1366 | (inputs | |
1367 | `(("gdsl" ,gdsl) | |
1368 | ("zlib" ,zlib) | |
1369 | ("perl" ,perl))) | |
1370 | (home-page "http://bwa-pssm.binf.ku.dk/") | |
1371 | (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper") | |
1372 | (description | |
1373 | "BWA-PSSM is a probabilistic short genomic sequence read aligner based on | |
1374 | the use of @dfn{position specific scoring matrices} (PSSM). Like many of the | |
1375 | existing aligners it is fast and sensitive. Unlike most other aligners, | |
1376 | however, it is also adaptible in the sense that one can direct the alignment | |
1377 | based on known biases within the data set. It is coded as a modification of | |
1378 | the original BWA alignment program and shares the genome index structure as | |
1379 | well as many of the command line options.") | |
1380 | (license license:gpl3+))) | |
1381 | ||
ad641d53 RW |
1382 | (define-public python2-bx-python |
1383 | (package | |
1384 | (name "python2-bx-python") | |
c1dfe8c3 | 1385 | (version "0.7.3") |
ad641d53 RW |
1386 | (source (origin |
1387 | (method url-fetch) | |
c1dfe8c3 | 1388 | (uri (pypi-uri "bx-python" version)) |
ad641d53 RW |
1389 | (sha256 |
1390 | (base32 | |
c1dfe8c3 | 1391 | "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i")) |
ad641d53 RW |
1392 | (modules '((guix build utils))) |
1393 | (snippet | |
1394 | '(substitute* "setup.py" | |
1395 | ;; remove dependency on outdated "distribute" module | |
1396 | (("^from distribute_setup import use_setuptools") "") | |
1397 | (("^use_setuptools\\(\\)") ""))))) | |
1398 | (build-system python-build-system) | |
1399 | (arguments | |
1400 | `(#:tests? #f ;tests fail because test data are not included | |
1401 | #:python ,python-2)) | |
1402 | (inputs | |
1403 | `(("python-numpy" ,python2-numpy) | |
1404 | ("zlib" ,zlib))) | |
1405 | (native-inputs | |
f3b98f4f | 1406 | `(("python-nose" ,python2-nose))) |
ad641d53 RW |
1407 | (home-page "http://bitbucket.org/james_taylor/bx-python/") |
1408 | (synopsis "Tools for manipulating biological data") | |
1409 | (description | |
1410 | "bx-python provides tools for manipulating biological data, particularly | |
1411 | multiple sequence alignments.") | |
1412 | (license license:expat))) | |
1413 | ||
55a9a8c2 RW |
1414 | (define-public python-pysam |
1415 | (package | |
1416 | (name "python-pysam") | |
68565184 | 1417 | (version "0.13.0") |
d454640c RW |
1418 | (source (origin |
1419 | (method url-fetch) | |
f536dce5 MB |
1420 | ;; Test data is missing on PyPi. |
1421 | (uri (string-append | |
1422 | "https://github.com/pysam-developers/pysam/archive/v" | |
1423 | version ".tar.gz")) | |
1424 | (file-name (string-append name "-" version ".tar.gz")) | |
d454640c RW |
1425 | (sha256 |
1426 | (base32 | |
68565184 | 1427 | "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp")) |
dff26b23 MB |
1428 | (modules '((guix build utils))) |
1429 | (snippet | |
1430 | ;; Drop bundled htslib. TODO: Also remove samtools and bcftools. | |
1431 | '(delete-file-recursively "htslib")))) | |
55a9a8c2 RW |
1432 | (build-system python-build-system) |
1433 | (arguments | |
71dbf592 RW |
1434 | `(#:modules ((ice-9 ftw) |
1435 | (srfi srfi-26) | |
1436 | (guix build python-build-system) | |
1437 | (guix build utils)) | |
1438 | #:phases | |
397d463a MB |
1439 | (modify-phases %standard-phases |
1440 | (add-before 'build 'set-flags | |
dff26b23 MB |
1441 | (lambda* (#:key inputs #:allow-other-keys) |
1442 | (setenv "HTSLIB_MODE" "external") | |
1443 | (setenv "HTSLIB_LIBRARY_DIR" | |
1444 | (string-append (assoc-ref inputs "htslib") "/lib")) | |
1445 | (setenv "HTSLIB_INCLUDE_DIR" | |
1446 | (string-append (assoc-ref inputs "htslib") "/include")) | |
397d463a MB |
1447 | (setenv "LDFLAGS" "-lncurses") |
1448 | (setenv "CFLAGS" "-D_CURSES_LIB=1") | |
f536dce5 | 1449 | #t)) |
71dbf592 | 1450 | (replace 'check |
f536dce5 | 1451 | (lambda* (#:key inputs outputs #:allow-other-keys) |
71dbf592 | 1452 | ;; Add first subdirectory of "build" directory to PYTHONPATH. |
f536dce5 MB |
1453 | (setenv "PYTHONPATH" |
1454 | (string-append | |
1455 | (getenv "PYTHONPATH") | |
71dbf592 RW |
1456 | ":" (getcwd) "/build/" |
1457 | (car (scandir "build" | |
e1f02f92 | 1458 | (negate (cut string-prefix? "." <>)))))) |
f536dce5 | 1459 | ;; Step out of source dir so python does not import from CWD. |
71dbf592 RW |
1460 | (with-directory-excursion "tests" |
1461 | (setenv "HOME" "/tmp") | |
1462 | (and (zero? (system* "make" "-C" "pysam_data")) | |
1463 | (zero? (system* "make" "-C" "cbcf_data")) | |
b2955e22 RW |
1464 | ;; Running nosetests without explicitly asking for a |
1465 | ;; single process leads to a crash. Running with multiple | |
1466 | ;; processes fails because the tests are not designed to | |
1467 | ;; run in parallel. | |
31c374e0 RW |
1468 | |
1469 | ;; FIXME: tests keep timing out on some systems. | |
1470 | ;; (zero? (system* "nosetests" "-v" | |
1471 | ;; "--processes" "1")) | |
1472 | ))))))) | |
dff26b23 MB |
1473 | (propagated-inputs |
1474 | `(("htslib" ,htslib))) ; Included from installed header files. | |
55a9a8c2 | 1475 | (inputs |
649e9b3b | 1476 | `(("ncurses" ,ncurses) |
55a9a8c2 | 1477 | ("zlib" ,zlib))) |
649e9b3b RW |
1478 | (native-inputs |
1479 | `(("python-cython" ,python-cython) | |
f536dce5 MB |
1480 | ;; Dependencies below are are for tests only. |
1481 | ("samtools" ,samtools) | |
1482 | ("bcftools" ,bcftools) | |
1483 | ("python-nose" ,python-nose))) | |
55a9a8c2 RW |
1484 | (home-page "https://github.com/pysam-developers/pysam") |
1485 | (synopsis "Python bindings to the SAMtools C API") | |
1486 | (description | |
1487 | "Pysam is a Python module for reading and manipulating files in the | |
1488 | SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It | |
1489 | also includes an interface for tabix.") | |
1490 | (license license:expat))) | |
1491 | ||
1492 | (define-public python2-pysam | |
1493 | (package-with-python2 python-pysam)) | |
1494 | ||
4db9433a RW |
1495 | (define-public python-twobitreader |
1496 | (package | |
1497 | (name "python-twobitreader") | |
044ac8d2 | 1498 | (version "3.1.4") |
4db9433a RW |
1499 | (source (origin |
1500 | (method url-fetch) | |
1501 | (uri (pypi-uri "twobitreader" version)) | |
1502 | (sha256 | |
1503 | (base32 | |
044ac8d2 | 1504 | "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22")))) |
4db9433a | 1505 | (build-system python-build-system) |
900fb8d0 LF |
1506 | (arguments |
1507 | '(;; Tests are not distributed in the PyPi release. | |
1508 | ;; TODO Try building from the Git repo or asking the upstream maintainer | |
1509 | ;; to distribute the tests on PyPi. | |
1510 | #:tests? #f)) | |
4db9433a RW |
1511 | (native-inputs |
1512 | `(("python-sphinx" ,python-sphinx))) | |
1513 | (home-page "https://github.com/benjschiller/twobitreader") | |
1514 | (synopsis "Python library for reading .2bit files") | |
1515 | (description | |
1516 | "twobitreader is a Python library for reading .2bit files as used by the | |
1517 | UCSC genome browser.") | |
1518 | (license license:artistic2.0))) | |
1519 | ||
1520 | (define-public python2-twobitreader | |
5c31f4aa | 1521 | (package-with-python2 python-twobitreader)) |
4db9433a | 1522 | |
f94bf198 RW |
1523 | (define-public python-plastid |
1524 | (package | |
1525 | (name "python-plastid") | |
897ab082 | 1526 | (version "0.4.8") |
f94bf198 RW |
1527 | (source (origin |
1528 | (method url-fetch) | |
1529 | (uri (pypi-uri "plastid" version)) | |
1530 | (sha256 | |
1531 | (base32 | |
897ab082 | 1532 | "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8")))) |
f94bf198 RW |
1533 | (build-system python-build-system) |
1534 | (arguments | |
1535 | ;; Some test files are not included. | |
1536 | `(#:tests? #f)) | |
1537 | (propagated-inputs | |
1538 | `(("python-numpy" ,python-numpy) | |
1539 | ("python-scipy" ,python-scipy) | |
1540 | ("python-pandas" ,python-pandas) | |
1541 | ("python-pysam" ,python-pysam) | |
1542 | ("python-matplotlib" ,python-matplotlib) | |
1543 | ("python-biopython" ,python-biopython) | |
99caa6f7 BW |
1544 | ("python-twobitreader" ,python-twobitreader) |
1545 | ("python-termcolor" ,python-termcolor))) | |
f94bf198 RW |
1546 | (native-inputs |
1547 | `(("python-cython" ,python-cython) | |
1548 | ("python-nose" ,python-nose))) | |
1549 | (home-page "https://github.com/joshuagryphon/plastid") | |
1550 | (synopsis "Python library for genomic analysis") | |
1551 | (description | |
1552 | "plastid is a Python library for genomic analysis – in particular, | |
1553 | high-throughput sequencing data – with an emphasis on simplicity.") | |
1554 | (license license:bsd-3))) | |
1555 | ||
1556 | (define-public python2-plastid | |
5c31f4aa | 1557 | (package-with-python2 python-plastid)) |
f94bf198 | 1558 | |
6c1305f9 RW |
1559 | (define-public cd-hit |
1560 | (package | |
1561 | (name "cd-hit") | |
ba773f65 | 1562 | (version "4.6.8") |
6c1305f9 RW |
1563 | (source (origin |
1564 | (method url-fetch) | |
1565 | (uri (string-append "https://github.com/weizhongli/cdhit" | |
1566 | "/releases/download/V" version | |
ba773f65 BW |
1567 | "/cd-hit-v" version |
1568 | "-2017-0621-source.tar.gz")) | |
6c1305f9 RW |
1569 | (sha256 |
1570 | (base32 | |
d4735e8c | 1571 | "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn")))) |
6c1305f9 RW |
1572 | (build-system gnu-build-system) |
1573 | (arguments | |
1574 | `(#:tests? #f ; there are no tests | |
1575 | #:make-flags | |
1576 | ;; Executables are copied directly to the PREFIX. | |
1577 | (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")) | |
1578 | #:phases | |
1579 | (modify-phases %standard-phases | |
1580 | ;; No "configure" script | |
1581 | (delete 'configure) | |
1582 | ;; Remove sources of non-determinism | |
1583 | (add-after 'unpack 'be-timeless | |
1584 | (lambda _ | |
1585 | (substitute* "cdhit-utility.c++" | |
1586 | ((" \\(built on \" __DATE__ \"\\)") "")) | |
1587 | (substitute* "cdhit-common.c++" | |
1588 | (("__DATE__") "\"0\"") | |
1589 | (("\", %s, \" __TIME__ \"\\\\n\", date") "")) | |
1590 | #t)) | |
ba773f65 | 1591 | ;; The "install" target does not create the target directory. |
6c1305f9 RW |
1592 | (add-before 'install 'create-target-dir |
1593 | (lambda* (#:key outputs #:allow-other-keys) | |
1594 | (mkdir-p (string-append (assoc-ref outputs "out") "/bin")) | |
1595 | #t))))) | |
1596 | (inputs | |
1597 | `(("perl" ,perl))) | |
1598 | (home-page "http://weizhongli-lab.org/cd-hit/") | |
1599 | (synopsis "Cluster and compare protein or nucleotide sequences") | |
1600 | (description | |
1601 | "CD-HIT is a program for clustering and comparing protein or nucleotide | |
1602 | sequences. CD-HIT is designed to be fast and handle extremely large | |
1603 | databases.") | |
1604 | ;; The manual says: "It can be copied under the GNU General Public License | |
1605 | ;; version 2 (GPLv2)." | |
1606 | (license license:gpl2))) | |
1607 | ||
810cff85 RW |
1608 | (define-public clipper |
1609 | (package | |
1610 | (name "clipper") | |
433530a5 | 1611 | (version "1.1") |
810cff85 RW |
1612 | (source (origin |
1613 | (method url-fetch) | |
1614 | (uri (string-append | |
1615 | "https://github.com/YeoLab/clipper/archive/" | |
1616 | version ".tar.gz")) | |
9ab5ea44 | 1617 | (file-name (string-append name "-" version ".tar.gz")) |
810cff85 RW |
1618 | (sha256 |
1619 | (base32 | |
433530a5 | 1620 | "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi")) |
810cff85 RW |
1621 | (modules '((guix build utils))) |
1622 | (snippet | |
433530a5 RW |
1623 | '(begin |
1624 | ;; remove unnecessary setup dependency | |
1625 | (substitute* "setup.py" | |
1626 | (("setup_requires = .*") "")) | |
1627 | (for-each delete-file | |
1628 | '("clipper/src/peaks.so" | |
1629 | "clipper/src/readsToWiggle.so")) | |
1630 | (delete-file-recursively "dist/") | |
1631 | #t)))) | |
810cff85 RW |
1632 | (build-system python-build-system) |
1633 | (arguments `(#:python ,python-2)) ; only Python 2 is supported | |
1634 | (inputs | |
92971d68 | 1635 | `(("htseq" ,python2-htseq) |
810cff85 RW |
1636 | ("python-pybedtools" ,python2-pybedtools) |
1637 | ("python-cython" ,python2-cython) | |
1638 | ("python-scikit-learn" ,python2-scikit-learn) | |
1639 | ("python-matplotlib" ,python2-matplotlib) | |
433530a5 | 1640 | ("python-pandas" ,python2-pandas) |
810cff85 RW |
1641 | ("python-pysam" ,python2-pysam) |
1642 | ("python-numpy" ,python2-numpy) | |
1643 | ("python-scipy" ,python2-scipy))) | |
1644 | (native-inputs | |
f3b98f4f | 1645 | `(("python-mock" ,python2-mock) ; for tests |
d281be18 | 1646 | ("python-nose" ,python2-nose) ; for tests |
f3b98f4f | 1647 | ("python-pytz" ,python2-pytz))) ; for tests |
810cff85 RW |
1648 | (home-page "https://github.com/YeoLab/clipper") |
1649 | (synopsis "CLIP peak enrichment recognition") | |
1650 | (description | |
1651 | "CLIPper is a tool to define peaks in CLIP-seq datasets.") | |
1652 | (license license:gpl2))) | |
1653 | ||
6a35566d RS |
1654 | (define-public codingquarry |
1655 | (package | |
1656 | (name "codingquarry") | |
1657 | (version "2.0") | |
1658 | (source (origin | |
1659 | (method url-fetch) | |
1660 | (uri (string-append | |
1661 | "mirror://sourceforge/codingquarry/CodingQuarry_v" | |
1662 | version ".tar.gz")) | |
1663 | (sha256 | |
1664 | (base32 | |
1665 | "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i")))) | |
1666 | (build-system gnu-build-system) | |
1667 | (arguments | |
1668 | '(#:tests? #f ; no "check" target | |
1669 | #:phases | |
1670 | (modify-phases %standard-phases | |
1671 | (delete 'configure) | |
1672 | (replace 'install | |
1673 | (lambda* (#:key outputs #:allow-other-keys) | |
1674 | (let* ((out (assoc-ref outputs "out")) | |
1675 | (bin (string-append out "/bin")) | |
1676 | (doc (string-append out "/share/doc/codingquarry"))) | |
1677 | (install-file "INSTRUCTIONS.pdf" doc) | |
1678 | (copy-recursively "QuarryFiles" | |
1679 | (string-append out "/QuarryFiles")) | |
1680 | (install-file "CodingQuarry" bin) | |
1681 | (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))))))) | |
1682 | (inputs `(("openmpi" ,openmpi))) | |
1683 | (native-search-paths | |
1684 | (list (search-path-specification | |
1685 | (variable "QUARRY_PATH") | |
1686 | (files '("QuarryFiles"))))) | |
1687 | (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported | |
1688 | (synopsis "Fungal gene predictor") | |
1689 | (description "CodingQuarry is a highly accurate, self-training GHMM fungal | |
1690 | gene predictor designed to work with assembled, aligned RNA-seq transcripts.") | |
1691 | (home-page "https://sourceforge.net/projects/codingquarry/") | |
1692 | (license license:gpl3+))) | |
1693 | ||
36742f43 RW |
1694 | (define-public couger |
1695 | (package | |
1696 | (name "couger") | |
1697 | (version "1.8.2") | |
1698 | (source (origin | |
1699 | (method url-fetch) | |
1700 | (uri (string-append | |
1701 | "http://couger.oit.duke.edu/static/assets/COUGER" | |
1702 | version ".zip")) | |
1703 | (sha256 | |
1704 | (base32 | |
1705 | "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq")))) | |
1706 | (build-system gnu-build-system) | |
1707 | (arguments | |
1708 | `(#:tests? #f | |
1709 | #:phases | |
1710 | (modify-phases %standard-phases | |
1711 | (delete 'configure) | |
1712 | (delete 'build) | |
1713 | (replace | |
1714 | 'install | |
1715 | (lambda* (#:key outputs #:allow-other-keys) | |
f3860753 TGR |
1716 | (let* ((out (assoc-ref outputs "out")) |
1717 | (bin (string-append out "/bin"))) | |
36742f43 | 1718 | (copy-recursively "src" (string-append out "/src")) |
f3860753 | 1719 | (mkdir bin) |
36742f43 RW |
1720 | ;; Add "src" directory to module lookup path. |
1721 | (substitute* "couger" | |
1722 | (("from argparse") | |
1723 | (string-append "import sys\nsys.path.append(\"" | |
1724 | out "\")\nfrom argparse"))) | |
f3860753 | 1725 | (install-file "couger" bin)) |
36742f43 RW |
1726 | #t)) |
1727 | (add-after | |
1728 | 'install 'wrap-program | |
1729 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
1730 | ;; Make sure 'couger' runs with the correct PYTHONPATH. | |
1731 | (let* ((out (assoc-ref outputs "out")) | |
1732 | (path (getenv "PYTHONPATH"))) | |
1733 | (wrap-program (string-append out "/bin/couger") | |
1734 | `("PYTHONPATH" ":" prefix (,path)))) | |
1735 | #t))))) | |
1736 | (inputs | |
1737 | `(("python" ,python-2) | |
1738 | ("python2-pillow" ,python2-pillow) | |
1739 | ("python2-numpy" ,python2-numpy) | |
1740 | ("python2-scipy" ,python2-scipy) | |
1741 | ("python2-matplotlib" ,python2-matplotlib))) | |
1742 | (propagated-inputs | |
2d7c4ae3 | 1743 | `(("r-minimal" ,r-minimal) |
36742f43 RW |
1744 | ("libsvm" ,libsvm) |
1745 | ("randomjungle" ,randomjungle))) | |
1746 | (native-inputs | |
1747 | `(("unzip" ,unzip))) | |
1748 | (home-page "http://couger.oit.duke.edu") | |
1749 | (synopsis "Identify co-factors in sets of genomic regions") | |
1750 | (description | |
1751 | "COUGER can be applied to any two sets of genomic regions bound by | |
1752 | paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify | |
1753 | putative co-factors that provide specificity to each TF. The framework | |
1754 | determines the genomic targets uniquely-bound by each TF, and identifies a | |
1755 | small set of co-factors that best explain the in vivo binding differences | |
1756 | between the two TFs. | |
1757 | ||
1758 | COUGER uses classification algorithms (support vector machines and random | |
1759 | forests) with features that reflect the DNA binding specificities of putative | |
1760 | co-factors. The features are generated either from high-throughput TF-DNA | |
1761 | binding data (from protein binding microarray experiments), or from large | |
1762 | collections of DNA motifs.") | |
1763 | (license license:gpl3+))) | |
1764 | ||
bfe3c685 RW |
1765 | (define-public clustal-omega |
1766 | (package | |
1767 | (name "clustal-omega") | |
b3936f35 | 1768 | (version "1.2.4") |
bfe3c685 RW |
1769 | (source (origin |
1770 | (method url-fetch) | |
b3936f35 RW |
1771 | (uri (string-append "http://www.clustal.org/omega/clustal-omega-" |
1772 | version ".tar.gz")) | |
bfe3c685 RW |
1773 | (sha256 |
1774 | (base32 | |
b3936f35 | 1775 | "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6")))) |
bfe3c685 RW |
1776 | (build-system gnu-build-system) |
1777 | (inputs | |
1778 | `(("argtable" ,argtable))) | |
1779 | (home-page "http://www.clustal.org/omega/") | |
1780 | (synopsis "Multiple sequence aligner for protein and DNA/RNA") | |
1781 | (description | |
1782 | "Clustal-Omega is a general purpose multiple sequence alignment (MSA) | |
1783 | program for protein and DNA/RNA. It produces high quality MSAs and is capable | |
1784 | of handling data-sets of hundreds of thousands of sequences in reasonable | |
1785 | time.") | |
1786 | (license license:gpl2+))) | |
1787 | ||
191c7101 RW |
1788 | (define-public crossmap |
1789 | (package | |
1790 | (name "crossmap") | |
61d5fd03 | 1791 | (version "0.2.1") |
191c7101 RW |
1792 | (source (origin |
1793 | (method url-fetch) | |
1794 | (uri (string-append "mirror://sourceforge/crossmap/CrossMap-" | |
1795 | version ".tar.gz")) | |
1796 | (sha256 | |
1797 | (base32 | |
61d5fd03 RW |
1798 | "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f")) |
1799 | ;; This patch has been sent upstream already and is available | |
1800 | ;; for download from Sourceforge, but it has not been merged. | |
fc1adab1 | 1801 | (patches (search-patches "crossmap-allow-system-pysam.patch")) |
191c7101 RW |
1802 | (modules '((guix build utils))) |
1803 | ;; remove bundled copy of pysam | |
1804 | (snippet | |
1805 | '(delete-file-recursively "lib/pysam")))) | |
1806 | (build-system python-build-system) | |
1807 | (arguments | |
1808 | `(#:python ,python-2 | |
1809 | #:phases | |
dc1d3cde KK |
1810 | (modify-phases %standard-phases |
1811 | (add-after 'unpack 'set-env | |
1812 | (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t))))) | |
191c7101 RW |
1813 | (inputs |
1814 | `(("python-numpy" ,python2-numpy) | |
1815 | ("python-pysam" ,python2-pysam) | |
1816 | ("zlib" ,zlib))) | |
1817 | (native-inputs | |
1818 | `(("python-cython" ,python2-cython) | |
f3b98f4f | 1819 | ("python-nose" ,python2-nose))) |
191c7101 RW |
1820 | (home-page "http://crossmap.sourceforge.net/") |
1821 | (synopsis "Convert genome coordinates between assemblies") | |
1822 | (description | |
1823 | "CrossMap is a program for conversion of genome coordinates or annotation | |
1824 | files between different genome assemblies. It supports most commonly used | |
1825 | file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.") | |
1826 | (license license:gpl2+))) | |
1827 | ||
8e913213 RW |
1828 | (define-public cutadapt |
1829 | (package | |
1830 | (name "cutadapt") | |
3ede1550 | 1831 | (version "1.16") |
8e913213 | 1832 | (source (origin |
3ede1550 RW |
1833 | (method git-fetch) |
1834 | (uri (git-reference | |
1835 | (url "https://github.com/marcelm/cutadapt.git") | |
1836 | (commit (string-append "v" version)))) | |
1837 | (file-name (string-append name "-" version "-checkout")) | |
8e913213 RW |
1838 | (sha256 |
1839 | (base32 | |
3ede1550 | 1840 | "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8")))) |
8e913213 | 1841 | (build-system python-build-system) |
1f94bff2 TGR |
1842 | (inputs |
1843 | `(("python-xopen" ,python-xopen))) | |
8e913213 RW |
1844 | (native-inputs |
1845 | `(("python-cython" ,python-cython) | |
3ede1550 | 1846 | ("python-pytest" ,python-pytest))) |
0c6c9c00 | 1847 | (home-page "https://cutadapt.readthedocs.io/en/stable/") |
8e913213 RW |
1848 | (synopsis "Remove adapter sequences from nucleotide sequencing reads") |
1849 | (description | |
1850 | "Cutadapt finds and removes adapter sequences, primers, poly-A tails and | |
1851 | other types of unwanted sequence from high-throughput sequencing reads.") | |
1852 | (license license:expat))) | |
1853 | ||
1baee943 RW |
1854 | (define-public libbigwig |
1855 | (package | |
1856 | (name "libbigwig") | |
1857 | (version "0.1.4") | |
1858 | (source (origin | |
1859 | (method url-fetch) | |
1860 | (uri (string-append "https://github.com/dpryan79/libBigWig/" | |
1861 | "archive/" version ".tar.gz")) | |
1862 | (file-name (string-append name "-" version ".tar.gz")) | |
1863 | (sha256 | |
1864 | (base32 | |
1865 | "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1")))) | |
1866 | (build-system gnu-build-system) | |
1867 | (arguments | |
1868 | `(#:test-target "test" | |
1869 | #:make-flags | |
1870 | (list "CC=gcc" | |
1871 | (string-append "prefix=" (assoc-ref %outputs "out"))) | |
1872 | #:phases | |
1873 | (modify-phases %standard-phases | |
1874 | (delete 'configure) | |
1875 | (add-before 'check 'disable-curl-test | |
1876 | (lambda _ | |
1877 | (substitute* "Makefile" | |
1878 | (("./test/testRemote.*") "")) | |
1879 | #t)) | |
1880 | ;; This has been fixed with the upstream commit 4ff6959cd8a0, but | |
1881 | ;; there has not yet been a release containing this change. | |
1882 | (add-before 'install 'create-target-dirs | |
1883 | (lambda* (#:key outputs #:allow-other-keys) | |
1884 | (let ((out (assoc-ref outputs "out"))) | |
1885 | (mkdir-p (string-append out "/lib")) | |
1886 | (mkdir-p (string-append out "/include")) | |
1887 | #t)))))) | |
1888 | (inputs | |
1889 | `(("zlib" ,zlib) | |
1890 | ("curl" ,curl))) | |
1891 | (native-inputs | |
1892 | `(("doxygen" ,doxygen))) | |
1893 | (home-page "https://github.com/dpryan79/libBigWig") | |
1894 | (synopsis "C library for handling bigWig files") | |
1895 | (description | |
1896 | "This package provides a C library for parsing local and remote BigWig | |
1897 | files.") | |
1898 | (license license:expat))) | |
1899 | ||
69e0e03c RW |
1900 | (define-public python-pybigwig |
1901 | (package | |
1902 | (name "python-pybigwig") | |
1903 | (version "0.2.5") | |
1904 | (source (origin | |
1905 | (method url-fetch) | |
1906 | (uri (pypi-uri "pyBigWig" version)) | |
1907 | (sha256 | |
1908 | (base32 | |
1909 | "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d")) | |
1910 | (modules '((guix build utils))) | |
1911 | (snippet | |
1912 | '(begin | |
1913 | ;; Delete bundled libBigWig sources | |
1914 | (delete-file-recursively "libBigWig"))))) | |
1915 | (build-system python-build-system) | |
1916 | (arguments | |
1917 | `(#:phases | |
1918 | (modify-phases %standard-phases | |
1919 | (add-after 'unpack 'link-with-libBigWig | |
1920 | (lambda* (#:key inputs #:allow-other-keys) | |
1921 | (substitute* "setup.py" | |
1922 | (("libs=\\[") "libs=[\"BigWig\", ")) | |
1923 | #t))))) | |
1924 | (inputs | |
1925 | `(("libbigwig" ,libbigwig) | |
1926 | ("zlib" ,zlib) | |
1927 | ("curl" ,curl))) | |
1928 | (home-page "https://github.com/dpryan79/pyBigWig") | |
1929 | (synopsis "Access bigWig files in Python using libBigWig") | |
1930 | (description | |
1931 | "This package provides Python bindings to the libBigWig library for | |
1932 | accessing bigWig files.") | |
1933 | (license license:expat))) | |
1934 | ||
1935 | (define-public python2-pybigwig | |
5c31f4aa | 1936 | (package-with-python2 python-pybigwig)) |
69e0e03c | 1937 | |
ec2a67de BW |
1938 | (define-public python-dendropy |
1939 | (package | |
1940 | (name "python-dendropy") | |
25d84d31 | 1941 | (version "4.2.0") |
ec2a67de BW |
1942 | (source |
1943 | (origin | |
1944 | (method url-fetch) | |
1945 | (uri (pypi-uri "DendroPy" version)) | |
1946 | (sha256 | |
1947 | (base32 | |
1885bb0c RW |
1948 | "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p")) |
1949 | (patches (search-patches "python-dendropy-fix-tests.patch")))) | |
ec2a67de BW |
1950 | (build-system python-build-system) |
1951 | (home-page "http://packages.python.org/DendroPy/") | |
1952 | (synopsis "Library for phylogenetics and phylogenetic computing") | |
1953 | (description | |
1954 | "DendroPy is a library for phylogenetics and phylogenetic computing: reading, | |
1955 | writing, simulation, processing and manipulation of phylogenetic | |
1956 | trees (phylogenies) and characters.") | |
1957 | (license license:bsd-3) | |
1958 | (properties `((python2-variant . ,(delay python2-dendropy)))))) | |
1959 | ||
1960 | (define-public python2-dendropy | |
1961 | (let ((base (package-with-python2 (strip-python2-variant python-dendropy)))) | |
1962 | (package | |
1963 | (inherit base) | |
9602e3cc BW |
1964 | (arguments |
1965 | `(#:python ,python-2 | |
1966 | #:phases | |
1967 | (modify-phases %standard-phases | |
1968 | (replace 'check | |
1969 | ;; There is currently a test failure that only happens on some | |
1970 | ;; systems, and only using "setup.py test" | |
1971 | (lambda _ (zero? (system* "nosetests"))))))) | |
f3b98f4f | 1972 | (native-inputs `(("python2-nose" ,python2-nose) |
ec2a67de BW |
1973 | ,@(package-native-inputs base)))))) |
1974 | ||
eb2200f3 RW |
1975 | (define-public python-py2bit |
1976 | (package | |
1977 | (name "python-py2bit") | |
1978 | (version "0.2.1") | |
1979 | (source | |
1980 | (origin | |
1981 | (method url-fetch) | |
1982 | (uri (pypi-uri "py2bit" version)) | |
1983 | (sha256 | |
1984 | (base32 | |
1985 | "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl")))) | |
1986 | (build-system python-build-system) | |
1987 | (home-page "https://github.com/dpryan79/py2bit") | |
1988 | (synopsis "Access 2bit files using lib2bit") | |
1989 | (description | |
1990 | "This package provides Python bindings for lib2bit to access 2bit files | |
1991 | with Python.") | |
1992 | (license license:expat))) | |
ec2a67de | 1993 | |
1921b1de RW |
1994 | (define-public deeptools |
1995 | (package | |
1996 | (name "deeptools") | |
fed72008 | 1997 | (version "2.5.1") |
1921b1de RW |
1998 | (source (origin |
1999 | (method url-fetch) | |
cd70f9bd | 2000 | (uri (string-append "https://github.com/deeptools/deepTools/" |
3acb8c85 | 2001 | "archive/" version ".tar.gz")) |
1921b1de RW |
2002 | (file-name (string-append name "-" version ".tar.gz")) |
2003 | (sha256 | |
2004 | (base32 | |
fed72008 | 2005 | "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540")))) |
1921b1de | 2006 | (build-system python-build-system) |
14bda1ff | 2007 | (inputs |
fed72008 RW |
2008 | `(("python-scipy" ,python-scipy) |
2009 | ("python-numpy" ,python-numpy) | |
2010 | ("python-numpydoc" ,python-numpydoc) | |
2011 | ("python-matplotlib" ,python-matplotlib) | |
2012 | ("python-pysam" ,python-pysam) | |
2013 | ("python-py2bit" ,python-py2bit) | |
2014 | ("python-pybigwig" ,python-pybigwig))) | |
1921b1de | 2015 | (native-inputs |
fed72008 RW |
2016 | `(("python-mock" ,python-mock) ;for tests |
2017 | ("python-nose" ,python-nose) ;for tests | |
2018 | ("python-pytz" ,python-pytz))) ;for tests | |
cd70f9bd | 2019 | (home-page "https://github.com/deeptools/deepTools") |
1921b1de RW |
2020 | (synopsis "Tools for normalizing and visualizing deep-sequencing data") |
2021 | (description | |
2022 | "DeepTools addresses the challenge of handling the large amounts of data | |
2023 | that are now routinely generated from DNA sequencing centers. To do so, | |
2024 | deepTools contains useful modules to process the mapped reads data to create | |
2025 | coverage files in standard bedGraph and bigWig file formats. By doing so, | |
2026 | deepTools allows the creation of normalized coverage files or the comparison | |
2027 | between two files (for example, treatment and control). Finally, using such | |
2028 | normalized and standardized files, multiple visualizations can be created to | |
2029 | identify enrichments with functional annotations of the genome.") | |
2030 | (license license:gpl3+))) | |
2031 | ||
fdc30687 RJ |
2032 | (define-public delly |
2033 | (package | |
2034 | (name "delly") | |
2035 | (version "0.7.7") | |
2036 | (source (origin | |
2037 | (method url-fetch) | |
2038 | (uri (string-append | |
2039 | "https://github.com/tobiasrausch/delly/archive/v" | |
2040 | version ".tar.gz")) | |
2041 | (file-name (string-append name "-" version ".tar.gz")) | |
2042 | (sha256 | |
2043 | (base32 "0dkwy3pyxmi6dhh1lpsr3698ri5sslw9qz67hfys0bz8dgrqwabj")) | |
2044 | (patches (search-patches "delly-use-system-libraries.patch")))) | |
2045 | (build-system gnu-build-system) | |
2046 | (arguments | |
2047 | `(#:tests? #f ; There are no tests to run. | |
2048 | #:make-flags '("PARALLEL=1") ; Allow parallel execution at run-time. | |
2049 | #:phases | |
2050 | (modify-phases %standard-phases | |
2051 | (delete 'configure) ; There is no configure phase. | |
2052 | (replace 'install | |
2053 | (lambda _ | |
2054 | (let ((bin (string-append (assoc-ref %outputs "out") "/bin")) | |
2055 | (templates (string-append (assoc-ref %outputs "out") | |
2056 | "/share/delly/templates"))) | |
2057 | (mkdir-p bin) | |
2058 | (mkdir-p templates) | |
2059 | (copy-recursively "excludeTemplates" templates) | |
2060 | (install-file "src/cov" bin) | |
2061 | (install-file "src/delly" bin) | |
2062 | (install-file "src/dpe" bin))))))) | |
2063 | (native-inputs | |
2064 | `(("python" ,python-2))) | |
2065 | (inputs | |
2066 | `(("boost" ,boost) | |
2067 | ("htslib" ,htslib) | |
2068 | ("zlib" ,zlib) | |
2069 | ("bzip2" ,bzip2))) | |
2070 | (home-page "https://github.com/tobiasrausch/delly") | |
2071 | (synopsis "Integrated structural variant prediction method") | |
2072 | (description "Delly is an integrated structural variant prediction method | |
2073 | that can discover and genotype deletions, tandem duplications, inversions and | |
2074 | translocations at single-nucleotide resolution in short-read massively parallel | |
2075 | sequencing data. It uses paired-ends and split-reads to sensitively and | |
2076 | accurately delineate genomic rearrangements throughout the genome.") | |
2077 | (license license:gpl3+))) | |
2078 | ||
684bf7c7 BW |
2079 | (define-public diamond |
2080 | (package | |
2081 | (name "diamond") | |
2c5289b2 | 2082 | (version "0.9.22") |
684bf7c7 BW |
2083 | (source (origin |
2084 | (method url-fetch) | |
2085 | (uri (string-append | |
2086 | "https://github.com/bbuchfink/diamond/archive/v" | |
2087 | version ".tar.gz")) | |
2088 | (file-name (string-append name "-" version ".tar.gz")) | |
2089 | (sha256 | |
2090 | (base32 | |
2c5289b2 | 2091 | "0adp87r9ak63frdrdmrdfhsn6g0jnnyq1lr2wibvqbxcl37iir9m")))) |
122395f9 | 2092 | (build-system cmake-build-system) |
684bf7c7 | 2093 | (arguments |
7c544991 BW |
2094 | '(#:tests? #f ; no "check" target |
2095 | #:phases | |
2096 | (modify-phases %standard-phases | |
2097 | (add-after 'unpack 'remove-native-compilation | |
2098 | (lambda _ | |
2099 | (substitute* "CMakeLists.txt" (("-march=native") "")) | |
2100 | #t))))) | |
684bf7c7 | 2101 | (inputs |
122395f9 | 2102 | `(("zlib" ,zlib))) |
684bf7c7 BW |
2103 | (home-page "https://github.com/bbuchfink/diamond") |
2104 | (synopsis "Accelerated BLAST compatible local sequence aligner") | |
2105 | (description | |
2106 | "DIAMOND is a BLAST-compatible local aligner for mapping protein and | |
2107 | translated DNA query sequences against a protein reference database (BLASTP | |
2108 | and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short | |
2109 | reads at a typical sensitivity of 90-99% relative to BLAST depending on the | |
2110 | data and settings.") | |
ef81341f | 2111 | (license license:agpl3+))) |
684bf7c7 | 2112 | |
97b9da68 RW |
2113 | (define-public discrover |
2114 | (package | |
2115 | (name "discrover") | |
2116 | (version "1.6.0") | |
2117 | (source | |
2118 | (origin | |
2119 | (method url-fetch) | |
2120 | (uri (string-append "https://github.com/maaskola/discrover/archive/" | |
2121 | version ".tar.gz")) | |
2122 | (file-name (string-append name "-" version ".tar.gz")) | |
2123 | (sha256 | |
2124 | (base32 | |
2125 | "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k")))) | |
2126 | (build-system cmake-build-system) | |
fa702e1a RW |
2127 | (arguments |
2128 | `(#:tests? #f ; there are no tests | |
2129 | #:phases | |
2130 | (modify-phases %standard-phases | |
2131 | (add-after 'unpack 'add-missing-includes | |
2132 | (lambda _ | |
2133 | (substitute* "src/executioninformation.hpp" | |
2134 | (("#define EXECUTIONINFORMATION_HPP" line) | |
2135 | (string-append line "\n#include <random>"))) | |
2136 | (substitute* "src/plasma/fasta.hpp" | |
2137 | (("#define FASTA_HPP" line) | |
2138 | (string-append line "\n#include <random>"))) | |
2139 | #t))))) | |
97b9da68 RW |
2140 | (inputs |
2141 | `(("boost" ,boost) | |
2142 | ("cairo" ,cairo))) | |
2143 | (native-inputs | |
2144 | `(("texlive" ,texlive) | |
2145 | ("imagemagick" ,imagemagick))) | |
2146 | (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/") | |
2147 | (synopsis "Discover discriminative nucleotide sequence motifs") | |
2148 | (description "Discrover is a motif discovery method to find binding sites | |
2149 | of nucleic acid binding proteins.") | |
2150 | (license license:gpl3+))) | |
2151 | ||
6619f9c7 RW |
2152 | (define-public eigensoft |
2153 | (let ((revision "1") | |
2154 | (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7")) | |
2155 | (package | |
2156 | (name "eigensoft") | |
2157 | (version (string-append "6.1.2-" | |
2158 | revision "." | |
2159 | (string-take commit 9))) | |
2160 | (source | |
2161 | (origin | |
2162 | (method git-fetch) | |
2163 | (uri (git-reference | |
2164 | (url "https://github.com/DReichLab/EIG.git") | |
2165 | (commit commit))) | |
2166 | (file-name (string-append "eigensoft-" commit "-checkout")) | |
2167 | (sha256 | |
2168 | (base32 | |
2169 | "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq")) | |
2170 | (modules '((guix build utils))) | |
2171 | ;; Remove pre-built binaries. | |
2172 | (snippet '(begin | |
2173 | (delete-file-recursively "bin") | |
2174 | (mkdir "bin") | |
2175 | #t)))) | |
2176 | (build-system gnu-build-system) | |
2177 | (arguments | |
2178 | `(#:tests? #f ; There are no tests. | |
2179 | #:make-flags '("CC=gcc") | |
2180 | #:phases | |
2181 | (modify-phases %standard-phases | |
2182 | ;; There is no configure phase, but the Makefile is in a | |
2183 | ;; sub-directory. | |
2184 | (replace 'configure | |
2185 | (lambda _ | |
2186 | (chdir "src") | |
2187 | ;; The link flags are incomplete. | |
2188 | (substitute* "Makefile" | |
2189 | (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread")) | |
2190 | #t)) | |
2191 | ;; The provided install target only copies executables to | |
2192 | ;; the "bin" directory in the build root. | |
2193 | (add-after 'install 'actually-install | |
2194 | (lambda* (#:key outputs #:allow-other-keys) | |
2195 | (let* ((out (assoc-ref outputs "out")) | |
2196 | (bin (string-append out "/bin"))) | |
6619f9c7 RW |
2197 | (for-each (lambda (file) |
2198 | (install-file file bin)) | |
2199 | (find-files "../bin" ".*")) | |
2200 | #t)))))) | |
2201 | (inputs | |
2202 | `(("gsl" ,gsl) | |
2203 | ("lapack" ,lapack) | |
6619f9c7 RW |
2204 | ("openblas" ,openblas) |
2205 | ("perl" ,perl) | |
2206 | ("gfortran" ,gfortran "lib"))) | |
2207 | (home-page "https://github.com/DReichLab/EIG") | |
2208 | (synopsis "Tools for population genetics") | |
2209 | (description "The EIGENSOFT package provides tools for population | |
2210 | genetics and stratification correction. EIGENSOFT implements methods commonly | |
2211 | used in population genetics analyses such as PCA, computation of Tracy-Widom | |
2212 | statistics, and finding related individuals in structured populations. It | |
2213 | comes with a built-in plotting script and supports multiple file formats and | |
2214 | quantitative phenotypes.") | |
2215 | ;; The license of the eigensoft tools is Expat, but since it's | |
2216 | ;; linking with the GNU Scientific Library (GSL) the effective | |
2217 | ;; license is the GPL. | |
2218 | (license license:gpl3+)))) | |
2219 | ||
365c8153 RW |
2220 | (define-public edirect |
2221 | (package | |
2222 | (name "edirect") | |
83b84fa8 | 2223 | (version "4.10") |
365c8153 RW |
2224 | (source (origin |
2225 | (method url-fetch) | |
83b84fa8 RW |
2226 | (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/" |
2227 | "versions/2016-05-03/edirect.tar.gz")) | |
365c8153 RW |
2228 | (sha256 |
2229 | (base32 | |
83b84fa8 | 2230 | "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli")))) |
365c8153 RW |
2231 | (build-system perl-build-system) |
2232 | (arguments | |
2233 | `(#:tests? #f ;no "check" target | |
2234 | #:phases | |
2235 | (modify-phases %standard-phases | |
2236 | (delete 'configure) | |
2237 | (delete 'build) | |
2238 | (replace 'install | |
2239 | (lambda* (#:key outputs #:allow-other-keys) | |
2240 | (let ((target (string-append (assoc-ref outputs "out") | |
2241 | "/bin"))) | |
2242 | (mkdir-p target) | |
f3860753 | 2243 | (install-file "edirect.pl" target) |
365c8153 RW |
2244 | #t))) |
2245 | (add-after | |
2246 | 'install 'wrap-program | |
2247 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
2248 | ;; Make sure 'edirect.pl' finds all perl inputs at runtime. | |
2249 | (let* ((out (assoc-ref outputs "out")) | |
2250 | (path (getenv "PERL5LIB"))) | |
2251 | (wrap-program (string-append out "/bin/edirect.pl") | |
2252 | `("PERL5LIB" ":" prefix (,path))))))))) | |
2253 | (inputs | |
2254 | `(("perl-html-parser" ,perl-html-parser) | |
2255 | ("perl-encode-locale" ,perl-encode-locale) | |
2256 | ("perl-file-listing" ,perl-file-listing) | |
2257 | ("perl-html-tagset" ,perl-html-tagset) | |
2258 | ("perl-html-tree" ,perl-html-tree) | |
2259 | ("perl-http-cookies" ,perl-http-cookies) | |
2260 | ("perl-http-date" ,perl-http-date) | |
2261 | ("perl-http-message" ,perl-http-message) | |
2262 | ("perl-http-negotiate" ,perl-http-negotiate) | |
2263 | ("perl-lwp-mediatypes" ,perl-lwp-mediatypes) | |
2264 | ("perl-lwp-protocol-https" ,perl-lwp-protocol-https) | |
2265 | ("perl-net-http" ,perl-net-http) | |
2266 | ("perl-uri" ,perl-uri) | |
2267 | ("perl-www-robotrules" ,perl-www-robotrules) | |
2268 | ("perl" ,perl))) | |
3d51ec91 | 2269 | (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/") |
365c8153 RW |
2270 | (synopsis "Tools for accessing the NCBI's set of databases") |
2271 | (description | |
2272 | "Entrez Direct (EDirect) is a method for accessing the National Center | |
2273 | for Biotechnology Information's (NCBI) set of interconnected | |
2274 | databases (publication, sequence, structure, gene, variation, expression, | |
2275 | etc.) from a terminal. Functions take search terms from command-line | |
2276 | arguments. Individual operations are combined to build multi-step queries. | |
2277 | Record retrieval and formatting normally complete the process. | |
2278 | ||
2279 | EDirect also provides an argument-driven function that simplifies the | |
2280 | extraction of data from document summaries or other results that are returned | |
2281 | in structured XML format. This can eliminate the need for writing custom | |
2282 | software to answer ad hoc questions.") | |
2283 | (license license:public-domain))) | |
2284 | ||
b16728b0 BW |
2285 | (define-public exonerate |
2286 | (package | |
2287 | (name "exonerate") | |
2288 | (version "2.4.0") | |
2289 | (source | |
2290 | (origin | |
2291 | (method url-fetch) | |
2292 | (uri | |
2293 | (string-append | |
2294 | "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/" | |
2295 | "exonerate-" version ".tar.gz")) | |
2296 | (sha256 | |
2297 | (base32 | |
2298 | "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq")))) | |
2299 | (build-system gnu-build-system) | |
2300 | (arguments | |
2301 | `(#:parallel-build? #f)) ; Building in parallel fails on some machines. | |
2302 | (native-inputs | |
2303 | `(("pkg-config" ,pkg-config))) | |
2304 | (inputs | |
2305 | `(("glib" ,glib))) | |
2306 | (home-page | |
2307 | "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate") | |
2308 | (synopsis "Generic tool for biological sequence alignment") | |
2309 | (description | |
2310 | "Exonerate is a generic tool for pairwise sequence comparison. It allows | |
2311 | the alignment of sequences using a many alignment models, either exhaustive | |
2312 | dynamic programming or a variety of heuristics.") | |
2313 | (license license:gpl3))) | |
2314 | ||
e4e5a4d8 RW |
2315 | (define-public express |
2316 | (package | |
2317 | (name "express") | |
2318 | (version "1.5.1") | |
2319 | (source (origin | |
2320 | (method url-fetch) | |
2321 | (uri | |
2322 | (string-append | |
2323 | "http://bio.math.berkeley.edu/eXpress/downloads/express-" | |
2324 | version "/express-" version "-src.tgz")) | |
2325 | (sha256 | |
2326 | (base32 | |
2327 | "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c")))) | |
2328 | (build-system cmake-build-system) | |
2329 | (arguments | |
2330 | `(#:tests? #f ;no "check" target | |
2331 | #:phases | |
dc1d3cde KK |
2332 | (modify-phases %standard-phases |
2333 | (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths | |
2334 | (lambda* (#:key inputs #:allow-other-keys) | |
2335 | (substitute* "CMakeLists.txt" | |
2336 | (("set\\(Boost_USE_STATIC_LIBS ON\\)") | |
2337 | "set(Boost_USE_STATIC_LIBS OFF)") | |
2338 | (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include") | |
2339 | (string-append (assoc-ref inputs "bamtools") "/include/bamtools"))) | |
2340 | (substitute* "src/CMakeLists.txt" | |
2341 | (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib") | |
4b93efec RJ |
2342 | (string-append (assoc-ref inputs "bamtools") "/lib")) |
2343 | (("libprotobuf.a") "libprotobuf.so")) | |
dc1d3cde | 2344 | #t))))) |
e4e5a4d8 RW |
2345 | (inputs |
2346 | `(("boost" ,boost) | |
2347 | ("bamtools" ,bamtools) | |
2348 | ("protobuf" ,protobuf) | |
2349 | ("zlib" ,zlib))) | |
2350 | (home-page "http://bio.math.berkeley.edu/eXpress") | |
2351 | (synopsis "Streaming quantification for high-throughput genomic sequencing") | |
2352 | (description | |
2353 | "eXpress is a streaming tool for quantifying the abundances of a set of | |
2354 | target sequences from sampled subsequences. Example applications include | |
2355 | transcript-level RNA-Seq quantification, allele-specific/haplotype expression | |
2356 | analysis (from RNA-Seq), transcription factor binding quantification in | |
2357 | ChIP-Seq, and analysis of metagenomic data.") | |
2358 | (license license:artistic2.0))) | |
2359 | ||
f3674b1c BW |
2360 | (define-public express-beta-diversity |
2361 | (package | |
2362 | (name "express-beta-diversity") | |
2363 | (version "1.0.7") | |
2364 | (source (origin | |
2365 | (method url-fetch) | |
2366 | (uri | |
2367 | (string-append | |
2368 | "https://github.com/dparks1134/ExpressBetaDiversity/archive/v" | |
2369 | version ".tar.gz")) | |
2370 | (file-name (string-append name "-" version ".tar.gz")) | |
2371 | (sha256 | |
2372 | (base32 | |
2373 | "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr")))) | |
2374 | (build-system gnu-build-system) | |
2375 | (arguments | |
2376 | `(#:phases | |
2377 | (modify-phases %standard-phases | |
2378 | (delete 'configure) | |
2379 | (add-before 'build 'enter-source (lambda _ (chdir "source") #t)) | |
2380 | (replace 'check | |
2381 | (lambda _ (zero? (system* "../bin/ExpressBetaDiversity" | |
2382 | "-u")))) | |
2383 | (add-after 'check 'exit-source (lambda _ (chdir "..") #t)) | |
2384 | (replace 'install | |
2385 | (lambda* (#:key outputs #:allow-other-keys) | |
2386 | (let ((bin (string-append (assoc-ref outputs "out") | |
2387 | "/bin"))) | |
2388 | (mkdir-p bin) | |
f3860753 TGR |
2389 | (install-file "scripts/convertToEBD.py" bin) |
2390 | (install-file "bin/ExpressBetaDiversity" bin) | |
f3674b1c BW |
2391 | #t)))))) |
2392 | (inputs | |
2393 | `(("python" ,python-2))) | |
2394 | (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity") | |
2395 | (synopsis "Taxon- and phylogenetic-based beta diversity measures") | |
2396 | (description | |
2397 | "Express Beta Diversity (EBD) calculates ecological beta diversity | |
2398 | (dissimilarity) measures between biological communities. EBD implements a | |
2399 | variety of diversity measures including those that make use of phylogenetic | |
2400 | similarity of community members.") | |
2401 | (license license:gpl3+))) | |
2402 | ||
12b04cbe BW |
2403 | (define-public fasttree |
2404 | (package | |
2405 | (name "fasttree") | |
88682c9a | 2406 | (version "2.1.10") |
12b04cbe BW |
2407 | (source (origin |
2408 | (method url-fetch) | |
2409 | (uri (string-append | |
2410 | "http://www.microbesonline.org/fasttree/FastTree-" | |
2411 | version ".c")) | |
2412 | (sha256 | |
2413 | (base32 | |
88682c9a | 2414 | "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl")))) |
12b04cbe BW |
2415 | (build-system gnu-build-system) |
2416 | (arguments | |
2417 | `(#:tests? #f ; no "check" target | |
2418 | #:phases | |
2419 | (modify-phases %standard-phases | |
2420 | (delete 'unpack) | |
2421 | (delete 'configure) | |
2422 | (replace 'build | |
e03a5153 BW |
2423 | (lambda* (#:key source #:allow-other-keys) |
2424 | (and (zero? (system* "gcc" | |
2425 | "-O3" | |
2426 | "-finline-functions" | |
2427 | "-funroll-loops" | |
2428 | "-Wall" | |
2429 | "-o" | |
2430 | "FastTree" | |
2431 | source | |
2432 | "-lm")) | |
2433 | (zero? (system* "gcc" | |
2434 | "-DOPENMP" | |
2435 | "-fopenmp" | |
2436 | "-O3" | |
2437 | "-finline-functions" | |
2438 | "-funroll-loops" | |
2439 | "-Wall" | |
2440 | "-o" | |
2441 | "FastTreeMP" | |
2442 | source | |
2443 | "-lm"))))) | |
12b04cbe | 2444 | (replace 'install |
e03a5153 BW |
2445 | (lambda* (#:key outputs #:allow-other-keys) |
2446 | (let ((bin (string-append (assoc-ref outputs "out") | |
2447 | "/bin"))) | |
2448 | (mkdir-p bin) | |
f3860753 TGR |
2449 | (install-file "FastTree" bin) |
2450 | (install-file "FastTreeMP" bin) | |
e03a5153 | 2451 | #t)))))) |
12b04cbe BW |
2452 | (home-page "http://www.microbesonline.org/fasttree") |
2453 | (synopsis "Infers approximately-maximum-likelihood phylogenetic trees") | |
2454 | (description | |
2455 | "FastTree can handle alignments with up to a million of sequences in a | |
2456 | reasonable amount of time and memory. For large alignments, FastTree is | |
2457 | 100-1,000 times faster than PhyML 3.0 or RAxML 7.") | |
2458 | (license license:gpl2+))) | |
2459 | ||
2127cedb RW |
2460 | (define-public fastx-toolkit |
2461 | (package | |
2462 | (name "fastx-toolkit") | |
2463 | (version "0.0.14") | |
2464 | (source (origin | |
2465 | (method url-fetch) | |
2466 | (uri | |
2467 | (string-append | |
2468 | "https://github.com/agordon/fastx_toolkit/releases/download/" | |
2469 | version "/fastx_toolkit-" version ".tar.bz2")) | |
2470 | (sha256 | |
2471 | (base32 | |
2472 | "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy")))) | |
2473 | (build-system gnu-build-system) | |
2474 | (inputs | |
2475 | `(("libgtextutils" ,libgtextutils))) | |
2476 | (native-inputs | |
2477 | `(("pkg-config" ,pkg-config))) | |
2478 | (home-page "http://hannonlab.cshl.edu/fastx_toolkit/") | |
2479 | (synopsis "Tools for FASTA/FASTQ file preprocessing") | |
2480 | (description | |
2481 | "The FASTX-Toolkit is a collection of command line tools for Short-Reads | |
2482 | FASTA/FASTQ files preprocessing. | |
2483 | ||
2484 | Next-Generation sequencing machines usually produce FASTA or FASTQ files, | |
2485 | containing multiple short-reads sequences. The main processing of such | |
2486 | FASTA/FASTQ files is mapping the sequences to reference genomes. However, it | |
2487 | is sometimes more productive to preprocess the files before mapping the | |
2488 | sequences to the genome---manipulating the sequences to produce better mapping | |
2489 | results. The FASTX-Toolkit tools perform some of these preprocessing tasks.") | |
2490 | (license license:agpl3+))) | |
2491 | ||
d7678942 RW |
2492 | (define-public flexbar |
2493 | (package | |
2494 | (name "flexbar") | |
2495 | (version "2.5") | |
2496 | (source (origin | |
2497 | (method url-fetch) | |
2498 | (uri | |
2499 | (string-append "mirror://sourceforge/flexbar/" | |
2500 | version "/flexbar_v" version "_src.tgz")) | |
2501 | (sha256 | |
2502 | (base32 | |
2503 | "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf")))) | |
2504 | (build-system cmake-build-system) | |
2505 | (arguments | |
4ca009c0 | 2506 | `(#:configure-flags (list |
d7678942 RW |
2507 | (string-append "-DFLEXBAR_BINARY_DIR=" |
2508 | (assoc-ref %outputs "out") | |
2509 | "/bin/")) | |
2510 | #:phases | |
dc1d3cde KK |
2511 | (modify-phases %standard-phases |
2512 | (replace 'check | |
2513 | (lambda* (#:key outputs #:allow-other-keys) | |
2514 | (setenv "PATH" (string-append | |
2515 | (assoc-ref outputs "out") "/bin:" | |
2516 | (getenv "PATH"))) | |
2517 | (chdir "../flexbar_v2.5_src/test") | |
2518 | (zero? (system* "bash" "flexbar_validate.sh")))) | |
2519 | (delete 'install)))) | |
d7678942 RW |
2520 | (inputs |
2521 | `(("tbb" ,tbb) | |
2522 | ("zlib" ,zlib))) | |
2523 | (native-inputs | |
2524 | `(("pkg-config" ,pkg-config) | |
2525 | ("seqan" ,seqan))) | |
2526 | (home-page "http://flexbar.sourceforge.net") | |
2527 | (synopsis "Barcode and adapter removal tool for sequencing platforms") | |
2528 | (description | |
2529 | "Flexbar preprocesses high-throughput nucleotide sequencing data | |
2530 | efficiently. It demultiplexes barcoded runs and removes adapter sequences. | |
2531 | Moreover, trimming and filtering features are provided. Flexbar increases | |
2532 | read mapping rates and improves genome and transcriptome assemblies. It | |
2533 | supports next-generation sequencing data in fasta/q and csfasta/q format from | |
2534 | Illumina, Roche 454, and the SOLiD platform.") | |
2535 | (license license:gpl3))) | |
2536 | ||
19f4554c BW |
2537 | (define-public fraggenescan |
2538 | (package | |
2539 | (name "fraggenescan") | |
74297231 | 2540 | (version "1.30") |
19f4554c BW |
2541 | (source |
2542 | (origin | |
2543 | (method url-fetch) | |
2544 | (uri | |
2545 | (string-append "mirror://sourceforge/fraggenescan/" | |
2546 | "FragGeneScan" version ".tar.gz")) | |
2547 | (sha256 | |
74297231 | 2548 | (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj")))) |
19f4554c BW |
2549 | (build-system gnu-build-system) |
2550 | (arguments | |
2551 | `(#:phases | |
2552 | (modify-phases %standard-phases | |
2553 | (delete 'configure) | |
2554 | (add-before 'build 'patch-paths | |
2555 | (lambda* (#:key outputs #:allow-other-keys) | |
2556 | (let* ((out (string-append (assoc-ref outputs "out"))) | |
2557 | (share (string-append out "/share/fraggenescan/"))) | |
2558 | (substitute* "run_FragGeneScan.pl" | |
2559 | (("system\\(\"rm") | |
2560 | (string-append "system(\"" (which "rm"))) | |
2561 | (("system\\(\"mv") | |
2562 | (string-append "system(\"" (which "mv"))) | |
74297231 | 2563 | (("\\\"awk") (string-append "\"" (which "awk"))) |
19f4554c BW |
2564 | ;; This script and other programs expect the training files |
2565 | ;; to be in the non-standard location bin/train/XXX. Change | |
2566 | ;; this to be share/fraggenescan/train/XXX instead. | |
2567 | (("^\\$train.file = \\$dir.*") | |
2568 | (string-append "$train_file = \"" | |
2569 | share | |
2570 | "train/\".$FGS_train_file;"))) | |
2571 | (substitute* "run_hmm.c" | |
2572 | (("^ strcat\\(train_dir, \\\"train/\\\"\\);") | |
74297231 | 2573 | (string-append " strcpy(train_dir, \"" share "/train/\");")))) |
19f4554c BW |
2574 | #t)) |
2575 | (replace 'build | |
2576 | (lambda _ (and (zero? (system* "make" "clean")) | |
2577 | (zero? (system* "make" "fgs"))))) | |
2578 | (replace 'install | |
2579 | (lambda* (#:key outputs #:allow-other-keys) | |
2580 | (let* ((out (string-append (assoc-ref outputs "out"))) | |
2581 | (bin (string-append out "/bin/")) | |
2582 | (share (string-append out "/share/fraggenescan/train"))) | |
2583 | (install-file "run_FragGeneScan.pl" bin) | |
2584 | (install-file "FragGeneScan" bin) | |
19f4554c BW |
2585 | (copy-recursively "train" share)))) |
2586 | (delete 'check) | |
2587 | (add-after 'install 'post-install-check | |
2588 | ;; In lieu of 'make check', run one of the examples and check the | |
2589 | ;; output files gets created. | |
2590 | (lambda* (#:key outputs #:allow-other-keys) | |
2591 | (let* ((out (string-append (assoc-ref outputs "out"))) | |
74297231 BW |
2592 | (bin (string-append out "/bin/")) |
2593 | (frag (string-append bin "run_FragGeneScan.pl"))) | |
2594 | (and (zero? (system* frag ; Test complete genome. | |
19f4554c BW |
2595 | "-genome=./example/NC_000913.fna" |
2596 | "-out=./test2" | |
2597 | "-complete=1" | |
2598 | "-train=complete")) | |
2599 | (file-exists? "test2.faa") | |
2600 | (file-exists? "test2.ffn") | |
2601 | (file-exists? "test2.gff") | |
74297231 BW |
2602 | (file-exists? "test2.out") |
2603 | (zero? (system* ; Test incomplete sequences. | |
2604 | frag | |
2605 | "-genome=./example/NC_000913-fgs.ffn" | |
2606 | "-out=out" | |
2607 | "-complete=0" | |
2608 | "-train=454_30"))))))))) | |
19f4554c BW |
2609 | (inputs |
2610 | `(("perl" ,perl) | |
2611 | ("python" ,python-2))) ;not compatible with python 3. | |
2612 | (home-page "https://sourceforge.net/projects/fraggenescan/") | |
2613 | (synopsis "Finds potentially fragmented genes in short reads") | |
2614 | (description | |
2615 | "FragGeneScan is a program for predicting bacterial and archaeal genes in | |
2616 | short and error-prone DNA sequencing reads. It can also be applied to predict | |
2617 | genes in incomplete assemblies or complete genomes.") | |
2618 | ;; GPL3+ according to private correspondense with the authors. | |
2619 | (license license:gpl3+))) | |
2620 | ||
81f3e0c1 BW |
2621 | (define-public fxtract |
2622 | (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115")) | |
2623 | (package | |
2624 | (name "fxtract") | |
2625 | (version "2.3") | |
2626 | (source | |
2627 | (origin | |
2628 | (method url-fetch) | |
2629 | (uri (string-append | |
2630 | "https://github.com/ctSkennerton/fxtract/archive/" | |
2631 | version ".tar.gz")) | |
2632 | (file-name (string-append "ctstennerton-util-" | |
2633 | (string-take util-commit 7) | |
2634 | "-checkout")) | |
2635 | (sha256 | |
2636 | (base32 | |
2637 | "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj")))) | |
2638 | (build-system gnu-build-system) | |
2639 | (arguments | |
2640 | `(#:make-flags (list | |
2641 | (string-append "PREFIX=" (assoc-ref %outputs "out")) | |
2642 | "CC=gcc") | |
2643 | #:test-target "fxtract_test" | |
2644 | #:phases | |
2645 | (modify-phases %standard-phases | |
2646 | (delete 'configure) | |
2647 | (add-before 'build 'copy-util | |
2648 | (lambda* (#:key inputs #:allow-other-keys) | |
2649 | (rmdir "util") | |
2650 | (copy-recursively (assoc-ref inputs "ctskennerton-util") "util") | |
2651 | #t)) | |
2652 | ;; Do not use make install as this requires additional dependencies. | |
2653 | (replace 'install | |
2654 | (lambda* (#:key outputs #:allow-other-keys) | |
2655 | (let* ((out (assoc-ref outputs "out")) | |
2656 | (bin (string-append out"/bin"))) | |
2657 | (install-file "fxtract" bin) | |
2658 | #t)))))) | |
2659 | (inputs | |
2660 | `(("pcre" ,pcre) | |
2661 | ("zlib" ,zlib))) | |
2662 | (native-inputs | |
2663 | ;; ctskennerton-util is licensed under GPL2. | |
2664 | `(("ctskennerton-util" | |
2665 | ,(origin | |
2666 | (method git-fetch) | |
2667 | (uri (git-reference | |
2668 | (url "https://github.com/ctSkennerton/util.git") | |
2669 | (commit util-commit))) | |
2670 | (file-name (string-append | |
2671 | "ctstennerton-util-" util-commit "-checkout")) | |
2672 | (sha256 | |
2673 | (base32 | |
2674 | "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7")))))) | |
2675 | (home-page "https://github.com/ctSkennerton/fxtract") | |
2676 | (synopsis "Extract sequences from FASTA and FASTQ files") | |
2677 | (description | |
2678 | "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA | |
2679 | or FASTQ) file given a subsequence. It uses a simple substring search for | |
2680 | basic tasks but can change to using POSIX regular expressions, PCRE, hash | |
2681 | lookups or multi-pattern searching as required. By default fxtract looks in | |
2682 | the sequence of each record but can also be told to look in the header, | |
2683 | comment or quality sections.") | |
afde1a26 BW |
2684 | ;; 'util' requires SSE instructions. |
2685 | (supported-systems '("x86_64-linux")) | |
81f3e0c1 BW |
2686 | (license license:expat)))) |
2687 | ||
2b18ad05 PP |
2688 | (define-public gemma |
2689 | (package | |
2690 | (name "gemma") | |
2691 | (version "0.96") | |
2692 | (source (origin | |
2693 | (method url-fetch) | |
2694 | (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v" | |
2695 | version ".tar.gz")) | |
2696 | (file-name (string-append name "-" version ".tar.gz")) | |
2697 | (sha256 | |
2698 | (base32 | |
ce7e361f EF |
2699 | "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222")) |
2700 | (patches (search-patches "gemma-intel-compat.patch")))) | |
2b18ad05 PP |
2701 | (inputs |
2702 | `(("gsl" ,gsl) | |
2703 | ("lapack" ,lapack) | |
2704 | ("zlib" ,zlib))) | |
2705 | (build-system gnu-build-system) | |
2706 | (arguments | |
2c9232ae | 2707 | `(#:make-flags |
ce7e361f EF |
2708 | '(,@(match (%current-system) |
2709 | ("x86_64-linux" | |
2710 | '("FORCE_DYNAMIC=1")) | |
2711 | ("i686-linux" | |
2712 | '("FORCE_DYNAMIC=1" "FORCE_32BIT=1")) | |
2713 | (_ | |
2714 | '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1")))) | |
2b18ad05 PP |
2715 | #:phases |
2716 | (modify-phases %standard-phases | |
2717 | (delete 'configure) | |
2718 | (add-before 'build 'bin-mkdir | |
07bf6929 EF |
2719 | (lambda _ |
2720 | (mkdir-p "bin") | |
2721 | #t)) | |
2b18ad05 | 2722 | (replace 'install |
07bf6929 EF |
2723 | (lambda* (#:key outputs #:allow-other-keys) |
2724 | (let ((out (assoc-ref outputs "out"))) | |
2725 | (install-file "bin/gemma" | |
2726 | (string-append | |
2727 | out "/bin"))) | |
2728 | #t))) | |
2b18ad05 PP |
2729 | #:tests? #f)) ; no tests included yet |
2730 | (home-page "https://github.com/xiangzhou/GEMMA") | |
2731 | (synopsis "Tool for genome-wide efficient mixed model association") | |
2732 | (description | |
2733 | "Genome-wide Efficient Mixed Model Association (GEMMA) provides a | |
2734 | standard linear mixed model resolver with application in genome-wide | |
2735 | association studies (GWAS).") | |
2736 | (license license:gpl3))) | |
2737 | ||
5854f685 RW |
2738 | (define-public grit |
2739 | (package | |
2740 | (name "grit") | |
2741 | (version "2.0.2") | |
2742 | (source (origin | |
2743 | (method url-fetch) | |
2744 | (uri (string-append | |
2745 | "https://github.com/nboley/grit/archive/" | |
2746 | version ".tar.gz")) | |
2747 | (file-name (string-append name "-" version ".tar.gz")) | |
2748 | (sha256 | |
2749 | (base32 | |
2750 | "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj")))) | |
2751 | (build-system python-build-system) | |
2752 | (arguments | |
2753 | `(#:python ,python-2 | |
2754 | #:phases | |
dc1d3cde KK |
2755 | (modify-phases %standard-phases |
2756 | (add-after 'unpack 'generate-from-cython-sources | |
2757 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
2758 | ;; Delete these C files to force fresh generation from pyx sources. | |
2759 | (delete-file "grit/sparsify_support_fns.c") | |
2760 | (delete-file "grit/call_peaks_support_fns.c") | |
2761 | (substitute* "setup.py" | |
2762 | (("Cython.Setup") "Cython.Build") | |
2763 | ;; Add numpy include path to fix compilation | |
2764 | (("pyx\", \\]") | |
2765 | (string-append "pyx\", ], include_dirs = ['" | |
2766 | (assoc-ref inputs "python-numpy") | |
2767 | "/lib/python2.7/site-packages/numpy/core/include/" | |
2768 | "']"))) | |
2769 | #t))))) | |
5854f685 RW |
2770 | (inputs |
2771 | `(("python-scipy" ,python2-scipy) | |
2772 | ("python-numpy" ,python2-numpy) | |
2773 | ("python-pysam" ,python2-pysam) | |
2774 | ("python-networkx" ,python2-networkx))) | |
2775 | (native-inputs | |
f3b98f4f | 2776 | `(("python-cython" ,python2-cython))) |
5854f685 RW |
2777 | (home-page "http://grit-bio.org") |
2778 | (synopsis "Tool for integrative analysis of RNA-seq type assays") | |
2779 | (description | |
2780 | "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify | |
2781 | full length transcript models. When none of these data sources are available, | |
2782 | GRIT can be run by providing a candidate set of TES or TSS sites. In | |
2783 | addition, GRIT can merge in reference junctions and gene boundaries. GRIT can | |
2784 | also be run in quantification mode, where it uses a provided GTF file and just | |
2785 | estimates transcript expression.") | |
2786 | (license license:gpl3+))) | |
2787 | ||
346a829a RW |
2788 | (define-public hisat |
2789 | (package | |
2790 | (name "hisat") | |
2791 | (version "0.1.4") | |
2792 | (source (origin | |
2793 | (method url-fetch) | |
2794 | (uri (string-append | |
2795 | "http://ccb.jhu.edu/software/hisat/downloads/hisat-" | |
2796 | version "-beta-source.zip")) | |
2797 | (sha256 | |
2798 | (base32 | |
2799 | "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5")))) | |
2800 | (build-system gnu-build-system) | |
2801 | (arguments | |
e58d01fa RW |
2802 | `(#:tests? #f ;no check target |
2803 | #:make-flags '("allall" | |
2804 | ;; Disable unsupported `popcnt' instructions on | |
2805 | ;; architectures other than x86_64 | |
2806 | ,@(if (string-prefix? "x86_64" | |
2807 | (or (%current-target-system) | |
2808 | (%current-system))) | |
2809 | '() | |
2810 | '("POPCNT_CAPABILITY=0"))) | |
346a829a | 2811 | #:phases |
dc1d3cde KK |
2812 | (modify-phases %standard-phases |
2813 | (add-after 'unpack 'patch-sources | |
2814 | (lambda _ | |
2815 | ;; XXX Cannot use snippet because zip files are not supported | |
2816 | (substitute* "Makefile" | |
2817 | (("^CC = .*$") "CC = gcc") | |
2818 | (("^CPP = .*$") "CPP = g++") | |
2819 | ;; replace BUILD_HOST and BUILD_TIME for deterministic build | |
2820 | (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"") | |
2821 | (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")) | |
2822 | (substitute* '("hisat-build" "hisat-inspect") | |
2823 | (("/usr/bin/env") (which "env"))) | |
2824 | #t)) | |
2825 | (replace 'install | |
2826 | (lambda* (#:key outputs #:allow-other-keys) | |
2827 | (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) | |
2828 | (for-each (lambda (file) | |
2829 | (install-file file bin)) | |
2830 | (find-files | |
2831 | "." | |
2832 | "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))) | |
2833 | #t)) | |
2834 | (delete 'configure)))) | |
346a829a RW |
2835 | (native-inputs |
2836 | `(("unzip" ,unzip))) | |
2837 | (inputs | |
2838 | `(("perl" ,perl) | |
2839 | ("python" ,python) | |
2840 | ("zlib" ,zlib))) | |
60af3d82 RW |
2841 | ;; Non-portable SSE instructions are used so building fails on platforms |
2842 | ;; other than x86_64. | |
2843 | (supported-systems '("x86_64-linux")) | |
346a829a RW |
2844 | (home-page "http://ccb.jhu.edu/software/hisat/index.shtml") |
2845 | (synopsis "Hierarchical indexing for spliced alignment of transcripts") | |
2846 | (description | |
2847 | "HISAT is a fast and sensitive spliced alignment program for mapping | |
2848 | RNA-seq reads. In addition to one global FM index that represents a whole | |
2849 | genome, HISAT uses a large set of small FM indexes that collectively cover the | |
2850 | whole genome. These small indexes (called local indexes) combined with | |
2851 | several alignment strategies enable effective alignment of RNA-seq reads, in | |
2852 | particular, reads spanning multiple exons.") | |
2853 | (license license:gpl3+))) | |
2854 | ||
e84efc50 RW |
2855 | (define-public hisat2 |
2856 | (package | |
2857 | (name "hisat2") | |
2858 | (version "2.0.5") | |
2859 | (source | |
2860 | (origin | |
2861 | (method url-fetch) | |
2862 | ;; FIXME: a better source URL is | |
2863 | ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2" | |
2864 | ;; "/downloads/hisat2-" version "-source.zip") | |
2865 | ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g" | |
2866 | ;; but it is currently unavailable. | |
2867 | (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz") | |
2868 | (file-name (string-append name "-" version ".tar.gz")) | |
2869 | (sha256 | |
2870 | (base32 | |
2871 | "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50")))) | |
2872 | (build-system gnu-build-system) | |
2873 | (arguments | |
2874 | `(#:tests? #f ; no check target | |
2875 | #:make-flags (list "CC=gcc" "CXX=g++" "allall") | |
2876 | #:modules ((guix build gnu-build-system) | |
2877 | (guix build utils) | |
2878 | (srfi srfi-26)) | |
2879 | #:phases | |
2880 | (modify-phases %standard-phases | |
2881 | (add-after 'unpack 'make-deterministic | |
2882 | (lambda _ | |
2883 | (substitute* "Makefile" | |
2884 | (("`date`") "0")) | |
2885 | #t)) | |
2886 | (delete 'configure) | |
2887 | (replace 'install | |
2888 | (lambda* (#:key outputs #:allow-other-keys) | |
2889 | (let* ((out (assoc-ref outputs "out")) | |
2890 | (bin (string-append out "/bin/")) | |
2891 | (doc (string-append out "/share/doc/hisat2/"))) | |
2892 | (for-each | |
2893 | (cut install-file <> bin) | |
2894 | (find-files "." | |
2895 | "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")) | |
2896 | (mkdir-p doc) | |
2897 | (install-file "doc/manual.inc.html" doc)) | |
2898 | #t))))) | |
2899 | (native-inputs | |
2900 | `(("unzip" ,unzip) ; needed for archive from ftp | |
2901 | ("perl" ,perl) | |
2902 | ("pandoc" ,ghc-pandoc))) ; for documentation | |
2903 | (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml") | |
2904 | (synopsis "Graph-based alignment of genomic sequencing reads") | |
2905 | (description "HISAT2 is a fast and sensitive alignment program for mapping | |
2906 | next-generation sequencing reads (both DNA and RNA) to a population of human | |
2907 | genomes (as well as to a single reference genome). In addition to using one | |
2908 | global @dfn{graph FM} (GFM) index that represents a population of human | |
2909 | genomes, HISAT2 uses a large set of small GFM indexes that collectively cover | |
2910 | the whole genome. These small indexes, combined with several alignment | |
2911 | strategies, enable rapid and accurate alignment of sequencing reads. This new | |
2912 | indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).") | |
2913 | ;; HISAT2 contains files from Bowtie2, which is released under | |
2914 | ;; GPLv2 or later. The HISAT2 source files are released under | |
2915 | ;; GPLv3 or later. | |
2916 | (license license:gpl3+))) | |
2917 | ||
c684629f BW |
2918 | (define-public hmmer |
2919 | (package | |
2920 | (name "hmmer") | |
2921 | (version "3.1b2") | |
79f09fa2 BW |
2922 | (source |
2923 | (origin | |
2924 | (method url-fetch) | |
2925 | (uri (string-append | |
2926 | "http://eddylab.org/software/hmmer" | |
9cf5f134 | 2927 | (version-major version) "/" |
79f09fa2 BW |
2928 | version "/hmmer-" version ".tar.gz")) |
2929 | (sha256 | |
2930 | (base32 | |
2931 | "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx")) | |
2932 | (patches (search-patches "hmmer-remove-cpu-specificity.patch")))) | |
c684629f | 2933 | (build-system gnu-build-system) |
b3546174 | 2934 | (native-inputs `(("perl" ,perl))) |
a83e6046 | 2935 | (home-page "http://hmmer.org/") |
c684629f BW |
2936 | (synopsis "Biosequence analysis using profile hidden Markov models") |
2937 | (description | |
2938 | "HMMER is used for searching sequence databases for homologs of protein | |
2939 | sequences, and for making protein sequence alignments. It implements methods | |
2940 | using probabilistic models called profile hidden Markov models (profile | |
2941 | HMMs).") | |
2942 | (license (list license:gpl3+ | |
2943 | ;; The bundled library 'easel' is distributed | |
2944 | ;; under The Janelia Farm Software License. | |
2945 | (license:non-copyleft | |
2946 | "file://easel/LICENSE" | |
2947 | "See easel/LICENSE in the distribution."))))) | |
2948 | ||
85652f59 RW |
2949 | (define-public htseq |
2950 | (package | |
2951 | (name "htseq") | |
92971d68 | 2952 | (version "0.9.1") |
85652f59 RW |
2953 | (source (origin |
2954 | (method url-fetch) | |
75e6639f | 2955 | (uri (pypi-uri "HTSeq" version)) |
85652f59 RW |
2956 | (sha256 |
2957 | (base32 | |
92971d68 | 2958 | "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg")))) |
85652f59 | 2959 | (build-system python-build-system) |
92971d68 BW |
2960 | (native-inputs |
2961 | `(("python-cython" ,python-cython))) | |
0536727e RW |
2962 | ;; Numpy needs to be propagated when htseq is used as a Python library. |
2963 | (propagated-inputs | |
92971d68 | 2964 | `(("python-numpy" ,python-numpy))) |
578b05d9 | 2965 | (inputs |
92971d68 BW |
2966 | `(("python-pysam" ,python-pysam) |
2967 | ("python-matplotlib" ,python-matplotlib))) | |
85652f59 RW |
2968 | (home-page "http://www-huber.embl.de/users/anders/HTSeq/") |
2969 | (synopsis "Analysing high-throughput sequencing data with Python") | |
2970 | (description | |
2971 | "HTSeq is a Python package that provides infrastructure to process data | |
2972 | from high-throughput sequencing assays.") | |
2973 | (license license:gpl3+))) | |
2974 | ||
92971d68 BW |
2975 | (define-public python2-htseq |
2976 | (package-with-python2 htseq)) | |
2977 | ||
1ad15c16 | 2978 | (define-public java-htsjdk |
15a3c3d4 | 2979 | (package |
1ad15c16 | 2980 | (name "java-htsjdk") |
bd94b6f8 | 2981 | (version "2.3.0") ; last version without build dependency on gradle |
15a3c3d4 RW |
2982 | (source (origin |
2983 | (method url-fetch) | |
2984 | (uri (string-append | |
2985 | "https://github.com/samtools/htsjdk/archive/" | |
2986 | version ".tar.gz")) | |
2987 | (file-name (string-append name "-" version ".tar.gz")) | |
2988 | (sha256 | |
2989 | (base32 | |
bd94b6f8 | 2990 | "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq")) |
15a3c3d4 | 2991 | (modules '((guix build utils))) |
bd94b6f8 RW |
2992 | (snippet |
2993 | ;; Delete pre-built binaries | |
2994 | '(begin | |
2995 | (delete-file-recursively "lib") | |
2996 | (mkdir-p "lib") | |
2997 | #t)))) | |
10b4a969 | 2998 | (build-system ant-build-system) |
15a3c3d4 | 2999 | (arguments |
10b4a969 | 3000 | `(#:tests? #f ; test require Internet access |
bd94b6f8 | 3001 | #:jdk ,icedtea-8 |
10b4a969 RW |
3002 | #:make-flags |
3003 | (list (string-append "-Ddist=" (assoc-ref %outputs "out") | |
3004 | "/share/java/htsjdk/")) | |
3005 | #:build-target "all" | |
3006 | #:phases | |
3007 | (modify-phases %standard-phases | |
3008 | ;; The build phase also installs the jars | |
3009 | (delete 'install)))) | |
bd94b6f8 RW |
3010 | (inputs |
3011 | `(("java-ngs" ,java-ngs) | |
3012 | ("java-snappy-1" ,java-snappy-1) | |
3013 | ("java-commons-compress" ,java-commons-compress) | |
3014 | ("java-commons-logging-minimal" ,java-commons-logging-minimal) | |
3015 | ("java-commons-jexl-2" ,java-commons-jexl-2) | |
3016 | ("java-xz" ,java-xz))) | |
3017 | (native-inputs | |
3018 | `(("java-testng" ,java-testng))) | |
15a3c3d4 | 3019 | (home-page "http://samtools.github.io/htsjdk/") |
9a599c17 RW |
3020 | (synopsis "Java API for high-throughput sequencing data (HTS) formats") |
3021 | (description | |
3022 | "HTSJDK is an implementation of a unified Java library for accessing | |
3023 | common file formats, such as SAM and VCF, used for high-throughput | |
3024 | sequencing (HTS) data. There are also an number of useful utilities for | |
3025 | manipulating HTS data.") | |
3026 | (license license:expat))) | |
3027 | ||
3028 | (define-public java-htsjdk-latest | |
3029 | (package | |
3030 | (name "java-htsjdk") | |
3031 | (version "2.14.3") | |
3032 | (source (origin | |
3033 | (method git-fetch) | |
3034 | (uri (git-reference | |
3035 | (url "https://github.com/samtools/htsjdk.git") | |
3036 | (commit version))) | |
3037 | (file-name (string-append name "-" version "-checkout")) | |
3038 | (sha256 | |
3039 | (base32 | |
3040 | "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc")))) | |
3041 | (build-system ant-build-system) | |
3042 | (arguments | |
3043 | `(#:tests? #f ; test require Scala | |
3044 | #:jdk ,icedtea-8 | |
3045 | #:jar-name "htsjdk.jar" | |
3046 | #:phases | |
3047 | (modify-phases %standard-phases | |
3048 | (add-after 'unpack 'remove-useless-build.xml | |
3049 | (lambda _ (delete-file "build.xml") #t)) | |
3050 | ;; The tests require the scalatest package. | |
3051 | (add-after 'unpack 'remove-tests | |
3052 | (lambda _ (delete-file-recursively "src/test") #t))))) | |
3053 | (inputs | |
3054 | `(("java-ngs" ,java-ngs) | |
3055 | ("java-snappy-1" ,java-snappy-1) | |
3056 | ("java-commons-compress" ,java-commons-compress) | |
3057 | ("java-commons-logging-minimal" ,java-commons-logging-minimal) | |
3058 | ("java-commons-jexl-2" ,java-commons-jexl-2) | |
3059 | ("java-xz" ,java-xz))) | |
3060 | (native-inputs | |
3061 | `(("java-junit" ,java-junit))) | |
3062 | (home-page "http://samtools.github.io/htsjdk/") | |
15a3c3d4 RW |
3063 | (synopsis "Java API for high-throughput sequencing data (HTS) formats") |
3064 | (description | |
3065 | "HTSJDK is an implementation of a unified Java library for accessing | |
3066 | common file formats, such as SAM and VCF, used for high-throughput | |
3067 | sequencing (HTS) data. There are also an number of useful utilities for | |
3068 | manipulating HTS data.") | |
3069 | (license license:expat))) | |
3070 | ||
719fa958 RW |
3071 | ;; This is needed for picard 2.10.3 |
3072 | (define-public java-htsjdk-2.10.1 | |
3073 | (package (inherit java-htsjdk-latest) | |
3074 | (name "java-htsjdk") | |
3075 | (version "2.10.1") | |
3076 | (source (origin | |
3077 | (method git-fetch) | |
3078 | (uri (git-reference | |
3079 | (url "https://github.com/samtools/htsjdk.git") | |
3080 | (commit version))) | |
3081 | (file-name (string-append name "-" version "-checkout")) | |
3082 | (sha256 | |
3083 | (base32 | |
3084 | "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2")))) | |
3085 | (build-system ant-build-system) | |
3086 | (arguments | |
3087 | `(#:tests? #f ; tests require Scala | |
3088 | #:jdk ,icedtea-8 | |
3089 | #:jar-name "htsjdk.jar" | |
3090 | #:phases | |
3091 | (modify-phases %standard-phases | |
3092 | (add-after 'unpack 'remove-useless-build.xml | |
3093 | (lambda _ (delete-file "build.xml") #t)) | |
3094 | ;; The tests require the scalatest package. | |
3095 | (add-after 'unpack 'remove-tests | |
3096 | (lambda _ (delete-file-recursively "src/test") #t))))))) | |
3097 | ||
d7fed31a RW |
3098 | ;; This version matches java-htsjdk 2.3.0. Later versions also require a more |
3099 | ;; recent version of java-htsjdk, which depends on gradle. | |
3100 | (define-public java-picard | |
3101 | (package | |
3102 | (name "java-picard") | |
3103 | (version "2.3.0") | |
3104 | (source (origin | |
3105 | (method git-fetch) | |
3106 | (uri (git-reference | |
3107 | (url "https://github.com/broadinstitute/picard.git") | |
3108 | (commit version))) | |
3109 | (file-name (string-append "java-picard-" version "-checkout")) | |
3110 | (sha256 | |
3111 | (base32 | |
3112 | "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6")) | |
3113 | (modules '((guix build utils))) | |
3114 | (snippet | |
3115 | '(begin | |
3116 | ;; Delete pre-built binaries. | |
3117 | (delete-file-recursively "lib") | |
3118 | (mkdir-p "lib") | |
3119 | (substitute* "build.xml" | |
3120 | ;; Remove build-time dependency on git. | |
3121 | (("failifexecutionfails=\"true\"") | |
3122 | "failifexecutionfails=\"false\"") | |
3123 | ;; Use our htsjdk. | |
3124 | (("depends=\"compile-htsjdk, ") | |
3125 | "depends=\"") | |
3126 | (("depends=\"compile-htsjdk-tests, ") | |
3127 | "depends=\"") | |
3128 | ;; Build picard-lib.jar before building picard.jar | |
3129 | (("name=\"picard-jar\" depends=\"" line) | |
3130 | (string-append line "picard-lib-jar, "))) | |
3131 | #t)))) | |
3132 | (build-system ant-build-system) | |
3133 | (arguments | |
3134 | `(#:build-target "picard-jar" | |
3135 | #:test-target "test" | |
3136 | ;; Tests require jacoco:coverage. | |
3137 | #:tests? #f | |
3138 | #:make-flags | |
3139 | (list (string-append "-Dhtsjdk_lib_dir=" | |
3140 | (assoc-ref %build-inputs "java-htsjdk") | |
3141 | "/share/java/htsjdk/") | |
3142 | "-Dhtsjdk-classes=dist/tmp" | |
3143 | (string-append "-Dhtsjdk-version=" | |
3144 | ,(package-version java-htsjdk))) | |
3145 | #:jdk ,icedtea-8 | |
3146 | #:phases | |
3147 | (modify-phases %standard-phases | |
3148 | (add-after 'unpack 'use-our-htsjdk | |
3149 | (lambda* (#:key inputs #:allow-other-keys) | |
3150 | (substitute* "build.xml" | |
3151 | (("\\$\\{htsjdk\\}/lib") | |
3152 | (string-append (assoc-ref inputs "java-htsjdk") | |
3153 | "/share/java/htsjdk/"))) | |
3154 | #t)) | |
3155 | (add-after 'unpack 'make-test-target-independent | |
3156 | (lambda* (#:key inputs #:allow-other-keys) | |
3157 | (substitute* "build.xml" | |
3158 | (("name=\"test\" depends=\"compile, ") | |
3159 | "name=\"test\" depends=\"")) | |
3160 | #t)) | |
3161 | (replace 'install (install-jars "dist"))))) | |
3162 | (inputs | |
3163 | `(("java-htsjdk" ,java-htsjdk) | |
3164 | ("java-guava" ,java-guava))) | |
3165 | (native-inputs | |
3166 | `(("java-testng" ,java-testng))) | |
3167 | (home-page "http://broadinstitute.github.io/picard/") | |
3168 | (synopsis "Tools for manipulating high-throughput sequencing data and formats") | |
3169 | (description "Picard is a set of Java command line tools for manipulating | |
3170 | high-throughput sequencing (HTS) data and formats. Picard is implemented | |
3171 | using the HTSJDK Java library to support accessing file formats that are | |
3172 | commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and | |
3173 | VCF.") | |
3174 | (license license:expat))) | |
3175 | ||
72299db9 RW |
3176 | ;; This is needed for dropseq-tools |
3177 | (define-public java-picard-2.10.3 | |
3178 | (package | |
3179 | (name "java-picard") | |
3180 | (version "2.10.3") | |
3181 | (source (origin | |
3182 | (method git-fetch) | |
3183 | (uri (git-reference | |
3184 | (url "https://github.com/broadinstitute/picard.git") | |
3185 | (commit version))) | |
3186 | (file-name (string-append "java-picard-" version "-checkout")) | |
3187 | (sha256 | |
3188 | (base32 | |
3189 | "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi")))) | |
3190 | (build-system ant-build-system) | |
3191 | (arguments | |
3192 | `(#:jar-name "picard.jar" | |
3193 | ;; Tests require jacoco:coverage. | |
3194 | #:tests? #f | |
3195 | #:jdk ,icedtea-8 | |
3196 | #:main-class "picard.cmdline.PicardCommandLine" | |
3197 | #:modules ((guix build ant-build-system) | |
3198 | (guix build utils) | |
3199 | (guix build java-utils) | |
3200 | (sxml simple) | |
3201 | (sxml transform) | |
3202 | (sxml xpath)) | |
3203 | #:phases | |
3204 | (modify-phases %standard-phases | |
3205 | (add-after 'unpack 'remove-useless-build.xml | |
3206 | (lambda _ (delete-file "build.xml") #t)) | |
3207 | ;; This is necessary to ensure that htsjdk is found when using | |
3208 | ;; picard.jar as an executable. | |
3209 | (add-before 'build 'edit-classpath-in-manifest | |
3210 | (lambda* (#:key inputs #:allow-other-keys) | |
3211 | (chmod "build.xml" #o664) | |
3212 | (call-with-output-file "build.xml.new" | |
3213 | (lambda (port) | |
3214 | (sxml->xml | |
3215 | (pre-post-order | |
3216 | (with-input-from-file "build.xml" | |
3217 | (lambda _ (xml->sxml #:trim-whitespace? #t))) | |
3218 | `((target . ,(lambda (tag . kids) | |
3219 | (let ((name ((sxpath '(name *text*)) | |
3220 | (car kids))) | |
3221 | ;; FIXME: We're breaking the line | |
3222 | ;; early with a dummy path to | |
3223 | ;; ensure that the store reference | |
3224 | ;; isn't broken apart and can still | |
3225 | ;; be found by the reference | |
3226 | ;; scanner. | |
3227 | (msg (format #f | |
3228 | "\ | |
3229 | Class-Path: /~a \ | |
3230 | ~a/share/java/htsjdk.jar${line.separator}" | |
3231 | ;; maximum line length is 70 | |
3232 | (string-tabulate (const #\b) 57) | |
3233 | (assoc-ref inputs "java-htsjdk")))) | |
3234 | (if (member "manifest" name) | |
3235 | `(,tag ,@kids | |
3236 | (echo | |
3237 | (@ (message ,msg) | |
3238 | (file "${manifest.file}") | |
3239 | (append "true")))) | |
3240 | `(,tag ,@kids))))) | |
3241 | (*default* . ,(lambda (tag . kids) `(,tag ,@kids))) | |
3242 | (*text* . ,(lambda (_ txt) txt)))) | |
3243 | port))) | |
3244 | (rename-file "build.xml.new" "build.xml") | |
3245 | #t))))) | |
3246 | (propagated-inputs | |
3247 | `(("java-htsjdk" ,java-htsjdk-2.10.1))) | |
3248 | (native-inputs | |
3249 | `(("java-testng" ,java-testng) | |
3250 | ("java-guava" ,java-guava))) | |
3251 | (home-page "http://broadinstitute.github.io/picard/") | |
3252 | (synopsis "Tools for manipulating high-throughput sequencing data and formats") | |
3253 | (description "Picard is a set of Java command line tools for manipulating | |
3254 | high-throughput sequencing (HTS) data and formats. Picard is implemented | |
3255 | using the HTSJDK Java library to support accessing file formats that are | |
3256 | commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and | |
3257 | VCF.") | |
3258 | (license license:expat))) | |
3259 | ||
d7f24778 RW |
3260 | ;; This is the last version of Picard to provide net.sf.samtools |
3261 | (define-public java-picard-1.113 | |
3262 | (package (inherit java-picard) | |
3263 | (name "java-picard") | |
3264 | (version "1.113") | |
3265 | (source (origin | |
3266 | (method git-fetch) | |
3267 | (uri (git-reference | |
3268 | (url "https://github.com/broadinstitute/picard.git") | |
3269 | (commit version))) | |
3270 | (file-name (string-append "java-picard-" version "-checkout")) | |
3271 | (sha256 | |
3272 | (base32 | |
3273 | "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973")) | |
3274 | (modules '((guix build utils))) | |
3275 | (snippet | |
3276 | '(begin | |
3277 | ;; Delete pre-built binaries. | |
3278 | (delete-file-recursively "lib") | |
3279 | (mkdir-p "lib") | |
3280 | #t)))) | |
3281 | (build-system ant-build-system) | |
3282 | (arguments | |
3283 | `(#:build-target "picard-jar" | |
3284 | #:test-target "test" | |
3285 | ;; FIXME: the class path at test time is wrong. | |
3286 | ;; [testng] Error: A JNI error has occurred, please check your installation and try again | |
3287 | ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException | |
3288 | #:tests? #f | |
3289 | #:jdk ,icedtea-8 | |
3290 | ;; This is only used for tests. | |
3291 | #:make-flags | |
3292 | (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so") | |
3293 | #:phases | |
3294 | (modify-phases %standard-phases | |
3295 | ;; Do not use bundled ant bzip2. | |
3296 | (add-after 'unpack 'use-ant-bzip | |
3297 | (lambda* (#:key inputs #:allow-other-keys) | |
3298 | (substitute* "build.xml" | |
3299 | (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar") | |
3300 | (string-append (assoc-ref inputs "ant") | |
3301 | "/lib/ant.jar"))) | |
3302 | #t)) | |
3303 | (add-after 'unpack 'make-test-target-independent | |
3304 | (lambda* (#:key inputs #:allow-other-keys) | |
3305 | (substitute* "build.xml" | |
3306 | (("name=\"test\" depends=\"compile, ") | |
3307 | "name=\"test\" depends=\"compile-tests, ") | |
3308 | (("name=\"compile\" depends=\"compile-src, compile-tests\"") | |
3309 | "name=\"compile\" depends=\"compile-src\"")) | |
3310 | #t)) | |
3311 | (add-after 'unpack 'fix-deflater-path | |
3312 | (lambda* (#:key outputs #:allow-other-keys) | |
3313 | (substitute* "src/java/net/sf/samtools/Defaults.java" | |
3314 | (("getStringProperty\\(\"intel_deflater_so_path\", null\\)") | |
3315 | (string-append "getStringProperty(\"intel_deflater_so_path\", \"" | |
3316 | (assoc-ref outputs "out") | |
3317 | "/lib/jni/libIntelDeflater.so" | |
3318 | "\")"))) | |
3319 | #t)) | |
3320 | ;; Build the deflater library, because we've previously deleted the | |
3321 | ;; pre-built one. This can only be built with access to the JDK | |
3322 | ;; sources. | |
3323 | (add-after 'build 'build-jni | |
3324 | (lambda* (#:key inputs #:allow-other-keys) | |
3325 | (mkdir-p "lib/jni") | |
3326 | (mkdir-p "jdk-src") | |
3327 | (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src" | |
3328 | "-xf" (assoc-ref inputs "jdk-src"))) | |
3329 | (zero? (system* "javah" "-jni" | |
3330 | "-classpath" "classes" | |
3331 | "-d" "lib/" | |
3332 | "net.sf.samtools.util.zip.IntelDeflater")) | |
3333 | (with-directory-excursion "src/c/inteldeflater" | |
3334 | (zero? (system* "gcc" "-I../../../lib" "-I." | |
3335 | (string-append "-I" (assoc-ref inputs "jdk") | |
3336 | "/include/linux") | |
3337 | "-I../../../jdk-src/src/share/native/common/" | |
3338 | "-I../../../jdk-src/src/solaris/native/common/" | |
3339 | "-c" "-O3" "-fPIC" "IntelDeflater.c")) | |
3340 | (zero? (system* "gcc" "-shared" | |
3341 | "-o" "../../../lib/jni/libIntelDeflater.so" | |
3342 | "IntelDeflater.o" "-lz" "-lstdc++")))))) | |
3343 | ;; We can only build everything else after building the JNI library. | |
3344 | (add-after 'build-jni 'build-rest | |
3345 | (lambda* (#:key make-flags #:allow-other-keys) | |
3346 | (zero? (apply system* `("ant" "all" ,@make-flags))))) | |
3347 | (add-before 'build 'set-JAVA6_HOME | |
3348 | (lambda _ | |
3349 | (setenv "JAVA6_HOME" (getenv "JAVA_HOME")) | |
3350 | #t)) | |
3351 | (replace 'install (install-jars "dist")) | |
3352 | (add-after 'install 'install-jni-lib | |
3353 | (lambda* (#:key outputs #:allow-other-keys) | |
3354 | (let ((jni (string-append (assoc-ref outputs "out") | |
3355 | "/lib/jni"))) | |
3356 | (mkdir-p jni) | |
3357 | (install-file "lib/jni/libIntelDeflater.so" jni) | |
3358 | #t)))))) | |
3359 | (inputs | |
3360 | `(("java-snappy-1" ,java-snappy-1) | |
3361 | ("java-commons-jexl-2" ,java-commons-jexl-2) | |
3362 | ("java-cofoja" ,java-cofoja) | |
3363 | ("ant" ,ant) ; for bzip2 support at runtime | |
3364 | ("zlib" ,zlib))) | |
3365 | (native-inputs | |
3366 | `(("ant-apache-bcel" ,ant-apache-bcel) | |
3367 | ("ant-junit" ,ant-junit) | |
3368 | ("java-testng" ,java-testng) | |
3369 | ("java-commons-bcel" ,java-commons-bcel) | |
3370 | ("java-jcommander" ,java-jcommander) | |
3371 | ("jdk" ,icedtea-8 "jdk") | |
3372 | ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop"))))))) | |
3373 | ||
bd975831 RW |
3374 | (define-public fastqc |
3375 | (package | |
3376 | (name "fastqc") | |
3377 | (version "0.11.5") | |
3378 | (source | |
3379 | (origin | |
3380 | (method url-fetch) | |
3381 | (uri (string-append "http://www.bioinformatics.babraham.ac.uk/" | |
3382 | "projects/fastqc/fastqc_v" | |
3383 | version "_source.zip")) | |
3384 | (sha256 | |
3385 | (base32 | |
3386 | "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f")))) | |
3387 | (build-system ant-build-system) | |
3388 | (arguments | |
3389 | `(#:tests? #f ; there are no tests | |
3390 | #:build-target "build" | |
3391 | #:phases | |
3392 | (modify-phases %standard-phases | |
3393 | (add-after 'unpack 'fix-dependencies | |
3394 | (lambda* (#:key inputs #:allow-other-keys) | |
3395 | (substitute* "build.xml" | |
3396 | (("jbzip2-0.9.jar") | |
3397 | (string-append (assoc-ref inputs "java-jbzip2") | |
3398 | "/share/java/jbzip2.jar")) | |
3399 | (("sam-1.103.jar") | |
3400 | (string-append (assoc-ref inputs "java-picard-1.113") | |
3401 | "/share/java/sam-1.112.jar")) | |
3402 | (("cisd-jhdf5.jar") | |
3403 | (string-append (assoc-ref inputs "java-cisd-jhdf5") | |
3404 | "/share/java/sis-jhdf5.jar"))) | |
3405 | #t)) | |
3406 | ;; There is no installation target | |
3407 | (replace 'install | |
3408 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
3409 | (let* ((out (assoc-ref outputs "out")) | |
3410 | (bin (string-append out "/bin")) | |
3411 | (share (string-append out "/share/fastqc/")) | |
3412 | (exe (string-append share "/fastqc"))) | |
3413 | (for-each mkdir-p (list bin share)) | |
3414 | (copy-recursively "bin" share) | |
3415 | (substitute* exe | |
3416 | (("my \\$java_bin = 'java';") | |
3417 | (string-append "my $java_bin = '" | |
3418 | (assoc-ref inputs "java") | |
3419 | "/bin/java';"))) | |
3420 | (chmod exe #o555) | |
3421 | (symlink exe (string-append bin "/fastqc")) | |
3422 | #t)))))) | |
3423 | (inputs | |
3424 | `(("java" ,icedtea) | |
3425 | ("perl" ,perl) ; needed for the wrapper script | |
3426 | ("java-cisd-jhdf5" ,java-cisd-jhdf5) | |
3427 | ("java-picard-1.113" ,java-picard-1.113) | |
3428 | ("java-jbzip2" ,java-jbzip2))) | |
3429 | (native-inputs | |
3430 | `(("unzip" ,unzip))) | |
3431 | (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/") | |
3432 | (synopsis "Quality control tool for high throughput sequence data") | |
3433 | (description | |
3434 | "FastQC aims to provide a simple way to do some quality control | |
3435 | checks on raw sequence data coming from high throughput sequencing | |
3436 | pipelines. It provides a modular set of analyses which you can use to | |
3437 | give a quick impression of whether your data has any problems of which | |
3438 | you should be aware before doing any further analysis. | |
3439 | ||
3440 | The main functions of FastQC are: | |
3441 | ||
3442 | @itemize | |
3443 | @item Import of data from BAM, SAM or FastQ files (any variant); | |
3444 | @item Providing a quick overview to tell you in which areas there may | |
3445 | be problems; | |
3446 | @item Summary graphs and tables to quickly assess your data; | |
3447 | @item Export of results to an HTML based permanent report; | |
3448 | @item Offline operation to allow automated generation of reports | |
3449 | without running the interactive application. | |
3450 | @end itemize\n") | |
3451 | (license license:gpl3+))) | |
3452 | ||
a1b80245 RW |
3453 | (define-public fastp |
3454 | (package | |
3455 | (name "fastp") | |
3456 | (version "0.14.1") | |
3457 | (source | |
3458 | (origin | |
3459 | (method git-fetch) | |
3460 | (uri (git-reference | |
3461 | (url "https://github.com/OpenGene/fastp.git") | |
3462 | (commit (string-append "v" version)))) | |
3463 | (file-name (git-file-name name version)) | |
3464 | (sha256 | |
3465 | (base32 | |
3466 | "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh")))) | |
3467 | (build-system gnu-build-system) | |
3468 | (arguments | |
3469 | `(#:tests? #f ; there are none | |
3470 | #:make-flags | |
3471 | (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin")) | |
3472 | #:phases | |
3473 | (modify-phases %standard-phases | |
3474 | (delete 'configure) | |
3475 | (add-before 'install 'create-target-dir | |
3476 | (lambda* (#:key outputs #:allow-other-keys) | |
3477 | (mkdir-p (string-append (assoc-ref outputs "out") "/bin")) | |
3478 | #t))))) | |
3479 | (inputs | |
3480 | `(("zlib" ,zlib))) | |
3481 | (home-page "https://github.com/OpenGene/fastp/") | |
3482 | (synopsis "All-in-one FastQ preprocessor") | |
3483 | (description | |
3484 | "Fastp is a tool designed to provide fast all-in-one preprocessing for | |
3485 | FastQ files. This tool has multi-threading support to afford high | |
3486 | performance.") | |
3487 | (license license:expat))) | |
3488 | ||
e7c09730 RW |
3489 | (define-public htslib |
3490 | (package | |
3491 | (name "htslib") | |
8df0267a | 3492 | (version "1.8") |
e7c09730 RW |
3493 | (source (origin |
3494 | (method url-fetch) | |
3495 | (uri (string-append | |
3496 | "https://github.com/samtools/htslib/releases/download/" | |
3497 | version "/htslib-" version ".tar.bz2")) | |
3498 | (sha256 | |
3499 | (base32 | |
8df0267a | 3500 | "18bw0mn9pj5wgarnlaxmf1bb8pdqgl1zd6czirqcr62ajpn1xvy0")))) |
e7c09730 | 3501 | (build-system gnu-build-system) |
e7c09730 | 3502 | (inputs |
a9e4a1e6 BW |
3503 | `(("openssl" ,openssl) |
3504 | ("curl" ,curl) | |
3505 | ("zlib" ,zlib))) | |
e7c09730 RW |
3506 | (native-inputs |
3507 | `(("perl" ,perl))) | |
3508 | (home-page "http://www.htslib.org") | |
3509 | (synopsis "C library for reading/writing high-throughput sequencing data") | |
3510 | (description | |
3511 | "HTSlib is a C library for reading/writing high-throughput sequencing | |
8057dee1 TGR |
3512 | data. It also provides the @command{bgzip}, @command{htsfile}, and |
3513 | @command{tabix} utilities.") | |
e7c09730 RW |
3514 | ;; Files under cram/ are released under the modified BSD license; |
3515 | ;; the rest is released under the Expat license | |
3516 | (license (list license:expat license:bsd-3)))) | |
3517 | ||
bca2c576 BW |
3518 | ;; This package should be removed once no packages rely upon it. |
3519 | (define htslib-1.3 | |
3520 | (package | |
3521 | (inherit htslib) | |
3522 | (version "1.3.1") | |
3523 | (source (origin | |
3524 | (method url-fetch) | |
3525 | (uri (string-append | |
3526 | "https://github.com/samtools/htslib/releases/download/" | |
3527 | version "/htslib-" version ".tar.bz2")) | |
3528 | (sha256 | |
3529 | (base32 | |
3530 | "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9")))))) | |
3531 | ||
c4325f62 RW |
3532 | (define-public idr |
3533 | (package | |
3534 | (name "idr") | |
aa33cc29 | 3535 | (version "2.0.3") |
c4325f62 RW |
3536 | (source (origin |
3537 | (method url-fetch) | |
3538 | (uri (string-append | |
3539 | "https://github.com/nboley/idr/archive/" | |
3540 | version ".tar.gz")) | |
3541 | (file-name (string-append name "-" version ".tar.gz")) | |
3542 | (sha256 | |
3543 | (base32 | |
aa33cc29 RW |
3544 | "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3")) |
3545 | ;; Delete generated C code. | |
3546 | (snippet | |
3547 | '(begin (delete-file "idr/inv_cdf.c") #t)))) | |
c4325f62 | 3548 | (build-system python-build-system) |
aa33cc29 RW |
3549 | ;; There is only one test ("test_inv_cdf.py") and it tests features that |
3550 | ;; are no longer part of this package. It also asserts False, which | |
3551 | ;; causes the tests to always fail. | |
3552 | (arguments `(#:tests? #f)) | |
b7a820fc | 3553 | (propagated-inputs |
c4325f62 | 3554 | `(("python-scipy" ,python-scipy) |
b7a820fc | 3555 | ("python-sympy" ,python-sympy) |
c4325f62 RW |
3556 | ("python-numpy" ,python-numpy) |
3557 | ("python-matplotlib" ,python-matplotlib))) | |
3558 | (native-inputs | |
f3b98f4f | 3559 | `(("python-cython" ,python-cython))) |
c4325f62 RW |
3560 | (home-page "https://github.com/nboley/idr") |
3561 | (synopsis "Tool to measure the irreproducible discovery rate (IDR)") | |
3562 | (description | |
3563 | "The IDR (Irreproducible Discovery Rate) framework is a unified approach | |
3564 | to measure the reproducibility of findings identified from replicate | |
3565 | experiments and provide highly stable thresholds based on reproducibility.") | |
40590caf | 3566 | (license license:gpl2+))) |
c4325f62 | 3567 | |
43c565d2 RW |
3568 | (define-public jellyfish |
3569 | (package | |
3570 | (name "jellyfish") | |
117d8cc4 | 3571 | (version "2.2.7") |
43c565d2 RW |
3572 | (source (origin |
3573 | (method url-fetch) | |
3574 | (uri (string-append "https://github.com/gmarcais/Jellyfish/" | |
3575 | "releases/download/v" version | |
3576 | "/jellyfish-" version ".tar.gz")) | |
3577 | (sha256 | |
3578 | (base32 | |
117d8cc4 | 3579 | "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q")))) |
43c565d2 RW |
3580 | (build-system gnu-build-system) |
3581 | (outputs '("out" ;for library | |
3582 | "ruby" ;for Ruby bindings | |
3583 | "python")) ;for Python bindings | |
3584 | (arguments | |
3585 | `(#:configure-flags | |
3586 | (list (string-append "--enable-ruby-binding=" | |
3587 | (assoc-ref %outputs "ruby")) | |
3588 | (string-append "--enable-python-binding=" | |
3589 | (assoc-ref %outputs "python"))) | |
3590 | #:phases | |
3591 | (modify-phases %standard-phases | |
3592 | (add-before 'check 'set-SHELL-variable | |
3593 | (lambda _ | |
3594 | ;; generator_manager.hpp either uses /bin/sh or $SHELL | |
3595 | ;; to run tests. | |
3596 | (setenv "SHELL" (which "bash")) | |
3597 | #t))))) | |
3598 | (native-inputs | |
3599 | `(("bc" ,bc) | |
3600 | ("time" ,time) | |
3601 | ("ruby" ,ruby) | |
117d8cc4 RW |
3602 | ("python" ,python-2) |
3603 | ("pkg-config" ,pkg-config))) | |
3604 | (inputs | |
3605 | `(("htslib" ,htslib))) | |
43c565d2 RW |
3606 | (synopsis "Tool for fast counting of k-mers in DNA") |
3607 | (description | |
3608 | "Jellyfish is a tool for fast, memory-efficient counting of k-mers in | |
3609 | DNA. A k-mer is a substring of length k, and counting the occurrences of all | |
3610 | such substrings is a central step in many analyses of DNA sequence. Jellyfish | |
3611 | is a command-line program that reads FASTA and multi-FASTA files containing | |
3612 | DNA sequences. It outputs its k-mer counts in a binary format, which can be | |
3613 | translated into a human-readable text format using the @code{jellyfish dump} | |
3614 | command, or queried for specific k-mers with @code{jellyfish query}.") | |
3615 | (home-page "http://www.genome.umd.edu/jellyfish.html") | |
6e8faf77 EF |
3616 | ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors |
3617 | (supported-systems '("x86_64-linux")) | |
43c565d2 RW |
3618 | ;; The combined work is published under the GPLv3 or later. Individual |
3619 | ;; files such as lib/jsoncpp.cpp are released under the Expat license. | |
3620 | (license (list license:gpl3+ license:expat)))) | |
3621 | ||
94ff3157 BW |
3622 | (define-public khmer |
3623 | (package | |
3624 | (name "khmer") | |
3625 | (version "2.0") | |
3626 | (source | |
3627 | (origin | |
3628 | (method url-fetch) | |
3629 | (uri (pypi-uri "khmer" version)) | |
3630 | (sha256 | |
3631 | (base32 | |
3632 | "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a")) | |
3633 | (patches (search-patches "khmer-use-libraries.patch")))) | |
3634 | (build-system python-build-system) | |
3635 | (arguments | |
3636 | `(#:phases | |
3637 | (modify-phases %standard-phases | |
3638 | (add-after 'unpack 'set-paths | |
3639 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
3640 | ;; Delete bundled libraries. | |
3641 | (delete-file-recursively "third-party/zlib") | |
3642 | (delete-file-recursively "third-party/bzip2") | |
3643 | ;; Replace bundled seqan. | |
3644 | (let* ((seqan-all "third-party/seqan") | |
3645 | (seqan-include (string-append | |
3646 | seqan-all "/core/include"))) | |
3647 | (delete-file-recursively seqan-all) | |
3648 | (copy-recursively (string-append (assoc-ref inputs "seqan") | |
3649 | "/include/seqan") | |
3650 | (string-append seqan-include "/seqan"))) | |
3651 | ;; We do not replace the bundled MurmurHash as the canonical | |
3652 | ;; repository for this code 'SMHasher' is unsuitable for | |
3653 | ;; providing a library. See | |
3654 | ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html | |
3655 | #t)) | |
3656 | (add-after 'unpack 'set-cc | |
3657 | (lambda _ | |
3658 | (setenv "CC" "gcc") | |
3659 | #t)) | |
3660 | ;; It is simpler to test after installation. | |
3661 | (delete 'check) | |
3662 | (add-after 'install 'post-install-check | |
3663 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
3664 | (let ((out (assoc-ref outputs "out"))) | |
3665 | (setenv "PATH" | |
3666 | (string-append | |
3667 | (getenv "PATH") | |
3668 | ":" | |
3669 | (assoc-ref outputs "out") | |
3670 | "/bin")) | |
3671 | (setenv "PYTHONPATH" | |
3672 | (string-append | |
3673 | (getenv "PYTHONPATH") | |
3674 | ":" | |
3675 | out | |
3676 | "/lib/python" | |
3677 | (string-take (string-take-right | |
3678 | (assoc-ref inputs "python") 5) 3) | |
3679 | "/site-packages")) | |
3680 | (with-directory-excursion "build" | |
3681 | (zero? (system* "nosetests" "khmer" "--attr" | |
3682 | "!known_failing"))))))))) | |
3683 | (native-inputs | |
3684 | `(("seqan" ,seqan) | |
3685 | ("python-nose" ,python-nose))) | |
3686 | (inputs | |
3687 | `(("zlib" ,zlib) | |
3688 | ("bzip2" ,bzip2) | |
3689 | ("python-screed" ,python-screed) | |
cf1d5814 BW |
3690 | ("python-bz2file" ,python-bz2file) |
3691 | ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least | |
3692 | ;; until the next version of khmer (likely 2.1) is released. | |
3693 | ("gcc" ,gcc-4.9))) | |
94ff3157 BW |
3694 | (home-page "https://khmer.readthedocs.org/") |
3695 | (synopsis "K-mer counting, filtering and graph traversal library") | |
3696 | (description "The khmer software is a set of command-line tools for | |
3697 | working with DNA shotgun sequencing data from genomes, transcriptomes, | |
3698 | metagenomes and single cells. Khmer can make de novo assemblies faster, and | |
3699 | sometimes better. Khmer can also identify and fix problems with shotgun | |
3700 | data.") | |
8157af2e EF |
3701 | ;; When building on i686, armhf and mips64el, we get the following error: |
3702 | ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system | |
3df57b3a | 3703 | (supported-systems '("x86_64-linux" "aarch64-linux")) |
94ff3157 BW |
3704 | (license license:bsd-3))) |
3705 | ||
b9a601d9 RJ |
3706 | (define-public kaiju |
3707 | (package | |
3708 | (name "kaiju") | |
53e42694 | 3709 | (version "1.6.2") |
b9a601d9 RJ |
3710 | (source (origin |
3711 | (method url-fetch) | |
3712 | (uri (string-append | |
3713 | "https://github.com/bioinformatics-centre/kaiju/archive/v" | |
3714 | version ".tar.gz")) | |
3715 | (file-name (string-append name "-" version ".tar.gz")) | |
3716 | (sha256 | |
3717 | (base32 | |
53e42694 | 3718 | "1kdn4rxs0kr9ibmrgrfcci71aa6j6gr71dbc8pff7731rpab6kj7")))) |
b9a601d9 RJ |
3719 | (build-system gnu-build-system) |
3720 | (arguments | |
3721 | `(#:tests? #f ; There are no tests. | |
3722 | #:phases | |
3723 | (modify-phases %standard-phases | |
3724 | (delete 'configure) | |
3725 | (add-before 'build 'move-to-src-dir | |
3726 | (lambda _ (chdir "src") #t)) | |
3727 | (replace 'install | |
3728 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
3729 | (let ((bin (string-append (assoc-ref outputs "out") "/bin"))) | |
3730 | (mkdir-p bin) | |
3731 | (chdir "..") | |
3732 | (copy-recursively "bin" bin) | |
3733 | (copy-recursively "util" bin)) | |
3734 | #t))))) | |
3735 | (inputs | |
53e42694 RJ |
3736 | `(("perl" ,perl) |
3737 | ("zlib" ,zlib))) | |
b9a601d9 RJ |
3738 | (home-page "http://kaiju.binf.ku.dk/") |
3739 | (synopsis "Fast and sensitive taxonomic classification for metagenomics") | |
3740 | (description "Kaiju is a program for sensitive taxonomic classification | |
3741 | of high-throughput sequencing reads from metagenomic whole genome sequencing | |
3742 | experiments.") | |
3743 | (license license:gpl3+))) | |
3744 | ||
d57e6d0f RW |
3745 | (define-public macs |
3746 | (package | |
3747 | (name "macs") | |
0d0bcaa0 | 3748 | (version "2.1.0.20151222") |
d57e6d0f RW |
3749 | (source (origin |
3750 | (method url-fetch) | |
43ec07f1 | 3751 | (uri (pypi-uri "MACS2" version)) |
d57e6d0f RW |
3752 | (sha256 |
3753 | (base32 | |
0d0bcaa0 | 3754 | "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5")))) |
d57e6d0f RW |
3755 | (build-system python-build-system) |
3756 | (arguments | |
3757 | `(#:python ,python-2 ; only compatible with Python 2.7 | |
3758 | #:tests? #f)) ; no test target | |
3759 | (inputs | |
3760 | `(("python-numpy" ,python2-numpy))) | |
7bf837fd | 3761 | (home-page "https://github.com/taoliu/MACS/") |
d57e6d0f RW |
3762 | (synopsis "Model based analysis for ChIP-Seq data") |
3763 | (description | |
3764 | "MACS is an implementation of a ChIP-Seq analysis algorithm for | |
3765 | identifying transcript factor binding sites named Model-based Analysis of | |
3766 | ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate | |
3767 | the significance of enriched ChIP regions and it improves the spatial | |
3768 | resolution of binding sites through combining the information of both | |
3769 | sequencing tag position and orientation.") | |
3770 | (license license:bsd-3))) | |
3771 | ||
41ddebdd BW |
3772 | (define-public mafft |
3773 | (package | |
3774 | (name "mafft") | |
c7a8aa13 | 3775 | (version "7.394") |
41ddebdd BW |
3776 | (source (origin |
3777 | (method url-fetch) | |
3778 | (uri (string-append | |
3146f22d | 3779 | "https://mafft.cbrc.jp/alignment/software/mafft-" version |
41ddebdd BW |
3780 | "-without-extensions-src.tgz")) |
3781 | (file-name (string-append name "-" version ".tgz")) | |
3782 | (sha256 | |
3783 | (base32 | |
c7a8aa13 | 3784 | "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b")))) |
41ddebdd BW |
3785 | (build-system gnu-build-system) |
3786 | (arguments | |
3787 | `(#:tests? #f ; no automated tests, though there are tests in the read me | |
3788 | #:make-flags (let ((out (assoc-ref %outputs "out"))) | |
3789 | (list (string-append "PREFIX=" out) | |
3790 | (string-append "BINDIR=" | |
3791 | (string-append out "/bin")))) | |
3792 | #:phases | |
3793 | (modify-phases %standard-phases | |
3794 | (add-after 'unpack 'enter-dir | |
101e8f71 | 3795 | (lambda _ (chdir "core") #t)) |
41ddebdd | 3796 | (add-after 'enter-dir 'patch-makefile |
101e8f71 BW |
3797 | (lambda _ |
3798 | ;; on advice from the MAFFT authors, there is no need to | |
3799 | ;; distribute mafft-profile, mafft-distance, or | |
3800 | ;; mafft-homologs.rb as they are too "specialised". | |
3801 | (substitute* "Makefile" | |
3802 | ;; remove mafft-homologs.rb from SCRIPTS | |
3803 | (("^SCRIPTS = mafft mafft-homologs.rb") | |
3804 | "SCRIPTS = mafft") | |
3805 | ;; remove mafft-homologs from MANPAGES | |
3806 | (("^MANPAGES = mafft.1 mafft-homologs.1") | |
3807 | "MANPAGES = mafft.1") | |
3808 | ;; remove mafft-distance from PROGS | |
3809 | (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance") | |
3810 | "PROGS = dvtditr dndfast7 dndblast sextet5") | |
3811 | ;; remove mafft-profile from PROGS | |
3812 | (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap") | |
3813 | "splittbfast disttbfast tbfast f2cl mccaskillwrap") | |
3814 | (("^rm -f mafft-profile mafft-profile.exe") "#") | |
3815 | (("^rm -f mafft-distance mafft-distance.exe") ")#") | |
3816 | ;; do not install MAN pages in libexec folder | |
3817 | (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \ | |
41ddebdd | 3818 | \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#")) |
101e8f71 | 3819 | #t)) |
02f35bb5 BW |
3820 | (add-after 'enter-dir 'patch-paths |
3821 | (lambda* (#:key inputs #:allow-other-keys) | |
3822 | (substitute* '("pairash.c" | |
3823 | "mafft.tmpl") | |
3824 | (("perl") (which "perl")) | |
3825 | (("([\"`| ])awk" _ prefix) | |
3826 | (string-append prefix (which "awk"))) | |
3827 | (("grep") (which "grep"))) | |
3828 | #t)) | |
101e8f71 BW |
3829 | (delete 'configure) |
3830 | (add-after 'install 'wrap-programs | |
3831 | (lambda* (#:key outputs #:allow-other-keys) | |
3832 | (let* ((out (assoc-ref outputs "out")) | |
3833 | (bin (string-append out "/bin")) | |
3834 | (path (string-append | |
3835 | (assoc-ref %build-inputs "coreutils") "/bin:"))) | |
3836 | (for-each (lambda (file) | |
3837 | (wrap-program file | |
3838 | `("PATH" ":" prefix (,path)))) | |
3839 | (find-files bin))) | |
3840 | #t))))) | |
41ddebdd | 3841 | (inputs |
02f35bb5 | 3842 | `(("perl" ,perl) |
71461f88 | 3843 | ("ruby" ,ruby) |
02f35bb5 | 3844 | ("gawk" ,gawk) |
101e8f71 BW |
3845 | ("grep" ,grep) |
3846 | ("coreutils" ,coreutils))) | |
41ddebdd BW |
3847 | (home-page "http://mafft.cbrc.jp/alignment/software/") |
3848 | (synopsis "Multiple sequence alignment program") | |
3849 | (description | |
3850 | "MAFFT offers a range of multiple alignment methods for nucleotide and | |
3851 | protein sequences. For instance, it offers L-INS-i (accurate; for alignment | |
3852 | of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000 | |
3853 | sequences).") | |
3854 | (license (license:non-copyleft | |
3855 | "http://mafft.cbrc.jp/alignment/software/license.txt" | |
3856 | "BSD-3 with different formatting")))) | |
8fd790eb | 3857 | |
84be3b99 MB |
3858 | (define-public mash |
3859 | (package | |
3860 | (name "mash") | |
f38ac742 | 3861 | (version "2.0") |
84be3b99 MB |
3862 | (source (origin |
3863 | (method url-fetch) | |
3864 | (uri (string-append | |
3865 | "https://github.com/marbl/mash/archive/v" | |
3866 | version ".tar.gz")) | |
3867 | (file-name (string-append name "-" version ".tar.gz")) | |
3868 | (sha256 | |
3869 | (base32 | |
f38ac742 | 3870 | "00fx14vpmgsijwxd1xql3if934l82v8ckqgjjyyhnr36qb9qrskv")) |
84be3b99 MB |
3871 | (modules '((guix build utils))) |
3872 | (snippet | |
3873 | ;; Delete bundled kseq. | |
3874 | ;; TODO: Also delete bundled murmurhash and open bloom filter. | |
3875 | '(delete-file "src/mash/kseq.h")))) | |
3876 | (build-system gnu-build-system) | |
3877 | (arguments | |
3878 | `(#:tests? #f ; No tests. | |
3879 | #:configure-flags | |
3880 | (list | |
3881 | (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto")) | |
3882 | (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl"))) | |
3883 | #:make-flags (list "CC=gcc") | |
3884 | #:phases | |
3885 | (modify-phases %standard-phases | |
3886 | (add-after 'unpack 'fix-includes | |
3887 | (lambda _ | |
f38ac742 BW |
3888 | (substitute* '("src/mash/Sketch.cpp" |
3889 | "src/mash/CommandFind.cpp" | |
3890 | "src/mash/CommandScreen.cpp") | |
84be3b99 MB |
3891 | (("^#include \"kseq\\.h\"") |
3892 | "#include \"htslib/kseq.h\"")) | |
3893 | #t)) | |
d10092b8 | 3894 | (add-after 'fix-includes 'autoconf |
84be3b99 MB |
3895 | (lambda _ (zero? (system* "autoconf"))))))) |
3896 | (native-inputs | |
3897 | `(("autoconf" ,autoconf) | |
3898 | ;; Capnproto and htslib are statically embedded in the final | |
3899 | ;; application. Therefore we also list their licenses, below. | |
3900 | ("capnproto" ,capnproto) | |
3901 | ("htslib" ,htslib))) | |
3902 | (inputs | |
3903 | `(("gsl" ,gsl) | |
3904 | ("zlib" ,zlib))) | |
3905 | (supported-systems '("x86_64-linux")) | |
3906 | (home-page "https://mash.readthedocs.io") | |
3907 | (synopsis "Fast genome and metagenome distance estimation using MinHash") | |
3908 | (description "Mash is a fast sequence distance estimator that uses the | |
3909 | MinHash algorithm and is designed to work with genomes and metagenomes in the | |
3910 | form of assemblies or reads.") | |
3911 | (license (list license:bsd-3 ; Mash | |
3912 | license:expat ; HTSlib and capnproto | |
3913 | license:public-domain ; MurmurHash 3 | |
3914 | license:cpl1.0)))) ; Open Bloom Filter | |
3915 | ||
8fd790eb | 3916 | (define-public metabat |
f3f68a44 BW |
3917 | (package |
3918 | (name "metabat") | |
25bd1fc1 | 3919 | (version "2.12.1") |
f3f68a44 BW |
3920 | (source |
3921 | (origin | |
25bd1fc1 BW |
3922 | (method url-fetch) |
3923 | (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v" | |
3924 | version ".tar.gz")) | |
3925 | (file-name (string-append name "-" version ".tar.gz")) | |
f3f68a44 BW |
3926 | (sha256 |
3927 | (base32 | |
25bd1fc1 BW |
3928 | "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73")) |
3929 | (patches (search-patches "metabat-fix-compilation.patch")))) | |
9364a520 | 3930 | (build-system scons-build-system) |
8fd790eb | 3931 | (arguments |
9364a520 AI |
3932 | `(#:scons ,scons-python2 |
3933 | #:scons-flags | |
3934 | (list (string-append "PREFIX=" (assoc-ref %outputs "out")) | |
3935 | (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost"))) | |
3936 | #:tests? #f ;; Tests are run during the build phase. | |
3937 | #:phases | |
8fd790eb BW |
3938 | (modify-phases %standard-phases |
3939 | (add-after 'unpack 'fix-includes | |
45469ebe BW |
3940 | (lambda _ |
3941 | (substitute* "src/BamUtils.h" | |
3942 | (("^#include \"bam/bam\\.h\"") | |
3943 | "#include \"samtools/bam.h\"") | |
3944 | (("^#include \"bam/sam\\.h\"") | |
3945 | "#include \"samtools/sam.h\"")) | |
3946 | (substitute* "src/KseqReader.h" | |
3947 | (("^#include \"bam/kseq\\.h\"") | |
3948 | "#include \"htslib/kseq.h\"")) | |
3949 | #t)) | |
8fd790eb | 3950 | (add-after 'unpack 'fix-scons |
f3f68a44 BW |
3951 | (lambda* (#:key inputs #:allow-other-keys) |
3952 | (substitute* "SConstruct" | |
3953 | (("^htslib_dir += 'samtools'") | |
3954 | (string-append "htslib_dir = '" | |
3955 | (assoc-ref inputs "htslib") | |
3956 | "'")) | |
3957 | (("^samtools_dir = 'samtools'") | |
3958 | (string-append "samtools_dir = '" | |
3959 | (assoc-ref inputs "samtools") | |
3960 | "'")) | |
3961 | (("^findStaticOrShared\\('bam', hts_lib") | |
3962 | (string-append "findStaticOrShared('bam', '" | |
3963 | (assoc-ref inputs "samtools") | |
3964 | "/lib'")) | |
3965 | ;; Do not distribute README. | |
3966 | (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") "")) | |
9364a520 | 3967 | #t))))) |
8fd790eb BW |
3968 | (inputs |
3969 | `(("zlib" ,zlib) | |
3970 | ("perl" ,perl) | |
3971 | ("samtools" ,samtools) | |
3972 | ("htslib" ,htslib) | |
3973 | ("boost" ,boost))) | |
8fd790eb BW |
3974 | (home-page "https://bitbucket.org/berkeleylab/metabat") |
3975 | (synopsis | |
3976 | "Reconstruction of single genomes from complex microbial communities") | |
3977 | (description | |
3978 | "Grouping large genomic fragments assembled from shotgun metagenomic | |
3979 | sequences to deconvolute complex microbial communities, or metagenome binning, | |
3980 | enables the study of individual organisms and their interactions. MetaBAT is | |
3981 | an automated metagenome binning software, which integrates empirical | |
3982 | probabilistic distances of genome abundance and tetranucleotide frequency.") | |
d931a4bb EF |
3983 | ;; The source code contains inline assembly. |
3984 | (supported-systems '("x86_64-linux" "i686-linux")) | |
f3f68a44 BW |
3985 | (license (license:non-copyleft "file://license.txt" |
3986 | "See license.txt in the distribution.")))) | |
8fd790eb | 3987 | |
318c0aee MB |
3988 | (define-public minced |
3989 | (package | |
3990 | (name "minced") | |
3991 | (version "0.2.0") | |
3992 | (source (origin | |
3993 | (method url-fetch) | |
3994 | (uri (string-append | |
3995 | "https://github.com/ctSkennerton/minced/archive/" | |
3996 | version ".tar.gz")) | |
3997 | (file-name (string-append name "-" version ".tar.gz")) | |
3998 | (sha256 | |
3999 | (base32 | |
4000 | "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1")))) | |
4001 | (build-system gnu-build-system) | |
4002 | (arguments | |
4003 | `(#:test-target "test" | |
4004 | #:phases | |
4005 | (modify-phases %standard-phases | |
4006 | (delete 'configure) | |
4007 | (add-before 'check 'fix-test | |
4008 | (lambda _ | |
4009 | ;; Fix test for latest version. | |
4010 | (substitute* "t/Aquifex_aeolicus_VF5.expected" | |
4011 | (("minced:0.1.6") "minced:0.2.0")) | |
4012 | #t)) | |
4013 | (replace 'install ; No install target. | |
4014 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
4015 | (let* ((out (assoc-ref outputs "out")) | |
4016 | (bin (string-append out "/bin")) | |
4017 | (wrapper (string-append bin "/minced"))) | |
4018 | ;; Minced comes with a wrapper script that tries to figure out where | |
4019 | ;; it is located before running the JAR. Since these paths are known | |
4020 | ;; to us, we build our own wrapper to avoid coreutils dependency. | |
4021 | (install-file "minced.jar" bin) | |
4022 | (with-output-to-file wrapper | |
4023 | (lambda _ | |
4024 | (display | |
4025 | (string-append | |
4026 | "#!" (assoc-ref inputs "bash") "/bin/sh\n\n" | |
4027 | (assoc-ref inputs "jre") "/bin/java -jar " | |
4028 | bin "/minced.jar \"$@\"\n")))) | |
4029 | (chmod wrapper #o555))))))) | |
4030 | (native-inputs | |
4031 | `(("jdk" ,icedtea "jdk"))) | |
4032 | (inputs | |
4033 | `(("bash" ,bash) | |
4034 | ("jre" ,icedtea "out"))) | |
4035 | (home-page "https://github.com/ctSkennerton/minced") | |
4036 | (synopsis "Mining CRISPRs in Environmental Datasets") | |
4037 | (description | |
4038 | "MinCED is a program to find Clustered Regularly Interspaced Short | |
4039 | Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for | |
4040 | unassembled metagenomic reads, but is mainly designed for full genomes and | |
4041 | assembled metagenomic sequence.") | |
4042 | (license license:gpl3+))) | |
4043 | ||
ddd82e0e RW |
4044 | (define-public miso |
4045 | (package | |
4046 | (name "miso") | |
ce4dfde0 | 4047 | (version "0.5.4") |
ddd82e0e RW |
4048 | (source (origin |
4049 | (method url-fetch) | |
34260a10 | 4050 | (uri (pypi-uri "misopy" version)) |
ddd82e0e RW |
4051 | (sha256 |
4052 | (base32 | |
ce4dfde0 | 4053 | "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip")) |
ddd82e0e | 4054 | (modules '((guix build utils))) |
ddd82e0e RW |
4055 | (snippet |
4056 | '(substitute* "setup.py" | |
0ec8b206 RW |
4057 | ;; Use setuptools, or else the executables are not |
4058 | ;; installed. | |
4059 | (("distutils.core") "setuptools") | |
4060 | ;; use "gcc" instead of "cc" for compilation | |
ddd82e0e RW |
4061 | (("^defines") |
4062 | "cc.set_executables( | |
4063 | compiler='gcc', | |
4064 | compiler_so='gcc', | |
4065 | linker_exe='gcc', | |
4066 | linker_so='gcc -shared'); defines"))))) | |
4067 | (build-system python-build-system) | |
4068 | (arguments | |
4069 | `(#:python ,python-2 ; only Python 2 is supported | |
4070 | #:tests? #f)) ; no "test" target | |
4071 | (inputs | |
4072 | `(("samtools" ,samtools) | |
4073 | ("python-numpy" ,python2-numpy) | |
4074 | ("python-pysam" ,python2-pysam) | |
4075 | ("python-scipy" ,python2-scipy) | |
4076 | ("python-matplotlib" ,python2-matplotlib))) | |
4077 | (native-inputs | |
f3b98f4f HG |
4078 | `(("python-mock" ,python2-mock) ;for tests |
4079 | ("python-pytz" ,python2-pytz))) ;for tests | |
ddd82e0e RW |
4080 | (home-page "http://genes.mit.edu/burgelab/miso/index.html") |
4081 | (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation") | |
4082 | (description | |
4083 | "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates | |
4084 | the expression level of alternatively spliced genes from RNA-Seq data, and | |
4085 | identifies differentially regulated isoforms or exons across samples. By | |
4086 | modeling the generative process by which reads are produced from isoforms in | |
4087 | RNA-Seq, the MISO model uses Bayesian inference to compute the probability | |
4088 | that a read originated from a particular isoform.") | |
4089 | (license license:gpl2))) | |
4090 | ||
324efb88 BW |
4091 | (define-public muscle |
4092 | (package | |
4093 | (name "muscle") | |
4094 | (version "3.8.1551") | |
4095 | (source (origin | |
4096 | (method url-fetch/tarbomb) | |
324efb88 BW |
4097 | (uri (string-append |
4098 | "http://www.drive5.com/muscle/muscle_src_" | |
4099 | version ".tar.gz")) | |
4100 | (sha256 | |
4101 | (base32 | |
4102 | "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367")))) | |
4103 | (build-system gnu-build-system) | |
4104 | (arguments | |
4105 | `(#:make-flags (list "LDLIBS = -lm") | |
4106 | #:phases | |
4107 | (modify-phases %standard-phases | |
4108 | (delete 'configure) | |
4109 | (replace 'check | |
4110 | ;; There are no tests, so just test if it runs. | |
4111 | (lambda _ (zero? (system* "./muscle" "-version")))) | |
4112 | (replace 'install | |
4113 | (lambda* (#:key outputs #:allow-other-keys) | |
4114 | (let* ((out (assoc-ref outputs "out")) | |
4115 | (bin (string-append out "/bin"))) | |
4116 | (install-file "muscle" bin))))))) | |
4117 | (home-page "http://www.drive5.com/muscle") | |
4118 | (synopsis "Multiple sequence alignment program") | |
4119 | (description | |
4120 | "MUSCLE aims to be a fast and accurate multiple sequence alignment | |
4121 | program for nucleotide and protein sequences.") | |
4122 | ;; License information found in 'muscle -h' and usage.cpp. | |
4123 | (license license:public-domain))) | |
4124 | ||
99268755 BW |
4125 | (define-public newick-utils |
4126 | ;; There are no recent releases so we package from git. | |
4127 | (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87")) | |
4128 | (package | |
4129 | (name "newick-utils") | |
4130 | (version (string-append "1.6-1." (string-take commit 8))) | |
4131 | (source (origin | |
4132 | (method git-fetch) | |
4133 | (uri (git-reference | |
4134 | (url "https://github.com/tjunier/newick_utils.git") | |
4135 | (commit commit))) | |
4136 | (file-name (string-append name "-" version "-checkout")) | |
4137 | (sha256 | |
4138 | (base32 | |
4139 | "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb")))) | |
4140 | (build-system gnu-build-system) | |
4141 | (arguments | |
4142 | `(#:phases | |
4143 | (modify-phases %standard-phases | |
4144 | (add-after 'unpack 'autoconf | |
4145 | (lambda _ (zero? (system* "autoreconf" "-vif"))))))) | |
4146 | (inputs | |
4147 | ;; XXX: TODO: Enable Lua and Guile bindings. | |
4148 | ;; https://github.com/tjunier/newick_utils/issues/13 | |
4149 | `(("libxml2" ,libxml2) | |
4150 | ("flex" ,flex) | |
4151 | ("bison" ,bison))) | |
4152 | (native-inputs | |
4153 | `(("autoconf" ,autoconf) | |
4154 | ("automake" ,automake) | |
4155 | ("libtool" ,libtool))) | |
4156 | (synopsis "Programs for working with newick format phylogenetic trees") | |
4157 | (description | |
4158 | "Newick-utils is a suite of utilities for processing phylogenetic trees | |
4159 | in Newick format. Functions include re-rooting, extracting subtrees, | |
4160 | trimming, pruning, condensing, drawing (ASCII graphics or SVG).") | |
4161 | (home-page "https://github.com/tjunier/newick_utils") | |
4162 | (license license:bsd-3)))) | |
4163 | ||
1e44cf8b BW |
4164 | (define-public orfm |
4165 | (package | |
4166 | (name "orfm") | |
dfc83ead | 4167 | (version "0.7.1") |
1e44cf8b BW |
4168 | (source (origin |
4169 | (method url-fetch) | |
4170 | (uri (string-append | |
4171 | "https://github.com/wwood/OrfM/releases/download/v" | |
4172 | version "/orfm-" version ".tar.gz")) | |
4173 | (sha256 | |
4174 | (base32 | |
dfc83ead | 4175 | "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr")))) |
1e44cf8b BW |
4176 | (build-system gnu-build-system) |
4177 | (inputs `(("zlib" ,zlib))) | |
6b6f7d6a BW |
4178 | (native-inputs |
4179 | `(("ruby-bio-commandeer" ,ruby-bio-commandeer) | |
4180 | ("ruby-rspec" ,ruby-rspec) | |
4181 | ("ruby" ,ruby))) | |
1e44cf8b BW |
4182 | (synopsis "Simple and not slow open reading frame (ORF) caller") |
4183 | (description | |
6b6f7d6a | 4184 | "An ORF caller finds stretches of DNA that, when translated, are not |
1e44cf8b BW |
4185 | interrupted by stop codons. OrfM finds and prints these ORFs.") |
4186 | (home-page "https://github.com/wwood/OrfM") | |
4187 | (license license:lgpl3+))) | |
4188 | ||
c033f5d6 BW |
4189 | (define-public pplacer |
4190 | (let ((commit "g807f6f3")) | |
4191 | (package | |
4192 | (name "pplacer") | |
4193 | ;; The commit should be updated with each version change. | |
4194 | (version "1.1.alpha19") | |
4195 | (source | |
4196 | (origin | |
4197 | (method url-fetch) | |
4198 | (uri (string-append "https://github.com/matsen/pplacer/archive/v" | |
4199 | version ".tar.gz")) | |
4200 | (file-name (string-append name "-" version ".tar.gz")) | |
4201 | (sha256 | |
4202 | (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f")))) | |
4203 | (build-system ocaml-build-system) | |
4204 | (arguments | |
4205 | `(#:ocaml ,ocaml-4.01 | |
4206 | #:findlib ,ocaml4.01-findlib | |
4207 | #:modules ((guix build ocaml-build-system) | |
4208 | (guix build utils) | |
4209 | (ice-9 ftw)) | |
4210 | #:phases | |
4211 | (modify-phases %standard-phases | |
4212 | (delete 'configure) | |
4213 | (add-after 'unpack 'replace-bundled-cddlib | |
4214 | (lambda* (#:key inputs #:allow-other-keys) | |
4215 | (let* ((cddlib-src (assoc-ref inputs "cddlib-src")) | |
4216 | (local-dir "cddlib_guix")) | |
4217 | (mkdir local-dir) | |
4218 | (with-directory-excursion local-dir | |
4219 | (system* "tar" "xvf" cddlib-src)) | |
4220 | (let ((cddlib-src-folder | |
4221 | (string-append local-dir "/" | |
4222 | (list-ref (scandir local-dir) 2) | |
4223 | "/lib-src"))) | |
4224 | (for-each | |
4225 | (lambda (file) | |
4226 | (copy-file file | |
4227 | (string-append "cdd_src/" (basename file)))) | |
4228 | (find-files cddlib-src-folder ".*[ch]$"))) | |
4229 | #t))) | |
4230 | (add-after 'unpack 'fix-makefile | |
4231 | (lambda _ | |
4232 | ;; Remove system calls to 'git'. | |
4233 | (substitute* "Makefile" | |
4234 | (("^DESCRIPT:=pplacer-.*") | |
4235 | (string-append | |
4236 | "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n"))) | |
4237 | (substitute* "myocamlbuild.ml" | |
4238 | (("git describe --tags --long .*\\\" with") | |
4239 | (string-append | |
4240 | "echo -n v" ,version "-" ,commit "\" with"))) | |
4241 | #t)) | |
4242 | (replace 'install | |
4243 | (lambda* (#:key outputs #:allow-other-keys) | |
4244 | (let* ((out (assoc-ref outputs "out")) | |
4245 | (bin (string-append out "/bin"))) | |
4246 | (copy-recursively "bin" bin)) | |
4247 | #t))))) | |
4248 | (native-inputs | |
4249 | `(("zlib" ,zlib) | |
4250 | ("gsl" ,gsl) | |
4251 | ("ocaml-ounit" ,ocaml4.01-ounit) | |
4252 | ("ocaml-batteries" ,ocaml4.01-batteries) | |
4253 | ("ocaml-camlzip" ,ocaml4.01-camlzip) | |
4254 | ("ocaml-csv" ,ocaml4.01-csv) | |
4255 | ("ocaml-sqlite3" ,ocaml4.01-sqlite3) | |
4256 | ("ocaml-xmlm" ,ocaml4.01-xmlm) | |
4257 | ("ocaml-mcl" ,ocaml4.01-mcl) | |
4258 | ("ocaml-gsl" ,ocaml4.01-gsl) | |
4259 | ("cddlib-src" ,(package-source cddlib)))) | |
4260 | (propagated-inputs | |
4261 | `(("pplacer-scripts" ,pplacer-scripts))) | |
4262 | (synopsis "Phylogenetic placement of biological sequences") | |
4263 | (description | |
4264 | "Pplacer places query sequences on a fixed reference phylogenetic tree | |
4265 | to maximize phylogenetic likelihood or posterior probability according to a | |
4266 | reference alignment. Pplacer is designed to be fast, to give useful | |
4267 | information about uncertainty, and to offer advanced visualization and | |
4268 | downstream analysis.") | |
4269 | (home-page "http://matsen.fhcrc.org/pplacer") | |
4270 | (license license:gpl3)))) | |
4271 | ||
4272 | ;; This package is installed alongside 'pplacer'. It is a separate package so | |
4273 | ;; that it can use the python-build-system for the scripts that are | |
4274 | ;; distributed alongside the main OCaml binaries. | |
4275 | (define pplacer-scripts | |
4276 | (package | |
4277 | (inherit pplacer) | |
4278 | (name "pplacer-scripts") | |
4279 | (build-system python-build-system) | |
4280 | (arguments | |
4281 | `(#:python ,python-2 | |
4282 | #:phases | |
4283 | (modify-phases %standard-phases | |
4284 | (add-after 'unpack 'enter-scripts-dir | |
4285 | (lambda _ (chdir "scripts"))) | |
4286 | (replace 'check | |
4287 | (lambda _ | |
4288 | (zero? (system* "python" "-m" "unittest" "discover" "-v")))) | |
4289 | (add-after 'install 'wrap-executables | |
4290 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
4291 | (let* ((out (assoc-ref outputs "out")) | |
4292 | (bin (string-append out "/bin"))) | |
4293 | (let ((path (string-append | |
4294 | (assoc-ref inputs "hmmer") "/bin:" | |
4295 | (assoc-ref inputs "infernal") "/bin"))) | |
4296 | (display path) | |
4297 | (wrap-program (string-append bin "/refpkg_align.py") | |
4298 | `("PATH" ":" prefix (,path)))) | |
4299 | (let ((path (string-append | |
4300 | (assoc-ref inputs "hmmer") "/bin"))) | |
4301 | (wrap-program (string-append bin "/hrefpkg_query.py") | |
4302 | `("PATH" ":" prefix (,path))))) | |
4303 | #t))))) | |
4304 | (inputs | |
4305 | `(("infernal" ,infernal) | |
4306 | ("hmmer" ,hmmer))) | |
4307 | (propagated-inputs | |
4308 | `(("python-biopython" ,python2-biopython) | |
4309 | ("taxtastic" ,taxtastic))) | |
4310 | (synopsis "Pplacer Python scripts"))) | |
4311 | ||
19ee9201 RW |
4312 | (define-public python2-pbcore |
4313 | (package | |
4314 | (name "python2-pbcore") | |
e301bfc8 | 4315 | (version "1.2.10") |
19ee9201 RW |
4316 | (source (origin |
4317 | (method url-fetch) | |
ddb83129 | 4318 | (uri (pypi-uri "pbcore" version)) |
19ee9201 RW |
4319 | (sha256 |
4320 | (base32 | |
e301bfc8 | 4321 | "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i")))) |
19ee9201 RW |
4322 | (build-system python-build-system) |
4323 | (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7 | |
de5bc890 | 4324 | (propagated-inputs |
19ee9201 RW |
4325 | `(("python-cython" ,python2-cython) |
4326 | ("python-numpy" ,python2-numpy) | |
4327 | ("python-pysam" ,python2-pysam) | |
4328 | ("python-h5py" ,python2-h5py))) | |
4329 | (native-inputs | |
de5bc890 HG |
4330 | `(("python-nose" ,python2-nose) |
4331 | ("python-sphinx" ,python2-sphinx) | |
4332 | ("python-pyxb" ,python2-pyxb))) | |
19ee9201 RW |
4333 | (home-page "http://pacificbiosciences.github.io/pbcore/") |
4334 | (synopsis "Library for reading and writing PacBio data files") | |
4335 | (description | |
4336 | "The pbcore package provides Python APIs for interacting with PacBio data | |
4337 | files and writing bioinformatics applications.") | |
4338 | (license license:bsd-3))) | |
4339 | ||
c61fe02c RW |
4340 | (define-public python2-warpedlmm |
4341 | (package | |
4342 | (name "python2-warpedlmm") | |
4343 | (version "0.21") | |
4344 | (source | |
4345 | (origin | |
4346 | (method url-fetch) | |
4347 | (uri (string-append | |
4348 | "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-" | |
4349 | version ".zip")) | |
4350 | (sha256 | |
4351 | (base32 | |
4352 | "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j")))) | |
4353 | (build-system python-build-system) | |
4354 | (arguments | |
54c85e12 | 4355 | `(#:python ,python-2)) ; requires Python 2.7 |
c61fe02c RW |
4356 | (propagated-inputs |
4357 | `(("python-scipy" ,python2-scipy) | |
4358 | ("python-numpy" ,python2-numpy) | |
4359 | ("python-matplotlib" ,python2-matplotlib) | |
4360 | ("python-fastlmm" ,python2-fastlmm) | |
4361 | ("python-pandas" ,python2-pandas) | |
4362 | ("python-pysnptools" ,python2-pysnptools))) | |
4363 | (native-inputs | |
f3b98f4f | 4364 | `(("python-mock" ,python2-mock) |
c61fe02c RW |
4365 | ("python-nose" ,python2-nose) |
4366 | ("unzip" ,unzip))) | |
4367 | (home-page "https://github.com/PMBio/warpedLMM") | |
4368 | (synopsis "Implementation of warped linear mixed models") | |
4369 | (description | |
4370 | "WarpedLMM is a Python implementation of the warped linear mixed model, | |
4371 | which automatically learns an optimal warping function (or transformation) for | |
4372 | the phenotype as it models the data.") | |
4373 | (license license:asl2.0))) | |
4374 | ||
2c16316e | 4375 | (define-public pbtranscript-tofu |
698bd297 | 4376 | (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4")) |
2c16316e RW |
4377 | (package |
4378 | (name "pbtranscript-tofu") | |
698bd297 | 4379 | (version (string-append "2.2.3." (string-take commit 7))) |
2c16316e RW |
4380 | (source (origin |
4381 | (method git-fetch) | |
4382 | (uri (git-reference | |
4383 | (url "https://github.com/PacificBiosciences/cDNA_primer.git") | |
4384 | (commit commit))) | |
9a067efd | 4385 | (file-name (string-append name "-" version "-checkout")) |
2c16316e RW |
4386 | (sha256 |
4387 | (base32 | |
9a067efd RW |
4388 | "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f")) |
4389 | (modules '((guix build utils))) | |
4390 | (snippet | |
4391 | '(begin | |
4392 | ;; remove bundled Cython sources | |
4393 | (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz") | |
4394 | #t)))) | |
2c16316e RW |
4395 | (build-system python-build-system) |
4396 | (arguments | |
4397 | `(#:python ,python-2 | |
cdc2bb50 MB |
4398 | ;; FIXME: Tests fail with "No such file or directory: |
4399 | ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so" | |
4400 | #:tests? #f | |
2c16316e | 4401 | #:phases |
9a067efd RW |
4402 | (modify-phases %standard-phases |
4403 | (add-after 'unpack 'enter-directory | |
4404 | (lambda _ | |
4405 | (chdir "pbtranscript-tofu/pbtranscript/") | |
4406 | #t)) | |
4407 | ;; With setuptools version 18.0 and later this setup.py hack causes | |
4408 | ;; a build error, so we disable it. | |
4409 | (add-after 'enter-directory 'patch-setuppy | |
4410 | (lambda _ | |
4411 | (substitute* "setup.py" | |
4412 | (("if 'setuptools.extension' in sys.modules:") | |
4413 | "if False:")) | |
4414 | #t))))) | |
2c16316e | 4415 | (inputs |
9a067efd | 4416 | `(("python-numpy" ,python2-numpy) |
2c16316e | 4417 | ("python-bx-python" ,python2-bx-python) |
c5372108 RW |
4418 | ("python-networkx" ,python2-networkx) |
4419 | ("python-scipy" ,python2-scipy) | |
9a067efd RW |
4420 | ("python-pbcore" ,python2-pbcore) |
4421 | ("python-h5py" ,python2-h5py))) | |
2c16316e | 4422 | (native-inputs |
9a067efd | 4423 | `(("python-cython" ,python2-cython) |
f3b98f4f | 4424 | ("python-nose" ,python2-nose))) |
2c16316e RW |
4425 | (home-page "https://github.com/PacificBiosciences/cDNA_primer") |
4426 | (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol") | |
4427 | (description | |
4428 | "pbtranscript-tofu contains scripts to analyze transcriptome data | |
4429 | generated using the PacBio Iso-Seq protocol.") | |
4430 | (license license:bsd-3)))) | |
4431 | ||
024130d2 BW |
4432 | (define-public prank |
4433 | (package | |
4434 | (name "prank") | |
4435 | (version "150803") | |
4436 | (source (origin | |
4437 | (method url-fetch) | |
4438 | (uri (string-append | |
4439 | "http://wasabiapp.org/download/prank/prank.source." | |
4440 | version ".tgz")) | |
4441 | (sha256 | |
4442 | (base32 | |
4443 | "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4")))) | |
4444 | (build-system gnu-build-system) | |
4445 | (arguments | |
4446 | `(#:phases | |
4447 | (modify-phases %standard-phases | |
4448 | (add-after 'unpack 'enter-src-dir | |
4449 | (lambda _ | |
4450 | (chdir "src") | |
4451 | #t)) | |
62d00095 EF |
4452 | (add-after 'unpack 'remove-m64-flag |
4453 | ;; Prank will build with the correct 'bit-ness' without this flag | |
4454 | ;; and this allows building on 32-bit machines. | |
4455 | (lambda _ (substitute* "src/Makefile" | |
4456 | (("-m64") "")) | |
4457 | #t)) | |
024130d2 BW |
4458 | (delete 'configure) |
4459 | (replace 'install | |
4460 | (lambda* (#:key outputs #:allow-other-keys) | |
4461 | (let* ((out (assoc-ref outputs "out")) | |
4462 | (bin (string-append out "/bin")) | |
4463 | (man (string-append out "/share/man/man1")) | |
4464 | (path (string-append | |
4465 | (assoc-ref %build-inputs "mafft") "/bin:" | |
4466 | (assoc-ref %build-inputs "exonerate") "/bin:" | |
4467 | (assoc-ref %build-inputs "bppsuite") "/bin"))) | |
4468 | (install-file "prank" bin) | |
4469 | (wrap-program (string-append bin "/prank") | |
4470 | `("PATH" ":" prefix (,path))) | |
4471 | (install-file "prank.1" man)) | |
4472 | #t))))) | |
4473 | (inputs | |
4474 | `(("mafft" ,mafft) | |
4475 | ("exonerate" ,exonerate) | |
4476 | ("bppsuite" ,bppsuite))) | |
4477 | (home-page "http://wasabiapp.org/software/prank/") | |
4478 | (synopsis "Probabilistic multiple sequence alignment program") | |
4479 | (description | |
4480 | "PRANK is a probabilistic multiple sequence alignment program for DNA, | |
4481 | codon and amino-acid sequences. It is based on a novel algorithm that treats | |
4482 | insertions correctly and avoids over-estimation of the number of deletion | |
4483 | events. In addition, PRANK borrows ideas from maximum likelihood methods used | |
4484 | in phylogenetics and correctly takes into account the evolutionary distances | |
4485 | between sequences. Lastly, PRANK allows for defining a potential structure | |
4486 | for sequences to be aligned and then, simultaneously with the alignment, | |
4487 | predicts the locations of structural units in the sequences.") | |
4488 | (license license:gpl2+))) | |
4489 | ||
31a9d653 BW |
4490 | (define-public proteinortho |
4491 | (package | |
4492 | (name "proteinortho") | |
8c864901 | 4493 | (version "5.16b") |
31a9d653 BW |
4494 | (source |
4495 | (origin | |
4496 | (method url-fetch) | |
4497 | (uri | |
4498 | (string-append | |
4499 | "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v" | |
4500 | version "_src.tar.gz")) | |
4501 | (sha256 | |
4502 | (base32 | |
8c864901 | 4503 | "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j")))) |
31a9d653 BW |
4504 | (build-system gnu-build-system) |
4505 | (arguments | |
4506 | `(#:test-target "test" | |
4507 | #:phases | |
4508 | (modify-phases %standard-phases | |
4509 | (replace 'configure | |
4510 | ;; There is no configure script, so we modify the Makefile directly. | |
4511 | (lambda* (#:key outputs #:allow-other-keys) | |
4512 | (substitute* "Makefile" | |
4513 | (("INSTALLDIR=.*") | |
4514 | (string-append | |
4515 | "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n"))) | |
4516 | #t)) | |
4517 | (add-before 'install 'make-install-directory | |
4518 | ;; The install directory is not created during 'make install'. | |
4519 | (lambda* (#:key outputs #:allow-other-keys) | |
4520 | (mkdir-p (string-append (assoc-ref outputs "out") "/bin")) | |
4521 | #t)) | |
4522 | (add-after 'install 'wrap-programs | |
4523 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
4524 | (let* ((path (getenv "PATH")) | |
4525 | (out (assoc-ref outputs "out")) | |
4526 | (binary (string-append out "/bin/proteinortho5.pl"))) | |
4527 | (wrap-program binary `("PATH" ":" prefix (,path)))) | |
4528 | #t))))) | |
4529 | (inputs | |
4530 | `(("perl" ,perl) | |
4531 | ("python" ,python-2) | |
4532 | ("blast+" ,blast+))) | |
4533 | (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho") | |
4534 | (synopsis "Detect orthologous genes across species") | |
4535 | (description | |
4536 | "Proteinortho is a tool to detect orthologous genes across different | |
4537 | species. For doing so, it compares similarities of given gene sequences and | |
4538 | clusters them to find significant groups. The algorithm was designed to handle | |
4539 | large-scale data and can be applied to hundreds of species at once.") | |
4540 | (license license:gpl2+))) | |
4541 | ||
846e3409 RW |
4542 | (define-public pyicoteo |
4543 | (package | |
4544 | (name "pyicoteo") | |
4545 | (version "2.0.7") | |
4546 | (source | |
4547 | (origin | |
4548 | (method url-fetch) | |
4549 | (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/" | |
4550 | "pyicoteo/get/v" version ".tar.bz2")) | |
4551 | (file-name (string-append name "-" version ".tar.bz2")) | |
4552 | (sha256 | |
4553 | (base32 | |
4554 | "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa")))) | |
4555 | (build-system python-build-system) | |
4556 | (arguments | |
4557 | `(#:python ,python-2 ; does not work with Python 3 | |
4558 | #:tests? #f)) ; there are no tests | |
4559 | (inputs | |
4560 | `(("python2-matplotlib" ,python2-matplotlib))) | |
4561 | (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo") | |
4562 | (synopsis "Analyze high-throughput genetic sequencing data") | |
4563 | (description | |
4564 | "Pyicoteo is a suite of tools for the analysis of high-throughput genetic | |
4565 | sequencing data. It works with genomic coordinates. There are currently six | |
4566 | different command-line tools: | |
4567 | ||
4568 | @enumerate | |
4569 | @item pyicoregion: for generating exploratory regions automatically; | |
4570 | @item pyicoenrich: for differential enrichment between two conditions; | |
4571 | @item pyicoclip: for calling CLIP-Seq peaks without a control; | |
4572 | @item pyicos: for genomic coordinates manipulation; | |
4573 | @item pyicoller: for peak calling on punctuated ChIP-Seq; | |
4574 | @item pyicount: to count how many reads from N experiment files overlap in a | |
4575 | region file; | |
4576 | @item pyicotrocol: to combine operations from pyicoteo. | |
4577 | @end enumerate\n") | |
4578 | (license license:gpl3+))) | |
4579 | ||
af860475 BW |
4580 | (define-public prodigal |
4581 | (package | |
4582 | (name "prodigal") | |
e70f7a23 | 4583 | (version "2.6.3") |
af860475 BW |
4584 | (source (origin |
4585 | (method url-fetch) | |
4586 | (uri (string-append | |
4587 | "https://github.com/hyattpd/Prodigal/archive/v" | |
4588 | version ".tar.gz")) | |
4589 | (file-name (string-append name "-" version ".tar.gz")) | |
4590 | (sha256 | |
4591 | (base32 | |
e70f7a23 | 4592 | "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9")))) |
af860475 BW |
4593 | (build-system gnu-build-system) |
4594 | (arguments | |
4595 | `(#:tests? #f ;no check target | |
4596 | #:make-flags (list (string-append "INSTALLDIR=" | |
4597 | (assoc-ref %outputs "out") | |
4598 | "/bin")) | |
4599 | #:phases | |
4600 | (modify-phases %standard-phases | |
4601 | (delete 'configure)))) | |
4602 | (home-page "http://prodigal.ornl.gov") | |
4603 | (synopsis "Protein-coding gene prediction for Archaea and Bacteria") | |
4604 | (description | |
4605 | "Prodigal runs smoothly on finished genomes, draft genomes, and | |
4606 | metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table | |
4607 | format. It runs quickly, in an unsupervised fashion, handles gaps, handles | |
4608 | partial genes, and identifies translation initiation sites.") | |
4609 | (license license:gpl3+))) | |
608dd932 | 4610 | |
ceb62d54 BW |
4611 | (define-public roary |
4612 | (package | |
4613 | (name "roary") | |
dad9556c | 4614 | (version "3.12.0") |
ceb62d54 BW |
4615 | (source |
4616 | (origin | |
4617 | (method url-fetch) | |
4618 | (uri (string-append | |
4619 | "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-" | |
4620 | version ".tar.gz")) | |
4621 | (sha256 | |
4622 | (base32 | |
dad9556c | 4623 | "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff")))) |
ceb62d54 BW |
4624 | (build-system perl-build-system) |
4625 | (arguments | |
4626 | `(#:phases | |
4627 | (modify-phases %standard-phases | |
4628 | (delete 'configure) | |
4629 | (delete 'build) | |
4630 | (replace 'check | |
4631 | (lambda _ | |
4632 | ;; The tests are not run by default, so we run each test file | |
4633 | ;; directly. | |
4634 | (setenv "PATH" (string-append (getcwd) "/bin" ":" | |
4635 | (getenv "PATH"))) | |
4636 | (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":" | |
4637 | (getenv "PERL5LIB"))) | |
4638 | (zero? (length (filter (lambda (file) | |
4639 | (display file)(display "\n") | |
4640 | (not (zero? (system* "perl" file)))) | |
4641 | (find-files "t" ".*\\.t$")))))) | |
4642 | (replace 'install | |
4643 | ;; There is no 'install' target in the Makefile. | |
4644 | (lambda* (#:key outputs #:allow-other-keys) | |
4645 | (let* ((out (assoc-ref outputs "out")) | |
4646 | (bin (string-append out "/bin")) | |
4647 | (perl (string-append out "/lib/perl5/site_perl")) | |
4648 | (roary-plots "contrib/roary_plots")) | |
4649 | (mkdir-p bin) | |
4650 | (mkdir-p perl) | |
4651 | (copy-recursively "bin" bin) | |
4652 | (copy-recursively "lib" perl) | |
4653 | #t))) | |
4654 | (add-after 'install 'wrap-programs | |
4655 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
4656 | (let* ((out (assoc-ref outputs "out")) | |
4657 | (perl5lib (getenv "PERL5LIB")) | |
4658 | (path (getenv "PATH"))) | |
4659 | (for-each (lambda (prog) | |
4660 | (let ((binary (string-append out "/" prog))) | |
4661 | (wrap-program binary | |
4662 | `("PERL5LIB" ":" prefix | |
4663 | (,(string-append perl5lib ":" out | |
4664 | "/lib/perl5/site_perl")))) | |
4665 | (wrap-program binary | |
4666 | `("PATH" ":" prefix | |
4667 | (,(string-append path ":" out "/bin")))))) | |
4668 | (find-files "bin" ".*[^R]$")) | |
4669 | (let ((file | |
4670 | (string-append out "/bin/roary-create_pan_genome_plots.R")) | |
4671 | (r-site-lib (getenv "R_LIBS_SITE")) | |
4672 | (coreutils-path | |
4673 | (string-append (assoc-ref inputs "coreutils") "/bin"))) | |
4674 | (wrap-program file | |
4675 | `("R_LIBS_SITE" ":" prefix | |
4676 | (,(string-append r-site-lib ":" out "/site-library/")))) | |
4677 | (wrap-program file | |
4678 | `("PATH" ":" prefix | |
4679 | (,(string-append coreutils-path ":" out "/bin")))))) | |
4680 | #t))))) | |
4681 | (native-inputs | |
4682 | `(("perl-env-path" ,perl-env-path) | |
4683 | ("perl-test-files" ,perl-test-files) | |
4684 | ("perl-test-most" ,perl-test-most) | |
4685 | ("perl-test-output" ,perl-test-output))) | |
4686 | (inputs | |
4687 | `(("perl-array-utils" ,perl-array-utils) | |
4688 | ("bioperl" ,bioperl-minimal) | |
da4a707c | 4689 | ("perl-digest-md5-file" ,perl-digest-md5-file) |
ceb62d54 BW |
4690 | ("perl-exception-class" ,perl-exception-class) |
4691 | ("perl-file-find-rule" ,perl-file-find-rule) | |
4692 | ("perl-file-grep" ,perl-file-grep) | |
4693 | ("perl-file-slurper" ,perl-file-slurper) | |
4694 | ("perl-file-which" ,perl-file-which) | |
4695 | ("perl-graph" ,perl-graph) | |
4696 | ("perl-graph-readwrite" ,perl-graph-readwrite) | |
4697 | ("perl-log-log4perl" ,perl-log-log4perl) | |
4698 | ("perl-moose" ,perl-moose) | |
4699 | ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict) | |
4700 | ("perl-text-csv" ,perl-text-csv) | |
4701 | ("bedtools" ,bedtools) | |
4702 | ("cd-hit" ,cd-hit) | |
4703 | ("blast+" ,blast+) | |
4704 | ("mcl" ,mcl) | |
4705 | ("parallel" ,parallel) | |
4706 | ("prank" ,prank) | |
4707 | ("mafft" ,mafft) | |
4708 | ("fasttree" ,fasttree) | |
4709 | ("grep" ,grep) | |
4710 | ("sed" ,sed) | |
4711 | ("gawk" ,gawk) | |
2d7c4ae3 | 4712 | ("r-minimal" ,r-minimal) |
ceb62d54 BW |
4713 | ("r-ggplot2" ,r-ggplot2) |
4714 | ("coreutils" ,coreutils))) | |
4715 | (home-page "http://sanger-pathogens.github.io/Roary") | |
4716 | (synopsis "High speed stand-alone pan genome pipeline") | |
4717 | (description | |
4718 | "Roary is a high speed stand alone pan genome pipeline, which takes | |
4719 | annotated assemblies in GFF3 format (produced by the Prokka program) and | |
4720 | calculates the pan genome. Using a standard desktop PC, it can analyse | |
4721 | datasets with thousands of samples, without compromising the quality of the | |
4722 | results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a | |
4723 | single processor. Roary is not intended for metagenomics or for comparing | |
4724 | extremely diverse sets of genomes.") | |
4725 | (license license:gpl3))) | |
4726 | ||
608dd932 BW |
4727 | (define-public raxml |
4728 | (package | |
4729 | (name "raxml") | |
e9e0fab0 | 4730 | (version "8.2.10") |
608dd932 BW |
4731 | (source |
4732 | (origin | |
4733 | (method url-fetch) | |
4734 | (uri | |
4735 | (string-append | |
4736 | "https://github.com/stamatak/standard-RAxML/archive/v" | |
4737 | version ".tar.gz")) | |
4738 | (file-name (string-append name "-" version ".tar.gz")) | |
4739 | (sha256 | |
4740 | (base32 | |
e9e0fab0 | 4741 | "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8")))) |
608dd932 BW |
4742 | (build-system gnu-build-system) |
4743 | (arguments | |
4744 | `(#:tests? #f ; There are no tests. | |
4745 | ;; Use 'standard' Makefile rather than SSE or AVX ones. | |
4746 | #:make-flags (list "-f" "Makefile.HYBRID.gcc") | |
4747 | #:phases | |
4748 | (modify-phases %standard-phases | |
4749 | (delete 'configure) | |
4750 | (replace 'install | |
4751 | (lambda* (#:key outputs #:allow-other-keys) | |
4752 | (let* ((out (assoc-ref outputs "out")) | |
4753 | (bin (string-append out "/bin")) | |
4754 | (executable "raxmlHPC-HYBRID")) | |
4755 | (install-file executable bin) | |
4756 | (symlink (string-append bin "/" executable) "raxml")) | |
4757 | #t))))) | |
4758 | (inputs | |
4759 | `(("openmpi" ,openmpi))) | |
4760 | (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html") | |
4761 | (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees") | |
4762 | (description | |
4763 | "RAxML is a tool for phylogenetic analysis and post-analysis of large | |
4764 | phylogenies.") | |
2805f9b2 EF |
4765 | ;; The source includes x86 specific code |
4766 | (supported-systems '("x86_64-linux" "i686-linux")) | |
608dd932 | 4767 | (license license:gpl2+))) |
af860475 | 4768 | |
66e3eff1 RW |
4769 | (define-public rsem |
4770 | (package | |
4771 | (name "rsem") | |
4772 | (version "1.2.20") | |
4773 | (source | |
4774 | (origin | |
4775 | (method url-fetch) | |
4776 | (uri | |
4777 | (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-" | |
4778 | version ".tar.gz")) | |
4779 | (sha256 | |
4780 | (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q")) | |
fc1adab1 | 4781 | (patches (search-patches "rsem-makefile.patch")) |
66e3eff1 RW |
4782 | (modules '((guix build utils))) |
4783 | (snippet | |
4784 | '(begin | |
4785 | ;; remove bundled copy of boost | |
4786 | (delete-file-recursively "boost") | |
4787 | #t)))) | |
4788 | (build-system gnu-build-system) | |
4789 | (arguments | |
4790 | `(#:tests? #f ;no "check" target | |
4791 | #:phases | |
4792 | (modify-phases %standard-phases | |
4793 | ;; No "configure" script. | |
4794 | ;; Do not build bundled samtools library. | |
4795 | (replace 'configure | |
4796 | (lambda _ | |
4797 | (substitute* "Makefile" | |
4798 | (("^all : sam/libbam.a") "all : ")) | |
4799 | #t)) | |
4800 | (replace 'install | |
4801 | (lambda* (#:key outputs #:allow-other-keys) | |
4802 | (let* ((out (string-append (assoc-ref outputs "out"))) | |
4803 | (bin (string-append out "/bin/")) | |
4804 | (perl (string-append out "/lib/perl5/site_perl"))) | |
4805 | (mkdir-p bin) | |
4806 | (mkdir-p perl) | |
4807 | (for-each (lambda (file) | |
f3860753 | 4808 | (install-file file bin)) |
66e3eff1 | 4809 | (find-files "." "rsem-.*")) |
f3860753 | 4810 | (install-file "rsem_perl_utils.pm" perl)) |
66e3eff1 RW |
4811 | #t)) |
4812 | (add-after | |
4813 | 'install 'wrap-program | |
4814 | (lambda* (#:key outputs #:allow-other-keys) | |
4815 | (let ((out (assoc-ref outputs "out"))) | |
4816 | (for-each (lambda (prog) | |
4817 | (wrap-program (string-append out "/bin/" prog) | |
4818 | `("PERL5LIB" ":" prefix | |
4819 | (,(string-append out "/lib/perl5/site_perl"))))) | |
4820 | '("rsem-plot-transcript-wiggles" | |
4821 | "rsem-calculate-expression" | |
4822 | "rsem-generate-ngvector" | |
4823 | "rsem-run-ebseq" | |
4824 | "rsem-prepare-reference"))) | |
4825 | #t))))) | |
4826 | (inputs | |
4827 | `(("boost" ,boost) | |
4828 | ("ncurses" ,ncurses) | |
2d7c4ae3 | 4829 | ("r-minimal" ,r-minimal) |
66e3eff1 RW |
4830 | ("perl" ,perl) |
4831 | ("samtools" ,samtools-0.1) | |
4832 | ("zlib" ,zlib))) | |
4833 | (home-page "http://deweylab.biostat.wisc.edu/rsem/") | |
4834 | (synopsis "Estimate gene expression levels from RNA-Seq data") | |
4835 | (description | |
4836 | "RSEM is a software package for estimating gene and isoform expression | |
4837 | levels from RNA-Seq data. The RSEM package provides a user-friendly | |
4838 | interface, supports threads for parallel computation of the EM algorithm, | |
4839 | single-end and paired-end read data, quality scores, variable-length reads and | |
4840 | RSPD estimation. In addition, it provides posterior mean and 95% credibility | |
4841 | interval estimates for expression levels. For visualization, it can generate | |
4842 | BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.") | |
4843 | (license license:gpl3+))) | |
4844 | ||
8622a072 RW |
4845 | (define-public rseqc |
4846 | (package | |
4847 | (name "rseqc") | |
4848 | (version "2.6.1") | |
4849 | (source | |
4850 | (origin | |
4851 | (method url-fetch) | |
4852 | (uri | |
4853 | (string-append "mirror://sourceforge/rseqc/" | |
de67e922 | 4854 | "RSeQC-" version ".tar.gz")) |
8622a072 | 4855 | (sha256 |
8214b7fb | 4856 | (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330")) |
8622a072 RW |
4857 | (modules '((guix build utils))) |
4858 | (snippet | |
4859 | '(begin | |
4860 | ;; remove bundled copy of pysam | |
4861 | (delete-file-recursively "lib/pysam") | |
4862 | (substitute* "setup.py" | |
4863 | ;; remove dependency on outdated "distribute" module | |
4864 | (("^from distribute_setup import use_setuptools") "") | |
4865 | (("^use_setuptools\\(\\)") "") | |
4866 | ;; do not use bundled copy of pysam | |
4867 | (("^have_pysam = False") "have_pysam = True")))))) | |
4868 | (build-system python-build-system) | |
4869 | (arguments `(#:python ,python-2)) | |
4870 | (inputs | |
4871 | `(("python-cython" ,python2-cython) | |
4872 | ("python-pysam" ,python2-pysam) | |
4873 | ("python-numpy" ,python2-numpy) | |
8622a072 RW |
4874 | ("zlib" ,zlib))) |
4875 | (native-inputs | |
4876 | `(("python-nose" ,python2-nose))) | |
4877 | (home-page "http://rseqc.sourceforge.net/") | |
4878 | (synopsis "RNA-seq quality control package") | |
4879 | (description | |
4880 | "RSeQC provides a number of modules that can comprehensively evaluate | |
4881 | high throughput sequence data, especially RNA-seq data. Some basic modules | |
4882 | inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, | |
4883 | while RNA-seq specific modules evaluate sequencing saturation, mapped reads | |
4884 | distribution, coverage uniformity, strand specificity, etc.") | |
4885 | (license license:gpl3+))) | |
4886 | ||
ec946638 RW |
4887 | (define-public seek |
4888 | ;; There are no release tarballs. According to the installation | |
4889 | ;; instructions at http://seek.princeton.edu/installation.jsp, the latest | |
4890 | ;; stable release is identified by this changeset ID. | |
4891 | (let ((changeset "2329130") | |
4892 | (revision "1")) | |
4893 | (package | |
4894 | (name "seek") | |
4895 | (version (string-append "0-" revision "." changeset)) | |
4896 | (source (origin | |
4897 | (method hg-fetch) | |
4898 | (uri (hg-reference | |
4899 | (url "https://bitbucket.org/libsleipnir/sleipnir") | |
4900 | (changeset changeset))) | |
51106724 | 4901 | (file-name (string-append name "-" version "-checkout")) |
ec946638 RW |
4902 | (sha256 |
4903 | (base32 | |
4904 | "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx")))) | |
4905 | (build-system gnu-build-system) | |
4906 | (arguments | |
4907 | `(#:modules ((srfi srfi-1) | |
4908 | (guix build gnu-build-system) | |
4909 | (guix build utils)) | |
4910 | #:phases | |
4911 | (let ((dirs '("SeekMiner" | |
4912 | "SeekEvaluator" | |
4913 | "SeekPrep" | |
4914 | "Distancer" | |
4915 | "Data2DB" | |
4916 | "PCL2Bin"))) | |
4917 | (modify-phases %standard-phases | |
4561498e | 4918 | (add-before 'configure 'bootstrap |
ec946638 RW |
4919 | (lambda _ |
4920 | (zero? (system* "bash" "gen_auto")))) | |
4921 | (add-after 'build 'build-additional-tools | |
4922 | (lambda* (#:key make-flags #:allow-other-keys) | |
4923 | (every (lambda (dir) | |
4924 | (with-directory-excursion (string-append "tools/" dir) | |
4925 | (zero? (apply system* "make" make-flags)))) | |
4926 | dirs))) | |
4927 | (add-after 'install 'install-additional-tools | |
4928 | (lambda* (#:key make-flags #:allow-other-keys) | |
4929 | (fold (lambda (dir result) | |
4930 | (with-directory-excursion (string-append "tools/" dir) | |
4931 | (and result | |
4932 | (zero? (apply system* | |
4933 | `("make" ,@make-flags "install")))))) | |
4934 | #t dirs))))))) | |
4935 | (inputs | |
4936 | `(("gsl" ,gsl) | |
4937 | ("boost" ,boost) | |
4938 | ("libsvm" ,libsvm) | |
4939 | ("readline" ,readline) | |
4940 | ("gengetopt" ,gengetopt) | |
4941 | ("log4cpp" ,log4cpp))) | |
4942 | (native-inputs | |
4943 | `(("autoconf" ,autoconf) | |
4944 | ("automake" ,automake) | |
4945 | ("perl" ,perl))) | |
4946 | (home-page "http://seek.princeton.edu") | |
4947 | (synopsis "Gene co-expression search engine") | |
4948 | (description | |
4949 | "SEEK is a computational gene co-expression search engine. SEEK provides | |
4950 | biologists with a way to navigate the massive human expression compendium that | |
4951 | now contains thousands of expression datasets. SEEK returns a robust ranking | |
4952 | of co-expressed genes in the biological area of interest defined by the user's | |
4953 | query genes. It also prioritizes thousands of expression datasets according | |
4954 | to the user's query of interest.") | |
4955 | (license license:cc-by3.0)))) | |
4956 | ||
4e10a221 RW |
4957 | (define-public samtools |
4958 | (package | |
4959 | (name "samtools") | |
c829c5ea | 4960 | (version "1.8") |
4e10a221 RW |
4961 | (source |
4962 | (origin | |
4963 | (method url-fetch) | |
4964 | (uri | |
de67e922 | 4965 | (string-append "mirror://sourceforge/samtools/samtools/" |
4e10a221 RW |
4966 | version "/samtools-" version ".tar.bz2")) |
4967 | (sha256 | |
4968 | (base32 | |
c829c5ea | 4969 | "05myg7bs90i68qbqab9cdg9rqj2xh39azibrx82ipzc5kcfvqhn9")))) |
4e10a221 RW |
4970 | (build-system gnu-build-system) |
4971 | (arguments | |
c4473411 | 4972 | `(#:modules ((ice-9 ftw) |
5bdda30b RW |
4973 | (ice-9 regex) |
4974 | (guix build gnu-build-system) | |
4975 | (guix build utils)) | |
c4473411 | 4976 | #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out"))) |
4ab16440 | 4977 | #:configure-flags (list "--with-ncurses" "--with-htslib=system") |
4e10a221 | 4978 | #:phases |
c842d425 BW |
4979 | (modify-phases %standard-phases |
4980 | (add-after 'unpack 'patch-tests | |
4981 | (lambda _ | |
4982 | (substitute* "test/test.pl" | |
4983 | ;; The test script calls out to /bin/bash | |
4984 | (("/bin/bash") (which "bash"))) | |
b2d748ed | 4985 | #t)) |
c842d425 BW |
4986 | (add-after 'install 'install-library |
4987 | (lambda* (#:key outputs #:allow-other-keys) | |
4988 | (let ((lib (string-append (assoc-ref outputs "out") "/lib"))) | |
4989 | (install-file "libbam.a" lib) | |
4990 | #t))) | |
4991 | (add-after 'install 'install-headers | |
4992 | (lambda* (#:key outputs #:allow-other-keys) | |
4993 | (let ((include (string-append (assoc-ref outputs "out") | |
4994 | "/include/samtools/"))) | |
4995 | (for-each (lambda (file) | |
4996 | (install-file file include)) | |
4997 | (scandir "." (lambda (name) (string-match "\\.h$" name)))) | |
4998 | #t)))))) | |
4e10a221 | 4999 | (native-inputs `(("pkg-config" ,pkg-config))) |
4ab16440 BW |
5000 | (inputs |
5001 | `(("htslib" ,htslib) | |
5002 | ("ncurses" ,ncurses) | |
5003 | ("perl" ,perl) | |
5004 | ("python" ,python) | |
5005 | ("zlib" ,zlib))) | |
4e10a221 RW |
5006 | (home-page "http://samtools.sourceforge.net") |
5007 | (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments") | |
5008 | (description | |
5009 | "Samtools implements various utilities for post-processing nucleotide | |
5010 | sequence alignments in the SAM, BAM, and CRAM formats, including indexing, | |
5011 | variant calling (in conjunction with bcftools), and a simple alignment | |
5012 | viewer.") | |
5013 | (license license:expat))) | |
d3517eda | 5014 | |
0b84a0aa RW |
5015 | (define-public samtools-0.1 |
5016 | ;; This is the most recent version of the 0.1 line of samtools. The input | |
5017 | ;; and output formats differ greatly from that used and produced by samtools | |
5018 | ;; 1.x and is still used in many bioinformatics pipelines. | |
5019 | (package (inherit samtools) | |
5020 | (version "0.1.19") | |
5021 | (source | |
5022 | (origin | |
5023 | (method url-fetch) | |
5024 | (uri | |
de67e922 | 5025 | (string-append "mirror://sourceforge/samtools/samtools/" |
0b84a0aa RW |
5026 | version "/samtools-" version ".tar.bz2")) |
5027 | (sha256 | |
5028 | (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h")))) | |
5029 | (arguments | |
2309ed68 RW |
5030 | `(#:tests? #f ;no "check" target |
5031 | ,@(substitute-keyword-arguments (package-arguments samtools) | |
5032 | ((#:make-flags flags) | |
5033 | `(cons "LIBCURSES=-lncurses" ,flags)) | |
5034 | ((#:phases phases) | |
5035 | `(modify-phases ,phases | |
5036 | (replace 'install | |
5037 | (lambda* (#:key outputs #:allow-other-keys) | |
5038 | (let ((bin (string-append | |
5039 | (assoc-ref outputs "out") "/bin"))) | |
5040 | (mkdir-p bin) | |
f3860753 | 5041 | (install-file "samtools" bin) |
b2d748ed | 5042 | #t))) |
2309ed68 RW |
5043 | (delete 'patch-tests) |
5044 | (delete 'configure)))))))) | |
0b84a0aa | 5045 | |
fe4c37c2 | 5046 | (define-public mosaik |
698bd297 | 5047 | (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67")) |
fe4c37c2 RW |
5048 | (package |
5049 | (name "mosaik") | |
5050 | (version "2.2.30") | |
5051 | (source (origin | |
5052 | ;; There are no release tarballs nor tags. | |
5053 | (method git-fetch) | |
5054 | (uri (git-reference | |
5055 | (url "https://github.com/wanpinglee/MOSAIK.git") | |
5056 | (commit commit))) | |
5057 | (file-name (string-append name "-" version)) | |
5058 | (sha256 | |
5059 | (base32 | |
5060 | "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw")))) | |
5061 | (build-system gnu-build-system) | |
5062 | (arguments | |
5063 | `(#:tests? #f ; no tests | |
5064 | #:make-flags (list "CC=gcc") | |
5065 | #:phases | |
5066 | (modify-phases %standard-phases | |
5067 | (replace 'configure | |
5068 | (lambda _ (chdir "src") #t)) | |
5069 | (replace 'install | |
5070 | (lambda* (#:key outputs #:allow-other-keys) | |
5071 | (let ((bin (string-append (assoc-ref outputs "out") | |
5072 | "/bin"))) | |
5073 | (mkdir-p bin) | |
5074 | (copy-recursively "../bin" bin) | |
5075 | #t)))))) | |
5076 | (inputs | |
5077 | `(("perl" ,perl) | |
5078 | ("zlib" ,zlib))) | |
029d9f77 | 5079 | (supported-systems '("x86_64-linux")) |
0c6c9c00 | 5080 | (home-page "https://github.com/wanpinglee/MOSAIK") |
fe4c37c2 RW |
5081 | (synopsis "Map nucleotide sequence reads to reference genomes") |
5082 | (description | |
5083 | "MOSAIK is a program for mapping second and third-generation sequencing | |
5084 | reads to a reference genome. MOSAIK can align reads generated by all the | |
5085 | major sequencing technologies, including Illumina, Applied Biosystems SOLiD, | |
5086 | Roche 454, Ion Torrent and Pacific BioSciences SMRT.") | |
5087 | ;; MOSAIK is released under the GPLv2+ with the exception of third-party | |
5088 | ;; code released into the public domain: | |
5089 | ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/ | |
5090 | ;; 2. MD5 implementation - RSA Data Security, RFC 1321 | |
5091 | (license (list license:gpl2+ license:public-domain))))) | |
5092 | ||
282c5087 RW |
5093 | (define-public ngs-sdk |
5094 | (package | |
5095 | (name "ngs-sdk") | |
6c4ccf32 | 5096 | (version "1.3.0") |
282c5087 RW |
5097 | (source |
5098 | (origin | |
5099 | (method url-fetch) | |
5100 | (uri | |
5101 | (string-append "https://github.com/ncbi/ngs/archive/" | |
5102 | version ".tar.gz")) | |
5103 | (file-name (string-append name "-" version ".tar.gz")) | |
5104 | (sha256 | |
5105 | (base32 | |
6c4ccf32 | 5106 | "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40")))) |
282c5087 RW |
5107 | (build-system gnu-build-system) |
5108 | (arguments | |
5109 | `(#:parallel-build? #f ; not supported | |
5110 | #:tests? #f ; no "check" target | |
5111 | #:phases | |
dc1d3cde KK |
5112 | (modify-phases %standard-phases |
5113 | (replace 'configure | |
5114 | (lambda* (#:key outputs #:allow-other-keys) | |
5115 | (let ((out (assoc-ref outputs "out"))) | |
5116 | ;; Allow 'konfigure.perl' to find 'package.prl'. | |
5117 | (setenv "PERL5LIB" | |
5118 | (string-append ".:" (getenv "PERL5LIB"))) | |
5119 | ||
5120 | ;; The 'configure' script doesn't recognize things like | |
5121 | ;; '--enable-fast-install'. | |
5122 | (zero? (system* "./configure" | |
5123 | (string-append "--build-prefix=" (getcwd) "/build") | |
5124 | (string-append "--prefix=" out)))))) | |
5125 | (add-after 'unpack 'enter-dir | |
5126 | (lambda _ (chdir "ngs-sdk") #t))))) | |
282c5087 | 5127 | (native-inputs `(("perl" ,perl))) |
a0dadf0c AE |
5128 | ;; According to the test |
5129 | ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i) | |
5130 | ;; in ngs-sdk/setup/konfigure.perl | |
ab29be81 | 5131 | (supported-systems '("i686-linux" "x86_64-linux")) |
282c5087 RW |
5132 | (home-page "https://github.com/ncbi/ngs") |
5133 | (synopsis "API for accessing Next Generation Sequencing data") | |
5134 | (description | |
5135 | "NGS is a domain-specific API for accessing reads, alignments and pileups | |
5136 | produced from Next Generation Sequencing. The API itself is independent from | |
5137 | any particular back-end implementation, and supports use of multiple back-ends | |
5138 | simultaneously.") | |
5139 | (license license:public-domain))) | |
5140 | ||
1ad15c16 | 5141 | (define-public java-ngs |
2651a5e6 | 5142 | (package (inherit ngs-sdk) |
1ad15c16 | 5143 | (name "java-ngs") |
2651a5e6 RW |
5144 | (arguments |
5145 | `(,@(substitute-keyword-arguments | |
5146 | `(#:modules ((guix build gnu-build-system) | |
5147 | (guix build utils) | |
5148 | (srfi srfi-1) | |
5149 | (srfi srfi-26)) | |
5150 | ,@(package-arguments ngs-sdk)) | |
5151 | ((#:phases phases) | |
614a8977 RW |
5152 | `(modify-phases ,phases |
5153 | (replace 'enter-dir (lambda _ (chdir "ngs-java") #t))))))) | |
2651a5e6 | 5154 | (inputs |
d2540f80 | 5155 | `(("jdk" ,icedtea "jdk") |
2651a5e6 RW |
5156 | ("ngs-sdk" ,ngs-sdk))) |
5157 | (synopsis "Java bindings for NGS SDK"))) | |
5158 | ||
75dd2424 RW |
5159 | (define-public ncbi-vdb |
5160 | (package | |
5161 | (name "ncbi-vdb") | |
5021f547 | 5162 | (version "2.8.2") |
75dd2424 RW |
5163 | (source |
5164 | (origin | |
5165 | (method url-fetch) | |
5166 | (uri | |
5167 | (string-append "https://github.com/ncbi/ncbi-vdb/archive/" | |
5168 | version ".tar.gz")) | |
5169 | (file-name (string-append name "-" version ".tar.gz")) | |
5170 | (sha256 | |
5171 | (base32 | |
5021f547 | 5172 | "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m")))) |
75dd2424 RW |
5173 | (build-system gnu-build-system) |
5174 | (arguments | |
5175 | `(#:parallel-build? #f ; not supported | |
5176 | #:tests? #f ; no "check" target | |
5177 | #:phases | |
70111198 | 5178 | (modify-phases %standard-phases |
0691851a BW |
5179 | (add-before 'configure 'set-perl-search-path |
5180 | (lambda _ | |
5181 | ;; Work around "dotless @INC" build failure. | |
5182 | (setenv "PERL5LIB" | |
5183 | (string-append (getcwd) "/setup:" | |
5184 | (getenv "PERL5LIB"))) | |
5185 | #t)) | |
70111198 RW |
5186 | (replace 'configure |
5187 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
5188 | (let ((out (assoc-ref outputs "out"))) | |
5189 | ;; Override include path for libmagic | |
5190 | (substitute* "setup/package.prl" | |
5191 | (("name => 'magic', Include => '/usr/include'") | |
5192 | (string-append "name=> 'magic', Include => '" | |
5193 | (assoc-ref inputs "libmagic") | |
5194 | "/include" "'"))) | |
75dd2424 | 5195 | |
70111198 RW |
5196 | ;; Install kdf5 library (needed by sra-tools) |
5197 | (substitute* "build/Makefile.install" | |
5198 | (("LIBRARIES_TO_INSTALL =") | |
5199 | "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)")) | |
75dd2424 | 5200 | |
70111198 RW |
5201 | (substitute* "build/Makefile.env" |
5202 | (("CFLAGS =" prefix) | |
5203 | (string-append prefix "-msse2 "))) | |
675d7ae2 | 5204 | |
558e2307 RW |
5205 | ;; Override search path for ngs-java |
5206 | (substitute* "setup/package.prl" | |
5207 | (("/usr/local/ngs/ngs-java") | |
5208 | (assoc-ref inputs "java-ngs"))) | |
5209 | ||
70111198 RW |
5210 | ;; The 'configure' script doesn't recognize things like |
5211 | ;; '--enable-fast-install'. | |
5212 | (zero? (system* | |
5213 | "./configure" | |
5214 | (string-append "--build-prefix=" (getcwd) "/build") | |
5215 | (string-append "--prefix=" (assoc-ref outputs "out")) | |
5216 | (string-append "--debug") | |
5217 | (string-append "--with-xml2-prefix=" | |
5218 | (assoc-ref inputs "libxml2")) | |
5219 | (string-append "--with-ngs-sdk-prefix=" | |
5220 | (assoc-ref inputs "ngs-sdk")) | |
70111198 RW |
5221 | (string-append "--with-hdf5-prefix=" |
5222 | (assoc-ref inputs "hdf5"))))))) | |
5223 | (add-after 'install 'install-interfaces | |
5224 | (lambda* (#:key outputs #:allow-other-keys) | |
5225 | ;; Install interface libraries. On i686 the interface libraries | |
5226 | ;; are installed to "linux/gcc/i386", so we need to use the Linux | |
5227 | ;; architecture name ("i386") instead of the target system prefix | |
5228 | ;; ("i686"). | |
5229 | (mkdir (string-append (assoc-ref outputs "out") "/ilib")) | |
5230 | (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/" | |
5231 | ,(system->linux-architecture | |
5232 | (or (%current-target-system) | |
5233 | (%current-system))) | |
5234 | "/rel/ilib") | |
5235 | (string-append (assoc-ref outputs "out") | |
5236 | "/ilib")) | |
5237 | ;; Install interface headers | |
5238 | (copy-recursively "interfaces" | |
5239 | (string-append (assoc-ref outputs "out") | |
5240 | "/include")) | |
d5e17162 RW |
5241 | #t)) |
5242 | ;; These files are needed by sra-tools. | |
5243 | (add-after 'install 'install-configuration-files | |
5244 | (lambda* (#:key outputs #:allow-other-keys) | |
5245 | (let ((target (string-append (assoc-ref outputs "out") "/kfg"))) | |
5246 | (mkdir target) | |
5247 | (install-file "libs/kfg/default.kfg" target) | |
5248 | (install-file "libs/kfg/certs.kfg" target)) | |
70111198 | 5249 | #t))))) |
75dd2424 RW |
5250 | (inputs |
5251 | `(("libxml2" ,libxml2) | |
5252 | ("ngs-sdk" ,ngs-sdk) | |
1ad15c16 | 5253 | ("java-ngs" ,java-ngs) |
75dd2424 RW |
5254 | ("libmagic" ,file) |
5255 | ("hdf5" ,hdf5))) | |
5256 | (native-inputs `(("perl" ,perl))) | |
675d7ae2 RW |
5257 | ;; NCBI-VDB requires SSE capability. |
5258 | (supported-systems '("i686-linux" "x86_64-linux")) | |
75dd2424 RW |
5259 | (home-page "https://github.com/ncbi/ncbi-vdb") |
5260 | (synopsis "Database engine for genetic information") | |
5261 | (description | |
5262 | "The NCBI-VDB library implements a highly compressed columnar data | |
5263 | warehousing engine that is most often used to store genetic information. | |
5264 | Databases are stored in a portable image within the file system, and can be | |
5265 | accessed/downloaded on demand across HTTP.") | |
5266 | (license license:public-domain))) | |
5267 | ||
cc6ed477 RW |
5268 | (define-public plink |
5269 | (package | |
5270 | (name "plink") | |
5271 | (version "1.07") | |
5272 | (source | |
5273 | (origin | |
5274 | (method url-fetch) | |
5275 | (uri (string-append | |
5276 | "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-" | |
5277 | version "-src.zip")) | |
5278 | (sha256 | |
5279 | (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa")) | |
0dbb7ac2 EF |
5280 | (patches (search-patches "plink-1.07-unclobber-i.patch" |
5281 | "plink-endian-detection.patch")))) | |
cc6ed477 RW |
5282 | (build-system gnu-build-system) |
5283 | (arguments | |
5284 | '(#:tests? #f ;no "check" target | |
5285 | #:make-flags (list (string-append "LIB_LAPACK=" | |
5286 | (assoc-ref %build-inputs "lapack") | |
5287 | "/lib/liblapack.so") | |
5288 | "WITH_LAPACK=1" | |
5289 | "FORCE_DYNAMIC=1" | |
5290 | ;; disable phoning home | |
5291 | "WITH_WEBCHECK=") | |
5292 | #:phases | |
5293 | (modify-phases %standard-phases | |
5294 | ;; no "configure" script | |
5295 | (delete 'configure) | |
5296 | (replace 'install | |
5297 | (lambda* (#:key outputs #:allow-other-keys) | |
5298 | (let ((bin (string-append (assoc-ref outputs "out") | |
5299 | "/bin/"))) | |
96c46210 | 5300 | (install-file "plink" bin) |
cc6ed477 RW |
5301 | #t)))))) |
5302 | (inputs | |
5303 | `(("zlib" ,zlib) | |
5304 | ("lapack" ,lapack))) | |
5305 | (native-inputs | |
5306 | `(("unzip" ,unzip))) | |
5307 | (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/") | |
5308 | (synopsis "Whole genome association analysis toolset") | |
5309 | (description | |
5310 | "PLINK is a whole genome association analysis toolset, designed to | |
5311 | perform a range of basic, large-scale analyses in a computationally efficient | |
5312 | manner. The focus of PLINK is purely on analysis of genotype/phenotype data, | |
5313 | so there is no support for steps prior to this (e.g. study design and | |
5314 | planning, generating genotype or CNV calls from raw data). Through | |
5315 | integration with gPLINK and Haploview, there is some support for the | |
5316 | subsequent visualization, annotation and storage of results.") | |
5317 | ;; Code is released under GPLv2, except for fisher.h, which is under | |
5318 | ;; LGPLv2.1+ | |
5319 | (license (list license:gpl2 license:lgpl2.1+)))) | |
5320 | ||
dad66da4 RW |
5321 | (define-public plink-ng |
5322 | (package (inherit plink) | |
5323 | (name "plink-ng") | |
5324 | (version "1.90b4") | |
5325 | (source | |
5326 | (origin | |
5327 | (method url-fetch) | |
5328 | (uri (string-append "https://github.com/chrchang/plink-ng/archive/v" | |
5329 | version ".tar.gz")) | |
5330 | (file-name (string-append name "-" version ".tar.gz")) | |
5331 | (sha256 | |
5332 | (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a")))) | |
5333 | (build-system gnu-build-system) | |
5334 | (arguments | |
5335 | '(#:tests? #f ;no "check" target | |
5336 | #:make-flags (list "BLASFLAGS=-llapack -lopenblas" | |
5337 | "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1" | |
5338 | "ZLIB=-lz" | |
5339 | "-f" "Makefile.std") | |
5340 | #:phases | |
5341 | (modify-phases %standard-phases | |
5342 | (add-after 'unpack 'chdir | |
5343 | (lambda _ (chdir "1.9") #t)) | |
5344 | (delete 'configure) ; no "configure" script | |
5345 | (replace 'install | |
5346 | (lambda* (#:key outputs #:allow-other-keys) | |
5347 | (let ((bin (string-append (assoc-ref outputs "out") | |
5348 | "/bin/"))) | |
5349 | (install-file "plink" bin) | |
5350 | #t)))))) | |
5351 | (inputs | |
5352 | `(("zlib" ,zlib) | |
5353 | ("lapack" ,lapack) | |
5354 | ("openblas" ,openblas))) | |
5355 | (home-page "https://www.cog-genomics.org/plink/") | |
5356 | (license license:gpl3+))) | |
5357 | ||
c6a24d6e RW |
5358 | (define-public smithlab-cpp |
5359 | (let ((revision "1") | |
698bd297 | 5360 | (commit "728a097bec88c6f4b8528b685932049e660eff2e")) |
c6a24d6e RW |
5361 | (package |
5362 | (name "smithlab-cpp") | |
698bd297 | 5363 | (version (string-append "0." revision "." (string-take commit 7))) |
c6a24d6e RW |
5364 | (source (origin |
5365 | (method git-fetch) | |
5366 | (uri (git-reference | |
5367 | (url "https://github.com/smithlabcode/smithlab_cpp.git") | |
5368 | (commit commit))) | |
5369 | (file-name (string-append name "-" version "-checkout")) | |
5370 | (sha256 | |
5371 | (base32 | |
5372 | "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74")))) | |
5373 | (build-system gnu-build-system) | |
5374 | (arguments | |
5375 | `(#:modules ((guix build gnu-build-system) | |
5376 | (guix build utils) | |
5377 | (srfi srfi-26)) | |
5378 | #:tests? #f ;no "check" target | |
5379 | #:phases | |
5380 | (modify-phases %standard-phases | |
5381 | (add-after 'unpack 'use-samtools-headers | |
5382 | (lambda _ | |
5383 | (substitute* '("SAM.cpp" | |
5384 | "SAM.hpp") | |
5385 | (("sam.h") "samtools/sam.h")) | |
5386 | #t)) | |
5387 | (replace 'install | |
5388 | (lambda* (#:key outputs #:allow-other-keys) | |
5389 | (let* ((out (assoc-ref outputs "out")) | |
5390 | (lib (string-append out "/lib")) | |
5391 | (include (string-append out "/include/smithlab-cpp"))) | |
5392 | (mkdir-p lib) | |
5393 | (mkdir-p include) | |
5394 | (for-each (cut install-file <> lib) | |
5395 | (find-files "." "\\.o$")) | |
5396 | (for-each (cut install-file <> include) | |
5397 | (find-files "." "\\.hpp$"))) | |
5398 | #t)) | |
5399 | (delete 'configure)))) | |
5400 | (inputs | |
5401 | `(("samtools" ,samtools-0.1) | |
5402 | ("zlib" ,zlib))) | |
5403 | (home-page "https://github.com/smithlabcode/smithlab_cpp") | |
5404 | (synopsis "C++ helper library for functions used in Smith lab projects") | |
5405 | (description | |
5406 | "Smithlab CPP is a C++ library that includes functions used in many of | |
5407 | the Smith lab bioinformatics projects, such as a wrapper around Samtools data | |
5408 | structures, classes for genomic regions, mapped sequencing reads, etc.") | |
5409 | (license license:gpl3+)))) | |
5410 | ||
56e373ef RW |
5411 | (define-public preseq |
5412 | (package | |
5413 | (name "preseq") | |
b49c5a58 | 5414 | (version "2.0") |
56e373ef RW |
5415 | (source (origin |
5416 | (method url-fetch) | |
b49c5a58 RW |
5417 | (uri (string-append "https://github.com/smithlabcode/" |
5418 | "preseq/archive/v" version ".tar.gz")) | |
5419 | (file-name (string-append name "-" version ".tar.gz")) | |
56e373ef | 5420 | (sha256 |
b49c5a58 | 5421 | (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq")) |
56e373ef RW |
5422 | (modules '((guix build utils))) |
5423 | (snippet | |
5424 | ;; Remove bundled samtools. | |
b49c5a58 | 5425 | '(delete-file-recursively "samtools")))) |
56e373ef RW |
5426 | (build-system gnu-build-system) |
5427 | (arguments | |
5428 | `(#:tests? #f ;no "check" target | |
5429 | #:phases | |
5430 | (modify-phases %standard-phases | |
56e373ef | 5431 | (delete 'configure)) |
b49c5a58 RW |
5432 | #:make-flags |
5433 | (list (string-append "PREFIX=" | |
5434 | (assoc-ref %outputs "out")) | |
5435 | (string-append "LIBBAM=" | |
5436 | (assoc-ref %build-inputs "samtools") | |
5437 | "/lib/libbam.a") | |
5438 | (string-append "SMITHLAB_CPP=" | |
5439 | (assoc-ref %build-inputs "smithlab-cpp") | |
5440 | "/lib") | |
5441 | "PROGS=preseq" | |
5442 | "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)"))) | |
56e373ef RW |
5443 | (inputs |
5444 | `(("gsl" ,gsl) | |
5445 | ("samtools" ,samtools-0.1) | |
b49c5a58 | 5446 | ("smithlab-cpp" ,smithlab-cpp) |
56e373ef RW |
5447 | ("zlib" ,zlib))) |
5448 | (home-page "http://smithlabresearch.org/software/preseq/") | |
5449 | (synopsis "Program for analyzing library complexity") | |
5450 | (description | |
5451 | "The preseq package is aimed at predicting and estimating the complexity | |
5452 | of a genomic sequencing library, equivalent to predicting and estimating the | |
5453 | number of redundant reads from a given sequencing depth and how many will be | |
5454 | expected from additional sequencing using an initial sequencing experiment. | |
5455 | The estimates can then be used to examine the utility of further sequencing, | |
5456 | optimize the sequencing depth, or to screen multiple libraries to avoid low | |
5457 | complexity samples.") | |
5458 | (license license:gpl3+))) | |
5459 | ||
9ded1457 BW |
5460 | (define-public python-screed |
5461 | (package | |
5462 | (name "python-screed") | |
5463 | (version "0.9") | |
5464 | (source | |
5465 | (origin | |
5466 | (method url-fetch) | |
5467 | (uri (pypi-uri "screed" version)) | |
5468 | (sha256 | |
5469 | (base32 | |
5470 | "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0")))) | |
5471 | (build-system python-build-system) | |
5472 | (arguments | |
5473 | `(#:phases | |
5474 | (modify-phases %standard-phases | |
5475 | (replace 'check | |
5476 | (lambda _ | |
5477 | (setenv "PYTHONPATH" | |
5478 | (string-append (getenv "PYTHONPATH") ":.")) | |
5479 | (zero? (system* "nosetests" "--attr" "!known_failing"))))))) | |
5480 | (native-inputs | |
5481 | `(("python-nose" ,python-nose))) | |
5482 | (inputs | |
5483 | `(("python-bz2file" ,python-bz2file))) | |
7bf837fd | 5484 | (home-page "https://github.com/dib-lab/screed/") |
9ded1457 BW |
5485 | (synopsis "Short read sequence database utilities") |
5486 | (description "Screed parses FASTA and FASTQ files and generates databases. | |
5487 | Values such as sequence name, sequence description, sequence quality and the | |
5488 | sequence itself can be retrieved from these databases.") | |
5489 | (license license:bsd-3))) | |
5490 | ||
5491 | (define-public python2-screed | |
5c31f4aa | 5492 | (package-with-python2 python-screed)) |
9ded1457 | 5493 | |
51c64999 RW |
5494 | (define-public sra-tools |
5495 | (package | |
5496 | (name "sra-tools") | |
79849358 | 5497 | (version "2.8.2-1") |
51c64999 RW |
5498 | (source |
5499 | (origin | |
5500 | (method url-fetch) | |
5501 | (uri | |
5502 | (string-append "https://github.com/ncbi/sra-tools/archive/" | |
5503 | version ".tar.gz")) | |
5504 | (file-name (string-append name "-" version ".tar.gz")) | |
5505 | (sha256 | |
5506 | (base32 | |
79849358 | 5507 | "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g")))) |
51c64999 RW |
5508 | (build-system gnu-build-system) |
5509 | (arguments | |
5510 | `(#:parallel-build? #f ; not supported | |
5511 | #:tests? #f ; no "check" target | |
2320e76b | 5512 | #:make-flags |
79849358 RW |
5513 | (list (string-append "DEFAULT_CRT=" |
5514 | (assoc-ref %build-inputs "ncbi-vdb") | |
5515 | "/kfg/certs.kfg") | |
5516 | (string-append "DEFAULT_KFG=" | |
5517 | (assoc-ref %build-inputs "ncbi-vdb") | |
5518 | "/kfg/default.kfg") | |
5519 | (string-append "VDB_LIBDIR=" | |
2320e76b RW |
5520 | (assoc-ref %build-inputs "ncbi-vdb") |
5521 | ,(if (string-prefix? "x86_64" | |
5522 | (or (%current-target-system) | |
5523 | (%current-system))) | |
5524 | "/lib64" | |
5525 | "/lib32"))) | |
51c64999 | 5526 | #:phases |
beebe431 | 5527 | (modify-phases %standard-phases |
0691851a BW |
5528 | (add-before 'configure 'set-perl-search-path |
5529 | (lambda _ | |
5530 | ;; Work around "dotless @INC" build failure. | |
5531 | (setenv "PERL5LIB" | |
5532 | (string-append (getcwd) "/setup:" | |
5533 | (getenv "PERL5LIB"))) | |
5534 | #t)) | |
beebe431 RW |
5535 | (replace 'configure |
5536 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
5537 | ;; The build system expects a directory containing the sources and | |
5538 | ;; raw build output of ncbi-vdb, including files that are not | |
5539 | ;; installed. Since we are building against an installed version of | |
5540 | ;; ncbi-vdb, the following modifications are needed. | |
5541 | (substitute* "setup/konfigure.perl" | |
5542 | ;; Make the configure script look for the "ilib" directory of | |
5543 | ;; "ncbi-vdb" without first checking for the existence of a | |
5544 | ;; matching library in its "lib" directory. | |
5545 | (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);") | |
5546 | "my $f = File::Spec->catdir($ilibdir, $ilib);") | |
5547 | ;; Look for interface libraries in ncbi-vdb's "ilib" directory. | |
5548 | (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);") | |
5549 | "my $ilibdir = File::Spec->catdir($dir, 'ilib');")) | |
51c64999 | 5550 | |
beebe431 RW |
5551 | ;; Dynamic linking |
5552 | (substitute* "tools/copycat/Makefile" | |
5553 | (("smagic-static") "lmagic")) | |
2320e76b | 5554 | |
beebe431 RW |
5555 | ;; The 'configure' script doesn't recognize things like |
5556 | ;; '--enable-fast-install'. | |
5557 | (zero? (system* | |
5558 | "./configure" | |
5559 | (string-append "--build-prefix=" (getcwd) "/build") | |
5560 | (string-append "--prefix=" (assoc-ref outputs "out")) | |
5561 | (string-append "--debug") | |
5562 | (string-append "--with-fuse-prefix=" | |
5563 | (assoc-ref inputs "fuse")) | |
5564 | (string-append "--with-magic-prefix=" | |
5565 | (assoc-ref inputs "libmagic")) | |
5566 | ;; TODO: building with libxml2 fails with linker errors | |
5567 | ;; (string-append "--with-xml2-prefix=" | |
5568 | ;; (assoc-ref inputs "libxml2")) | |
5569 | (string-append "--with-ncbi-vdb-sources=" | |
5570 | (assoc-ref inputs "ncbi-vdb")) | |
5571 | (string-append "--with-ncbi-vdb-build=" | |
5572 | (assoc-ref inputs "ncbi-vdb")) | |
5573 | (string-append "--with-ngs-sdk-prefix=" | |
5574 | (assoc-ref inputs "ngs-sdk")) | |
5575 | (string-append "--with-hdf5-prefix=" | |
1108a920 RW |
5576 | (assoc-ref inputs "hdf5")))))) |
5577 | ;; This version of sra-tools fails to build with glibc because of a | |
5578 | ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already | |
5579 | ;; contains a definition of "canonicalize", so we rename it. | |
5580 | ;; | |
5581 | ;; See upstream bug report: | |
5582 | ;; https://github.com/ncbi/sra-tools/issues/67 | |
5583 | (add-after 'unpack 'patch-away-glibc-conflict | |
5584 | (lambda _ | |
5585 | (substitute* "tools/bam-loader/bam.c" | |
5586 | (("canonicalize\\(" line) | |
5587 | (string-append "sra_tools_" line))) | |
5588 | #t))))) | |
51c64999 RW |
5589 | (native-inputs `(("perl" ,perl))) |
5590 | (inputs | |
5591 | `(("ngs-sdk" ,ngs-sdk) | |
5592 | ("ncbi-vdb" ,ncbi-vdb) | |
5593 | ("libmagic" ,file) | |
5594 | ("fuse" ,fuse) | |
5595 | ("hdf5" ,hdf5) | |
5596 | ("zlib" ,zlib))) | |
5597 | (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software") | |
5598 | (synopsis "Tools and libraries for reading and writing sequencing data") | |
5599 | (description | |
5600 | "The SRA Toolkit from NCBI is a collection of tools and libraries for | |
5601 | reading of sequencing files from the Sequence Read Archive (SRA) database and | |
5602 | writing files into the .sra format.") | |
5603 | (license license:public-domain))) | |
5604 | ||
d3517eda RW |
5605 | (define-public seqan |
5606 | (package | |
5607 | (name "seqan") | |
5608 | (version "1.4.2") | |
5609 | (source (origin | |
5610 | (method url-fetch) | |
5611 | (uri (string-append "http://packages.seqan.de/seqan-library/" | |
5612 | "seqan-library-" version ".tar.bz2")) | |
5613 | (sha256 | |
5614 | (base32 | |
5615 | "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp")))) | |
5616 | ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it | |
5617 | ;; makes sense to split the outputs. | |
5618 | (outputs '("out" "doc")) | |
5619 | (build-system trivial-build-system) | |
5620 | (arguments | |
5621 | `(#:modules ((guix build utils)) | |
5622 | #:builder | |
5623 | (begin | |
5624 | (use-modules (guix build utils)) | |
5625 | (let ((tar (assoc-ref %build-inputs "tar")) | |
5626 | (bzip (assoc-ref %build-inputs "bzip2")) | |
5627 | (out (assoc-ref %outputs "out")) | |
5628 | (doc (assoc-ref %outputs "doc"))) | |
5629 | (setenv "PATH" (string-append tar "/bin:" bzip "/bin")) | |
5630 | (system* "tar" "xvf" (assoc-ref %build-inputs "source")) | |
5631 | (chdir (string-append "seqan-library-" ,version)) | |
5632 | (copy-recursively "include" (string-append out "/include")) | |
5633 | (copy-recursively "share" (string-append doc "/share")))))) | |
5634 | (native-inputs | |
5635 | `(("source" ,source) | |
5636 | ("tar" ,tar) | |
5637 | ("bzip2" ,bzip2))) | |
5638 | (home-page "http://www.seqan.de") | |
5639 | (synopsis "Library for nucleotide sequence analysis") | |
5640 | (description | |
5641 | "SeqAn is a C++ library of efficient algorithms and data structures for | |
5642 | the analysis of sequences with the focus on biological data. It contains | |
5643 | algorithms and data structures for string representation and their | |
5644 | manipulation, online and indexed string search, efficient I/O of | |
5645 | bioinformatics file formats, sequence alignment, and more.") | |
5646 | (license license:bsd-3))) | |
ce7155d5 | 5647 | |
d708b7a9 BW |
5648 | (define-public seqmagick |
5649 | (package | |
5650 | (name "seqmagick") | |
39fb853a | 5651 | (version "0.7.0") |
d708b7a9 BW |
5652 | (source |
5653 | (origin | |
5654 | (method url-fetch) | |
f6e2d86f | 5655 | (uri (pypi-uri "seqmagick" version)) |
d708b7a9 BW |
5656 | (sha256 |
5657 | (base32 | |
39fb853a | 5658 | "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5")))) |
d708b7a9 | 5659 | (build-system python-build-system) |
d708b7a9 | 5660 | (inputs |
39fb853a | 5661 | `(("python-biopython" ,python-biopython))) |
d708b7a9 | 5662 | (native-inputs |
39fb853a | 5663 | `(("python-nose" ,python-nose))) |
7bf837fd | 5664 | (home-page "https://github.com/fhcrc/seqmagick") |
d708b7a9 BW |
5665 | (synopsis "Tools for converting and modifying sequence files") |
5666 | (description | |
5667 | "Bioinformaticians often have to convert sequence files between formats | |
5668 | and do little manipulations on them, and it's not worth writing scripts for | |
5669 | that. Seqmagick is a utility to expose the file format conversion in | |
5670 | BioPython in a convenient way. Instead of having a big mess of scripts, there | |
5671 | is one that takes arguments.") | |
5672 | (license license:gpl3))) | |
5673 | ||
66daf78c BW |
5674 | (define-public seqtk |
5675 | (package | |
5676 | (name "seqtk") | |
5677 | (version "1.2") | |
5678 | (source (origin | |
5679 | (method url-fetch) | |
5680 | (uri (string-append | |
5681 | "https://github.com/lh3/seqtk/archive/v" | |
5682 | version ".tar.gz")) | |
5683 | (file-name (string-append name "-" version ".tar.gz")) | |
5684 | (sha256 | |
5685 | (base32 | |
5686 | "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx")) | |
5687 | (modules '((guix build utils))) | |
5688 | (snippet | |
5689 | '(begin | |
5690 | ;; Remove extraneous header files, as is done in the seqtk | |
5691 | ;; master branch. | |
5692 | (for-each (lambda (file) (delete-file file)) | |
5693 | (list "ksort.h" "kstring.h" "kvec.h")) | |
5694 | #t)))) | |
5695 | (build-system gnu-build-system) | |
5696 | (arguments | |
5697 | `(#:phases | |
5698 | (modify-phases %standard-phases | |
5699 | (delete 'configure) | |
5700 | (replace 'check | |
5701 | ;; There are no tests, so we just run a sanity check. | |
5702 | (lambda _ (zero? (system* "./seqtk" "seq")))) | |
5703 | (replace 'install | |
5704 | (lambda* (#:key outputs #:allow-other-keys) | |
5705 | (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) | |
5706 | (install-file "seqtk" bin))))))) | |
5707 | (inputs | |
5708 | `(("zlib" ,zlib))) | |
5709 | (home-page "https://github.com/lh3/seqtk") | |
5710 | (synopsis "Toolkit for processing biological sequences in FASTA/Q format") | |
5711 | (description | |
5712 | "Seqtk is a fast and lightweight tool for processing sequences in the | |
5713 | FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be | |
5714 | optionally compressed by gzip.") | |
5715 | (license license:expat))) | |
5716 | ||
5f7e17be BW |
5717 | (define-public snap-aligner |
5718 | (package | |
5719 | (name "snap-aligner") | |
5720 | (version "1.0beta.18") | |
5721 | (source (origin | |
5722 | (method url-fetch) | |
5723 | (uri (string-append | |
5724 | "https://github.com/amplab/snap/archive/v" | |
5725 | version ".tar.gz")) | |
5726 | (file-name (string-append name "-" version ".tar.gz")) | |
5727 | (sha256 | |
5728 | (base32 | |
5729 | "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly")))) | |
5730 | (build-system gnu-build-system) | |
5731 | (arguments | |
5732 | '(#:phases | |
5733 | (modify-phases %standard-phases | |
5734 | (delete 'configure) | |
5735 | (replace 'check (lambda _ (zero? (system* "./unit_tests")))) | |
5736 | (replace 'install | |
5737 | (lambda* (#:key outputs #:allow-other-keys) | |
5738 | (let* ((out (assoc-ref outputs "out")) | |
5739 | (bin (string-append out "/bin"))) | |
5f7e17be BW |
5740 | (install-file "snap-aligner" bin) |
5741 | (install-file "SNAPCommand" bin) | |
5742 | #t)))))) | |
5743 | (native-inputs | |
5744 | `(("zlib" ,zlib))) | |
5745 | (home-page "http://snap.cs.berkeley.edu/") | |
5746 | (synopsis "Short read DNA sequence aligner") | |
5747 | (description | |
5748 | "SNAP is a fast and accurate aligner for short DNA reads. It is | |
5749 | optimized for modern read lengths of 100 bases or higher, and takes advantage | |
5750 | of these reads to align data quickly through a hash-based indexing scheme.") | |
3e6fdd5f EF |
5751 | ;; 32-bit systems are not supported by the unpatched code. |
5752 | ;; Following the bug reports https://github.com/amplab/snap/issues/68 and | |
5753 | ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that | |
5754 | ;; systems without a lot of memory cannot make good use of this program. | |
5755 | (supported-systems '("x86_64-linux")) | |
5f7e17be BW |
5756 | (license license:asl2.0))) |
5757 | ||
bcadaf00 BW |
5758 | (define-public sortmerna |
5759 | (package | |
5760 | (name "sortmerna") | |
849485f5 | 5761 | (version "2.1b") |
bcadaf00 BW |
5762 | (source |
5763 | (origin | |
5764 | (method url-fetch) | |
5765 | (uri (string-append | |
5766 | "https://github.com/biocore/sortmerna/archive/" | |
5767 | version ".tar.gz")) | |
5768 | (file-name (string-append name "-" version ".tar.gz")) | |
5769 | (sha256 | |
5770 | (base32 | |
849485f5 | 5771 | "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk")))) |
bcadaf00 BW |
5772 | (build-system gnu-build-system) |
5773 | (outputs '("out" ;for binaries | |
5774 | "db")) ;for sequence databases | |
5775 | (arguments | |
5776 | `(#:phases | |
5777 | (modify-phases %standard-phases | |
5778 | (replace 'install | |
5779 | (lambda* (#:key outputs #:allow-other-keys) | |
5780 | (let* ((out (assoc-ref outputs "out")) | |
5781 | (bin (string-append out "/bin")) | |
5782 | (db (assoc-ref outputs "db")) | |
5783 | (share | |
5784 | (string-append db "/share/sortmerna/rRNA_databases"))) | |
5785 | (install-file "sortmerna" bin) | |
5786 | (install-file "indexdb_rna" bin) | |
5787 | (for-each (lambda (file) | |
5788 | (install-file file share)) | |
5789 | (find-files "rRNA_databases" ".*fasta")) | |
5790 | #t)))))) | |
849485f5 BW |
5791 | (inputs |
5792 | `(("zlib" ,zlib))) | |
bcadaf00 BW |
5793 | (home-page "http://bioinfo.lifl.fr/RNA/sortmerna") |
5794 | (synopsis "Biological sequence analysis tool for NGS reads") | |
5795 | (description | |
5796 | "SortMeRNA is a biological sequence analysis tool for filtering, mapping | |
5797 | and operational taxonomic unit (OTU) picking of next generation | |
5798 | sequencing (NGS) reads. The core algorithm is based on approximate seeds and | |
5799 | allows for fast and sensitive analyses of nucleotide sequences. The main | |
5800 | application of SortMeRNA is filtering rRNA from metatranscriptomic data.") | |
2324541b EF |
5801 | ;; The source includes x86 specific code |
5802 | (supported-systems '("x86_64-linux" "i686-linux")) | |
bcadaf00 BW |
5803 | (license license:lgpl3))) |
5804 | ||
ce7155d5 RW |
5805 | (define-public star |
5806 | (package | |
5807 | (name "star") | |
d36d5229 | 5808 | (version "2.6.0a") |
ce7155d5 RW |
5809 | (source (origin |
5810 | (method url-fetch) | |
3062d750 RW |
5811 | (uri (string-append "https://github.com/alexdobin/STAR/archive/" |
5812 | version ".tar.gz")) | |
5813 | (file-name (string-append name "-" version ".tar.gz")) | |
ce7155d5 RW |
5814 | (sha256 |
5815 | (base32 | |
d36d5229 | 5816 | "0yci4ymy4407kjh0lqp021nzccp6r31wgrkixkmix5p130cxvc56")) |
ce7155d5 RW |
5817 | (modules '((guix build utils))) |
5818 | (snippet | |
3062d750 RW |
5819 | '(begin |
5820 | (substitute* "source/Makefile" | |
5821 | (("/bin/rm") "rm")) | |
5822 | ;; Remove pre-built binaries and bundled htslib sources. | |
5823 | (delete-file-recursively "bin/MacOSX_x86_64") | |
5824 | (delete-file-recursively "bin/Linux_x86_64") | |
c9e9154e | 5825 | (delete-file-recursively "bin/Linux_x86_64_static") |
3062d750 RW |
5826 | (delete-file-recursively "source/htslib") |
5827 | #t)))) | |
ce7155d5 RW |
5828 | (build-system gnu-build-system) |
5829 | (arguments | |
5830 | '(#:tests? #f ;no check target | |
5831 | #:make-flags '("STAR") | |
5832 | #:phases | |
c0266e8d RW |
5833 | (modify-phases %standard-phases |
5834 | (add-after 'unpack 'enter-source-dir | |
5835 | (lambda _ (chdir "source") #t)) | |
625cdc3f RW |
5836 | (add-after 'enter-source-dir 'make-reproducible |
5837 | (lambda _ | |
5838 | (substitute* "Makefile" | |
5839 | (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post) | |
5840 | (string-append pre "Built with Guix" post))))) | |
3062d750 RW |
5841 | (add-after 'enter-source-dir 'do-not-use-bundled-htslib |
5842 | (lambda _ | |
5843 | (substitute* "Makefile" | |
5844 | (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib" | |
5845 | _ prefix) prefix)) | |
5846 | (substitute* '("BAMfunctions.cpp" | |
5847 | "signalFromBAM.h" | |
5848 | "bam_cat.h" | |
5849 | "bam_cat.c" | |
5850 | "STAR.cpp" | |
5851 | "bamRemoveDuplicates.cpp") | |
5852 | (("#include \"htslib/([^\"]+\\.h)\"" _ header) | |
5853 | (string-append "#include <" header ">"))) | |
5854 | (substitute* "IncludeDefine.h" | |
5855 | (("\"htslib/(htslib/[^\"]+.h)\"" _ header) | |
5856 | (string-append "<" header ">"))) | |
5857 | #t)) | |
c0266e8d RW |
5858 | (replace 'install |
5859 | (lambda* (#:key outputs #:allow-other-keys) | |
5860 | (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) | |
5861 | (install-file "STAR" bin)) | |
5862 | #t)) | |
5863 | (delete 'configure)))) | |
ce7155d5 | 5864 | (native-inputs |
9fc513ad | 5865 | `(("xxd" ,xxd))) |
ce7155d5 | 5866 | (inputs |
3062d750 RW |
5867 | `(("htslib" ,htslib) |
5868 | ("zlib" ,zlib))) | |
ce7155d5 RW |
5869 | (home-page "https://github.com/alexdobin/STAR") |
5870 | (synopsis "Universal RNA-seq aligner") | |
5871 | (description | |
5872 | "The Spliced Transcripts Alignment to a Reference (STAR) software is | |
5873 | based on a previously undescribed RNA-seq alignment algorithm that uses | |
5874 | sequential maximum mappable seed search in uncompressed suffix arrays followed | |
5875 | by seed clustering and stitching procedure. In addition to unbiased de novo | |
5876 | detection of canonical junctions, STAR can discover non-canonical splices and | |
5877 | chimeric (fusion) transcripts, and is also capable of mapping full-length RNA | |
5878 | sequences.") | |
c11f79a4 BW |
5879 | ;; Only 64-bit systems are supported according to the README. |
5880 | (supported-systems '("x86_64-linux" "mips64el-linux")) | |
ce7155d5 RW |
5881 | ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed. |
5882 | (license license:gpl3+))) | |
de07c0db | 5883 | |
dbf4ed7c RW |
5884 | (define-public subread |
5885 | (package | |
5886 | (name "subread") | |
e6debcaf | 5887 | (version "1.6.0") |
dbf4ed7c RW |
5888 | (source (origin |
5889 | (method url-fetch) | |
de67e922 LF |
5890 | (uri (string-append "mirror://sourceforge/subread/subread-" |
5891 | version "/subread-" version "-source.tar.gz")) | |
dbf4ed7c RW |
5892 | (sha256 |
5893 | (base32 | |
e6debcaf | 5894 | "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i")))) |
dbf4ed7c RW |
5895 | (build-system gnu-build-system) |
5896 | (arguments | |
5897 | `(#:tests? #f ;no "check" target | |
104c1986 RW |
5898 | ;; The CC and CCFLAGS variables are set to contain a lot of x86_64 |
5899 | ;; optimizations by default, so we override these flags such that x86_64 | |
5900 | ;; flags are only added when the build target is an x86_64 system. | |
5901 | #:make-flags | |
5902 | (list (let ((system ,(or (%current-target-system) | |
5903 | (%current-system))) | |
5904 | (flags '("-ggdb" "-fomit-frame-pointer" | |
5905 | "-ffast-math" "-funroll-loops" | |
5906 | "-fmessage-length=0" | |
5907 | "-O9" "-Wall" "-DMAKE_FOR_EXON" | |
5908 | "-DMAKE_STANDALONE" | |
5909 | "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\"")) | |
5910 | (flags64 '("-mmmx" "-msse" "-msse2" "-msse3"))) | |
5911 | (if (string-prefix? "x86_64" system) | |
5912 | (string-append "CCFLAGS=" (string-join (append flags flags64))) | |
5913 | (string-append "CCFLAGS=" (string-join flags)))) | |
5914 | "-f" "Makefile.Linux" | |
5915 | "CC=gcc ${CCFLAGS}") | |
dbf4ed7c | 5916 | #:phases |
dc1d3cde KK |
5917 | (modify-phases %standard-phases |
5918 | (add-after 'unpack 'enter-dir | |
5919 | (lambda _ (chdir "src") #t)) | |
5920 | (replace 'install | |
5921 | (lambda* (#:key outputs #:allow-other-keys) | |
5922 | (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) | |
5923 | (mkdir-p bin) | |
5924 | (copy-recursively "../bin" bin)))) | |
dbf4ed7c | 5925 | ;; no "configure" script |
dc1d3cde | 5926 | (delete 'configure)))) |
dbf4ed7c RW |
5927 | (inputs `(("zlib" ,zlib))) |
5928 | (home-page "http://bioinf.wehi.edu.au/subread-package/") | |
5929 | (synopsis "Tool kit for processing next-gen sequencing data") | |
5930 | (description | |
5931 | "The subread package contains the following tools: subread aligner, a | |
5932 | general-purpose read aligner; subjunc aligner: detecting exon-exon junctions | |
5933 | and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic | |
5934 | features; exactSNP: a SNP caller that discovers SNPs by testing signals | |
5935 | against local background noises.") | |
5936 | (license license:gpl3+))) | |
5937 | ||
d15d981e RW |
5938 | (define-public stringtie |
5939 | (package | |
5940 | (name "stringtie") | |
5941 | (version "1.2.1") | |
5942 | (source (origin | |
5943 | (method url-fetch) | |
5944 | (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/" | |
5945 | "stringtie-" version ".tar.gz")) | |
5946 | (sha256 | |
5947 | (base32 | |
5948 | "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz")) | |
5949 | (modules '((guix build utils))) | |
5950 | (snippet | |
5951 | '(begin | |
5952 | (delete-file-recursively "samtools-0.1.18") | |
5953 | #t)))) | |
5954 | (build-system gnu-build-system) | |
5955 | (arguments | |
5956 | `(#:tests? #f ;no test suite | |
5957 | #:phases | |
5958 | (modify-phases %standard-phases | |
5959 | ;; no configure script | |
5960 | (delete 'configure) | |
5961 | (add-before 'build 'use-system-samtools | |
5962 | (lambda _ | |
5963 | (substitute* "Makefile" | |
5964 | (("stringtie: \\$\\{BAM\\}/libbam\\.a") | |
5965 | "stringtie: ")) | |
5966 | (substitute* '("gclib/GBam.h" | |
5967 | "gclib/GBam.cpp") | |
5968 | (("#include \"(bam|sam|kstring).h\"" _ header) | |
5969 | (string-append "#include <samtools/" header ".h>"))) | |
5970 | #t)) | |
0d2c0562 RW |
5971 | (add-after 'unpack 'remove-duplicate-typedef |
5972 | (lambda _ | |
5973 | ;; This typedef conflicts with the typedef in | |
5974 | ;; glibc-2.25/include/bits/types.h | |
5975 | (substitute* "gclib/GThreads.h" | |
5976 | (("typedef long long __intmax_t;") "")) | |
5977 | #t)) | |
d15d981e RW |
5978 | (replace 'install |
5979 | (lambda* (#:key outputs #:allow-other-keys) | |
5980 | (let ((bin (string-append (assoc-ref outputs "out") "/bin/"))) | |
5981 | (install-file "stringtie" bin) | |
5982 | #t)))))) | |
5983 | (inputs | |
5984 | `(("samtools" ,samtools-0.1) | |
5985 | ("zlib" ,zlib))) | |
5986 | (home-page "http://ccb.jhu.edu/software/stringtie/") | |
5987 | (synopsis "Transcript assembly and quantification for RNA-Seq data") | |
5988 | (description | |
5989 | "StringTie is a fast and efficient assembler of RNA-Seq sequence | |
5990 | alignments into potential transcripts. It uses a novel network flow algorithm | |
5991 | as well as an optional de novo assembly step to assemble and quantitate | |
5992 | full-length transcripts representing multiple splice variants for each gene | |
5993 | locus. Its input can include not only the alignments of raw reads used by | |
5994 | other transcript assemblers, but also alignments of longer sequences that have | |
5995 | been assembled from those reads. To identify differentially expressed genes | |
5996 | between experiments, StringTie's output can be processed either by the | |
5997 | Cuffdiff or Ballgown programs.") | |
5998 | (license license:artistic2.0))) | |
5999 | ||
ad0ae297 BW |
6000 | (define-public taxtastic |
6001 | (package | |
6002 | (name "taxtastic") | |
d0c75e73 | 6003 | (version "0.8.5") |
ad0ae297 BW |
6004 | (source (origin |
6005 | (method url-fetch) | |
3cbfc149 | 6006 | (uri (pypi-uri "taxtastic" version)) |
ad0ae297 BW |
6007 | (sha256 |
6008 | (base32 | |
d0c75e73 | 6009 | "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk")))) |
ad0ae297 BW |
6010 | (build-system python-build-system) |
6011 | (arguments | |
6012 | `(#:python ,python-2 | |
6013 | #:phases | |
6014 | (modify-phases %standard-phases | |
6015 | (replace 'check | |
6016 | (lambda _ | |
6017 | (zero? (system* "python" "-m" "unittest" "discover" "-v"))))))) | |
6018 | (propagated-inputs | |
6019 | `(("python-sqlalchemy" ,python2-sqlalchemy) | |
6020 | ("python-decorator" ,python2-decorator) | |
6021 | ("python-biopython" ,python2-biopython) | |
6022 | ("python-pandas" ,python2-pandas))) | |
6023 | (home-page "https://github.com/fhcrc/taxtastic") | |
6024 | (synopsis "Tools for taxonomic naming and annotation") | |
6025 | (description | |
6026 | "Taxtastic is software written in python used to build and maintain | |
6027 | reference packages i.e. collections of reference trees, reference alignments, | |
6028 | profiles, and associated taxonomic information.") | |
6029 | (license license:gpl3+))) | |
6030 | ||
de07c0db RW |
6031 | (define-public vcftools |
6032 | (package | |
6033 | (name "vcftools") | |
f4322542 | 6034 | (version "0.1.15") |
de07c0db RW |
6035 | (source (origin |
6036 | (method url-fetch) | |
6037 | (uri (string-append | |
9b36e256 RJ |
6038 | "https://github.com/vcftools/vcftools/releases/download/v" |
6039 | version "/vcftools-" version ".tar.gz")) | |
de07c0db RW |
6040 | (sha256 |
6041 | (base32 | |
f4322542 | 6042 | "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i")))) |
de07c0db RW |
6043 | (build-system gnu-build-system) |
6044 | (arguments | |
6045 | `(#:tests? #f ; no "check" target | |
6046 | #:make-flags (list | |
7c3958e1 | 6047 | "CFLAGS=-O2" ; override "-m64" flag |
de07c0db RW |
6048 | (string-append "PREFIX=" (assoc-ref %outputs "out")) |
6049 | (string-append "MANDIR=" (assoc-ref %outputs "out") | |
9b36e256 RJ |
6050 | "/share/man/man1")))) |
6051 | (native-inputs | |
6052 | `(("pkg-config" ,pkg-config))) | |
de07c0db RW |
6053 | (inputs |
6054 | `(("perl" ,perl) | |
6055 | ("zlib" ,zlib))) | |
9b36e256 | 6056 | (home-page "https://vcftools.github.io/") |
de07c0db RW |
6057 | (synopsis "Tools for working with VCF files") |
6058 | (description | |
6059 | "VCFtools is a program package designed for working with VCF files, such | |
6060 | as those generated by the 1000 Genomes Project. The aim of VCFtools is to | |
6061 | provide easily accessible methods for working with complex genetic variation | |
6062 | data in the form of VCF files.") | |
6063 | ;; The license is declared as LGPLv3 in the README and | |
9b36e256 | 6064 | ;; at https://vcftools.github.io/license.html |
de07c0db | 6065 | (license license:lgpl3))) |
9c38b540 | 6066 | |
35aa90a1 RW |
6067 | (define-public infernal |
6068 | (package | |
6069 | (name "infernal") | |
6070 | (version "1.1.2") | |
6071 | (source (origin | |
6072 | (method url-fetch) | |
6073 | (uri (string-append "http://eddylab.org/software/infernal/" | |
6074 | "infernal-" version ".tar.gz")) | |
6075 | (sha256 | |
6076 | (base32 | |
6077 | "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c")))) | |
6078 | (build-system gnu-build-system) | |
6079 | (native-inputs | |
6080 | `(("perl" ,perl))) ; for tests | |
6081 | (home-page "http://eddylab.org/infernal/") | |
6082 | (synopsis "Inference of RNA alignments") | |
6083 | (description "Infernal (\"INFERence of RNA ALignment\") is a tool for | |
6084 | searching DNA sequence databases for RNA structure and sequence similarities. | |
6085 | It is an implementation of a special case of profile stochastic context-free | |
6086 | grammars called @dfn{covariance models} (CMs). A CM is like a sequence | |
6087 | profile, but it scores a combination of sequence consensus and RNA secondary | |
6088 | structure consensus, so in many cases, it is more capable of identifying RNA | |
6089 | homologs that conserve their secondary structure more than their primary | |
6090 | sequence.") | |
48409ef2 EF |
6091 | ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions. |
6092 | (supported-systems '("i686-linux" "x86_64-linux")) | |
35aa90a1 RW |
6093 | (license license:bsd-3))) |
6094 | ||
b91cfa22 RW |
6095 | (define-public r-centipede |
6096 | (package | |
6097 | (name "r-centipede") | |
6098 | (version "1.2") | |
6099 | (source (origin | |
6100 | (method url-fetch) | |
6101 | (uri (string-append "http://download.r-forge.r-project.org/" | |
6102 | "src/contrib/CENTIPEDE_" version ".tar.gz")) | |
6103 | (sha256 | |
6104 | (base32 | |
6105 | "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9")))) | |
6106 | (build-system r-build-system) | |
6107 | (home-page "http://centipede.uchicago.edu/") | |
6108 | (synopsis "Predict transcription factor binding sites") | |
6109 | (description | |
6110 | "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions | |
6111 | of the genome that are bound by particular transcription factors. It starts | |
6112 | by identifying a set of candidate binding sites, and then aims to classify the | |
6113 | sites according to whether each site is bound or not bound by a transcription | |
6114 | factor. CENTIPEDE is an unsupervised learning algorithm that discriminates | |
6115 | between two different types of motif instances using as much relevant | |
6116 | information as possible.") | |
6117 | (license (list license:gpl2+ license:gpl3+)))) | |
6118 | ||
7b3df1e5 BW |
6119 | (define-public r-vegan |
6120 | (package | |
6121 | (name "r-vegan") | |
3ca31735 | 6122 | (version "2.5-2") |
7b3df1e5 BW |
6123 | (source |
6124 | (origin | |
6125 | (method url-fetch) | |
6126 | (uri (cran-uri "vegan" version)) | |
6127 | (sha256 | |
6128 | (base32 | |
3ca31735 | 6129 | "13pyqvlpz64qibi8k5d109v7q09j06mbv6ndix3n4cn21mjx391c")))) |
7b3df1e5 | 6130 | (build-system r-build-system) |
7b3df1e5 | 6131 | (native-inputs |
db2e4386 | 6132 | `(("gfortran" ,gfortran))) |
7b3df1e5 BW |
6133 | (propagated-inputs |
6134 | `(("r-cluster" ,r-cluster) | |
3ca31735 | 6135 | ("r-knitr" ,r-knitr) ; needed for vignettes |
7b3df1e5 | 6136 | ("r-lattice" ,r-lattice) |
aeb64f3c | 6137 | ("r-mass" ,r-mass) |
7b3df1e5 BW |
6138 | ("r-mgcv" ,r-mgcv) |
6139 | ("r-permute" ,r-permute))) | |
6140 | (home-page "https://cran.r-project.org/web/packages/vegan") | |
6141 | (synopsis "Functions for community ecology") | |
6142 | (description | |
6143 | "The vegan package provides tools for descriptive community ecology. It | |
6144 | has most basic functions of diversity analysis, community ordination and | |
6145 | dissimilarity analysis. Most of its multivariate tools can be used for other | |
6146 | data types as well.") | |
6147 | (license license:gpl2+))) | |
6148 | ||
8c6de588 RW |
6149 | (define-public r-annotate |
6150 | (package | |
6151 | (name "r-annotate") | |
02be8180 | 6152 | (version "1.58.0") |
8c6de588 RW |
6153 | (source |
6154 | (origin | |
6155 | (method url-fetch) | |
6156 | (uri (bioconductor-uri "annotate" version)) | |
6157 | (sha256 | |
6158 | (base32 | |
02be8180 | 6159 | "1qmncyvy147a1ll3iri45p822kcs3s7583jfnq9jf6sz9ilk8cjf")))) |
8c6de588 RW |
6160 | (build-system r-build-system) |
6161 | (propagated-inputs | |
6162 | `(("r-annotationdbi" ,r-annotationdbi) | |
6163 | ("r-biobase" ,r-biobase) | |
6164 | ("r-biocgenerics" ,r-biocgenerics) | |
6165 | ("r-dbi" ,r-dbi) | |
d0f0579e | 6166 | ("r-rcurl" ,r-rcurl) |
8c6de588 RW |
6167 | ("r-xml" ,r-xml) |
6168 | ("r-xtable" ,r-xtable))) | |
6169 | (home-page | |
5713bbf1 | 6170 | "https://bioconductor.org/packages/annotate") |
8c6de588 | 6171 | (synopsis "Annotation for microarrays") |
d1e4ad1b | 6172 | (description "This package provides R environments for the annotation of |
8c6de588 RW |
6173 | microarrays.") |
6174 | (license license:artistic2.0))) | |
6175 | ||
efa6a1dd RJ |
6176 | (define-public r-copynumber |
6177 | (package | |
6178 | (name "r-copynumber") | |
14e9235f | 6179 | (version "1.20.0") |
efa6a1dd RJ |
6180 | (source (origin |
6181 | (method url-fetch) | |
6182 | (uri (bioconductor-uri "copynumber" version)) | |
6183 | (sha256 | |
6184 | (base32 | |
14e9235f | 6185 | "0y9nnwb0psphp3ix88wj2f8z5gr45r5znf55w892ysm27isdpmms")))) |
efa6a1dd RJ |
6186 | (build-system r-build-system) |
6187 | (propagated-inputs | |
6188 | `(("r-s4vectors" ,r-s4vectors) | |
6189 | ("r-iranges" ,r-iranges) | |
6190 | ("r-genomicranges" ,r-genomicranges) | |
6191 | ("r-biocgenerics" ,r-biocgenerics))) | |
6192 | (home-page "https://bioconductor.org/packages/copynumber") | |
6193 | (synopsis "Segmentation of single- and multi-track copy number data") | |
6194 | (description | |
6195 | "This package segments single- and multi-track copy number data by a | |
6196 | penalized least squares regression method.") | |
6197 | (license license:artistic2.0))) | |
6198 | ||
07a664cd RW |
6199 | (define-public r-geneplotter |
6200 | (package | |
6201 | (name "r-geneplotter") | |
4d70c8c4 | 6202 | (version "1.58.0") |
07a664cd RW |
6203 | (source |
6204 | (origin | |
6205 | (method url-fetch) | |
6206 | (uri (bioconductor-uri "geneplotter" version)) | |
6207 | (sha256 | |
6208 | (base32 | |
4d70c8c4 | 6209 | "055g28xgiazl4l0gkg8xiamks64f5yckjjyvw1abd6d6qjavwx0g")))) |
07a664cd RW |
6210 | (build-system r-build-system) |
6211 | (propagated-inputs | |
6212 | `(("r-annotate" ,r-annotate) | |
6213 | ("r-annotationdbi" ,r-annotationdbi) | |
6214 | ("r-biobase" ,r-biobase) | |
6215 | ("r-biocgenerics" ,r-biocgenerics) | |
6216 | ("r-lattice" ,r-lattice) | |
6217 | ("r-rcolorbrewer" ,r-rcolorbrewer))) | |
5713bbf1 | 6218 | (home-page "https://bioconductor.org/packages/geneplotter") |
07a664cd RW |
6219 | (synopsis "Graphics functions for genomic data") |
6220 | (description | |
6221 | "This package provides functions for plotting genomic data.") | |
6222 | (license license:artistic2.0))) | |
6223 | ||
2301fd3e RW |
6224 | (define-public r-genefilter |
6225 | (package | |
6226 | (name "r-genefilter") | |
41657b15 | 6227 | (version "1.62.0") |
2301fd3e RW |
6228 | (source |
6229 | (origin | |
6230 | (method url-fetch) | |
6231 | (uri (bioconductor-uri "genefilter" version)) | |
6232 | (sha256 | |
6233 | (base32 | |
41657b15 | 6234 | "14l0ff02spmjwxj0m1czhg5vlkgwcfi73cym8m2n9vn6i7bjdaqi")))) |
2301fd3e RW |
6235 | (build-system r-build-system) |
6236 | (native-inputs | |
6237 | `(("gfortran" ,gfortran))) | |
6238 | (propagated-inputs | |
6239 | `(("r-annotate" ,r-annotate) | |
6240 | ("r-annotationdbi" ,r-annotationdbi) | |
6241 | ("r-biobase" ,r-biobase) | |
aeb64f3c RW |
6242 | ("r-s4vectors" ,r-s4vectors) |
6243 | ("r-survival" ,r-survival))) | |
5713bbf1 | 6244 | (home-page "https://bioconductor.org/packages/genefilter") |
2301fd3e RW |
6245 | (synopsis "Filter genes from high-throughput experiments") |
6246 | (description | |
6247 | "This package provides basic functions for filtering genes from | |
6248 | high-throughput sequencing experiments.") | |
6249 | (license license:artistic2.0))) | |
6250 | ||
ad34f0ac RW |
6251 | (define-public r-deseq2 |
6252 | (package | |
6253 | (name "r-deseq2") | |
51c1f96e | 6254 | (version "1.20.0") |
ad34f0ac RW |
6255 | (source |
6256 | (origin | |
6257 | (method url-fetch) | |
6258 | (uri (bioconductor-uri "DESeq2" version)) | |
6259 | (sha256 | |
6260 | (base32 | |
51c1f96e | 6261 | "1wjnfpb41a9mmf9a22bz4zh7r1d4id50vpdc1mn5vfzrz7li9qik")))) |
ad34f0ac RW |
6262 | (properties `((upstream-name . "DESeq2"))) |
6263 | (build-system r-build-system) | |
ad34f0ac RW |
6264 | (propagated-inputs |
6265 | `(("r-biobase" ,r-biobase) | |
6266 | ("r-biocgenerics" ,r-biocgenerics) | |
6267 | ("r-biocparallel" ,r-biocparallel) | |
6268 | ("r-genefilter" ,r-genefilter) | |
6269 | ("r-geneplotter" ,r-geneplotter) | |
6270 | ("r-genomicranges" ,r-genomicranges) | |
6271 | ("r-ggplot2" ,r-ggplot2) | |
6272 | ("r-hmisc" ,r-hmisc) | |
6273 | ("r-iranges" ,r-iranges) | |
6274 | ("r-locfit" ,r-locfit) | |
6275 | ("r-rcpp" ,r-rcpp) | |
6276 | ("r-rcpparmadillo" ,r-rcpparmadillo) | |
6277 | ("r-s4vectors" ,r-s4vectors) | |
6278 | ("r-summarizedexperiment" ,r-summarizedexperiment))) | |
5713bbf1 | 6279 | (home-page "https://bioconductor.org/packages/DESeq2") |
ad34f0ac RW |
6280 | (synopsis "Differential gene expression analysis") |
6281 | (description | |
6282 | "This package provides functions to estimate variance-mean dependence in | |
6283 | count data from high-throughput nucleotide sequencing assays and test for | |
6284 | differential expression based on a model using the negative binomial | |
6285 | distribution.") | |
6286 | (license license:lgpl3+))) | |
6287 | ||
86763fdd RW |
6288 | (define-public r-dexseq |
6289 | (package | |
6290 | (name "r-dexseq") | |
16da69b5 | 6291 | (version "1.26.0") |
86763fdd RW |
6292 | (source |
6293 | (origin | |
6294 | (method url-fetch) | |
6295 | (uri (bioconductor-uri "DEXSeq" version)) | |
6296 | (sha256 | |
6297 | (base32 | |
16da69b5 | 6298 | "1mqb3mdxcsi3largsl7k27bvqrgps9ixv806xvmf29pw0xn05sg1")))) |
86763fdd RW |
6299 | (properties `((upstream-name . "DEXSeq"))) |
6300 | (build-system r-build-system) | |
6301 | (propagated-inputs | |
6302 | `(("r-annotationdbi" ,r-annotationdbi) | |
6303 | ("r-biobase" ,r-biobase) | |
6304 | ("r-biocgenerics" ,r-biocgenerics) | |
6305 | ("r-biocparallel" ,r-biocparallel) | |
6306 | ("r-biomart" ,r-biomart) | |
6307 | ("r-deseq2" ,r-deseq2) | |
6308 | ("r-genefilter" ,r-genefilter) | |
6309 | ("r-geneplotter" ,r-geneplotter) | |
6310 | ("r-genomicranges" ,r-genomicranges) | |
6311 | ("r-hwriter" ,r-hwriter) | |
6312 | ("r-iranges" ,r-iranges) | |
6313 | ("r-rcolorbrewer" ,r-rcolorbrewer) | |
6314 | ("r-rsamtools" ,r-rsamtools) | |
6315 | ("r-s4vectors" ,r-s4vectors) | |
6316 | ("r-statmod" ,r-statmod) | |
6317 | ("r-stringr" ,r-stringr) | |
6318 | ("r-summarizedexperiment" ,r-summarizedexperiment))) | |
5713bbf1 | 6319 | (home-page "https://bioconductor.org/packages/DEXSeq") |
86763fdd RW |
6320 | (synopsis "Inference of differential exon usage in RNA-Seq") |
6321 | (description | |
6322 | "This package is focused on finding differential exon usage using RNA-seq | |
6323 | exon counts between samples with different experimental designs. It provides | |
6324 | functions that allows the user to make the necessary statistical tests based | |
6325 | on a model that uses the negative binomial distribution to estimate the | |
6326 | variance between biological replicates and generalized linear models for | |
6327 | testing. The package also provides functions for the visualization and | |
6328 | exploration of the results.") | |
6329 | (license license:gpl3+))) | |
6330 | ||
e8163773 RW |
6331 | (define-public r-annotationforge |
6332 | (package | |
6333 | (name "r-annotationforge") | |
5516db9e | 6334 | (version "1.22.0") |
e8163773 RW |
6335 | (source |
6336 | (origin | |
6337 | (method url-fetch) | |
6338 | (uri (bioconductor-uri "AnnotationForge" version)) | |
6339 | (sha256 | |
6340 | (base32 | |
5516db9e | 6341 | "12ffj7h95adiya5mzyjxazqn1qgr434ajpabfcyhrj5v83s4vk65")))) |
e8163773 RW |
6342 | (properties |
6343 | `((upstream-name . "AnnotationForge"))) | |
6344 | (build-system r-build-system) | |
6345 | (propagated-inputs | |
6346 | `(("r-annotationdbi" ,r-annotationdbi) | |
6347 | ("r-biobase" ,r-biobase) | |
6348 | ("r-biocgenerics" ,r-biocgenerics) | |
6349 | ("r-dbi" ,r-dbi) | |
55cd914c | 6350 | ("r-rcurl" ,r-rcurl) |
e8163773 RW |
6351 | ("r-rsqlite" ,r-rsqlite) |
6352 | ("r-s4vectors" ,r-s4vectors) | |
6353 | ("r-xml" ,r-xml))) | |
5713bbf1 | 6354 | (home-page "https://bioconductor.org/packages/AnnotationForge") |
e8163773 RW |
6355 | (synopsis "Code for building annotation database packages") |
6356 | (description | |
6357 | "This package provides code for generating Annotation packages and their | |
6358 | databases. Packages produced are intended to be used with AnnotationDbi.") | |
6359 | (license license:artistic2.0))) | |
6360 | ||
cd9e7dc7 RW |
6361 | (define-public r-rbgl |
6362 | (package | |
6363 | (name "r-rbgl") | |
9177ac22 | 6364 | (version "1.56.0") |
cd9e7dc7 RW |
6365 | (source |
6366 | (origin | |
6367 | (method url-fetch) | |
6368 | (uri (bioconductor-uri "RBGL" version)) | |
6369 | (sha256 | |
6370 | (base32 | |
9177ac22 | 6371 | "0hj972mmqpyi5fx1rq33kysavdyz4nspi6gcffzi3rv339m0anhf")))) |
cd9e7dc7 RW |
6372 | (properties `((upstream-name . "RBGL"))) |
6373 | (build-system r-build-system) | |
6374 | (propagated-inputs `(("r-graph" ,r-graph))) | |
5713bbf1 | 6375 | (home-page "https://www.bioconductor.org/packages/RBGL") |
cd9e7dc7 RW |
6376 | (synopsis "Interface to the Boost graph library") |
6377 | (description | |
6378 | "This package provides a fairly extensive and comprehensive interface to | |
6379 | the graph algorithms contained in the Boost library.") | |
6380 | (license license:artistic2.0))) | |
6381 | ||
ad740ff8 RW |
6382 | (define-public r-gseabase |
6383 | (package | |
6384 | (name "r-gseabase") | |
f1094f50 | 6385 | (version "1.42.0") |
ad740ff8 RW |
6386 | (source |
6387 | (origin | |
6388 | (method url-fetch) | |
6389 | (uri (bioconductor-uri "GSEABase" version)) | |
6390 | (sha256 | |
6391 | (base32 | |
f1094f50 | 6392 | "11bv92svik399q677jv96b71i4bq68xxyxn1yijpdik2lq4hgl7a")))) |
ad740ff8 RW |
6393 | (properties `((upstream-name . "GSEABase"))) |
6394 | (build-system r-build-system) | |
6395 | (propagated-inputs | |
6396 | `(("r-annotate" ,r-annotate) | |
6397 | ("r-annotationdbi" ,r-annotationdbi) | |
6398 | ("r-biobase" ,r-biobase) | |
6399 | ("r-biocgenerics" ,r-biocgenerics) | |
6400 | ("r-graph" ,r-graph) | |
6401 | ("r-xml" ,r-xml))) | |
5713bbf1 | 6402 | (home-page "https://bioconductor.org/packages/GSEABase") |
ad740ff8 RW |
6403 | (synopsis "Gene set enrichment data structures and methods") |
6404 | (description | |
6405 | "This package provides classes and methods to support @dfn{Gene Set | |
6406 | Enrichment Analysis} (GSEA).") | |
6407 | (license license:artistic2.0))) | |
6408 | ||
1a1931f7 RW |
6409 | (define-public r-category |
6410 | (package | |
6411 | (name "r-category") | |
d8410d66 | 6412 | (version "2.46.0") |
1a1931f7 RW |
6413 | (source |
6414 | (origin | |
6415 | (method url-fetch) | |
6416 | (uri (bioconductor-uri "Category" version)) | |
6417 | (sha256 | |
6418 | (base32 | |
d8410d66 | 6419 | "03wfqa8d1dgwsm327zl2mpkq7dq3mzhq12598qz3ylfhrwplbgx0")))) |
1a1931f7 RW |
6420 | (properties `((upstream-name . "Category"))) |
6421 | (build-system r-build-system) | |
6422 | (propagated-inputs | |
6423 | `(("r-annotate" ,r-annotate) | |
6424 | ("r-annotationdbi" ,r-annotationdbi) | |
6425 | ("r-biobase" ,r-biobase) | |
6426 | ("r-biocgenerics" ,r-biocgenerics) | |
6427 | ("r-genefilter" ,r-genefilter) | |
6428 | ("r-graph" ,r-graph) | |
6429 | ("r-gseabase" ,r-gseabase) | |
6430 | ("r-matrix" ,r-matrix) | |
6431 | ("r-rbgl" ,r-rbgl) | |
2404cc42 | 6432 | ("r-dbi" ,r-dbi))) |
5713bbf1 | 6433 | (home-page "https://bioconductor.org/packages/Category") |
1a1931f7 RW |
6434 | (synopsis "Category analysis") |
6435 | (description | |
6436 | "This package provides a collection of tools for performing category | |
6437 | analysis.") | |
6438 | (license license:artistic2.0))) | |
6439 | ||
89f40c5e RW |
6440 | (define-public r-gostats |
6441 | (package | |
6442 | (name "r-gostats") | |
9da8e275 | 6443 | (version "2.46.0") |
89f40c5e RW |
6444 | (source |
6445 | (origin | |
6446 | (method url-fetch) | |
6447 | (uri (bioconductor-uri "GOstats" version)) | |
6448 | (sha256 | |
6449 | (base32 | |
9da8e275 | 6450 | "1i5mydz5d95w2k28qr9j01hmbnl2id55jq94jvcpcyp1pvinkdq0")))) |
89f40c5e RW |
6451 | (properties `((upstream-name . "GOstats"))) |
6452 | (build-system r-build-system) | |
6453 | (propagated-inputs | |
6454 | `(("r-annotate" ,r-annotate) | |
6455 | ("r-annotationdbi" ,r-annotationdbi) | |
6456 | ("r-annotationforge" ,r-annotationforge) | |
6457 | ("r-biobase" ,r-biobase) | |
6458 | ("r-category" ,r-category) | |
6459 | ("r-go-db" ,r-go-db) | |
6460 | ("r-graph" ,r-graph) | |
eb3f5cc7 | 6461 | ("r-rgraphviz" ,r-rgraphviz) |
89f40c5e | 6462 | ("r-rbgl" ,r-rbgl))) |
5713bbf1 | 6463 | (home-page "https://bioconductor.org/packages/GOstats") |
89f40c5e RW |
6464 | (synopsis "Tools for manipulating GO and microarrays") |
6465 | (description | |
6466 | "This package provides a set of tools for interacting with GO and | |
6467 | microarray data. A variety of basic manipulation tools for graphs, hypothesis | |
6468 | testing and other simple calculations.") | |
6469 | (license license:artistic2.0))) | |
6470 | ||
cb99d457 RW |
6471 | (define-public r-shortread |
6472 | (package | |
6473 | (name "r-shortread") | |
eabe78fa | 6474 | (version "1.38.0") |
cb99d457 RW |
6475 | (source |
6476 | (origin | |
6477 | (method url-fetch) | |
6478 | (uri (bioconductor-uri "ShortRead" version)) | |
6479 | (sha256 | |
6480 | (base32 | |
eabe78fa | 6481 | "038z3z7qaw5bpgjzy91sjkybsny6jwjjsrnnq4gdqdw9ss1qy1fb")))) |
cb99d457 RW |
6482 | (properties `((upstream-name . "ShortRead"))) |
6483 | (build-system r-build-system) | |
6484 | (inputs | |
6485 | `(("zlib" ,zlib))) | |
6486 | (propagated-inputs | |
6487 | `(("r-biobase" ,r-biobase) | |
6488 | ("r-biocgenerics" ,r-biocgenerics) | |
6489 | ("r-biocparallel" ,r-biocparallel) | |
6490 | ("r-biostrings" ,r-biostrings) | |
6491 | ("r-genomeinfodb" ,r-genomeinfodb) | |
6492 | ("r-genomicalignments" ,r-genomicalignments) | |
6493 | ("r-genomicranges" ,r-genomicranges) | |
6494 | ("r-hwriter" ,r-hwriter) | |
6495 | ("r-iranges" ,r-iranges) | |
6496 | ("r-lattice" ,r-lattice) | |
6497 | ("r-latticeextra" ,r-latticeextra) | |
6498 | ("r-rsamtools" ,r-rsamtools) | |
6499 | ("r-s4vectors" ,r-s4vectors) | |
6500 | ("r-xvector" ,r-xvector) | |
6501 | ("r-zlibbioc" ,r-zlibbioc))) | |
5713bbf1 | 6502 | (home-page "https://bioconductor.org/packages/ShortRead") |
cb99d457 RW |
6503 | (synopsis "FASTQ input and manipulation tools") |
6504 | (description | |
6505 | "This package implements sampling, iteration, and input of FASTQ files. | |
6506 | It includes functions for filtering and trimming reads, and for generating a | |
6507 | quality assessment report. Data are represented as | |
6508 | @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of | |
6509 | purposes. The package also contains legacy support for early single-end, | |
6510 | ungapped alignment formats.") | |
6511 | (license license:artistic2.0))) | |
6512 | ||
7f903d73 RW |
6513 | (define-public r-systempiper |
6514 | (package | |
6515 | (name "r-systempiper") | |
712fe396 | 6516 | (version "1.14.0") |
7f903d73 RW |
6517 | (source |
6518 | (origin | |
6519 | (method url-fetch) | |
6520 | (uri (bioconductor-uri "systemPipeR" version)) | |
6521 | (sha256 | |
6522 | (base32 | |
712fe396 | 6523 | "1550pd63mmky0vgkmpni7zf14kqz1741wv63nfaw29kcmhh3m5lm")))) |
7f903d73 RW |
6524 | (properties `((upstream-name . "systemPipeR"))) |
6525 | (build-system r-build-system) | |
6526 | (propagated-inputs | |
6527 | `(("r-annotate" ,r-annotate) | |
6528 | ("r-batchjobs" ,r-batchjobs) | |
6529 | ("r-biocgenerics" ,r-biocgenerics) | |
6530 | ("r-biostrings" ,r-biostrings) | |
6531 | ("r-deseq2" ,r-deseq2) | |
6532 | ("r-edger" ,r-edger) | |
6533 | ("r-genomicfeatures" ,r-genomicfeatures) | |
6534 | ("r-genomicranges" ,r-genomicranges) | |
6535 | ("r-ggplot2" ,r-ggplot2) | |
6536 | ("r-go-db" ,r-go-db) | |
6537 | ("r-gostats" ,r-gostats) | |
6538 | ("r-limma" ,r-limma) | |
6539 | ("r-pheatmap" ,r-pheatmap) | |
6540 | ("r-rjson" ,r-rjson) | |
6541 | ("r-rsamtools" ,r-rsamtools) | |
6542 | ("r-shortread" ,r-shortread) | |
6543 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
6544 | ("r-variantannotation" ,r-variantannotation))) | |
6545 | (home-page "https://github.com/tgirke/systemPipeR") | |
6546 | (synopsis "Next generation sequencing workflow and reporting environment") | |
6547 | (description | |
6548 | "This R package provides tools for building and running automated | |
6549 | end-to-end analysis workflows for a wide range of @dfn{next generation | |
6550 | sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq. | |
6551 | Important features include a uniform workflow interface across different NGS | |
6552 | applications, automated report generation, and support for running both R and | |
6553 | command-line software, such as NGS aligners or peak/variant callers, on local | |
6554 | computers or compute clusters. Efficient handling of complex sample sets and | |
6555 | experimental designs is facilitated by a consistently implemented sample | |
6556 | annotation infrastructure.") | |
6557 | (license license:artistic2.0))) | |
6558 | ||
684f29bd RW |
6559 | (define-public r-grohmm |
6560 | (package | |
6561 | (name "r-grohmm") | |
9370b8ee | 6562 | (version "1.14.0") |
684f29bd RW |
6563 | (source |
6564 | (origin | |
6565 | (method url-fetch) | |
6566 | (uri (bioconductor-uri "groHMM" version)) | |
6567 | (sha256 | |
6568 | (base32 | |
9370b8ee | 6569 | "1kjb14apyly44qdlx2ld6gr69wlazd4mbhs58l35hir12aphgrzp")))) |
684f29bd RW |
6570 | (properties `((upstream-name . "groHMM"))) |
6571 | (build-system r-build-system) | |
6572 | (propagated-inputs | |
6573 | `(("r-genomeinfodb" ,r-genomeinfodb) | |
6574 | ("r-genomicalignments" ,r-genomicalignments) | |
6575 | ("r-genomicranges" ,r-genomicranges) | |
6576 | ("r-iranges" ,r-iranges) | |
aeb64f3c | 6577 | ("r-mass" ,r-mass) |
684f29bd RW |
6578 | ("r-rtracklayer" ,r-rtracklayer) |
6579 | ("r-s4vectors" ,r-s4vectors))) | |
6580 | (home-page "https://github.com/Kraus-Lab/groHMM") | |
6581 | (synopsis "GRO-seq analysis pipeline") | |
6582 | (description | |
6583 | "This package provides a pipeline for the analysis of GRO-seq data.") | |
6584 | (license license:gpl3+))) | |
6585 | ||
f3cfe451 RW |
6586 | (define-public r-txdb-hsapiens-ucsc-hg19-knowngene |
6587 | (package | |
6588 | (name "r-txdb-hsapiens-ucsc-hg19-knowngene") | |
6589 | (version "3.2.2") | |
6590 | (source (origin | |
6591 | (method url-fetch) | |
6592 | ;; We cannot use bioconductor-uri here because this tarball is | |
6593 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 6594 | (uri (string-append "https://bioconductor.org/packages/" |
f3cfe451 RW |
6595 | "release/data/annotation/src/contrib" |
6596 | "/TxDb.Hsapiens.UCSC.hg19.knownGene_" | |
6597 | version ".tar.gz")) | |
6598 | (sha256 | |
6599 | (base32 | |
6600 | "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86")))) | |
6601 | (properties | |
6602 | `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene"))) | |
6603 | (build-system r-build-system) | |
6604 | ;; As this package provides little more than a very large data file it | |
6605 | ;; doesn't make sense to build substitutes. | |
6606 | (arguments `(#:substitutable? #f)) | |
6607 | (propagated-inputs | |
6608 | `(("r-genomicfeatures" ,r-genomicfeatures))) | |
6609 | (home-page | |
5713bbf1 | 6610 | "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/") |
f3cfe451 RW |
6611 | (synopsis "Annotation package for human genome in TxDb format") |
6612 | (description | |
6613 | "This package provides an annotation database of Homo sapiens genome | |
6614 | data. It is derived from the UCSC hg19 genome and based on the \"knownGene\" | |
6615 | track. The database is exposed as a @code{TxDb} object.") | |
6616 | (license license:artistic2.0))) | |
6617 | ||
325c039c RJ |
6618 | (define-public r-sparql |
6619 | (package | |
6620 | (name "r-sparql") | |
6621 | (version "1.16") | |
6622 | (source (origin | |
6623 | (method url-fetch) | |
6624 | (uri (cran-uri "SPARQL" version)) | |
6625 | (sha256 | |
6626 | (base32 | |
6627 | "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc")))) | |
6628 | (properties `((upstream-name . "SPARQL"))) | |
6629 | (build-system r-build-system) | |
6630 | (propagated-inputs | |
6631 | `(("r-rcurl" ,r-rcurl) | |
6632 | ("r-xml" ,r-xml))) | |
e9960d8c | 6633 | (home-page "https://cran.r-project.org/web/packages/SPARQL") |
325c039c RJ |
6634 | (synopsis "SPARQL client for R") |
6635 | (description "This package provides an interface to use SPARQL to pose | |
6636 | SELECT or UPDATE queries to an end-point.") | |
6637 | ;; The only license indication is found in the DESCRIPTION file, | |
6638 | ;; which states GPL-3. So we cannot assume GPLv3+. | |
6639 | (license license:gpl3))) | |
6640 | ||
a2950fa4 BW |
6641 | (define-public vsearch |
6642 | (package | |
6643 | (name "vsearch") | |
53ec1b7e | 6644 | (version "2.8.0") |
a2950fa4 BW |
6645 | (source |
6646 | (origin | |
6647 | (method url-fetch) | |
6648 | (uri (string-append | |
6649 | "https://github.com/torognes/vsearch/archive/v" | |
6650 | version ".tar.gz")) | |
6651 | (file-name (string-append name "-" version ".tar.gz")) | |
6652 | (sha256 | |
6653 | (base32 | |
53ec1b7e | 6654 | "15pbirgzhvflj4pi5n82vybbzjy9mlb0lv5l3qhrmdkfzpbyahw3")) |
206af46f | 6655 | (patches (search-patches "vsearch-unbundle-cityhash.patch")) |
a2950fa4 BW |
6656 | (snippet |
6657 | '(begin | |
206af46f BW |
6658 | ;; Remove bundled cityhash sources. The vsearch source is adjusted |
6659 | ;; for this in the patch. | |
cf6edaba BW |
6660 | (delete-file "src/city.h") |
6661 | (delete-file "src/citycrc.h") | |
6662 | (delete-file "src/city.cc") | |
a2950fa4 BW |
6663 | #t)))) |
6664 | (build-system gnu-build-system) | |
6665 | (arguments | |
6666 | `(#:phases | |
6667 | (modify-phases %standard-phases | |
d10092b8 KK |
6668 | (add-after 'unpack 'autogen |
6669 | (lambda _ (zero? (system* "autoreconf" "-vif"))))))) | |
a2950fa4 BW |
6670 | (inputs |
6671 | `(("zlib" ,zlib) | |
6672 | ("bzip2" ,bzip2) | |
6673 | ("cityhash" ,cityhash))) | |
6674 | (native-inputs | |
6675 | `(("autoconf" ,autoconf) | |
6676 | ("automake" ,automake))) | |
6677 | (synopsis "Sequence search tools for metagenomics") | |
6678 | (description | |
6679 | "VSEARCH supports DNA sequence searching, clustering, chimera detection, | |
6680 | dereplication, pairwise alignment, shuffling, subsampling, sorting and | |
6681 | masking. The tool takes advantage of parallelism in the form of SIMD | |
6682 | vectorization as well as multiple threads to perform accurate alignments at | |
6683 | high speed. VSEARCH uses an optimal global aligner (full dynamic programming | |
6684 | Needleman-Wunsch).") | |
6685 | (home-page "https://github.com/torognes/vsearch") | |
6f04e515 BW |
6686 | ;; vsearch uses non-portable SSE intrinsics so building fails on other |
6687 | ;; platforms. | |
6688 | (supported-systems '("x86_64-linux")) | |
a2950fa4 BW |
6689 | ;; Dual licensed; also includes public domain source. |
6690 | (license (list license:gpl3 license:bsd-2)))) | |
6691 | ||
07837874 RW |
6692 | (define-public pardre |
6693 | (package | |
6694 | (name "pardre") | |
7922ab8f BW |
6695 | ;; The source of 1.1.5 changed in place, so we append "-1" to the version. |
6696 | (version "1.1.5-1") | |
07837874 RW |
6697 | (source |
6698 | (origin | |
6699 | (method url-fetch) | |
6700 | (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel" | |
7922ab8f | 6701 | "1.1.5" ".tar.gz")) |
07837874 RW |
6702 | (sha256 |
6703 | (base32 | |
7922ab8f | 6704 | "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b")))) |
07837874 RW |
6705 | (build-system gnu-build-system) |
6706 | (arguments | |
6707 | `(#:tests? #f ; no tests included | |
6708 | #:phases | |
6709 | (modify-phases %standard-phases | |
6710 | (delete 'configure) | |
6711 | (replace 'install | |
6712 | (lambda* (#:key outputs #:allow-other-keys) | |
6713 | (let ((bin (string-append (assoc-ref outputs "out") "/bin"))) | |
07837874 RW |
6714 | (install-file "ParDRe" bin) |
6715 | #t)))))) | |
6716 | (inputs | |
6717 | `(("openmpi" ,openmpi) | |
6718 | ("zlib" ,zlib))) | |
6719 | (synopsis "Parallel tool to remove duplicate DNA reads") | |
6720 | (description | |
6721 | "ParDRe is a parallel tool to remove duplicate genetic sequence reads. | |
6722 | Duplicate reads can be seen as identical or nearly identical sequences with | |
6723 | some mismatches. This tool lets users avoid the analysis of unnecessary | |
6724 | reads, reducing the time of subsequent procedures with the | |
6725 | dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI | |
6726 | in order to exploit the parallel capabilities of multicore clusters. It is | |
6727 | faster than multithreaded counterparts (end of 2015) for the same number of | |
6728 | cores and, thanks to the message-passing technology, it can be executed on | |
6729 | clusters.") | |
6730 | (home-page "https://sourceforge.net/projects/pardre/") | |
6731 | (license license:gpl3+))) | |
6732 | ||
e4a44a6a BW |
6733 | (define-public ruby-bio-kseq |
6734 | (package | |
6735 | (name "ruby-bio-kseq") | |
6736 | (version "0.0.2") | |
6737 | (source | |
6738 | (origin | |
6739 | (method url-fetch) | |
6740 | (uri (rubygems-uri "bio-kseq" version)) | |
6741 | (sha256 | |
6742 | (base32 | |
6743 | "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz")))) | |
6744 | (build-system ruby-build-system) | |
6745 | (arguments | |
6746 | `(#:test-target "spec")) | |
6747 | (native-inputs | |
6748 | `(("bundler" ,bundler) | |
6749 | ("ruby-rspec" ,ruby-rspec) | |
6750 | ("ruby-rake-compiler" ,ruby-rake-compiler))) | |
6751 | (inputs | |
6752 | `(("zlib" ,zlib))) | |
6753 | (synopsis "Ruby bindings for the kseq.h FASTA/Q parser") | |
6754 | (description | |
6755 | "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and | |
6756 | FASTQ parsing code. It provides a fast iterator over sequences and their | |
6757 | quality scores.") | |
6758 | (home-page "https://github.com/gusevfe/bio-kseq") | |
6759 | (license license:expat))) | |
6760 | ||
9c38b540 PP |
6761 | (define-public bio-locus |
6762 | (package | |
6763 | (name "bio-locus") | |
6764 | (version "0.0.7") | |
6765 | (source | |
6766 | (origin | |
6767 | (method url-fetch) | |
6768 | (uri (rubygems-uri "bio-locus" version)) | |
6769 | (sha256 | |
6770 | (base32 | |
6771 | "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0")))) | |
6772 | (build-system ruby-build-system) | |
6773 | (native-inputs | |
6774 | `(("ruby-rspec" ,ruby-rspec))) | |
6775 | (synopsis "Tool for fast querying of genome locations") | |
6776 | (description | |
6777 | "Bio-locus is a tabix-like tool for fast querying of genome | |
6778 | locations. Many file formats in bioinformatics contain records that | |
6779 | start with a chromosome name and a position for a SNP, or a start-end | |
6780 | position for indels. Bio-locus allows users to store this chr+pos or | |
6781 | chr+pos+alt information in a database.") | |
6782 | (home-page "https://github.com/pjotrp/bio-locus") | |
6783 | (license license:expat))) | |
edb15985 | 6784 | |
b2bddb07 PP |
6785 | (define-public bio-blastxmlparser |
6786 | (package | |
6787 | (name "bio-blastxmlparser") | |
6788 | (version "2.0.4") | |
6789 | (source (origin | |
6790 | (method url-fetch) | |
6791 | (uri (rubygems-uri "bio-blastxmlparser" version)) | |
6792 | (sha256 | |
6793 | (base32 | |
6794 | "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692")))) | |
6795 | (build-system ruby-build-system) | |
6796 | (propagated-inputs | |
6797 | `(("ruby-bio-logger" ,ruby-bio-logger) | |
6798 | ("ruby-nokogiri" ,ruby-nokogiri))) | |
6799 | (inputs | |
6800 | `(("ruby-rspec" ,ruby-rspec))) | |
6801 | (synopsis "Fast big data BLAST XML parser and library") | |
6802 | (description | |
6803 | "Very fast parallel big-data BLAST XML file parser which can be used as | |
6804 | command line utility. Use blastxmlparser to: Parse BLAST XML; filter output; | |
6805 | generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.") | |
7bf837fd | 6806 | (home-page "https://github.com/pjotrp/blastxmlparser") |
b2bddb07 PP |
6807 | (license license:expat))) |
6808 | ||
edb15985 PP |
6809 | (define-public bioruby |
6810 | (package | |
6811 | (name "bioruby") | |
dbf9d371 | 6812 | (version "1.5.1") |
edb15985 PP |
6813 | (source |
6814 | (origin | |
6815 | (method url-fetch) | |
6816 | (uri (rubygems-uri "bio" version)) | |
6817 | (sha256 | |
6818 | (base32 | |
dbf9d371 | 6819 | "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49")))) |
edb15985 PP |
6820 | (build-system ruby-build-system) |
6821 | (propagated-inputs | |
6822 | `(("ruby-libxml" ,ruby-libxml))) | |
6823 | (native-inputs | |
6824 | `(("which" ,which))) ; required for test phase | |
6825 | (arguments | |
6826 | `(#:phases | |
6827 | (modify-phases %standard-phases | |
6828 | (add-before 'build 'patch-test-command | |
6829 | (lambda _ | |
6830 | (substitute* '("test/functional/bio/test_command.rb") | |
6831 | (("/bin/sh") (which "sh"))) | |
6832 | (substitute* '("test/functional/bio/test_command.rb") | |
6833 | (("/bin/ls") (which "ls"))) | |
6834 | (substitute* '("test/functional/bio/test_command.rb") | |
6835 | (("which") (which "which"))) | |
6836 | (substitute* '("test/functional/bio/test_command.rb", | |
6837 | "test/data/command/echoarg2.sh") | |
6838 | (("/bin/echo") (which "echo"))) | |
6839 | #t))))) | |
6840 | (synopsis "Ruby library, shell and utilities for bioinformatics") | |
6841 | (description "BioRuby comes with a comprehensive set of Ruby development | |
6842 | tools and libraries for bioinformatics and molecular biology. BioRuby has | |
6843 | components for sequence analysis, pathway analysis, protein modelling and | |
6844 | phylogenetic analysis; it supports many widely used data formats and provides | |
6845 | easy access to databases, external programs and public web services, including | |
6846 | BLAST, KEGG, GenBank, MEDLINE and GO.") | |
6847 | (home-page "http://bioruby.org/") | |
6848 | ;; Code is released under Ruby license, except for setup | |
6849 | ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+) | |
6850 | (license (list license:ruby license:lgpl2.1+ license:gpl2+ )))) | |
a5002ae7 | 6851 | |
9fba89e8 RW |
6852 | (define-public r-acsnminer |
6853 | (package | |
6854 | (name "r-acsnminer") | |
0b54b4c9 | 6855 | (version "0.16.8.25") |
9fba89e8 RW |
6856 | (source (origin |
6857 | (method url-fetch) | |
6858 | (uri (cran-uri "ACSNMineR" version)) | |
6859 | (sha256 | |
6860 | (base32 | |
0b54b4c9 | 6861 | "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l")))) |
9fba89e8 RW |
6862 | (properties `((upstream-name . "ACSNMineR"))) |
6863 | (build-system r-build-system) | |
6864 | (propagated-inputs | |
6865 | `(("r-ggplot2" ,r-ggplot2) | |
6866 | ("r-gridextra" ,r-gridextra))) | |
e9960d8c | 6867 | (home-page "https://cran.r-project.org/web/packages/ACSNMineR") |
9fba89e8 RW |
6868 | (synopsis "Gene enrichment analysis") |
6869 | (description | |
6870 | "This package provides tools to compute and represent gene set enrichment | |
6871 | or depletion from your data based on pre-saved maps from the @dfn{Atlas of | |
6872 | Cancer Signalling Networks} (ACSN) or user imported maps. The gene set | |
6873 | enrichment can be run with hypergeometric test or Fisher exact test, and can | |
6874 | use multiple corrections. Visualization of data can be done either by | |
6875 | barplots or heatmaps.") | |
6876 | (license license:gpl2+))) | |
6877 | ||
d29b25c4 RW |
6878 | (define-public r-biocgenerics |
6879 | (package | |
6880 | (name "r-biocgenerics") | |
e5907a44 | 6881 | (version "0.26.0") |
d29b25c4 RW |
6882 | (source (origin |
6883 | (method url-fetch) | |
6884 | (uri (bioconductor-uri "BiocGenerics" version)) | |
6885 | (sha256 | |
6886 | (base32 | |
e5907a44 | 6887 | "19qxhy2cd3pykkhzbb5q3crgaxf65cpzf2mkfsz16gqhi8flj72p")))) |
d29b25c4 | 6888 | (properties |
1d216b6e | 6889 | `((upstream-name . "BiocGenerics"))) |
d29b25c4 | 6890 | (build-system r-build-system) |
5713bbf1 | 6891 | (home-page "https://bioconductor.org/packages/BiocGenerics") |
d29b25c4 RW |
6892 | (synopsis "S4 generic functions for Bioconductor") |
6893 | (description | |
6894 | "This package provides S4 generic functions needed by many Bioconductor | |
6895 | packages.") | |
6896 | (license license:artistic2.0))) | |
6897 | ||
eb24341f RJ |
6898 | (define-public r-biocinstaller |
6899 | (package | |
6900 | (name "r-biocinstaller") | |
97af51ef | 6901 | (version "1.30.0") |
eb24341f RJ |
6902 | (source (origin |
6903 | (method url-fetch) | |
6904 | (uri (bioconductor-uri "BiocInstaller" version)) | |
6905 | (sha256 | |
6906 | (base32 | |
97af51ef | 6907 | "1xg1gi1hf5vflp71ji21gnmr4kcjpx8a6c47cllpc7yqnjv5nfg0")))) |
eb24341f RJ |
6908 | (properties |
6909 | `((upstream-name . "BiocInstaller"))) | |
6910 | (build-system r-build-system) | |
5713bbf1 | 6911 | (home-page "https://bioconductor.org/packages/BiocInstaller") |
eb24341f RJ |
6912 | (synopsis "Install Bioconductor packages") |
6913 | (description "This package is used to install and update R packages from | |
6914 | Bioconductor, CRAN, and Github.") | |
6915 | (license license:artistic2.0))) | |
6916 | ||
207ce8fb RJ |
6917 | (define-public r-biocviews |
6918 | (package | |
6919 | (name "r-biocviews") | |
e5f52b69 | 6920 | (version "1.48.0") |
207ce8fb RJ |
6921 | (source (origin |
6922 | (method url-fetch) | |
6923 | (uri (bioconductor-uri "biocViews" version)) | |
6924 | (sha256 | |
6925 | (base32 | |
e5f52b69 | 6926 | "1yx2lir67ny0j150wyfqca0wsxp84byri8nscbs9qlndkh2jppq9")))) |
207ce8fb RJ |
6927 | (properties |
6928 | `((upstream-name . "biocViews"))) | |
6929 | (build-system r-build-system) | |
6930 | (propagated-inputs | |
6931 | `(("r-biobase" ,r-biobase) | |
6932 | ("r-graph" ,r-graph) | |
6933 | ("r-rbgl" ,r-rbgl) | |
6934 | ("r-rcurl" ,r-rcurl) | |
6935 | ("r-xml" ,r-xml) | |
207ce8fb | 6936 | ("r-runit" ,r-runit))) |
5713bbf1 | 6937 | (home-page "https://bioconductor.org/packages/biocViews") |
207ce8fb RJ |
6938 | (synopsis "Bioconductor package categorization helper") |
6939 | (description "The purpose of biocViews is to create HTML pages that | |
6940 | categorize packages in a Bioconductor package repository according to keywords, | |
6941 | also known as views, in a controlled vocabulary.") | |
6942 | (license license:artistic2.0))) | |
6943 | ||
2abfc5b8 RJ |
6944 | (define-public r-bookdown |
6945 | (package | |
9800f7d9 RW |
6946 | (name "r-bookdown") |
6947 | (version "0.7") | |
6948 | (source (origin | |
6949 | (method url-fetch) | |
6950 | (uri (cran-uri "bookdown" version)) | |
6951 | (sha256 | |
6952 | (base32 | |
6953 | "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q")))) | |
6954 | (build-system r-build-system) | |
6955 | (propagated-inputs | |
6956 | `(("r-htmltools" ,r-htmltools) | |
6957 | ("r-knitr" ,r-knitr) | |
6958 | ("r-rmarkdown" ,r-rmarkdown) | |
6959 | ("r-tinytex" ,r-tinytex) | |
6960 | ("r-yaml" ,r-yaml) | |
618050a1 | 6961 | ("r-xfun" ,r-xfun))) |
9800f7d9 RW |
6962 | (home-page "https://github.com/rstudio/bookdown") |
6963 | (synopsis "Authoring books and technical documents with R markdown") | |
6964 | (description "This package provides output formats and utilities for | |
2abfc5b8 | 6965 | authoring books and technical documents with R Markdown.") |
9800f7d9 | 6966 | (license license:gpl3))) |
2abfc5b8 | 6967 | |
99df12cd RJ |
6968 | (define-public r-biocstyle |
6969 | (package | |
6970 | (name "r-biocstyle") | |
dc6c168a | 6971 | (version "2.8.2") |
99df12cd RJ |
6972 | (source (origin |
6973 | (method url-fetch) | |
6974 | (uri (bioconductor-uri "BiocStyle" version)) | |
6975 | (sha256 | |
6976 | (base32 | |
dc6c168a | 6977 | "17m901ylz00w1a3nq5f910v55zixm1nr6rb3qrsbhqd94qzr0l2p")))) |
99df12cd RJ |
6978 | (properties |
6979 | `((upstream-name . "BiocStyle"))) | |
6980 | (build-system r-build-system) | |
3bef24c9 RJ |
6981 | (propagated-inputs |
6982 | `(("r-bookdown" ,r-bookdown) | |
6983 | ("r-knitr" ,r-knitr) | |
6984 | ("r-rmarkdown" ,r-rmarkdown) | |
6985 | ("r-yaml" ,r-yaml))) | |
5713bbf1 | 6986 | (home-page "https://bioconductor.org/packages/BiocStyle") |
99df12cd RJ |
6987 | (synopsis "Bioconductor formatting styles") |
6988 | (description "This package provides standard formatting styles for | |
6989 | Bioconductor PDF and HTML documents. Package vignettes illustrate use and | |
6990 | functionality.") | |
6991 | (license license:artistic2.0))) | |
6992 | ||
4644644a RJ |
6993 | (define-public r-bioccheck |
6994 | (package | |
6995 | (name "r-bioccheck") | |
3679a2fe | 6996 | (version "1.16.0") |
4644644a RJ |
6997 | (source (origin |
6998 | (method url-fetch) | |
6999 | (uri (bioconductor-uri "BiocCheck" version)) | |
7000 | (sha256 | |
7001 | (base32 | |
3679a2fe | 7002 | "1srp1g809f1nn0fyqknr7r6dq89bw1xpjvmygr7cw6ffknbc671s")))) |
4644644a RJ |
7003 | (properties |
7004 | `((upstream-name . "BiocCheck"))) | |
7005 | (build-system r-build-system) | |
7006 | (arguments | |
7007 | '(#:phases | |
7008 | (modify-phases %standard-phases | |
7009 | ;; This package can be used by calling BiocCheck(<package>) from | |
7010 | ;; within R, or by running R CMD BiocCheck <package>. This phase | |
7011 | ;; makes sure the latter works. For this to work, the BiocCheck | |
7012 | ;; script must be somewhere on the PATH (not the R bin directory). | |
7013 | (add-after 'install 'install-bioccheck-subcommand | |
7014 | (lambda* (#:key outputs #:allow-other-keys) | |
7015 | (let* ((out (assoc-ref outputs "out")) | |
7016 | (dest-dir (string-append out "/bin")) | |
7017 | (script-dir | |
7018 | (string-append out "/site-library/BiocCheck/script/"))) | |
7019 | (mkdir-p dest-dir) | |
7020 | (symlink (string-append script-dir "/checkBadDeps.R") | |
7021 | (string-append dest-dir "/checkBadDeps.R")) | |
7022 | (symlink (string-append script-dir "/BiocCheck") | |
7023 | (string-append dest-dir "/BiocCheck"))) | |
7024 | #t))))) | |
4644644a | 7025 | (propagated-inputs |
aeb64f3c RW |
7026 | `(("r-codetools" ,r-codetools) |
7027 | ("r-graph" ,r-graph) | |
4644644a RJ |
7028 | ("r-httr" ,r-httr) |
7029 | ("r-optparse" ,r-optparse) | |
4644644a | 7030 | ("r-biocinstaller" ,r-biocinstaller) |
7373b416 RW |
7031 | ("r-biocviews" ,r-biocviews) |
7032 | ("r-stringdist" ,r-stringdist))) | |
5713bbf1 | 7033 | (home-page "https://bioconductor.org/packages/BiocCheck") |
4644644a RJ |
7034 | (synopsis "Executes Bioconductor-specific package checks") |
7035 | (description "This package contains tools to perform additional quality | |
7036 | checks on R packages that are to be submitted to the Bioconductor repository.") | |
7037 | (license license:artistic2.0))) | |
7038 | ||
2acaaee5 RJ |
7039 | (define-public r-getopt |
7040 | (package | |
7041 | (name "r-getopt") | |
e8484711 | 7042 | (version "1.20.2") |
2acaaee5 RJ |
7043 | (source |
7044 | (origin | |
7045 | (method url-fetch) | |
7046 | (uri (cran-uri "getopt" version)) | |
7047 | (sha256 | |
7048 | (base32 | |
e8484711 | 7049 | "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x")))) |
2acaaee5 RJ |
7050 | (build-system r-build-system) |
7051 | (home-page "https://github.com/trevorld/getopt") | |
7052 | (synopsis "Command-line option processor for R") | |
7053 | (description | |
7054 | "This package is designed to be used with Rscript to write shebang | |
7055 | scripts that accept short and long options. Many users will prefer to | |
7056 | use the packages @code{optparse} or @code{argparse} which add extra | |
7057 | features like automatically generated help options and usage texts, | |
7058 | support for default values, positional argument support, etc.") | |
7059 | (license license:gpl2+))) | |
7060 | ||
c79ad57a RJ |
7061 | (define-public r-optparse |
7062 | (package | |
7063 | (name "r-optparse") | |
7150f1c3 | 7064 | (version "1.4.4") |
c79ad57a RJ |
7065 | (source |
7066 | (origin | |
7067 | (method url-fetch) | |
7068 | (uri (cran-uri "optparse" version)) | |
7069 | (sha256 | |
7070 | (base32 | |
7150f1c3 | 7071 | "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb")))) |
c79ad57a RJ |
7072 | (build-system r-build-system) |
7073 | (propagated-inputs | |
7074 | `(("r-getopt" ,r-getopt))) | |
7075 | (home-page | |
7076 | "https://github.com/trevorld/optparse") | |
7077 | (synopsis "Command line option parser") | |
7078 | (description | |
7079 | "This package provides a command line parser inspired by Python's | |
7080 | @code{optparse} library to be used with Rscript to write shebang scripts | |
7081 | that accept short and long options.") | |
7082 | (license license:gpl2+))) | |
7083 | ||
247d498a RJ |
7084 | (define-public r-dnacopy |
7085 | (package | |
7086 | (name "r-dnacopy") | |
607acf31 | 7087 | (version "1.54.0") |
247d498a RJ |
7088 | (source (origin |
7089 | (method url-fetch) | |
7090 | (uri (bioconductor-uri "DNAcopy" version)) | |
7091 | (sha256 | |
7092 | (base32 | |
607acf31 | 7093 | "03hfhmmc5y60r2gcgm367w2fr7qj115l74m9bp3h9qpn5yci0d8n")))) |
247d498a RJ |
7094 | (properties |
7095 | `((upstream-name . "DNAcopy"))) | |
7096 | (build-system r-build-system) | |
7097 | (inputs | |
7098 | `(("gfortran" ,gfortran))) | |
5697fdc3 | 7099 | (home-page "https://bioconductor.org/packages/DNAcopy") |
247d498a RJ |
7100 | (synopsis "Implementation of a circular binary segmentation algorithm") |
7101 | (description "This package implements the circular binary segmentation (CBS) | |
7102 | algorithm to segment DNA copy number data and identify genomic regions with | |
7103 | abnormal copy number.") | |
7104 | (license license:gpl2+))) | |
7105 | ||
7485129e RW |
7106 | (define-public r-s4vectors |
7107 | (package | |
7108 | (name "r-s4vectors") | |
33cd15fa | 7109 | (version "0.18.2") |
7485129e RW |
7110 | (source (origin |
7111 | (method url-fetch) | |
7112 | (uri (bioconductor-uri "S4Vectors" version)) | |
7113 | (sha256 | |
7114 | (base32 | |
33cd15fa | 7115 | "0qvj2j0zl4djjl7vrwc6xak6h8dxr53iwypfbcvfb3sh7jwhdiz5")))) |
7485129e | 7116 | (properties |
1d216b6e | 7117 | `((upstream-name . "S4Vectors"))) |
7485129e RW |
7118 | (build-system r-build-system) |
7119 | (propagated-inputs | |
7120 | `(("r-biocgenerics" ,r-biocgenerics))) | |
5713bbf1 | 7121 | (home-page "https://bioconductor.org/packages/S4Vectors") |
7485129e RW |
7122 | (synopsis "S4 implementation of vectors and lists") |
7123 | (description | |
7124 | "The S4Vectors package defines the @code{Vector} and @code{List} virtual | |
7125 | classes and a set of generic functions that extend the semantic of ordinary | |
7126 | vectors and lists in R. Package developers can easily implement vector-like | |
7127 | or list-like objects as concrete subclasses of @code{Vector} or @code{List}. | |
7128 | In addition, a few low-level concrete subclasses of general interest (e.g. | |
7129 | @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the | |
7130 | S4Vectors package itself.") | |
7131 | (license license:artistic2.0))) | |
7132 | ||
274da826 RW |
7133 | (define-public r-seqinr |
7134 | (package | |
7135 | (name "r-seqinr") | |
023aa8ff | 7136 | (version "3.4-5") |
274da826 RW |
7137 | (source |
7138 | (origin | |
7139 | (method url-fetch) | |
7140 | (uri (cran-uri "seqinr" version)) | |
7141 | (sha256 | |
7142 | (base32 | |
023aa8ff | 7143 | "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn")))) |
274da826 RW |
7144 | (build-system r-build-system) |
7145 | (propagated-inputs | |
3b851cd4 RW |
7146 | `(("r-ade4" ,r-ade4) |
7147 | ("r-segmented" ,r-segmented))) | |
274da826 RW |
7148 | (inputs |
7149 | `(("zlib" ,zlib))) | |
7150 | (home-page "http://seqinr.r-forge.r-project.org/") | |
7151 | (synopsis "Biological sequences retrieval and analysis") | |
7152 | (description | |
7153 | "This package provides tools for exploratory data analysis and data | |
7154 | visualization of biological sequence (DNA and protein) data. It also includes | |
7155 | utilities for sequence data management under the ACNUC system.") | |
7156 | (license license:gpl2+))) | |
7157 | ||
78addcb0 RW |
7158 | (define-public r-iranges |
7159 | (package | |
7160 | (name "r-iranges") | |
8b44c28f | 7161 | (version "2.14.10") |
78addcb0 RW |
7162 | (source (origin |
7163 | (method url-fetch) | |
7164 | (uri (bioconductor-uri "IRanges" version)) | |
7165 | (sha256 | |
7166 | (base32 | |
8b44c28f | 7167 | "10ccw930vfmkskkrzbps14xglqlkxf588623dr7f1a9ckx7yr2p6")))) |
78addcb0 | 7168 | (properties |
1d216b6e | 7169 | `((upstream-name . "IRanges"))) |
78addcb0 RW |
7170 | (build-system r-build-system) |
7171 | (propagated-inputs | |
7172 | `(("r-biocgenerics" ,r-biocgenerics) | |
7173 | ("r-s4vectors" ,r-s4vectors))) | |
5713bbf1 | 7174 | (home-page "https://bioconductor.org/packages/IRanges") |
78addcb0 RW |
7175 | (synopsis "Infrastructure for manipulating intervals on sequences") |
7176 | (description | |
7177 | "This package provides efficient low-level and highly reusable S4 classes | |
7178 | for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more | |
7179 | generally, data that can be organized sequentially (formally defined as | |
7180 | @code{Vector} objects), as well as views on these @code{Vector} objects. | |
7181 | Efficient list-like classes are also provided for storing big collections of | |
7182 | instances of the basic classes. All classes in the package use consistent | |
7183 | naming and share the same rich and consistent \"Vector API\" as much as | |
7184 | possible.") | |
7185 | (license license:artistic2.0))) | |
7186 | ||
ffef27f3 RJ |
7187 | (define-public r-genomeinfodbdata |
7188 | (package | |
7189 | (name "r-genomeinfodbdata") | |
261b38a9 | 7190 | (version "0.99.1") |
ffef27f3 RJ |
7191 | (source (origin |
7192 | (method url-fetch) | |
90f83099 EF |
7193 | ;; We cannot use bioconductor-uri here because this tarball is |
7194 | ;; located under "data/annotation/" instead of "bioc/". | |
7195 | (uri (string-append "https://bioconductor.org/packages/release/" | |
7196 | "data/annotation/src/contrib/GenomeInfoDbData_" | |
7197 | version ".tar.gz")) | |
ffef27f3 RJ |
7198 | (sha256 |
7199 | (base32 | |
261b38a9 | 7200 | "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r")))) |
ffef27f3 RJ |
7201 | (properties |
7202 | `((upstream-name . "GenomeInfoDbData"))) | |
7203 | (build-system r-build-system) | |
5713bbf1 | 7204 | (home-page "https://bioconductor.org/packages/GenomeInfoDbData") |
ffef27f3 RJ |
7205 | (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb") |
7206 | (description "This package contains data for mapping between NCBI taxonomy | |
7207 | ID and species. It is used by functions in the GenomeInfoDb package.") | |
7208 | (license license:artistic2.0))) | |
7209 | ||
bf7764b7 RW |
7210 | (define-public r-genomeinfodb |
7211 | (package | |
7212 | (name "r-genomeinfodb") | |
953c8b18 | 7213 | (version "1.16.0") |
bf7764b7 RW |
7214 | (source (origin |
7215 | (method url-fetch) | |
7216 | (uri (bioconductor-uri "GenomeInfoDb" version)) | |
7217 | (sha256 | |
7218 | (base32 | |
953c8b18 | 7219 | "0yhnqhaydmmq7ihmhj3rbal4afq5p993l2qqrd0n5wmbyg7glg2d")))) |
bf7764b7 | 7220 | (properties |
1d216b6e | 7221 | `((upstream-name . "GenomeInfoDb"))) |
bf7764b7 RW |
7222 | (build-system r-build-system) |
7223 | (propagated-inputs | |
7224 | `(("r-biocgenerics" ,r-biocgenerics) | |
38b99ccc | 7225 | ("r-genomeinfodbdata" ,r-genomeinfodbdata) |
bf7764b7 | 7226 | ("r-iranges" ,r-iranges) |
4cd07e48 | 7227 | ("r-rcurl" ,r-rcurl) |
bf7764b7 | 7228 | ("r-s4vectors" ,r-s4vectors))) |
5713bbf1 | 7229 | (home-page "https://bioconductor.org/packages/GenomeInfoDb") |
bf7764b7 RW |
7230 | (synopsis "Utilities for manipulating chromosome identifiers") |
7231 | (description | |
7232 | "This package contains data and functions that define and allow | |
7233 | translation between different chromosome sequence naming conventions (e.g., | |
7234 | \"chr1\" versus \"1\"), including a function that attempts to place sequence | |
7235 | names in their natural, rather than lexicographic, order.") | |
7236 | (license license:artistic2.0))) | |
7237 | ||
744004a3 RJ |
7238 | (define-public r-edger |
7239 | (package | |
7240 | (name "r-edger") | |
46390252 | 7241 | (version "3.22.2") |
744004a3 RJ |
7242 | (source (origin |
7243 | (method url-fetch) | |
7244 | (uri (bioconductor-uri "edgeR" version)) | |
7245 | (sha256 | |
7246 | (base32 | |
46390252 | 7247 | "07py2g6vg9jbflwhc1hnzr2silbinrjwxq3mkq30nzjgf0n0hrf3")))) |
744004a3 RJ |
7248 | (properties `((upstream-name . "edgeR"))) |
7249 | (build-system r-build-system) | |
7250 | (propagated-inputs | |
5e48005f | 7251 | `(("r-limma" ,r-limma) |
47055b27 | 7252 | ("r-locfit" ,r-locfit) |
010ab2ff | 7253 | ("r-rcpp" ,r-rcpp) |
47055b27 | 7254 | ("r-statmod" ,r-statmod))) ;for estimateDisp |
744004a3 RJ |
7255 | (home-page "http://bioinf.wehi.edu.au/edgeR") |
7256 | (synopsis "EdgeR does empirical analysis of digital gene expression data") | |
7257 | (description "This package can do differential expression analysis of | |
7258 | RNA-seq expression profiles with biological replication. It implements a range | |
7259 | of statistical methodology based on the negative binomial distributions, | |
7260 | including empirical Bayes estimation, exact tests, generalized linear models | |
7261 | and quasi-likelihood tests. It be applied to differential signal analysis of | |
7262 | other types of genomic data that produce counts, including ChIP-seq, SAGE and | |
7263 | CAGE.") | |
7264 | (license license:gpl2+))) | |
7265 | ||
b669d9c4 RJ |
7266 | (define-public r-variantannotation |
7267 | (package | |
7268 | (name "r-variantannotation") | |
d358a5a0 | 7269 | (version "1.26.0") |
b669d9c4 RJ |
7270 | (source (origin |
7271 | (method url-fetch) | |
7272 | (uri (bioconductor-uri "VariantAnnotation" version)) | |
7273 | (sha256 | |
7274 | (base32 | |
d358a5a0 | 7275 | "06bccdf57vja7m63chmgc4539lwng3q3b8zxn285fj8524l6mcn7")))) |
b669d9c4 RJ |
7276 | (properties |
7277 | `((upstream-name . "VariantAnnotation"))) | |
7278 | (inputs | |
7279 | `(("zlib" ,zlib))) | |
7280 | (propagated-inputs | |
7281 | `(("r-annotationdbi" ,r-annotationdbi) | |
37d96f1d | 7282 | ("r-biobase" ,r-biobase) |
b669d9c4 | 7283 | ("r-biocgenerics" ,r-biocgenerics) |
37d96f1d | 7284 | ("r-biostrings" ,r-biostrings) |
b669d9c4 RJ |
7285 | ("r-bsgenome" ,r-bsgenome) |
7286 | ("r-dbi" ,r-dbi) | |
7287 | ("r-genomeinfodb" ,r-genomeinfodb) | |
7288 | ("r-genomicfeatures" ,r-genomicfeatures) | |
7289 | ("r-genomicranges" ,r-genomicranges) | |
37d96f1d | 7290 | ("r-iranges" ,r-iranges) |
b669d9c4 RJ |
7291 | ("r-summarizedexperiment" ,r-summarizedexperiment) |
7292 | ("r-rsamtools" ,r-rsamtools) | |
37d96f1d RW |
7293 | ("r-rtracklayer" ,r-rtracklayer) |
7294 | ("r-s4vectors" ,r-s4vectors) | |
7295 | ("r-xvector" ,r-xvector) | |
b669d9c4 RJ |
7296 | ("r-zlibbioc" ,r-zlibbioc))) |
7297 | (build-system r-build-system) | |
7298 | (home-page "https://bioconductor.org/packages/VariantAnnotation") | |
7299 | (synopsis "Package for annotation of genetic variants") | |
7300 | (description "This R package can annotate variants, compute amino acid | |
7301 | coding changes and predict coding outcomes.") | |
7302 | (license license:artistic2.0))) | |
7303 | ||
7d4224d7 RJ |
7304 | (define-public r-limma |
7305 | (package | |
7306 | (name "r-limma") | |
0a465e56 | 7307 | (version "3.36.1") |
7d4224d7 RJ |
7308 | (source (origin |
7309 | (method url-fetch) | |
7310 | (uri (bioconductor-uri "limma" version)) | |
7311 | (sha256 | |
7312 | (base32 | |
0a465e56 | 7313 | "1982g5v35ilfgxm2vkq1p3j1bbir795pjvfzx4nzam2rlqqymbqm")))) |
7d4224d7 RJ |
7314 | (build-system r-build-system) |
7315 | (home-page "http://bioinf.wehi.edu.au/limma") | |
7316 | (synopsis "Package for linear models for microarray and RNA-seq data") | |
7317 | (description "This package can be used for the analysis of gene expression | |
7318 | studies, especially the use of linear models for analysing designed experiments | |
7319 | and the assessment of differential expression. The analysis methods apply to | |
7320 | different technologies, including microarrays, RNA-seq, and quantitative PCR.") | |
7321 | (license license:gpl2+))) | |
7322 | ||
0e7d5560 RW |
7323 | (define-public r-xvector |
7324 | (package | |
7325 | (name "r-xvector") | |
c2401d06 | 7326 | (version "0.20.0") |
0e7d5560 RW |
7327 | (source (origin |
7328 | (method url-fetch) | |
7329 | (uri (bioconductor-uri "XVector" version)) | |
7330 | (sha256 | |
7331 | (base32 | |
c2401d06 | 7332 | "1zjlhh9lsyhg0js1858csyw2389kbrzdqnqnha833wazkwxilp3f")))) |
0e7d5560 | 7333 | (properties |
1d216b6e | 7334 | `((upstream-name . "XVector"))) |
0e7d5560 RW |
7335 | (build-system r-build-system) |
7336 | (arguments | |
7337 | `(#:phases | |
7338 | (modify-phases %standard-phases | |
7339 | (add-after 'unpack 'use-system-zlib | |
7340 | (lambda _ | |
7341 | (substitute* "DESCRIPTION" | |
7342 | (("zlibbioc, ") "")) | |
7343 | (substitute* "NAMESPACE" | |
7344 | (("import\\(zlibbioc\\)") "")) | |
7345 | #t))))) | |
7346 | (inputs | |
7347 | `(("zlib" ,zlib))) | |
7348 | (propagated-inputs | |
7349 | `(("r-biocgenerics" ,r-biocgenerics) | |
7350 | ("r-iranges" ,r-iranges) | |
7351 | ("r-s4vectors" ,r-s4vectors))) | |
5713bbf1 | 7352 | (home-page "https://bioconductor.org/packages/XVector") |
0e7d5560 RW |
7353 | (synopsis "Representation and manpulation of external sequences") |
7354 | (description | |
7355 | "This package provides memory efficient S4 classes for storing sequences | |
7356 | \"externally\" (behind an R external pointer, or on disk).") | |
7357 | (license license:artistic2.0))) | |
7358 | ||
e2cd1d0f RW |
7359 | (define-public r-genomicranges |
7360 | (package | |
7361 | (name "r-genomicranges") | |
e51afc63 | 7362 | (version "1.32.3") |
e2cd1d0f RW |
7363 | (source (origin |
7364 | (method url-fetch) | |
7365 | (uri (bioconductor-uri "GenomicRanges" version)) | |
7366 | (sha256 | |
7367 | (base32 | |
e51afc63 | 7368 | "03gmka6rlz18vd4229796l5l3l6446v5cb90sn2nb5knjbp84hni")))) |
e2cd1d0f | 7369 | (properties |
1d216b6e | 7370 | `((upstream-name . "GenomicRanges"))) |
e2cd1d0f RW |
7371 | (build-system r-build-system) |
7372 | (propagated-inputs | |
7373 | `(("r-biocgenerics" ,r-biocgenerics) | |
7374 | ("r-genomeinfodb" ,r-genomeinfodb) | |
92a740af RW |
7375 | ("r-iranges" ,r-iranges) |
7376 | ("r-s4vectors" ,r-s4vectors) | |
e2cd1d0f | 7377 | ("r-xvector" ,r-xvector))) |
5713bbf1 | 7378 | (home-page "https://bioconductor.org/packages/GenomicRanges") |
e2cd1d0f RW |
7379 | (synopsis "Representation and manipulation of genomic intervals") |
7380 | (description | |
7381 | "This package provides tools to efficiently represent and manipulate | |
7382 | genomic annotations and alignments is playing a central role when it comes to | |
7383 | analyzing high-throughput sequencing data (a.k.a. NGS data). The | |
7384 | GenomicRanges package defines general purpose containers for storing and | |
7385 | manipulating genomic intervals and variables defined along a genome.") | |
7386 | (license license:artistic2.0))) | |
7387 | ||
555e3399 RW |
7388 | (define-public r-biobase |
7389 | (package | |
7390 | (name "r-biobase") | |
6fd71f1b | 7391 | (version "2.40.0") |
555e3399 RW |
7392 | (source (origin |
7393 | (method url-fetch) | |
7394 | (uri (bioconductor-uri "Biobase" version)) | |
7395 | (sha256 | |
7396 | (base32 | |
6fd71f1b | 7397 | "1iwds2a5ir29k19dbpynlc7nn836cw2gamchhgpi2jf2xar9m9jz")))) |
555e3399 RW |
7398 | (properties |
7399 | `((upstream-name . "Biobase"))) | |
7400 | (build-system r-build-system) | |
7401 | (propagated-inputs | |
7402 | `(("r-biocgenerics" ,r-biocgenerics))) | |
5713bbf1 | 7403 | (home-page "https://bioconductor.org/packages/Biobase") |
555e3399 RW |
7404 | (synopsis "Base functions for Bioconductor") |
7405 | (description | |
7406 | "This package provides functions that are needed by many other packages | |
7407 | on Bioconductor or which replace R functions.") | |
7408 | (license license:artistic2.0))) | |
7409 | ||
8b7bce74 RW |
7410 | (define-public r-annotationdbi |
7411 | (package | |
7412 | (name "r-annotationdbi") | |
77f66fee | 7413 | (version "1.42.1") |
8b7bce74 RW |
7414 | (source (origin |
7415 | (method url-fetch) | |
7416 | (uri (bioconductor-uri "AnnotationDbi" version)) | |
7417 | (sha256 | |
7418 | (base32 | |
77f66fee | 7419 | "0afkbzli08vq02r2pr9phrz3rxd6ilp1w7yw8y99nbjiz14f8b1c")))) |
8b7bce74 RW |
7420 | (properties |
7421 | `((upstream-name . "AnnotationDbi"))) | |
7422 | (build-system r-build-system) | |
7423 | (propagated-inputs | |
7424 | `(("r-biobase" ,r-biobase) | |
7425 | ("r-biocgenerics" ,r-biocgenerics) | |
7426 | ("r-dbi" ,r-dbi) | |
7427 | ("r-iranges" ,r-iranges) | |
7428 | ("r-rsqlite" ,r-rsqlite) | |
7429 | ("r-s4vectors" ,r-s4vectors))) | |
5713bbf1 | 7430 | (home-page "https://bioconductor.org/packages/AnnotationDbi") |
8b7bce74 RW |
7431 | (synopsis "Annotation database interface") |
7432 | (description | |
7433 | "This package provides user interface and database connection code for | |
7434 | annotation data packages using SQLite data storage.") | |
7435 | (license license:artistic2.0))) | |
7436 | ||
c465fa72 RW |
7437 | (define-public r-biomart |
7438 | (package | |
7439 | (name "r-biomart") | |
1763cba8 | 7440 | (version "2.36.1") |
c465fa72 RW |
7441 | (source (origin |
7442 | (method url-fetch) | |
7443 | (uri (bioconductor-uri "biomaRt" version)) | |
7444 | (sha256 | |
7445 | (base32 | |
1763cba8 | 7446 | "0b70s350ffc74v3xz5c3jpazr9zxdb7gjmjfj7aghlsrizrspill")))) |
c465fa72 RW |
7447 | (properties |
7448 | `((upstream-name . "biomaRt"))) | |
7449 | (build-system r-build-system) | |
7450 | (propagated-inputs | |
7451 | `(("r-annotationdbi" ,r-annotationdbi) | |
b9e8a5c5 | 7452 | ("r-httr" ,r-httr) |
42e11d33 | 7453 | ("r-progress" ,r-progress) |
c465fa72 | 7454 | ("r-rcurl" ,r-rcurl) |
42e11d33 | 7455 | ("r-stringr" ,r-stringr) |
c465fa72 | 7456 | ("r-xml" ,r-xml))) |
5713bbf1 | 7457 | (home-page "https://bioconductor.org/packages/biomaRt") |
c465fa72 RW |
7458 | (synopsis "Interface to BioMart databases") |
7459 | (description | |
7460 | "biomaRt provides an interface to a growing collection of databases | |
7461 | implementing the @url{BioMart software suite, http://www.biomart.org}. The | |
7462 | package enables retrieval of large amounts of data in a uniform way without | |
7463 | the need to know the underlying database schemas or write complex SQL queries. | |
7464 | Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene, | |
7465 | Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt | |
7466 | users direct access to a diverse set of data and enable a wide range of | |
7467 | powerful online queries from gene annotation to database mining.") | |
7468 | (license license:artistic2.0))) | |
7469 | ||
e91d362e RW |
7470 | (define-public r-biocparallel |
7471 | (package | |
7472 | (name "r-biocparallel") | |
a044c7f4 | 7473 | (version "1.12.0") |
e91d362e RW |
7474 | (source (origin |
7475 | (method url-fetch) | |
7476 | (uri (bioconductor-uri "BiocParallel" version)) | |
7477 | (sha256 | |
7478 | (base32 | |
a044c7f4 | 7479 | "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd")))) |
e91d362e RW |
7480 | (properties |
7481 | `((upstream-name . "BiocParallel"))) | |
7482 | (build-system r-build-system) | |
7483 | (propagated-inputs | |
7484 | `(("r-futile-logger" ,r-futile-logger) | |
a044c7f4 RW |
7485 | ("r-snow" ,r-snow) |
7486 | ("r-bh" ,r-bh))) | |
5713bbf1 | 7487 | (home-page "https://bioconductor.org/packages/BiocParallel") |
e91d362e RW |
7488 | (synopsis "Bioconductor facilities for parallel evaluation") |
7489 | (description | |
7490 | "This package provides modified versions and novel implementation of | |
7491 | functions for parallel evaluation, tailored to use with Bioconductor | |
7492 | objects.") | |
7493 | (license (list license:gpl2+ license:gpl3+)))) | |
7494 | ||
bf159353 RW |
7495 | (define-public r-biostrings |
7496 | (package | |
7497 | (name "r-biostrings") | |
b719435e | 7498 | (version "2.46.0") |
bf159353 RW |
7499 | (source (origin |
7500 | (method url-fetch) | |
7501 | (uri (bioconductor-uri "Biostrings" version)) | |
7502 | (sha256 | |
7503 | (base32 | |
b719435e | 7504 | "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk")))) |
bf159353 RW |
7505 | (properties |
7506 | `((upstream-name . "Biostrings"))) | |
7507 | (build-system r-build-system) | |
7508 | (propagated-inputs | |
7509 | `(("r-biocgenerics" ,r-biocgenerics) | |
7510 | ("r-iranges" ,r-iranges) | |
7511 | ("r-s4vectors" ,r-s4vectors) | |
7512 | ("r-xvector" ,r-xvector))) | |
5713bbf1 | 7513 | (home-page "https://bioconductor.org/packages/Biostrings") |
bf159353 RW |
7514 | (synopsis "String objects and algorithms for biological sequences") |
7515 | (description | |
7516 | "This package provides memory efficient string containers, string | |
7517 | matching algorithms, and other utilities, for fast manipulation of large | |
7518 | biological sequences or sets of sequences.") | |
7519 | (license license:artistic2.0))) | |
7520 | ||
f8d74f70 RW |
7521 | (define-public r-rsamtools |
7522 | (package | |
7523 | (name "r-rsamtools") | |
f8068419 | 7524 | (version "1.30.0") |
f8d74f70 RW |
7525 | (source (origin |
7526 | (method url-fetch) | |
7527 | (uri (bioconductor-uri "Rsamtools" version)) | |
7528 | (sha256 | |
7529 | (base32 | |
f8068419 | 7530 | "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams")))) |
f8d74f70 RW |
7531 | (properties |
7532 | `((upstream-name . "Rsamtools"))) | |
7533 | (build-system r-build-system) | |
7534 | (arguments | |
7535 | `(#:phases | |
7536 | (modify-phases %standard-phases | |
7537 | (add-after 'unpack 'use-system-zlib | |
7538 | (lambda _ | |
7539 | (substitute* "DESCRIPTION" | |
7540 | (("zlibbioc, ") "")) | |
7541 | (substitute* "NAMESPACE" | |
7542 | (("import\\(zlibbioc\\)") "")) | |
7543 | #t))))) | |
7544 | (inputs | |
7545 | `(("zlib" ,zlib))) | |
7546 | (propagated-inputs | |
7547 | `(("r-biocgenerics" ,r-biocgenerics) | |
7548 | ("r-biocparallel" ,r-biocparallel) | |
7549 | ("r-biostrings" ,r-biostrings) | |
7550 | ("r-bitops" ,r-bitops) | |
7551 | ("r-genomeinfodb" ,r-genomeinfodb) | |
7552 | ("r-genomicranges" ,r-genomicranges) | |
7553 | ("r-iranges" ,r-iranges) | |
7554 | ("r-s4vectors" ,r-s4vectors) | |
7555 | ("r-xvector" ,r-xvector))) | |
5713bbf1 | 7556 | (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html") |
f8d74f70 RW |
7557 | (synopsis "Interface to samtools, bcftools, and tabix") |
7558 | (description | |
7559 | "This package provides an interface to the 'samtools', 'bcftools', and | |
7560 | 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA, | |
7561 | binary variant call (BCF) and compressed indexed tab-delimited (tabix) | |
7562 | files.") | |
7563 | (license license:expat))) | |
7564 | ||
71e34e6b RJ |
7565 | (define-public r-delayedarray |
7566 | (package | |
7567 | (name "r-delayedarray") | |
cb0a9a74 | 7568 | (version "0.4.1") |
71e34e6b RJ |
7569 | (source (origin |
7570 | (method url-fetch) | |
7571 | (uri (bioconductor-uri "DelayedArray" version)) | |
7572 | (sha256 | |
7573 | (base32 | |
cb0a9a74 | 7574 | "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b")))) |
71e34e6b RJ |
7575 | (properties |
7576 | `((upstream-name . "DelayedArray"))) | |
7577 | (build-system r-build-system) | |
7578 | (propagated-inputs | |
7579 | `(("r-biocgenerics" ,r-biocgenerics) | |
7580 | ("r-s4vectors" ,r-s4vectors) | |
7581 | ("r-iranges" ,r-iranges) | |
7582 | ("r-matrixstats" ,r-matrixstats))) | |
5713bbf1 | 7583 | (home-page "https://bioconductor.org/packages/DelayedArray") |
71e34e6b RJ |
7584 | (synopsis "Delayed operations on array-like objects") |
7585 | (description | |
7586 | "Wrapping an array-like object (typically an on-disk object) in a | |
7587 | @code{DelayedArray} object allows one to perform common array operations on it | |
7588 | without loading the object in memory. In order to reduce memory usage and | |
7589 | optimize performance, operations on the object are either delayed or executed | |
7590 | using a block processing mechanism. Note that this also works on in-memory | |
7591 | array-like objects like @code{DataFrame} objects (typically with Rle columns), | |
7592 | @code{Matrix} objects, and ordinary arrays and data frames.") | |
7593 | (license license:artistic2.0))) | |
7594 | ||
6e76dda2 RW |
7595 | (define-public r-summarizedexperiment |
7596 | (package | |
7597 | (name "r-summarizedexperiment") | |
c37b361e | 7598 | (version "1.8.1") |
6e76dda2 RW |
7599 | (source (origin |
7600 | (method url-fetch) | |
7601 | (uri (bioconductor-uri "SummarizedExperiment" version)) | |
7602 | (sha256 | |
7603 | (base32 | |
c37b361e | 7604 | "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh")))) |
6e76dda2 RW |
7605 | (properties |
7606 | `((upstream-name . "SummarizedExperiment"))) | |
7607 | (build-system r-build-system) | |
7608 | (propagated-inputs | |
7609 | `(("r-biobase" ,r-biobase) | |
7610 | ("r-biocgenerics" ,r-biocgenerics) | |
d006ee31 | 7611 | ("r-delayedarray" ,r-delayedarray) |
6e76dda2 RW |
7612 | ("r-genomeinfodb" ,r-genomeinfodb) |
7613 | ("r-genomicranges" ,r-genomicranges) | |
7614 | ("r-iranges" ,r-iranges) | |
aeb64f3c | 7615 | ("r-matrix" ,r-matrix) |
6e76dda2 | 7616 | ("r-s4vectors" ,r-s4vectors))) |
5713bbf1 | 7617 | (home-page "https://bioconductor.org/packages/SummarizedExperiment") |
6e76dda2 RW |
7618 | (synopsis "Container for representing genomic ranges by sample") |
7619 | (description | |
7620 | "The SummarizedExperiment container contains one or more assays, each | |
7621 | represented by a matrix-like object of numeric or other mode. The rows | |
7622 | typically represent genomic ranges of interest and the columns represent | |
7623 | samples.") | |
7624 | (license license:artistic2.0))) | |
7625 | ||
d8a828af RW |
7626 | (define-public r-genomicalignments |
7627 | (package | |
7628 | (name "r-genomicalignments") | |
0bd5c7b8 | 7629 | (version "1.14.2") |
d8a828af RW |
7630 | (source (origin |
7631 | (method url-fetch) | |
7632 | (uri (bioconductor-uri "GenomicAlignments" version)) | |
7633 | (sha256 | |
7634 | (base32 | |
0bd5c7b8 | 7635 | "1659nj1xps7vliy5955i51x6hvrf16n1z0dfh10mmpaaswn2d2mv")))) |
d8a828af RW |
7636 | (properties |
7637 | `((upstream-name . "GenomicAlignments"))) | |
7638 | (build-system r-build-system) | |
7639 | (propagated-inputs | |
7640 | `(("r-biocgenerics" ,r-biocgenerics) | |
7641 | ("r-biocparallel" ,r-biocparallel) | |
7642 | ("r-biostrings" ,r-biostrings) | |
7643 | ("r-genomeinfodb" ,r-genomeinfodb) | |
7644 | ("r-genomicranges" ,r-genomicranges) | |
7645 | ("r-iranges" ,r-iranges) | |
7646 | ("r-rsamtools" ,r-rsamtools) | |
7647 | ("r-s4vectors" ,r-s4vectors) | |
7648 | ("r-summarizedexperiment" ,r-summarizedexperiment))) | |
5713bbf1 | 7649 | (home-page "https://bioconductor.org/packages/GenomicAlignments") |
d8a828af RW |
7650 | (synopsis "Representation and manipulation of short genomic alignments") |
7651 | (description | |
7652 | "This package provides efficient containers for storing and manipulating | |
7653 | short genomic alignments (typically obtained by aligning short reads to a | |
7654 | reference genome). This includes read counting, computing the coverage, | |
7655 | junction detection, and working with the nucleotide content of the | |
7656 | alignments.") | |
7657 | (license license:artistic2.0))) | |
7658 | ||
317755ff RW |
7659 | (define-public r-rtracklayer |
7660 | (package | |
7661 | (name "r-rtracklayer") | |
99b3236e | 7662 | (version "1.38.3") |
317755ff RW |
7663 | (source (origin |
7664 | (method url-fetch) | |
7665 | (uri (bioconductor-uri "rtracklayer" version)) | |
7666 | (sha256 | |
7667 | (base32 | |
99b3236e | 7668 | "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k")))) |
317755ff RW |
7669 | (build-system r-build-system) |
7670 | (arguments | |
7671 | `(#:phases | |
7672 | (modify-phases %standard-phases | |
7673 | (add-after 'unpack 'use-system-zlib | |
7674 | (lambda _ | |
7675 | (substitute* "DESCRIPTION" | |
4dd469ef | 7676 | ((" zlibbioc,") "")) |
317755ff RW |
7677 | (substitute* "NAMESPACE" |
7678 | (("import\\(zlibbioc\\)") "")) | |
7679 | #t))))) | |
7680 | (inputs | |
7681 | `(("zlib" ,zlib))) | |
7682 | (propagated-inputs | |
7683 | `(("r-biocgenerics" ,r-biocgenerics) | |
7684 | ("r-biostrings" ,r-biostrings) | |
7685 | ("r-genomeinfodb" ,r-genomeinfodb) | |
7686 | ("r-genomicalignments" ,r-genomicalignments) | |
7687 | ("r-genomicranges" ,r-genomicranges) | |
7688 | ("r-iranges" ,r-iranges) | |
7689 | ("r-rcurl" ,r-rcurl) | |
7690 | ("r-rsamtools" ,r-rsamtools) | |
7691 | ("r-s4vectors" ,r-s4vectors) | |
7692 | ("r-xml" ,r-xml) | |
7693 | ("r-xvector" ,r-xvector))) | |
5713bbf1 | 7694 | (home-page "https://bioconductor.org/packages/rtracklayer") |
317755ff RW |
7695 | (synopsis "R interface to genome browsers and their annotation tracks") |
7696 | (description | |
7697 | "rtracklayer is an extensible framework for interacting with multiple | |
7698 | genome browsers (currently UCSC built-in) and manipulating annotation tracks | |
7699 | in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit | |
7700 | built-in). The user may export/import tracks to/from the supported browsers, | |
7701 | as well as query and modify the browser state, such as the current viewport.") | |
7702 | (license license:artistic2.0))) | |
7703 | ||
2fd7c049 RW |
7704 | (define-public r-genomicfeatures |
7705 | (package | |
7706 | (name "r-genomicfeatures") | |
0b188565 | 7707 | (version "1.30.3") |
2fd7c049 RW |
7708 | (source (origin |
7709 | (method url-fetch) | |
7710 | (uri (bioconductor-uri "GenomicFeatures" version)) | |
7711 | (sha256 | |
7712 | (base32 | |
0b188565 | 7713 | "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z")))) |
2fd7c049 RW |
7714 | (properties |
7715 | `((upstream-name . "GenomicFeatures"))) | |
7716 | (build-system r-build-system) | |
7717 | (propagated-inputs | |
7718 | `(("r-annotationdbi" ,r-annotationdbi) | |
7719 | ("r-biobase" ,r-biobase) | |
7720 | ("r-biocgenerics" ,r-biocgenerics) | |
7721 | ("r-biomart" ,r-biomart) | |
7722 | ("r-biostrings" ,r-biostrings) | |
7723 | ("r-dbi" ,r-dbi) | |
7724 | ("r-genomeinfodb" ,r-genomeinfodb) | |
7725 | ("r-genomicranges" ,r-genomicranges) | |
7726 | ("r-iranges" ,r-iranges) | |
7727 | ("r-rcurl" ,r-rcurl) | |
7728 | ("r-rsqlite" ,r-rsqlite) | |
158b6743 | 7729 | ("r-rmysql" ,r-rmysql) |
2fd7c049 RW |
7730 | ("r-rtracklayer" ,r-rtracklayer) |
7731 | ("r-s4vectors" ,r-s4vectors) | |
7732 | ("r-xvector" ,r-xvector))) | |
5713bbf1 | 7733 | (home-page "https://bioconductor.org/packages/GenomicFeatures") |
2fd7c049 RW |
7734 | (synopsis "Tools for working with transcript centric annotations") |
7735 | (description | |
7736 | "This package provides a set of tools and methods for making and | |
7737 | manipulating transcript centric annotations. With these tools the user can | |
7738 | easily download the genomic locations of the transcripts, exons and cds of a | |
7739 | given organism, from either the UCSC Genome Browser or a BioMart | |
7740 | database (more sources will be supported in the future). This information is | |
7741 | then stored in a local database that keeps track of the relationship between | |
7742 | transcripts, exons, cds and genes. Flexible methods are provided for | |
7743 | extracting the desired features in a convenient format.") | |
7744 | (license license:artistic2.0))) | |
7745 | ||
fb25d880 RW |
7746 | (define-public r-go-db |
7747 | (package | |
7748 | (name "r-go-db") | |
592f4a94 | 7749 | (version "3.5.0") |
fb25d880 RW |
7750 | (source (origin |
7751 | (method url-fetch) | |
5713bbf1 | 7752 | (uri (string-append "https://www.bioconductor.org/packages/" |
f82c8c3c PP |
7753 | "release/data/annotation/src/contrib/GO.db_" |
7754 | version ".tar.gz")) | |
fb25d880 RW |
7755 | (sha256 |
7756 | (base32 | |
592f4a94 | 7757 | "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35")))) |
fb25d880 RW |
7758 | (properties |
7759 | `((upstream-name . "GO.db"))) | |
7760 | (build-system r-build-system) | |
3141b83d RW |
7761 | (propagated-inputs |
7762 | `(("r-annotationdbi" ,r-annotationdbi))) | |
5713bbf1 | 7763 | (home-page "https://bioconductor.org/packages/GO.db") |
fb25d880 RW |
7764 | (synopsis "Annotation maps describing the entire Gene Ontology") |
7765 | (description | |
7766 | "The purpose of this GO.db annotation package is to provide detailed | |
7767 | information about the latest version of the Gene Ontologies.") | |
7768 | (license license:artistic2.0))) | |
7769 | ||
d1dbde6a RW |
7770 | (define-public r-graph |
7771 | (package | |
7772 | (name "r-graph") | |
aeb73879 | 7773 | (version "1.56.0") |
d1dbde6a RW |
7774 | (source (origin |
7775 | (method url-fetch) | |
7776 | (uri (bioconductor-uri "graph" version)) | |
7777 | (sha256 | |
7778 | (base32 | |
aeb73879 | 7779 | "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1")))) |
d1dbde6a RW |
7780 | (build-system r-build-system) |
7781 | (propagated-inputs | |
7782 | `(("r-biocgenerics" ,r-biocgenerics))) | |
5713bbf1 | 7783 | (home-page "https://bioconductor.org/packages/graph") |
d1dbde6a RW |
7784 | (synopsis "Handle graph data structures in R") |
7785 | (description | |
7786 | "This package implements some simple graph handling capabilities for R.") | |
7787 | (license license:artistic2.0))) | |
7788 | ||
d547ce5e RW |
7789 | (define-public r-topgo |
7790 | (package | |
7791 | (name "r-topgo") | |
61cbd49b | 7792 | (version "2.30.1") |
d547ce5e RW |
7793 | (source (origin |
7794 | (method url-fetch) | |
7795 | (uri (bioconductor-uri "topGO" version)) | |
7796 | (sha256 | |
7797 | (base32 | |
61cbd49b | 7798 | "1cgz4knxr328xfqlhl6ypxl6x86rfrlqz748kn94ainxjzz55i6x")))) |
d547ce5e RW |
7799 | (properties |
7800 | `((upstream-name . "topGO"))) | |
7801 | (build-system r-build-system) | |
7802 | (propagated-inputs | |
7803 | `(("r-annotationdbi" ,r-annotationdbi) | |
30ec4de7 | 7804 | ("r-dbi" ,r-dbi) |
d547ce5e RW |
7805 | ("r-biobase" ,r-biobase) |
7806 | ("r-biocgenerics" ,r-biocgenerics) | |
7807 | ("r-go-db" ,r-go-db) | |
6d415db2 | 7808 | ("r-graph" ,r-graph) |
aeb64f3c RW |
7809 | ("r-lattice" ,r-lattice) |
7810 | ("r-matrixstats" ,r-matrixstats) | |
d547ce5e | 7811 | ("r-sparsem" ,r-sparsem))) |
5713bbf1 | 7812 | (home-page "https://bioconductor.org/packages/topGO") |
d547ce5e RW |
7813 | (synopsis "Enrichment analysis for gene ontology") |
7814 | (description | |
7815 | "The topGO package provides tools for testing @dfn{gene ontology} (GO) | |
7816 | terms while accounting for the topology of the GO graph. Different test | |
7817 | statistics and different methods for eliminating local similarities and | |
7818 | dependencies between GO terms can be implemented and applied.") | |
7819 | ;; Any version of the LGPL applies. | |
7820 | (license license:lgpl2.1+))) | |
7821 | ||
c63cef66 RW |
7822 | (define-public r-bsgenome |
7823 | (package | |
7824 | (name "r-bsgenome") | |
e67850b4 | 7825 | (version "1.46.0") |
c63cef66 RW |
7826 | (source (origin |
7827 | (method url-fetch) | |
7828 | (uri (bioconductor-uri "BSgenome" version)) | |
7829 | (sha256 | |
7830 | (base32 | |
e67850b4 | 7831 | "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq")))) |
c63cef66 RW |
7832 | (properties |
7833 | `((upstream-name . "BSgenome"))) | |
7834 | (build-system r-build-system) | |
7835 | (propagated-inputs | |
7836 | `(("r-biocgenerics" ,r-biocgenerics) | |
7837 | ("r-biostrings" ,r-biostrings) | |
7838 | ("r-genomeinfodb" ,r-genomeinfodb) | |
7839 | ("r-genomicranges" ,r-genomicranges) | |
7840 | ("r-iranges" ,r-iranges) | |
7841 | ("r-rsamtools" ,r-rsamtools) | |
7842 | ("r-rtracklayer" ,r-rtracklayer) | |
7843 | ("r-s4vectors" ,r-s4vectors) | |
7844 | ("r-xvector" ,r-xvector))) | |
5713bbf1 | 7845 | (home-page "https://bioconductor.org/packages/BSgenome") |
c63cef66 RW |
7846 | (synopsis "Infrastructure for Biostrings-based genome data packages") |
7847 | (description | |
7848 | "This package provides infrastructure shared by all Biostrings-based | |
7849 | genome data packages and support for efficient SNP representation.") | |
7850 | (license license:artistic2.0))) | |
7851 | ||
aa3eeeb5 RJ |
7852 | (define-public r-bsgenome-hsapiens-1000genomes-hs37d5 |
7853 | (package | |
7854 | (name "r-bsgenome-hsapiens-1000genomes-hs37d5") | |
7855 | (version "0.99.1") | |
7856 | (source (origin | |
7857 | (method url-fetch) | |
7858 | ;; We cannot use bioconductor-uri here because this tarball is | |
7859 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 7860 | (uri (string-append "https://www.bioconductor.org/packages/" |
aa3eeeb5 RJ |
7861 | "release/data/annotation/src/contrib/" |
7862 | "BSgenome.Hsapiens.1000genomes.hs37d5_" | |
7863 | version ".tar.gz")) | |
7864 | (sha256 | |
7865 | (base32 | |
7866 | "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr")))) | |
7867 | (properties | |
7868 | `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5"))) | |
7869 | (build-system r-build-system) | |
7870 | ;; As this package provides little more than a very large data file it | |
7871 | ;; doesn't make sense to build substitutes. | |
7872 | (arguments `(#:substitutable? #f)) | |
7873 | (propagated-inputs | |
7874 | `(("r-bsgenome" ,r-bsgenome))) | |
7875 | (home-page | |
5713bbf1 | 7876 | "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/") |
aa3eeeb5 RJ |
7877 | (synopsis "Full genome sequences for Homo sapiens") |
7878 | (description | |
7879 | "This package provides full genome sequences for Homo sapiens from | |
7880 | 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.") | |
7881 | (license license:artistic2.0))) | |
7882 | ||
c43a011d RW |
7883 | (define-public r-impute |
7884 | (package | |
7885 | (name "r-impute") | |
e6ce4bf0 | 7886 | (version "1.52.0") |
c43a011d RW |
7887 | (source (origin |
7888 | (method url-fetch) | |
7889 | (uri (bioconductor-uri "impute" version)) | |
7890 | (sha256 | |
7891 | (base32 | |
e6ce4bf0 | 7892 | "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n")))) |
c43a011d RW |
7893 | (inputs |
7894 | `(("gfortran" ,gfortran))) | |
7895 | (build-system r-build-system) | |
5713bbf1 | 7896 | (home-page "https://bioconductor.org/packages/impute") |
c43a011d RW |
7897 | (synopsis "Imputation for microarray data") |
7898 | (description | |
7899 | "This package provides a function to impute missing gene expression | |
7900 | microarray data, using nearest neighbor averaging.") | |
7901 | (license license:gpl2+))) | |
7902 | ||
03ea5a35 RW |
7903 | (define-public r-seqpattern |
7904 | (package | |
7905 | (name "r-seqpattern") | |
0f948b11 | 7906 | (version "1.10.0") |
03ea5a35 RW |
7907 | (source (origin |
7908 | (method url-fetch) | |
7909 | (uri (bioconductor-uri "seqPattern" version)) | |
7910 | (sha256 | |
7911 | (base32 | |
0f948b11 | 7912 | "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm")))) |
03ea5a35 RW |
7913 | (properties |
7914 | `((upstream-name . "seqPattern"))) | |
7915 | (build-system r-build-system) | |
7916 | (propagated-inputs | |
7917 | `(("r-biostrings" ,r-biostrings) | |
7918 | ("r-genomicranges" ,r-genomicranges) | |
7919 | ("r-iranges" ,r-iranges) | |
e92dd6f5 | 7920 | ("r-kernsmooth" ,r-kernsmooth) |
03ea5a35 | 7921 | ("r-plotrix" ,r-plotrix))) |
5713bbf1 | 7922 | (home-page "https://bioconductor.org/packages/seqPattern") |
03ea5a35 RW |
7923 | (synopsis "Visualising oligonucleotide patterns and motif occurrences") |
7924 | (description | |
7925 | "This package provides tools to visualize oligonucleotide patterns and | |
7926 | sequence motif occurrences across a large set of sequences centred at a common | |
7927 | reference point and sorted by a user defined feature.") | |
7928 | (license license:gpl3+))) | |
7929 | ||
cb933df6 RW |
7930 | (define-public r-genomation |
7931 | (package | |
7932 | (name "r-genomation") | |
e1129446 | 7933 | (version "1.11.3") |
cb933df6 RW |
7934 | (source (origin |
7935 | (method url-fetch) | |
7936 | (uri (bioconductor-uri "genomation" version)) | |
7937 | (sha256 | |
7938 | (base32 | |
e1129446 | 7939 | "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v")))) |
cb933df6 RW |
7940 | (build-system r-build-system) |
7941 | (propagated-inputs | |
7942 | `(("r-biostrings" ,r-biostrings) | |
7943 | ("r-bsgenome" ,r-bsgenome) | |
7944 | ("r-data-table" ,r-data-table) | |
7945 | ("r-genomeinfodb" ,r-genomeinfodb) | |
7946 | ("r-genomicalignments" ,r-genomicalignments) | |
7947 | ("r-genomicranges" ,r-genomicranges) | |
7948 | ("r-ggplot2" ,r-ggplot2) | |
7949 | ("r-gridbase" ,r-gridbase) | |
7950 | ("r-impute" ,r-impute) | |
7951 | ("r-iranges" ,r-iranges) | |
7952 | ("r-matrixstats" ,r-matrixstats) | |
7953 | ("r-plotrix" ,r-plotrix) | |
7954 | ("r-plyr" ,r-plyr) | |
51c3c490 | 7955 | ("r-rcpp" ,r-rcpp) |
cb933df6 RW |
7956 | ("r-readr" ,r-readr) |
7957 | ("r-reshape2" ,r-reshape2) | |
7958 | ("r-rsamtools" ,r-rsamtools) | |
7959 | ("r-rtracklayer" ,r-rtracklayer) | |
51c3c490 RW |
7960 | ("r-runit" ,r-runit) |
7961 | ("r-s4vectors" ,r-s4vectors) | |
cb933df6 RW |
7962 | ("r-seqpattern" ,r-seqpattern))) |
7963 | (home-page "http://bioinformatics.mdc-berlin.de/genomation/") | |
7964 | (synopsis "Summary, annotation and visualization of genomic data") | |
7965 | (description | |
7966 | "This package provides a package for summary and annotation of genomic | |
7967 | intervals. Users can visualize and quantify genomic intervals over | |
7968 | pre-defined functional regions, such as promoters, exons, introns, etc. The | |
7969 | genomic intervals represent regions with a defined chromosome position, which | |
7970 | may be associated with a score, such as aligned reads from HT-seq experiments, | |
7971 | TF binding sites, methylation scores, etc. The package can use any tabular | |
7972 | genomic feature data as long as it has minimal information on the locations of | |
7973 | genomic intervals. In addition, it can use BAM or BigWig files as input.") | |
7974 | (license license:artistic2.0))) | |
7975 | ||
64efa307 RW |
7976 | (define-public r-genomationdata |
7977 | (package | |
7978 | (name "r-genomationdata") | |
57dc9b58 | 7979 | (version "1.10.0") |
64efa307 RW |
7980 | (source (origin |
7981 | (method url-fetch) | |
7982 | ;; We cannot use bioconductor-uri here because this tarball is | |
7983 | ;; located under "data/annotation/" instead of "bioc/". | |
7984 | (uri (string-append "https://bioconductor.org/packages/" | |
7985 | "release/data/experiment/src/contrib/" | |
7986 | "genomationData_" version ".tar.gz")) | |
7987 | (sha256 | |
7988 | (base32 | |
57dc9b58 | 7989 | "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla")))) |
64efa307 RW |
7990 | (build-system r-build-system) |
7991 | ;; As this package provides little more than large data files, it doesn't | |
7992 | ;; make sense to build substitutes. | |
7993 | (arguments `(#:substitutable? #f)) | |
7994 | (native-inputs | |
7995 | `(("r-knitr" ,r-knitr))) | |
7996 | (home-page "http://bioinformatics.mdc-berlin.de/genomation/") | |
7997 | (synopsis "Experimental data for use with the genomation package") | |
7998 | (description | |
7999 | "This package contains experimental genetic data for use with the | |
8000 | genomation package. Included are Chip Seq, Methylation and Cage data, | |
8001 | downloaded from Encode.") | |
8002 | (license license:gpl3+))) | |
8003 | ||
486da491 RW |
8004 | (define-public r-org-hs-eg-db |
8005 | (package | |
8006 | (name "r-org-hs-eg-db") | |
d595fed3 | 8007 | (version "3.5.0") |
486da491 RW |
8008 | (source (origin |
8009 | (method url-fetch) | |
8010 | ;; We cannot use bioconductor-uri here because this tarball is | |
8011 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8012 | (uri (string-append "https://www.bioconductor.org/packages/" |
486da491 RW |
8013 | "release/data/annotation/src/contrib/" |
8014 | "org.Hs.eg.db_" version ".tar.gz")) | |
8015 | (sha256 | |
8016 | (base32 | |
d595fed3 | 8017 | "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927")))) |
486da491 RW |
8018 | (properties |
8019 | `((upstream-name . "org.Hs.eg.db"))) | |
8020 | (build-system r-build-system) | |
8021 | (propagated-inputs | |
8022 | `(("r-annotationdbi" ,r-annotationdbi))) | |
5713bbf1 | 8023 | (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/") |
486da491 RW |
8024 | (synopsis "Genome wide annotation for Human") |
8025 | (description | |
676507e3 RW |
8026 | "This package contains genome-wide annotations for Human, primarily based |
8027 | on mapping using Entrez Gene identifiers.") | |
486da491 RW |
8028 | (license license:artistic2.0))) |
8029 | ||
fefedf98 RW |
8030 | (define-public r-org-ce-eg-db |
8031 | (package | |
8032 | (name "r-org-ce-eg-db") | |
e4664290 | 8033 | (version "3.5.0") |
fefedf98 RW |
8034 | (source (origin |
8035 | (method url-fetch) | |
8036 | ;; We cannot use bioconductor-uri here because this tarball is | |
8037 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8038 | (uri (string-append "https://www.bioconductor.org/packages/" |
fefedf98 RW |
8039 | "release/data/annotation/src/contrib/" |
8040 | "org.Ce.eg.db_" version ".tar.gz")) | |
8041 | (sha256 | |
8042 | (base32 | |
e4664290 | 8043 | "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9")))) |
fefedf98 RW |
8044 | (properties |
8045 | `((upstream-name . "org.Ce.eg.db"))) | |
8046 | (build-system r-build-system) | |
8047 | (propagated-inputs | |
8048 | `(("r-annotationdbi" ,r-annotationdbi))) | |
5713bbf1 | 8049 | (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/") |
fefedf98 RW |
8050 | (synopsis "Genome wide annotation for Worm") |
8051 | (description | |
8052 | "This package provides mappings from Entrez gene identifiers to various | |
8053 | annotations for the genome of the model worm Caenorhabditis elegans.") | |
8054 | (license license:artistic2.0))) | |
8055 | ||
16c53a1e RW |
8056 | (define-public r-org-dm-eg-db |
8057 | (package | |
8058 | (name "r-org-dm-eg-db") | |
19fc299f | 8059 | (version "3.5.0") |
16c53a1e RW |
8060 | (source (origin |
8061 | (method url-fetch) | |
8062 | ;; We cannot use bioconductor-uri here because this tarball is | |
8063 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8064 | (uri (string-append "https://www.bioconductor.org/packages/" |
16c53a1e RW |
8065 | "release/data/annotation/src/contrib/" |
8066 | "org.Dm.eg.db_" version ".tar.gz")) | |
8067 | (sha256 | |
8068 | (base32 | |
19fc299f | 8069 | "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d")))) |
16c53a1e RW |
8070 | (properties |
8071 | `((upstream-name . "org.Dm.eg.db"))) | |
8072 | (build-system r-build-system) | |
8073 | (propagated-inputs | |
8074 | `(("r-annotationdbi" ,r-annotationdbi))) | |
5713bbf1 | 8075 | (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/") |
16c53a1e RW |
8076 | (synopsis "Genome wide annotation for Fly") |
8077 | (description | |
8078 | "This package provides mappings from Entrez gene identifiers to various | |
8079 | annotations for the genome of the model fruit fly Drosophila melanogaster.") | |
8080 | (license license:artistic2.0))) | |
8081 | ||
e761beb9 RW |
8082 | (define-public r-org-mm-eg-db |
8083 | (package | |
8084 | (name "r-org-mm-eg-db") | |
f3569f52 | 8085 | (version "3.5.0") |
e761beb9 RW |
8086 | (source (origin |
8087 | (method url-fetch) | |
8088 | ;; We cannot use bioconductor-uri here because this tarball is | |
8089 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8090 | (uri (string-append "https://www.bioconductor.org/packages/" |
e761beb9 RW |
8091 | "release/data/annotation/src/contrib/" |
8092 | "org.Mm.eg.db_" version ".tar.gz")) | |
8093 | (sha256 | |
8094 | (base32 | |
f3569f52 | 8095 | "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g")))) |
e761beb9 RW |
8096 | (properties |
8097 | `((upstream-name . "org.Mm.eg.db"))) | |
8098 | (build-system r-build-system) | |
8099 | (propagated-inputs | |
8100 | `(("r-annotationdbi" ,r-annotationdbi))) | |
5713bbf1 | 8101 | (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/") |
e761beb9 RW |
8102 | (synopsis "Genome wide annotation for Mouse") |
8103 | (description | |
8104 | "This package provides mappings from Entrez gene identifiers to various | |
8105 | annotations for the genome of the model mouse Mus musculus.") | |
8106 | (license license:artistic2.0))) | |
8107 | ||
936e7d67 RW |
8108 | (define-public r-seqlogo |
8109 | (package | |
8110 | (name "r-seqlogo") | |
61770089 | 8111 | (version "1.44.0") |
936e7d67 RW |
8112 | (source |
8113 | (origin | |
8114 | (method url-fetch) | |
8115 | (uri (bioconductor-uri "seqLogo" version)) | |
8116 | (sha256 | |
8117 | (base32 | |
61770089 | 8118 | "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq")))) |
936e7d67 RW |
8119 | (properties `((upstream-name . "seqLogo"))) |
8120 | (build-system r-build-system) | |
5713bbf1 | 8121 | (home-page "https://bioconductor.org/packages/seqLogo") |
936e7d67 RW |
8122 | (synopsis "Sequence logos for DNA sequence alignments") |
8123 | (description | |
8124 | "seqLogo takes the position weight matrix of a DNA sequence motif and | |
8125 | plots the corresponding sequence logo as introduced by Schneider and | |
8126 | Stephens (1990).") | |
8127 | (license license:lgpl2.0+))) | |
8128 | ||
c90a4baf RW |
8129 | (define-public r-bsgenome-hsapiens-ucsc-hg19 |
8130 | (package | |
8131 | (name "r-bsgenome-hsapiens-ucsc-hg19") | |
8132 | (version "1.4.0") | |
8133 | (source (origin | |
8134 | (method url-fetch) | |
8135 | ;; We cannot use bioconductor-uri here because this tarball is | |
8136 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8137 | (uri (string-append "https://www.bioconductor.org/packages/" |
c90a4baf RW |
8138 | "release/data/annotation/src/contrib/" |
8139 | "BSgenome.Hsapiens.UCSC.hg19_" | |
8140 | version ".tar.gz")) | |
8141 | (sha256 | |
8142 | (base32 | |
9d217d27 | 8143 | "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8")))) |
c90a4baf RW |
8144 | (properties |
8145 | `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19"))) | |
8146 | (build-system r-build-system) | |
8147 | ;; As this package provides little more than a very large data file it | |
8148 | ;; doesn't make sense to build substitutes. | |
8149 | (arguments `(#:substitutable? #f)) | |
8150 | (propagated-inputs | |
8151 | `(("r-bsgenome" ,r-bsgenome))) | |
8152 | (home-page | |
5713bbf1 | 8153 | "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/") |
c90a4baf RW |
8154 | (synopsis "Full genome sequences for Homo sapiens") |
8155 | (description | |
8156 | "This package provides full genome sequences for Homo sapiens as provided | |
8157 | by UCSC (hg19, February 2009) and stored in Biostrings objects.") | |
8158 | (license license:artistic2.0))) | |
8159 | ||
a3e90287 RW |
8160 | (define-public r-bsgenome-mmusculus-ucsc-mm9 |
8161 | (package | |
8162 | (name "r-bsgenome-mmusculus-ucsc-mm9") | |
8163 | (version "1.4.0") | |
8164 | (source (origin | |
8165 | (method url-fetch) | |
8166 | ;; We cannot use bioconductor-uri here because this tarball is | |
8167 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8168 | (uri (string-append "https://www.bioconductor.org/packages/" |
a3e90287 RW |
8169 | "release/data/annotation/src/contrib/" |
8170 | "BSgenome.Mmusculus.UCSC.mm9_" | |
8171 | version ".tar.gz")) | |
8172 | (sha256 | |
8173 | (base32 | |
8174 | "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i")))) | |
8175 | (properties | |
8176 | `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9"))) | |
8177 | (build-system r-build-system) | |
8178 | ;; As this package provides little more than a very large data file it | |
8179 | ;; doesn't make sense to build substitutes. | |
8180 | (arguments `(#:substitutable? #f)) | |
8181 | (propagated-inputs | |
8182 | `(("r-bsgenome" ,r-bsgenome))) | |
8183 | (home-page | |
5713bbf1 | 8184 | "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/") |
a3e90287 RW |
8185 | (synopsis "Full genome sequences for Mouse") |
8186 | (description | |
8187 | "This package provides full genome sequences for Mus musculus (Mouse) as | |
8188 | provided by UCSC (mm9, July 2007) and stored in Biostrings objects.") | |
8189 | (license license:artistic2.0))) | |
8190 | ||
4714d521 RW |
8191 | (define-public r-bsgenome-mmusculus-ucsc-mm10 |
8192 | (package | |
8193 | (name "r-bsgenome-mmusculus-ucsc-mm10") | |
8194 | (version "1.4.0") | |
8195 | (source (origin | |
8196 | (method url-fetch) | |
8197 | ;; We cannot use bioconductor-uri here because this tarball is | |
8198 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8199 | (uri (string-append "https://www.bioconductor.org/packages/" |
4714d521 RW |
8200 | "release/data/annotation/src/contrib/" |
8201 | "BSgenome.Mmusculus.UCSC.mm10_" | |
8202 | version ".tar.gz")) | |
8203 | (sha256 | |
8204 | (base32 | |
8205 | "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf")))) | |
8206 | (properties | |
8207 | `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10"))) | |
8208 | (build-system r-build-system) | |
8209 | ;; As this package provides little more than a very large data file it | |
8210 | ;; doesn't make sense to build substitutes. | |
8211 | (arguments `(#:substitutable? #f)) | |
8212 | (propagated-inputs | |
8213 | `(("r-bsgenome" ,r-bsgenome))) | |
8214 | (home-page | |
5713bbf1 | 8215 | "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/") |
4714d521 RW |
8216 | (synopsis "Full genome sequences for Mouse") |
8217 | (description | |
8218 | "This package provides full genome sequences for Mus | |
8219 | musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored | |
8220 | in Biostrings objects.") | |
8221 | (license license:artistic2.0))) | |
8222 | ||
c5173d74 RJ |
8223 | (define-public r-txdb-mmusculus-ucsc-mm10-knowngene |
8224 | (package | |
8225 | (name "r-txdb-mmusculus-ucsc-mm10-knowngene") | |
8226 | (version "3.4.0") | |
8227 | (source (origin | |
8228 | (method url-fetch) | |
8229 | ;; We cannot use bioconductor-uri here because this tarball is | |
8230 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8231 | (uri (string-append "https://www.bioconductor.org/packages/" |
c5173d74 RJ |
8232 | "release/data/annotation/src/contrib/" |
8233 | "TxDb.Mmusculus.UCSC.mm10.knownGene_" | |
8234 | version ".tar.gz")) | |
8235 | (sha256 | |
8236 | (base32 | |
8237 | "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb")))) | |
8238 | (properties | |
8239 | `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene"))) | |
8240 | (build-system r-build-system) | |
8241 | ;; As this package provides little more than a very large data file it | |
8242 | ;; doesn't make sense to build substitutes. | |
8243 | (arguments `(#:substitutable? #f)) | |
8244 | (propagated-inputs | |
8245 | `(("r-bsgenome" ,r-bsgenome) | |
8246 | ("r-genomicfeatures" ,r-genomicfeatures) | |
8247 | ("r-annotationdbi" ,r-annotationdbi))) | |
8248 | (home-page | |
5713bbf1 | 8249 | "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/") |
c5173d74 RJ |
8250 | (synopsis "Annotation package for TxDb knownGene object(s) for Mouse") |
8251 | (description | |
8252 | "This package loads a TxDb object, which is an R interface to | |
8253 | prefabricated databases contained in this package. This package provides | |
8254 | the TxDb object of Mouse data as provided by UCSC (mm10, December 2011) | |
8255 | based on the knownGene track.") | |
8256 | (license license:artistic2.0))) | |
8257 | ||
943bd627 RW |
8258 | (define-public r-bsgenome-celegans-ucsc-ce6 |
8259 | (package | |
8260 | (name "r-bsgenome-celegans-ucsc-ce6") | |
8261 | (version "1.4.0") | |
8262 | (source (origin | |
8263 | (method url-fetch) | |
8264 | ;; We cannot use bioconductor-uri here because this tarball is | |
8265 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8266 | (uri (string-append "https://www.bioconductor.org/packages/" |
943bd627 RW |
8267 | "release/data/annotation/src/contrib/" |
8268 | "BSgenome.Celegans.UCSC.ce6_" | |
8269 | version ".tar.gz")) | |
8270 | (sha256 | |
8271 | (base32 | |
8272 | "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9")))) | |
8273 | (properties | |
8274 | `((upstream-name . "BSgenome.Celegans.UCSC.ce6"))) | |
8275 | (build-system r-build-system) | |
8276 | ;; As this package provides little more than a very large data file it | |
8277 | ;; doesn't make sense to build substitutes. | |
8278 | (arguments `(#:substitutable? #f)) | |
8279 | (propagated-inputs | |
8280 | `(("r-bsgenome" ,r-bsgenome))) | |
8281 | (home-page | |
5713bbf1 | 8282 | "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/") |
943bd627 RW |
8283 | (synopsis "Full genome sequences for Worm") |
8284 | (description | |
8285 | "This package provides full genome sequences for Caenorhabditis | |
8286 | elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings | |
8287 | objects.") | |
8288 | (license license:artistic2.0))) | |
8289 | ||
fc47c7d6 RW |
8290 | (define-public r-bsgenome-celegans-ucsc-ce10 |
8291 | (package | |
8292 | (name "r-bsgenome-celegans-ucsc-ce10") | |
8293 | (version "1.4.0") | |
8294 | (source (origin | |
8295 | (method url-fetch) | |
8296 | ;; We cannot use bioconductor-uri here because this tarball is | |
8297 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8298 | (uri (string-append "https://www.bioconductor.org/packages/" |
fc47c7d6 RW |
8299 | "release/data/annotation/src/contrib/" |
8300 | "BSgenome.Celegans.UCSC.ce10_" | |
8301 | version ".tar.gz")) | |
8302 | (sha256 | |
8303 | (base32 | |
8304 | "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk")))) | |
8305 | (properties | |
8306 | `((upstream-name . "BSgenome.Celegans.UCSC.ce10"))) | |
8307 | (build-system r-build-system) | |
8308 | ;; As this package provides little more than a very large data file it | |
8309 | ;; doesn't make sense to build substitutes. | |
8310 | (arguments `(#:substitutable? #f)) | |
8311 | (propagated-inputs | |
8312 | `(("r-bsgenome" ,r-bsgenome))) | |
8313 | (home-page | |
5713bbf1 | 8314 | "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/") |
fc47c7d6 RW |
8315 | (synopsis "Full genome sequences for Worm") |
8316 | (description | |
8317 | "This package provides full genome sequences for Caenorhabditis | |
8318 | elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings | |
8319 | objects.") | |
8320 | (license license:artistic2.0))) | |
8321 | ||
6dc60998 RW |
8322 | (define-public r-bsgenome-dmelanogaster-ucsc-dm3 |
8323 | (package | |
8324 | (name "r-bsgenome-dmelanogaster-ucsc-dm3") | |
8325 | (version "1.4.0") | |
8326 | (source (origin | |
8327 | (method url-fetch) | |
8328 | ;; We cannot use bioconductor-uri here because this tarball is | |
8329 | ;; located under "data/annotation/" instead of "bioc/". | |
5713bbf1 | 8330 | (uri (string-append "https://www.bioconductor.org/packages/" |
6dc60998 RW |
8331 | "release/data/annotation/src/contrib/" |
8332 | "BSgenome.Dmelanogaster.UCSC.dm3_" | |
8333 | version ".tar.gz")) | |
8334 | (sha256 | |
8335 | (base32 | |
8336 | "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8")))) | |
8337 | (properties | |
8338 | `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3"))) | |
8339 | (build-system r-build-system) | |
8340 | ;; As this package provides little more than a very large data file it | |
8341 | ;; doesn't make sense to build substitutes. | |
8342 | (arguments `(#:substitutable? #f)) | |
8343 | (propagated-inputs | |
8344 | `(("r-bsgenome" ,r-bsgenome))) | |
8345 | (home-page | |
5713bbf1 | 8346 | "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/") |
6dc60998 RW |
8347 | (synopsis "Full genome sequences for Fly") |
8348 | (description | |
8349 | "This package provides full genome sequences for Drosophila | |
8350 | melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in | |
8351 | Biostrings objects.") | |
8352 | (license license:artistic2.0))) | |
8353 | ||
ae2462f7 RW |
8354 | (define-public r-motifrg |
8355 | (package | |
8356 | (name "r-motifrg") | |
ce59d625 | 8357 | (version "1.22.0") |
ae2462f7 RW |
8358 | (source |
8359 | (origin | |
8360 | (method url-fetch) | |
8361 | (uri (bioconductor-uri "motifRG" version)) | |
8362 | (sha256 | |
8363 | (base32 | |
ce59d625 | 8364 | "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44")))) |
ae2462f7 RW |
8365 | (properties `((upstream-name . "motifRG"))) |
8366 | (build-system r-build-system) | |
8367 | (propagated-inputs | |
8368 | `(("r-biostrings" ,r-biostrings) | |
8369 | ("r-bsgenome" ,r-bsgenome) | |
007424b5 | 8370 | ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19) |
ae2462f7 RW |
8371 | ("r-iranges" ,r-iranges) |
8372 | ("r-seqlogo" ,r-seqlogo) | |
8373 | ("r-xvector" ,r-xvector))) | |
5713bbf1 | 8374 | (home-page "https://bioconductor.org/packages/motifRG") |
ae2462f7 RW |
8375 | (synopsis "Discover motifs in high throughput sequencing data") |
8376 | (description | |
8377 | "This package provides tools for discriminative motif discovery in high | |
8378 | throughput genetic sequencing data sets using regression methods.") | |
8379 | (license license:artistic2.0))) | |
8380 | ||
a5002ae7 AE |
8381 | (define-public r-qtl |
8382 | (package | |
8383 | (name "r-qtl") | |
65c9d257 | 8384 | (version "1.42-8") |
a5002ae7 AE |
8385 | (source |
8386 | (origin | |
8387 | (method url-fetch) | |
8388 | (uri (string-append "mirror://cran/src/contrib/qtl_" | |
8389 | version ".tar.gz")) | |
8390 | (sha256 | |
8391 | (base32 | |
65c9d257 | 8392 | "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6")))) |
a5002ae7 AE |
8393 | (build-system r-build-system) |
8394 | (home-page "http://rqtl.org/") | |
8395 | (synopsis "R package for analyzing QTL experiments in genetics") | |
8396 | (description "R/qtl is an extension library for the R statistics | |
8397 | system. It is used to analyze experimental crosses for identifying | |
8398 | genes contributing to variation in quantitative traits (so-called | |
8399 | quantitative trait loci, QTLs). | |
8400 | ||
8401 | Using a hidden Markov model, R/qtl allows to estimate genetic maps, to | |
8402 | identify genotyping errors, and to perform single-QTL and two-QTL, | |
8403 | two-dimensional genome scans.") | |
8404 | (license license:gpl3))) | |
d1e32822 | 8405 | |
9e3ba31c RJ |
8406 | (define-public r-zlibbioc |
8407 | (package | |
8408 | (name "r-zlibbioc") | |
5c184700 | 8409 | (version "1.24.0") |
9e3ba31c RJ |
8410 | (source (origin |
8411 | (method url-fetch) | |
8412 | (uri (bioconductor-uri "zlibbioc" version)) | |
8413 | (sha256 | |
8414 | (base32 | |
5c184700 | 8415 | "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92")))) |
9e3ba31c RJ |
8416 | (properties |
8417 | `((upstream-name . "zlibbioc"))) | |
8418 | (build-system r-build-system) | |
8419 | (home-page "https://bioconductor.org/packages/zlibbioc") | |
8420 | (synopsis "Provider for zlib-1.2.5 to R packages") | |
8421 | (description "This package uses the source code of zlib-1.2.5 to create | |
8422 | libraries for systems that do not have these available via other means.") | |
8423 | (license license:artistic2.0))) | |
8424 | ||
e619a5c2 RW |
8425 | (define-public r-r4rna |
8426 | (package | |
8427 | (name "r-r4rna") | |
8428 | (version "0.1.4") | |
8429 | (source | |
8430 | (origin | |
8431 | (method url-fetch) | |
8432 | (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_" | |
8433 | version ".tar.gz")) | |
8434 | (sha256 | |
8435 | (base32 | |
8436 | "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5")))) | |
8437 | (build-system r-build-system) | |
8438 | (propagated-inputs | |
8439 | `(("r-optparse" ,r-optparse) | |
8440 | ("r-rcolorbrewer" ,r-rcolorbrewer))) | |
8441 | (home-page "http://www.e-rna.org/r-chie/index.cgi") | |
8442 | (synopsis "Analysis framework for RNA secondary structure") | |
8443 | (description | |
8444 | "The R4RNA package aims to be a general framework for the analysis of RNA | |
8445 | secondary structure and comparative analysis in R.") | |
8446 | (license license:gpl3+))) | |
8447 | ||
52765a63 RW |
8448 | (define-public r-rhtslib |
8449 | (package | |
8450 | (name "r-rhtslib") | |
1d0263b4 | 8451 | (version "1.10.0") |
52765a63 RW |
8452 | (source |
8453 | (origin | |
8454 | (method url-fetch) | |
8455 | (uri (bioconductor-uri "Rhtslib" version)) | |
8456 | (sha256 | |
8457 | (base32 | |
1d0263b4 | 8458 | "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j")))) |
52765a63 RW |
8459 | (properties `((upstream-name . "Rhtslib"))) |
8460 | (build-system r-build-system) | |
8461 | (propagated-inputs | |
8462 | `(("r-zlibbioc" ,r-zlibbioc))) | |
8463 | (inputs | |
8464 | `(("zlib" ,zlib))) | |
53ca52f0 RW |
8465 | (native-inputs |
8466 | `(("autoconf" ,autoconf))) | |
52765a63 RW |
8467 | (home-page "https://github.com/nhayden/Rhtslib") |
8468 | (synopsis "High-throughput sequencing library as an R package") | |
8469 | (description | |
8470 | "This package provides the HTSlib C library for high-throughput | |
8471 | nucleotide sequence analysis. The package is primarily useful to developers | |
8472 | of other R packages who wish to make use of HTSlib.") | |
8473 | (license license:lgpl2.0+))) | |
8474 | ||
fe02c4c9 RW |
8475 | (define-public r-bamsignals |
8476 | (package | |
8477 | (name "r-bamsignals") | |
da153b7f | 8478 | (version "1.10.0") |
fe02c4c9 RW |
8479 | (source |
8480 | (origin | |
8481 | (method url-fetch) | |
8482 | (uri (bioconductor-uri "bamsignals" version)) | |
8483 | (sha256 | |
8484 | (base32 | |
da153b7f | 8485 | "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl")))) |
fe02c4c9 RW |
8486 | (build-system r-build-system) |
8487 | (propagated-inputs | |
8488 | `(("r-biocgenerics" ,r-biocgenerics) | |
8489 | ("r-genomicranges" ,r-genomicranges) | |
8490 | ("r-iranges" ,r-iranges) | |
8491 | ("r-rcpp" ,r-rcpp) | |
8492 | ("r-rhtslib" ,r-rhtslib) | |
8493 | ("r-zlibbioc" ,r-zlibbioc))) | |
8494 | (inputs | |
8495 | `(("zlib" ,zlib))) | |
5713bbf1 | 8496 | (home-page "https://bioconductor.org/packages/bamsignals") |
fe02c4c9 RW |
8497 | (synopsis "Extract read count signals from bam files") |
8498 | (description | |
8499 | "This package allows to efficiently obtain count vectors from indexed bam | |
8500 | files. It counts the number of nucleotide sequence reads in given genomic | |
8501 | ranges and it computes reads profiles and coverage profiles. It also handles | |
8502 | paired-end data.") | |
8503 | (license license:gpl2+))) | |
8504 | ||
89984be4 RW |
8505 | (define-public r-rcas |
8506 | (package | |
8507 | (name "r-rcas") | |
d82937fb | 8508 | (version "1.3.4") |
89984be4 RW |
8509 | (source (origin |
8510 | (method url-fetch) | |
8511 | (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v" | |
8512 | version ".tar.gz")) | |
8513 | (file-name (string-append name "-" version ".tar.gz")) | |
8514 | (sha256 | |
8515 | (base32 | |
d82937fb | 8516 | "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg")))) |
89984be4 RW |
8517 | (build-system r-build-system) |
8518 | (native-inputs | |
8519 | `(("r-knitr" ,r-knitr) | |
8520 | ("r-testthat" ,r-testthat) | |
8521 | ;; During vignette building knitr checks that "pandoc-citeproc" | |
8522 | ;; is in the PATH. | |
d93a1c27 | 8523 | ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1))) |
89984be4 RW |
8524 | (propagated-inputs |
8525 | `(("r-data-table" ,r-data-table) | |
8526 | ("r-biomart" ,r-biomart) | |
8527 | ("r-org-hs-eg-db" ,r-org-hs-eg-db) | |
8528 | ("r-org-ce-eg-db" ,r-org-ce-eg-db) | |
8529 | ("r-org-dm-eg-db" ,r-org-dm-eg-db) | |
8530 | ("r-org-mm-eg-db" ,r-org-mm-eg-db) | |
8531 | ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19) | |
8532 | ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9) | |
8533 | ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10) | |
8534 | ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3) | |
8535 | ("r-topgo" ,r-topgo) | |
8536 | ("r-dt" ,r-dt) | |
ebfd6a71 | 8537 | ("r-pbapply" ,r-pbapply) |
89984be4 | 8538 | ("r-plotly" ,r-plotly) |
2c8d6c0b | 8539 | ("r-plotrix" ,r-plotrix) |
89984be4 RW |
8540 | ("r-motifrg" ,r-motifrg) |
8541 | ("r-genomation" ,r-genomation) | |
8542 | ("r-genomicfeatures" ,r-genomicfeatures) | |
8543 | ("r-rtracklayer" ,r-rtracklayer) | |
8544 | ("r-rmarkdown" ,r-rmarkdown))) | |
8545 | (synopsis "RNA-centric annotation system") | |
8546 | (description | |
8547 | "RCAS aims to be a standalone RNA-centric annotation system that provides | |
8548 | intuitive reports and publication-ready graphics. This package provides the R | |
8549 | library implementing most of the pipeline's features.") | |
8550 | (home-page "https://github.com/BIMSBbioinfo/RCAS") | |
75690c9f | 8551 | (license license:artistic2.0))) |
89984be4 | 8552 | |
50937297 RW |
8553 | (define-public rcas-web |
8554 | (package | |
8555 | (name "rcas-web") | |
01d87d3c | 8556 | (version "0.0.4") |
50937297 RW |
8557 | (source |
8558 | (origin | |
8559 | (method url-fetch) | |
8560 | (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/" | |
8561 | "releases/download/v" version | |
8562 | "/rcas-web-" version ".tar.gz")) | |
8563 | (sha256 | |
8564 | (base32 | |
01d87d3c | 8565 | "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm")))) |
50937297 RW |
8566 | (build-system gnu-build-system) |
8567 | (arguments | |
8568 | `(#:phases | |
8569 | (modify-phases %standard-phases | |
8570 | (add-after 'install 'wrap-executable | |
8571 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
8572 | (let* ((out (assoc-ref outputs "out")) | |
8573 | (json (assoc-ref inputs "guile-json")) | |
8574 | (redis (assoc-ref inputs "guile-redis")) | |
8575 | (path (string-append | |
8576 | json "/share/guile/site/2.2:" | |
8577 | redis "/share/guile/site/2.2"))) | |
8578 | (wrap-program (string-append out "/bin/rcas-web") | |
8579 | `("GUILE_LOAD_PATH" ":" = (,path)) | |
8580 | `("GUILE_LOAD_COMPILED_PATH" ":" = (,path)) | |
8581 | `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE"))))) | |
8582 | #t))))) | |
8583 | (inputs | |
2d7c4ae3 | 8584 | `(("r-minimal" ,r-minimal) |
50937297 | 8585 | ("r-rcas" ,r-rcas) |
f6396d86 | 8586 | ("guile-next" ,guile-2.2) |
2252f087 | 8587 | ("guile-json" ,guile-json) |
50937297 RW |
8588 | ("guile-redis" ,guile2.2-redis))) |
8589 | (native-inputs | |
8590 | `(("pkg-config" ,pkg-config))) | |
8591 | (home-page "https://github.com/BIMSBbioinfo/rcas-web") | |
8592 | (synopsis "Web interface for RNA-centric annotation system (RCAS)") | |
8593 | (description "This package provides a simple web interface for the | |
8594 | @dfn{RNA-centric annotation system} (RCAS).") | |
8595 | (license license:agpl3+))) | |
8596 | ||
7500e42b RJ |
8597 | (define-public r-mutationalpatterns |
8598 | (package | |
8599 | (name "r-mutationalpatterns") | |
e086d2f6 | 8600 | (version "1.4.3") |
7500e42b RJ |
8601 | (source |
8602 | (origin | |
8603 | (method url-fetch) | |
8604 | (uri (bioconductor-uri "MutationalPatterns" version)) | |
8605 | (sha256 | |
8606 | (base32 | |
e086d2f6 | 8607 | "0ml4gsp5dfv23xqrknxh25q8q65hly1xb1215lcwyc8hj9z8f941")))) |
7500e42b RJ |
8608 | (build-system r-build-system) |
8609 | (propagated-inputs | |
8610 | `(("r-biocgenerics" ,r-biocgenerics) | |
8611 | ("r-biostrings" ,r-biostrings) | |
cf4ac4e4 RJ |
8612 | ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5) |
8613 | ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19) | |
7500e42b RJ |
8614 | ("r-genomicranges" ,r-genomicranges) |
8615 | ("r-genomeinfodb" ,r-genomeinfodb) | |
8616 | ("r-ggplot2" ,r-ggplot2) | |
7500e42b RJ |
8617 | ("r-iranges" ,r-iranges) |
8618 | ("r-nmf" ,r-nmf) | |
8619 | ("r-plyr" ,r-plyr) | |
8620 | ("r-pracma" ,r-pracma) | |
8621 | ("r-reshape2" ,r-reshape2) | |
39d9098d RW |
8622 | ("r-cowplot" ,r-cowplot) |
8623 | ("r-ggdendro" ,r-ggdendro) | |
8624 | ("r-s4vectors" ,r-s4vectors) | |
7500e42b RJ |
8625 | ("r-summarizedexperiment" ,r-summarizedexperiment) |
8626 | ("r-variantannotation" ,r-variantannotation))) | |
5713bbf1 | 8627 | (home-page "https://bioconductor.org/packages/MutationalPatterns/") |
7500e42b RJ |
8628 | (synopsis "Extract and visualize mutational patterns in genomic data") |
8629 | (description "This package provides an extensive toolset for the | |
8630 | characterization and visualization of a wide range of mutational patterns | |
8631 | in SNV base substitution data.") | |
8632 | (license license:expat))) | |
8633 | ||
d7160529 RW |
8634 | (define-public r-wgcna |
8635 | (package | |
8636 | (name "r-wgcna") | |
6a0e1390 | 8637 | (version "1.63") |
d7160529 RW |
8638 | (source |
8639 | (origin | |
8640 | (method url-fetch) | |
8641 | (uri (cran-uri "WGCNA" version)) | |
8642 | (sha256 | |
8643 | (base32 | |
6a0e1390 | 8644 | "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309")))) |
d7160529 RW |
8645 | (properties `((upstream-name . "WGCNA"))) |
8646 | (build-system r-build-system) | |
8647 | (propagated-inputs | |
8648 | `(("r-annotationdbi" ,r-annotationdbi) | |
8649 | ("r-doparallel" ,r-doparallel) | |
8650 | ("r-dynamictreecut" ,r-dynamictreecut) | |
8651 | ("r-fastcluster" ,r-fastcluster) | |
8652 | ("r-foreach" ,r-foreach) | |
8653 | ("r-go-db" ,r-go-db) | |
8654 | ("r-hmisc" ,r-hmisc) | |
8655 | ("r-impute" ,r-impute) | |
1b22ecda RW |
8656 | ("r-rcpp" ,r-rcpp) |
8657 | ("r-robust" ,r-robust) | |
8658 | ("r-survival" ,r-survival) | |
d7160529 RW |
8659 | ("r-matrixstats" ,r-matrixstats) |
8660 | ("r-preprocesscore" ,r-preprocesscore))) | |
8661 | (home-page | |
8662 | "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/") | |
8663 | (synopsis "Weighted correlation network analysis") | |
8664 | (description | |
8665 | "This package provides functions necessary to perform Weighted | |
8666 | Correlation Network Analysis on high-dimensional data. It includes functions | |
8667 | for rudimentary data cleaning, construction and summarization of correlation | |
8668 | networks, module identification and functions for relating both variables and | |
8669 | modules to sample traits. It also includes a number of utility functions for | |
8670 | data manipulation and visualization.") | |
8671 | (license license:gpl2+))) | |
8672 | ||
c827f202 RW |
8673 | (define-public r-chipkernels |
8674 | (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372") | |
8675 | (revision "1")) | |
8676 | (package | |
8677 | (name "r-chipkernels") | |
8678 | (version (string-append "1.1-" revision "." (string-take commit 9))) | |
8679 | (source | |
8680 | (origin | |
8681 | (method git-fetch) | |
8682 | (uri (git-reference | |
8683 | (url "https://github.com/ManuSetty/ChIPKernels.git") | |
8684 | (commit commit))) | |
8685 | (file-name (string-append name "-" version)) | |
8686 | (sha256 | |
8687 | (base32 | |
8688 | "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0")))) | |
8689 | (build-system r-build-system) | |
8690 | (propagated-inputs | |
8691 | `(("r-iranges" ,r-iranges) | |
8692 | ("r-xvector" ,r-xvector) | |
8693 | ("r-biostrings" ,r-biostrings) | |
8694 | ("r-bsgenome" ,r-bsgenome) | |
8695 | ("r-gtools" ,r-gtools) | |
8696 | ("r-genomicranges" ,r-genomicranges) | |
8697 | ("r-sfsmisc" ,r-sfsmisc) | |
8698 | ("r-kernlab" ,r-kernlab) | |
8699 | ("r-s4vectors" ,r-s4vectors) | |
8700 | ("r-biocgenerics" ,r-biocgenerics))) | |
8701 | (home-page "https://github.com/ManuSetty/ChIPKernels") | |
8702 | (synopsis "Build string kernels for DNA Sequence analysis") | |
8703 | (description "ChIPKernels is an R package for building different string | |
8704 | kernels used for DNA Sequence analysis. A dictionary of the desired kernel | |
8705 | must be built and this dictionary can be used for determining kernels for DNA | |
8706 | Sequences.") | |
8707 | (license license:gpl2+)))) | |
8708 | ||
2d9fb170 RW |
8709 | (define-public r-seqgl |
8710 | (package | |
8711 | (name "r-seqgl") | |
8712 | (version "1.1.4") | |
8713 | (source | |
8714 | (origin | |
8715 | (method url-fetch) | |
8716 | (uri (string-append "https://github.com/ManuSetty/SeqGL/" | |
8717 | "archive/" version ".tar.gz")) | |
8718 | (file-name (string-append name "-" version ".tar.gz")) | |
8719 | (sha256 | |
8720 | (base32 | |
8721 | "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh")))) | |
8722 | (build-system r-build-system) | |
8723 | (propagated-inputs | |
8724 | `(("r-biostrings" ,r-biostrings) | |
8725 | ("r-chipkernels" ,r-chipkernels) | |
8726 | ("r-genomicranges" ,r-genomicranges) | |
8727 | ("r-spams" ,r-spams) | |
8728 | ("r-wgcna" ,r-wgcna) | |
8729 | ("r-fastcluster" ,r-fastcluster))) | |
8730 | (home-page "https://github.com/ManuSetty/SeqGL") | |
8731 | (synopsis "Group lasso for Dnase/ChIP-seq data") | |
8732 | (description "SeqGL is a group lasso based algorithm to extract | |
8733 | transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles. | |
8734 | This package presents a method which uses group lasso to discriminate between | |
8735 | bound and non bound genomic regions to accurately identify transcription | |
8736 | factors bound at the specific regions.") | |
8737 | (license license:gpl2+))) | |
8738 | ||
bd3be46e RW |
8739 | (define-public r-gkmsvm |
8740 | (package | |
8741 | (name "r-gkmsvm") | |
5ef76bc2 | 8742 | (version "0.79.0") |
bd3be46e RW |
8743 | (source |
8744 | (origin | |
8745 | (method url-fetch) | |
8746 | (uri (cran-uri "gkmSVM" version)) | |
8747 | (sha256 | |
8748 | (base32 | |
5ef76bc2 | 8749 | "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3")))) |
bd3be46e RW |
8750 | (properties `((upstream-name . "gkmSVM"))) |
8751 | (build-system r-build-system) | |
8752 | (propagated-inputs | |
8753 | `(("r-biocgenerics" ,r-biocgenerics) | |
8754 | ("r-biostrings" ,r-biostrings) | |
8755 | ("r-genomeinfodb" ,r-genomeinfodb) | |
8756 | ("r-genomicranges" ,r-genomicranges) | |
8757 | ("r-iranges" ,r-iranges) | |
8758 | ("r-kernlab" ,r-kernlab) | |
8759 | ("r-rcpp" ,r-rcpp) | |
8760 | ("r-rocr" ,r-rocr) | |
8761 | ("r-rtracklayer" ,r-rtracklayer) | |
8762 | ("r-s4vectors" ,r-s4vectors) | |
8763 | ("r-seqinr" ,r-seqinr))) | |
e9960d8c | 8764 | (home-page "https://cran.r-project.org/web/packages/gkmSVM") |
bd3be46e RW |
8765 | (synopsis "Gapped-kmer support vector machine") |
8766 | (description | |
8767 | "This R package provides tools for training gapped-kmer SVM classifiers | |
8768 | for DNA and protein sequences. This package supports several sequence | |
8769 | kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.") | |
8770 | (license license:gpl2+))) | |
8771 | ||
d4af25b5 RJPB |
8772 | (define-public r-tximport |
8773 | (package | |
8774 | (name "r-tximport") | |
19e8929c | 8775 | (version "1.6.0") |
d4af25b5 RJPB |
8776 | (source (origin |
8777 | (method url-fetch) | |
8778 | (uri (bioconductor-uri "tximport" version)) | |
8779 | (sha256 | |
8780 | (base32 | |
19e8929c | 8781 | "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h")))) |
d4af25b5 | 8782 | (build-system r-build-system) |
5713bbf1 | 8783 | (home-page "https://bioconductor.org/packages/tximport") |
d4af25b5 RJPB |
8784 | (synopsis "Import and summarize transcript-level estimates for gene-level analysis") |
8785 | (description | |
8786 | "This package provides tools to import transcript-level abundance, | |
8787 | estimated counts and transcript lengths, and to summarize them into matrices | |
8788 | for use with downstream gene-level analysis packages. Average transcript | |
8789 | length, weighted by sample-specific transcript abundance estimates, is | |
8790 | provided as a matrix which can be used as an offset for different expression | |
8791 | of gene-level counts.") | |
8792 | (license license:gpl2+))) | |
8793 | ||
69f2b3bd RJPB |
8794 | (define-public r-rhdf5 |
8795 | (package | |
8796 | (name "r-rhdf5") | |
e6b332d4 | 8797 | (version "2.22.0") |
69f2b3bd RJPB |
8798 | (source (origin |
8799 | (method url-fetch) | |
8800 | (uri (bioconductor-uri "rhdf5" version)) | |
8801 | (sha256 | |
8802 | (base32 | |
e6b332d4 | 8803 | "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1")))) |
69f2b3bd RJPB |
8804 | (build-system r-build-system) |
8805 | (arguments | |
8806 | `(#:phases | |
8807 | (modify-phases %standard-phases | |
8808 | (add-after 'unpack 'unpack-smallhdf5 | |
8809 | (lambda* (#:key outputs #:allow-other-keys) | |
8810 | (system* "tar" "-xzvf" | |
8811 | "src/hdf5source/hdf5small.tgz" "-C" "src/" ) | |
69f2b3bd RJPB |
8812 | (substitute* "src/hdf5/configure" |
8813 | (("/bin/mv") "mv")) | |
e325c890 RW |
8814 | ;; Remove timestamp and host system information to make |
8815 | ;; the build reproducible. | |
8816 | (substitute* "src/hdf5/src/libhdf5.settings.in" | |
8817 | (("Configured on: @CONFIG_DATE@") | |
8818 | "Configured on: Guix") | |
8819 | (("Uname information:.*") | |
8820 | "Uname information: Linux\n") | |
8821 | ;; Remove unnecessary store reference. | |
8822 | (("C Compiler:.*") | |
8823 | "C Compiler: GCC\n")) | |
69f2b3bd RJPB |
8824 | #t))))) |
8825 | (propagated-inputs | |
8826 | `(("r-zlibbioc" ,r-zlibbioc))) | |
8827 | (inputs | |
8828 | `(("perl" ,perl) | |
8829 | ("zlib" ,zlib))) | |
5713bbf1 | 8830 | (home-page "https://bioconductor.org/packages/rhdf5") |
69f2b3bd RJPB |
8831 | (synopsis "HDF5 interface to R") |
8832 | (description | |
8833 | "This R/Bioconductor package provides an interface between HDF5 and R. | |
8834 | HDF5's main features are the ability to store and access very large and/or | |
8835 | complex datasets and a wide variety of metadata on mass storage (disk) through | |
8836 | a completely portable file format. The rhdf5 package is thus suited for the | |
8837 | exchange of large and/or complex datasets between R and other software | |
8838 | package, and for letting R applications work on datasets that are larger than | |
8839 | the available RAM.") | |
8840 | (license license:artistic2.0))) | |
8841 | ||
17cddc17 RW |
8842 | (define-public r-annotationfilter |
8843 | (package | |
8844 | (name "r-annotationfilter") | |
598dacf6 | 8845 | (version "1.2.0") |
17cddc17 RW |
8846 | (source (origin |
8847 | (method url-fetch) | |
8848 | (uri (bioconductor-uri "AnnotationFilter" version)) | |
8849 | (sha256 | |
8850 | (base32 | |
598dacf6 | 8851 | "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs")))) |
17cddc17 RW |
8852 | (properties |
8853 | `((upstream-name . "AnnotationFilter"))) | |
8854 | (build-system r-build-system) | |
8855 | (propagated-inputs | |
8856 | `(("r-genomicranges" ,r-genomicranges) | |
8857 | ("r-lazyeval" ,r-lazyeval))) | |
8858 | (home-page "https://github.com/Bioconductor/AnnotationFilter") | |
8859 | (synopsis "Facilities for filtering Bioconductor annotation resources") | |
8860 | (description | |
8861 | "This package provides classes and other infrastructure to implement | |
8862 | filters for manipulating Bioconductor annotation resources. The filters are | |
8863 | used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.") | |
8864 | (license license:artistic2.0))) | |
8865 | ||
66e40e00 RW |
8866 | (define-public emboss |
8867 | (package | |
8868 | (name "emboss") | |
8869 | (version "6.5.7") | |
8870 | (source (origin | |
8871 | (method url-fetch) | |
8872 | (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/" | |
8873 | (version-major+minor version) ".0/" | |
8874 | "EMBOSS-" version ".tar.gz")) | |
8875 | (sha256 | |
8876 | (base32 | |
8877 | "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q")))) | |
8878 | (build-system gnu-build-system) | |
8879 | (arguments | |
8880 | `(#:configure-flags | |
8881 | (list (string-append "--with-hpdf=" | |
8882 | (assoc-ref %build-inputs "libharu"))) | |
8883 | #:phases | |
8884 | (modify-phases %standard-phases | |
8885 | (add-after 'unpack 'fix-checks | |
8886 | (lambda _ | |
8887 | ;; The PNGDRIVER tests check for the presence of libgd, libpng | |
8888 | ;; and zlib, but assume that they are all found at the same | |
8889 | ;; prefix. | |
8890 | (substitute* "configure.in" | |
8891 | (("CHECK_PNGDRIVER") | |
8892 | "LIBS=\"$LIBS -lgd -lpng -lz -lm\" | |
8893 | AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available]) | |
8894 | AM_CONDITIONAL(AMPNG, true)")) | |
8895 | #t)) | |
d10092b8 | 8896 | (add-after 'fix-checks 'disable-update-check |
66e40e00 RW |
8897 | (lambda _ |
8898 | ;; At build time there is no connection to the Internet, so | |
8899 | ;; looking for updates will not work. | |
8900 | (substitute* "Makefile.am" | |
8901 | (("\\$\\(bindir\\)/embossupdate") "")) | |
8902 | #t)) | |
d10092b8 | 8903 | (add-after 'disable-update-check 'autogen |
66e40e00 RW |
8904 | (lambda _ (zero? (system* "autoreconf" "-vif"))))))) |
8905 | (inputs | |
8906 | `(("perl" ,perl) | |
8907 | ("libpng" ,libpng) | |
8908 | ("gd" ,gd) | |
8909 | ("libx11" ,libx11) | |
8910 | ("libharu" ,libharu) | |
8911 | ("zlib" ,zlib))) | |
8912 | (native-inputs | |
8913 | `(("autoconf" ,autoconf) | |
8914 | ("automake" ,automake) | |
8915 | ("libtool" ,libtool) | |
8916 | ("pkg-config" ,pkg-config))) | |
8917 | (home-page "http://emboss.sourceforge.net") | |
8918 | (synopsis "Molecular biology analysis suite") | |
8919 | (description "EMBOSS is the \"European Molecular Biology Open Software | |
8920 | Suite\". EMBOSS is an analysis package specially developed for the needs of | |
8921 | the molecular biology (e.g. EMBnet) user community. The software | |
8922 | automatically copes with data in a variety of formats and even allows | |
8923 | transparent retrieval of sequence data from the web. It also provides a | |
8924 | number of libraries for the development of software in the field of molecular | |
8925 | biology. EMBOSS also integrates a range of currently available packages and | |
8926 | tools for sequence analysis into a seamless whole.") | |
8927 | (license license:gpl2+))) | |
8928 | ||
1f1b20b8 RW |
8929 | (define-public bits |
8930 | (let ((revision "1") | |
8931 | (commit "3cc4567896d9d6442923da944beb704750a08d2d")) | |
8932 | (package | |
8933 | (name "bits") | |
8934 | ;; The version is 2.13.0 even though no release archives have been | |
8935 | ;; published as yet. | |
8936 | (version (string-append "2.13.0-" revision "." (string-take commit 9))) | |
8937 | (source (origin | |
8938 | (method git-fetch) | |
8939 | (uri (git-reference | |
8940 | (url "https://github.com/arq5x/bits.git") | |
8941 | (commit commit))) | |
8942 | (file-name (string-append name "-" version "-checkout")) | |
8943 | (sha256 | |
8944 | (base32 | |
8945 | "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs")))) | |
8946 | (build-system gnu-build-system) | |
8947 | (arguments | |
8948 | `(#:tests? #f ;no tests included | |
8949 | #:phases | |
8950 | (modify-phases %standard-phases | |
8951 | (delete 'configure) | |
8952 | (add-after 'unpack 'remove-cuda | |
8953 | (lambda _ | |
8954 | (substitute* "Makefile" | |
8955 | ((".*_cuda") "") | |
8956 | (("(bits_test_intersections) \\\\" _ match) match)) | |
8957 | #t)) | |
8958 | (replace 'install | |
8959 | (lambda* (#:key outputs #:allow-other-keys) | |
8960 | (copy-recursively | |
8961 | "bin" (string-append (assoc-ref outputs "out") "/bin")) | |
8962 | #t))))) | |
8963 | (inputs | |
8964 | `(("gsl" ,gsl) | |
8965 | ("zlib" ,zlib))) | |
8966 | (home-page "https://github.com/arq5x/bits") | |
8967 | (synopsis "Implementation of binary interval search algorithm") | |
8968 | (description "This package provides an implementation of the | |
8969 | BITS (Binary Interval Search) algorithm, an approach to interval set | |
8970 | intersection. It is especially suited for the comparison of diverse genomic | |
8971 | datasets and the exploration of large datasets of genome | |
8972 | intervals (e.g. genes, sequence alignments).") | |
8973 | (license license:gpl2)))) | |
8974 | ||
e62ffce5 | 8975 | (define-public piranha |
883302da RW |
8976 | ;; There is no release tarball for the latest version. The latest commit is |
8977 | ;; older than one year at the time of this writing. | |
8978 | (let ((revision "1") | |
8979 | (commit "0466d364b71117d01e4471b74c514436cc281233")) | |
8980 | (package | |
8981 | (name "piranha") | |
8982 | (version (string-append "1.2.1-" revision "." (string-take commit 9))) | |
8983 | (source (origin | |
8984 | (method git-fetch) | |
8985 | (uri (git-reference | |
8986 | (url "https://github.com/smithlabcode/piranha.git") | |
8987 | (commit commit))) | |
da49d137 | 8988 | (file-name (git-file-name name version)) |
883302da RW |
8989 | (sha256 |
8990 | (base32 | |
8991 | "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n")))) | |
8992 | (build-system gnu-build-system) | |
8993 | (arguments | |
8994 | `(#:test-target "test" | |
8995 | #:phases | |
8996 | (modify-phases %standard-phases | |
8997 | (add-after 'unpack 'copy-smithlab-cpp | |
8998 | (lambda* (#:key inputs #:allow-other-keys) | |
e62ffce5 | 8999 | (for-each (lambda (file) |
883302da RW |
9000 | (install-file file "./src/smithlab_cpp/")) |
9001 | (find-files (assoc-ref inputs "smithlab-cpp"))) | |
9002 | #t)) | |
9003 | (add-after 'install 'install-to-store | |
9004 | (lambda* (#:key outputs #:allow-other-keys) | |
9005 | (let* ((out (assoc-ref outputs "out")) | |
9006 | (bin (string-append out "/bin"))) | |
883302da RW |
9007 | (for-each (lambda (file) |
9008 | (install-file file bin)) | |
9009 | (find-files "bin" ".*"))) | |
9010 | #t))) | |
9011 | #:configure-flags | |
9012 | (list (string-append "--with-bam_tools_headers=" | |
9013 | (assoc-ref %build-inputs "bamtools") "/include/bamtools") | |
9014 | (string-append "--with-bam_tools_library=" | |
9015 | (assoc-ref %build-inputs "bamtools") "/lib/bamtools")))) | |
9016 | (inputs | |
9017 | `(("bamtools" ,bamtools) | |
9018 | ("samtools" ,samtools-0.1) | |
9019 | ("gsl" ,gsl) | |
9020 | ("smithlab-cpp" | |
9021 | ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a")) | |
9022 | (origin | |
9023 | (method git-fetch) | |
9024 | (uri (git-reference | |
9025 | (url "https://github.com/smithlabcode/smithlab_cpp.git") | |
9026 | (commit commit))) | |
9027 | (file-name (string-append "smithlab_cpp-" commit "-checkout")) | |
9028 | (sha256 | |
9029 | (base32 | |
9030 | "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g"))))))) | |
9031 | (native-inputs | |
9032 | `(("python" ,python-2))) | |
9033 | (home-page "https://github.com/smithlabcode/piranha") | |
9034 | (synopsis "Peak-caller for CLIP-seq and RIP-seq data") | |
9035 | (description | |
9036 | "Piranha is a peak-caller for genomic data produced by CLIP-seq and | |
e62ffce5 RW |
9037 | RIP-seq experiments. It takes input in BED or BAM format and identifies |
9038 | regions of statistically significant read enrichment. Additional covariates | |
9039 | may optionally be provided to further inform the peak-calling process.") | |
883302da | 9040 | (license license:gpl3+)))) |
e62ffce5 | 9041 | |
d1e32822 RW |
9042 | (define-public pepr |
9043 | (package | |
9044 | (name "pepr") | |
9045 | (version "1.0.9") | |
9046 | (source (origin | |
9047 | (method url-fetch) | |
9048 | (uri (string-append "https://pypi.python.org/packages/source/P" | |
9049 | "/PePr/PePr-" version ".tar.gz")) | |
9050 | (sha256 | |
9051 | (base32 | |
9052 | "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx")))) | |
9053 | (build-system python-build-system) | |
9054 | (arguments | |
9055 | `(#:python ,python-2 ; python2 only | |
b41a05ce | 9056 | #:tests? #f)) ; no tests included |
d1e32822 RW |
9057 | (propagated-inputs |
9058 | `(("python2-numpy" ,python2-numpy) | |
9059 | ("python2-scipy" ,python2-scipy) | |
9060 | ("python2-pysam" ,python2-pysam))) | |
0c6c9c00 | 9061 | (home-page "https://github.com/shawnzhangyx/PePr") |
d1e32822 RW |
9062 | (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data") |
9063 | (description | |
9064 | "PePr is a ChIP-Seq peak calling or differential binding analysis tool | |
9065 | that is primarily designed for data with biological replicates. It uses a | |
9066 | negative binomial distribution to model the read counts among the samples in | |
9067 | the same group, and look for consistent differences between ChIP and control | |
9068 | group or two ChIP groups run under different conditions.") | |
9069 | (license license:gpl3+))) | |
6b49a37e RJ |
9070 | |
9071 | (define-public filevercmp | |
9072 | (let ((commit "1a9b779b93d0b244040274794d402106907b71b7")) | |
9073 | (package | |
9074 | (name "filevercmp") | |
9075 | (version (string-append "0-1." (string-take commit 7))) | |
9076 | (source (origin | |
9077 | (method url-fetch) | |
9078 | (uri (string-append "https://github.com/ekg/filevercmp/archive/" | |
9079 | commit ".tar.gz")) | |
9080 | (file-name (string-append name "-" version ".tar.gz")) | |
9081 | (sha256 | |
9082 | (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450")))) | |
9083 | (build-system gnu-build-system) | |
9084 | (arguments | |
9085 | `(#:tests? #f ; There are no tests to run. | |
9086 | #:phases | |
9087 | (modify-phases %standard-phases | |
9088 | (delete 'configure) ; There is no configure phase. | |
9089 | (replace 'install | |
9090 | (lambda* (#:key outputs #:allow-other-keys) | |
9091 | (let ((bin (string-append (assoc-ref outputs "out") "/bin"))) | |
9092 | (install-file "filevercmp" bin))))))) | |
9093 | (home-page "https://github.com/ekg/filevercmp") | |
9094 | (synopsis "This program compares version strings") | |
9095 | (description "This program compares version strings. It intends to be a | |
9096 | replacement for strverscmp.") | |
9097 | (license license:gpl3+)))) | |
5fb5dffb RW |
9098 | |
9099 | (define-public multiqc | |
9100 | (package | |
9101 | (name "multiqc") | |
457fd268 | 9102 | (version "1.5") |
5fb5dffb RW |
9103 | (source |
9104 | (origin | |
9105 | (method url-fetch) | |
9106 | (uri (pypi-uri "multiqc" version)) | |
9107 | (sha256 | |
9108 | (base32 | |
457fd268 | 9109 | "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy")))) |
5fb5dffb RW |
9110 | (build-system python-build-system) |
9111 | (propagated-inputs | |
9e94d063 | 9112 | `(("python-jinja2" ,python-jinja2) |
5fb5dffb RW |
9113 | ("python-simplejson" ,python-simplejson) |
9114 | ("python-pyyaml" ,python-pyyaml) | |
9115 | ("python-click" ,python-click) | |
799247d2 RW |
9116 | ("python-spectra" ,python-spectra) |
9117 | ("python-requests" ,python-requests) | |
9118 | ("python-markdown" ,python-markdown) | |
9119 | ("python-lzstring" ,python-lzstring) | |
5fb5dffb | 9120 | ("python-matplotlib" ,python-matplotlib) |
1778ea74 RW |
9121 | ("python-numpy" ,python-numpy) |
9122 | ;; MultQC checks for the presence of nose at runtime. | |
9123 | ("python-nose" ,python-nose))) | |
4ca95811 TGR |
9124 | (arguments |
9125 | `(#:phases | |
9126 | (modify-phases %standard-phases | |
9127 | (add-after 'unpack 'relax-requirements | |
9128 | (lambda _ | |
9129 | (substitute* "setup.py" | |
9130 | ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older | |
9131 | ;; than the one in Guix, but should work fine with 2.2.2. | |
9132 | ;; See <https://github.com/ewels/MultiQC/issues/725> and | |
9133 | ;; <https://github.com/ewels/MultiQC/issues/732> for details. | |
9134 | (("['\"]matplotlib.*?['\"]") | |
9135 | "'matplotlib'")) | |
9136 | #t))))) | |
5fb5dffb RW |
9137 | (home-page "http://multiqc.info") |
9138 | (synopsis "Aggregate bioinformatics analysis reports") | |
9139 | (description | |
9140 | "MultiQC is a tool to aggregate bioinformatics results across many | |
9141 | samples into a single report. It contains modules for a large number of | |
9142 | common bioinformatics tools.") | |
66865ab8 | 9143 | (license license:gpl3+))) |
6193563a RW |
9144 | |
9145 | (define-public r-chipseq | |
9146 | (package | |
9147 | (name "r-chipseq") | |
eeaa6967 | 9148 | (version "1.28.0") |
6193563a RW |
9149 | (source |
9150 | (origin | |
9151 | (method url-fetch) | |
9152 | (uri (bioconductor-uri "chipseq" version)) | |
9153 | (sha256 | |
9154 | (base32 | |
eeaa6967 | 9155 | "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq")))) |
6193563a RW |
9156 | (build-system r-build-system) |
9157 | (propagated-inputs | |
9158 | `(("r-biocgenerics" ,r-biocgenerics) | |
9159 | ("r-genomicranges" ,r-genomicranges) | |
9160 | ("r-iranges" ,r-iranges) | |
eeaa6967 | 9161 | ("r-lattice" ,r-lattice) |
6193563a RW |
9162 | ("r-s4vectors" ,r-s4vectors) |
9163 | ("r-shortread" ,r-shortread))) | |
5713bbf1 | 9164 | (home-page "https://bioconductor.org/packages/chipseq") |
6193563a RW |
9165 | (synopsis "Package for analyzing ChIPseq data") |
9166 | (description | |
9167 | "This package provides tools for processing short read data from ChIPseq | |
9168 | experiments.") | |
9169 | (license license:artistic2.0))) | |
d407bdb9 RW |
9170 | |
9171 | (define-public r-copyhelper | |
9172 | (package | |
9173 | (name "r-copyhelper") | |
9174 | (version "1.6.0") | |
9175 | (source | |
9176 | (origin | |
9177 | (method url-fetch) | |
5713bbf1 | 9178 | (uri (string-append "https://bioconductor.org/packages/release/" |
d407bdb9 RW |
9179 | "data/experiment/src/contrib/CopyhelpeR_" |
9180 | version ".tar.gz")) | |
9181 | (sha256 | |
9182 | (base32 | |
9183 | "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq")))) | |
9184 | (properties `((upstream-name . "CopyhelpeR"))) | |
9185 | (build-system r-build-system) | |
5713bbf1 | 9186 | (home-page "https://bioconductor.org/packages/CopyhelpeR/") |
d407bdb9 RW |
9187 | (synopsis "Helper files for CopywriteR") |
9188 | (description | |
9189 | "This package contains the helper files that are required to run the | |
9190 | Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content | |
9191 | and mappability files for the reference genomes hg18, hg19, hg38, mm9 and | |
9192 | mm10. In addition, it contains a blacklist filter to remove regions that | |
9193 | display copy number variation. Files are stored as GRanges objects from the | |
9194 | GenomicRanges Bioconductor package.") | |
9195 | (license license:gpl2))) | |
3a3bf2f8 RW |
9196 | |
9197 | (define-public r-copywriter | |
9198 | (package | |
9199 | (name "r-copywriter") | |
c126ba69 | 9200 | (version "2.10.0") |
3a3bf2f8 RW |
9201 | (source |
9202 | (origin | |
9203 | (method url-fetch) | |
9204 | (uri (bioconductor-uri "CopywriteR" version)) | |
9205 | (sha256 | |
9206 | (base32 | |
c126ba69 | 9207 | "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca")))) |
3a3bf2f8 RW |
9208 | (properties `((upstream-name . "CopywriteR"))) |
9209 | (build-system r-build-system) | |
9210 | (propagated-inputs | |
9211 | `(("r-biocparallel" ,r-biocparallel) | |
9212 | ("r-chipseq" ,r-chipseq) | |
9213 | ("r-copyhelper" ,r-copyhelper) | |
9214 | ("r-data-table" ,r-data-table) | |
9215 | ("r-dnacopy" ,r-dnacopy) | |
9216 | ("r-futile-logger" ,r-futile-logger) | |
9217 | ("r-genomeinfodb" ,r-genomeinfodb) | |
9218 | ("r-genomicalignments" ,r-genomicalignments) | |
9219 | ("r-genomicranges" ,r-genomicranges) | |
9220 | ("r-gtools" ,r-gtools) | |
9221 | ("r-iranges" ,r-iranges) | |
9222 | ("r-matrixstats" ,r-matrixstats) | |
9223 | ("r-rsamtools" ,r-rsamtools) | |
9224 | ("r-s4vectors" ,r-s4vectors))) | |
9225 | (home-page "https://github.com/PeeperLab/CopywriteR") | |
9226 | (synopsis "Copy number information from targeted sequencing") | |
9227 | (description | |
9228 | "CopywriteR extracts DNA copy number information from targeted sequencing | |
9229 | by utilizing off-target reads. It allows for extracting uniformly distributed | |
9230 | copy number information, can be used without reference, and can be applied to | |
9231 | sequencing data obtained from various techniques including chromatin | |
9232 | immunoprecipitation and target enrichment on small gene panels. Thereby, | |
9233 | CopywriteR constitutes a widely applicable alternative to available copy | |
9234 | number detection tools.") | |
9235 | (license license:gpl2))) | |
dd42a330 | 9236 | |
bf3fa996 RW |
9237 | (define-public r-methylkit |
9238 | (package | |
9239 | (name "r-methylkit") | |
b1f27536 | 9240 | (version "1.4.1") |
bf3fa996 RW |
9241 | (source (origin |
9242 | (method url-fetch) | |
9243 | (uri (bioconductor-uri "methylKit" version)) | |
9244 | (sha256 | |
9245 | (base32 | |
b1f27536 | 9246 | "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai")))) |
bf3fa996 RW |
9247 | (properties `((upstream-name . "methylKit"))) |
9248 | (build-system r-build-system) | |
9249 | (propagated-inputs | |
9250 | `(("r-data-table" ,r-data-table) | |
9251 | ("r-emdbook" ,r-emdbook) | |
9252 | ("r-fastseg" ,r-fastseg) | |
9253 | ("r-genomeinfodb" ,r-genomeinfodb) | |
9254 | ("r-genomicranges" ,r-genomicranges) | |
9255 | ("r-gtools" ,r-gtools) | |
9256 | ("r-iranges" ,r-iranges) | |
9257 | ("r-kernsmooth" ,r-kernsmooth) | |
9258 | ("r-limma" ,r-limma) | |
9259 | ("r-mclust" ,r-mclust) | |
9260 | ("r-qvalue" ,r-qvalue) | |
9261 | ("r-r-utils" ,r-r-utils) | |
9262 | ("r-rcpp" ,r-rcpp) | |
9263 | ("r-rhtslib" ,r-rhtslib) | |
9264 | ("r-rsamtools" ,r-rsamtools) | |
9265 | ("r-rtracklayer" ,r-rtracklayer) | |
9266 | ("r-s4vectors" ,r-s4vectors) | |
9267 | ("r-zlibbioc" ,r-zlibbioc))) | |
9268 | (inputs | |
9269 | `(("zlib" ,zlib))) | |
11ed4108 | 9270 | (home-page "https://github.com/al2na/methylKit") |
bf3fa996 RW |
9271 | (synopsis |
9272 | "DNA methylation analysis from high-throughput bisulfite sequencing results") | |
9273 | (description | |
9274 | "MethylKit is an R package for DNA methylation analysis and annotation | |
9275 | from high-throughput bisulfite sequencing. The package is designed to deal | |
9276 | with sequencing data from @dfn{Reduced representation bisulfite | |
9277 | sequencing} (RRBS) and its variants, but also target-capture methods and whole | |
9278 | genome bisulfite sequencing. It also has functions to analyze base-pair | |
9279 | resolution 5hmC data from experimental protocols such as oxBS-Seq and | |
9280 | TAB-Seq.") | |
9281 | (license license:artistic2.0))) | |
9282 | ||
dd42a330 RJPB |
9283 | (define-public r-sva |
9284 | (package | |
9285 | (name "r-sva") | |
fad7c0c7 | 9286 | (version "3.26.0") |
dd42a330 RJPB |
9287 | (source |
9288 | (origin | |
9289 | (method url-fetch) | |
9290 | (uri (bioconductor-uri "sva" version)) | |
9291 | (sha256 | |
9292 | (base32 | |
fad7c0c7 | 9293 | "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw")))) |
dd42a330 RJPB |
9294 | (build-system r-build-system) |
9295 | (propagated-inputs | |
aeb64f3c | 9296 | `(("r-genefilter" ,r-genefilter) |
bfa0d1e7 RJ |
9297 | ("r-mgcv" ,r-mgcv) |
9298 | ("r-biocparallel" ,r-biocparallel) | |
9299 | ("r-matrixstats" ,r-matrixstats) | |
9300 | ("r-limma" ,r-limma))) | |
5713bbf1 | 9301 | (home-page "https://bioconductor.org/packages/sva") |
dd42a330 RJPB |
9302 | (synopsis "Surrogate variable analysis") |
9303 | (description | |
9304 | "This package contains functions for removing batch effects and other | |
9305 | unwanted variation in high-throughput experiment. It also contains functions | |
9306 | for identifying and building surrogate variables for high-dimensional data | |
9307 | sets. Surrogate variables are covariates constructed directly from | |
9308 | high-dimensional data like gene expression/RNA sequencing/methylation/brain | |
9309 | imaging data that can be used in subsequent analyses to adjust for unknown, | |
9310 | unmodeled, or latent sources of noise.") | |
9311 | (license license:artistic2.0))) | |
fb1e528e RW |
9312 | |
9313 | (define-public r-seqminer | |
9314 | (package | |
9315 | (name "r-seqminer") | |
5e0de298 | 9316 | (version "6.0") |
fb1e528e RW |
9317 | (source |
9318 | (origin | |
9319 | (method url-fetch) | |
9320 | (uri (cran-uri "seqminer" version)) | |
9321 | (sha256 | |
9322 | (base32 | |
5e0de298 | 9323 | "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l")))) |
fb1e528e RW |
9324 | (build-system r-build-system) |
9325 | (inputs | |
9326 | `(("zlib" ,zlib))) | |
9327 | (home-page "http://seqminer.genomic.codes") | |
9328 | (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)") | |
9329 | (description | |
9330 | "This package provides tools to integrate nucleotide sequencing | |
9331 | data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.") | |
9332 | ;; Any version of the GPL is acceptable | |
9333 | (license (list license:gpl2+ license:gpl3+)))) | |
1f40e73c RW |
9334 | |
9335 | (define-public r-raremetals2 | |
9336 | (package | |
9337 | (name "r-raremetals2") | |
9338 | (version "0.1") | |
9339 | (source | |
9340 | (origin | |
9341 | (method url-fetch) | |
9342 | (uri (string-append "http://genome.sph.umich.edu/w/images/" | |
9343 | "b/b7/RareMETALS2_" version ".tar.gz")) | |
9344 | (sha256 | |
9345 | (base32 | |
9346 | "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s")))) | |
9347 | (properties `((upstream-name . "RareMETALS2"))) | |
9348 | (build-system r-build-system) | |
9349 | (propagated-inputs | |
9350 | `(("r-seqminer" ,r-seqminer) | |
9351 | ("r-mvtnorm" ,r-mvtnorm) | |
aeb64f3c | 9352 | ("r-mass" ,r-mass) |
1f40e73c RW |
9353 | ("r-compquadform" ,r-compquadform) |
9354 | ("r-getopt" ,r-getopt))) | |
9355 | (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2") | |
9356 | (synopsis "Analyze gene-level association tests for binary trait") | |
9357 | (description | |
9358 | "The R package rareMETALS2 is an extension of the R package rareMETALS. | |
9359 | It was designed to meta-analyze gene-level association tests for binary trait. | |
9360 | While rareMETALS offers a near-complete solution for meta-analysis of | |
9361 | gene-level tests for quantitative trait, it does not offer the optimal | |
9362 | solution for binary trait. The package rareMETALS2 offers improved features | |
9363 | for analyzing gene-level association tests in meta-analyses for binary | |
9364 | trait.") | |
9365 | (license license:gpl3))) | |
0e7d058e RW |
9366 | |
9367 | (define-public r-maldiquant | |
9368 | (package | |
9369 | (name "r-maldiquant") | |
43949265 | 9370 | (version "1.17") |
0e7d058e RW |
9371 | (source |
9372 | (origin | |
9373 | (method url-fetch) | |
9374 | (uri (cran-uri "MALDIquant" version)) | |
9375 | (sha256 | |
9376 | (base32 | |
43949265 | 9377 | "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z")))) |
0e7d058e RW |
9378 | (properties `((upstream-name . "MALDIquant"))) |
9379 | (build-system r-build-system) | |
e9960d8c | 9380 | (home-page "https://cran.r-project.org/web/packages/MALDIquant") |
0e7d058e RW |
9381 | (synopsis "Quantitative analysis of mass spectrometry data") |
9382 | (description | |
9383 | "This package provides a complete analysis pipeline for matrix-assisted | |
9384 | laser desorption/ionization-time-of-flight (MALDI-TOF) and other | |
9385 | two-dimensional mass spectrometry data. In addition to commonly used plotting | |
9386 | and processing methods it includes distinctive features, namely baseline | |
9387 | subtraction methods such as morphological filters (TopHat) or the | |
9388 | statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak | |
9389 | alignment using warping functions, handling of replicated measurements as well | |
9390 | as allowing spectra with different resolutions.") | |
9391 | (license license:gpl3+))) | |
ae262174 RW |
9392 | |
9393 | (define-public r-protgenerics | |
9394 | (package | |
9395 | (name "r-protgenerics") | |
9a665dfb | 9396 | (version "1.10.0") |
ae262174 RW |
9397 | (source |
9398 | (origin | |
9399 | (method url-fetch) | |
9400 | (uri (bioconductor-uri "ProtGenerics" version)) | |
9401 | (sha256 | |
9402 | (base32 | |
9a665dfb | 9403 | "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni")))) |
ae262174 RW |
9404 | (properties `((upstream-name . "ProtGenerics"))) |
9405 | (build-system r-build-system) | |
9406 | (home-page "https://github.com/lgatto/ProtGenerics") | |
9407 | (synopsis "S4 generic functions for proteomics infrastructure") | |
9408 | (description | |
9409 | "This package provides S4 generic functions needed by Bioconductor | |
9410 | proteomics packages.") | |
9411 | (license license:artistic2.0))) | |
71676a1f RW |
9412 | |
9413 | (define-public r-mzr | |
9414 | (package | |
9415 | (name "r-mzr") | |
34b96754 | 9416 | (version "2.12.0") |
71676a1f RW |
9417 | (source |
9418 | (origin | |
9419 | (method url-fetch) | |
9420 | (uri (bioconductor-uri "mzR" version)) | |
9421 | (sha256 | |
9422 | (base32 | |
15ca1959 RW |
9423 | "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c")) |
9424 | (modules '((guix build utils))) | |
9425 | (snippet | |
9426 | '(begin | |
9427 | (delete-file-recursively "src/boost") | |
9428 | #t)))) | |
71676a1f RW |
9429 | (properties `((upstream-name . "mzR"))) |
9430 | (build-system r-build-system) | |
15ca1959 RW |
9431 | (arguments |
9432 | `(#:phases | |
9433 | (modify-phases %standard-phases | |
9434 | (add-after 'unpack 'use-system-boost | |
9435 | (lambda _ | |
9436 | (substitute* "src/Makevars" | |
9437 | (("\\./boost/libs.*") "") | |
9438 | (("ARCH_OBJS=" line) | |
9439 | (string-append line | |
9440 | "\nARCH_LIBS=-lboost_system -lboost_regex \ | |
9441 | -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n"))) | |
9442 | #t))))) | |
71676a1f | 9443 | (inputs |
34b96754 | 9444 | `(("boost" ,boost) ; use this instead of the bundled boost sources |
d534f3a4 | 9445 | ("netcdf" ,netcdf))) |
71676a1f RW |
9446 | (propagated-inputs |
9447 | `(("r-biobase" ,r-biobase) | |
9448 | ("r-biocgenerics" ,r-biocgenerics) | |
9449 | ("r-protgenerics" ,r-protgenerics) | |
9450 | ("r-rcpp" ,r-rcpp) | |
9451 | ("r-zlibbioc" ,r-zlibbioc))) | |
9452 | (home-page "https://github.com/sneumann/mzR/") | |
9453 | (synopsis "Parser for mass spectrometry data files") | |
9454 | (description | |
9455 | "The mzR package provides a unified API to the common file formats and | |
9456 | parsers available for mass spectrometry data. It comes with a wrapper for the | |
9457 | ISB random access parser for mass spectrometry mzXML, mzData and mzML files. | |
9458 | The package contains the original code written by the ISB, and a subset of the | |
9459 | proteowizard library for mzML and mzIdentML. The netCDF reading code has | |
9460 | previously been used in XCMS.") | |
9461 | (license license:artistic2.0))) | |
5c9d1505 RW |
9462 | |
9463 | (define-public r-affyio | |
9464 | (package | |
9465 | (name "r-affyio") | |
8a8138d2 | 9466 | (version "1.48.0") |
5c9d1505 RW |
9467 | (source |
9468 | (origin | |
9469 | (method url-fetch) | |
9470 | (uri (bioconductor-uri "affyio" version)) | |
9471 | (sha256 | |
9472 | (base32 | |
8a8138d2 | 9473 | "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9")))) |
5c9d1505 RW |
9474 | (build-system r-build-system) |
9475 | (propagated-inputs | |
9476 | `(("r-zlibbioc" ,r-zlibbioc))) | |
9477 | (inputs | |
9478 | `(("zlib" ,zlib))) | |
9479 | (home-page "https://github.com/bmbolstad/affyio") | |
9480 | (synopsis "Tools for parsing Affymetrix data files") | |
9481 | (description | |
9482 | "This package provides routines for parsing Affymetrix data files based | |
9483 | upon file format information. The primary focus is on accessing the CEL and | |
9484 | CDF file formats.") | |
9485 | (license license:lgpl2.0+))) | |
05c7e5fb RW |
9486 | |
9487 | (define-public r-affy | |
9488 | (package | |
9489 | (name "r-affy") | |
dad5f838 | 9490 | (version "1.56.0") |
05c7e5fb RW |
9491 | (source |
9492 | (origin | |
9493 | (method url-fetch) | |
9494 | (uri (bioconductor-uri "affy" version)) | |
9495 | (sha256 | |
9496 | (base32 | |
dad5f838 | 9497 | "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj")))) |
05c7e5fb RW |
9498 | (build-system r-build-system) |
9499 | (propagated-inputs | |
9500 | `(("r-affyio" ,r-affyio) | |
9501 | ("r-biobase" ,r-biobase) | |
9502 | ("r-biocgenerics" ,r-biocgenerics) | |
9503 | ("r-biocinstaller" ,r-biocinstaller) | |
9504 | ("r-preprocesscore" ,r-preprocesscore) | |
9505 | ("r-zlibbioc" ,r-zlibbioc))) | |
5713bbf1 | 9506 | (home-page "https://bioconductor.org/packages/affy") |
05c7e5fb RW |
9507 | (synopsis "Methods for affymetrix oligonucleotide arrays") |
9508 | (description | |
9509 | "This package contains functions for exploratory oligonucleotide array | |
9510 | analysis.") | |
9511 | (license license:lgpl2.0+))) | |
7c08afaf RW |
9512 | |
9513 | (define-public r-vsn | |
9514 | (package | |
9515 | (name "r-vsn") | |
1be0f536 | 9516 | (version "3.46.0") |
7c08afaf RW |
9517 | (source |
9518 | (origin | |
9519 | (method url-fetch) | |
9520 | (uri (bioconductor-uri "vsn" version)) | |
9521 | (sha256 | |
9522 | (base32 | |
1be0f536 | 9523 | "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j")))) |
7c08afaf RW |
9524 | (build-system r-build-system) |
9525 | (propagated-inputs | |
9526 | `(("r-affy" ,r-affy) | |
9527 | ("r-biobase" ,r-biobase) | |
9528 | ("r-ggplot2" ,r-ggplot2) | |
aeb64f3c | 9529 | ("r-lattice" ,r-lattice) |
7c08afaf | 9530 | ("r-limma" ,r-limma))) |
5713bbf1 | 9531 | (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html") |
7c08afaf RW |
9532 | (synopsis "Variance stabilization and calibration for microarray data") |
9533 | (description | |
9534 | "The package implements a method for normalising microarray intensities, | |
9535 | and works for single- and multiple-color arrays. It can also be used for data | |
9536 | from other technologies, as long as they have similar format. The method uses | |
9537 | a robust variant of the maximum-likelihood estimator for an | |
9538 | additive-multiplicative error model and affine calibration. The model | |
9539 | incorporates data calibration step (a.k.a. normalization), a model for the | |
9540 | dependence of the variance on the mean intensity and a variance stabilizing | |
9541 | data transformation. Differences between transformed intensities are | |
9542 | analogous to \"normalized log-ratios\". However, in contrast to the latter, | |
9543 | their variance is independent of the mean, and they are usually more sensitive | |
9544 | and specific in detecting differential transcription.") | |
9545 | (license license:artistic2.0))) | |
4aa7d592 RW |
9546 | |
9547 | (define-public r-mzid | |
9548 | (package | |
9549 | (name "r-mzid") | |
b500dbcd | 9550 | (version "1.16.0") |
4aa7d592 RW |
9551 | (source |
9552 | (origin | |
9553 | (method url-fetch) | |
9554 | (uri (bioconductor-uri "mzID" version)) | |
9555 | (sha256 | |
9556 | (base32 | |
b500dbcd | 9557 | "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9")))) |
4aa7d592 RW |
9558 | (properties `((upstream-name . "mzID"))) |
9559 | (build-system r-build-system) | |
9560 | (propagated-inputs | |
9561 | `(("r-doparallel" ,r-doparallel) | |
9562 | ("r-foreach" ,r-foreach) | |
9563 | ("r-iterators" ,r-iterators) | |
9564 | ("r-plyr" ,r-plyr) | |
9565 | ("r-protgenerics" ,r-protgenerics) | |
9566 | ("r-rcpp" ,r-rcpp) | |
9567 | ("r-xml" ,r-xml))) | |
5713bbf1 | 9568 | (home-page "https://bioconductor.org/packages/mzID") |
4aa7d592 RW |
9569 | (synopsis "Parser for mzIdentML files") |
9570 | (description | |
9571 | "This package provides a parser for mzIdentML files implemented using the | |
9572 | XML package. The parser tries to be general and able to handle all types of | |
9573 | mzIdentML files with the drawback of having less pretty output than a vendor | |
9574 | specific parser.") | |
9575 | (license license:gpl2+))) | |
6a67e181 RW |
9576 | |
9577 | (define-public r-pcamethods | |
9578 | (package | |
9579 | (name "r-pcamethods") | |
a998c9a4 | 9580 | (version "1.70.0") |
6a67e181 RW |
9581 | (source |
9582 | (origin | |
9583 | (method url-fetch) | |
9584 | (uri (bioconductor-uri "pcaMethods" version)) | |
9585 | (sha256 | |
9586 | (base32 | |
a998c9a4 | 9587 | "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8")))) |
6a67e181 RW |
9588 | (properties `((upstream-name . "pcaMethods"))) |
9589 | (build-system r-build-system) | |
9590 | (propagated-inputs | |
9591 | `(("r-biobase" ,r-biobase) | |
9592 | ("r-biocgenerics" ,r-biocgenerics) | |
aeb64f3c | 9593 | ("r-mass" ,r-mass) |
6a67e181 RW |
9594 | ("r-rcpp" ,r-rcpp))) |
9595 | (home-page "https://github.com/hredestig/pcamethods") | |
9596 | (synopsis "Collection of PCA methods") | |
9597 | (description | |
9598 | "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA, | |
9599 | Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method | |
9600 | for missing value estimation is included for comparison. BPCA, PPCA and | |
9601 | NipalsPCA may be used to perform PCA on incomplete data as well as for | |
9602 | accurate missing value estimation. A set of methods for printing and plotting | |
9603 | the results is also provided. All PCA methods make use of the same data | |
9604 | structure (pcaRes) to provide a common interface to the PCA results.") | |
9605 | (license license:gpl3+))) | |
11879284 RW |
9606 | |
9607 | (define-public r-msnbase | |
9608 | (package | |
9609 | (name "r-msnbase") | |
53f0dea9 | 9610 | (version "2.4.2") |
11879284 RW |
9611 | (source |
9612 | (origin | |
9613 | (method url-fetch) | |
9614 | (uri (bioconductor-uri "MSnbase" version)) | |
9615 | (sha256 | |
9616 | (base32 | |
53f0dea9 | 9617 | "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif")))) |
11879284 RW |
9618 | (properties `((upstream-name . "MSnbase"))) |
9619 | (build-system r-build-system) | |
9620 | (propagated-inputs | |
9621 | `(("r-affy" ,r-affy) | |
9622 | ("r-biobase" ,r-biobase) | |
9623 | ("r-biocgenerics" ,r-biocgenerics) | |
9624 | ("r-biocparallel" ,r-biocparallel) | |
9625 | ("r-digest" ,r-digest) | |
9626 | ("r-ggplot2" ,r-ggplot2) | |
9627 | ("r-impute" ,r-impute) | |
9628 | ("r-iranges" ,r-iranges) | |
baa00ee9 | 9629 | ("r-lattice" ,r-lattice) |
11879284 RW |
9630 | ("r-maldiquant" ,r-maldiquant) |
9631 | ("r-mzid" ,r-mzid) | |
9632 | ("r-mzr" ,r-mzr) | |
9633 | ("r-pcamethods" ,r-pcamethods) | |
9634 | ("r-plyr" ,r-plyr) | |
9635 | ("r-preprocesscore" ,r-preprocesscore) | |
9636 | ("r-protgenerics" ,r-protgenerics) | |
9637 | ("r-rcpp" ,r-rcpp) | |
11879284 RW |
9638 | ("r-s4vectors" ,r-s4vectors) |
9639 | ("r-vsn" ,r-vsn) | |
9640 | ("r-xml" ,r-xml))) | |
9641 | (home-page "https://github.com/lgatto/MSnbase") | |
9642 | (synopsis "Base functions and classes for MS-based proteomics") | |
9643 | (description | |
9644 | "This package provides basic plotting, data manipulation and processing | |
e614d639 | 9645 | of mass spectrometry based proteomics data.") |
11879284 | 9646 | (license license:artistic2.0))) |
66da3a9f RW |
9647 | |
9648 | (define-public r-msnid | |
9649 | (package | |
9650 | (name "r-msnid") | |
87e91a9f | 9651 | (version "1.12.1") |
66da3a9f RW |
9652 | (source |
9653 | (origin | |
9654 | (method url-fetch) | |
9655 | (uri (bioconductor-uri "MSnID" version)) | |
9656 | (sha256 | |
9657 | (base32 | |
87e91a9f | 9658 | "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx")))) |
66da3a9f RW |
9659 | (properties `((upstream-name . "MSnID"))) |
9660 | (build-system r-build-system) | |
9661 | (propagated-inputs | |
9662 | `(("r-biobase" ,r-biobase) | |
9663 | ("r-data-table" ,r-data-table) | |
9664 | ("r-doparallel" ,r-doparallel) | |
9665 | ("r-dplyr" ,r-dplyr) | |
9666 | ("r-foreach" ,r-foreach) | |
9667 | ("r-iterators" ,r-iterators) | |
9668 | ("r-msnbase" ,r-msnbase) | |
9669 | ("r-mzid" ,r-mzid) | |
9670 | ("r-mzr" ,r-mzr) | |
9671 | ("r-protgenerics" ,r-protgenerics) | |
9672 | ("r-r-cache" ,r-r-cache) | |
9673 | ("r-rcpp" ,r-rcpp) | |
9674 | ("r-reshape2" ,r-reshape2))) | |
5713bbf1 | 9675 | (home-page "https://bioconductor.org/packages/MSnID") |
66da3a9f RW |
9676 | (synopsis "Utilities for LC-MSn proteomics identifications") |
9677 | (description | |
2923f3e5 RW |
9678 | "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data |
9679 | from mzIdentML (leveraging the mzID package) or text files. After collating | |
9680 | the search results from multiple datasets it assesses their identification | |
9681 | quality and optimize filtering criteria to achieve the maximum number of | |
9682 | identifications while not exceeding a specified false discovery rate. It also | |
9683 | contains a number of utilities to explore the MS/MS results and assess missed | |
9684 | and irregular enzymatic cleavages, mass measurement accuracy, etc.") | |
66da3a9f | 9685 | (license license:artistic2.0))) |
5ded35d8 | 9686 | |
2441c284 | 9687 | (define-public r-seurat |
f1a2b1cb RW |
9688 | (package |
9689 | (name "r-seurat") | |
ce8b9e3b | 9690 | (version "2.3.1") |
f1a2b1cb RW |
9691 | (source (origin |
9692 | (method url-fetch) | |
9693 | (uri (cran-uri "Seurat" version)) | |
9694 | (sha256 | |
9695 | (base32 | |
ce8b9e3b | 9696 | "0hi59rgdrr2iqfvx5bq7yq02hbjxkjl1fzidqj14z0ypq0nzbjys")) |
f1a2b1cb RW |
9697 | ;; Delete pre-built jar. |
9698 | (snippet | |
9699 | '(begin (delete-file "inst/java/ModularityOptimizer.jar") | |
9700 | #t)))) | |
9701 | (properties `((upstream-name . "Seurat"))) | |
9702 | (build-system r-build-system) | |
9703 | (arguments | |
9704 | `(#:phases | |
9705 | (modify-phases %standard-phases | |
9706 | (add-after 'unpack 'build-jar | |
9707 | (lambda* (#:key inputs #:allow-other-keys) | |
9708 | (let ((classesdir "tmp-classes")) | |
9709 | (setenv "JAVA_HOME" (assoc-ref inputs "jdk")) | |
9710 | (mkdir classesdir) | |
9711 | (with-output-to-file "manifest" | |
8271b8d2 RW |
9712 | (lambda _ |
9713 | (display "Manifest-Version: 1.0 | |
9714 | Main-Class: ModularityOptimizer\n"))) | |
9715 | (and (zero? (apply system* `("javac" "-d" ,classesdir | |
9716 | ,@(find-files "java" "\\.java$")))) | |
9717 | (zero? (system* "jar" | |
9718 | "-cmf" "manifest" | |
9719 | "inst/java/ModularityOptimizer.jar" | |
f1a2b1cb RW |
9720 | "-C" classesdir "."))))))))) |
9721 | (native-inputs | |
9722 | `(("jdk" ,icedtea "jdk"))) | |
9723 | (propagated-inputs | |
9724 | `(("r-ape" ,r-ape) | |
9725 | ("r-caret" ,r-caret) | |
c36ce476 | 9726 | ("r-cluster" ,r-cluster) |
f1a2b1cb RW |
9727 | ("r-cowplot" ,r-cowplot) |
9728 | ("r-diffusionmap" ,r-diffusionmap) | |
c36ce476 | 9729 | ("r-dosnow" ,r-dosnow) |
f1a2b1cb RW |
9730 | ("r-dplyr" ,r-dplyr) |
9731 | ("r-dtw" ,r-dtw) | |
c36ce476 | 9732 | ("r-fitdistrplus" ,r-fitdistrplus) |
f1a2b1cb | 9733 | ("r-fnn" ,r-fnn) |
c36ce476 | 9734 | ("r-foreach" ,r-foreach) |
f1a2b1cb RW |
9735 | ("r-fpc" ,r-fpc) |
9736 | ("r-gdata" ,r-gdata) | |
f1a2b1cb | 9737 | ("r-ggplot2" ,r-ggplot2) |
26e3e28c | 9738 | ("r-ggridges" ,r-ggridges) |
f1a2b1cb | 9739 | ("r-gplots" ,r-gplots) |
f1a2b1cb RW |
9740 | ("r-hmisc" ,r-hmisc) |
9741 | ("r-ica" ,r-ica) | |
9742 | ("r-igraph" ,r-igraph) | |
9743 | ("r-irlba" ,r-irlba) | |
9744 | ("r-lars" ,r-lars) | |
c36ce476 | 9745 | ("r-lmtest" ,r-lmtest) |
f1a2b1cb RW |
9746 | ("r-mass" ,r-mass) |
9747 | ("r-matrix" ,r-matrix) | |
ebec98ae | 9748 | ("r-metap" ,r-metap) |
f1a2b1cb | 9749 | ("r-mixtools" ,r-mixtools) |
f1a2b1cb RW |
9750 | ("r-pbapply" ,r-pbapply) |
9751 | ("r-plotly" ,r-plotly) | |
c36ce476 | 9752 | ("r-png" ,r-png) |
f1a2b1cb | 9753 | ("r-ranger" ,r-ranger) |
c36ce476 | 9754 | ("r-rann" ,r-rann) |
f1a2b1cb RW |
9755 | ("r-rcolorbrewer" ,r-rcolorbrewer) |
9756 | ("r-rcpp" ,r-rcpp) | |
26e3e28c | 9757 | ("r-rcppeigen" ,r-rcppeigen) |
f1a2b1cb RW |
9758 | ("r-rcppprogress" ,r-rcppprogress) |
9759 | ("r-reshape2" ,r-reshape2) | |
ce8b9e3b | 9760 | ("r-reticulate" ,r-reticulate) |
f1a2b1cb RW |
9761 | ("r-rocr" ,r-rocr) |
9762 | ("r-rtsne" ,r-rtsne) | |
9763 | ("r-sdmtools" ,r-sdmtools) | |
9764 | ("r-stringr" ,r-stringr) | |
9765 | ("r-tclust" ,r-tclust) | |
9766 | ("r-tidyr" ,r-tidyr) | |
9767 | ("r-tsne" ,r-tsne) | |
9768 | ("r-vgam" ,r-vgam))) | |
9769 | (home-page "http://www.satijalab.org/seurat") | |
9770 | (synopsis "Seurat is an R toolkit for single cell genomics") | |
9771 | (description | |
9772 | "This package is an R package designed for QC, analysis, and | |
2441c284 RJPB |
9773 | exploration of single cell RNA-seq data. It easily enables widely-used |
9774 | analytical techniques, including the identification of highly variable genes, | |
9775 | dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering | |
9776 | algorithms; density clustering, hierarchical clustering, k-means, and the | |
9777 | discovery of differentially expressed genes and markers.") | |
f1a2b1cb | 9778 | (license license:gpl3))) |
2441c284 | 9779 | |
d4b83651 RW |
9780 | (define-public r-aroma-light |
9781 | (package | |
9782 | (name "r-aroma-light") | |
531e8090 | 9783 | (version "3.8.0") |
d4b83651 RW |
9784 | (source |
9785 | (origin | |
9786 | (method url-fetch) | |
9787 | (uri (bioconductor-uri "aroma.light" version)) | |
9788 | (sha256 | |
9789 | (base32 | |
531e8090 | 9790 | "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc")))) |
d4b83651 RW |
9791 | (properties `((upstream-name . "aroma.light"))) |
9792 | (build-system r-build-system) | |
9793 | (propagated-inputs | |
9794 | `(("r-matrixstats" ,r-matrixstats) | |
9795 | ("r-r-methodss3" ,r-r-methodss3) | |
9796 | ("r-r-oo" ,r-r-oo) | |
9797 | ("r-r-utils" ,r-r-utils))) | |
9798 | (home-page "https://github.com/HenrikBengtsson/aroma.light") | |
9799 | (synopsis "Methods for normalization and visualization of microarray data") | |
9800 | (description | |
9801 | "This package provides methods for microarray analysis that take basic | |
9802 | data types such as matrices and lists of vectors. These methods can be used | |
9803 | standalone, be utilized in other packages, or be wrapped up in higher-level | |
9804 | classes.") | |
9805 | (license license:gpl2+))) | |
9806 | ||
7b465327 RW |
9807 | (define-public r-deseq |
9808 | (package | |
9809 | (name "r-deseq") | |
8140f680 | 9810 | (version "1.30.0") |
7b465327 RW |
9811 | (source |
9812 | (origin | |
9813 | (method url-fetch) | |
9814 | (uri (bioconductor-uri "DESeq" version)) | |
9815 | (sha256 | |
9816 | (base32 | |
8140f680 | 9817 | "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9")))) |
7b465327 RW |
9818 | (properties `((upstream-name . "DESeq"))) |
9819 | (build-system r-build-system) | |
9820 | (propagated-inputs | |
9821 | `(("r-biobase" ,r-biobase) | |
9822 | ("r-biocgenerics" ,r-biocgenerics) | |
9823 | ("r-genefilter" ,r-genefilter) | |
9824 | ("r-geneplotter" ,r-geneplotter) | |
9825 | ("r-lattice" ,r-lattice) | |
9826 | ("r-locfit" ,r-locfit) | |
9827 | ("r-mass" ,r-mass) | |
9828 | ("r-rcolorbrewer" ,r-rcolorbrewer))) | |
9829 | (home-page "http://www-huber.embl.de/users/anders/DESeq") | |
9830 | (synopsis "Differential gene expression analysis") | |
9831 | (description | |
9832 | "This package provides tools for estimating variance-mean dependence in | |
9833 | count data from high-throughput genetic sequencing assays and for testing for | |
9834 | differential expression based on a model using the negative binomial | |
9835 | distribution.") | |
9836 | (license license:gpl3+))) | |
9837 | ||
296b3c63 RW |
9838 | (define-public r-edaseq |
9839 | (package | |
9840 | (name "r-edaseq") | |
00961279 | 9841 | (version "2.12.0") |
296b3c63 RW |
9842 | (source |
9843 | (origin | |
9844 | (method url-fetch) | |
9845 | (uri (bioconductor-uri "EDASeq" version)) | |
9846 | (sha256 | |
9847 | (base32 | |
00961279 | 9848 | "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv")))) |
296b3c63 RW |
9849 | (properties `((upstream-name . "EDASeq"))) |
9850 | (build-system r-build-system) | |
9851 | (propagated-inputs | |
9852 | `(("r-annotationdbi" ,r-annotationdbi) | |
9853 | ("r-aroma-light" ,r-aroma-light) | |
9854 | ("r-biobase" ,r-biobase) | |
9855 | ("r-biocgenerics" ,r-biocgenerics) | |
9856 | ("r-biomart" ,r-biomart) | |
9857 | ("r-biostrings" ,r-biostrings) | |
9858 | ("r-deseq" ,r-deseq) | |
9859 | ("r-genomicfeatures" ,r-genomicfeatures) | |
9860 | ("r-genomicranges" ,r-genomicranges) | |
9861 | ("r-iranges" ,r-iranges) | |
9862 | ("r-rsamtools" ,r-rsamtools) | |
9863 | ("r-shortread" ,r-shortread))) | |
9864 | (home-page "https://github.com/drisso/EDASeq") | |
9865 | (synopsis "Exploratory data analysis and normalization for RNA-Seq") | |
9866 | (description | |
9867 | "This package provides support for numerical and graphical summaries of | |
9868 | RNA-Seq genomic read data. Provided within-lane normalization procedures to | |
9869 | adjust for GC-content effect (or other gene-level effects) on read counts: | |
9870 | loess robust local regression, global-scaling, and full-quantile | |
9871 | normalization. Between-lane normalization procedures to adjust for | |
9872 | distributional differences between lanes (e.g., sequencing depth): | |
9873 | global-scaling and full-quantile normalization.") | |
9874 | (license license:artistic2.0))) | |
9875 | ||
5f96f30f RW |
9876 | (define-public r-interactivedisplaybase |
9877 | (package | |
9878 | (name "r-interactivedisplaybase") | |
1567c8d9 | 9879 | (version "1.16.0") |
5f96f30f RW |
9880 | (source |
9881 | (origin | |
9882 | (method url-fetch) | |
9883 | (uri (bioconductor-uri "interactiveDisplayBase" version)) | |
9884 | (sha256 | |
9885 | (base32 | |
1567c8d9 | 9886 | "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5")))) |
5f96f30f RW |
9887 | (properties |
9888 | `((upstream-name . "interactiveDisplayBase"))) | |
9889 | (build-system r-build-system) | |
9890 | (propagated-inputs | |
9891 | `(("r-biocgenerics" ,r-biocgenerics) | |
9892 | ("r-shiny" ,r-shiny))) | |
5713bbf1 | 9893 | (home-page "https://bioconductor.org/packages/interactiveDisplayBase") |
5f96f30f RW |
9894 | (synopsis "Base package for web displays of Bioconductor objects") |
9895 | (description | |
9896 | "This package contains the basic methods needed to generate interactive | |
9897 | Shiny-based display methods for Bioconductor objects.") | |
9898 | (license license:artistic2.0))) | |
9899 | ||
4a007ffa RW |
9900 | (define-public r-annotationhub |
9901 | (package | |
9902 | (name "r-annotationhub") | |
9b8d0201 | 9903 | (version "2.10.1") |
4a007ffa RW |
9904 | (source |
9905 | (origin | |
9906 | (method url-fetch) | |
9907 | (uri (bioconductor-uri "AnnotationHub" version)) | |
9908 | (sha256 | |
9909 | (base32 | |
9b8d0201 | 9910 | "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4")))) |
4a007ffa RW |
9911 | (properties `((upstream-name . "AnnotationHub"))) |
9912 | (build-system r-build-system) | |
9913 | (propagated-inputs | |
9914 | `(("r-annotationdbi" ,r-annotationdbi) | |
9915 | ("r-biocgenerics" ,r-biocgenerics) | |
9916 | ("r-biocinstaller" ,r-biocinstaller) | |
14b3c719 | 9917 | ("r-curl" ,r-curl) |
4a007ffa RW |
9918 | ("r-httr" ,r-httr) |
9919 | ("r-interactivedisplaybase" ,r-interactivedisplaybase) | |
9920 | ("r-rsqlite" ,r-rsqlite) | |
9921 | ("r-s4vectors" ,r-s4vectors) | |
9922 | ("r-yaml" ,r-yaml))) | |
5713bbf1 | 9923 | (home-page "https://bioconductor.org/packages/AnnotationHub") |
4a007ffa RW |
9924 | (synopsis "Client to access AnnotationHub resources") |
9925 | (description | |
9926 | "This package provides a client for the Bioconductor AnnotationHub web | |
9927 | resource. The AnnotationHub web resource provides a central location where | |
9928 | genomic files (e.g. VCF, bed, wig) and other resources from standard | |
9929 | locations (e.g. UCSC, Ensembl) can be discovered. The resource includes | |
9930 | metadata about each resource, e.g., a textual description, tags, and date of | |
9931 | modification. The client creates and manages a local cache of files retrieved | |
9932 | by the user, helping with quick and reproducible access.") | |
9933 | (license license:artistic2.0))) | |
9934 | ||
d4a1e918 RW |
9935 | (define-public r-fastseg |
9936 | (package | |
9937 | (name "r-fastseg") | |
87fa5afa | 9938 | (version "1.24.0") |
d4a1e918 RW |
9939 | (source |
9940 | (origin | |
9941 | (method url-fetch) | |
9942 | (uri (bioconductor-uri "fastseg" version)) | |
9943 | (sha256 | |
9944 | (base32 | |
87fa5afa | 9945 | "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp")))) |
d4a1e918 RW |
9946 | (build-system r-build-system) |
9947 | (propagated-inputs | |
9948 | `(("r-biobase" ,r-biobase) | |
9949 | ("r-biocgenerics" ,r-biocgenerics) | |
9950 | ("r-genomicranges" ,r-genomicranges) | |
9951 | ("r-iranges" ,r-iranges) | |
9952 | ("r-s4vectors" ,r-s4vectors))) | |
9953 | (home-page "http://www.bioinf.jku.at/software/fastseg/index.html") | |
9954 | (synopsis "Fast segmentation algorithm for genetic sequencing data") | |
9955 | (description | |
9956 | "Fastseg implements a very fast and efficient segmentation algorithm. | |
9957 | It can segment data from DNA microarrays and data from next generation | |
9958 | sequencing for example to detect copy number segments. Further it can segment | |
9959 | data from RNA microarrays like tiling arrays to identify transcripts. Most | |
9960 | generally, it can segment data given as a matrix or as a vector. Various data | |
9961 | formats can be used as input to fastseg like expression set objects for | |
9962 | microarrays or GRanges for sequencing data.") | |
9963 | (license license:lgpl2.0+))) | |
9964 | ||
3121814e RW |
9965 | (define-public r-keggrest |
9966 | (package | |
9967 | (name "r-keggrest") | |
f5f94427 | 9968 | (version "1.18.1") |
3121814e RW |
9969 | (source |
9970 | (origin | |
9971 | (method url-fetch) | |
9972 | (uri (bioconductor-uri "KEGGREST" version)) | |
9973 | (sha256 | |
9974 | (base32 | |
f5f94427 | 9975 | "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c")))) |
3121814e RW |
9976 | (properties `((upstream-name . "KEGGREST"))) |
9977 | (build-system r-build-system) | |
9978 | (propagated-inputs | |
9979 | `(("r-biostrings" ,r-biostrings) | |
9980 | ("r-httr" ,r-httr) | |
9981 | ("r-png" ,r-png))) | |
9982 | (home-page "https://bioconductor.org/packages/KEGGREST") | |
9983 | (synopsis "Client-side REST access to KEGG") | |
9984 | (description | |
9985 | "This package provides a package that provides a client interface to the | |
9986 | @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.") | |
9987 | (license license:artistic2.0))) | |
9988 | ||
e160aa1f RW |
9989 | (define-public r-gage |
9990 | (package | |
9991 | (name "r-gage") | |
34d077b8 | 9992 | (version "2.28.2") |
e160aa1f RW |
9993 | (source |
9994 | (origin | |
9995 | (method url-fetch) | |
9996 | (uri (bioconductor-uri "gage" version)) | |
9997 | (sha256 | |
9998 | (base32 | |
34d077b8 | 9999 | "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii")))) |
e160aa1f RW |
10000 | (build-system r-build-system) |
10001 | (propagated-inputs | |
10002 | `(("r-annotationdbi" ,r-annotationdbi) | |
10003 | ("r-graph" ,r-graph) | |
10004 | ("r-keggrest" ,r-keggrest))) | |
10005 | (home-page "http://www.biomedcentral.com/1471-2105/10/161") | |
10006 | (synopsis "Generally applicable gene-set enrichment for pathway analysis") | |
10007 | (description | |
10008 | "GAGE is a published method for gene set (enrichment or GSEA) or pathway | |
10009 | analysis. GAGE is generally applicable independent of microarray or RNA-Seq | |
10010 | data attributes including sample sizes, experimental designs, assay platforms, | |
10011 | and other types of heterogeneity. The gage package provides functions for | |
10012 | basic GAGE analysis, result processing and presentation. In addition, it | |
10013 | provides demo microarray data and commonly used gene set data based on KEGG | |
10014 | pathways and GO terms. These funtions and data are also useful for gene set | |
10015 | analysis using other methods.") | |
10016 | (license license:gpl2+))) | |
10017 | ||
902fb15d RW |
10018 | (define-public r-genomicfiles |
10019 | (package | |
10020 | (name "r-genomicfiles") | |
10021 | (version "1.14.0") | |
10022 | (source | |
10023 | (origin | |
10024 | (method url-fetch) | |
10025 | (uri (bioconductor-uri "GenomicFiles" version)) | |
10026 | (sha256 | |
10027 | (base32 | |
10028 | "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n")))) | |
10029 | (properties `((upstream-name . "GenomicFiles"))) | |
10030 | (build-system r-build-system) | |
10031 | (propagated-inputs | |
10032 | `(("r-biocgenerics" ,r-biocgenerics) | |
10033 | ("r-biocparallel" ,r-biocparallel) | |
10034 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10035 | ("r-genomicalignments" ,r-genomicalignments) | |
10036 | ("r-genomicranges" ,r-genomicranges) | |
10037 | ("r-iranges" ,r-iranges) | |
10038 | ("r-rsamtools" ,r-rsamtools) | |
10039 | ("r-rtracklayer" ,r-rtracklayer) | |
10040 | ("r-s4vectors" ,r-s4vectors) | |
10041 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
10042 | ("r-variantannotation" ,r-variantannotation))) | |
10043 | (home-page "https://bioconductor.org/packages/GenomicFiles") | |
10044 | (synopsis "Distributed computing by file or by range") | |
10045 | (description | |
10046 | "This package provides infrastructure for parallel computations | |
10047 | distributed by file or by range. User defined mapper and reducer functions | |
10048 | provide added flexibility for data combination and manipulation.") | |
10049 | (license license:artistic2.0))) | |
10050 | ||
3af149f5 RW |
10051 | (define-public r-complexheatmap |
10052 | (package | |
10053 | (name "r-complexheatmap") | |
10054 | (version "1.17.1") | |
10055 | (source | |
10056 | (origin | |
10057 | (method url-fetch) | |
10058 | (uri (bioconductor-uri "ComplexHeatmap" version)) | |
10059 | (sha256 | |
10060 | (base32 | |
10061 | "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy")))) | |
10062 | (properties | |
10063 | `((upstream-name . "ComplexHeatmap"))) | |
10064 | (build-system r-build-system) | |
10065 | (propagated-inputs | |
10066 | `(("r-circlize" ,r-circlize) | |
10067 | ("r-colorspace" ,r-colorspace) | |
10068 | ("r-getoptlong" ,r-getoptlong) | |
10069 | ("r-globaloptions" ,r-globaloptions) | |
10070 | ("r-rcolorbrewer" ,r-rcolorbrewer))) | |
10071 | (home-page | |
10072 | "https://github.com/jokergoo/ComplexHeatmap") | |
10073 | (synopsis "Making Complex Heatmaps") | |
10074 | (description | |
10075 | "Complex heatmaps are efficient to visualize associations between | |
10076 | different sources of data sets and reveal potential structures. This package | |
10077 | provides a highly flexible way to arrange multiple heatmaps and supports | |
10078 | self-defined annotation graphics.") | |
10079 | (license license:gpl2+))) | |
10080 | ||
04e2a2e9 RW |
10081 | (define-public r-dirichletmultinomial |
10082 | (package | |
10083 | (name "r-dirichletmultinomial") | |
10084 | (version "1.20.0") | |
10085 | (source | |
10086 | (origin | |
10087 | (method url-fetch) | |
10088 | (uri (bioconductor-uri "DirichletMultinomial" version)) | |
10089 | (sha256 | |
10090 | (base32 | |
10091 | "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1")))) | |
10092 | (properties | |
10093 | `((upstream-name . "DirichletMultinomial"))) | |
10094 | (build-system r-build-system) | |
10095 | (inputs | |
10096 | `(("gsl" ,gsl))) | |
10097 | (propagated-inputs | |
10098 | `(("r-biocgenerics" ,r-biocgenerics) | |
10099 | ("r-iranges" ,r-iranges) | |
10100 | ("r-s4vectors" ,r-s4vectors))) | |
10101 | (home-page "https://bioconductor.org/packages/DirichletMultinomial") | |
10102 | (synopsis "Dirichlet-Multinomial mixture models for microbiome data") | |
10103 | (description | |
10104 | "Dirichlet-multinomial mixture models can be used to describe variability | |
10105 | in microbial metagenomic data. This package is an interface to code | |
10106 | originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2): | |
10107 | 1-15.") | |
10108 | (license license:lgpl3))) | |
10109 | ||
aa30ab5a RW |
10110 | (define-public r-ensembldb |
10111 | (package | |
10112 | (name "r-ensembldb") | |
8877ab43 | 10113 | (version "2.2.2") |
aa30ab5a RW |
10114 | (source |
10115 | (origin | |
10116 | (method url-fetch) | |
10117 | (uri (bioconductor-uri "ensembldb" version)) | |
10118 | (sha256 | |
10119 | (base32 | |
8877ab43 | 10120 | "1yngndkf3588z91z0a2fvkg423p26ajm6xv1p27x0l9mzhhaqq3k")))) |
aa30ab5a RW |
10121 | (build-system r-build-system) |
10122 | (propagated-inputs | |
10123 | `(("r-annotationdbi" ,r-annotationdbi) | |
10124 | ("r-annotationfilter" ,r-annotationfilter) | |
10125 | ("r-annotationhub" ,r-annotationhub) | |
10126 | ("r-biobase" ,r-biobase) | |
10127 | ("r-biocgenerics" ,r-biocgenerics) | |
10128 | ("r-biostrings" ,r-biostrings) | |
10129 | ("r-curl" ,r-curl) | |
10130 | ("r-dbi" ,r-dbi) | |
10131 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10132 | ("r-genomicfeatures" ,r-genomicfeatures) | |
10133 | ("r-genomicranges" ,r-genomicranges) | |
10134 | ("r-iranges" ,r-iranges) | |
10135 | ("r-protgenerics" ,r-protgenerics) | |
10136 | ("r-rsamtools" ,r-rsamtools) | |
10137 | ("r-rsqlite" ,r-rsqlite) | |
10138 | ("r-rtracklayer" ,r-rtracklayer) | |
10139 | ("r-s4vectors" ,r-s4vectors))) | |
10140 | (home-page "https://github.com/jotsetung/ensembldb") | |
10141 | (synopsis "Utilities to create and use Ensembl-based annotation databases") | |
10142 | (description | |
10143 | "The package provides functions to create and use transcript-centric | |
10144 | annotation databases/packages. The annotation for the databases are directly | |
10145 | fetched from Ensembl using their Perl API. The functionality and data is | |
10146 | similar to that of the TxDb packages from the @code{GenomicFeatures} package, | |
10147 | but, in addition to retrieve all gene/transcript models and annotations from | |
10148 | the database, the @code{ensembldb} package also provides a filter framework | |
10149 | allowing to retrieve annotations for specific entries like genes encoded on a | |
10150 | chromosome region or transcript models of lincRNA genes.") | |
10151 | ;; No version specified | |
10152 | (license license:lgpl3+))) | |
10153 | ||
2f6f61fd RW |
10154 | (define-public r-organismdbi |
10155 | (package | |
10156 | (name "r-organismdbi") | |
10157 | (version "1.20.0") | |
10158 | (source | |
10159 | (origin | |
10160 | (method url-fetch) | |
10161 | (uri (bioconductor-uri "OrganismDbi" version)) | |
10162 | (sha256 | |
10163 | (base32 | |
10164 | "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8")))) | |
10165 | (properties `((upstream-name . "OrganismDbi"))) | |
10166 | (build-system r-build-system) | |
10167 | (propagated-inputs | |
10168 | `(("r-annotationdbi" ,r-annotationdbi) | |
10169 | ("r-biobase" ,r-biobase) | |
10170 | ("r-biocgenerics" ,r-biocgenerics) | |
10171 | ("r-biocinstaller" ,r-biocinstaller) | |
10172 | ("r-dbi" ,r-dbi) | |
10173 | ("r-genomicfeatures" ,r-genomicfeatures) | |
10174 | ("r-genomicranges" ,r-genomicranges) | |
10175 | ("r-graph" ,r-graph) | |
10176 | ("r-iranges" ,r-iranges) | |
10177 | ("r-rbgl" ,r-rbgl) | |
10178 | ("r-s4vectors" ,r-s4vectors))) | |
10179 | (home-page "https://bioconductor.org/packages/OrganismDbi") | |
10180 | (synopsis "Software to enable the smooth interfacing of database packages") | |
10181 | (description "The package enables a simple unified interface to several | |
10182 | annotation packages each of which has its own schema by taking advantage of | |
10183 | the fact that each of these packages implements a select methods.") | |
10184 | (license license:artistic2.0))) | |
10185 | ||
7af1f403 RW |
10186 | (define-public r-biovizbase |
10187 | (package | |
10188 | (name "r-biovizbase") | |
10189 | (version "1.26.0") | |
10190 | (source | |
10191 | (origin | |
10192 | (method url-fetch) | |
10193 | (uri (bioconductor-uri "biovizBase" version)) | |
10194 | (sha256 | |
10195 | (base32 | |
10196 | "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f")))) | |
10197 | (properties `((upstream-name . "biovizBase"))) | |
10198 | (build-system r-build-system) | |
10199 | (propagated-inputs | |
10200 | `(("r-annotationdbi" ,r-annotationdbi) | |
10201 | ("r-annotationfilter" ,r-annotationfilter) | |
10202 | ("r-biocgenerics" ,r-biocgenerics) | |
10203 | ("r-biostrings" ,r-biostrings) | |
10204 | ("r-dichromat" ,r-dichromat) | |
10205 | ("r-ensembldb" ,r-ensembldb) | |
10206 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10207 | ("r-genomicalignments" ,r-genomicalignments) | |
10208 | ("r-genomicfeatures" ,r-genomicfeatures) | |
10209 | ("r-genomicranges" ,r-genomicranges) | |
10210 | ("r-hmisc" ,r-hmisc) | |
10211 | ("r-iranges" ,r-iranges) | |
10212 | ("r-rcolorbrewer" ,r-rcolorbrewer) | |
10213 | ("r-rsamtools" ,r-rsamtools) | |
10214 | ("r-s4vectors" ,r-s4vectors) | |
10215 | ("r-scales" ,r-scales) | |
10216 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
10217 | ("r-variantannotation" ,r-variantannotation))) | |
10218 | (home-page "https://bioconductor.org/packages/biovizBase") | |
10219 | (synopsis "Basic graphic utilities for visualization of genomic data") | |
10220 | (description | |
10221 | "The biovizBase package is designed to provide a set of utilities, color | |
10222 | schemes and conventions for genomic data. It serves as the base for various | |
10223 | high-level packages for biological data visualization. This saves development | |
10224 | effort and encourages consistency.") | |
10225 | (license license:artistic2.0))) | |
10226 | ||
60faf945 RW |
10227 | (define-public r-ggbio |
10228 | (package | |
10229 | (name "r-ggbio") | |
fc6d3e26 | 10230 | (version "1.26.1") |
60faf945 RW |
10231 | (source |
10232 | (origin | |
10233 | (method url-fetch) | |
10234 | (uri (bioconductor-uri "ggbio" version)) | |
10235 | (sha256 | |
10236 | (base32 | |
fc6d3e26 | 10237 | "1xlmlngn27iwnr21s9di4059kav1a7c1sajx08wja8yn8f7j06hp")))) |
60faf945 RW |
10238 | (build-system r-build-system) |
10239 | (propagated-inputs | |
10240 | `(("r-annotationdbi" ,r-annotationdbi) | |
10241 | ("r-annotationfilter" ,r-annotationfilter) | |
10242 | ("r-biobase" ,r-biobase) | |
10243 | ("r-biocgenerics" ,r-biocgenerics) | |
10244 | ("r-biostrings" ,r-biostrings) | |
10245 | ("r-biovizbase" ,r-biovizbase) | |
10246 | ("r-bsgenome" ,r-bsgenome) | |
10247 | ("r-ensembldb" ,r-ensembldb) | |
10248 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10249 | ("r-genomicalignments" ,r-genomicalignments) | |
10250 | ("r-genomicfeatures" ,r-genomicfeatures) | |
10251 | ("r-genomicranges" ,r-genomicranges) | |
10252 | ("r-ggally" ,r-ggally) | |
10253 | ("r-ggplot2" ,r-ggplot2) | |
10254 | ("r-gridextra" ,r-gridextra) | |
10255 | ("r-gtable" ,r-gtable) | |
10256 | ("r-hmisc" ,r-hmisc) | |
10257 | ("r-iranges" ,r-iranges) | |
10258 | ("r-organismdbi" ,r-organismdbi) | |
10259 | ("r-reshape2" ,r-reshape2) | |
10260 | ("r-rsamtools" ,r-rsamtools) | |
10261 | ("r-rtracklayer" ,r-rtracklayer) | |
10262 | ("r-s4vectors" ,r-s4vectors) | |
10263 | ("r-scales" ,r-scales) | |
10264 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
10265 | ("r-variantannotation" ,r-variantannotation))) | |
10266 | (home-page "http://www.tengfei.name/ggbio/") | |
10267 | (synopsis "Visualization tools for genomic data") | |
10268 | (description | |
10269 | "The ggbio package extends and specializes the grammar of graphics for | |
10270 | biological data. The graphics are designed to answer common scientific | |
10271 | questions, in particular those often asked of high throughput genomics data. | |
10272 | All core Bioconductor data structures are supported, where appropriate. The | |
10273 | package supports detailed views of particular genomic regions, as well as | |
10274 | genome-wide overviews. Supported overviews include ideograms and grand linear | |
10275 | views. High-level plots include sequence fragment length, edge-linked | |
10276 | interval to data view, mismatch pileup, and several splicing summaries.") | |
10277 | (license license:artistic2.0))) | |
10278 | ||
96a392a0 RW |
10279 | (define-public r-gprofiler |
10280 | (package | |
10281 | (name "r-gprofiler") | |
8defca1d | 10282 | (version "0.6.6") |
96a392a0 RW |
10283 | (source |
10284 | (origin | |
10285 | (method url-fetch) | |
10286 | (uri (cran-uri "gProfileR" version)) | |
10287 | (sha256 | |
10288 | (base32 | |
8defca1d | 10289 | "1n6cj12j102b4x9vhyl4dljp1i0r43p23cnhqbx4als2xfxdlqgi")))) |
96a392a0 RW |
10290 | (properties `((upstream-name . "gProfileR"))) |
10291 | (build-system r-build-system) | |
10292 | (propagated-inputs | |
10293 | `(("r-plyr" ,r-plyr) | |
10294 | ("r-rcurl" ,r-rcurl))) | |
e9960d8c | 10295 | (home-page "https://cran.r-project.org/web/packages/gProfileR/") |
96a392a0 RW |
10296 | (synopsis "Interface to the g:Profiler toolkit") |
10297 | (description | |
10298 | "This package provides tools for functional enrichment analysis, | |
10299 | gene identifier conversion and mapping homologous genes across related | |
10300 | organisms via the @code{g:Profiler} toolkit.") | |
10301 | (license license:gpl2+))) | |
10302 | ||
e2b92799 RW |
10303 | (define-public r-gqtlbase |
10304 | (package | |
10305 | (name "r-gqtlbase") | |
10306 | (version "1.10.0") | |
10307 | (source | |
10308 | (origin | |
10309 | (method url-fetch) | |
10310 | (uri (bioconductor-uri "gQTLBase" version)) | |
10311 | (sha256 | |
10312 | (base32 | |
10313 | "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035")))) | |
10314 | (properties `((upstream-name . "gQTLBase"))) | |
10315 | (build-system r-build-system) | |
10316 | (propagated-inputs | |
10317 | `(("r-batchjobs" ,r-batchjobs) | |
10318 | ("r-bbmisc" ,r-bbmisc) | |
10319 | ("r-biocgenerics" ,r-biocgenerics) | |
10320 | ("r-bit" ,r-bit) | |
10321 | ("r-doparallel" ,r-doparallel) | |
10322 | ("r-ff" ,r-ff) | |
10323 | ("r-ffbase" ,r-ffbase) | |
10324 | ("r-foreach" ,r-foreach) | |
10325 | ("r-genomicfiles" ,r-genomicfiles) | |
10326 | ("r-genomicranges" ,r-genomicranges) | |
10327 | ("r-rtracklayer" ,r-rtracklayer) | |
10328 | ("r-s4vectors" ,r-s4vectors) | |
10329 | ("r-summarizedexperiment" ,r-summarizedexperiment))) | |
10330 | (home-page "https://bioconductor.org/packages/gQTLBase") | |
10331 | (synopsis "Infrastructure for eQTL, mQTL and similar studies") | |
10332 | (description | |
10333 | "The purpose of this package is to simplify the storage and interrogation | |
10334 | of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL, | |
10335 | and more.") | |
10336 | (license license:artistic2.0))) | |
10337 | ||
dd5fc8b7 RW |
10338 | (define-public r-snpstats |
10339 | (package | |
10340 | (name "r-snpstats") | |
10341 | (version "1.28.0") | |
10342 | (source | |
10343 | (origin | |
10344 | (method url-fetch) | |
10345 | (uri (bioconductor-uri "snpStats" version)) | |
10346 | (sha256 | |
10347 | (base32 | |
10348 | "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir")))) | |
10349 | (properties `((upstream-name . "snpStats"))) | |
10350 | (build-system r-build-system) | |
10351 | (inputs `(("zlib" ,zlib))) | |
10352 | (propagated-inputs | |
10353 | `(("r-biocgenerics" ,r-biocgenerics) | |
10354 | ("r-matrix" ,r-matrix) | |
10355 | ("r-survival" ,r-survival) | |
10356 | ("r-zlibbioc" ,r-zlibbioc))) | |
10357 | (home-page "https://bioconductor.org/packages/snpStats") | |
10358 | (synopsis "Methods for SNP association studies") | |
10359 | (description | |
10360 | "This package provides classes and statistical methods for large | |
10361 | @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends | |
10362 | the earlier snpMatrix package, allowing for uncertainty in genotypes.") | |
10363 | (license license:gpl3))) | |
10364 | ||
421c68e3 RW |
10365 | (define-public r-homo-sapiens |
10366 | (package | |
10367 | (name "r-homo-sapiens") | |
10368 | (version "1.3.1") | |
10369 | (source (origin | |
10370 | (method url-fetch) | |
10371 | ;; We cannot use bioconductor-uri here because this tarball is | |
10372 | ;; located under "data/annotation/" instead of "bioc/". | |
10373 | (uri (string-append "http://www.bioconductor.org/packages/" | |
10374 | "release/data/annotation/src/contrib/" | |
10375 | "Homo.sapiens_" | |
10376 | version ".tar.gz")) | |
10377 | (sha256 | |
10378 | (base32 | |
10379 | "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01")))) | |
10380 | (properties | |
10381 | `((upstream-name . "Homo.sapiens"))) | |
10382 | (build-system r-build-system) | |
10383 | (propagated-inputs | |
10384 | `(("r-genomicfeatures" ,r-genomicfeatures) | |
10385 | ("r-go-db" ,r-go-db) | |
10386 | ("r-org-hs-eg-db" ,r-org-hs-eg-db) | |
10387 | ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene) | |
10388 | ("r-organismdbi" ,r-organismdbi) | |
10389 | ("r-annotationdbi" ,r-annotationdbi))) | |
10390 | (home-page "https://bioconductor.org/packages/Homo.sapiens/") | |
10391 | (synopsis "Annotation package for the Homo.sapiens object") | |
10392 | (description | |
10393 | "This package contains the Homo.sapiens object to access data from | |
10394 | several related annotation packages.") | |
10395 | (license license:artistic2.0))) | |
10396 | ||
15f98b0d RW |
10397 | (define-public r-erma |
10398 | (package | |
10399 | (name "r-erma") | |
fb1dcfac | 10400 | (version "0.10.1") |
15f98b0d RW |
10401 | (source |
10402 | (origin | |
10403 | (method url-fetch) | |
10404 | (uri (bioconductor-uri "erma" version)) | |
10405 | (sha256 | |
10406 | (base32 | |
fb1dcfac | 10407 | "1fi8nc6fbd7i4p9i9hli31xplmdpsxqcdrb8v3nf8fx9klllbdav")))) |
15f98b0d RW |
10408 | (build-system r-build-system) |
10409 | (propagated-inputs | |
10410 | `(("r-annotationdbi" ,r-annotationdbi) | |
10411 | ("r-biobase" ,r-biobase) | |
10412 | ("r-biocgenerics" ,r-biocgenerics) | |
10413 | ("r-foreach" ,r-foreach) | |
10414 | ("r-genomicfiles" ,r-genomicfiles) | |
10415 | ("r-genomicranges" ,r-genomicranges) | |
10416 | ("r-ggplot2" ,r-ggplot2) | |
10417 | ("r-homo-sapiens" ,r-homo-sapiens) | |
10418 | ("r-rtracklayer" ,r-rtracklayer) | |
10419 | ("r-s4vectors" ,r-s4vectors) | |
10420 | ("r-shiny" ,r-shiny) | |
10421 | ("r-summarizedexperiment" ,r-summarizedexperiment))) | |
10422 | (home-page "https://bioconductor.org/packages/erma") | |
10423 | (synopsis "Epigenomic road map adventures") | |
10424 | (description | |
10425 | "The epigenomics road map describes locations of epigenetic marks in DNA | |
10426 | from a variety of cell types. Of interest are locations of histone | |
10427 | modifications, sites of DNA methylation, and regions of accessible chromatin. | |
10428 | This package presents a selection of elements of the road map including | |
10429 | metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines | |
10430 | by Ernst and Kellis.") | |
10431 | (license license:artistic2.0))) | |
10432 | ||
66c39102 RW |
10433 | (define-public r-ldblock |
10434 | (package | |
10435 | (name "r-ldblock") | |
b6d7deca | 10436 | (version "1.8.1") |
66c39102 RW |
10437 | (source |
10438 | (origin | |
10439 | (method url-fetch) | |
10440 | (uri (bioconductor-uri "ldblock" version)) | |
10441 | (sha256 | |
10442 | (base32 | |
b6d7deca | 10443 | "1q8dz8wcq1r7kr635s9q21g36sxkdybk8khhpa4p57qv8r0gppl0")))) |
66c39102 RW |
10444 | (build-system r-build-system) |
10445 | (propagated-inputs | |
10446 | `(("r-erma" ,r-erma) | |
10447 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10448 | ("r-genomicfiles" ,r-genomicfiles) | |
10449 | ("r-go-db" ,r-go-db) | |
10450 | ("r-homo-sapiens" ,r-homo-sapiens) | |
10451 | ("r-matrix" ,r-matrix) | |
10452 | ("r-rsamtools" ,r-rsamtools) | |
10453 | ("r-snpstats" ,r-snpstats) | |
10454 | ("r-variantannotation" ,r-variantannotation))) | |
10455 | (home-page "https://bioconductor.org/packages/ldblock") | |
10456 | (synopsis "Data structures for linkage disequilibrium measures in populations") | |
10457 | (description | |
10458 | "This package defines data structures for @dfn{linkage | |
10459 | disequilibrium} (LD) measures in populations. Its purpose is to simplify | |
10460 | handling of existing population-level data for the purpose of flexibly | |
10461 | defining LD blocks.") | |
10462 | (license license:artistic2.0))) | |
10463 | ||
794ff347 RW |
10464 | (define-public r-gqtlstats |
10465 | (package | |
10466 | (name "r-gqtlstats") | |
2ccd8501 | 10467 | (version "1.10.1") |
794ff347 RW |
10468 | (source |
10469 | (origin | |
10470 | (method url-fetch) | |
10471 | (uri (bioconductor-uri "gQTLstats" version)) | |
10472 | (sha256 | |
10473 | (base32 | |
2ccd8501 | 10474 | "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq")))) |
794ff347 RW |
10475 | (properties `((upstream-name . "gQTLstats"))) |
10476 | (build-system r-build-system) | |
10477 | (propagated-inputs | |
10478 | `(("r-annotationdbi" ,r-annotationdbi) | |
10479 | ("r-batchjobs" ,r-batchjobs) | |
10480 | ("r-bbmisc" ,r-bbmisc) | |
10481 | ("r-beeswarm" ,r-beeswarm) | |
10482 | ("r-biobase" ,r-biobase) | |
10483 | ("r-biocgenerics" ,r-biocgenerics) | |
10484 | ("r-doparallel" ,r-doparallel) | |
10485 | ("r-dplyr" ,r-dplyr) | |
10486 | ("r-erma" ,r-erma) | |
10487 | ("r-ffbase" ,r-ffbase) | |
10488 | ("r-foreach" ,r-foreach) | |
10489 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10490 | ("r-genomicfeatures" ,r-genomicfeatures) | |
10491 | ("r-genomicfiles" ,r-genomicfiles) | |
10492 | ("r-genomicranges" ,r-genomicranges) | |
10493 | ("r-ggbeeswarm" ,r-ggbeeswarm) | |
10494 | ("r-ggplot2" ,r-ggplot2) | |
10495 | ("r-gqtlbase" ,r-gqtlbase) | |
10496 | ("r-hardyweinberg" ,r-hardyweinberg) | |
10497 | ("r-iranges" ,r-iranges) | |
10498 | ("r-ldblock" ,r-ldblock) | |
10499 | ("r-limma" ,r-limma) | |
10500 | ("r-mgcv" ,r-mgcv) | |
10501 | ("r-plotly" ,r-plotly) | |
10502 | ("r-reshape2" ,r-reshape2) | |
10503 | ("r-s4vectors" ,r-s4vectors) | |
10504 | ("r-shiny" ,r-shiny) | |
10505 | ("r-snpstats" ,r-snpstats) | |
10506 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
10507 | ("r-variantannotation" ,r-variantannotation))) | |
10508 | (home-page "https://bioconductor.org/packages/gQTLstats") | |
10509 | (synopsis "Computationally efficient analysis for eQTL and allied studies") | |
10510 | (description | |
10511 | "This package provides tools for the computationally efficient analysis | |
10512 | of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc. | |
10513 | The software in this package aims to support refinements and functional | |
10514 | interpretation of members of a collection of association statistics on a | |
10515 | family of feature/genome hypotheses.") | |
10516 | (license license:artistic2.0))) | |
10517 | ||
42720006 RW |
10518 | (define-public r-gviz |
10519 | (package | |
10520 | (name "r-gviz") | |
d578278e | 10521 | (version "1.22.3") |
42720006 RW |
10522 | (source |
10523 | (origin | |
10524 | (method url-fetch) | |
10525 | (uri (bioconductor-uri "Gviz" version)) | |
10526 | (sha256 | |
10527 | (base32 | |
d578278e | 10528 | "1grjzrjpzkw572pbvpsvdnfkfgwybl0cnjd7nnk2xdr26wnbsi9a")))) |
42720006 RW |
10529 | (properties `((upstream-name . "Gviz"))) |
10530 | (build-system r-build-system) | |
10531 | (propagated-inputs | |
10532 | `(("r-annotationdbi" ,r-annotationdbi) | |
10533 | ("r-biobase" ,r-biobase) | |
10534 | ("r-biocgenerics" ,r-biocgenerics) | |
10535 | ("r-biomart" ,r-biomart) | |
10536 | ("r-biostrings" ,r-biostrings) | |
10537 | ("r-biovizbase" ,r-biovizbase) | |
10538 | ("r-bsgenome" ,r-bsgenome) | |
10539 | ("r-digest" ,r-digest) | |
10540 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10541 | ("r-genomicalignments" ,r-genomicalignments) | |
10542 | ("r-genomicfeatures" ,r-genomicfeatures) | |
10543 | ("r-genomicranges" ,r-genomicranges) | |
10544 | ("r-iranges" ,r-iranges) | |
10545 | ("r-lattice" ,r-lattice) | |
10546 | ("r-latticeextra" ,r-latticeextra) | |
10547 | ("r-matrixstats" ,r-matrixstats) | |
10548 | ("r-rcolorbrewer" ,r-rcolorbrewer) | |
10549 | ("r-rsamtools" ,r-rsamtools) | |
10550 | ("r-rtracklayer" ,r-rtracklayer) | |
10551 | ("r-s4vectors" ,r-s4vectors) | |
10552 | ("r-xvector" ,r-xvector))) | |
10553 | (home-page "https://bioconductor.org/packages/Gviz") | |
10554 | (synopsis "Plotting data and annotation information along genomic coordinates") | |
10555 | (description | |
10556 | "Genomic data analyses requires integrated visualization of known genomic | |
10557 | information and new experimental data. Gviz uses the biomaRt and the | |
10558 | rtracklayer packages to perform live annotation queries to Ensembl and UCSC | |
10559 | and translates this to e.g. gene/transcript structures in viewports of the | |
10560 | grid graphics package. This results in genomic information plotted together | |
10561 | with your data.") | |
10562 | (license license:artistic2.0))) | |
10563 | ||
2e4ce60e RW |
10564 | (define-public r-gwascat |
10565 | (package | |
10566 | (name "r-gwascat") | |
10567 | (version "2.10.0") | |
10568 | (source | |
10569 | (origin | |
10570 | (method url-fetch) | |
10571 | (uri (bioconductor-uri "gwascat" version)) | |
10572 | (sha256 | |
10573 | (base32 | |
10574 | "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi")))) | |
10575 | (build-system r-build-system) | |
10576 | (propagated-inputs | |
10577 | `(("r-annotationdbi" ,r-annotationdbi) | |
10578 | ("r-annotationhub" ,r-annotationhub) | |
10579 | ("r-biocgenerics" ,r-biocgenerics) | |
10580 | ("r-biostrings" ,r-biostrings) | |
10581 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10582 | ("r-genomicfeatures" ,r-genomicfeatures) | |
10583 | ("r-genomicranges" ,r-genomicranges) | |
10584 | ("r-ggbio" ,r-ggbio) | |
10585 | ("r-ggplot2" ,r-ggplot2) | |
10586 | ("r-gqtlstats" ,r-gqtlstats) | |
10587 | ("r-graph" ,r-graph) | |
10588 | ("r-gviz" ,r-gviz) | |
10589 | ("r-homo-sapiens" ,r-homo-sapiens) | |
10590 | ("r-iranges" ,r-iranges) | |
10591 | ("r-rsamtools" ,r-rsamtools) | |
10592 | ("r-rtracklayer" ,r-rtracklayer) | |
10593 | ("r-s4vectors" ,r-s4vectors) | |
10594 | ("r-snpstats" ,r-snpstats) | |
10595 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
10596 | ("r-variantannotation" ,r-variantannotation))) | |
10597 | (home-page "https://bioconductor.org/packages/gwascat") | |
10598 | (synopsis "Tools for data in the EMBL-EBI GWAS catalog") | |
10599 | (description | |
10600 | "This package provides tools for representing and modeling data in the | |
10601 | EMBL-EBI GWAS catalog.") | |
10602 | (license license:artistic2.0))) | |
10603 | ||
fbf54406 RW |
10604 | (define-public r-sushi |
10605 | (package | |
10606 | (name "r-sushi") | |
10607 | (version "1.16.0") | |
10608 | (source (origin | |
10609 | (method url-fetch) | |
10610 | (uri (bioconductor-uri "Sushi" version)) | |
10611 | (sha256 | |
10612 | (base32 | |
10613 | "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g")))) | |
10614 | (properties `((upstream-name . "Sushi"))) | |
10615 | (build-system r-build-system) | |
10616 | (propagated-inputs | |
10617 | `(("r-biomart" ,r-biomart) | |
10618 | ("r-zoo" ,r-zoo))) | |
10619 | (home-page "https://bioconductor.org/packages/Sushi") | |
10620 | (synopsis "Tools for visualizing genomics data") | |
10621 | (description | |
10622 | "This package provides flexible, quantitative, and integrative genomic | |
10623 | visualizations for publication-quality multi-panel figures.") | |
10624 | (license license:gpl2+))) | |
10625 | ||
30eb4e37 RW |
10626 | (define-public r-fithic |
10627 | (package | |
10628 | (name "r-fithic") | |
10629 | (version "1.4.0") | |
10630 | (source (origin | |
10631 | (method url-fetch) | |
10632 | (uri (bioconductor-uri "FitHiC" version)) | |
10633 | (sha256 | |
10634 | (base32 | |
10635 | "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n")))) | |
10636 | (properties `((upstream-name . "FitHiC"))) | |
10637 | (build-system r-build-system) | |
10638 | (propagated-inputs | |
10639 | `(("r-data-table" ,r-data-table) | |
10640 | ("r-fdrtool" ,r-fdrtool) | |
10641 | ("r-rcpp" ,r-rcpp))) | |
10642 | (home-page "https://bioconductor.org/packages/FitHiC") | |
10643 | (synopsis "Confidence estimation for intra-chromosomal contact maps") | |
10644 | (description | |
10645 | "Fit-Hi-C is a tool for assigning statistical confidence estimates to | |
10646 | intra-chromosomal contact maps produced by genome-wide genome architecture | |
10647 | assays such as Hi-C.") | |
10648 | (license license:gpl2+))) | |
10649 | ||
c49102ec RW |
10650 | (define-public r-hitc |
10651 | (package | |
10652 | (name "r-hitc") | |
80323c3c | 10653 | (version "1.22.1") |
c49102ec RW |
10654 | (source (origin |
10655 | (method url-fetch) | |
10656 | (uri (bioconductor-uri "HiTC" version)) | |
10657 | (sha256 | |
10658 | (base32 | |
80323c3c | 10659 | "0da1jw9my2n2gihs31zyn14wwr23d8v2vij39ll7rm6fma3ydfbl")))) |
c49102ec RW |
10660 | (properties `((upstream-name . "HiTC"))) |
10661 | (build-system r-build-system) | |
10662 | (propagated-inputs | |
10663 | `(("r-biostrings" ,r-biostrings) | |
10664 | ("r-genomeinfodb" ,r-genomeinfodb) | |
10665 | ("r-genomicranges" ,r-genomicranges) | |
10666 | ("r-iranges" ,r-iranges) | |
10667 | ("r-matrix" ,r-matrix) | |
10668 | ("r-rcolorbrewer" ,r-rcolorbrewer) | |
10669 | ("r-rtracklayer" ,r-rtracklayer))) | |
10670 | (home-page "https://bioconductor.org/packages/HiTC") | |
10671 | (synopsis "High throughput chromosome conformation capture analysis") | |
10672 | (description | |
10673 | "The HiTC package was developed to explore high-throughput \"C\" data | |
10674 | such as 5C or Hi-C. Dedicated R classes as well as standard methods for | |
10675 | quality controls, normalization, visualization, and further analysis are also | |
10676 | provided.") | |
10677 | (license license:artistic2.0))) | |
10678 | ||
212f6120 RW |
10679 | (define-public r-qvalue |
10680 | (package | |
10681 | (name "r-qvalue") | |
98791c25 | 10682 | (version "2.10.0") |
212f6120 RW |
10683 | (source |
10684 | (origin | |
10685 | (method url-fetch) | |
10686 | (uri (bioconductor-uri "qvalue" version)) | |
10687 | (sha256 | |
10688 | (base32 | |
98791c25 | 10689 | "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i")))) |
212f6120 RW |
10690 | (build-system r-build-system) |
10691 | (propagated-inputs | |
10692 | `(("r-ggplot2" ,r-ggplot2) | |
10693 | ("r-reshape2" ,r-reshape2))) | |
10694 | (home-page "http://github.com/jdstorey/qvalue") | |
10695 | (synopsis "Q-value estimation for false discovery rate control") | |
10696 | (description | |
10697 | "This package takes a list of p-values resulting from the simultaneous | |
10698 | testing of many hypotheses and estimates their q-values and local @dfn{false | |
10699 | discovery rate} (FDR) values. The q-value of a test measures the proportion | |
10700 | of false positives incurred when that particular test is called significant. | |
10701 | The local FDR measures the posterior probability the null hypothesis is true | |
10702 | given the test's p-value. Various plots are automatically generated, allowing | |
10703 | one to make sensible significance cut-offs. The software can be applied to | |
10704 | problems in genomics, brain imaging, astrophysics, and data mining.") | |
10705 | ;; Any version of the LGPL. | |
10706 | (license license:lgpl3+))) | |
10707 | ||
aba3e482 RW |
10708 | (define-public r-hdf5array |
10709 | (package | |
10710 | (name "r-hdf5array") | |
10711 | (version "1.6.0") | |
10712 | (source | |
10713 | (origin | |
10714 | (method url-fetch) | |
10715 | (uri (bioconductor-uri "HDF5Array" version)) | |
10716 | (sha256 | |
10717 | (base32 | |
10718 | "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh")))) | |
10719 | (properties `((upstream-name . "HDF5Array"))) | |
10720 | (build-system r-build-system) | |
10721 | (propagated-inputs | |
10722 | `(("r-biocgenerics" ,r-biocgenerics) | |
10723 | ("r-delayedarray" ,r-delayedarray) | |
10724 | ("r-iranges" ,r-iranges) | |
10725 | ("r-rhdf5" ,r-rhdf5) | |
10726 | ("r-s4vectors" ,r-s4vectors))) | |
10727 | (home-page "https://bioconductor.org/packages/HDF5Array") | |
10728 | (synopsis "HDF5 back end for DelayedArray objects") | |
10729 | (description "This package provides an array-like container for convenient | |
10730 | access and manipulation of HDF5 datasets. It supports delayed operations and | |
10731 | block processing.") | |
10732 | (license license:artistic2.0))) | |
10733 | ||
748e9f16 RW |
10734 | (define-public r-rhdf5lib |
10735 | (package | |
10736 | (name "r-rhdf5lib") | |
10737 | (version "1.0.0") | |
10738 | (source | |
10739 | (origin | |
10740 | (method url-fetch) | |
10741 | (uri (bioconductor-uri "Rhdf5lib" version)) | |
10742 | (sha256 | |
10743 | (base32 | |
10744 | "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w")))) | |
10745 | (properties `((upstream-name . "Rhdf5lib"))) | |
10746 | (build-system r-build-system) | |
10747 | (arguments | |
10748 | `(#:phases | |
10749 | (modify-phases %standard-phases | |
10750 | (add-after 'unpack 'do-not-use-bundled-hdf5 | |
10751 | (lambda* (#:key inputs #:allow-other-keys) | |
10752 | (for-each delete-file '("configure" "configure.ac")) | |
10753 | ;; Do not make other packages link with the proprietary libsz. | |
10754 | (substitute* "R/zzz.R" | |
10755 | (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'") | |
10756 | "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'") | |
10757 | (("'%s/libhdf5.a %s/libsz.a'") | |
10758 | "'%s/libhdf5.a %s/libhdf5.a'")) | |
10759 | (with-directory-excursion "src" | |
10760 | (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source")) | |
10761 | (rename-file (string-append "hdf5-" ,(package-version hdf5)) | |
10762 | "hdf5") | |
a539ad86 RW |
10763 | ;; Remove timestamp and host system information to make |
10764 | ;; the build reproducible. | |
10765 | (substitute* "hdf5/src/libhdf5.settings.in" | |
10766 | (("Configured on: @CONFIG_DATE@") | |
10767 | "Configured on: Guix") | |
10768 | (("Uname information:.*") | |
10769 | "Uname information: Linux\n") | |
10770 | ;; Remove unnecessary store reference. | |
10771 | (("C Compiler:.*") | |
10772 | "C Compiler: GCC\n")) | |
748e9f16 RW |
10773 | (rename-file "Makevars.in" "Makevars") |
10774 | (substitute* "Makevars" | |
10775 | (("HDF5_CXX_LIB=.*") | |
10776 | (string-append "HDF5_CXX_LIB=" | |
10777 | (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n")) | |
10778 | (("HDF5_LIB=.*") | |
10779 | (string-append "HDF5_LIB=" | |
10780 | (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n")) | |
10781 | (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n") | |
10782 | (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n") | |
10783 | ;; szip is non-free software | |
10784 | (("cp \\$\\{SZIP_LIB\\}.*") "") | |
10785 | (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}") | |
10786 | "PKG_LIBS = ${HDF5_LIB}\n"))) | |
10787 | #t))))) | |
10788 | (inputs | |
10789 | `(("zlib" ,zlib))) | |
10790 | (propagated-inputs | |
10791 | `(("hdf5" ,hdf5))) | |
10792 | (native-inputs | |
10793 | `(("hdf5-source" ,(package-source hdf5)))) | |
10794 | (home-page "https://bioconductor.org/packages/Rhdf5lib") | |
10795 | (synopsis "HDF5 library as an R package") | |
10796 | (description "This package provides C and C++ HDF5 libraries for use in R | |
10797 | packages.") | |
10798 | (license license:artistic2.0))) | |
10799 | ||
9ec08988 RW |
10800 | (define-public r-beachmat |
10801 | (package | |
10802 | (name "r-beachmat") | |
10803 | (version "1.0.2") | |
10804 | (source | |
10805 | (origin | |
10806 | (method url-fetch) | |
10807 | (uri (bioconductor-uri "beachmat" version)) | |
10808 | (sha256 | |
10809 | (base32 | |
10810 | "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz")))) | |
10811 | (build-system r-build-system) | |
10812 | (inputs | |
10813 | `(("hdf5" ,hdf5))) | |
10814 | (propagated-inputs | |
10815 | `(("r-delayedarray" ,r-delayedarray) | |
10816 | ("r-hdf5array" ,r-hdf5array) | |
10817 | ("r-rcpp" ,r-rcpp) | |
10818 | ("r-rhdf5" ,r-rhdf5) | |
10819 | ("r-rhdf5lib" ,r-rhdf5lib))) | |
10820 | (home-page "https://bioconductor.org/packages/beachmat") | |
10821 | (synopsis "Compiling Bioconductor to handle each matrix type") | |
10822 | (description "This package provides a consistent C++ class interface for a | |
10823 | variety of commonly used matrix types, including sparse and HDF5-backed | |
10824 | matrices.") | |
10825 | (license license:gpl3))) | |
10826 | ||
6fb1dc17 RW |
10827 | (define-public r-singlecellexperiment |
10828 | (package | |
10829 | (name "r-singlecellexperiment") | |
10830 | (version "1.0.0") | |
10831 | (source | |
10832 | (origin | |
10833 | (method url-fetch) | |
10834 | (uri (bioconductor-uri "SingleCellExperiment" version)) | |
10835 | (sha256 | |
10836 | (base32 | |
10837 | "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars")))) | |
10838 | (properties | |
10839 | `((upstream-name . "SingleCellExperiment"))) | |
10840 | (build-system r-build-system) | |
10841 | (propagated-inputs | |
10842 | `(("r-biocgenerics" ,r-biocgenerics) | |
10843 | ("r-s4vectors" ,r-s4vectors) | |
10844 | ("r-summarizedexperiment" ,r-summarizedexperiment))) | |
10845 | (home-page "https://bioconductor.org/packages/SingleCellExperiment") | |
10846 | (synopsis "S4 classes for single cell data") | |
10847 | (description "This package defines an S4 class for storing data from | |
10848 | single-cell experiments. This includes specialized methods to store and | |
10849 | retrieve spike-in information, dimensionality reduction coordinates and size | |
10850 | factors for each cell, along with the usual metadata for genes and | |
10851 | libraries.") | |
10852 | (license license:gpl3))) | |
10853 | ||
658ab21d RW |
10854 | (define-public r-scater |
10855 | (package | |
10856 | (name "r-scater") | |
59b2864d | 10857 | (version "1.6.3") |
658ab21d RW |
10858 | (source (origin |
10859 | (method url-fetch) | |
10860 | (uri (bioconductor-uri "scater" version)) | |
10861 | (sha256 | |
10862 | (base32 | |
59b2864d | 10863 | "0q3s96gf8saa1dq2fvmpl0jyj7bx3wrdfck3hanb8pxkcir2p7dn")))) |
658ab21d RW |
10864 | (build-system r-build-system) |
10865 | (propagated-inputs | |
10866 | `(("r-beachmat" ,r-beachmat) | |
10867 | ("r-biobase" ,r-biobase) | |
10868 | ("r-biocgenerics" ,r-biocgenerics) | |
10869 | ("r-biomart" ,r-biomart) | |
10870 | ("r-data-table" ,r-data-table) | |
10871 | ("r-dplyr" ,r-dplyr) | |
10872 | ("r-edger" ,r-edger) | |
10873 | ("r-ggbeeswarm" ,r-ggbeeswarm) | |
10874 | ("r-ggplot2" ,r-ggplot2) | |
10875 | ("r-limma" ,r-limma) | |
10876 | ("r-matrix" ,r-matrix) | |
10877 | ("r-matrixstats" ,r-matrixstats) | |
10878 | ("r-plyr" ,r-plyr) | |
10879 | ("r-rcpp" ,r-rcpp) | |
10880 | ("r-reshape2" ,r-reshape2) | |
10881 | ("r-rhdf5" ,r-rhdf5) | |
10882 | ("r-rhdf5lib" ,r-rhdf5lib) | |
10883 | ("r-rjson" ,r-rjson) | |
10884 | ("r-s4vectors" ,r-s4vectors) | |
10885 | ("r-shiny" ,r-shiny) | |
10886 | ("r-shinydashboard" ,r-shinydashboard) | |
10887 | ("r-singlecellexperiment" ,r-singlecellexperiment) | |
10888 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
10889 | ("r-tximport" ,r-tximport) | |
10890 | ("r-viridis" ,r-viridis))) | |
10891 | (home-page "https://github.com/davismcc/scater") | |
10892 | (synopsis "Single-cell analysis toolkit for gene expression data in R") | |
10893 | (description "This package provides a collection of tools for doing | |
10894 | various analyses of single-cell RNA-seq gene expression data, with a focus on | |
10895 | quality control.") | |
10896 | (license license:gpl2+))) | |
10897 | ||
7f1d9bef RW |
10898 | (define-public r-scran |
10899 | (package | |
10900 | (name "r-scran") | |
aeca5f0c | 10901 | (version "1.6.9") |
7f1d9bef RW |
10902 | (source |
10903 | (origin | |
10904 | (method url-fetch) | |
10905 | (uri (bioconductor-uri "scran" version)) | |
10906 | (sha256 | |
10907 | (base32 | |
aeca5f0c | 10908 | "0cs64cnf0xjcgmawr210y99j3gxs6aqgh8081n9827kkqnx2y5dm")))) |
7f1d9bef RW |
10909 | (build-system r-build-system) |
10910 | (propagated-inputs | |
10911 | `(("r-beachmat" ,r-beachmat) | |
10912 | ("r-biocgenerics" ,r-biocgenerics) | |
10913 | ("r-biocparallel" ,r-biocparallel) | |
10914 | ("r-dt" ,r-dt) | |
10915 | ("r-dynamictreecut" ,r-dynamictreecut) | |
10916 | ("r-edger" ,r-edger) | |
10917 | ("r-fnn" ,r-fnn) | |
10918 | ("r-ggplot2" ,r-ggplot2) | |
10919 | ("r-igraph" ,r-igraph) | |
10920 | ("r-limma" ,r-limma) | |
10921 | ("r-matrix" ,r-matrix) | |
10922 | ("r-rcpp" ,r-rcpp) | |
10923 | ("r-rhdf5lib" ,r-rhdf5lib) | |
10924 | ("r-s4vectors" ,r-s4vectors) | |
10925 | ("r-scater" ,r-scater) | |
10926 | ("r-shiny" ,r-shiny) | |
10927 | ("r-singlecellexperiment" ,r-singlecellexperiment) | |
10928 | ("r-statmod" ,r-statmod) | |
10929 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
10930 | ("r-viridis" ,r-viridis) | |
10931 | ("r-zoo" ,r-zoo))) | |
10932 | (home-page "https://bioconductor.org/packages/scran") | |
10933 | (synopsis "Methods for single-cell RNA-Seq data analysis") | |
10934 | (description "This package implements a variety of low-level analyses of | |
10935 | single-cell RNA-seq data. Methods are provided for normalization of | |
10936 | cell-specific biases, assignment of cell cycle phase, and detection of highly | |
10937 | variable and significantly correlated genes.") | |
10938 | (license license:gpl3))) | |
10939 | ||
05f72960 RW |
10940 | (define-public r-delayedmatrixstats |
10941 | (package | |
10942 | (name "r-delayedmatrixstats") | |
79c6af13 | 10943 | (version "1.0.3") |
05f72960 RW |
10944 | (source |
10945 | (origin | |
10946 | (method url-fetch) | |
10947 | (uri (bioconductor-uri "DelayedMatrixStats" version)) | |
10948 | (sha256 | |
10949 | (base32 | |
79c6af13 | 10950 | "1cxjbjdq9hg9cm95rci0al7a4pk2h73ym276ahw9q4977zbg6381")))) |
05f72960 RW |
10951 | (properties |
10952 | `((upstream-name . "DelayedMatrixStats"))) | |
10953 | (build-system r-build-system) | |
10954 | (propagated-inputs | |
10955 | `(("r-delayedarray" ,r-delayedarray) | |
10956 | ("r-iranges" ,r-iranges) | |
10957 | ("r-matrix" ,r-matrix) | |
10958 | ("r-matrixstats" ,r-matrixstats) | |
10959 | ("r-s4vectors" ,r-s4vectors))) | |
10960 | (home-page "https://github.com/PeteHaitch/DelayedMatrixStats") | |
10961 | (synopsis "Functions that apply to rows and columns of DelayedMatrix objects") | |
10962 | (description | |
10963 | "This package provides a port of the @code{matrixStats} API for use with | |
10964 | @code{DelayedMatrix} objects from the @code{DelayedArray} package. It | |
10965 | contains high-performing functions operating on rows and columns of | |
10966 | @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians}, | |
10967 | @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions | |
10968 | are optimized per data type and for subsetted calculations such that both | |
10969 | memory usage and processing time is minimized.") | |
10970 | (license license:expat))) | |
10971 | ||
22a0c659 RW |
10972 | (define-public r-phangorn |
10973 | (package | |
10974 | (name "r-phangorn") | |
10975 | (version "2.4.0") | |
10976 | (source | |
10977 | (origin | |
10978 | (method url-fetch) | |
10979 | (uri (cran-uri "phangorn" version)) | |
10980 | (sha256 | |
10981 | (base32 | |
10982 | "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i")))) | |
10983 | (build-system r-build-system) | |
10984 | (propagated-inputs | |
10985 | `(("r-ape" ,r-ape) | |
10986 | ("r-fastmatch" ,r-fastmatch) | |
10987 | ("r-igraph" ,r-igraph) | |
10988 | ("r-magrittr" ,r-magrittr) | |
10989 | ("r-matrix" ,r-matrix) | |
10990 | ("r-quadprog" ,r-quadprog) | |
10991 | ("r-rcpp" ,r-rcpp))) | |
10992 | (home-page "https://github.com/KlausVigo/phangorn") | |
10993 | (synopsis "Phylogenetic analysis in R") | |
10994 | (description | |
10995 | "Phangorn is a package for phylogenetic analysis in R. It supports | |
10996 | estimation of phylogenetic trees and networks using Maximum Likelihood, | |
10997 | Maximum Parsimony, distance methods and Hadamard conjugation.") | |
10998 | (license license:gpl2+))) | |
10999 | ||
3082de04 | 11000 | (define-public r-dropbead |
84c195e5 RW |
11001 | (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247") |
11002 | (revision "2")) | |
3082de04 RW |
11003 | (package |
11004 | (name "r-dropbead") | |
11005 | (version (string-append "0-" revision "." (string-take commit 7))) | |
11006 | (source | |
11007 | (origin | |
11008 | (method git-fetch) | |
11009 | (uri (git-reference | |
11010 | (url "https://github.com/rajewsky-lab/dropbead.git") | |
11011 | (commit commit))) | |
b1d4026d | 11012 | (file-name (git-file-name name version)) |
3082de04 RW |
11013 | (sha256 |
11014 | (base32 | |
84c195e5 | 11015 | "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26")))) |
3082de04 RW |
11016 | (build-system r-build-system) |
11017 | (propagated-inputs | |
11018 | `(("r-ggplot2" ,r-ggplot2) | |
11019 | ("r-rcolorbrewer" ,r-rcolorbrewer) | |
11020 | ("r-gridextra" ,r-gridextra) | |
11021 | ("r-gplots" ,r-gplots) | |
11022 | ("r-plyr" ,r-plyr))) | |
11023 | (home-page "https://github.com/rajewsky-lab/dropbead") | |
11024 | (synopsis "Basic exploration and analysis of Drop-seq data") | |
11025 | (description "This package offers a quick and straight-forward way to | |
11026 | explore and perform basic analysis of single cell sequencing data coming from | |
11027 | droplet sequencing. It has been particularly tailored for Drop-seq.") | |
11028 | (license license:gpl3)))) | |
11029 | ||
5ded35d8 RW |
11030 | (define htslib-for-sambamba |
11031 | (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5")) | |
11032 | (package | |
11033 | (inherit htslib) | |
11034 | (name "htslib-for-sambamba") | |
11035 | (version (string-append "1.3.1-1." (string-take commit 9))) | |
11036 | (source | |
11037 | (origin | |
11038 | (method git-fetch) | |
11039 | (uri (git-reference | |
11040 | (url "https://github.com/lomereiter/htslib.git") | |
11041 | (commit commit))) | |
11042 | (file-name (string-append "htslib-" version "-checkout")) | |
11043 | (sha256 | |
11044 | (base32 | |
11045 | "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9")))) | |
11046 | (arguments | |
262ee8ea RW |
11047 | `(#:phases |
11048 | (modify-phases %standard-phases | |
11049 | (add-after 'unpack 'bootstrap | |
11050 | (lambda _ (invoke "autoreconf" "-vif")))))) | |
5ded35d8 RW |
11051 | (native-inputs |
11052 | `(("autoconf" ,autoconf) | |
11053 | ("automake" ,automake) | |
11054 | ,@(package-native-inputs htslib)))))) | |
11055 | ||
11056 | (define-public sambamba | |
11057 | (package | |
11058 | (name "sambamba") | |
482959ff | 11059 | (version "0.6.7-10-g223fa20") |
5ded35d8 RW |
11060 | (source |
11061 | (origin | |
482959ff RW |
11062 | (method git-fetch) |
11063 | (uri (git-reference | |
11064 | (url "https://github.com/lomereiter/sambamba.git") | |
11065 | (commit (string-append "v" version)))) | |
11066 | (file-name (string-append name "-" version "-checkout")) | |
5ded35d8 RW |
11067 | (sha256 |
11068 | (base32 | |
482959ff | 11069 | "1zb9hrxglxqh13ava9wwri30cvf85hjnbn8ccnr8l60a3k5avczn")))) |
5ded35d8 RW |
11070 | (build-system gnu-build-system) |
11071 | (arguments | |
482959ff RW |
11072 | `(#:tests? #f ; there is no test target |
11073 | #:parallel-build? #f ; not supported | |
5ded35d8 RW |
11074 | #:phases |
11075 | (modify-phases %standard-phases | |
11076 | (delete 'configure) | |
482959ff RW |
11077 | (add-after 'unpack 'fix-ldc-version |
11078 | (lambda _ | |
11079 | (substitute* "gen_ldc_version_info.py" | |
11080 | (("/usr/bin/env.*") (which "python"))) | |
11081 | (substitute* "Makefile" | |
11082 | (("\\$\\(shell which ldmd2\\)") (which "ldmd2"))) | |
11083 | #t)) | |
11084 | (add-after 'unpack 'place-biod-and-undead | |
5ded35d8 RW |
11085 | (lambda* (#:key inputs #:allow-other-keys) |
11086 | (copy-recursively (assoc-ref inputs "biod") "BioD") | |
482959ff | 11087 | (copy-recursively (assoc-ref inputs "undead") "undeaD") |
5ded35d8 RW |
11088 | #t)) |
11089 | (add-after 'unpack 'unbundle-prerequisites | |
11090 | (lambda _ | |
11091 | (substitute* "Makefile" | |
482959ff RW |
11092 | (("htslib/libhts.a lz4/lib/liblz4.a") |
11093 | "-L-lhts -L-llz4") | |
5ded35d8 RW |
11094 | ((" htslib-static lz4-static") "")) |
11095 | #t)) | |
11096 | (replace 'install | |
11097 | (lambda* (#:key outputs #:allow-other-keys) | |
11098 | (let* ((out (assoc-ref outputs "out")) | |
11099 | (bin (string-append out "/bin"))) | |
11100 | (mkdir-p bin) | |
11101 | (install-file "build/sambamba" bin) | |
11102 | #t)))))) | |
11103 | (native-inputs | |
11104 | `(("ldc" ,ldc) | |
11105 | ("rdmd" ,rdmd) | |
482959ff | 11106 | ("python" ,python2-minimal) |
5ded35d8 | 11107 | ("biod" |
482959ff | 11108 | ,(let ((commit "c778e4f2d8bacea7499283ce39f5577b232732c6")) |
5ded35d8 RW |
11109 | (origin |
11110 | (method git-fetch) | |
11111 | (uri (git-reference | |
11112 | (url "https://github.com/biod/BioD.git") | |
11113 | (commit commit))) | |
11114 | (file-name (string-append "biod-" | |
11115 | (string-take commit 9) | |
11116 | "-checkout")) | |
11117 | (sha256 | |
11118 | (base32 | |
482959ff RW |
11119 | "1z90562hg47i63gx042wb3ak2vqjg5z7hwgn9bp2pdxfg3nxrw37"))))) |
11120 | ("undead" | |
11121 | ,(let ((commit "92803d25c88657e945511f0976a0c79d8da46e89")) | |
11122 | (origin | |
11123 | (method git-fetch) | |
11124 | (uri (git-reference | |
11125 | (url "https://github.com/dlang/undeaD.git") | |
11126 | (commit commit))) | |
11127 | (file-name (string-append "undead-" | |
11128 | (string-take commit 9) | |
11129 | "-checkout")) | |
11130 | (sha256 | |
11131 | (base32 | |
11132 | "0vq6n81vzqvgphjw54lz2isc1j8lcxwjdbrhqz1h5gwrvw9w5138"))))))) | |
5ded35d8 RW |
11133 | (inputs |
11134 | `(("lz4" ,lz4) | |
11135 | ("htslib" ,htslib-for-sambamba))) | |
11136 | (home-page "http://lomereiter.github.io/sambamba") | |
11137 | (synopsis "Tools for working with SAM/BAM data") | |
11138 | (description "Sambamba is a high performance modern robust and | |
11139 | fast tool (and library), written in the D programming language, for | |
11140 | working with SAM and BAM files. Current parallelised functionality is | |
11141 | an important subset of samtools functionality, including view, index, | |
11142 | sort, markdup, and depth.") | |
11143 | (license license:gpl2+))) | |
b8fffd3a RW |
11144 | |
11145 | (define-public ritornello | |
11146 | (package | |
11147 | (name "ritornello") | |
11148 | (version "1.0.0") | |
11149 | (source (origin | |
11150 | (method url-fetch) | |
11151 | (uri (string-append "https://github.com/KlugerLab/" | |
11152 | "Ritornello/archive/v" | |
11153 | version ".tar.gz")) | |
11154 | (file-name (string-append name "-" version ".tar.gz")) | |
11155 | (sha256 | |
11156 | (base32 | |
11157 | "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38")))) | |
11158 | (build-system gnu-build-system) | |
11159 | (arguments | |
11160 | `(#:tests? #f ; there are no tests | |
11161 | #:phases | |
11162 | (modify-phases %standard-phases | |
11163 | (add-after 'unpack 'patch-samtools-references | |
11164 | (lambda* (#:key inputs #:allow-other-keys) | |
11165 | (substitute* '("src/SamStream.h" | |
11166 | "src/BufferedGenomeReader.h") | |
11167 | (("<sam.h>") "<samtools/sam.h>")) | |
11168 | #t)) | |
11169 | (delete 'configure) | |
11170 | (replace 'install | |
11171 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
11172 | (let* ((out (assoc-ref outputs "out")) | |
11173 | (bin (string-append out "/bin/"))) | |
11174 | (mkdir-p bin) | |
11175 | (install-file "bin/Ritornello" bin) | |
11176 | #t)))))) | |
11177 | (inputs | |
11178 | `(("samtools" ,samtools-0.1) | |
11179 | ("fftw" ,fftw) | |
11180 | ("boost" ,boost) | |
11181 | ("zlib" ,zlib))) | |
11182 | (home-page "https://github.com/KlugerLab/Ritornello") | |
11183 | (synopsis "Control-free peak caller for ChIP-seq data") | |
11184 | (description "Ritornello is a ChIP-seq peak calling algorithm based on | |
11185 | signal processing that can accurately call binding events without the need to | |
11186 | do a pair total DNA input or IgG control sample. It has been tested for use | |
11187 | with narrow binding events such as transcription factor ChIP-seq.") | |
11188 | (license license:gpl3+))) | |
44f6c889 RW |
11189 | |
11190 | (define-public trim-galore | |
11191 | (package | |
11192 | (name "trim-galore") | |
f895a7a4 | 11193 | (version "0.4.5") |
44f6c889 RW |
11194 | (source |
11195 | (origin | |
f895a7a4 RW |
11196 | (method git-fetch) |
11197 | (uri (git-reference | |
11198 | (url "https://github.com/FelixKrueger/TrimGalore.git") | |
11199 | (commit version))) | |
11200 | (file-name (string-append name "-" version "-checkout")) | |
44f6c889 RW |
11201 | (sha256 |
11202 | (base32 | |
f895a7a4 | 11203 | "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71")))) |
44f6c889 RW |
11204 | (build-system gnu-build-system) |
11205 | (arguments | |
11206 | `(#:tests? #f ; no tests | |
11207 | #:phases | |
11208 | (modify-phases %standard-phases | |
44f6c889 RW |
11209 | (delete 'configure) |
11210 | (delete 'build) | |
11211 | (add-after 'unpack 'hardcode-tool-references | |
11212 | (lambda* (#:key inputs #:allow-other-keys) | |
11213 | (substitute* "trim_galore" | |
11214 | (("\\$path_to_cutadapt = 'cutadapt'") | |
11215 | (string-append "$path_to_cutadapt = '" | |
11216 | (assoc-ref inputs "cutadapt") | |
11217 | "/bin/cutadapt'")) | |
11218 | (("\\| gzip") | |
11219 | (string-append "| " | |
11220 | (assoc-ref inputs "gzip") | |
11221 | "/bin/gzip")) | |
11222 | (("\"gunzip") | |
11223 | (string-append "\"" | |
11224 | (assoc-ref inputs "gzip") | |
11225 | "/bin/gunzip"))) | |
11226 | #t)) | |
11227 | (replace 'install | |
11228 | (lambda* (#:key outputs #:allow-other-keys) | |
11229 | (let ((bin (string-append (assoc-ref outputs "out") | |
11230 | "/bin"))) | |
11231 | (mkdir-p bin) | |
11232 | (install-file "trim_galore" bin) | |
11233 | #t)))))) | |
11234 | (inputs | |
11235 | `(("gzip" ,gzip) | |
11236 | ("perl" ,perl) | |
11237 | ("cutadapt" ,cutadapt))) | |
11238 | (native-inputs | |
11239 | `(("unzip" ,unzip))) | |
11240 | (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/") | |
11241 | (synopsis "Wrapper around Cutadapt and FastQC") | |
11242 | (description "Trim Galore! is a wrapper script to automate quality and | |
11243 | adapter trimming as well as quality control, with some added functionality to | |
11244 | remove biased methylation positions for RRBS sequence files.") | |
11245 | (license license:gpl3+))) | |
3420c905 RW |
11246 | |
11247 | (define-public gess | |
11248 | (package | |
11249 | (name "gess") | |
11250 | (version "1.0") | |
11251 | (source (origin | |
11252 | (method url-fetch) | |
11253 | (uri (string-append "http://compbio.uthscsa.edu/" | |
11254 | "GESS_Web/files/" | |
11255 | "gess-" version ".src.tar.gz")) | |
11256 | (sha256 | |
11257 | (base32 | |
11258 | "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7")))) | |
11259 | (build-system gnu-build-system) | |
11260 | (arguments | |
11261 | `(#:tests? #f ; no tests | |
11262 | #:phases | |
11263 | (modify-phases %standard-phases | |
11264 | (delete 'configure) | |
11265 | (delete 'build) | |
11266 | (replace 'install | |
11267 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
11268 | (let* ((python (assoc-ref inputs "python")) | |
11269 | (out (assoc-ref outputs "out")) | |
11270 | (bin (string-append out "/bin/")) | |
11271 | (target (string-append | |
11272 | out "/lib/python2.7/site-packages/gess/"))) | |
11273 | (mkdir-p target) | |
11274 | (copy-recursively "." target) | |
11275 | ;; Make GESS.py executable | |
11276 | (chmod (string-append target "GESS.py") #o555) | |
11277 | ;; Add Python shebang to the top and make Matplotlib | |
11278 | ;; usable. | |
11279 | (substitute* (string-append target "GESS.py") | |
11280 | (("\"\"\"Description:" line) | |
11281 | (string-append "#!" (which "python") " | |
11282 | import matplotlib | |
11283 | matplotlib.use('Agg') | |
11284 | " line))) | |
11285 | ;; Make sure GESS has all modules in its path | |
11286 | (wrap-program (string-append target "GESS.py") | |
11287 | `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH")))) | |
11288 | (mkdir-p bin) | |
11289 | (symlink (string-append target "GESS.py") | |
11290 | (string-append bin "GESS.py")) | |
11291 | #t)))))) | |
11292 | (inputs | |
11293 | `(("python" ,python-2) | |
11294 | ("python2-pysam" ,python2-pysam) | |
11295 | ("python2-scipy" ,python2-scipy) | |
11296 | ("python2-numpy" ,python2-numpy) | |
11297 | ("python2-networkx" ,python2-networkx) | |
11298 | ("python2-biopython" ,python2-biopython))) | |
11299 | (home-page "http://compbio.uthscsa.edu/GESS_Web/") | |
11300 | (synopsis "Detect exon-skipping events from raw RNA-seq data") | |
11301 | (description | |
11302 | "GESS is an implementation of a novel computational method to detect de | |
11303 | novo exon-skipping events directly from raw RNA-seq data without the prior | |
11304 | knowledge of gene annotation information. GESS stands for the graph-based | |
11305 | exon-skipping scanner detection scheme.") | |
11306 | (license license:bsd-3))) | |
282b0151 RW |
11307 | |
11308 | (define-public phylip | |
11309 | (package | |
11310 | (name "phylip") | |
11311 | (version "3.696") | |
11312 | (source | |
11313 | (origin | |
11314 | (method url-fetch) | |
11315 | (uri (string-append "http://evolution.gs.washington.edu/phylip/" | |
11316 | "download/phylip-" version ".tar.gz")) | |
11317 | (sha256 | |
11318 | (base32 | |
11319 | "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd")))) | |
11320 | (build-system gnu-build-system) | |
11321 | (arguments | |
11322 | `(#:tests? #f ; no check target | |
11323 | #:make-flags (list "-f" "Makefile.unx" "install") | |
11324 | #:parallel-build? #f ; not supported | |
11325 | #:phases | |
11326 | (modify-phases %standard-phases | |
11327 | (add-after 'unpack 'enter-dir | |
11328 | (lambda _ (chdir "src") #t)) | |
11329 | (delete 'configure) | |
11330 | (replace 'install | |
11331 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
11332 | (let ((target (string-append (assoc-ref outputs "out") | |
11333 | "/bin"))) | |
11334 | (mkdir-p target) | |
11335 | (for-each (lambda (file) | |
11336 | (install-file file target)) | |
11337 | (find-files "../exe" ".*"))) | |
11338 | #t))))) | |
11339 | (home-page "http://evolution.genetics.washington.edu/phylip/") | |
11340 | (synopsis "Tools for inferring phylogenies") | |
11341 | (description "PHYLIP (the PHYLogeny Inference Package) is a package of | |
11342 | programs for inferring phylogenies (evolutionary trees).") | |
11343 | (license license:bsd-2))) | |
aa163424 RW |
11344 | |
11345 | (define-public imp | |
11346 | (package | |
11347 | (name "imp") | |
11348 | (version "2.6.2") | |
11349 | (source | |
11350 | (origin | |
11351 | (method url-fetch) | |
11352 | (uri (string-append "https://integrativemodeling.org/" | |
11353 | version "/download/imp-" version ".tar.gz")) | |
11354 | (sha256 | |
11355 | (base32 | |
11356 | "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h")))) | |
11357 | (build-system cmake-build-system) | |
11358 | (arguments | |
11359 | `(;; FIXME: Some tests fail because they produce warnings, others fail | |
11360 | ;; because the PYTHONPATH does not include the modeller's directory. | |
677bc34d | 11361 | #:tests? #f)) |
aa163424 RW |
11362 | (inputs |
11363 | `(("boost" ,boost) | |
11364 | ("gsl" ,gsl) | |
11365 | ("swig" ,swig) | |
11366 | ("hdf5" ,hdf5) | |
11367 | ("fftw" ,fftw) | |
11368 | ("python" ,python-2))) | |
11369 | (propagated-inputs | |
11370 | `(("python2-numpy" ,python2-numpy) | |
11371 | ("python2-scipy" ,python2-scipy) | |
11372 | ("python2-pandas" ,python2-pandas) | |
11373 | ("python2-scikit-learn" ,python2-scikit-learn) | |
11374 | ("python2-networkx" ,python2-networkx))) | |
11375 | (home-page "https://integrativemodeling.org") | |
11376 | (synopsis "Integrative modeling platform") | |
11377 | (description "IMP's broad goal is to contribute to a comprehensive | |
11378 | structural characterization of biomolecules ranging in size and complexity | |
11379 | from small peptides to large macromolecular assemblies, by integrating data | |
11380 | from diverse biochemical and biophysical experiments. IMP provides a C++ and | |
11381 | Python toolbox for solving complex modeling problems, and a number of | |
11382 | applications for tackling some common problems in a user-friendly way.") | |
11383 | ;; IMP is largely available under the GNU Lesser GPL; see the file | |
11384 | ;; COPYING.LGPL for the full text of this license. Some IMP modules are | |
11385 | ;; available under the GNU GPL (see the file COPYING.GPL). | |
11386 | (license (list license:lgpl2.1+ | |
11387 | license:gpl3+)))) | |
8befd094 RW |
11388 | |
11389 | (define-public tadbit | |
11390 | (package | |
11391 | (name "tadbit") | |
11392 | (version "0.2") | |
11393 | (source (origin | |
11394 | (method url-fetch) | |
11395 | (uri (string-append "https://github.com/3DGenomes/TADbit/" | |
11396 | "archive/v" version ".tar.gz")) | |
11397 | (file-name (string-append name "-" version ".tar.gz")) | |
11398 | (sha256 | |
11399 | (base32 | |
11400 | "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f")))) | |
11401 | (build-system python-build-system) | |
11402 | (arguments | |
11403 | `(;; Tests are included and must be run after installation, but | |
11404 | ;; they are incomplete and thus cannot be run. | |
11405 | #:tests? #f | |
11406 | #:python ,python-2 | |
11407 | #:phases | |
11408 | (modify-phases %standard-phases | |
11409 | (add-after 'unpack 'fix-problems-with-setup.py | |
11410 | (lambda* (#:key outputs #:allow-other-keys) | |
11411 | ;; setup.py opens these files for writing | |
11412 | (chmod "_pytadbit/_version.py" #o664) | |
11413 | (chmod "README.rst" #o664) | |
11414 | ||
11415 | ;; Don't attempt to install the bash completions to | |
11416 | ;; the home directory. | |
11417 | (rename-file "extras/.bash_completion" | |
11418 | "extras/tadbit") | |
11419 | (substitute* "setup.py" | |
11420 | (("\\(path.expanduser\\('~'\\)") | |
11421 | (string-append "(\"" | |
11422 | (assoc-ref outputs "out") | |
11423 | "/etc/bash_completion.d\"")) | |
11424 | (("extras/\\.bash_completion") | |
11425 | "extras/tadbit")) | |
11426 | #t))))) | |
11427 | (inputs | |
11428 | ;; TODO: add Chimera for visualization | |
11429 | `(("imp" ,imp) | |
11430 | ("mcl" ,mcl) | |
11431 | ("python2-scipy" ,python2-scipy) | |
11432 | ("python2-numpy" ,python2-numpy) | |
11433 | ("python2-matplotlib" ,python2-matplotlib) | |
11434 | ("python2-pysam" ,python2-pysam))) | |
11435 | (home-page "http://3dgenomes.github.io/TADbit/") | |
11436 | (synopsis "Analyze, model, and explore 3C-based data") | |
11437 | (description | |
11438 | "TADbit is a complete Python library to deal with all steps to analyze, | |
11439 | model, and explore 3C-based data. With TADbit the user can map FASTQ files to | |
11440 | obtain raw interaction binned matrices (Hi-C like matrices), normalize and | |
a147fadd | 11441 | correct interaction matrices, identify and compare the so-called |
8befd094 RW |
11442 | @dfn{Topologically Associating Domains} (TADs), build 3D models from the |
11443 | interaction matrices, and finally, extract structural properties from the | |
11444 | models. TADbit is complemented by TADkit for visualizing 3D models.") | |
11445 | (license license:gpl3+))) | |
94820951 RW |
11446 | |
11447 | (define-public kentutils | |
11448 | (package | |
11449 | (name "kentutils") | |
11450 | ;; 302.1.0 is out, but the only difference is the inclusion of | |
11451 | ;; pre-built binaries. | |
11452 | (version "302.0.0") | |
11453 | (source | |
11454 | (origin | |
11455 | (method url-fetch) | |
11456 | (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/" | |
11457 | "archive/v" version ".tar.gz")) | |
11458 | (file-name (string-append name "-" version ".tar.gz")) | |
11459 | (sha256 | |
11460 | (base32 | |
11461 | "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm")) | |
11462 | (modules '((guix build utils) | |
11463 | (srfi srfi-26) | |
11464 | (ice-9 ftw))) | |
11465 | (snippet | |
11466 | '(begin | |
11467 | ;; Only the contents of the specified directories are free | |
11468 | ;; for all uses, so we remove the rest. "hg/autoSql" and | |
11469 | ;; "hg/autoXml" are nominally free, but they depend on a | |
11470 | ;; library that is built from the sources in "hg/lib", | |
11471 | ;; which is nonfree. | |
11472 | (let ((free (list "." ".." | |
11473 | "utils" "lib" "inc" "tagStorm" | |
11474 | "parasol" "htslib")) | |
11475 | (directory? (lambda (file) | |
11476 | (eq? 'directory (stat:type (stat file)))))) | |
11477 | (for-each (lambda (file) | |
11478 | (and (directory? file) | |
11479 | (delete-file-recursively file))) | |
11480 | (map (cut string-append "src/" <>) | |
11481 | (scandir "src" | |
11482 | (lambda (file) | |
11483 | (not (member file free))))))) | |
11484 | ;; Only make the utils target, not the userApps target, | |
11485 | ;; because that requires libraries we won't build. | |
11486 | (substitute* "Makefile" | |
11487 | ((" userApps") " utils")) | |
11488 | ;; Only build libraries that are free. | |
11489 | (substitute* "src/makefile" | |
11490 | (("DIRS =.*") "DIRS =\n") | |
11491 | (("cd jkOwnLib.*") "") | |
11492 | ((" hgLib") "") | |
11493 | (("cd hg.*") "")) | |
11494 | (substitute* "src/utils/makefile" | |
11495 | ;; These tools depend on "jkhgap.a", which is part of the | |
11496 | ;; nonfree "src/hg/lib" directory. | |
11497 | (("raSqlQuery") "") | |
11498 | (("pslLiftSubrangeBlat") "") | |
11499 | ||
11500 | ;; Do not build UCSC tools, which may require nonfree | |
11501 | ;; components. | |
11502 | (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n")) | |
11503 | #t)))) | |
11504 | (build-system gnu-build-system) | |
11505 | (arguments | |
11506 | `( ;; There is no global test target and the test target for | |
11507 | ;; individual tools depends on input files that are not | |
11508 | ;; included. | |
11509 | #:tests? #f | |
11510 | #:phases | |
11511 | (modify-phases %standard-phases | |
11512 | (add-after 'unpack 'fix-paths | |
11513 | (lambda _ | |
11514 | (substitute* "Makefile" | |
11515 | (("/bin/echo") (which "echo"))) | |
11516 | #t)) | |
11517 | (add-after 'unpack 'prepare-samtabix | |
11518 | (lambda* (#:key inputs #:allow-other-keys) | |
11519 | (copy-recursively (assoc-ref inputs "samtabix") | |
11520 | "samtabix") | |
11521 | #t)) | |
11522 | (delete 'configure) | |
11523 | (replace 'install | |
11524 | (lambda* (#:key outputs #:allow-other-keys) | |
11525 | (let ((bin (string-append (assoc-ref outputs "out") | |
11526 | "/bin"))) | |
11527 | (copy-recursively "bin" bin)) | |
11528 | #t))))) | |
11529 | (native-inputs | |
11530 | `(("samtabix" | |
11531 | ,(origin | |
11532 | (method git-fetch) | |
11533 | (uri (git-reference | |
11534 | (url "http://genome-source.cse.ucsc.edu/samtabix.git") | |
11535 | (commit "10fd107909c1ac4d679299908be4262a012965ba"))) | |
11536 | (sha256 | |
11537 | (base32 | |
11538 | "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma")))))) | |
11539 | (inputs | |
11540 | `(("zlib" ,zlib) | |
11541 | ("tcsh" ,tcsh) | |
11542 | ("perl" ,perl) | |
11543 | ("libpng" ,libpng) | |
b44437c5 | 11544 | ("mariadb" ,mariadb) |
94820951 RW |
11545 | ("openssl" ,openssl))) |
11546 | (home-page "http://genome.cse.ucsc.edu/index.html") | |
11547 | (synopsis "Assorted bioinformatics utilities") | |
11548 | (description "This package provides the kentUtils, a selection of | |
11549 | bioinformatics utilities used in combination with the UCSC genome | |
11550 | browser.") | |
11551 | ;; Only a subset of the sources are released under a non-copyleft | |
11552 | ;; free software license. All other sources are removed in a | |
11553 | ;; snippet. See this bug report for an explanation of how the | |
11554 | ;; license statements apply: | |
11555 | ;; https://github.com/ENCODE-DCC/kentUtils/issues/12 | |
11556 | (license (license:non-copyleft | |
11557 | "http://genome.ucsc.edu/license/" | |
11558 | "The contents of this package are free for all uses.")))) | |
7ceb0a83 RW |
11559 | |
11560 | (define-public f-seq | |
11561 | (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b") | |
11562 | (revision "1")) | |
11563 | (package | |
11564 | (name "f-seq") | |
c6643f2d | 11565 | (version (string-append "1.1-" revision "." (string-take commit 7))) |
7ceb0a83 RW |
11566 | (source (origin |
11567 | (method git-fetch) | |
11568 | (uri (git-reference | |
11569 | (url "https://github.com/aboyle/F-seq.git") | |
11570 | (commit commit))) | |
11571 | (file-name (string-append name "-" version)) | |
11572 | (sha256 | |
11573 | (base32 | |
11574 | "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h")) | |
11575 | (modules '((guix build utils))) | |
11576 | ;; Remove bundled Java library archives. | |
11577 | (snippet | |
11578 | '(begin | |
11579 | (for-each delete-file (find-files "lib" ".*")) | |
11580 | #t)))) | |
11581 | (build-system ant-build-system) | |
11582 | (arguments | |
11583 | `(#:tests? #f ; no tests included | |
11584 | #:phases | |
11585 | (modify-phases %standard-phases | |
11586 | (replace 'install | |
c0770fee | 11587 | (lambda* (#:key inputs outputs #:allow-other-keys) |
7ceb0a83 | 11588 | (let* ((target (assoc-ref outputs "out")) |
c61d8226 TGR |
11589 | (bin (string-append target "/bin")) |
11590 | (doc (string-append target "/share/doc/f-seq")) | |
11591 | (lib (string-append target "/lib"))) | |
7ceb0a83 RW |
11592 | (mkdir-p target) |
11593 | (mkdir-p doc) | |
11594 | (substitute* "bin/linux/fseq" | |
c0770fee RW |
11595 | (("java") (which "java")) |
11596 | (("\\$REALDIR/../lib/commons-cli-1.1.jar") | |
11597 | (string-append (assoc-ref inputs "java-commons-cli") | |
11598 | "/share/java/commons-cli.jar")) | |
11599 | (("REALDIR=.*") | |
c61d8226 | 11600 | (string-append "REALDIR=" bin "\n"))) |
7ceb0a83 | 11601 | (install-file "README.txt" doc) |
c61d8226 TGR |
11602 | (install-file "bin/linux/fseq" bin) |
11603 | (install-file "build~/fseq.jar" lib) | |
11604 | (copy-recursively "lib" lib) | |
7ceb0a83 RW |
11605 | #t)))))) |
11606 | (inputs | |
11607 | `(("perl" ,perl) | |
11608 | ("java-commons-cli" ,java-commons-cli))) | |
11609 | (home-page "http://fureylab.web.unc.edu/software/fseq/") | |
11610 | (synopsis "Feature density estimator for high-throughput sequence tags") | |
11611 | (description | |
11612 | "F-Seq is a software package that generates a continuous tag sequence | |
11613 | density estimation allowing identification of biologically meaningful sites | |
11614 | such as transcription factor binding sites (ChIP-seq) or regions of open | |
11615 | chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome | |
11616 | Browser.") | |
11617 | (license license:gpl3+)))) | |
96348048 RW |
11618 | |
11619 | (define-public bismark | |
11620 | (package | |
11621 | (name "bismark") | |
126c9e3f | 11622 | (version "0.19.1") |
96348048 RW |
11623 | (source |
11624 | (origin | |
126c9e3f RW |
11625 | (method git-fetch) |
11626 | (uri (git-reference | |
11627 | (url "https://github.com/FelixKrueger/Bismark.git") | |
11628 | (commit version))) | |
11629 | (file-name (string-append name "-" version "-checkout")) | |
96348048 RW |
11630 | (sha256 |
11631 | (base32 | |
126c9e3f RW |
11632 | "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84")) |
11633 | (snippet | |
11634 | '(begin | |
11635 | ;; highcharts.js is non-free software. The code is available under | |
11636 | ;; CC-BY-NC or proprietary licenses only. | |
11637 | (delete-file "bismark_sitrep/highcharts.js") | |
11638 | #t)))) | |
96348048 RW |
11639 | (build-system perl-build-system) |
11640 | (arguments | |
126c9e3f | 11641 | `(#:tests? #f ; there are no tests |
96348048 RW |
11642 | #:phases |
11643 | (modify-phases %standard-phases | |
11644 | (delete 'configure) | |
11645 | (delete 'build) | |
11646 | (replace 'install | |
09658903 | 11647 | (lambda* (#:key inputs outputs #:allow-other-keys) |
126c9e3f RW |
11648 | (let* ((out (assoc-ref outputs "out")) |
11649 | (bin (string-append out "/bin")) | |
11650 | (share (string-append out "/share/bismark")) | |
11651 | (docdir (string-append out "/share/doc/bismark")) | |
11652 | (docs '("Docs/Bismark_User_Guide.html")) | |
11653 | (scripts '("bismark" | |
11654 | "bismark_genome_preparation" | |
11655 | "bismark_methylation_extractor" | |
11656 | "bismark2bedGraph" | |
11657 | "bismark2report" | |
11658 | "coverage2cytosine" | |
11659 | "deduplicate_bismark" | |
11660 | "filter_non_conversion" | |
11661 | "bam2nuc" | |
11662 | "bismark2summary"))) | |
0f5ad3a1 RW |
11663 | (substitute* "bismark2report" |
11664 | (("\\$RealBin/bismark_sitrep") | |
11665 | (string-append share "/bismark_sitrep"))) | |
126c9e3f | 11666 | (mkdir-p share) |
96348048 RW |
11667 | (mkdir-p docdir) |
11668 | (mkdir-p bin) | |
11669 | (for-each (lambda (file) (install-file file bin)) | |
11670 | scripts) | |
11671 | (for-each (lambda (file) (install-file file docdir)) | |
11672 | docs) | |
126c9e3f | 11673 | (copy-recursively "Docs/Images" (string-append docdir "/Images")) |
126c9e3f RW |
11674 | (copy-recursively "bismark_sitrep" |
11675 | (string-append share "/bismark_sitrep")) | |
11676 | ||
09658903 RW |
11677 | ;; Fix references to gunzip |
11678 | (substitute* (map (lambda (file) | |
11679 | (string-append bin "/" file)) | |
11680 | scripts) | |
11681 | (("\"gunzip -c") | |
11682 | (string-append "\"" (assoc-ref inputs "gzip") | |
11683 | "/bin/gunzip -c"))) | |
96348048 | 11684 | #t)))))) |
09658903 RW |
11685 | (inputs |
11686 | `(("gzip" ,gzip))) | |
96348048 RW |
11687 | (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/") |
11688 | (synopsis "Map bisulfite treated sequence reads and analyze methylation") | |
11689 | (description "Bismark is a program to map bisulfite treated sequencing | |
11690 | reads to a genome of interest and perform methylation calls in a single step. | |
11691 | The output can be easily imported into a genome viewer, such as SeqMonk, and | |
11692 | enables a researcher to analyse the methylation levels of their samples | |
11693 | straight away. Its main features are: | |
11694 | ||
11695 | @itemize | |
11696 | @item Bisulfite mapping and methylation calling in one single step | |
11697 | @item Supports single-end and paired-end read alignments | |
11698 | @item Supports ungapped and gapped alignments | |
11699 | @item Alignment seed length, number of mismatches etc are adjustable | |
11700 | @item Output discriminates between cytosine methylation in CpG, CHG | |
11701 | and CHH context | |
11702 | @end itemize\n") | |
11703 | (license license:gpl3+))) | |
dc8ddbfb RW |
11704 | |
11705 | (define-public paml | |
11706 | (package | |
11707 | (name "paml") | |
11708 | (version "4.9e") | |
11709 | (source (origin | |
11710 | (method url-fetch) | |
11711 | (uri (string-append "http://abacus.gene.ucl.ac.uk/software/" | |
11712 | "paml" version ".tgz")) | |
11713 | (sha256 | |
11714 | (base32 | |
11715 | "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6")) | |
11716 | (modules '((guix build utils))) | |
11717 | ;; Remove Windows binaries | |
11718 | (snippet | |
11719 | '(begin | |
11720 | (for-each delete-file (find-files "." "\\.exe$")) | |
11721 | #t)))) | |
11722 | (build-system gnu-build-system) | |
11723 | (arguments | |
11724 | `(#:tests? #f ; there are no tests | |
11725 | #:make-flags '("CC=gcc") | |
11726 | #:phases | |
11727 | (modify-phases %standard-phases | |
11728 | (replace 'configure | |
11729 | (lambda _ | |
11730 | (substitute* "src/BFdriver.c" | |
11731 | (("/bin/bash") (which "bash"))) | |
11732 | (chdir "src") | |
11733 | #t)) | |
11734 | (replace 'install | |
11735 | (lambda* (#:key outputs #:allow-other-keys) | |
11736 | (let ((tools '("baseml" "basemlg" "codeml" | |
11737 | "pamp" "evolver" "yn00" "chi2")) | |
11738 | (bin (string-append (assoc-ref outputs "out") "/bin")) | |
11739 | (docdir (string-append (assoc-ref outputs "out") | |
11740 | "/share/doc/paml"))) | |
11741 | (mkdir-p bin) | |
11742 | (for-each (lambda (file) (install-file file bin)) tools) | |
11743 | (copy-recursively "../doc" docdir) | |
11744 | #t)))))) | |
11745 | (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html") | |
11746 | (synopsis "Phylogentic analysis by maximum likelihood") | |
11747 | (description "PAML (for Phylogentic Analysis by Maximum Likelihood) | |
11748 | contains a few programs for model fitting and phylogenetic tree reconstruction | |
11749 | using nucleotide or amino-acid sequence data.") | |
11750 | ;; GPLv3 only | |
11751 | (license license:gpl3))) | |
d112e5a8 RW |
11752 | |
11753 | (define-public kallisto | |
11754 | (package | |
11755 | (name "kallisto") | |
11756 | (version "0.43.1") | |
11757 | (source (origin | |
11758 | (method url-fetch) | |
11759 | (uri (string-append "https://github.com/pachterlab/" | |
11760 | "kallisto/archive/v" version ".tar.gz")) | |
11761 | (file-name (string-append name "-" version ".tar.gz")) | |
11762 | (sha256 | |
11763 | (base32 | |
11764 | "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11")))) | |
11765 | (build-system cmake-build-system) | |
11766 | (arguments `(#:tests? #f)) ; no "check" target | |
11767 | (inputs | |
11768 | `(("hdf5" ,hdf5) | |
11769 | ("zlib" ,zlib))) | |
11770 | (home-page "http://pachterlab.github.io/kallisto/") | |
11771 | (synopsis "Near-optimal RNA-Seq quantification") | |
11772 | (description | |
11773 | "Kallisto is a program for quantifying abundances of transcripts from | |
11774 | RNA-Seq data, or more generally of target sequences using high-throughput | |
11775 | sequencing reads. It is based on the novel idea of pseudoalignment for | |
11776 | rapidly determining the compatibility of reads with targets, without the need | |
11777 | for alignment. Pseudoalignment of reads preserves the key information needed | |
11778 | for quantification, and kallisto is therefore not only fast, but also as | |
11779 | accurate as existing quantification tools.") | |
11780 | (license license:bsd-2))) | |
c3b2ab9d RW |
11781 | |
11782 | (define-public libgff | |
11783 | (package | |
11784 | (name "libgff") | |
11785 | (version "1.0") | |
11786 | (source (origin | |
11787 | (method url-fetch) | |
11788 | (uri (string-append | |
11789 | "https://github.com/Kingsford-Group/" | |
11790 | "libgff/archive/v" version ".tar.gz")) | |
11791 | (file-name (string-append name "-" version ".tar.gz")) | |
11792 | (sha256 | |
11793 | (base32 | |
11794 | "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls")))) | |
11795 | (build-system cmake-build-system) | |
11796 | (arguments `(#:tests? #f)) ; no tests included | |
11797 | (home-page "https://github.com/Kingsford-Group/libgff") | |
11798 | (synopsis "Parser library for reading/writing GFF files") | |
11799 | (description "This is a simple \"libraryfication\" of the GFF/GTF parsing | |
11800 | code that is used in the Cufflinks codebase. The goal of this library is to | |
11801 | provide this functionality without the necessity of drawing in a heavy-weight | |
11802 | dependency like SeqAn.") | |
a2cfe190 | 11803 | (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt")))) |
1fe0bde3 RW |
11804 | |
11805 | (define-public libdivsufsort | |
11806 | (package | |
11807 | (name "libdivsufsort") | |
11808 | (version "2.0.1") | |
11809 | (source (origin | |
11810 | (method git-fetch) | |
11811 | (uri (git-reference | |
11812 | (url "https://github.com/y-256/libdivsufsort.git") | |
11813 | (commit version))) | |
d9a069c2 | 11814 | (file-name (git-file-name name version)) |
1fe0bde3 RW |
11815 | (sha256 |
11816 | (base32 | |
11817 | "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2")))) | |
11818 | (build-system cmake-build-system) | |
11819 | (arguments | |
11820 | '(#:tests? #f ; there are no tests | |
11821 | #:configure-flags | |
11822 | ;; Needed for rapmap and sailfish. | |
11823 | '("-DBUILD_DIVSUFSORT64=ON"))) | |
11824 | (home-page "https://github.com/y-256/libdivsufsort") | |
11825 | (synopsis "Lightweight suffix-sorting library") | |
11826 | (description "libdivsufsort is a software library that implements a | |
11827 | lightweight suffix array construction algorithm. This library provides a | |
11828 | simple and an efficient C API to construct a suffix array and a | |
11829 | Burrows-Wheeler transformed string from a given string over a constant-size | |
11830 | alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1) | |
11831 | bytes of memory space, where n is the length of the string.") | |
11832 | (license license:expat))) | |
8d77a085 RW |
11833 | |
11834 | (define-public sailfish | |
11835 | (package | |
11836 | (name "sailfish") | |
11837 | (version "0.10.1") | |
11838 | (source (origin | |
11839 | (method url-fetch) | |
11840 | (uri | |
11841 | (string-append "https://github.com/kingsfordgroup/" | |
11842 | "sailfish/archive/v" version ".tar.gz")) | |
11843 | (file-name (string-append name "-" version ".tar.gz")) | |
11844 | (sha256 | |
11845 | (base32 | |
11846 | "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0")) | |
11847 | (modules '((guix build utils))) | |
11848 | (snippet | |
11849 | '(begin | |
11850 | ;; Delete bundled headers for eigen3. | |
11851 | (delete-file-recursively "include/eigen3/") | |
11852 | #t)))) | |
11853 | (build-system cmake-build-system) | |
11854 | (arguments | |
11855 | `(#:configure-flags | |
11856 | (list (string-append "-DBOOST_INCLUDEDIR=" | |
11857 | (assoc-ref %build-inputs "boost") | |
11858 | "/include/") | |
11859 | (string-append "-DBOOST_LIBRARYDIR=" | |
11860 | (assoc-ref %build-inputs "boost") | |
11861 | "/lib/") | |
11862 | (string-append "-DBoost_LIBRARIES=" | |
11863 | "-lboost_iostreams " | |
11864 | "-lboost_filesystem " | |
11865 | "-lboost_system " | |
11866 | "-lboost_thread " | |
11867 | "-lboost_timer " | |
11868 | "-lboost_chrono " | |
11869 | "-lboost_program_options") | |
11870 | "-DBoost_FOUND=TRUE" | |
11871 | ;; Don't download RapMap---we already have it! | |
11872 | "-DFETCHED_RAPMAP=1") | |
11873 | ;; Tests must be run after installation and the location of the test | |
11874 | ;; data file must be overridden. But the tests fail. It looks like | |
11875 | ;; they are not really meant to be run. | |
11876 | #:tests? #f | |
11877 | #:phases | |
11878 | (modify-phases %standard-phases | |
11879 | ;; Boost cannot be found, even though it's right there. | |
11880 | (add-after 'unpack 'do-not-look-for-boost | |
11881 | (lambda* (#:key inputs #:allow-other-keys) | |
11882 | (substitute* "CMakeLists.txt" | |
11883 | (("find_package\\(Boost 1\\.53\\.0") "#")))) | |
11884 | (add-after 'unpack 'do-not-assign-to-macro | |
11885 | (lambda _ | |
11886 | (substitute* "include/spdlog/details/format.cc" | |
11887 | (("const unsigned CHAR_WIDTH = 1;") "")))) | |
11888 | (add-after 'unpack 'prepare-rapmap | |
11889 | (lambda* (#:key inputs #:allow-other-keys) | |
11890 | (let ((src "external/install/src/rapmap/") | |
11891 | (include "external/install/include/rapmap/") | |
11892 | (rapmap (assoc-ref inputs "rapmap"))) | |
11893 | (mkdir-p "/tmp/rapmap") | |
11894 | (system* "tar" "xf" | |
11895 | (assoc-ref inputs "rapmap") | |
11896 | "-C" "/tmp/rapmap" | |
11897 | "--strip-components=1") | |
11898 | (mkdir-p src) | |
11899 | (mkdir-p include) | |
11900 | (for-each (lambda (file) | |
11901 | (install-file file src)) | |
11902 | (find-files "/tmp/rapmap/src" "\\.(c|cpp)")) | |
11903 | (copy-recursively "/tmp/rapmap/include" include)))) | |
11904 | (add-after 'unpack 'use-system-libraries | |
11905 | (lambda* (#:key inputs #:allow-other-keys) | |
11906 | (substitute* '("src/SailfishIndexer.cpp" | |
11907 | "src/SailfishUtils.cpp" | |
11908 | "src/SailfishQuantify.cpp" | |
11909 | "src/FASTAParser.cpp" | |
11910 | "include/PCA.hpp" | |
11911 | "include/SailfishUtils.hpp" | |
11912 | "include/SailfishIndex.hpp" | |
11913 | "include/CollapsedEMOptimizer.hpp" | |
11914 | "src/CollapsedEMOptimizer.cpp") | |
11915 | (("#include \"jellyfish/config.h\"") "")) | |
11916 | (substitute* "src/CMakeLists.txt" | |
11917 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..") | |
11918 | (string-append (assoc-ref inputs "jellyfish") | |
11919 | "/include/jellyfish-" ,(package-version jellyfish))) | |
11920 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a") | |
11921 | (string-append (assoc-ref inputs "jellyfish") | |
11922 | "/lib/libjellyfish-2.0.a")) | |
11923 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a") | |
11924 | (string-append (assoc-ref inputs "libdivsufsort") | |
11925 | "/lib/libdivsufsort.so")) | |
11926 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a") | |
11927 | (string-append (assoc-ref inputs "libdivsufsort") | |
11928 | "/lib/libdivsufsort64.so"))) | |
11929 | (substitute* "CMakeLists.txt" | |
11930 | ;; Don't prefer static libs | |
11931 | (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "") | |
11932 | (("find_package\\(Jellyfish.*") "") | |
11933 | (("ExternalProject_Add\\(libjellyfish") "message(") | |
11934 | (("ExternalProject_Add\\(libgff") "message(") | |
11935 | (("ExternalProject_Add\\(libsparsehash") "message(") | |
11936 | (("ExternalProject_Add\\(libdivsufsort") "message(")) | |
11937 | ||
11938 | ;; Ensure that Eigen headers can be found | |
11939 | (setenv "CPLUS_INCLUDE_PATH" | |
11940 | (string-append (getenv "CPLUS_INCLUDE_PATH") | |
11941 | ":" | |
11942 | (assoc-ref inputs "eigen") | |
11943 | "/include/eigen3"))))))) | |
11944 | (inputs | |
11945 | `(("boost" ,boost) | |
11946 | ("eigen" ,eigen) | |
11947 | ("jemalloc" ,jemalloc) | |
11948 | ("jellyfish" ,jellyfish) | |
11949 | ("sparsehash" ,sparsehash) | |
11950 | ("rapmap" ,(origin | |
11951 | (method git-fetch) | |
11952 | (uri (git-reference | |
11953 | (url "https://github.com/COMBINE-lab/RapMap.git") | |
11954 | (commit (string-append "sf-v" version)))) | |
11955 | (file-name (string-append "rapmap-sf-v" version "-checkout")) | |
11956 | (sha256 | |
11957 | (base32 | |
11958 | "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf")) | |
11959 | (modules '((guix build utils))) | |
11960 | ;; These files are expected to be excluded. | |
11961 | (snippet | |
11962 | '(begin (delete-file-recursively "include/spdlog") | |
11963 | (for-each delete-file '("include/xxhash.h" | |
11964 | "src/xxhash.c")))))) | |
11965 | ("libdivsufsort" ,libdivsufsort) | |
11966 | ("libgff" ,libgff) | |
11967 | ("tbb" ,tbb) | |
11968 | ("zlib" ,zlib))) | |
11969 | (native-inputs | |
11970 | `(("pkg-config" ,pkg-config))) | |
11971 | (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish") | |
11972 | (synopsis "Mapping-based isoform quantification from RNA-Seq reads") | |
11973 | (description "Sailfish is a tool for genomic transcript quantification | |
11974 | from RNA-seq data. It requires a set of target transcripts (either from a | |
11975 | reference or de-novo assembly) to quantify. All you need to run sailfish is a | |
11976 | fasta file containing your reference transcripts and a (set of) fasta/fastq | |
11977 | file(s) containing your reads.") | |
11978 | (license license:gpl3+))) | |
7762646d RW |
11979 | |
11980 | (define libstadenio-for-salmon | |
11981 | (package | |
11982 | (name "libstadenio") | |
11983 | (version "1.14.8") | |
11984 | (source (origin | |
11985 | (method git-fetch) | |
11986 | (uri (git-reference | |
11987 | (url "https://github.com/COMBINE-lab/staden-io_lib.git") | |
11988 | (commit (string-append "v" version)))) | |
11989 | (file-name (string-append name "-" version "-checkout")) | |
11990 | (sha256 | |
11991 | (base32 | |
11992 | "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx")))) | |
11993 | (build-system gnu-build-system) | |
11994 | (arguments '(#:parallel-tests? #f)) ; not supported | |
11995 | (inputs | |
11996 | `(("zlib" ,zlib))) | |
11997 | (native-inputs | |
11998 | `(("perl" ,perl))) ; for tests | |
11999 | (home-page "https://github.com/COMBINE-lab/staden-io_lib") | |
12000 | (synopsis "General purpose trace and experiment file library") | |
12001 | (description "This package provides a library of file reading and writing | |
12002 | code to provide a general purpose Trace file (and Experiment File) reading | |
12003 | interface. | |
12004 | ||
12005 | The following file formats are supported: | |
12006 | ||
12007 | @enumerate | |
12008 | @item SCF trace files | |
12009 | @item ABI trace files | |
12010 | @item ALF trace files | |
12011 | @item ZTR trace files | |
12012 | @item SFF trace archives | |
12013 | @item SRF trace archives | |
12014 | @item Experiment files | |
12015 | @item Plain text files | |
12016 | @item SAM/BAM sequence files | |
12017 | @item CRAM sequence files | |
12018 | @end enumerate\n") | |
12019 | (license license:bsd-3))) | |
12020 | ||
12021 | (define spdlog-for-salmon | |
12022 | (package | |
12023 | (name "spdlog") | |
12024 | (version "0.14.0") | |
12025 | (source (origin | |
12026 | (method git-fetch) | |
12027 | (uri (git-reference | |
12028 | (url "https://github.com/COMBINE-lab/spdlog.git") | |
12029 | (commit (string-append "v" version)))) | |
12030 | (file-name (string-append name "-" version "-checkout")) | |
12031 | (sha256 | |
12032 | (base32 | |
12033 | "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q")))) | |
12034 | (build-system cmake-build-system) | |
12035 | (home-page "https://github.com/COMBINE-lab/spdlog") | |
12036 | (synopsis "Very fast C++ logging library") | |
12037 | (description "Spdlog is a very fast header-only C++ logging library with | |
12038 | performance as its primary goal.") | |
12039 | (license license:expat))) | |
12040 | ||
12041 | ;; This is a modified variant of bwa for use with Salmon. It installs a | |
12042 | ;; library to avoid having to build this as part of Salmon. | |
12043 | (define bwa-for-salmon | |
12044 | (package (inherit bwa) | |
12045 | (name "bwa") | |
12046 | (version "0.7.12.5") | |
12047 | (source (origin | |
12048 | (method git-fetch) | |
12049 | (uri (git-reference | |
12050 | (url "https://github.com/COMBINE-lab/bwa.git") | |
12051 | (commit (string-append "v" version)))) | |
12052 | (file-name (string-append "bwa-for-salmon-" version "-checkout")) | |
12053 | (sha256 | |
12054 | (base32 | |
12055 | "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb")))) | |
12056 | (build-system gnu-build-system) | |
12057 | (arguments | |
12058 | '(#:tests? #f ;no "check" target | |
12059 | #:phases | |
12060 | (modify-phases %standard-phases | |
12061 | (replace 'install | |
12062 | (lambda* (#:key outputs #:allow-other-keys) | |
12063 | (let* ((out (assoc-ref outputs "out")) | |
12064 | (bin (string-append out "/bin")) | |
12065 | (lib (string-append out "/lib")) | |
12066 | (doc (string-append out "/share/doc/bwa")) | |
12067 | (man (string-append out "/share/man/man1")) | |
12068 | (inc (string-append out "/include/bwa"))) | |
12069 | (install-file "bwa" bin) | |
12070 | (install-file "README.md" doc) | |
12071 | (install-file "bwa.1" man) | |
12072 | (install-file "libbwa.a" lib) | |
12073 | (mkdir-p lib) | |
12074 | (mkdir-p inc) | |
12075 | (for-each (lambda (file) | |
12076 | (install-file file inc)) | |
12077 | (find-files "." "\\.h$"))) | |
12078 | #t)) | |
12079 | ;; no "configure" script | |
12080 | (delete 'configure)))))) | |
12081 | ||
12082 | (define-public salmon | |
12083 | (package | |
12084 | (name "salmon") | |
12085 | (version "0.9.1") | |
12086 | (source (origin | |
12087 | (method git-fetch) | |
12088 | (uri (git-reference | |
12089 | (url "https://github.com/COMBINE-lab/salmon.git") | |
12090 | (commit (string-append "v" version)))) | |
12091 | (file-name (string-append name "-" version "-checkout")) | |
12092 | (sha256 | |
12093 | (base32 | |
12094 | "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a")) | |
12095 | (modules '((guix build utils))) | |
12096 | (snippet | |
12097 | '(begin | |
12098 | ;; Delete bundled headers for eigen3. | |
12099 | (delete-file-recursively "include/eigen3/") | |
12100 | #t)))) | |
12101 | (build-system cmake-build-system) | |
12102 | (arguments | |
12103 | `(#:configure-flags | |
12104 | (list (string-append "-DBOOST_INCLUDEDIR=" | |
12105 | (assoc-ref %build-inputs "boost") | |
12106 | "/include/") | |
12107 | (string-append "-DBOOST_LIBRARYDIR=" | |
12108 | (assoc-ref %build-inputs "boost") | |
12109 | "/lib/") | |
12110 | (string-append "-DBoost_LIBRARIES=" | |
12111 | "-lboost_iostreams " | |
12112 | "-lboost_filesystem " | |
12113 | "-lboost_system " | |
12114 | "-lboost_thread " | |
12115 | "-lboost_timer " | |
12116 | "-lboost_chrono " | |
12117 | "-lboost_program_options") | |
12118 | "-DBoost_FOUND=TRUE" | |
12119 | "-DTBB_LIBRARIES=tbb tbbmalloc" | |
12120 | ;; Don't download RapMap---we already have it! | |
12121 | "-DFETCHED_RAPMAP=1") | |
12122 | #:phases | |
12123 | (modify-phases %standard-phases | |
12124 | ;; Boost cannot be found, even though it's right there. | |
12125 | (add-after 'unpack 'do-not-look-for-boost | |
12126 | (lambda* (#:key inputs #:allow-other-keys) | |
12127 | (substitute* "CMakeLists.txt" | |
12128 | (("find_package\\(Boost 1\\.53\\.0") "#")))) | |
12129 | (add-after 'unpack 'do-not-phone-home | |
12130 | (lambda _ | |
12131 | (substitute* "src/Salmon.cpp" | |
12132 | (("getVersionMessage\\(\\)") "\"\"")))) | |
12133 | (add-after 'unpack 'prepare-rapmap | |
12134 | (lambda* (#:key inputs #:allow-other-keys) | |
12135 | (let ((src "external/install/src/rapmap/") | |
12136 | (include "external/install/include/rapmap/") | |
12137 | (rapmap (assoc-ref inputs "rapmap"))) | |
12138 | (mkdir-p src) | |
12139 | (mkdir-p include) | |
12140 | (for-each (lambda (file) | |
12141 | (install-file file src)) | |
12142 | (find-files (string-append rapmap "/src") "\\.(c|cpp)")) | |
12143 | (copy-recursively (string-append rapmap "/include") include) | |
12144 | (for-each delete-file '("external/install/include/rapmap/xxhash.h" | |
12145 | "external/install/include/rapmap/FastxParser.hpp" | |
12146 | "external/install/include/rapmap/concurrentqueue.h" | |
12147 | "external/install/include/rapmap/FastxParserThreadUtils.hpp" | |
12148 | "external/install/src/rapmap/FastxParser.cpp" | |
12149 | "external/install/src/rapmap/xxhash.c"))))) | |
12150 | (add-after 'unpack 'use-system-libraries | |
12151 | (lambda* (#:key inputs #:allow-other-keys) | |
12152 | (substitute* "src/CMakeLists.txt" | |
12153 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..") | |
12154 | (string-append (assoc-ref inputs "jellyfish") | |
12155 | "/include/jellyfish-" ,(package-version jellyfish))) | |
12156 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a") | |
12157 | (string-append (assoc-ref inputs "jellyfish") | |
12158 | "/lib/libjellyfish-2.0.a")) | |
12159 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a") | |
12160 | (string-append (assoc-ref inputs "libdivsufsort") | |
12161 | "/lib/libdivsufsort.so")) | |
12162 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a") | |
12163 | (string-append (assoc-ref inputs "libstadenio-for-salmon") | |
12164 | "/lib/libstaden-read.a")) | |
12165 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a") | |
12166 | (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a")) | |
12167 | (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a") | |
12168 | (string-append (assoc-ref inputs "libdivsufsort") | |
12169 | "/lib/libdivsufsort64.so"))) | |
12170 | (substitute* "CMakeLists.txt" | |
12171 | ;; Don't prefer static libs | |
12172 | (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "") | |
12173 | (("set\\(TBB_LIBRARIES") "message(") | |
12174 | (("find_package\\(Jellyfish.*") "") | |
12175 | (("ExternalProject_Add\\(libcereal") "message(") | |
12176 | (("ExternalProject_Add\\(libbwa") "message(") | |
12177 | (("ExternalProject_Add\\(libjellyfish") "message(") | |
12178 | (("ExternalProject_Add\\(libgff") "message(") | |
12179 | (("ExternalProject_Add\\(libtbb") "message(") | |
12180 | (("ExternalProject_Add\\(libspdlog") "message(") | |
12181 | (("ExternalProject_Add\\(libdivsufsort") "message(") | |
12182 | (("ExternalProject_Add\\(libstadenio") "message(") | |
12183 | (("ExternalProject_Add_Step\\(") "message(")) | |
12184 | ||
12185 | ;; Ensure that all headers can be found | |
12186 | (setenv "CPLUS_INCLUDE_PATH" | |
12187 | (string-append (getenv "CPLUS_INCLUDE_PATH") | |
12188 | ":" | |
12189 | (assoc-ref inputs "bwa") | |
12190 | "/include/bwa" | |
12191 | ":" | |
12192 | (assoc-ref inputs "eigen") | |
12193 | "/include/eigen3")) | |
12194 | (setenv "CPATH" | |
12195 | (string-append (assoc-ref inputs "bwa") | |
12196 | "/include/bwa" | |
12197 | ":" | |
12198 | (assoc-ref inputs "eigen") | |
12199 | "/include/eigen3")) | |
12200 | #t)) | |
12201 | ;; CMAKE_INSTALL_PREFIX does not exist when the tests are | |
12202 | ;; run. It only exists after the install phase. | |
12203 | (add-after 'unpack 'fix-tests | |
12204 | (lambda _ | |
12205 | (substitute* "src/CMakeLists.txt" | |
12206 | (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX") | |
12207 | "DTOPLEVEL_DIR=${GAT_SOURCE_DIR")) | |
12208 | #t))))) | |
12209 | (inputs | |
12210 | `(("boost" ,boost) | |
12211 | ("bwa" ,bwa-for-salmon) | |
12212 | ("bzip2" ,bzip2) | |
12213 | ("cereal" ,cereal) | |
12214 | ("eigen" ,eigen) | |
12215 | ("rapmap" ,(origin | |
12216 | (method git-fetch) | |
12217 | (uri (git-reference | |
12218 | (url "https://github.com/COMBINE-lab/RapMap.git") | |
12219 | (commit (string-append "salmon-v" version)))) | |
12220 | (file-name (string-append "rapmap-salmon-v" version "-checkout")) | |
12221 | (sha256 | |
12222 | (base32 | |
12223 | "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p")))) | |
12224 | ("jemalloc" ,jemalloc) | |
12225 | ("jellyfish" ,jellyfish) | |
12226 | ("libgff" ,libgff) | |
12227 | ("tbb" ,tbb) | |
12228 | ("libdivsufsort" ,libdivsufsort) | |
12229 | ("libstadenio-for-salmon" ,libstadenio-for-salmon) | |
12230 | ("spdlog-for-salmon" ,spdlog-for-salmon) | |
12231 | ("xz" ,xz) | |
12232 | ("zlib" ,zlib))) | |
12233 | (home-page "https://github.com/COMBINE-lab/salmon") | |
12234 | (synopsis "Quantification from RNA-seq reads using lightweight alignments") | |
12235 | (description "Salmon is a program to produce highly-accurate, | |
12236 | transcript-level quantification estimates from RNA-seq data. Salmon achieves | |
12237 | its accuracy and speed via a number of different innovations, including the | |
12238 | use of lightweight alignments (accurate but fast-to-compute proxies for | |
12239 | traditional read alignments) and massively-parallel stochastic collapsed | |
12240 | variational inference.") | |
12241 | (license license:gpl3+))) | |
152d30c3 RW |
12242 | |
12243 | (define-public python-loompy | |
12244 | (package | |
12245 | (name "python-loompy") | |
12246 | (version "2.0.2") | |
12247 | (source | |
12248 | (origin | |
12249 | (method url-fetch) | |
12250 | (uri (pypi-uri "loompy" version)) | |
12251 | (sha256 | |
12252 | (base32 | |
12253 | "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51")))) | |
12254 | (build-system python-build-system) | |
12255 | ;; There are no tests | |
12256 | (arguments '(#:tests? #f)) | |
12257 | (propagated-inputs | |
12258 | `(("python-h5py" ,python-h5py) | |
12259 | ("python-numpy" ,python-numpy) | |
12260 | ("python-scipy" ,python-scipy) | |
12261 | ("python-typing" ,python-typing))) | |
12262 | (home-page "https://github.com/linnarsson-lab/loompy") | |
12263 | (synopsis "Work with .loom files for single-cell RNA-seq data") | |
12264 | (description "The loom file format is an efficient format for very large | |
12265 | omics datasets, consisting of a main matrix, optional additional layers, a | |
12266 | variable number of row and column annotations. Loom also supports sparse | |
12267 | graphs. This library makes it easy to work with @file{.loom} files for | |
12268 | single-cell RNA-seq data.") | |
12269 | (license license:bsd-3))) | |
5fef15e5 | 12270 | |
f09d16e5 RW |
12271 | ;; We cannot use the latest commit because it requires Java 9. |
12272 | (define-public java-forester | |
12273 | (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6") | |
12274 | (revision "1")) | |
12275 | (package | |
12276 | (name "java-forester") | |
12277 | (version (string-append "0-" revision "." (string-take commit 7))) | |
12278 | (source (origin | |
12279 | (method git-fetch) | |
12280 | (uri (git-reference | |
12281 | (url "https://github.com/cmzmasek/forester.git") | |
12282 | (commit commit))) | |
12283 | (file-name (string-append name "-" version "-checkout")) | |
12284 | (sha256 | |
12285 | (base32 | |
12286 | "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z")) | |
12287 | (modules '((guix build utils))) | |
12288 | (snippet | |
12289 | '(begin | |
12290 | ;; Delete bundled jars and pre-built classes | |
12291 | (delete-file-recursively "forester/java/resources") | |
12292 | (delete-file-recursively "forester/java/classes") | |
12293 | (for-each delete-file (find-files "forester/java/" "\\.jar$")) | |
12294 | ;; Delete bundled applications | |
12295 | (delete-file-recursively "forester_applications") | |
12296 | #t)))) | |
12297 | (build-system ant-build-system) | |
12298 | (arguments | |
12299 | `(#:tests? #f ; there are none | |
12300 | #:jdk ,icedtea-8 | |
12301 | #:modules ((guix build ant-build-system) | |
12302 | (guix build utils) | |
12303 | (guix build java-utils) | |
12304 | (sxml simple) | |
12305 | (sxml transform)) | |
12306 | #:phases | |
12307 | (modify-phases %standard-phases | |
12308 | (add-after 'unpack 'chdir | |
12309 | (lambda _ (chdir "forester/java") #t)) | |
12310 | (add-after 'chdir 'fix-dependencies | |
12311 | (lambda _ | |
12312 | (chmod "build.xml" #o664) | |
12313 | (call-with-output-file "build.xml.new" | |
12314 | (lambda (port) | |
12315 | (sxml->xml | |
12316 | (pre-post-order | |
12317 | (with-input-from-file "build.xml" | |
12318 | (lambda _ (xml->sxml #:trim-whitespace? #t))) | |
12319 | `(;; Remove all unjar tags to avoid repacking classes. | |
12320 | (unjar . ,(lambda _ '())) | |
12321 | (*default* . ,(lambda (tag . kids) `(,tag ,@kids))) | |
12322 | (*text* . ,(lambda (_ txt) txt)))) | |
12323 | port))) | |
12324 | (rename-file "build.xml.new" "build.xml") | |
12325 | #t)) | |
12326 | ;; FIXME: itext is difficult to package as it depends on a few | |
12327 | ;; unpackaged libraries. | |
12328 | (add-after 'chdir 'remove-dependency-on-unpackaged-itext | |
12329 | (lambda _ | |
12330 | (delete-file "src/org/forester/archaeopteryx/PdfExporter.java") | |
12331 | (substitute* "src/org/forester/archaeopteryx/MainFrame.java" | |
12332 | (("pdf_written_to = PdfExporter.*") | |
12333 | "throw new IOException(\"PDF export is not available.\");")) | |
12334 | #t)) | |
12335 | ;; There is no install target | |
12336 | (replace 'install (install-jars "."))))) | |
12337 | (propagated-inputs | |
12338 | `(("java-commons-codec" ,java-commons-codec) | |
12339 | ("java-openchart2" ,java-openchart2))) | |
12340 | (home-page "https://sites.google.com/site/cmzmasek/home/software/forester") | |
12341 | (synopsis "Phylogenomics libraries for Java") | |
12342 | (description "Forester is a collection of Java libraries for | |
12343 | phylogenomics and evolutionary biology research. It includes support for | |
12344 | reading, writing, and exporting phylogenetic trees.") | |
12345 | (license license:lgpl2.1+)))) | |
12346 | ||
10645b92 RW |
12347 | (define-public java-forester-1.005 |
12348 | (package | |
12349 | (name "java-forester") | |
12350 | (version "1.005") | |
12351 | (source (origin | |
12352 | (method url-fetch) | |
12353 | (uri (string-append "http://search.maven.org/remotecontent?" | |
12354 | "filepath=org/biojava/thirdparty/forester/" | |
12355 | version "/forester-" version "-sources.jar")) | |
12356 | (file-name (string-append name "-" version ".jar")) | |
12357 | (sha256 | |
12358 | (base32 | |
12359 | "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv")))) | |
12360 | (build-system ant-build-system) | |
12361 | (arguments | |
12362 | `(#:tests? #f ; there are none | |
12363 | #:jdk ,icedtea-8 | |
12364 | #:modules ((guix build ant-build-system) | |
12365 | (guix build utils) | |
12366 | (guix build java-utils) | |
12367 | (sxml simple) | |
12368 | (sxml transform)) | |
12369 | #:phases | |
12370 | (modify-phases %standard-phases | |
12371 | (add-after 'unpack 'fix-dependencies | |
12372 | (lambda* (#:key inputs #:allow-other-keys) | |
12373 | (call-with-output-file "build.xml" | |
12374 | (lambda (port) | |
12375 | (sxml->xml | |
12376 | (pre-post-order | |
12377 | (with-input-from-file "src/build.xml" | |
12378 | (lambda _ (xml->sxml #:trim-whitespace? #t))) | |
12379 | `(;; Remove all unjar tags to avoid repacking classes. | |
12380 | (unjar . ,(lambda _ '())) | |
12381 | (*default* . ,(lambda (tag . kids) `(,tag ,@kids))) | |
12382 | (*text* . ,(lambda (_ txt) txt)))) | |
12383 | port))) | |
12384 | (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml") | |
12385 | "synth_look_and_feel_1.xml") | |
12386 | (copy-file (assoc-ref inputs "phyloxml.xsd") | |
12387 | "phyloxml.xsd") | |
12388 | (substitute* "build.xml" | |
12389 | (("../resources/synth_laf/synth_look_and_feel_1.xml") | |
12390 | "synth_look_and_feel_1.xml") | |
12391 | (("../resources/phyloxml_schema/1.10/phyloxml.xsd") | |
12392 | "phyloxml.xsd")) | |
12393 | #t)) | |
12394 | ;; FIXME: itext is difficult to package as it depends on a few | |
12395 | ;; unpackaged libraries. | |
12396 | (add-after 'unpack 'remove-dependency-on-unpackaged-itext | |
12397 | (lambda _ | |
12398 | (delete-file "src/org/forester/archaeopteryx/PdfExporter.java") | |
12399 | (substitute* '("src/org/forester/archaeopteryx/MainFrame.java" | |
12400 | "src/org/forester/archaeopteryx/MainFrameApplication.java") | |
12401 | (("pdf_written_to = PdfExporter.*") | |
12402 | "throw new IOException(\"PDF export is not available.\"); /*") | |
12403 | ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/") | |
12404 | (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/")) | |
12405 | #t)) | |
12406 | (add-after 'unpack 'delete-pre-built-classes | |
12407 | (lambda _ (delete-file-recursively "src/classes") #t)) | |
12408 | ;; There is no install target | |
12409 | (replace 'install (install-jars "."))))) | |
12410 | (propagated-inputs | |
12411 | `(("java-commons-codec" ,java-commons-codec) | |
12412 | ("java-openchart2" ,java-openchart2))) | |
12413 | ;; The source archive does not contain the resources. | |
12414 | (native-inputs | |
12415 | `(("phyloxml.xsd" | |
12416 | ,(origin | |
12417 | (method url-fetch) | |
12418 | (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/" | |
12419 | "b61cc2dcede0bede317db362472333115756b8c6/" | |
12420 | "forester/resources/phyloxml_schema/1.10/phyloxml.xsd")) | |
12421 | (file-name (string-append name "-phyloxml-" version ".xsd")) | |
12422 | (sha256 | |
12423 | (base32 | |
12424 | "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv")))) | |
12425 | ("synth_look_and_feel_1.xml" | |
12426 | ,(origin | |
12427 | (method url-fetch) | |
12428 | (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/" | |
12429 | "29e04321615da6b35c1e15c60e52caf3f21d8e6a/" | |
12430 | "forester/java/classes/resources/synth_look_and_feel_1.xml")) | |
12431 | (file-name (string-append name "-synth-look-and-feel-" version ".xml")) | |
12432 | (sha256 | |
12433 | (base32 | |
12434 | "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h")))))) | |
12435 | (home-page "https://sites.google.com/site/cmzmasek/home/software/forester") | |
12436 | (synopsis "Phylogenomics libraries for Java") | |
12437 | (description "Forester is a collection of Java libraries for | |
12438 | phylogenomics and evolutionary biology research. It includes support for | |
12439 | reading, writing, and exporting phylogenetic trees.") | |
12440 | (license license:lgpl2.1+))) | |
12441 | ||
5fef15e5 RW |
12442 | (define-public java-biojava-core |
12443 | (package | |
12444 | (name "java-biojava-core") | |
12445 | (version "4.2.11") | |
12446 | (source (origin | |
12447 | (method git-fetch) | |
12448 | (uri (git-reference | |
12449 | (url "https://github.com/biojava/biojava") | |
12450 | (commit (string-append "biojava-" version)))) | |
12451 | (file-name (string-append name "-" version "-checkout")) | |
12452 | (sha256 | |
12453 | (base32 | |
12454 | "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk")))) | |
12455 | (build-system ant-build-system) | |
12456 | (arguments | |
12457 | `(#:jdk ,icedtea-8 | |
12458 | #:jar-name "biojava-core.jar" | |
12459 | #:source-dir "biojava-core/src/main/java/" | |
12460 | #:test-dir "biojava-core/src/test" | |
12461 | ;; These tests seem to require internet access. | |
12462 | #:test-exclude (list "**/SearchIOTest.java" | |
12463 | "**/BlastXMLParserTest.java" | |
12464 | "**/GenbankCookbookTest.java" | |
12465 | "**/GenbankProxySequenceReaderTest.java") | |
12466 | #:phases | |
12467 | (modify-phases %standard-phases | |
12468 | (add-before 'build 'copy-resources | |
12469 | (lambda _ | |
12470 | (copy-recursively "biojava-core/src/main/resources" | |
12471 | "build/classes") | |
12472 | #t)) | |
12473 | (add-before 'check 'copy-test-resources | |
12474 | (lambda _ | |
12475 | (copy-recursively "biojava-core/src/test/resources" | |
12476 | "build/test-classes") | |
12477 | #t))))) | |
12478 | (propagated-inputs | |
12479 | `(("java-log4j-api" ,java-log4j-api) | |
12480 | ("java-log4j-core" ,java-log4j-core) | |
12481 | ("java-slf4j-api" ,java-slf4j-api) | |
12482 | ("java-slf4j-simple" ,java-slf4j-simple))) | |
12483 | (native-inputs | |
12484 | `(("java-junit" ,java-junit) | |
12485 | ("java-hamcrest-core" ,java-hamcrest-core))) | |
12486 | (home-page "http://biojava.org") | |
12487 | (synopsis "Core libraries of Java framework for processing biological data") | |
12488 | (description "BioJava is a project dedicated to providing a Java framework | |
12489 | for processing biological data. It provides analytical and statistical | |
12490 | routines, parsers for common file formats, reference implementations of | |
12491 | popular algorithms, and allows the manipulation of sequences and 3D | |
12492 | structures. The goal of the biojava project is to facilitate rapid | |
12493 | application development for bioinformatics. | |
12494 | ||
12495 | This package provides the core libraries.") | |
12496 | (license license:lgpl2.1+))) | |
b28c8037 RW |
12497 | |
12498 | (define-public java-biojava-phylo | |
12499 | (package (inherit java-biojava-core) | |
12500 | (name "java-biojava-phylo") | |
12501 | (build-system ant-build-system) | |
12502 | (arguments | |
12503 | `(#:jdk ,icedtea-8 | |
12504 | #:jar-name "biojava-phylo.jar" | |
12505 | #:source-dir "biojava-phylo/src/main/java/" | |
12506 | #:test-dir "biojava-phylo/src/test" | |
12507 | #:phases | |
12508 | (modify-phases %standard-phases | |
12509 | (add-before 'build 'copy-resources | |
12510 | (lambda _ | |
12511 | (copy-recursively "biojava-phylo/src/main/resources" | |
12512 | "build/classes") | |
12513 | #t)) | |
12514 | (add-before 'check 'copy-test-resources | |
12515 | (lambda _ | |
12516 | (copy-recursively "biojava-phylo/src/test/resources" | |
12517 | "build/test-classes") | |
12518 | #t))))) | |
12519 | (propagated-inputs | |
12520 | `(("java-log4j-api" ,java-log4j-api) | |
12521 | ("java-log4j-core" ,java-log4j-core) | |
12522 | ("java-slf4j-api" ,java-slf4j-api) | |
12523 | ("java-slf4j-simple" ,java-slf4j-simple) | |
12524 | ("java-biojava-core" ,java-biojava-core) | |
12525 | ("java-forester" ,java-forester))) | |
12526 | (native-inputs | |
12527 | `(("java-junit" ,java-junit) | |
12528 | ("java-hamcrest-core" ,java-hamcrest-core))) | |
12529 | (home-page "http://biojava.org") | |
12530 | (synopsis "Biojava interface to the forester phylogenomics library") | |
12531 | (description "The phylo module provides a biojava interface layer to the | |
12532 | forester phylogenomics library for constructing phylogenetic trees."))) | |
22c09c33 RW |
12533 | |
12534 | (define-public java-biojava-alignment | |
12535 | (package (inherit java-biojava-core) | |
12536 | (name "java-biojava-alignment") | |
12537 | (build-system ant-build-system) | |
12538 | (arguments | |
12539 | `(#:jdk ,icedtea-8 | |
12540 | #:jar-name "biojava-alignment.jar" | |
12541 | #:source-dir "biojava-alignment/src/main/java/" | |
12542 | #:test-dir "biojava-alignment/src/test" | |
12543 | #:phases | |
12544 | (modify-phases %standard-phases | |
12545 | (add-before 'build 'copy-resources | |
12546 | (lambda _ | |
12547 | (copy-recursively "biojava-alignment/src/main/resources" | |
12548 | "build/classes") | |
12549 | #t)) | |
12550 | (add-before 'check 'copy-test-resources | |
12551 | (lambda _ | |
12552 | (copy-recursively "biojava-alignment/src/test/resources" | |
12553 | "build/test-classes") | |
12554 | #t))))) | |
12555 | (propagated-inputs | |
12556 | `(("java-log4j-api" ,java-log4j-api) | |
12557 | ("java-log4j-core" ,java-log4j-core) | |
12558 | ("java-slf4j-api" ,java-slf4j-api) | |
12559 | ("java-slf4j-simple" ,java-slf4j-simple) | |
12560 | ("java-biojava-core" ,java-biojava-core) | |
12561 | ("java-biojava-phylo" ,java-biojava-phylo) | |
12562 | ("java-forester" ,java-forester))) | |
12563 | (native-inputs | |
12564 | `(("java-junit" ,java-junit) | |
12565 | ("java-hamcrest-core" ,java-hamcrest-core))) | |
12566 | (home-page "http://biojava.org") | |
12567 | (synopsis "Biojava API for genetic sequence alignment") | |
12568 | (description "The alignment module of BioJava provides an API that | |
12569 | contains | |
12570 | ||
12571 | @itemize | |
12572 | @item implementations of dynamic programming algorithms for sequence | |
12573 | alignment; | |
12574 | @item reading and writing of popular alignment file formats; | |
12575 | @item a single-, or multi- threaded multiple sequence alignment algorithm. | |
12576 | @end itemize\n"))) | |
e44da58c RW |
12577 | |
12578 | (define-public java-biojava-core-4.0 | |
12579 | (package (inherit java-biojava-core) | |
12580 | (name "java-biojava-core") | |
12581 | (version "4.0.0") | |
12582 | (source (origin | |
12583 | (method git-fetch) | |
12584 | (uri (git-reference | |
12585 | (url "https://github.com/biojava/biojava") | |
12586 | (commit (string-append "biojava-" version)))) | |
12587 | (file-name (string-append name "-" version "-checkout")) | |
12588 | (sha256 | |
12589 | (base32 | |
12590 | "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8")))))) | |
5528f9e8 RW |
12591 | |
12592 | (define-public java-biojava-phylo-4.0 | |
12593 | (package (inherit java-biojava-core-4.0) | |
12594 | (name "java-biojava-phylo") | |
12595 | (build-system ant-build-system) | |
12596 | (arguments | |
12597 | `(#:jdk ,icedtea-8 | |
12598 | #:jar-name "biojava-phylo.jar" | |
12599 | #:source-dir "biojava-phylo/src/main/java/" | |
12600 | #:test-dir "biojava-phylo/src/test" | |
12601 | #:phases | |
12602 | (modify-phases %standard-phases | |
12603 | (add-before 'build 'copy-resources | |
12604 | (lambda _ | |
12605 | (copy-recursively "biojava-phylo/src/main/resources" | |
12606 | "build/classes") | |
12607 | #t)) | |
12608 | (add-before 'check 'copy-test-resources | |
12609 | (lambda _ | |
12610 | (copy-recursively "biojava-phylo/src/test/resources" | |
12611 | "build/test-classes") | |
12612 | #t))))) | |
12613 | (propagated-inputs | |
12614 | `(("java-log4j-api" ,java-log4j-api) | |
12615 | ("java-log4j-core" ,java-log4j-core) | |
12616 | ("java-slf4j-api" ,java-slf4j-api) | |
12617 | ("java-slf4j-simple" ,java-slf4j-simple) | |
12618 | ("java-biojava-core" ,java-biojava-core-4.0) | |
12619 | ("java-forester" ,java-forester-1.005))) | |
12620 | (native-inputs | |
12621 | `(("java-junit" ,java-junit) | |
12622 | ("java-hamcrest-core" ,java-hamcrest-core))) | |
12623 | (home-page "http://biojava.org") | |
12624 | (synopsis "Biojava interface to the forester phylogenomics library") | |
12625 | (description "The phylo module provides a biojava interface layer to the | |
12626 | forester phylogenomics library for constructing phylogenetic trees."))) | |
9ac7db18 RW |
12627 | |
12628 | (define-public java-biojava-alignment-4.0 | |
12629 | (package (inherit java-biojava-core-4.0) | |
12630 | (name "java-biojava-alignment") | |
12631 | (build-system ant-build-system) | |
12632 | (arguments | |
12633 | `(#:jdk ,icedtea-8 | |
12634 | #:jar-name "biojava-alignment.jar" | |
12635 | #:source-dir "biojava-alignment/src/main/java/" | |
12636 | #:test-dir "biojava-alignment/src/test" | |
12637 | #:phases | |
12638 | (modify-phases %standard-phases | |
12639 | (add-before 'build 'copy-resources | |
12640 | (lambda _ | |
12641 | (copy-recursively "biojava-alignment/src/main/resources" | |
12642 | "build/classes") | |
12643 | #t)) | |
12644 | (add-before 'check 'copy-test-resources | |
12645 | (lambda _ | |
12646 | (copy-recursively "biojava-alignment/src/test/resources" | |
12647 | "build/test-classes") | |
12648 | #t))))) | |
12649 | (propagated-inputs | |
12650 | `(("java-log4j-api" ,java-log4j-api) | |
12651 | ("java-log4j-core" ,java-log4j-core) | |
12652 | ("java-slf4j-api" ,java-slf4j-api) | |
12653 | ("java-slf4j-simple" ,java-slf4j-simple) | |
12654 | ("java-biojava-core" ,java-biojava-core-4.0) | |
12655 | ("java-biojava-phylo" ,java-biojava-phylo-4.0) | |
12656 | ("java-forester" ,java-forester-1.005))) | |
12657 | (native-inputs | |
12658 | `(("java-junit" ,java-junit) | |
12659 | ("java-hamcrest-core" ,java-hamcrest-core))) | |
12660 | (home-page "http://biojava.org") | |
12661 | (synopsis "Biojava API for genetic sequence alignment") | |
12662 | (description "The alignment module of BioJava provides an API that | |
12663 | contains | |
12664 | ||
12665 | @itemize | |
12666 | @item implementations of dynamic programming algorithms for sequence | |
12667 | alignment; | |
12668 | @item reading and writing of popular alignment file formats; | |
12669 | @item a single-, or multi- threaded multiple sequence alignment algorithm. | |
12670 | @end itemize\n"))) | |
1adeef31 RW |
12671 | |
12672 | (define-public dropseq-tools | |
12673 | (package | |
12674 | (name "dropseq-tools") | |
12675 | (version "1.13") | |
12676 | (source | |
12677 | (origin | |
12678 | (method url-fetch) | |
12679 | (uri "http://mccarrolllab.com/download/1276/") | |
12680 | (file-name (string-append "dropseq-tools-" version ".zip")) | |
12681 | (sha256 | |
12682 | (base32 | |
12683 | "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s")) | |
12684 | ;; Delete bundled libraries | |
12685 | (modules '((guix build utils))) | |
12686 | (snippet | |
12687 | '(begin | |
12688 | (for-each delete-file (find-files "jar/lib" "\\.jar$")) | |
12689 | (delete-file-recursively "3rdParty"))))) | |
12690 | (build-system ant-build-system) | |
12691 | (arguments | |
12692 | `(#:tests? #f ; test data are not included | |
12693 | #:test-target "test" | |
12694 | #:build-target "all" | |
12695 | #:source-dir "public/src/" | |
12696 | #:jdk ,icedtea-8 | |
12697 | #:make-flags | |
12698 | (list (string-append "-Dpicard.executable.dir=" | |
12699 | (assoc-ref %build-inputs "java-picard") | |
12700 | "/share/java/")) | |
12701 | #:modules ((ice-9 match) | |
12702 | (srfi srfi-1) | |
12703 | (guix build utils) | |
12704 | (guix build java-utils) | |
12705 | (guix build ant-build-system)) | |
12706 | #:phases | |
12707 | (modify-phases %standard-phases | |
12708 | ;; All dependencies must be linked to "lib", because that's where | |
12709 | ;; they will be searched for when the Class-Path property of the | |
12710 | ;; manifest is computed. | |
12711 | (add-after 'unpack 'record-references | |
12712 | (lambda* (#:key inputs #:allow-other-keys) | |
12713 | (mkdir-p "jar/lib") | |
12714 | (let ((dirs (filter-map (match-lambda | |
12715 | ((name . dir) | |
12716 | (if (and (string-prefix? "java-" name) | |
12717 | (not (string=? name "java-testng"))) | |
12718 | dir #f))) | |
12719 | inputs))) | |
12720 | (for-each (lambda (jar) | |
12721 | (symlink jar (string-append "jar/lib/" (basename jar)))) | |
12722 | (append-map (lambda (dir) (find-files dir "\\.jar$")) | |
12723 | dirs))) | |
12724 | #t)) | |
12725 | ;; There is no installation target | |
12726 | (replace 'install | |
12727 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
12728 | (let* ((out (assoc-ref outputs "out")) | |
12729 | (bin (string-append out "/bin")) | |
12730 | (share (string-append out "/share/java/")) | |
12731 | (lib (string-append share "/lib/")) | |
12732 | (scripts (list "BAMTagHistogram" | |
12733 | "BAMTagofTagCounts" | |
12734 | "BaseDistributionAtReadPosition" | |
12735 | "CollapseBarcodesInPlace" | |
12736 | "CollapseTagWithContext" | |
12737 | "ConvertToRefFlat" | |
12738 | "CreateIntervalsFiles" | |
12739 | "DetectBeadSynthesisErrors" | |
12740 | "DigitalExpression" | |
12741 | "Drop-seq_alignment.sh" | |
12742 | "FilterBAM" | |
12743 | "FilterBAMByTag" | |
12744 | "GatherGeneGCLength" | |
12745 | "GatherMolecularBarcodeDistributionByGene" | |
12746 | "GatherReadQualityMetrics" | |
12747 | "PolyATrimmer" | |
12748 | "ReduceGTF" | |
12749 | "SelectCellsByNumTranscripts" | |
12750 | "SingleCellRnaSeqMetricsCollector" | |
12751 | "TagBamWithReadSequenceExtended" | |
12752 | "TagReadWithGeneExon" | |
12753 | "TagReadWithInterval" | |
12754 | "TrimStartingSequence" | |
12755 | "ValidateReference"))) | |
12756 | (for-each mkdir-p (list bin share lib)) | |
12757 | (install-file "dist/dropseq.jar" share) | |
12758 | (for-each (lambda (script) | |
12759 | (chmod script #o555) | |
12760 | (install-file script bin)) | |
12761 | scripts) | |
12762 | (substitute* (map (lambda (script) | |
12763 | (string-append bin "/" script)) | |
12764 | scripts) | |
12765 | (("^java") (which "java")) | |
12766 | (("jar_deploy_dir=.*") | |
12767 | (string-append "jar_deploy_dir=" share "\n")))) | |
12768 | #t)) | |
12769 | ;; FIXME: We do this after stripping jars because we don't want it to | |
12770 | ;; copy all these jars and strip them. We only want to install | |
12771 | ;; links. Arguably, this is a problem with the ant-build-system. | |
12772 | (add-after 'strip-jar-timestamps 'install-links | |
12773 | (lambda* (#:key outputs #:allow-other-keys) | |
12774 | (let* ((out (assoc-ref outputs "out")) | |
12775 | (share (string-append out "/share/java/")) | |
12776 | (lib (string-append share "/lib/"))) | |
12777 | (for-each (lambda (jar) | |
12778 | (symlink (readlink jar) | |
12779 | (string-append lib (basename jar)))) | |
12780 | (find-files "jar/lib" "\\.jar$"))) | |
12781 | #t))))) | |
12782 | (inputs | |
12783 | `(("jdk" ,icedtea-8) | |
12784 | ("java-picard" ,java-picard-2.10.3) | |
12785 | ("java-log4j-1.2-api" ,java-log4j-1.2-api) | |
12786 | ("java-commons-math3" ,java-commons-math3) | |
12787 | ("java-commons-jexl2" ,java-commons-jexl-2) | |
12788 | ("java-commons-collections4" ,java-commons-collections4) | |
12789 | ("java-commons-lang2" ,java-commons-lang) | |
12790 | ("java-commons-io" ,java-commons-io) | |
12791 | ("java-snappy-1.0.3-rc3" ,java-snappy-1) | |
12792 | ("java-guava" ,java-guava) | |
12793 | ("java-la4j" ,java-la4j) | |
12794 | ("java-biojava-core" ,java-biojava-core-4.0) | |
12795 | ("java-biojava-alignment" ,java-biojava-alignment-4.0) | |
12796 | ("java-jdistlib" ,java-jdistlib) | |
12797 | ("java-simple-xml" ,java-simple-xml) | |
12798 | ("java-snakeyaml" ,java-snakeyaml))) | |
12799 | (native-inputs | |
12800 | `(("unzip" ,unzip) | |
12801 | ("java-testng" ,java-testng))) | |
12802 | (home-page "http://mccarrolllab.com/dropseq/") | |
12803 | (synopsis "Tools for Drop-seq analyses") | |
12804 | (description "Drop-seq is a technology to enable biologists to | |
12805 | analyze RNA expression genome-wide in thousands of individual cells at | |
12806 | once. This package provides tools to perform Drop-seq analyses.") | |
12807 | (license license:expat))) | |
0bdd5b8a RW |
12808 | |
12809 | (define-public pigx-rnaseq | |
12810 | (package | |
12811 | (name "pigx-rnaseq") | |
616446ff | 12812 | (version "0.0.3") |
0bdd5b8a RW |
12813 | (source (origin |
12814 | (method url-fetch) | |
12815 | (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/" | |
12816 | "releases/download/v" version | |
12817 | "/pigx_rnaseq-" version ".tar.gz")) | |
12818 | (sha256 | |
12819 | (base32 | |
616446ff | 12820 | "0pz080k4ajlc4rlznkn3najy2a6874gb56rf9g4ag9wqz31q174j")))) |
0bdd5b8a RW |
12821 | (build-system gnu-build-system) |
12822 | (arguments | |
12823 | `(#:parallel-tests? #f ; not supported | |
12824 | #:phases | |
12825 | (modify-phases %standard-phases | |
fe52a215 RW |
12826 | ;; "test.sh" runs STAR, which requires excessive amounts of memory. |
12827 | (add-after 'unpack 'disable-resource-intensive-test | |
12828 | (lambda _ | |
12829 | (substitute* "Makefile.in" | |
12830 | (("(^ tests/test_trim_galore/test.sh).*" _ m) m) | |
12831 | (("^ test.sh") "")) | |
12832 | #t)) | |
0bdd5b8a RW |
12833 | (add-after 'install 'wrap-executable |
12834 | ;; Make sure the executable finds all R modules. | |
12835 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
12836 | (let ((out (assoc-ref outputs "out"))) | |
12837 | (wrap-program (string-append out "/bin/pigx-rnaseq") | |
12838 | `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE"))) | |
12839 | `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH"))))) | |
12840 | #t))))) | |
12841 | (inputs | |
616446ff RW |
12842 | `(("gzip" ,gzip) |
12843 | ("snakemake" ,snakemake) | |
0bdd5b8a RW |
12844 | ("fastqc" ,fastqc) |
12845 | ("multiqc" ,multiqc) | |
12846 | ("star" ,star) | |
12847 | ("trim-galore" ,trim-galore) | |
12848 | ("htseq" ,htseq) | |
12849 | ("samtools" ,samtools) | |
12850 | ("bedtools" ,bedtools) | |
12851 | ("r-minimal" ,r-minimal) | |
12852 | ("r-rmarkdown" ,r-rmarkdown) | |
12853 | ("r-ggplot2" ,r-ggplot2) | |
12854 | ("r-ggrepel" ,r-ggrepel) | |
12855 | ("r-gprofiler" ,r-gprofiler) | |
12856 | ("r-deseq2" ,r-deseq2) | |
12857 | ("r-dt" ,r-dt) | |
12858 | ("r-knitr" ,r-knitr) | |
12859 | ("r-pheatmap" ,r-pheatmap) | |
12860 | ("r-corrplot" ,r-corrplot) | |
12861 | ("r-reshape2" ,r-reshape2) | |
12862 | ("r-plotly" ,r-plotly) | |
12863 | ("r-scales" ,r-scales) | |
12864 | ("r-summarizedexperiment" ,r-summarizedexperiment) | |
12865 | ("r-crosstalk" ,r-crosstalk) | |
12866 | ("r-tximport" ,r-tximport) | |
12867 | ("r-rtracklayer" ,r-rtracklayer) | |
12868 | ("r-rjson" ,r-rjson) | |
12869 | ("salmon" ,salmon) | |
1a29fc3f RW |
12870 | ("ghc-pandoc" ,ghc-pandoc-1) |
12871 | ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1) | |
0bdd5b8a RW |
12872 | ("python-wrapper" ,python-wrapper) |
12873 | ("python-pyyaml" ,python-pyyaml))) | |
12874 | (home-page "http://bioinformatics.mdc-berlin.de/pigx/") | |
12875 | (synopsis "Analysis pipeline for RNA sequencing experiments") | |
12876 | (description "PiGX RNAseq is an analysis pipeline for preprocessing and | |
12877 | reporting for RNA sequencing experiments. It is easy to use and produces high | |
12878 | quality reports. The inputs are reads files from the sequencing experiment, | |
12879 | and a configuration file which describes the experiment. In addition to | |
12880 | quality control of the experiment, the pipeline produces a differential | |
12881 | expression report comparing samples in an easily configurable manner.") | |
12882 | (license license:gpl3+))) | |
531afc8a RW |
12883 | |
12884 | (define-public pigx-chipseq | |
12885 | (package | |
12886 | (name "pigx-chipseq") | |
3d7f9cbe | 12887 | (version "0.0.15") |
531afc8a RW |
12888 | (source (origin |
12889 | (method url-fetch) | |
12890 | (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/" | |
12891 | "releases/download/v" version | |
12892 | "/pigx_chipseq-" version ".tar.gz")) | |
12893 | (sha256 | |
12894 | (base32 | |
3d7f9cbe | 12895 | "11v9v3vyda0sv4cl45nki7mm4v4bjfcdq7a70kcvi9h465nq66wg")))) |
531afc8a RW |
12896 | (build-system gnu-build-system) |
12897 | (arguments | |
32b7ccf9 RW |
12898 | `(#:tests? #f ; parts of the tests rely on access to the network |
12899 | #:phases | |
531afc8a RW |
12900 | (modify-phases %standard-phases |
12901 | (add-after 'install 'wrap-executable | |
12902 | ;; Make sure the executable finds all R modules. | |
12903 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
12904 | (let ((out (assoc-ref outputs "out"))) | |
12905 | (wrap-program (string-append out "/bin/pigx-chipseq") | |
12906 | `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE"))) | |
12907 | `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH"))))) | |
12908 | #t))))) | |
12909 | (inputs | |
d7a11f1a RW |
12910 | `(("grep" ,grep) |
12911 | ("coreutils" ,coreutils) | |
12912 | ("r-minimal" ,r-minimal) | |
531afc8a | 12913 | ("r-argparser" ,r-argparser) |
363ee7a3 RW |
12914 | ("r-biocparallel" ,r-biocparallel) |
12915 | ("r-biostrings" ,r-biostrings) | |
531afc8a RW |
12916 | ("r-chipseq" ,r-chipseq) |
12917 | ("r-data-table" ,r-data-table) | |
363ee7a3 | 12918 | ("r-dplyr" ,r-dplyr) |
531afc8a | 12919 | ("r-genomation" ,r-genomation) |
363ee7a3 | 12920 | ("r-genomicalignments" ,r-genomicalignments) |
531afc8a | 12921 | ("r-genomicranges" ,r-genomicranges) |
363ee7a3 | 12922 | ("r-rsamtools" ,r-rsamtools) |
531afc8a | 12923 | ("r-rtracklayer" ,r-rtracklayer) |
363ee7a3 | 12924 | ("r-s4vectors" ,r-s4vectors) |
531afc8a | 12925 | ("r-stringr" ,r-stringr) |
363ee7a3 RW |
12926 | ("r-tibble" ,r-tibble) |
12927 | ("r-tidyr" ,r-tidyr) | |
531afc8a RW |
12928 | ("r-jsonlite" ,r-jsonlite) |
12929 | ("r-heatmaply" ,r-heatmaply) | |
363ee7a3 | 12930 | ("r-htmlwidgets" ,r-htmlwidgets) |
531afc8a RW |
12931 | ("r-ggplot2" ,r-ggplot2) |
12932 | ("r-plotly" ,r-plotly) | |
363ee7a3 | 12933 | ("r-rmarkdown" ,r-rmarkdown) |
531afc8a RW |
12934 | ("python-wrapper" ,python-wrapper) |
12935 | ("python-pyyaml" ,python-pyyaml) | |
363ee7a3 | 12936 | ("python-magic" ,python-magic) |
32b7ccf9 | 12937 | ("python-xlrd" ,python-xlrd) |
32b7ccf9 | 12938 | ("trim-galore" ,trim-galore) |
531afc8a RW |
12939 | ("macs" ,macs) |
12940 | ("multiqc" ,multiqc) | |
12941 | ("perl" ,perl) | |
fd757a8f RW |
12942 | ("ghc-pandoc" ,ghc-pandoc-1) |
12943 | ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1) | |
531afc8a RW |
12944 | ("fastqc" ,fastqc) |
12945 | ("bowtie" ,bowtie) | |
12946 | ("idr" ,idr) | |
12947 | ("snakemake" ,snakemake) | |
12948 | ("samtools" ,samtools) | |
12949 | ("bedtools" ,bedtools) | |
12950 | ("kentutils" ,kentutils))) | |
12951 | (native-inputs | |
12952 | `(("python-pytest" ,python-pytest))) | |
12953 | (home-page "http://bioinformatics.mdc-berlin.de/pigx/") | |
12954 | (synopsis "Analysis pipeline for ChIP sequencing experiments") | |
12955 | (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak | |
12956 | calling and reporting for ChIP sequencing experiments. It is easy to use and | |
12957 | produces high quality reports. The inputs are reads files from the sequencing | |
12958 | experiment, and a configuration file which describes the experiment. In | |
12959 | addition to quality control of the experiment, the pipeline enables to set up | |
12960 | multiple peak calling analysis and allows the generation of a UCSC track hub | |
12961 | in an easily configurable manner.") | |
12962 | (license license:gpl3+))) | |
fb94174f RW |
12963 | |
12964 | (define-public pigx-bsseq | |
12965 | (package | |
12966 | (name "pigx-bsseq") | |
4f1e4f33 | 12967 | (version "0.0.8") |
fb94174f RW |
12968 | (source (origin |
12969 | (method url-fetch) | |
12970 | (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/" | |
12971 | "releases/download/v" version | |
12972 | "/pigx_bsseq-" version ".tar.gz")) | |
12973 | (sha256 | |
12974 | (base32 | |
4f1e4f33 | 12975 | "0irlnlhhw9fd4ha7hksrxn3y7j76mz5qq1wjswbs9p364laqg69y")))) |
fb94174f RW |
12976 | (build-system gnu-build-system) |
12977 | (arguments | |
12978 | `(#:phases | |
12979 | (modify-phases %standard-phases | |
12980 | (add-before 'check 'set-timezone | |
12981 | ;; The readr package is picky about timezones. | |
12982 | (lambda* (#:key inputs #:allow-other-keys) | |
12983 | (setenv "TZ" "UTC+1") | |
12984 | (setenv "TZDIR" | |
12985 | (string-append (assoc-ref inputs "tzdata") | |
12986 | "/share/zoneinfo")) | |
12987 | #t)) | |
12988 | (add-after 'install 'wrap-executable | |
12989 | ;; Make sure the executable finds all R modules. | |
12990 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
12991 | (let ((out (assoc-ref outputs "out"))) | |
12992 | (wrap-program (string-append out "/bin/pigx-bsseq") | |
12993 | `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE"))) | |
12994 | `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH"))))) | |
12995 | #t))))) | |
12996 | (native-inputs | |
12997 | `(("tzdata" ,tzdata))) | |
12998 | (inputs | |
9dbdc830 RW |
12999 | `(("coreutils" ,coreutils) |
13000 | ("sed" ,sed) | |
13001 | ("grep" ,grep) | |
13002 | ("r-minimal" ,r-minimal) | |
fb94174f RW |
13003 | ("r-annotationhub" ,r-annotationhub) |
13004 | ("r-dt" ,r-dt) | |
13005 | ("r-genomation" ,r-genomation) | |
13006 | ("r-methylkit" ,r-methylkit) | |
13007 | ("r-rtracklayer" ,r-rtracklayer) | |
13008 | ("r-rmarkdown" ,r-rmarkdown) | |
13009 | ("r-bookdown" ,r-bookdown) | |
13010 | ("r-ggplot2" ,r-ggplot2) | |
13011 | ("r-ggbio" ,r-ggbio) | |
9dcb4d22 RW |
13012 | ("ghc-pandoc" ,ghc-pandoc-1) |
13013 | ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1) | |
fb94174f RW |
13014 | ("python-wrapper" ,python-wrapper) |
13015 | ("python-pyyaml" ,python-pyyaml) | |
13016 | ("snakemake" ,snakemake) | |
13017 | ("bismark" ,bismark) | |
13018 | ("fastqc" ,fastqc) | |
13019 | ("bowtie" ,bowtie) | |
13020 | ("trim-galore" ,trim-galore) | |
13021 | ("cutadapt" ,cutadapt) | |
13022 | ("samtools" ,samtools))) | |
13023 | (home-page "http://bioinformatics.mdc-berlin.de/pigx/") | |
13024 | (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports") | |
13025 | (description "PiGx BSseq is a data processing pipeline for raw fastq read | |
13026 | data of bisulfite experiments; it produces reports on aggregate methylation | |
13027 | and coverage and can be used to produce information on differential | |
13028 | methylation and segmentation.") | |
13029 | (license license:gpl3+))) | |
32cbbac1 | 13030 | |
46264c73 RW |
13031 | (define-public pigx-scrnaseq |
13032 | (package | |
13033 | (name "pigx-scrnaseq") | |
a4ab65ee | 13034 | (version "0.0.4") |
46264c73 RW |
13035 | (source (origin |
13036 | (method url-fetch) | |
13037 | (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/" | |
13038 | "releases/download/v" version | |
13039 | "/pigx_scrnaseq-" version ".tar.gz")) | |
13040 | (sha256 | |
13041 | (base32 | |
a4ab65ee | 13042 | "1pvjm6f3mascprs65vflggwwg5v925knvgal7k7a6nnlmw5qndrf")))) |
46264c73 RW |
13043 | (build-system gnu-build-system) |
13044 | (arguments | |
13045 | `(#:configure-flags | |
13046 | (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard") | |
13047 | "/share/java/picard.jar") | |
13048 | (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools") | |
13049 | "/share/java/dropseq.jar")) | |
13050 | #:phases | |
13051 | (modify-phases %standard-phases | |
13052 | (add-after 'install 'wrap-executable | |
13053 | ;; Make sure the executable finds all R modules. | |
13054 | (lambda* (#:key inputs outputs #:allow-other-keys) | |
13055 | (let ((out (assoc-ref outputs "out"))) | |
13056 | (wrap-program (string-append out "/bin/pigx-scrnaseq") | |
13057 | `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE"))) | |
13058 | `("PYTHONPATH" ":" = (,(getenv "PYTHONPATH"))))) | |
13059 | #t))))) | |
13060 | (inputs | |
51237011 RW |
13061 | `(("coreutils" ,coreutils) |
13062 | ("perl" ,perl) | |
13063 | ("dropseq-tools" ,dropseq-tools) | |
46264c73 RW |
13064 | ("fastqc" ,fastqc) |
13065 | ("java-picard" ,java-picard) | |
13066 | ("java" ,icedtea-8) | |
13067 | ("python-wrapper" ,python-wrapper) | |
13068 | ("python-pyyaml" ,python-pyyaml) | |
13069 | ("python-pandas" ,python-pandas) | |
13070 | ("python-numpy" ,python-numpy) | |
13071 | ("python-loompy" ,python-loompy) | |
2915221b RW |
13072 | ("ghc-pandoc" ,ghc-pandoc-1) |
13073 | ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc-with-pandoc-1) | |
46264c73 RW |
13074 | ("snakemake" ,snakemake) |
13075 | ("star" ,star) | |
13076 | ("r-minimal" ,r-minimal) | |
13077 | ("r-argparser" ,r-argparser) | |
13078 | ("r-cowplot" ,r-cowplot) | |
13079 | ("r-data-table" ,r-data-table) | |
13080 | ("r-delayedarray" ,r-delayedarray) | |
13081 | ("r-delayedmatrixstats" ,r-delayedmatrixstats) | |
13082 | ("r-dplyr" ,r-dplyr) | |
13083 | ("r-dropbead" ,r-dropbead) | |
13084 | ("r-dt" ,r-dt) | |
13085 | ("r-genomicalignments" ,r-genomicalignments) | |
13086 | ("r-genomicfiles" ,r-genomicfiles) | |
13087 | ("r-genomicranges" ,r-genomicranges) | |
13088 | ("r-ggplot2" ,r-ggplot2) | |
13089 | ("r-hdf5array" ,r-hdf5array) | |
13090 | ("r-pheatmap" ,r-pheatmap) | |
13091 | ("r-rmarkdown" ,r-rmarkdown) | |
13092 | ("r-rsamtools" ,r-rsamtools) | |
13093 | ("r-rtracklayer" ,r-rtracklayer) | |
13094 | ("r-rtsne" ,r-rtsne) | |
13095 | ("r-scater" ,r-scater) | |
13096 | ("r-scran" ,r-scran) | |
13097 | ("r-singlecellexperiment" ,r-singlecellexperiment) | |
13098 | ("r-stringr" ,r-stringr) | |
13099 | ("r-yaml" ,r-yaml))) | |
13100 | (home-page "http://bioinformatics.mdc-berlin.de/pigx/") | |
13101 | (synopsis "Analysis pipeline for single-cell RNA sequencing experiments") | |
13102 | (description "PiGX scRNAseq is an analysis pipeline for preprocessing and | |
13103 | quality control for single cell RNA sequencing experiments. The inputs are | |
13104 | read files from the sequencing experiment, and a configuration file which | |
13105 | describes the experiment. It produces processed files for downstream analysis | |
13106 | and interactive quality reports. The pipeline is designed to work with UMI | |
13107 | based methods.") | |
13108 | (license license:gpl3+))) | |
13109 | ||
c1c9cc66 RW |
13110 | (define-public pigx |
13111 | (package | |
13112 | (name "pigx") | |
d8f08c85 | 13113 | (version "0.0.2") |
c1c9cc66 RW |
13114 | (source (origin |
13115 | (method url-fetch) | |
13116 | (uri (string-append "https://github.com/BIMSBbioinfo/pigx/" | |
13117 | "releases/download/v" version | |
13118 | "/pigx-" version ".tar.gz")) | |
13119 | (sha256 | |
13120 | (base32 | |
d8f08c85 | 13121 | "0sb708sl42h3s5z872jb1w70bbqplwapnsc1wm27zcsvi7li4gw8")))) |
c1c9cc66 RW |
13122 | (build-system gnu-build-system) |
13123 | (inputs | |
13124 | `(("python" ,python) | |
13125 | ("pigx-bsseq" ,pigx-bsseq) | |
13126 | ("pigx-chipseq" ,pigx-chipseq) | |
13127 | ("pigx-rnaseq" ,pigx-rnaseq) | |
13128 | ("pigx-scrnaseq" ,pigx-scrnaseq))) | |
13129 | (home-page "http://bioinformatics.mdc-berlin.de/pigx/") | |
13130 | (synopsis "Analysis pipelines for genomics") | |
13131 | (description "PiGx is a collection of genomics pipelines. It includes the | |
13132 | following pipelines: | |
13133 | ||
13134 | @itemize | |
13135 | @item PiGx BSseq for raw fastq read data of bisulfite experiments | |
13136 | @item PiGx RNAseq for RNAseq samples | |
13137 | @item PiGx scRNAseq for single cell dropseq analysis | |
13138 | @item PiGx ChIPseq for reads from ChIPseq experiments | |
13139 | @end itemize | |
13140 | ||
13141 | All pipelines are easily configured with a simple sample sheet and a | |
13142 | descriptive settings file. The result is a set of comprehensive, interactive | |
13143 | HTML reports with interesting findings about your samples.") | |
13144 | (license license:gpl3+))) | |
13145 | ||
32cbbac1 LF |
13146 | (define-public r-diversitree |
13147 | (package | |
13148 | (name "r-diversitree") | |
13149 | (version "0.9-10") | |
13150 | (source | |
13151 | (origin | |
13152 | (method url-fetch) | |
13153 | (uri (cran-uri "diversitree" version)) | |
13154 | (sha256 | |
13155 | (base32 | |
13156 | "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7")))) | |
13157 | (build-system r-build-system) | |
13158 | (native-inputs | |
13159 | `(("gfortran" ,gfortran))) | |
13160 | (inputs `(("fftw" ,fftw) ("gsl" ,gsl))) | |
13161 | (propagated-inputs | |
13162 | `(("r-ape" ,r-ape) | |
13163 | ("r-desolve" ,r-desolve) | |
13164 | ("r-rcpp" ,r-rcpp) | |
13165 | ("r-suplex" ,r-subplex))) | |
13166 | (home-page "https://www.zoology.ubc.ca/prog/diversitree") | |
13167 | (synopsis "Comparative 'phylogenetic' analyses of diversification") | |
13168 | (description "This package contains a number of comparative \"phylogenetic\" | |
13169 | methods, mostly focusing on analysing diversification and character evolution. | |
13170 | Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction) | |
13171 | and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and | |
13172 | Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods | |
13173 | include Markov models of discrete and continuous trait evolution and constant | |
13174 | rate speciation and extinction.") | |
13175 | (license license:gpl2+))) |