HCoop / jackhill / guix / guix.git / blame
? search:
summary | shortlog | log | commit | commitdiff | tree
blob | blame (incremental) | history | HEAD
gnu: r-rtracklayer: Update to 1.38.2.
[jackhill/guix/guix.git] / gnu / packages / bioinformatics.scm
CommitLineData
4e10a221 1;;; GNU Guix --- Functional package management for GNU
6193563a 2;;; Copyright © 2014, 2015, 2016, 2017 Ricardo Wurmus <rekado@elephly.net>
a9f754d7 3;;; Copyright © 2015, 2016, 2017 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>
ce7e361f 7;;; Copyright © 2016, 2017 Efraim Flashner <efraim@flashner.co.il>
318c0aee 8;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
3fffabce 9;;; Copyright © 2016 Raoul Bonnal <ilpuccio.febo@gmail.com>
ce4dfde0 10;;; Copyright © 2017 Tobias Geerinckx-Rice <me@tobias.gr>
9364a520 11;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
4e10a221
RW		 12;;;
13;;; This file is part of GNU Guix.
14;;;
15;;; GNU Guix is free software; you can redistribute it and/or modify it
16;;; under the terms of the GNU General Public License as published by
17;;; the Free Software Foundation; either version 3 of the License, or (at
18;;; your option) any later version.
19;;;
20;;; GNU Guix is distributed in the hope that it will be useful, but
21;;; WITHOUT ANY WARRANTY; without even the implied warranty of
22;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23;;; GNU General Public License for more details.
24;;;
25;;; You should have received a copy of the GNU General Public License
26;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
27
28(define-module (gnu packages bioinformatics)
29 #:use-module ((guix licenses) #:prefix license:)
30 #:use-module (guix packages)
8e913213 31 #:use-module (guix utils)
4e10a221 32 #:use-module (guix download)
2c16316e 33 #:use-module (guix git-download)
ec946638 34 #:use-module (guix hg-download)
10b4a969 35 #:use-module (guix build-system ant)
4e10a221 36 #:use-module (guix build-system gnu)
d7678942 37 #:use-module (guix build-system cmake)
c033f5d6 38 #:use-module (guix build-system ocaml)
365c8153 39 #:use-module (guix build-system perl)
8622a072 40 #:use-module (guix build-system python)
a5002ae7 41 #:use-module (guix build-system r)
9c38b540 42 #:use-module (guix build-system ruby)
9364a520 43 #:use-module (guix build-system scons)
d3517eda 44 #:use-module (guix build-system trivial)
4e10a221 45 #:use-module (gnu packages)
a2950fa4 46 #:use-module (gnu packages autotools)
684bf7c7 47 #:use-module (gnu packages algebra)
d3517eda 48 #:use-module (gnu packages base)
318c0aee 49 #:use-module (gnu packages bash)
a0a71439 50 #:use-module (gnu packages bison)
e4e5a4d8 51 #:use-module (gnu packages boost)
ac257f12 52 #:use-module (gnu packages check)
4e10a221 53 #:use-module (gnu packages compression)
82c370de 54 #:use-module (gnu packages cpio)
7cb61550 55 #:use-module (gnu packages cran)
1baee943 56 #:use-module (gnu packages curl)
99828fa7 57 #:use-module (gnu packages documentation)
94820951 58 #:use-module (gnu packages databases)
d29150b5 59 #:use-module (gnu packages datastructures)
75dd2424 60 #:use-module (gnu packages file)
99268755 61 #:use-module (gnu packages flex)
02f35bb5 62 #:use-module (gnu packages gawk)
2409f37f 63 #:use-module (gnu packages gcc)
66e40e00 64 #:use-module (gnu packages gd)
97b9da68 65 #:use-module (gnu packages gtk)
b16728b0 66 #:use-module (gnu packages glib)
18f5d2a7 67 #:use-module (gnu packages graph)
db7a3444 68 #:use-module (gnu packages groff)
50937297 69 #:use-module (gnu packages guile)
89984be4 70 #:use-module (gnu packages haskell)
66e40e00 71 #:use-module (gnu packages image)
97b9da68 72 #:use-module (gnu packages imagemagick)
15a3c3d4 73 #:use-module (gnu packages java)
5ded35d8 74 #:use-module (gnu packages ldc)
51c64999 75 #:use-module (gnu packages linux)
ec946638 76 #:use-module (gnu packages logging)
36742f43 77 #:use-module (gnu packages machine-learning)
db7a3444 78 #:use-module (gnu packages man)
c833ab55 79 #:use-module (gnu packages maths)
6c2b26e2 80 #:use-module (gnu packages mpi)
4e10a221 81 #:use-module (gnu packages ncurses)
c033f5d6 82 #:use-module (gnu packages ocaml)
81f3e0c1 83 #:use-module (gnu packages pcre)
ceb62d54 84 #:use-module (gnu packages parallel)
66e40e00 85 #:use-module (gnu packages pdf)
4e10a221 86 #:use-module (gnu packages perl)
5ccde207 87 #:use-module (gnu packages perl-check)
4e10a221 88 #:use-module (gnu packages pkg-config)
bfe3c685 89 #:use-module (gnu packages popt)
e4e5a4d8 90 #:use-module (gnu packages protobuf)
346a829a 91 #:use-module (gnu packages python)
589e3f4e 92 #:use-module (gnu packages python-web)
ec946638 93 #:use-module (gnu packages readline)
9c38b540 94 #:use-module (gnu packages ruby)
84be3b99 95 #:use-module (gnu packages serialization)
94820951 96 #:use-module (gnu packages shells)
c833ab55 97 #:use-module (gnu packages statistics)
aa163424 98 #:use-module (gnu packages swig)
d7678942 99 #:use-module (gnu packages tbb)
97b9da68 100 #:use-module (gnu packages tex)
db7a3444 101 #:use-module (gnu packages texinfo)
2127cedb 102 #:use-module (gnu packages textutils)
43c565d2 103 #:use-module (gnu packages time)
a2950fa4 104 #:use-module (gnu packages tls)
ce7155d5 105 #:use-module (gnu packages vim)
365c8153 106 #:use-module (gnu packages web)
c833ab55 107 #:use-module (gnu packages xml)
66e40e00 108 #:use-module (gnu packages xorg)
2c9232ae 109 #:use-module (srfi srfi-1)
ce7e361f 110 #:use-module (ice-9 match))
4e10a221 111
036cd0cb
RJPB		 112(define-public r-ape
113 (package
114 (name "r-ape")
b12c6a66 115 (version "5.0")
036cd0cb
RJPB		 116 (source
117 (origin
118 (method url-fetch)
119 (uri (cran-uri "ape" version))
120 (sha256
121 (base32
b12c6a66 122 "0q59pmxawz498cb9mv5m49lhiwxib8ak94yyydz7qg8b6lpd4bn3"))))
036cd0cb 123 (build-system r-build-system)
aeb64f3c
RW		 124 (propagated-inputs
125 `(("r-lattice" ,r-lattice)
b12c6a66
RW		 126 ("r-nlme" ,r-nlme)
127 ("r-rcpp" ,r-rcpp)))
036cd0cb
RJPB		 128 (home-page "http://ape-package.ird.fr/")
129 (synopsis "Analyses of phylogenetics and evolution")
130 (description
131 "This package provides functions for reading, writing, plotting, and
132manipulating phylogenetic trees, analyses of comparative data in a
133phylogenetic framework, ancestral character analyses, analyses of
134diversification and macroevolution, computing distances from DNA sequences,
135and several other tools.")
136 (license license:gpl2+)))
137
8dc797fa
BW		 138(define-public aragorn
139 (package
140 (name "aragorn")
e990c81d 141 (version "1.2.38")
8dc797fa
BW		 142 (source (origin
143 (method url-fetch)
144 (uri (string-append
145 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
146 version ".tgz"))
147 (sha256
148 (base32
e990c81d 149 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
8dc797fa
BW		 150 (build-system gnu-build-system)
151 (arguments
152 `(#:tests? #f ; there are no tests
153 #:phases
154 (modify-phases %standard-phases
155 (delete 'configure)
156 (replace 'build
157 (lambda _
158 (zero? (system* "gcc"
159 "-O3"
160 "-ffast-math"
161 "-finline-functions"
162 "-o"
163 "aragorn"
164 (string-append "aragorn" ,version ".c")))))
165 (replace 'install
166 (lambda* (#:key outputs #:allow-other-keys)
167 (let* ((out (assoc-ref outputs "out"))
168 (bin (string-append out "/bin"))
169 (man (string-append out "/share/man/man1")))
170 (mkdir-p bin)
f3860753 171 (install-file "aragorn" bin)
8dc797fa 172 (mkdir-p man)
f3860753 173 (install-file "aragorn.1" man))
8dc797fa
BW		 174 #t)))))
175 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
176 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
177 (description
178 "Aragorn identifies transfer RNA, mitochondrial RNA and
179transfer-messenger RNA from nucleotide sequences, based on homology to known
180tRNA consensus sequences and RNA structure. It also outputs the secondary
181structure of the predicted RNA.")
182 (license license:gpl2)))
183
a12ba6e8
BW		 184(define-public bamm
185 (package
186 (name "bamm")
4b6da268 187 (version "1.7.3")
a12ba6e8
BW		 188 (source (origin
189 (method url-fetch)
190 ;; BamM is not available on pypi.
191 (uri (string-append
4b6da268 192 "https://github.com/Ecogenomics/BamM/archive/"
a12ba6e8
BW		 193 version ".tar.gz"))
194 (file-name (string-append name "-" version ".tar.gz"))
195 (sha256
196 (base32
4b6da268 197 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
a12ba6e8
BW		 198 (modules '((guix build utils)))
199 (snippet
200 `(begin
201 ;; Delete bundled htslib.
202 (delete-file-recursively "c/htslib-1.3.1")
203 #t))))
204 (build-system python-build-system)
205 (arguments
206 `(#:python ,python-2 ; BamM is Python 2 only.
207 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
208 ;; been modified from its original form.
209 #:configure-flags
210 (let ((htslib (assoc-ref %build-inputs "htslib")))
211 (list "--with-libhts-lib" (string-append htslib "/lib")
212 "--with-libhts-inc" (string-append htslib "/include/htslib")))
213 #:phases
214 (modify-phases %standard-phases
215 (add-after 'unpack 'autogen
216 (lambda _
217 (with-directory-excursion "c"
218 (let ((sh (which "sh")))
219 ;; Use autogen so that 'configure' works.
220 (substitute* "autogen.sh" (("/bin/sh") sh))
221 (setenv "CONFIG_SHELL" sh)
222 (substitute* "configure" (("/bin/sh") sh))
223 (zero? (system* "./autogen.sh"))))))
224 (delete 'build)
225 ;; Run tests after installation so compilation only happens once.
226 (delete 'check)
227 (add-after 'install 'wrap-executable
228 (lambda* (#:key outputs #:allow-other-keys)
229 (let* ((out (assoc-ref outputs "out"))
230 (path (getenv "PATH")))
231 (wrap-program (string-append out "/bin/bamm")
232 `("PATH" ":" prefix (,path))))
233 #t))
234 (add-after 'wrap-executable 'post-install-check
235 (lambda* (#:key inputs outputs #:allow-other-keys)
236 (setenv "PATH"
237 (string-append (assoc-ref outputs "out")
238 "/bin:"
239 (getenv "PATH")))
240 (setenv "PYTHONPATH"
241 (string-append
242 (assoc-ref outputs "out")
243 "/lib/python"
244 (string-take (string-take-right
245 (assoc-ref inputs "python") 5) 3)
246 "/site-packages:"
247 (getenv "PYTHONPATH")))
248 ;; There are 2 errors printed, but they are safe to ignore:
249 ;; 1) [E::hts_open_format] fail to open file ...
250 ;; 2) samtools view: failed to open ...
251 (zero? (system* "nosetests")))))))
252 (native-inputs
253 `(("autoconf" ,autoconf)
254 ("automake" ,automake)
255 ("libtool" ,libtool)
256 ("zlib" ,zlib)
257 ("python-nose" ,python2-nose)
f3b98f4f 258 ("python-pysam" ,python2-pysam)))
a12ba6e8 259 (inputs
bca2c576 260 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
a12ba6e8
BW		 261 ("samtools" ,samtools)
262 ("bwa" ,bwa)
263 ("grep" ,grep)
264 ("sed" ,sed)
265 ("coreutils" ,coreutils)))
266 (propagated-inputs
267 `(("python-numpy" ,python2-numpy)))
268 (home-page "http://ecogenomics.github.io/BamM/")
269 (synopsis "Metagenomics-focused BAM file manipulator")
270 (description
271 "BamM is a C library, wrapped in python, to efficiently generate and
272parse BAM files, specifically for the analysis of metagenomic data. For
273instance, it implements several methods to assess contig-wise read coverage.")
274 (license license:lgpl3+)))
275
9794180d
RW		 276(define-public bamtools
277 (package
278 (name "bamtools")
48d66a9c 279 (version "2.4.1")
9794180d
RW		 280 (source (origin
281 (method url-fetch)
282 (uri (string-append
283 "https://github.com/pezmaster31/bamtools/archive/v"
284 version ".tar.gz"))
285 (file-name (string-append name "-" version ".tar.gz"))
286 (sha256
287 (base32
48d66a9c 288 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
9794180d 289 (build-system cmake-build-system)
4702cec2
RW		 290 (arguments
291 `(#:tests? #f ;no "check" target
292 #:phases
293 (modify-phases %standard-phases
294 (add-before
295 'configure 'set-ldflags
296 (lambda* (#:key outputs #:allow-other-keys)
297 (setenv "LDFLAGS"
298 (string-append
299 "-Wl,-rpath="
300 (assoc-ref outputs "out") "/lib/bamtools")))))))
9794180d
RW		 301 (inputs `(("zlib" ,zlib)))
302 (home-page "https://github.com/pezmaster31/bamtools")
303 (synopsis "C++ API and command-line toolkit for working with BAM data")
304 (description
305 "BamTools provides both a C++ API and a command-line toolkit for handling
306BAM files.")
307 (license license:expat)))
308
bdc7be59
MB		 309(define-public bcftools
310 (package
311 (name "bcftools")
0620387a 312 (version "1.5")
bdc7be59
MB		 313 (source (origin
314 (method url-fetch)
315 (uri (string-append
316 "https://github.com/samtools/bcftools/releases/download/"
317 version "/bcftools-" version ".tar.bz2"))
318 (sha256
319 (base32
0620387a 320 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
3837108e 321 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
bdc7be59
MB		 322 (modules '((guix build utils)))
323 (snippet
324 ;; Delete bundled htslib.
0620387a 325 '(delete-file-recursively "htslib-1.5"))))
bdc7be59
MB		 326 (build-system gnu-build-system)
327 (arguments
328 `(#:test-target "test"
0620387a 329 #:configure-flags (list "--with-htslib=system")
bdc7be59
MB		 330 #:make-flags
331 (list
332 "USE_GPL=1"
0620387a 333 "LIBS=-lgsl -lgslcblas"
bdc7be59
MB		 334 (string-append "prefix=" (assoc-ref %outputs "out"))
335 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
98593f9f 336 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
bdc7be59 337 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
98593f9f
BW		 338 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
339 (string-append "PACKAGE_VERSION=" ,version))
bdc7be59
MB		 340 #:phases
341 (modify-phases %standard-phases
bdc7be59
MB		 342 (add-before 'check 'patch-tests
343 (lambda _
344 (substitute* "test/test.pl"
345 (("/bin/bash") (which "bash")))
346 #t)))))
347 (native-inputs
348 `(("htslib" ,htslib)
349 ("perl" ,perl)))
350 (inputs
351 `(("gsl" ,gsl)
352 ("zlib" ,zlib)))
353 (home-page "https://samtools.github.io/bcftools/")
354 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
355 (description
356 "BCFtools is a set of utilities that manipulate variant calls in the
357Variant Call Format (VCF) and its binary counterpart BCF. All commands work
358transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
359 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
360 (license (list license:gpl3+ license:expat))))
361
8dd4ff11
RW		 362(define-public bedops
363 (package
364 (name "bedops")
1bbc3b1d 365 (version "2.4.14")
8dd4ff11
RW		 366 (source (origin
367 (method url-fetch)
368 (uri (string-append "https://github.com/bedops/bedops/archive/v"
369 version ".tar.gz"))
f586c877 370 (file-name (string-append name "-" version ".tar.gz"))
8dd4ff11
RW		 371 (sha256
372 (base32
1bbc3b1d 373 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
8dd4ff11
RW		 374 (build-system gnu-build-system)
375 (arguments
376 '(#:tests? #f
377 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
378 #:phases
dc1d3cde
KK		 379 (modify-phases %standard-phases
380 (add-after 'unpack 'unpack-tarballs
381 (lambda _
382 ;; FIXME: Bedops includes tarballs of minimally patched upstream
383 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
384 ;; libraries because at least one of the libraries (zlib) is
385 ;; patched to add a C++ function definition (deflateInit2cpp).
386 ;; Until the Bedops developers offer a way to link against system
387 ;; libraries we have to build the in-tree copies of these three
388 ;; libraries.
389
390 ;; See upstream discussion:
391 ;; https://github.com/bedops/bedops/issues/124
392
393 ;; Unpack the tarballs to benefit from shebang patching.
394 (with-directory-excursion "third-party"
395 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
396 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
397 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
398 ;; Disable unpacking of tarballs in Makefile.
399 (substitute* "system.mk/Makefile.linux"
400 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
401 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
402 (substitute* "third-party/zlib-1.2.7/Makefile.in"
403 (("^SHELL=.*$") "SHELL=bash\n"))
404 #t))
405 (delete 'configure))))
8dd4ff11
RW		 406 (home-page "https://github.com/bedops/bedops")
407 (synopsis "Tools for high-performance genomic feature operations")
408 (description
409 "BEDOPS is a suite of tools to address common questions raised in genomic
410studies---mostly with regard to overlap and proximity relationships between
411data sets. It aims to be scalable and flexible, facilitating the efficient
412and accurate analysis and management of large-scale genomic data.
413
414BEDOPS provides tools that perform highly efficient and scalable Boolean and
415other set operations, statistical calculations, archiving, conversion and
416other management of genomic data of arbitrary scale. Tasks can be easily
417split by chromosome for distributing whole-genome analyses across a
418computational cluster.")
419 (license license:gpl2+)))
420
81de5647
RW		 421(define-public bedtools
422 (package
423 (name "bedtools")
6098a386 424 (version "2.27.1")
81de5647
RW		 425 (source (origin
426 (method url-fetch)
0d9824cc
RW		 427 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
428 "download/v" version "/"
429 "bedtools-" version ".tar.gz"))
81de5647
RW		 430 (sha256
431 (base32
6098a386 432 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
81de5647 433 (build-system gnu-build-system)
81de5647
RW		 434 (arguments
435 '(#:test-target "test"
0d9824cc
RW		 436 #:make-flags
437 (list (string-append "prefix=" (assoc-ref %outputs "out")))
81de5647 438 #:phases
6573ac82 439 (modify-phases %standard-phases
0d9824cc
RW		 440 (delete 'configure))))
441 (native-inputs `(("python" ,python-2)))
442 (inputs
443 `(("samtools" ,samtools)
444 ("zlib" ,zlib)))
81de5647
RW		 445 (home-page "https://github.com/arq5x/bedtools2")
446 (synopsis "Tools for genome analysis and arithmetic")
447 (description
448 "Collectively, the bedtools utilities are a swiss-army knife of tools for
449a wide-range of genomics analysis tasks. The most widely-used tools enable
450genome arithmetic: that is, set theory on the genome. For example, bedtools
451allows one to intersect, merge, count, complement, and shuffle genomic
452intervals from multiple files in widely-used genomic file formats such as BAM,
453BED, GFF/GTF, VCF.")
454 (license license:gpl2)))
455
9a8f309c
RW		 456;; Later releases of bedtools produce files with more columns than
457;; what Ribotaper expects.
458(define-public bedtools-2.18
459 (package (inherit bedtools)
460 (name "bedtools")
461 (version "2.18.0")
462 (source (origin
463 (method url-fetch)
464 (uri (string-append "https://github.com/arq5x/bedtools2/"
465 "archive/v" version ".tar.gz"))
466 (file-name (string-append name "-" version ".tar.gz"))
467 (sha256
468 (base32
83b9d121
RW		 469 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
470 (arguments
471 '(#:test-target "test"
472 #:phases
473 (modify-phases %standard-phases
474 (delete 'configure)
475 (replace 'install
476 (lambda* (#:key outputs #:allow-other-keys)
477 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
478 (for-each (lambda (file)
479 (install-file file bin))
480 (find-files "bin" ".*")))
481 #t)))))))
9a8f309c 482
17dc32a4
RW		 483(define-public ribotaper
484 (package
485 (name "ribotaper")
486 (version "1.3.1")
487 (source (origin
488 (method url-fetch)
489 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
490 "files/RiboTaper/RiboTaper_Version_"
491 version ".tar.gz"))
492 (sha256
493 (base32
494 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
495 (build-system gnu-build-system)
496 (inputs
497 `(("bedtools" ,bedtools-2.18)
498 ("samtools" ,samtools-0.1)
2d7c4ae3 499 ("r-minimal" ,r-minimal)
17dc32a4
RW		 500 ("r-foreach" ,r-foreach)
501 ("r-xnomial" ,r-xnomial)
502 ("r-domc" ,r-domc)
503 ("r-multitaper" ,r-multitaper)
504 ("r-seqinr" ,r-seqinr)))
505 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
506 (synopsis "Define translated ORFs using ribosome profiling data")
507 (description
508 "Ribotaper is a method for defining translated @dfn{open reading
509frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
510provides the Ribotaper pipeline.")
511 (license license:gpl3+)))
512
769fc6bb
RW		 513(define-public ribodiff
514 (package
515 (name "ribodiff")
516 (version "0.2.2")
517 (source
518 (origin
519 (method url-fetch)
520 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
521 "archive/v" version ".tar.gz"))
522 (file-name (string-append name "-" version ".tar.gz"))
523 (sha256
524 (base32
525 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
526 (build-system python-build-system)
527 (arguments
528 `(#:python ,python-2
529 #:phases
530 (modify-phases %standard-phases
531 ;; Generate an installable executable script wrapper.
532 (add-after 'unpack 'patch-setup.py
533 (lambda _
534 (substitute* "setup.py"
535 (("^(.*)packages=.*" line prefix)
536 (string-append line "\n"
537 prefix "scripts=['scripts/TE.py'],\n")))
538 #t)))))
539 (inputs
540 `(("python-numpy" ,python2-numpy)
541 ("python-matplotlib" ,python2-matplotlib)
542 ("python-scipy" ,python2-scipy)
543 ("python-statsmodels" ,python2-statsmodels)))
2bb12f5a
MB		 544 (native-inputs
545 `(("python-mock" ,python2-mock)
546 ("python-nose" ,python2-nose)))
769fc6bb
RW		 547 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
548 (synopsis "Detect translation efficiency changes from ribosome footprints")
549 (description "RiboDiff is a statistical tool that detects the protein
550translational efficiency change from Ribo-Seq (ribosome footprinting) and
551RNA-Seq data. It uses a generalized linear model to detect genes showing
552difference in translational profile taking mRNA abundance into account. It
553facilitates us to decipher the translational regulation that behave
554independently with transcriptional regulation.")
555 (license license:gpl3+)))
556
a0a71439
RJ		 557(define-public bioawk
558 (package
559 (name "bioawk")
560 (version "1.0")
561 (source (origin
562 (method url-fetch)
563 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
564 version ".tar.gz"))
565 (file-name (string-append name "-" version ".tar.gz"))
566 (sha256
567 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
568 (build-system gnu-build-system)
569 (inputs
570 `(("zlib" ,zlib)))
571 (native-inputs
572 `(("bison" ,bison)))
573 (arguments
574 `(#:tests? #f ; There are no tests to run.
575 ;; Bison must generate files, before other targets can build.
576 #:parallel-build? #f
577 #:phases
578 (modify-phases %standard-phases
579 (delete 'configure) ; There is no configure phase.
580 (replace 'install
581 (lambda* (#:key outputs #:allow-other-keys)
582 (let* ((out (assoc-ref outputs "out"))
583 (bin (string-append out "/bin"))
584 (man (string-append out "/share/man/man1")))
585 (mkdir-p man)
586 (copy-file "awk.1" (string-append man "/bioawk.1"))
587 (install-file "bioawk" bin)))))))
588 (home-page "https://github.com/lh3/bioawk")
589 (synopsis "AWK with bioinformatics extensions")
590 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
591support of several common biological data formats, including optionally gzip'ed
592BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
593also adds a few built-in functions and a command line option to use TAB as the
594input/output delimiter. When the new functionality is not used, bioawk is
595intended to behave exactly the same as the original BWK awk.")
596 (license license:x11)))
597
a2fb1492
RW		 598(define-public python2-pybedtools
599 (package
600 (name "python2-pybedtools")
601 (version "0.6.9")
602 (source (origin
603 (method url-fetch)
604 (uri (string-append
605 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
606 version ".tar.gz"))
607 (sha256
608 (base32
609 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
610 (build-system python-build-system)
611 (arguments `(#:python ,python-2)) ; no Python 3 support
612 (inputs
f2516de2 613 `(("python-matplotlib" ,python2-matplotlib)))
a2fb1492
RW		 614 (propagated-inputs
615 `(("bedtools" ,bedtools)
616 ("samtools" ,samtools)))
617 (native-inputs
f2516de2
HG		 618 `(("python-cython" ,python2-cython)
619 ("python-pyyaml" ,python2-pyyaml)
f3b98f4f 620 ("python-nose" ,python2-nose)))
a2fb1492
RW		 621 (home-page "https://pythonhosted.org/pybedtools/")
622 (synopsis "Python wrapper for BEDtools programs")
623 (description
624 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
625which are widely used for genomic interval manipulation or \"genome algebra\".
626pybedtools extends BEDTools by offering feature-level manipulations from with
627Python.")
628 (license license:gpl2+)))
629
9e12eba8
BW		 630(define-public python-biom-format
631 (package
632 (name "python-biom-format")
abc08cba 633 (version "2.1.6")
9e12eba8
BW		 634 (source
635 (origin
636 (method url-fetch)
637 ;; Use GitHub as source because PyPI distribution does not contain
638 ;; test data: https://github.com/biocore/biom-format/issues/693
639 (uri (string-append "https://github.com/biocore/biom-format/archive/"
640 version ".tar.gz"))
641 (file-name (string-append name "-" version ".tar.gz"))
642 (sha256
643 (base32
abc08cba 644 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
9e12eba8 645 (build-system python-build-system)
de96ea28 646 (propagated-inputs
9e12eba8
BW		 647 `(("python-numpy" ,python-numpy)
648 ("python-scipy" ,python-scipy)
649 ("python-future" ,python-future)
650 ("python-click" ,python-click)
abc08cba
BW		 651 ("python-h5py" ,python-h5py)
652 ("python-pandas" ,python-pandas)))
da5ebd10
MB		 653 (native-inputs
654 `(("python-nose" ,python-nose)))
9e12eba8
BW		 655 (home-page "http://www.biom-format.org")
656 (synopsis "Biological Observation Matrix (BIOM) format utilities")
657 (description
658 "The BIOM file format is designed to be a general-use format for
659representing counts of observations e.g. operational taxonomic units, KEGG
660orthology groups or lipid types, in one or more biological samples
661e.g. microbiome samples, genomes, metagenomes.")
662 (license license:bsd-3)
663 (properties `((python2-variant . ,(delay python2-biom-format))))))
664
665(define-public python2-biom-format
666 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
667 (package
668 (inherit base)
669 (arguments
670 `(#:phases
671 (modify-phases %standard-phases
672 ;; Do not require the unmaintained pyqi library.
673 (add-after 'unpack 'remove-pyqi
674 (lambda _
675 (substitute* "setup.py"
676 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
677 #t)))
00e10c6e 678 ,@(package-arguments base))))))
9e12eba8 679
f7283db3
RW		 680(define-public bioperl-minimal
681 (let* ((inputs `(("perl-module-build" ,perl-module-build)
682 ("perl-data-stag" ,perl-data-stag)
683 ("perl-libwww" ,perl-libwww)
684 ("perl-uri" ,perl-uri)))
685 (transitive-inputs
686 (map (compose package-name cadr)
687 (delete-duplicates
688 (concatenate
689 (map (compose package-transitive-target-inputs cadr) inputs))))))
690 (package
691 (name "bioperl-minimal")
c70271ec 692 (version "1.7.0")
f7283db3
RW		 693 (source
694 (origin
695 (method url-fetch)
c70271ec
RW		 696 (uri (string-append "https://github.com/bioperl/bioperl-live/"
697 "archive/release-"
698 (string-map (lambda (c)
699 (if (char=? c #\.)
700 #\- c)) version)
701 ".tar.gz"))
f7283db3
RW		 702 (sha256
703 (base32
c70271ec 704 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
f7283db3
RW		 705 (build-system perl-build-system)
706 (arguments
707 `(#:phases
708 (modify-phases %standard-phases
709 (add-after
710 'install 'wrap-programs
711 (lambda* (#:key outputs #:allow-other-keys)
712 ;; Make sure all executables in "bin" find the required Perl
713 ;; modules at runtime. As the PERL5LIB variable contains also
714 ;; the paths of native inputs, we pick the transitive target
715 ;; inputs from %build-inputs.
716 (let* ((out (assoc-ref outputs "out"))
717 (bin (string-append out "/bin/"))
718 (path (string-join
719 (cons (string-append out "/lib/perl5/site_perl")
720 (map (lambda (name)
721 (assoc-ref %build-inputs name))
722 ',transitive-inputs))
723 ":")))
724 (for-each (lambda (file)
725 (wrap-program file
726 `("PERL5LIB" ":" prefix (,path))))
727 (find-files bin "\\.pl$"))
728 #t))))))
729 (inputs inputs)
730 (native-inputs
731 `(("perl-test-most" ,perl-test-most)))
732 (home-page "http://search.cpan.org/dist/BioPerl")
733 (synopsis "Bioinformatics toolkit")
734 (description
735 "BioPerl is the product of a community effort to produce Perl code which
736is useful in biology. Examples include Sequence objects, Alignment objects
737and database searching objects. These objects not only do what they are
738advertised to do in the documentation, but they also interact - Alignment
739objects are made from the Sequence objects, Sequence objects have access to
740Annotation and SeqFeature objects and databases, Blast objects can be
741converted to Alignment objects, and so on. This means that the objects
742provide a coordinated and extensible framework to do computational biology.")
2f3108ad 743 (license license:perl-license))))
f7283db3 744
85c37e29
RW		 745(define-public python-biopython
746 (package
747 (name "python-biopython")
af6ce610 748 (version "1.70")
85c37e29
RW		 749 (source (origin
750 (method url-fetch)
e815c094
BW		 751 ;; use PyPi rather than biopython.org to ease updating
752 (uri (pypi-uri "biopython" version))
85c37e29
RW		 753 (sha256
754 (base32
af6ce610 755 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
85c37e29 756 (build-system python-build-system)
4ce60305
BW		 757 (arguments
758 `(#:phases
759 (modify-phases %standard-phases
760 (add-before 'check 'set-home
761 ;; Some tests require a home directory to be set.
762 (lambda _ (setenv "HOME" "/tmp") #t)))))
f22efa01 763 (propagated-inputs
85c37e29 764 `(("python-numpy" ,python-numpy)))
85c37e29
RW		 765 (home-page "http://biopython.org/")
766 (synopsis "Tools for biological computation in Python")
767 (description
768 "Biopython is a set of tools for biological computation including parsers
769for bioinformatics files into Python data structures; interfaces to common
770bioinformatics programs; a standard sequence class and tools for performing
771common operations on them; code to perform data classification; code for
772dealing with alignments; code making it easy to split up parallelizable tasks
773into separate processes; and more.")
5c31f4aa 774 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
85c37e29
RW		 775
776(define-public python2-biopython
5c31f4aa 777 (package-with-python2 python-biopython))
85c37e29 778
4b1a1528
BW		 779;; An outdated version of biopython is required for seqmagick, see
780;; https://github.com/fhcrc/seqmagick/issues/59
781;; When that issue has been resolved this package should be removed.
782(define python2-biopython-1.66
783 (package
784 (inherit python2-biopython)
785 (version "1.66")
786 (source (origin
787 (method url-fetch)
788 (uri (pypi-uri "biopython" version))
789 (sha256
790 (base32
791 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
792
985d8411
BW		 793(define-public bpp-core
794 ;; The last release was in 2014 and the recommended way to install from source
795 ;; is to clone the git repository, so we do this.
796 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
797 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
798 (package
799 (name "bpp-core")
800 (version (string-append "2.2.0-1." (string-take commit 7)))
801 (source (origin
802 (method git-fetch)
803 (uri (git-reference
804 (url "http://biopp.univ-montp2.fr/git/bpp-core")
805 (commit commit)))
806 (file-name (string-append name "-" version "-checkout"))
807 (sha256
808 (base32
809 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
810 (build-system cmake-build-system)
811 (arguments
812 `(#:parallel-build? #f))
813 (inputs
814 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
815 ; compile all of the bpp packages with GCC 5.
816 (home-page "http://biopp.univ-montp2.fr")
817 (synopsis "C++ libraries for Bioinformatics")
818 (description
819 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
820analysis, phylogenetics, molecular evolution and population genetics. It is
821Object Oriented and is designed to be both easy to use and computer efficient.
822Bio++ intends to help programmers to write computer expensive programs, by
823providing them a set of re-usable tools.")
824 (license license:cecill-c))))
825
8b5f4d57
BW		 826(define-public bpp-phyl
827 ;; The last release was in 2014 and the recommended way to install from source
828 ;; is to clone the git repository, so we do this.
829 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
830 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
831 (package
832 (name "bpp-phyl")
833 (version (string-append "2.2.0-1." (string-take commit 7)))
834 (source (origin
835 (method git-fetch)
836 (uri (git-reference
837 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
838 (commit commit)))
839 (file-name (string-append name "-" version "-checkout"))
840 (sha256
841 (base32
842 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
843 (build-system cmake-build-system)
844 (arguments
845 `(#:parallel-build? #f
846 ;; If out-of-source, test data is not copied into the build directory
847 ;; so the tests fail.
848 #:out-of-source? #f))
849 (inputs
850 `(("bpp-core" ,bpp-core)
851 ("bpp-seq" ,bpp-seq)
852 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
853 ;; modern GCC.
854 ("gcc" ,gcc-5)))
855 (home-page "http://biopp.univ-montp2.fr")
856 (synopsis "Bio++ phylogenetic Library")
857 (description
858 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
859analysis, phylogenetics, molecular evolution and population genetics. This
860library provides phylogenetics-related modules.")
861 (license license:cecill-c))))
862
159a7016
BW		 863(define-public bpp-popgen
864 ;; The last release was in 2014 and the recommended way to install from source
865 ;; is to clone the git repository, so we do this.
866 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
867 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
868 (package
869 (name "bpp-popgen")
870 (version (string-append "2.2.0-1." (string-take commit 7)))
871 (source (origin
872 (method git-fetch)
873 (uri (git-reference
874 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
875 (commit commit)))
876 (file-name (string-append name "-" version "-checkout"))
877 (sha256
878 (base32
879 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
880 (build-system cmake-build-system)
881 (arguments
882 `(#:parallel-build? #f
883 #:tests? #f)) ; There are no tests.
884 (inputs
885 `(("bpp-core" ,bpp-core)
886 ("bpp-seq" ,bpp-seq)
887 ("gcc" ,gcc-5)))
888 (home-page "http://biopp.univ-montp2.fr")
889 (synopsis "Bio++ population genetics library")
890 (description
891 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
892analysis, phylogenetics, molecular evolution and population genetics. This
893library provides population genetics-related modules.")
894 (license license:cecill-c))))
895
70f1bc05
BW		 896(define-public bpp-seq
897 ;; The last release was in 2014 and the recommended way to install from source
898 ;; is to clone the git repository, so we do this.
899 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
900 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
901 (package
902 (name "bpp-seq")
903 (version (string-append "2.2.0-1." (string-take commit 7)))
904 (source (origin
905 (method git-fetch)
906 (uri (git-reference
907 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
908 (commit commit)))
909 (file-name (string-append name "-" version "-checkout"))
910 (sha256
911 (base32
912 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
913 (build-system cmake-build-system)
914 (arguments
915 `(#:parallel-build? #f
916 ;; If out-of-source, test data is not copied into the build directory
917 ;; so the tests fail.
918 #:out-of-source? #f))
919 (inputs
920 `(("bpp-core" ,bpp-core)
921 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
922 (home-page "http://biopp.univ-montp2.fr")
923 (synopsis "Bio++ sequence library")
924 (description
925 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
926analysis, phylogenetics, molecular evolution and population genetics. This
927library provides sequence-related modules.")
928 (license license:cecill-c))))
929
db7a3444
BW		 930(define-public bppsuite
931 ;; The last release was in 2014 and the recommended way to install from source
932 ;; is to clone the git repository, so we do this.
933 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
934 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
935 (package
936 (name "bppsuite")
937 (version (string-append "2.2.0-1." (string-take commit 7)))
938 (source (origin
939 (method git-fetch)
940 (uri (git-reference
941 (url "http://biopp.univ-montp2.fr/git/bppsuite")
942 (commit commit)))
943 (file-name (string-append name "-" version "-checkout"))
944 (sha256
945 (base32
946 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
947 (build-system cmake-build-system)
948 (arguments
949 `(#:parallel-build? #f
950 #:tests? #f)) ; There are no tests.
951 (native-inputs
952 `(("groff" ,groff)
953 ("man-db" ,man-db)
954 ("texinfo" ,texinfo)))
955 (inputs
956 `(("bpp-core" ,bpp-core)
957 ("bpp-seq" ,bpp-seq)
958 ("bpp-phyl" ,bpp-phyl)
959 ("bpp-phyl" ,bpp-popgen)
960 ("gcc" ,gcc-5)))
961 (home-page "http://biopp.univ-montp2.fr")
962 (synopsis "Bioinformatics tools written with the Bio++ libraries")
963 (description
964 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
965analysis, phylogenetics, molecular evolution and population genetics. This
966package provides command line tools using the Bio++ library.")
967 (license license:cecill-c))))
968
82c370de
RW		 969(define-public blast+
970 (package
971 (name "blast+")
4732e6ee 972 (version "2.6.0")
82c370de
RW		 973 (source (origin
974 (method url-fetch)
975 (uri (string-append
976 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
977 version "/ncbi-blast-" version "+-src.tar.gz"))
978 (sha256
979 (base32
4732e6ee
BW		 980 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
981 (patches (search-patches "blast+-fix-makefile.patch"))
82c370de
RW		 982 (modules '((guix build utils)))
983 (snippet
984 '(begin
4732e6ee 985 ;; Remove bundled bzip2, zlib and pcre.
82c370de
RW		 986 (delete-file-recursively "c++/src/util/compress/bzip2")
987 (delete-file-recursively "c++/src/util/compress/zlib")
4732e6ee 988 (delete-file-recursively "c++/src/util/regexp")
82c370de
RW		 989 (substitute* "c++/src/util/compress/Makefile.in"
990 (("bzip2 zlib api") "api"))
991 ;; Remove useless msbuild directory
992 (delete-file-recursively
993 "c++/src/build-system/project_tree_builder/msbuild")
994 #t))))
995 (build-system gnu-build-system)
996 (arguments
4732e6ee 997 `(;; There are two(!) tests for this massive library, and both fail with
82c370de 998 ;; "unparsable timing stats".
82c370de
RW		 999 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1000 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1001 #:tests? #f
1002 #:out-of-source? #t
1003 #:parallel-build? #f ; not supported
1004 #:phases
1005 (modify-phases %standard-phases
1006 (add-before
1007 'configure 'set-HOME
1008 ;; $HOME needs to be set at some point during the configure phase
1009 (lambda _ (setenv "HOME" "/tmp") #t))
1010 (add-after
1011 'unpack 'enter-dir
1012 (lambda _ (chdir "c++") #t))
1013 (add-after
1014 'enter-dir 'fix-build-system
1015 (lambda _
1016 (define (which* cmd)
1017 (cond ((string=? cmd "date")
1018 ;; make call to "date" deterministic
1019 "date -d @0")
1020 ((which cmd)
1021 => identity)
1022 (else
1023 (format (current-error-port)
1024 "WARNING: Unable to find absolute path for ~s~%"
1025 cmd)
1026 #f)))
1027
1028 ;; Rewrite hardcoded paths to various tools
1029 (substitute* (append '("src/build-system/configure.ac"
1030 "src/build-system/configure"
4732e6ee 1031 "src/build-system/helpers/run_with_lock.c"
82c370de
RW		 1032 "scripts/common/impl/if_diff.sh"
1033 "scripts/common/impl/run_with_lock.sh"
1034 "src/build-system/Makefile.configurables.real"
1035 "src/build-system/Makefile.in.top"
1036 "src/build-system/Makefile.meta.gmake=no"
1037 "src/build-system/Makefile.meta.in"
1038 "src/build-system/Makefile.meta_l"
1039 "src/build-system/Makefile.meta_p"
1040 "src/build-system/Makefile.meta_r"
1041 "src/build-system/Makefile.mk.in"
1042 "src/build-system/Makefile.requirements"
1043 "src/build-system/Makefile.rules_with_autodep.in")
1044 (find-files "scripts/common/check" "\\.sh$"))
1045 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1046 (or (which* cmd) all)))
1047
1048 (substitute* (find-files "src/build-system" "^config.*")
1049 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1050 (("^PATH=.*") ""))
1051
1052 ;; rewrite "/var/tmp" in check script
1053 (substitute* "scripts/common/check/check_make_unix.sh"
1054 (("/var/tmp") "/tmp"))
1055
1056 ;; do not reset PATH
1057 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1058 (("^ *PATH=.*") "")
1059 (("action=/bin/") "action=")
1060 (("export PATH") ":"))
1061 #t))
1062 (replace
1063 'configure
1064 (lambda* (#:key inputs outputs #:allow-other-keys)
1065 (let ((out (assoc-ref outputs "out"))
1066 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1067 (include (string-append (assoc-ref outputs "include")
1068 "/include/ncbi-tools++")))
1069 ;; The 'configure' script doesn't recognize things like
1070 ;; '--enable-fast-install'.
1071 (zero? (system* "./configure.orig"
1072 (string-append "--with-build-root=" (getcwd) "/build")
1073 (string-append "--prefix=" out)
1074 (string-append "--libdir=" lib)
1075 (string-append "--includedir=" include)
1076 (string-append "--with-bz2="
1077 (assoc-ref inputs "bzip2"))
1078 (string-append "--with-z="
1079 (assoc-ref inputs "zlib"))
4732e6ee
BW		 1080 (string-append "--with-pcre="
1081 (assoc-ref inputs "pcre"))
82c370de
RW		 1082 ;; Each library is built twice by default, once
1083 ;; with "-static" in its name, and again
1084 ;; without.
1085 "--without-static"
1086 "--with-dll"))))))))
4732e6ee
BW		 1087 (outputs '("out" ; 21 MB
1088 "lib" ; 226 MB
1089 "include")) ; 33 MB
82c370de
RW		 1090 (inputs
1091 `(("bzip2" ,bzip2)
4732e6ee
BW		 1092 ("zlib" ,zlib)
1093 ("pcre" ,pcre)
1094 ("perl" ,perl)
1095 ("python" ,python-wrapper)))
82c370de
RW		 1096 (native-inputs
1097 `(("cpio" ,cpio)))
1098 (home-page "http://blast.ncbi.nlm.nih.gov")
1099 (synopsis "Basic local alignment search tool")
1100 (description
1101 "BLAST is a popular method of performing a DNA or protein sequence
1102similarity search, using heuristics to produce results quickly. It also
1103calculates an “expect value” that estimates how many matches would have
1104occurred at a given score by chance, which can aid a user in judging how much
1105confidence to have in an alignment.")
1106 ;; Most of the sources are in the public domain, with the following
1107 ;; exceptions:
1108 ;; * Expat:
1109 ;; * ./c++/include/util/bitset/
1110 ;; * ./c++/src/html/ncbi_menu*.js
1111 ;; * Boost license:
1112 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1113 ;; * LGPL 2+:
1114 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1115 ;; * ASL 2.0:
1116 ;; * ./c++/src/corelib/teamcity_*
1117 (license (list license:public-domain
1118 license:expat
1119 license:boost1.0
1120 license:lgpl2.0+
1121 license:asl2.0))))
1122
6c2b26e2
RW		 1123(define-public bless
1124 (package
1125 (name "bless")
1126 (version "1p02")
1127 (source (origin
1128 (method url-fetch)
1129 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1130 version ".tgz"))
1131 (sha256
1132 (base32
4d75e03a
RW		 1133 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1134 (modules '((guix build utils)))
6c2b26e2
RW		 1135 (snippet
1136 `(begin
1137 ;; Remove bundled boost, pigz, zlib, and .git directory
953c1223
RW		 1138 ;; FIXME: also remove bundled sources for murmurhash3 and
1139 ;; kmc once packaged.
6c2b26e2
RW		 1140 (delete-file-recursively "boost")
1141 (delete-file-recursively "pigz")
953c1223 1142 (delete-file-recursively "google-sparsehash")
6c2b26e2
RW		 1143 (delete-file-recursively "zlib")
1144 (delete-file-recursively ".git")
1145 #t))))
1146 (build-system gnu-build-system)
1147 (arguments
1148 '(#:tests? #f ;no "check" target
1149 #:make-flags
1150 (list (string-append "ZLIB="
1151 (assoc-ref %build-inputs "zlib")
1152 "/lib/libz.a")
1153 (string-append "LDFLAGS="
1154 (string-join '("-lboost_filesystem"
1155 "-lboost_system"
1156 "-lboost_iostreams"
1157 "-lz"
1158 "-fopenmp"
1159 "-std=c++11"))))
1160 #:phases
1161 (modify-phases %standard-phases
1162 (add-after 'unpack 'do-not-build-bundled-pigz
1163 (lambda* (#:key inputs outputs #:allow-other-keys)
1164 (substitute* "Makefile"
1165 (("cd pigz/pigz-2.3.3; make") ""))
1166 #t))
1167 (add-after 'unpack 'patch-paths-to-executables
1168 (lambda* (#:key inputs outputs #:allow-other-keys)
1169 (substitute* "parse_args.cpp"
1170 (("kmc_binary = .*")
1171 (string-append "kmc_binary = \""
1172 (assoc-ref outputs "out")
1173 "/bin/kmc\";"))
1174 (("pigz_binary = .*")
1175 (string-append "pigz_binary = \""
1176 (assoc-ref inputs "pigz")
1177 "/bin/pigz\";")))
1178 #t))
1179 (replace 'install
1180 (lambda* (#:key outputs #:allow-other-keys)
1181 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1182 (for-each (lambda (file)
1183 (install-file file bin))
1184 '("bless" "kmc/bin/kmc"))
1185 #t)))
1186 (delete 'configure))))
1187 (native-inputs
1188 `(("perl" ,perl)))
1189 (inputs
1190 `(("openmpi" ,openmpi)
1191 ("boost" ,boost)
953c1223 1192 ("sparsehash" ,sparsehash)
6c2b26e2
RW		 1193 ("pigz" ,pigz)
1194 ("zlib" ,zlib)))
9641a899 1195 (supported-systems '("x86_64-linux"))
3b3b60d0 1196 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
6c2b26e2
RW		 1197 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1198 (description
1199 "@dfn{Bloom-filter-based error correction solution for high-throughput
1200sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1201correction tool for genomic reads produced by @dfn{Next-generation
1202sequencing} (NGS). BLESS produces accurate correction results with much less
1203memory compared with previous solutions and is also able to tolerate a higher
1204false-positive rate. BLESS can extend reads like DNA assemblers to correct
1205errors at the end of reads.")
1206 (license license:gpl3+)))
1207
2c7ee167
RW		 1208(define-public bowtie
1209 (package
1210 (name "bowtie")
d6e63cf3 1211 (version "2.3.2")
2c7ee167
RW		 1212 (source (origin
1213 (method url-fetch)
1214 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1215 version ".tar.gz"))
f586c877 1216 (file-name (string-append name "-" version ".tar.gz"))
2c7ee167
RW		 1217 (sha256
1218 (base32
d6e63cf3 1219 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
2c7ee167
RW		 1220 (modules '((guix build utils)))
1221 (snippet
1222 '(substitute* "Makefile"
2c7ee167
RW		 1223 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1224 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
0047d26a 1225 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
2c7ee167 1226 (build-system gnu-build-system)
d6e63cf3
BW		 1227 (inputs
1228 `(("perl" ,perl)
1229 ("perl-clone" ,perl-clone)
1230 ("perl-test-deep" ,perl-test-deep)
1231 ("perl-test-simple" ,perl-test-simple)
1232 ("python" ,python-2)
1233 ("tbb" ,tbb)
1234 ("zlib" ,zlib)))
2c7ee167 1235 (arguments
0047d26a
RW		 1236 '(#:make-flags
1237 (list "allall"
1238 "WITH_TBB=1"
1239 (string-append "prefix=" (assoc-ref %outputs "out")))
2c7ee167 1240 #:phases
06e37236
BW		 1241 (modify-phases %standard-phases
1242 (delete 'configure)
1243 (replace 'check
1244 (lambda* (#:key outputs #:allow-other-keys)
1245 (zero? (system* "perl"
1246 "scripts/test/simple_tests.pl"
1247 "--bowtie2=./bowtie2"
1248 "--bowtie2-build=./bowtie2-build")))))))
2c7ee167
RW		 1249 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1250 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1251 (description
1252 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1253reads to long reference sequences. It is particularly good at aligning reads
1254of about 50 up to 100s or 1,000s of characters, and particularly good at
1255aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1256genome with an FM Index to keep its memory footprint small: for the human
1257genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1258gapped, local, and paired-end alignment modes.")
241e1221 1259 (supported-systems '("x86_64-linux"))
2c7ee167
RW		 1260 (license license:gpl3+)))
1261
94ce537e
RW		 1262(define-public tophat
1263 (package
1264 (name "tophat")
1265 (version "2.1.0")
1266 (source (origin
1267 (method url-fetch)
1268 (uri (string-append
1269 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1270 version ".tar.gz"))
1271 (sha256
1272 (base32
1273 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
fc1adab1 1274 (patches (search-patches "tophat-build-with-later-seqan.patch"))
94ce537e
RW		 1275 (modules '((guix build utils)))
1276 (snippet
1277 '(begin
1278 ;; Remove bundled SeqAn and samtools
1279 (delete-file-recursively "src/SeqAn-1.3")
1280 (delete-file-recursively "src/samtools-0.1.18")
1281 #t))))
1282 (build-system gnu-build-system)
1283 (arguments
1284 '(#:parallel-build? #f ; not supported
1285 #:phases
1286 (modify-phases %standard-phases
1287 (add-after 'unpack 'use-system-samtools
1288 (lambda* (#:key inputs #:allow-other-keys)
1289 (substitute* "src/Makefile.in"
1290 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1291 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1292 (("SAMPROG = samtools_0\\.1\\.18") "")
1293 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1294 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1295 (substitute* '("src/common.cpp"
1296 "src/tophat.py")
1297 (("samtools_0.1.18") (which "samtools")))
1298 (substitute* '("src/common.h"
1299 "src/bam2fastx.cpp")
1300 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1301 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1302 (substitute* '("src/bwt_map.h"
1303 "src/map2gtf.h"
1304 "src/align_status.h")
1305 (("#include <bam.h>") "#include <samtools/bam.h>")
1306 (("#include <sam.h>") "#include <samtools/sam.h>"))
1307 #t)))))
1308 (inputs
1309 `(("boost" ,boost)
1310 ("bowtie" ,bowtie)
1311 ("samtools" ,samtools-0.1)
1312 ("ncurses" ,ncurses)
1313 ("python" ,python-2)
1314 ("perl" ,perl)
1315 ("zlib" ,zlib)
1316 ("seqan" ,seqan)))
1317 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1318 (synopsis "Spliced read mapper for RNA-Seq data")
1319 (description
1320 "TopHat is a fast splice junction mapper for nucleotide sequence
1321reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1322mammalian-sized genomes using the ultra high-throughput short read
1323aligner Bowtie, and then analyzes the mapping results to identify
1324splice junctions between exons.")
1325 ;; TopHat is released under the Boost Software License, Version 1.0
1326 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1327 (license license:boost1.0)))
1328
9a8336d8
RW		 1329(define-public bwa
1330 (package
1331 (name "bwa")
6f141eff 1332 (version "0.7.17")
9a8336d8
RW		 1333 (source (origin
1334 (method url-fetch)
ae6e00f6
BW		 1335 (uri (string-append
1336 "https://github.com/lh3/bwa/releases/download/v"
1337 version "/bwa-" version ".tar.bz2"))
9a8336d8
RW		 1338 (sha256
1339 (base32
6f141eff 1340 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
9a8336d8
RW		 1341 (build-system gnu-build-system)
1342 (arguments
1343 '(#:tests? #f ;no "check" target
1344 #:phases
dc1d3cde
KK		 1345 (modify-phases %standard-phases
1346 (replace 'install
1347 (lambda* (#:key outputs #:allow-other-keys)
1348 (let ((bin (string-append
1349 (assoc-ref outputs "out") "/bin"))
1350 (doc (string-append
1351 (assoc-ref outputs "out") "/share/doc/bwa"))
1352 (man (string-append
1353 (assoc-ref outputs "out") "/share/man/man1")))
1354 (install-file "bwa" bin)
1355 (install-file "README.md" doc)
1356 (install-file "bwa.1" man))
1357 #t))
1358 ;; no "configure" script
1359 (delete 'configure))))
9a8336d8 1360 (inputs `(("zlib" ,zlib)))
db94f8c7
RW		 1361 ;; Non-portable SSE instructions are used so building fails on platforms
1362 ;; other than x86_64.
1363 (supported-systems '("x86_64-linux"))
9a8336d8
RW		 1364 (home-page "http://bio-bwa.sourceforge.net/")
1365 (synopsis "Burrows-Wheeler sequence aligner")
1366 (description
1367 "BWA is a software package for mapping low-divergent sequences against a
1368large reference genome, such as the human genome. It consists of three
1369algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1370designed for Illumina sequence reads up to 100bp, while the rest two for
1371longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1372features such as long-read support and split alignment, but BWA-MEM, which is
1373the latest, is generally recommended for high-quality queries as it is faster
1374and more accurate. BWA-MEM also has better performance than BWA-backtrack for
137570-100bp Illumina reads.")
1376 (license license:gpl3+)))
1377
d29150b5
RW		 1378(define-public bwa-pssm
1379 (package (inherit bwa)
1380 (name "bwa-pssm")
1381 (version "0.5.11")
1382 (source (origin
1383 (method url-fetch)
1384 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1385 "archive/" version ".tar.gz"))
1386 (file-name (string-append name "-" version ".tar.gz"))
1387 (sha256
1388 (base32
1389 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1390 (build-system gnu-build-system)
1391 (inputs
1392 `(("gdsl" ,gdsl)
1393 ("zlib" ,zlib)
1394 ("perl" ,perl)))
1395 (home-page "http://bwa-pssm.binf.ku.dk/")
1396 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1397 (description
1398 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1399the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1400existing aligners it is fast and sensitive. Unlike most other aligners,
1401however, it is also adaptible in the sense that one can direct the alignment
1402based on known biases within the data set. It is coded as a modification of
1403the original BWA alignment program and shares the genome index structure as
1404well as many of the command line options.")
1405 (license license:gpl3+)))
1406
ad641d53
RW		 1407(define-public python2-bx-python
1408 (package
1409 (name "python2-bx-python")
c1dfe8c3 1410 (version "0.7.3")
ad641d53
RW		 1411 (source (origin
1412 (method url-fetch)
c1dfe8c3 1413 (uri (pypi-uri "bx-python" version))
ad641d53
RW		 1414 (sha256
1415 (base32
c1dfe8c3 1416 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
ad641d53
RW		 1417 (modules '((guix build utils)))
1418 (snippet
1419 '(substitute* "setup.py"
1420 ;; remove dependency on outdated "distribute" module
1421 (("^from distribute_setup import use_setuptools") "")
1422 (("^use_setuptools\\(\\)") "")))))
1423 (build-system python-build-system)
1424 (arguments
1425 `(#:tests? #f ;tests fail because test data are not included
1426 #:python ,python-2))
1427 (inputs
1428 `(("python-numpy" ,python2-numpy)
1429 ("zlib" ,zlib)))
1430 (native-inputs
f3b98f4f 1431 `(("python-nose" ,python2-nose)))
ad641d53
RW		 1432 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1433 (synopsis "Tools for manipulating biological data")
1434 (description
1435 "bx-python provides tools for manipulating biological data, particularly
1436multiple sequence alignments.")
1437 (license license:expat)))
1438
55a9a8c2
RW		 1439(define-public python-pysam
1440 (package
1441 (name "python-pysam")
60739965 1442 (version "0.11.2.2")
d454640c
RW		 1443 (source (origin
1444 (method url-fetch)
f536dce5
MB		 1445 ;; Test data is missing on PyPi.
1446 (uri (string-append
1447 "https://github.com/pysam-developers/pysam/archive/v"
1448 version ".tar.gz"))
1449 (file-name (string-append name "-" version ".tar.gz"))
d454640c
RW		 1450 (sha256
1451 (base32
60739965 1452 "1cfqdxsqs3xhacns9n0271ck6wkc76px66ddjm91wfw2jxxfklvc"))
dff26b23
MB		 1453 (modules '((guix build utils)))
1454 (snippet
1455 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1456 '(delete-file-recursively "htslib"))))
55a9a8c2
RW		 1457 (build-system python-build-system)
1458 (arguments
71dbf592
RW		 1459 `(#:modules ((ice-9 ftw)
1460 (srfi srfi-26)
1461 (guix build python-build-system)
1462 (guix build utils))
1463 #:phases
397d463a
MB		 1464 (modify-phases %standard-phases
1465 (add-before 'build 'set-flags
dff26b23
MB		 1466 (lambda* (#:key inputs #:allow-other-keys)
1467 (setenv "HTSLIB_MODE" "external")
1468 (setenv "HTSLIB_LIBRARY_DIR"
1469 (string-append (assoc-ref inputs "htslib") "/lib"))
1470 (setenv "HTSLIB_INCLUDE_DIR"
1471 (string-append (assoc-ref inputs "htslib") "/include"))
397d463a
MB		 1472 (setenv "LDFLAGS" "-lncurses")
1473 (setenv "CFLAGS" "-D_CURSES_LIB=1")
f536dce5 1474 #t))
71dbf592 1475 (replace 'check
f536dce5 1476 (lambda* (#:key inputs outputs #:allow-other-keys)
71dbf592 1477 ;; Add first subdirectory of "build" directory to PYTHONPATH.
f536dce5
MB		 1478 (setenv "PYTHONPATH"
1479 (string-append
1480 (getenv "PYTHONPATH")
71dbf592
RW		 1481 ":" (getcwd) "/build/"
1482 (car (scandir "build"
e1f02f92 1483 (negate (cut string-prefix? "." <>))))))
f536dce5 1484 ;; Step out of source dir so python does not import from CWD.
71dbf592
RW		 1485 (with-directory-excursion "tests"
1486 (setenv "HOME" "/tmp")
1487 (and (zero? (system* "make" "-C" "pysam_data"))
1488 (zero? (system* "make" "-C" "cbcf_data"))
b2955e22
RW		 1489 ;; Running nosetests without explicitly asking for a
1490 ;; single process leads to a crash. Running with multiple
1491 ;; processes fails because the tests are not designed to
1492 ;; run in parallel.
31c374e0
RW		 1493
1494 ;; FIXME: tests keep timing out on some systems.
1495 ;; (zero? (system* "nosetests" "-v"
1496 ;; "--processes" "1"))
1497 )))))))
dff26b23
MB		 1498 (propagated-inputs
1499 `(("htslib" ,htslib))) ; Included from installed header files.
55a9a8c2 1500 (inputs
649e9b3b 1501 `(("ncurses" ,ncurses)
55a9a8c2 1502 ("zlib" ,zlib)))
649e9b3b
RW		 1503 (native-inputs
1504 `(("python-cython" ,python-cython)
f536dce5
MB		 1505 ;; Dependencies below are are for tests only.
1506 ("samtools" ,samtools)
1507 ("bcftools" ,bcftools)
1508 ("python-nose" ,python-nose)))
55a9a8c2
RW		 1509 (home-page "https://github.com/pysam-developers/pysam")
1510 (synopsis "Python bindings to the SAMtools C API")
1511 (description
1512 "Pysam is a Python module for reading and manipulating files in the
1513SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1514also includes an interface for tabix.")
1515 (license license:expat)))
1516
1517(define-public python2-pysam
1518 (package-with-python2 python-pysam))
1519
4db9433a
RW		 1520(define-public python-twobitreader
1521 (package
1522 (name "python-twobitreader")
044ac8d2 1523 (version "3.1.4")
4db9433a
RW		 1524 (source (origin
1525 (method url-fetch)
1526 (uri (pypi-uri "twobitreader" version))
1527 (sha256
1528 (base32
044ac8d2 1529 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
4db9433a 1530 (build-system python-build-system)
900fb8d0
LF		 1531 (arguments
1532 '(;; Tests are not distributed in the PyPi release.
1533 ;; TODO Try building from the Git repo or asking the upstream maintainer
1534 ;; to distribute the tests on PyPi.
1535 #:tests? #f))
4db9433a
RW		 1536 (native-inputs
1537 `(("python-sphinx" ,python-sphinx)))
1538 (home-page "https://github.com/benjschiller/twobitreader")
1539 (synopsis "Python library for reading .2bit files")
1540 (description
1541 "twobitreader is a Python library for reading .2bit files as used by the
1542UCSC genome browser.")
1543 (license license:artistic2.0)))
1544
1545(define-public python2-twobitreader
5c31f4aa 1546 (package-with-python2 python-twobitreader))
4db9433a 1547
f94bf198
RW		 1548(define-public python-plastid
1549 (package
1550 (name "python-plastid")
897ab082 1551 (version "0.4.8")
f94bf198
RW		 1552 (source (origin
1553 (method url-fetch)
1554 (uri (pypi-uri "plastid" version))
1555 (sha256
1556 (base32
897ab082 1557 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
f94bf198
RW		 1558 (build-system python-build-system)
1559 (arguments
1560 ;; Some test files are not included.
1561 `(#:tests? #f))
1562 (propagated-inputs
1563 `(("python-numpy" ,python-numpy)
1564 ("python-scipy" ,python-scipy)
1565 ("python-pandas" ,python-pandas)
1566 ("python-pysam" ,python-pysam)
1567 ("python-matplotlib" ,python-matplotlib)
1568 ("python-biopython" ,python-biopython)
99caa6f7
BW		 1569 ("python-twobitreader" ,python-twobitreader)
1570 ("python-termcolor" ,python-termcolor)))
f94bf198
RW		 1571 (native-inputs
1572 `(("python-cython" ,python-cython)
1573 ("python-nose" ,python-nose)))
1574 (home-page "https://github.com/joshuagryphon/plastid")
1575 (synopsis "Python library for genomic analysis")
1576 (description
1577 "plastid is a Python library for genomic analysis – in particular,
1578high-throughput sequencing data – with an emphasis on simplicity.")
1579 (license license:bsd-3)))
1580
1581(define-public python2-plastid
5c31f4aa 1582 (package-with-python2 python-plastid))
f94bf198 1583
6c1305f9
RW		 1584(define-public cd-hit
1585 (package
1586 (name "cd-hit")
ba773f65 1587 (version "4.6.8")
6c1305f9
RW		 1588 (source (origin
1589 (method url-fetch)
1590 (uri (string-append "https://github.com/weizhongli/cdhit"
1591 "/releases/download/V" version
ba773f65
BW		 1592 "/cd-hit-v" version
1593 "-2017-0621-source.tar.gz"))
6c1305f9
RW		 1594 (sha256
1595 (base32
d4735e8c 1596 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
6c1305f9
RW		 1597 (build-system gnu-build-system)
1598 (arguments
1599 `(#:tests? #f ; there are no tests
1600 #:make-flags
1601 ;; Executables are copied directly to the PREFIX.
1602 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1603 #:phases
1604 (modify-phases %standard-phases
1605 ;; No "configure" script
1606 (delete 'configure)
1607 ;; Remove sources of non-determinism
1608 (add-after 'unpack 'be-timeless
1609 (lambda _
1610 (substitute* "cdhit-utility.c++"
1611 ((" \\(built on \" __DATE__ \"\\)") ""))
1612 (substitute* "cdhit-common.c++"
1613 (("__DATE__") "\"0\"")
1614 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1615 #t))
ba773f65 1616 ;; The "install" target does not create the target directory.
6c1305f9
RW		 1617 (add-before 'install 'create-target-dir
1618 (lambda* (#:key outputs #:allow-other-keys)
1619 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1620 #t)))))
1621 (inputs
1622 `(("perl" ,perl)))
1623 (home-page "http://weizhongli-lab.org/cd-hit/")
1624 (synopsis "Cluster and compare protein or nucleotide sequences")
1625 (description
1626 "CD-HIT is a program for clustering and comparing protein or nucleotide
1627sequences. CD-HIT is designed to be fast and handle extremely large
1628databases.")
1629 ;; The manual says: "It can be copied under the GNU General Public License
1630 ;; version 2 (GPLv2)."
1631 (license license:gpl2)))
1632
810cff85
RW		 1633(define-public clipper
1634 (package
1635 (name "clipper")
433530a5 1636 (version "1.1")
810cff85
RW		 1637 (source (origin
1638 (method url-fetch)
1639 (uri (string-append
1640 "https://github.com/YeoLab/clipper/archive/"
1641 version ".tar.gz"))
9ab5ea44 1642 (file-name (string-append name "-" version ".tar.gz"))
810cff85
RW		 1643 (sha256
1644 (base32
433530a5 1645 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
810cff85
RW		 1646 (modules '((guix build utils)))
1647 (snippet
433530a5
RW		 1648 '(begin
1649 ;; remove unnecessary setup dependency
1650 (substitute* "setup.py"
1651 (("setup_requires = .*") ""))
1652 (for-each delete-file
1653 '("clipper/src/peaks.so"
1654 "clipper/src/readsToWiggle.so"))
1655 (delete-file-recursively "dist/")
1656 #t))))
810cff85
RW		 1657 (build-system python-build-system)
1658 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1659 (inputs
92971d68 1660 `(("htseq" ,python2-htseq)
810cff85
RW		 1661 ("python-pybedtools" ,python2-pybedtools)
1662 ("python-cython" ,python2-cython)
1663 ("python-scikit-learn" ,python2-scikit-learn)
1664 ("python-matplotlib" ,python2-matplotlib)
433530a5 1665 ("python-pandas" ,python2-pandas)
810cff85
RW		 1666 ("python-pysam" ,python2-pysam)
1667 ("python-numpy" ,python2-numpy)
1668 ("python-scipy" ,python2-scipy)))
1669 (native-inputs
f3b98f4f 1670 `(("python-mock" ,python2-mock) ; for tests
d281be18 1671 ("python-nose" ,python2-nose) ; for tests
f3b98f4f 1672 ("python-pytz" ,python2-pytz))) ; for tests
810cff85
RW		 1673 (home-page "https://github.com/YeoLab/clipper")
1674 (synopsis "CLIP peak enrichment recognition")
1675 (description
1676 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1677 (license license:gpl2)))
1678
6a35566d
RS		 1679(define-public codingquarry
1680 (package
1681 (name "codingquarry")
1682 (version "2.0")
1683 (source (origin
1684 (method url-fetch)
1685 (uri (string-append
1686 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1687 version ".tar.gz"))
1688 (sha256
1689 (base32
1690 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1691 (build-system gnu-build-system)
1692 (arguments
1693 '(#:tests? #f ; no "check" target
1694 #:phases
1695 (modify-phases %standard-phases
1696 (delete 'configure)
1697 (replace 'install
1698 (lambda* (#:key outputs #:allow-other-keys)
1699 (let* ((out (assoc-ref outputs "out"))
1700 (bin (string-append out "/bin"))
1701 (doc (string-append out "/share/doc/codingquarry")))
1702 (install-file "INSTRUCTIONS.pdf" doc)
1703 (copy-recursively "QuarryFiles"
1704 (string-append out "/QuarryFiles"))
1705 (install-file "CodingQuarry" bin)
1706 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1707 (inputs `(("openmpi" ,openmpi)))
1708 (native-search-paths
1709 (list (search-path-specification
1710 (variable "QUARRY_PATH")
1711 (files '("QuarryFiles")))))
1712 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1713 (synopsis "Fungal gene predictor")
1714 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1715gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1716 (home-page "https://sourceforge.net/projects/codingquarry/")
1717 (license license:gpl3+)))
1718
36742f43
RW		 1719(define-public couger
1720 (package
1721 (name "couger")
1722 (version "1.8.2")
1723 (source (origin
1724 (method url-fetch)
1725 (uri (string-append
1726 "http://couger.oit.duke.edu/static/assets/COUGER"
1727 version ".zip"))
1728 (sha256
1729 (base32
1730 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1731 (build-system gnu-build-system)
1732 (arguments
1733 `(#:tests? #f
1734 #:phases
1735 (modify-phases %standard-phases
1736 (delete 'configure)
1737 (delete 'build)
1738 (replace
1739 'install
1740 (lambda* (#:key outputs #:allow-other-keys)
f3860753
TGR		 1741 (let* ((out (assoc-ref outputs "out"))
1742 (bin (string-append out "/bin")))
36742f43 1743 (copy-recursively "src" (string-append out "/src"))
f3860753 1744 (mkdir bin)
36742f43
RW		 1745 ;; Add "src" directory to module lookup path.
1746 (substitute* "couger"
1747 (("from argparse")
1748 (string-append "import sys\nsys.path.append(\""
1749 out "\")\nfrom argparse")))
f3860753 1750 (install-file "couger" bin))
36742f43
RW		 1751 #t))
1752 (add-after
1753 'install 'wrap-program
1754 (lambda* (#:key inputs outputs #:allow-other-keys)
1755 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1756 (let* ((out (assoc-ref outputs "out"))
1757 (path (getenv "PYTHONPATH")))
1758 (wrap-program (string-append out "/bin/couger")
1759 `("PYTHONPATH" ":" prefix (,path))))
1760 #t)))))
1761 (inputs
1762 `(("python" ,python-2)
1763 ("python2-pillow" ,python2-pillow)
1764 ("python2-numpy" ,python2-numpy)
1765 ("python2-scipy" ,python2-scipy)
1766 ("python2-matplotlib" ,python2-matplotlib)))
1767 (propagated-inputs
2d7c4ae3 1768 `(("r-minimal" ,r-minimal)
36742f43
RW		 1769 ("libsvm" ,libsvm)
1770 ("randomjungle" ,randomjungle)))
1771 (native-inputs
1772 `(("unzip" ,unzip)))
1773 (home-page "http://couger.oit.duke.edu")
1774 (synopsis "Identify co-factors in sets of genomic regions")
1775 (description
1776 "COUGER can be applied to any two sets of genomic regions bound by
1777paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1778putative co-factors that provide specificity to each TF. The framework
1779determines the genomic targets uniquely-bound by each TF, and identifies a
1780small set of co-factors that best explain the in vivo binding differences
1781between the two TFs.
1782
1783COUGER uses classification algorithms (support vector machines and random
1784forests) with features that reflect the DNA binding specificities of putative
1785co-factors. The features are generated either from high-throughput TF-DNA
1786binding data (from protein binding microarray experiments), or from large
1787collections of DNA motifs.")
1788 (license license:gpl3+)))
1789
bfe3c685
RW		 1790(define-public clustal-omega
1791 (package
1792 (name "clustal-omega")
b3936f35 1793 (version "1.2.4")
bfe3c685
RW		 1794 (source (origin
1795 (method url-fetch)
b3936f35
RW		 1796 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1797 version ".tar.gz"))
bfe3c685
RW		 1798 (sha256
1799 (base32
b3936f35 1800 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
bfe3c685
RW		 1801 (build-system gnu-build-system)
1802 (inputs
1803 `(("argtable" ,argtable)))
1804 (home-page "http://www.clustal.org/omega/")
1805 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1806 (description
1807 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1808program for protein and DNA/RNA. It produces high quality MSAs and is capable
1809of handling data-sets of hundreds of thousands of sequences in reasonable
1810time.")
1811 (license license:gpl2+)))
1812
191c7101
RW		 1813(define-public crossmap
1814 (package
1815 (name "crossmap")
61d5fd03 1816 (version "0.2.1")
191c7101
RW		 1817 (source (origin
1818 (method url-fetch)
1819 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1820 version ".tar.gz"))
1821 (sha256
1822 (base32
61d5fd03
RW		 1823 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1824 ;; This patch has been sent upstream already and is available
1825 ;; for download from Sourceforge, but it has not been merged.
fc1adab1 1826 (patches (search-patches "crossmap-allow-system-pysam.patch"))
191c7101
RW		 1827 (modules '((guix build utils)))
1828 ;; remove bundled copy of pysam
1829 (snippet
1830 '(delete-file-recursively "lib/pysam"))))
1831 (build-system python-build-system)
1832 (arguments
1833 `(#:python ,python-2
1834 #:phases
dc1d3cde
KK		 1835 (modify-phases %standard-phases
1836 (add-after 'unpack 'set-env
1837 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
191c7101
RW		 1838 (inputs
1839 `(("python-numpy" ,python2-numpy)
1840 ("python-pysam" ,python2-pysam)
1841 ("zlib" ,zlib)))
1842 (native-inputs
1843 `(("python-cython" ,python2-cython)
f3b98f4f 1844 ("python-nose" ,python2-nose)))
191c7101
RW		 1845 (home-page "http://crossmap.sourceforge.net/")
1846 (synopsis "Convert genome coordinates between assemblies")
1847 (description
1848 "CrossMap is a program for conversion of genome coordinates or annotation
1849files between different genome assemblies. It supports most commonly used
1850file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1851 (license license:gpl2+)))
1852
8e913213
RW		 1853(define-public cutadapt
1854 (package
1855 (name "cutadapt")
0af4df7e 1856 (version "1.14")
8e913213
RW		 1857 (source (origin
1858 (method url-fetch)
1859 (uri (string-append
1860 "https://github.com/marcelm/cutadapt/archive/v"
1861 version ".tar.gz"))
1862 (file-name (string-append name "-" version ".tar.gz"))
1863 (sha256
1864 (base32
0af4df7e 1865 "16gbpiwy4m48vq2h5wqar3i8vr6vcj9gcl2qvqim19x6ya9dp8kd"))))
8e913213
RW		 1866 (build-system python-build-system)
1867 (arguments
33d5b246
TGR		 1868 `(#:phases
1869 (modify-phases %standard-phases
1870 ;; The tests must be run after installation.
1871 (delete 'check)
1872 (add-after 'install 'check
1873 (lambda* (#:key inputs outputs #:allow-other-keys)
1874 (setenv "PYTHONPATH"
1875 (string-append
1876 (getenv "PYTHONPATH")
1877 ":" (assoc-ref outputs "out")
1878 "/lib/python"
1879 (string-take (string-take-right
1880 (assoc-ref inputs "python") 5) 3)
1881 "/site-packages"))
1882 (zero? (system* "nosetests" "-P" "tests")))))))
1f94bff2
TGR		 1883 (inputs
1884 `(("python-xopen" ,python-xopen)))
8e913213
RW		 1885 (native-inputs
1886 `(("python-cython" ,python-cython)
f3b98f4f 1887 ("python-nose" ,python-nose)))
0c6c9c00 1888 (home-page "https://cutadapt.readthedocs.io/en/stable/")
8e913213
RW		 1889 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1890 (description
1891 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1892other types of unwanted sequence from high-throughput sequencing reads.")
1893 (license license:expat)))
1894
1baee943
RW		 1895(define-public libbigwig
1896 (package
1897 (name "libbigwig")
1898 (version "0.1.4")
1899 (source (origin
1900 (method url-fetch)
1901 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1902 "archive/" version ".tar.gz"))
1903 (file-name (string-append name "-" version ".tar.gz"))
1904 (sha256
1905 (base32
1906 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1907 (build-system gnu-build-system)
1908 (arguments
1909 `(#:test-target "test"
1910 #:make-flags
1911 (list "CC=gcc"
1912 (string-append "prefix=" (assoc-ref %outputs "out")))
1913 #:phases
1914 (modify-phases %standard-phases
1915 (delete 'configure)
1916 (add-before 'check 'disable-curl-test
1917 (lambda _
1918 (substitute* "Makefile"
1919 (("./test/testRemote.*") ""))
1920 #t))
1921 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1922 ;; there has not yet been a release containing this change.
1923 (add-before 'install 'create-target-dirs
1924 (lambda* (#:key outputs #:allow-other-keys)
1925 (let ((out (assoc-ref outputs "out")))
1926 (mkdir-p (string-append out "/lib"))
1927 (mkdir-p (string-append out "/include"))
1928 #t))))))
1929 (inputs
1930 `(("zlib" ,zlib)
1931 ("curl" ,curl)))
1932 (native-inputs
1933 `(("doxygen" ,doxygen)))
1934 (home-page "https://github.com/dpryan79/libBigWig")
1935 (synopsis "C library for handling bigWig files")
1936 (description
1937 "This package provides a C library for parsing local and remote BigWig
1938files.")
1939 (license license:expat)))
1940
69e0e03c
RW		 1941(define-public python-pybigwig
1942 (package
1943 (name "python-pybigwig")
1944 (version "0.2.5")
1945 (source (origin
1946 (method url-fetch)
1947 (uri (pypi-uri "pyBigWig" version))
1948 (sha256
1949 (base32
1950 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1951 (modules '((guix build utils)))
1952 (snippet
1953 '(begin
1954 ;; Delete bundled libBigWig sources
1955 (delete-file-recursively "libBigWig")))))
1956 (build-system python-build-system)
1957 (arguments
1958 `(#:phases
1959 (modify-phases %standard-phases
1960 (add-after 'unpack 'link-with-libBigWig
1961 (lambda* (#:key inputs #:allow-other-keys)
1962 (substitute* "setup.py"
1963 (("libs=\\[") "libs=[\"BigWig\", "))
1964 #t)))))
1965 (inputs
1966 `(("libbigwig" ,libbigwig)
1967 ("zlib" ,zlib)
1968 ("curl" ,curl)))
1969 (home-page "https://github.com/dpryan79/pyBigWig")
1970 (synopsis "Access bigWig files in Python using libBigWig")
1971 (description
1972 "This package provides Python bindings to the libBigWig library for
1973accessing bigWig files.")
1974 (license license:expat)))
1975
1976(define-public python2-pybigwig
5c31f4aa 1977 (package-with-python2 python-pybigwig))
69e0e03c 1978
ec2a67de
BW		 1979(define-public python-dendropy
1980 (package
1981 (name "python-dendropy")
25d84d31 1982 (version "4.2.0")
ec2a67de
BW		 1983 (source
1984 (origin
1985 (method url-fetch)
1986 (uri (pypi-uri "DendroPy" version))
1987 (sha256
1988 (base32
1885bb0c
RW		 1989 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1990 (patches (search-patches "python-dendropy-fix-tests.patch"))))
ec2a67de
BW		 1991 (build-system python-build-system)
1992 (home-page "http://packages.python.org/DendroPy/")
1993 (synopsis "Library for phylogenetics and phylogenetic computing")
1994 (description
1995 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1996writing, simulation, processing and manipulation of phylogenetic
1997trees (phylogenies) and characters.")
1998 (license license:bsd-3)
1999 (properties `((python2-variant . ,(delay python2-dendropy))))))
2000
2001(define-public python2-dendropy
2002 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2003 (package
2004 (inherit base)
9602e3cc
BW		 2005 (arguments
2006 `(#:python ,python-2
2007 #:phases
2008 (modify-phases %standard-phases
2009 (replace 'check
2010 ;; There is currently a test failure that only happens on some
2011 ;; systems, and only using "setup.py test"
2012 (lambda _ (zero? (system* "nosetests")))))))
f3b98f4f 2013 (native-inputs `(("python2-nose" ,python2-nose)
ec2a67de
BW		 2014 ,@(package-native-inputs base))))))
2015
eb2200f3
RW		 2016(define-public python-py2bit
2017 (package
2018 (name "python-py2bit")
2019 (version "0.2.1")
2020 (source
2021 (origin
2022 (method url-fetch)
2023 (uri (pypi-uri "py2bit" version))
2024 (sha256
2025 (base32
2026 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2027 (build-system python-build-system)
2028 (home-page "https://github.com/dpryan79/py2bit")
2029 (synopsis "Access 2bit files using lib2bit")
2030 (description
2031 "This package provides Python bindings for lib2bit to access 2bit files
2032with Python.")
2033 (license license:expat)))
ec2a67de 2034
1921b1de
RW		 2035(define-public deeptools
2036 (package
2037 (name "deeptools")
fed72008 2038 (version "2.5.1")
1921b1de
RW		 2039 (source (origin
2040 (method url-fetch)
3acb8c85
RW		 2041 (uri (string-append "https://github.com/fidelram/deepTools/"
2042 "archive/" version ".tar.gz"))
1921b1de
RW		 2043 (file-name (string-append name "-" version ".tar.gz"))
2044 (sha256
2045 (base32
fed72008 2046 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
1921b1de 2047 (build-system python-build-system)
14bda1ff 2048 (inputs
fed72008
RW		 2049 `(("python-scipy" ,python-scipy)
2050 ("python-numpy" ,python-numpy)
2051 ("python-numpydoc" ,python-numpydoc)
2052 ("python-matplotlib" ,python-matplotlib)
2053 ("python-pysam" ,python-pysam)
2054 ("python-py2bit" ,python-py2bit)
2055 ("python-pybigwig" ,python-pybigwig)))
1921b1de 2056 (native-inputs
fed72008
RW		 2057 `(("python-mock" ,python-mock) ;for tests
2058 ("python-nose" ,python-nose) ;for tests
2059 ("python-pytz" ,python-pytz))) ;for tests
1921b1de
RW		 2060 (home-page "https://github.com/fidelram/deepTools")
2061 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2062 (description
2063 "DeepTools addresses the challenge of handling the large amounts of data
2064that are now routinely generated from DNA sequencing centers. To do so,
2065deepTools contains useful modules to process the mapped reads data to create
2066coverage files in standard bedGraph and bigWig file formats. By doing so,
2067deepTools allows the creation of normalized coverage files or the comparison
2068between two files (for example, treatment and control). Finally, using such
2069normalized and standardized files, multiple visualizations can be created to
2070identify enrichments with functional annotations of the genome.")
2071 (license license:gpl3+)))
2072
684bf7c7
BW		 2073(define-public diamond
2074 (package
2075 (name "diamond")
4e0b3583 2076 (version "0.9.14")
684bf7c7
BW		 2077 (source (origin
2078 (method url-fetch)
2079 (uri (string-append
2080 "https://github.com/bbuchfink/diamond/archive/v"
2081 version ".tar.gz"))
2082 (file-name (string-append name "-" version ".tar.gz"))
2083 (sha256
2084 (base32
4e0b3583 2085 "07li3chjdna0wjyh680j3bhwiqh1fbfq9dy9jxxs82mc0rw0m1yy"))))
122395f9 2086 (build-system cmake-build-system)
684bf7c7 2087 (arguments
7c544991
BW		 2088 '(#:tests? #f ; no "check" target
2089 #:phases
2090 (modify-phases %standard-phases
2091 (add-after 'unpack 'remove-native-compilation
2092 (lambda _
2093 (substitute* "CMakeLists.txt" (("-march=native") ""))
2094 #t)))))
684bf7c7 2095 (inputs
122395f9 2096 `(("zlib" ,zlib)))
684bf7c7
BW		 2097 (home-page "https://github.com/bbuchfink/diamond")
2098 (synopsis "Accelerated BLAST compatible local sequence aligner")
2099 (description
2100 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2101translated DNA query sequences against a protein reference database (BLASTP
2102and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2103reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2104data and settings.")
ef81341f 2105 (license license:agpl3+)))
684bf7c7 2106
97b9da68
RW		 2107(define-public discrover
2108 (package
2109 (name "discrover")
2110 (version "1.6.0")
2111 (source
2112 (origin
2113 (method url-fetch)
2114 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2115 version ".tar.gz"))
2116 (file-name (string-append name "-" version ".tar.gz"))
2117 (sha256
2118 (base32
2119 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2120 (build-system cmake-build-system)
fa702e1a
RW		 2121 (arguments
2122 `(#:tests? #f ; there are no tests
2123 #:phases
2124 (modify-phases %standard-phases
2125 (add-after 'unpack 'add-missing-includes
2126 (lambda _
2127 (substitute* "src/executioninformation.hpp"
2128 (("#define EXECUTIONINFORMATION_HPP" line)
2129 (string-append line "\n#include <random>")))
2130 (substitute* "src/plasma/fasta.hpp"
2131 (("#define FASTA_HPP" line)
2132 (string-append line "\n#include <random>")))
2133 #t)))))
97b9da68
RW		 2134 (inputs
2135 `(("boost" ,boost)
2136 ("cairo" ,cairo)))
2137 (native-inputs
2138 `(("texlive" ,texlive)
2139 ("imagemagick" ,imagemagick)))
2140 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2141 (synopsis "Discover discriminative nucleotide sequence motifs")
2142 (description "Discrover is a motif discovery method to find binding sites
2143of nucleic acid binding proteins.")
2144 (license license:gpl3+)))
2145
6619f9c7
RW		 2146(define-public eigensoft
2147 (let ((revision "1")
2148 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2149 (package
2150 (name "eigensoft")
2151 (version (string-append "6.1.2-"
2152 revision "."
2153 (string-take commit 9)))
2154 (source
2155 (origin
2156 (method git-fetch)
2157 (uri (git-reference
2158 (url "https://github.com/DReichLab/EIG.git")
2159 (commit commit)))
2160 (file-name (string-append "eigensoft-" commit "-checkout"))
2161 (sha256
2162 (base32
2163 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2164 (modules '((guix build utils)))
2165 ;; Remove pre-built binaries.
2166 (snippet '(begin
2167 (delete-file-recursively "bin")
2168 (mkdir "bin")
2169 #t))))
2170 (build-system gnu-build-system)
2171 (arguments
2172 `(#:tests? #f ; There are no tests.
2173 #:make-flags '("CC=gcc")
2174 #:phases
2175 (modify-phases %standard-phases
2176 ;; There is no configure phase, but the Makefile is in a
2177 ;; sub-directory.
2178 (replace 'configure
2179 (lambda _
2180 (chdir "src")
2181 ;; The link flags are incomplete.
2182 (substitute* "Makefile"
2183 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2184 #t))
2185 ;; The provided install target only copies executables to
2186 ;; the "bin" directory in the build root.
2187 (add-after 'install 'actually-install
2188 (lambda* (#:key outputs #:allow-other-keys)
2189 (let* ((out (assoc-ref outputs "out"))
2190 (bin (string-append out "/bin")))
6619f9c7
RW		 2191 (for-each (lambda (file)
2192 (install-file file bin))
2193 (find-files "../bin" ".*"))
2194 #t))))))
2195 (inputs
2196 `(("gsl" ,gsl)
2197 ("lapack" ,lapack)
6619f9c7
RW		 2198 ("openblas" ,openblas)
2199 ("perl" ,perl)
2200 ("gfortran" ,gfortran "lib")))
2201 (home-page "https://github.com/DReichLab/EIG")
2202 (synopsis "Tools for population genetics")
2203 (description "The EIGENSOFT package provides tools for population
2204genetics and stratification correction. EIGENSOFT implements methods commonly
2205used in population genetics analyses such as PCA, computation of Tracy-Widom
2206statistics, and finding related individuals in structured populations. It
2207comes with a built-in plotting script and supports multiple file formats and
2208quantitative phenotypes.")
2209 ;; The license of the eigensoft tools is Expat, but since it's
2210 ;; linking with the GNU Scientific Library (GSL) the effective
2211 ;; license is the GPL.
2212 (license license:gpl3+))))
2213
365c8153
RW		 2214(define-public edirect
2215 (package
2216 (name "edirect")
83b84fa8 2217 (version "4.10")
365c8153
RW		 2218 (source (origin
2219 (method url-fetch)
83b84fa8
RW		 2220 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2221 "versions/2016-05-03/edirect.tar.gz"))
365c8153
RW		 2222 (sha256
2223 (base32
83b84fa8 2224 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
365c8153
RW		 2225 (build-system perl-build-system)
2226 (arguments
2227 `(#:tests? #f ;no "check" target
2228 #:phases
2229 (modify-phases %standard-phases
2230 (delete 'configure)
2231 (delete 'build)
2232 (replace 'install
2233 (lambda* (#:key outputs #:allow-other-keys)
2234 (let ((target (string-append (assoc-ref outputs "out")
2235 "/bin")))
2236 (mkdir-p target)
f3860753 2237 (install-file "edirect.pl" target)
365c8153
RW		 2238 #t)))
2239 (add-after
2240 'install 'wrap-program
2241 (lambda* (#:key inputs outputs #:allow-other-keys)
2242 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2243 (let* ((out (assoc-ref outputs "out"))
2244 (path (getenv "PERL5LIB")))
2245 (wrap-program (string-append out "/bin/edirect.pl")
2246 `("PERL5LIB" ":" prefix (,path)))))))))
2247 (inputs
2248 `(("perl-html-parser" ,perl-html-parser)
2249 ("perl-encode-locale" ,perl-encode-locale)
2250 ("perl-file-listing" ,perl-file-listing)
2251 ("perl-html-tagset" ,perl-html-tagset)
2252 ("perl-html-tree" ,perl-html-tree)
2253 ("perl-http-cookies" ,perl-http-cookies)
2254 ("perl-http-date" ,perl-http-date)
2255 ("perl-http-message" ,perl-http-message)
2256 ("perl-http-negotiate" ,perl-http-negotiate)
2257 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2258 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2259 ("perl-net-http" ,perl-net-http)
2260 ("perl-uri" ,perl-uri)
2261 ("perl-www-robotrules" ,perl-www-robotrules)
2262 ("perl" ,perl)))
3d51ec91 2263 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
365c8153
RW		 2264 (synopsis "Tools for accessing the NCBI's set of databases")
2265 (description
2266 "Entrez Direct (EDirect) is a method for accessing the National Center
2267for Biotechnology Information's (NCBI) set of interconnected
2268databases (publication, sequence, structure, gene, variation, expression,
2269etc.) from a terminal. Functions take search terms from command-line
2270arguments. Individual operations are combined to build multi-step queries.
2271Record retrieval and formatting normally complete the process.
2272
2273EDirect also provides an argument-driven function that simplifies the
2274extraction of data from document summaries or other results that are returned
2275in structured XML format. This can eliminate the need for writing custom
2276software to answer ad hoc questions.")
2277 (license license:public-domain)))
2278
b16728b0
BW		 2279(define-public exonerate
2280 (package
2281 (name "exonerate")
2282 (version "2.4.0")
2283 (source
2284 (origin
2285 (method url-fetch)
2286 (uri
2287 (string-append
2288 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2289 "exonerate-" version ".tar.gz"))
2290 (sha256
2291 (base32
2292 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2293 (build-system gnu-build-system)
2294 (arguments
2295 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2296 (native-inputs
2297 `(("pkg-config" ,pkg-config)))
2298 (inputs
2299 `(("glib" ,glib)))
2300 (home-page
2301 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2302 (synopsis "Generic tool for biological sequence alignment")
2303 (description
2304 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2305the alignment of sequences using a many alignment models, either exhaustive
2306dynamic programming or a variety of heuristics.")
2307 (license license:gpl3)))
2308
e4e5a4d8
RW		 2309(define-public express
2310 (package
2311 (name "express")
2312 (version "1.5.1")
2313 (source (origin
2314 (method url-fetch)
2315 (uri
2316 (string-append
2317 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2318 version "/express-" version "-src.tgz"))
2319 (sha256
2320 (base32
2321 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2322 (build-system cmake-build-system)
2323 (arguments
2324 `(#:tests? #f ;no "check" target
2325 #:phases
dc1d3cde
KK		 2326 (modify-phases %standard-phases
2327 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2328 (lambda* (#:key inputs #:allow-other-keys)
2329 (substitute* "CMakeLists.txt"
2330 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2331 "set(Boost_USE_STATIC_LIBS OFF)")
2332 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2333 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2334 (substitute* "src/CMakeLists.txt"
2335 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2336 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2337 #t)))))
e4e5a4d8
RW		 2338 (inputs
2339 `(("boost" ,boost)
2340 ("bamtools" ,bamtools)
2341 ("protobuf" ,protobuf)
2342 ("zlib" ,zlib)))
2343 (home-page "http://bio.math.berkeley.edu/eXpress")
2344 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2345 (description
2346 "eXpress is a streaming tool for quantifying the abundances of a set of
2347target sequences from sampled subsequences. Example applications include
2348transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2349analysis (from RNA-Seq), transcription factor binding quantification in
2350ChIP-Seq, and analysis of metagenomic data.")
2351 (license license:artistic2.0)))
2352
f3674b1c
BW		 2353(define-public express-beta-diversity
2354 (package
2355 (name "express-beta-diversity")
2356 (version "1.0.7")
2357 (source (origin
2358 (method url-fetch)
2359 (uri
2360 (string-append
2361 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2362 version ".tar.gz"))
2363 (file-name (string-append name "-" version ".tar.gz"))
2364 (sha256
2365 (base32
2366 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2367 (build-system gnu-build-system)
2368 (arguments
2369 `(#:phases
2370 (modify-phases %standard-phases
2371 (delete 'configure)
2372 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2373 (replace 'check
2374 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2375 "-u"))))
2376 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2377 (replace 'install
2378 (lambda* (#:key outputs #:allow-other-keys)
2379 (let ((bin (string-append (assoc-ref outputs "out")
2380 "/bin")))
2381 (mkdir-p bin)
f3860753
TGR		 2382 (install-file "scripts/convertToEBD.py" bin)
2383 (install-file "bin/ExpressBetaDiversity" bin)
f3674b1c
BW		 2384 #t))))))
2385 (inputs
2386 `(("python" ,python-2)))
2387 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2388 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2389 (description
2390 "Express Beta Diversity (EBD) calculates ecological beta diversity
2391(dissimilarity) measures between biological communities. EBD implements a
2392variety of diversity measures including those that make use of phylogenetic
2393similarity of community members.")
2394 (license license:gpl3+)))
2395
12b04cbe
BW		 2396(define-public fasttree
2397 (package
2398 (name "fasttree")
88682c9a 2399 (version "2.1.10")
12b04cbe
BW		 2400 (source (origin
2401 (method url-fetch)
2402 (uri (string-append
2403 "http://www.microbesonline.org/fasttree/FastTree-"
2404 version ".c"))
2405 (sha256
2406 (base32
88682c9a 2407 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
12b04cbe
BW		 2408 (build-system gnu-build-system)
2409 (arguments
2410 `(#:tests? #f ; no "check" target
2411 #:phases
2412 (modify-phases %standard-phases
2413 (delete 'unpack)
2414 (delete 'configure)
2415 (replace 'build
e03a5153
BW		 2416 (lambda* (#:key source #:allow-other-keys)
2417 (and (zero? (system* "gcc"
2418 "-O3"
2419 "-finline-functions"
2420 "-funroll-loops"
2421 "-Wall"
2422 "-o"
2423 "FastTree"
2424 source
2425 "-lm"))
2426 (zero? (system* "gcc"
2427 "-DOPENMP"
2428 "-fopenmp"
2429 "-O3"
2430 "-finline-functions"
2431 "-funroll-loops"
2432 "-Wall"
2433 "-o"
2434 "FastTreeMP"
2435 source
2436 "-lm")))))
12b04cbe 2437 (replace 'install
e03a5153
BW		 2438 (lambda* (#:key outputs #:allow-other-keys)
2439 (let ((bin (string-append (assoc-ref outputs "out")
2440 "/bin")))
2441 (mkdir-p bin)
f3860753
TGR		 2442 (install-file "FastTree" bin)
2443 (install-file "FastTreeMP" bin)
e03a5153 2444 #t))))))
12b04cbe
BW		 2445 (home-page "http://www.microbesonline.org/fasttree")
2446 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2447 (description
2448 "FastTree can handle alignments with up to a million of sequences in a
2449reasonable amount of time and memory. For large alignments, FastTree is
2450100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2451 (license license:gpl2+)))
2452
2127cedb
RW		 2453(define-public fastx-toolkit
2454 (package
2455 (name "fastx-toolkit")
2456 (version "0.0.14")
2457 (source (origin
2458 (method url-fetch)
2459 (uri
2460 (string-append
2461 "https://github.com/agordon/fastx_toolkit/releases/download/"
2462 version "/fastx_toolkit-" version ".tar.bz2"))
2463 (sha256
2464 (base32
2465 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2466 (build-system gnu-build-system)
2467 (inputs
2468 `(("libgtextutils" ,libgtextutils)))
2469 (native-inputs
2470 `(("pkg-config" ,pkg-config)))
2471 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2472 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2473 (description
2474 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2475FASTA/FASTQ files preprocessing.
2476
2477Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2478containing multiple short-reads sequences. The main processing of such
2479FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2480is sometimes more productive to preprocess the files before mapping the
2481sequences to the genome---manipulating the sequences to produce better mapping
2482results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2483 (license license:agpl3+)))
2484
d7678942
RW		 2485(define-public flexbar
2486 (package
2487 (name "flexbar")
2488 (version "2.5")
2489 (source (origin
2490 (method url-fetch)
2491 (uri
2492 (string-append "mirror://sourceforge/flexbar/"
2493 version "/flexbar_v" version "_src.tgz"))
2494 (sha256
2495 (base32
2496 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2497 (build-system cmake-build-system)
2498 (arguments
4ca009c0 2499 `(#:configure-flags (list
d7678942
RW		 2500 (string-append "-DFLEXBAR_BINARY_DIR="
2501 (assoc-ref %outputs "out")
2502 "/bin/"))
2503 #:phases
dc1d3cde
KK		 2504 (modify-phases %standard-phases
2505 (replace 'check
2506 (lambda* (#:key outputs #:allow-other-keys)
2507 (setenv "PATH" (string-append
2508 (assoc-ref outputs "out") "/bin:"
2509 (getenv "PATH")))
2510 (chdir "../flexbar_v2.5_src/test")
2511 (zero? (system* "bash" "flexbar_validate.sh"))))
2512 (delete 'install))))
d7678942
RW		 2513 (inputs
2514 `(("tbb" ,tbb)
2515 ("zlib" ,zlib)))
2516 (native-inputs
2517 `(("pkg-config" ,pkg-config)
2518 ("seqan" ,seqan)))
2519 (home-page "http://flexbar.sourceforge.net")
2520 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2521 (description
2522 "Flexbar preprocesses high-throughput nucleotide sequencing data
2523efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2524Moreover, trimming and filtering features are provided. Flexbar increases
2525read mapping rates and improves genome and transcriptome assemblies. It
2526supports next-generation sequencing data in fasta/q and csfasta/q format from
2527Illumina, Roche 454, and the SOLiD platform.")
2528 (license license:gpl3)))
2529
19f4554c
BW		 2530(define-public fraggenescan
2531 (package
2532 (name "fraggenescan")
74297231 2533 (version "1.30")
19f4554c
BW		 2534 (source
2535 (origin
2536 (method url-fetch)
2537 (uri
2538 (string-append "mirror://sourceforge/fraggenescan/"
2539 "FragGeneScan" version ".tar.gz"))
2540 (sha256
74297231 2541 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
19f4554c
BW		 2542 (build-system gnu-build-system)
2543 (arguments
2544 `(#:phases
2545 (modify-phases %standard-phases
2546 (delete 'configure)
2547 (add-before 'build 'patch-paths
2548 (lambda* (#:key outputs #:allow-other-keys)
2549 (let* ((out (string-append (assoc-ref outputs "out")))
2550 (share (string-append out "/share/fraggenescan/")))
2551 (substitute* "run_FragGeneScan.pl"
2552 (("system\\(\"rm")
2553 (string-append "system(\"" (which "rm")))
2554 (("system\\(\"mv")
2555 (string-append "system(\"" (which "mv")))
74297231 2556 (("\\\"awk") (string-append "\"" (which "awk")))
19f4554c
BW		 2557 ;; This script and other programs expect the training files
2558 ;; to be in the non-standard location bin/train/XXX. Change
2559 ;; this to be share/fraggenescan/train/XXX instead.
2560 (("^\\$train.file = \\$dir.*")
2561 (string-append "$train_file = \""
2562 share
2563 "train/\".$FGS_train_file;")))
2564 (substitute* "run_hmm.c"
2565 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
74297231 2566 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
19f4554c
BW		 2567 #t))
2568 (replace 'build
2569 (lambda _ (and (zero? (system* "make" "clean"))
2570 (zero? (system* "make" "fgs")))))
2571 (replace 'install
2572 (lambda* (#:key outputs #:allow-other-keys)
2573 (let* ((out (string-append (assoc-ref outputs "out")))
2574 (bin (string-append out "/bin/"))
2575 (share (string-append out "/share/fraggenescan/train")))
2576 (install-file "run_FragGeneScan.pl" bin)
2577 (install-file "FragGeneScan" bin)
19f4554c
BW		 2578 (copy-recursively "train" share))))
2579 (delete 'check)
2580 (add-after 'install 'post-install-check
2581 ;; In lieu of 'make check', run one of the examples and check the
2582 ;; output files gets created.
2583 (lambda* (#:key outputs #:allow-other-keys)
2584 (let* ((out (string-append (assoc-ref outputs "out")))
74297231
BW		 2585 (bin (string-append out "/bin/"))
2586 (frag (string-append bin "run_FragGeneScan.pl")))
2587 (and (zero? (system* frag ; Test complete genome.
19f4554c
BW		 2588 "-genome=./example/NC_000913.fna"
2589 "-out=./test2"
2590 "-complete=1"
2591 "-train=complete"))
2592 (file-exists? "test2.faa")
2593 (file-exists? "test2.ffn")
2594 (file-exists? "test2.gff")
74297231
BW		 2595 (file-exists? "test2.out")
2596 (zero? (system* ; Test incomplete sequences.
2597 frag
2598 "-genome=./example/NC_000913-fgs.ffn"
2599 "-out=out"
2600 "-complete=0"
2601 "-train=454_30")))))))))
19f4554c
BW		 2602 (inputs
2603 `(("perl" ,perl)
2604 ("python" ,python-2))) ;not compatible with python 3.
2605 (home-page "https://sourceforge.net/projects/fraggenescan/")
2606 (synopsis "Finds potentially fragmented genes in short reads")
2607 (description
2608 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2609short and error-prone DNA sequencing reads. It can also be applied to predict
2610genes in incomplete assemblies or complete genomes.")
2611 ;; GPL3+ according to private correspondense with the authors.
2612 (license license:gpl3+)))
2613
81f3e0c1
BW		 2614(define-public fxtract
2615 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2616 (package
2617 (name "fxtract")
2618 (version "2.3")
2619 (source
2620 (origin
2621 (method url-fetch)
2622 (uri (string-append
2623 "https://github.com/ctSkennerton/fxtract/archive/"
2624 version ".tar.gz"))
2625 (file-name (string-append "ctstennerton-util-"
2626 (string-take util-commit 7)
2627 "-checkout"))
2628 (sha256
2629 (base32
2630 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2631 (build-system gnu-build-system)
2632 (arguments
2633 `(#:make-flags (list
2634 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2635 "CC=gcc")
2636 #:test-target "fxtract_test"
2637 #:phases
2638 (modify-phases %standard-phases
2639 (delete 'configure)
2640 (add-before 'build 'copy-util
2641 (lambda* (#:key inputs #:allow-other-keys)
2642 (rmdir "util")
2643 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2644 #t))
2645 ;; Do not use make install as this requires additional dependencies.
2646 (replace 'install
2647 (lambda* (#:key outputs #:allow-other-keys)
2648 (let* ((out (assoc-ref outputs "out"))
2649 (bin (string-append out"/bin")))
2650 (install-file "fxtract" bin)
2651 #t))))))
2652 (inputs
2653 `(("pcre" ,pcre)
2654 ("zlib" ,zlib)))
2655 (native-inputs
2656 ;; ctskennerton-util is licensed under GPL2.
2657 `(("ctskennerton-util"
2658 ,(origin
2659 (method git-fetch)
2660 (uri (git-reference
2661 (url "https://github.com/ctSkennerton/util.git")
2662 (commit util-commit)))
2663 (file-name (string-append
2664 "ctstennerton-util-" util-commit "-checkout"))
2665 (sha256
2666 (base32
2667 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2668 (home-page "https://github.com/ctSkennerton/fxtract")
2669 (synopsis "Extract sequences from FASTA and FASTQ files")
2670 (description
2671 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2672or FASTQ) file given a subsequence. It uses a simple substring search for
2673basic tasks but can change to using POSIX regular expressions, PCRE, hash
2674lookups or multi-pattern searching as required. By default fxtract looks in
2675the sequence of each record but can also be told to look in the header,
2676comment or quality sections.")
afde1a26
BW		 2677 ;; 'util' requires SSE instructions.
2678 (supported-systems '("x86_64-linux"))
81f3e0c1
BW		 2679 (license license:expat))))
2680
2b18ad05
PP		 2681(define-public gemma
2682 (package
2683 (name "gemma")
2684 (version "0.96")
2685 (source (origin
2686 (method url-fetch)
2687 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2688 version ".tar.gz"))
2689 (file-name (string-append name "-" version ".tar.gz"))
2690 (sha256
2691 (base32
ce7e361f
EF		 2692 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2693 (patches (search-patches "gemma-intel-compat.patch"))))
2b18ad05
PP		 2694 (inputs
2695 `(("gsl" ,gsl)
2696 ("lapack" ,lapack)
2697 ("zlib" ,zlib)))
2698 (build-system gnu-build-system)
2699 (arguments
2c9232ae 2700 `(#:make-flags
ce7e361f
EF		 2701 '(,@(match (%current-system)
2702 ("x86_64-linux"
2703 '("FORCE_DYNAMIC=1"))
2704 ("i686-linux"
2705 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2706 (_
2707 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2b18ad05
PP		 2708 #:phases
2709 (modify-phases %standard-phases
2710 (delete 'configure)
2711 (add-before 'build 'bin-mkdir
07bf6929
EF		 2712 (lambda _
2713 (mkdir-p "bin")
2714 #t))
2b18ad05 2715 (replace 'install
07bf6929
EF		 2716 (lambda* (#:key outputs #:allow-other-keys)
2717 (let ((out (assoc-ref outputs "out")))
2718 (install-file "bin/gemma"
2719 (string-append
2720 out "/bin")))
2721 #t)))
2b18ad05
PP		 2722 #:tests? #f)) ; no tests included yet
2723 (home-page "https://github.com/xiangzhou/GEMMA")
2724 (synopsis "Tool for genome-wide efficient mixed model association")
2725 (description
2726 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2727standard linear mixed model resolver with application in genome-wide
2728association studies (GWAS).")
2729 (license license:gpl3)))
2730
5854f685
RW		 2731(define-public grit
2732 (package
2733 (name "grit")
2734 (version "2.0.2")
2735 (source (origin
2736 (method url-fetch)
2737 (uri (string-append
2738 "https://github.com/nboley/grit/archive/"
2739 version ".tar.gz"))
2740 (file-name (string-append name "-" version ".tar.gz"))
2741 (sha256
2742 (base32
2743 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2744 (build-system python-build-system)
2745 (arguments
2746 `(#:python ,python-2
2747 #:phases
dc1d3cde
KK		 2748 (modify-phases %standard-phases
2749 (add-after 'unpack 'generate-from-cython-sources
2750 (lambda* (#:key inputs outputs #:allow-other-keys)
2751 ;; Delete these C files to force fresh generation from pyx sources.
2752 (delete-file "grit/sparsify_support_fns.c")
2753 (delete-file "grit/call_peaks_support_fns.c")
2754 (substitute* "setup.py"
2755 (("Cython.Setup") "Cython.Build")
2756 ;; Add numpy include path to fix compilation
2757 (("pyx\", \\]")
2758 (string-append "pyx\", ], include_dirs = ['"
2759 (assoc-ref inputs "python-numpy")
2760 "/lib/python2.7/site-packages/numpy/core/include/"
2761 "']")))
2762 #t)))))
5854f685
RW		 2763 (inputs
2764 `(("python-scipy" ,python2-scipy)
2765 ("python-numpy" ,python2-numpy)
2766 ("python-pysam" ,python2-pysam)
2767 ("python-networkx" ,python2-networkx)))
2768 (native-inputs
f3b98f4f 2769 `(("python-cython" ,python2-cython)))
5854f685
RW		 2770 (home-page "http://grit-bio.org")
2771 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2772 (description
2773 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2774full length transcript models. When none of these data sources are available,
2775GRIT can be run by providing a candidate set of TES or TSS sites. In
2776addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2777also be run in quantification mode, where it uses a provided GTF file and just
2778estimates transcript expression.")
2779 (license license:gpl3+)))
2780
346a829a
RW		 2781(define-public hisat
2782 (package
2783 (name "hisat")
2784 (version "0.1.4")
2785 (source (origin
2786 (method url-fetch)
2787 (uri (string-append
2788 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2789 version "-beta-source.zip"))
2790 (sha256
2791 (base32
2792 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2793 (build-system gnu-build-system)
2794 (arguments
e58d01fa
RW		 2795 `(#:tests? #f ;no check target
2796 #:make-flags '("allall"
2797 ;; Disable unsupported `popcnt' instructions on
2798 ;; architectures other than x86_64
2799 ,@(if (string-prefix? "x86_64"
2800 (or (%current-target-system)
2801 (%current-system)))
2802 '()
2803 '("POPCNT_CAPABILITY=0")))
346a829a 2804 #:phases
dc1d3cde
KK		 2805 (modify-phases %standard-phases
2806 (add-after 'unpack 'patch-sources
2807 (lambda _
2808 ;; XXX Cannot use snippet because zip files are not supported
2809 (substitute* "Makefile"
2810 (("^CC = .*$") "CC = gcc")
2811 (("^CPP = .*$") "CPP = g++")
2812 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2813 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2814 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2815 (substitute* '("hisat-build" "hisat-inspect")
2816 (("/usr/bin/env") (which "env")))
2817 #t))
2818 (replace 'install
2819 (lambda* (#:key outputs #:allow-other-keys)
2820 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2821 (for-each (lambda (file)
2822 (install-file file bin))
2823 (find-files
2824 "."
2825 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2826 #t))
2827 (delete 'configure))))
346a829a
RW		 2828 (native-inputs
2829 `(("unzip" ,unzip)))
2830 (inputs
2831 `(("perl" ,perl)
2832 ("python" ,python)
2833 ("zlib" ,zlib)))
60af3d82
RW		 2834 ;; Non-portable SSE instructions are used so building fails on platforms
2835 ;; other than x86_64.
2836 (supported-systems '("x86_64-linux"))
346a829a
RW		 2837 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2838 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2839 (description
2840 "HISAT is a fast and sensitive spliced alignment program for mapping
2841RNA-seq reads. In addition to one global FM index that represents a whole
2842genome, HISAT uses a large set of small FM indexes that collectively cover the
2843whole genome. These small indexes (called local indexes) combined with
2844several alignment strategies enable effective alignment of RNA-seq reads, in
2845particular, reads spanning multiple exons.")
2846 (license license:gpl3+)))
2847
e84efc50
RW		 2848(define-public hisat2
2849 (package
2850 (name "hisat2")
2851 (version "2.0.5")
2852 (source
2853 (origin
2854 (method url-fetch)
2855 ;; FIXME: a better source URL is
2856 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2857 ;; "/downloads/hisat2-" version "-source.zip")
2858 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2859 ;; but it is currently unavailable.
2860 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2861 (file-name (string-append name "-" version ".tar.gz"))
2862 (sha256
2863 (base32
2864 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2865 (build-system gnu-build-system)
2866 (arguments
2867 `(#:tests? #f ; no check target
2868 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2869 #:modules ((guix build gnu-build-system)
2870 (guix build utils)
2871 (srfi srfi-26))
2872 #:phases
2873 (modify-phases %standard-phases
2874 (add-after 'unpack 'make-deterministic
2875 (lambda _
2876 (substitute* "Makefile"
2877 (("`date`") "0"))
2878 #t))
2879 (delete 'configure)
2880 (replace 'install
2881 (lambda* (#:key outputs #:allow-other-keys)
2882 (let* ((out (assoc-ref outputs "out"))
2883 (bin (string-append out "/bin/"))
2884 (doc (string-append out "/share/doc/hisat2/")))
2885 (for-each
2886 (cut install-file <> bin)
2887 (find-files "."
2888 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2889 (mkdir-p doc)
2890 (install-file "doc/manual.inc.html" doc))
2891 #t)))))
2892 (native-inputs
2893 `(("unzip" ,unzip) ; needed for archive from ftp
2894 ("perl" ,perl)
2895 ("pandoc" ,ghc-pandoc))) ; for documentation
2896 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2897 (synopsis "Graph-based alignment of genomic sequencing reads")
2898 (description "HISAT2 is a fast and sensitive alignment program for mapping
2899next-generation sequencing reads (both DNA and RNA) to a population of human
2900genomes (as well as to a single reference genome). In addition to using one
2901global @dfn{graph FM} (GFM) index that represents a population of human
2902genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2903the whole genome. These small indexes, combined with several alignment
2904strategies, enable rapid and accurate alignment of sequencing reads. This new
2905indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2906 ;; HISAT2 contains files from Bowtie2, which is released under
2907 ;; GPLv2 or later. The HISAT2 source files are released under
2908 ;; GPLv3 or later.
2909 (license license:gpl3+)))
2910
c684629f
BW		 2911(define-public hmmer
2912 (package
2913 (name "hmmer")
2914 (version "3.1b2")
79f09fa2
BW		 2915 (source
2916 (origin
2917 (method url-fetch)
2918 (uri (string-append
2919 "http://eddylab.org/software/hmmer"
9cf5f134 2920 (version-major version) "/"
79f09fa2
BW		 2921 version "/hmmer-" version ".tar.gz"))
2922 (sha256
2923 (base32
2924 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2925 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
c684629f 2926 (build-system gnu-build-system)
b3546174 2927 (native-inputs `(("perl" ,perl)))
a83e6046 2928 (home-page "http://hmmer.org/")
c684629f
BW		 2929 (synopsis "Biosequence analysis using profile hidden Markov models")
2930 (description
2931 "HMMER is used for searching sequence databases for homologs of protein
2932sequences, and for making protein sequence alignments. It implements methods
2933using probabilistic models called profile hidden Markov models (profile
2934HMMs).")
2935 (license (list license:gpl3+
2936 ;; The bundled library 'easel' is distributed
2937 ;; under The Janelia Farm Software License.
2938 (license:non-copyleft
2939 "file://easel/LICENSE"
2940 "See easel/LICENSE in the distribution.")))))
2941
85652f59
RW		 2942(define-public htseq
2943 (package
2944 (name "htseq")
92971d68 2945 (version "0.9.1")
85652f59
RW		 2946 (source (origin
2947 (method url-fetch)
75e6639f 2948 (uri (pypi-uri "HTSeq" version))
85652f59
RW		 2949 (sha256
2950 (base32
92971d68 2951 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
85652f59 2952 (build-system python-build-system)
92971d68
BW		 2953 (native-inputs
2954 `(("python-cython" ,python-cython)))
0536727e
RW		 2955 ;; Numpy needs to be propagated when htseq is used as a Python library.
2956 (propagated-inputs
92971d68 2957 `(("python-numpy" ,python-numpy)))
578b05d9 2958 (inputs
92971d68
BW		 2959 `(("python-pysam" ,python-pysam)
2960 ("python-matplotlib" ,python-matplotlib)))
85652f59
RW		 2961 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2962 (synopsis "Analysing high-throughput sequencing data with Python")
2963 (description
2964 "HTSeq is a Python package that provides infrastructure to process data
2965from high-throughput sequencing assays.")
2966 (license license:gpl3+)))
2967
92971d68
BW		 2968(define-public python2-htseq
2969 (package-with-python2 htseq))
2970
1ad15c16 2971(define-public java-htsjdk
15a3c3d4 2972 (package
1ad15c16 2973 (name "java-htsjdk")
bd94b6f8 2974 (version "2.3.0") ; last version without build dependency on gradle
15a3c3d4
RW		 2975 (source (origin
2976 (method url-fetch)
2977 (uri (string-append
2978 "https://github.com/samtools/htsjdk/archive/"
2979 version ".tar.gz"))
2980 (file-name (string-append name "-" version ".tar.gz"))
2981 (sha256
2982 (base32
bd94b6f8 2983 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
15a3c3d4 2984 (modules '((guix build utils)))
bd94b6f8
RW		 2985 (snippet
2986 ;; Delete pre-built binaries
2987 '(begin
2988 (delete-file-recursively "lib")
2989 (mkdir-p "lib")
2990 #t))))
10b4a969 2991 (build-system ant-build-system)
15a3c3d4 2992 (arguments
10b4a969 2993 `(#:tests? #f ; test require Internet access
bd94b6f8 2994 #:jdk ,icedtea-8
10b4a969
RW		 2995 #:make-flags
2996 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2997 "/share/java/htsjdk/"))
2998 #:build-target "all"
2999 #:phases
3000 (modify-phases %standard-phases
3001 ;; The build phase also installs the jars
3002 (delete 'install))))
bd94b6f8
RW		 3003 (inputs
3004 `(("java-ngs" ,java-ngs)
3005 ("java-snappy-1" ,java-snappy-1)
3006 ("java-commons-compress" ,java-commons-compress)
3007 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3008 ("java-commons-jexl-2" ,java-commons-jexl-2)
3009 ("java-xz" ,java-xz)))
3010 (native-inputs
3011 `(("java-testng" ,java-testng)))
15a3c3d4
RW		 3012 (home-page "http://samtools.github.io/htsjdk/")
3013 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3014 (description
3015 "HTSJDK is an implementation of a unified Java library for accessing
3016common file formats, such as SAM and VCF, used for high-throughput
3017sequencing (HTS) data. There are also an number of useful utilities for
3018manipulating HTS data.")
3019 (license license:expat)))
3020
d7fed31a
RW		 3021;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3022;; recent version of java-htsjdk, which depends on gradle.
3023(define-public java-picard
3024 (package
3025 (name "java-picard")
3026 (version "2.3.0")
3027 (source (origin
3028 (method git-fetch)
3029 (uri (git-reference
3030 (url "https://github.com/broadinstitute/picard.git")
3031 (commit version)))
3032 (file-name (string-append "java-picard-" version "-checkout"))
3033 (sha256
3034 (base32
3035 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3036 (modules '((guix build utils)))
3037 (snippet
3038 '(begin
3039 ;; Delete pre-built binaries.
3040 (delete-file-recursively "lib")
3041 (mkdir-p "lib")
3042 (substitute* "build.xml"
3043 ;; Remove build-time dependency on git.
3044 (("failifexecutionfails=\"true\"")
3045 "failifexecutionfails=\"false\"")
3046 ;; Use our htsjdk.
3047 (("depends=\"compile-htsjdk, ")
3048 "depends=\"")
3049 (("depends=\"compile-htsjdk-tests, ")
3050 "depends=\"")
3051 ;; Build picard-lib.jar before building picard.jar
3052 (("name=\"picard-jar\" depends=\"" line)
3053 (string-append line "picard-lib-jar, ")))
3054 #t))))
3055 (build-system ant-build-system)
3056 (arguments
3057 `(#:build-target "picard-jar"
3058 #:test-target "test"
3059 ;; Tests require jacoco:coverage.
3060 #:tests? #f
3061 #:make-flags
3062 (list (string-append "-Dhtsjdk_lib_dir="
3063 (assoc-ref %build-inputs "java-htsjdk")
3064 "/share/java/htsjdk/")
3065 "-Dhtsjdk-classes=dist/tmp"
3066 (string-append "-Dhtsjdk-version="
3067 ,(package-version java-htsjdk)))
3068 #:jdk ,icedtea-8
3069 #:phases
3070 (modify-phases %standard-phases
3071 (add-after 'unpack 'use-our-htsjdk
3072 (lambda* (#:key inputs #:allow-other-keys)
3073 (substitute* "build.xml"
3074 (("\\$\\{htsjdk\\}/lib")
3075 (string-append (assoc-ref inputs "java-htsjdk")
3076 "/share/java/htsjdk/")))
3077 #t))
3078 (add-after 'unpack 'make-test-target-independent
3079 (lambda* (#:key inputs #:allow-other-keys)
3080 (substitute* "build.xml"
3081 (("name=\"test\" depends=\"compile, ")
3082 "name=\"test\" depends=\""))
3083 #t))
3084 (replace 'install (install-jars "dist")))))
3085 (inputs
3086 `(("java-htsjdk" ,java-htsjdk)
3087 ("java-guava" ,java-guava)))
3088 (native-inputs
3089 `(("java-testng" ,java-testng)))
3090 (home-page "http://broadinstitute.github.io/picard/")
3091 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3092 (description "Picard is a set of Java command line tools for manipulating
3093high-throughput sequencing (HTS) data and formats. Picard is implemented
3094using the HTSJDK Java library to support accessing file formats that are
3095commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3096VCF.")
3097 (license license:expat)))
3098
d7f24778
RW		 3099;; This is the last version of Picard to provide net.sf.samtools
3100(define-public java-picard-1.113
3101 (package (inherit java-picard)
3102 (name "java-picard")
3103 (version "1.113")
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 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3113 (modules '((guix build utils)))
3114 (snippet
3115 '(begin
3116 ;; Delete pre-built binaries.
3117 (delete-file-recursively "lib")
3118 (mkdir-p "lib")
3119 #t))))
3120 (build-system ant-build-system)
3121 (arguments
3122 `(#:build-target "picard-jar"
3123 #:test-target "test"
3124 ;; FIXME: the class path at test time is wrong.
3125 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3126 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3127 #:tests? #f
3128 #:jdk ,icedtea-8
3129 ;; This is only used for tests.
3130 #:make-flags
3131 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3132 #:phases
3133 (modify-phases %standard-phases
3134 ;; Do not use bundled ant bzip2.
3135 (add-after 'unpack 'use-ant-bzip
3136 (lambda* (#:key inputs #:allow-other-keys)
3137 (substitute* "build.xml"
3138 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3139 (string-append (assoc-ref inputs "ant")
3140 "/lib/ant.jar")))
3141 #t))
3142 (add-after 'unpack 'make-test-target-independent
3143 (lambda* (#:key inputs #:allow-other-keys)
3144 (substitute* "build.xml"
3145 (("name=\"test\" depends=\"compile, ")
3146 "name=\"test\" depends=\"compile-tests, ")
3147 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3148 "name=\"compile\" depends=\"compile-src\""))
3149 #t))
3150 (add-after 'unpack 'fix-deflater-path
3151 (lambda* (#:key outputs #:allow-other-keys)
3152 (substitute* "src/java/net/sf/samtools/Defaults.java"
3153 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3154 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3155 (assoc-ref outputs "out")
3156 "/lib/jni/libIntelDeflater.so"
3157 "\")")))
3158 #t))
3159 ;; Build the deflater library, because we've previously deleted the
3160 ;; pre-built one. This can only be built with access to the JDK
3161 ;; sources.
3162 (add-after 'build 'build-jni
3163 (lambda* (#:key inputs #:allow-other-keys)
3164 (mkdir-p "lib/jni")
3165 (mkdir-p "jdk-src")
3166 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3167 "-xf" (assoc-ref inputs "jdk-src")))
3168 (zero? (system* "javah" "-jni"
3169 "-classpath" "classes"
3170 "-d" "lib/"
3171 "net.sf.samtools.util.zip.IntelDeflater"))
3172 (with-directory-excursion "src/c/inteldeflater"
3173 (zero? (system* "gcc" "-I../../../lib" "-I."
3174 (string-append "-I" (assoc-ref inputs "jdk")
3175 "/include/linux")
3176 "-I../../../jdk-src/src/share/native/common/"
3177 "-I../../../jdk-src/src/solaris/native/common/"
3178 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3179 (zero? (system* "gcc" "-shared"
3180 "-o" "../../../lib/jni/libIntelDeflater.so"
3181 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3182 ;; We can only build everything else after building the JNI library.
3183 (add-after 'build-jni 'build-rest
3184 (lambda* (#:key make-flags #:allow-other-keys)
3185 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3186 (add-before 'build 'set-JAVA6_HOME
3187 (lambda _
3188 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3189 #t))
3190 (replace 'install (install-jars "dist"))
3191 (add-after 'install 'install-jni-lib
3192 (lambda* (#:key outputs #:allow-other-keys)
3193 (let ((jni (string-append (assoc-ref outputs "out")
3194 "/lib/jni")))
3195 (mkdir-p jni)
3196 (install-file "lib/jni/libIntelDeflater.so" jni)
3197 #t))))))
3198 (inputs
3199 `(("java-snappy-1" ,java-snappy-1)
3200 ("java-commons-jexl-2" ,java-commons-jexl-2)
3201 ("java-cofoja" ,java-cofoja)
3202 ("ant" ,ant) ; for bzip2 support at runtime
3203 ("zlib" ,zlib)))
3204 (native-inputs
3205 `(("ant-apache-bcel" ,ant-apache-bcel)
3206 ("ant-junit" ,ant-junit)
3207 ("java-testng" ,java-testng)
3208 ("java-commons-bcel" ,java-commons-bcel)
3209 ("java-jcommander" ,java-jcommander)
3210 ("jdk" ,icedtea-8 "jdk")
3211 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3212
e7c09730
RW		 3213(define-public htslib
3214 (package
3215 (name "htslib")
4fb6d128 3216 (version "1.5")
e7c09730
RW		 3217 (source (origin
3218 (method url-fetch)
3219 (uri (string-append
3220 "https://github.com/samtools/htslib/releases/download/"
3221 version "/htslib-" version ".tar.bz2"))
3222 (sha256
3223 (base32
4fb6d128 3224 "0bcjmnbwp2bib1z1bkrp95w9v2syzdwdfqww10mkb1hxlmg52ax0"))))
e7c09730
RW		 3225 (build-system gnu-build-system)
3226 (arguments
3227 `(#:phases
3228 (modify-phases %standard-phases
3229 (add-after
3230 'unpack 'patch-tests
3231 (lambda _
3232 (substitute* "test/test.pl"
3233 (("/bin/bash") (which "bash")))
3234 #t)))))
3235 (inputs
a9e4a1e6
BW		 3236 `(("openssl" ,openssl)
3237 ("curl" ,curl)
3238 ("zlib" ,zlib)))
e7c09730
RW		 3239 (native-inputs
3240 `(("perl" ,perl)))
3241 (home-page "http://www.htslib.org")
3242 (synopsis "C library for reading/writing high-throughput sequencing data")
3243 (description
3244 "HTSlib is a C library for reading/writing high-throughput sequencing
3245data. It also provides the bgzip, htsfile, and tabix utilities.")
3246 ;; Files under cram/ are released under the modified BSD license;
3247 ;; the rest is released under the Expat license
3248 (license (list license:expat license:bsd-3))))
3249
bca2c576
BW		 3250;; This package should be removed once no packages rely upon it.
3251(define htslib-1.3
3252 (package
3253 (inherit htslib)
3254 (version "1.3.1")
3255 (source (origin
3256 (method url-fetch)
3257 (uri (string-append
3258 "https://github.com/samtools/htslib/releases/download/"
3259 version "/htslib-" version ".tar.bz2"))
3260 (sha256
3261 (base32
3262 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3263
c4325f62
RW		 3264(define-public idr
3265 (package
3266 (name "idr")
aa33cc29 3267 (version "2.0.3")
c4325f62
RW		 3268 (source (origin
3269 (method url-fetch)
3270 (uri (string-append
3271 "https://github.com/nboley/idr/archive/"
3272 version ".tar.gz"))
3273 (file-name (string-append name "-" version ".tar.gz"))
3274 (sha256
3275 (base32
aa33cc29
RW		 3276 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3277 ;; Delete generated C code.
3278 (snippet
3279 '(begin (delete-file "idr/inv_cdf.c") #t))))
c4325f62 3280 (build-system python-build-system)
aa33cc29
RW		 3281 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3282 ;; are no longer part of this package. It also asserts False, which
3283 ;; causes the tests to always fail.
3284 (arguments `(#:tests? #f))
b7a820fc 3285 (propagated-inputs
c4325f62 3286 `(("python-scipy" ,python-scipy)
b7a820fc 3287 ("python-sympy" ,python-sympy)
c4325f62
RW		 3288 ("python-numpy" ,python-numpy)
3289 ("python-matplotlib" ,python-matplotlib)))
3290 (native-inputs
f3b98f4f 3291 `(("python-cython" ,python-cython)))
c4325f62
RW		 3292 (home-page "https://github.com/nboley/idr")
3293 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3294 (description
3295 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3296to measure the reproducibility of findings identified from replicate
3297experiments and provide highly stable thresholds based on reproducibility.")
40590caf 3298 (license license:gpl2+)))
c4325f62 3299
43c565d2
RW		 3300(define-public jellyfish
3301 (package
3302 (name "jellyfish")
117d8cc4 3303 (version "2.2.7")
43c565d2
RW		 3304 (source (origin
3305 (method url-fetch)
3306 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3307 "releases/download/v" version
3308 "/jellyfish-" version ".tar.gz"))
3309 (sha256
3310 (base32
117d8cc4 3311 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
43c565d2
RW		 3312 (build-system gnu-build-system)
3313 (outputs '("out" ;for library
3314 "ruby" ;for Ruby bindings
3315 "python")) ;for Python bindings
3316 (arguments
3317 `(#:configure-flags
3318 (list (string-append "--enable-ruby-binding="
3319 (assoc-ref %outputs "ruby"))
3320 (string-append "--enable-python-binding="
3321 (assoc-ref %outputs "python")))
3322 #:phases
3323 (modify-phases %standard-phases
3324 (add-before 'check 'set-SHELL-variable
3325 (lambda _
3326 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3327 ;; to run tests.
3328 (setenv "SHELL" (which "bash"))
3329 #t)))))
3330 (native-inputs
3331 `(("bc" ,bc)
3332 ("time" ,time)
3333 ("ruby" ,ruby)
117d8cc4
RW		 3334 ("python" ,python-2)
3335 ("pkg-config" ,pkg-config)))
3336 (inputs
3337 `(("htslib" ,htslib)))
43c565d2
RW		 3338 (synopsis "Tool for fast counting of k-mers in DNA")
3339 (description
3340 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3341DNA. A k-mer is a substring of length k, and counting the occurrences of all
3342such substrings is a central step in many analyses of DNA sequence. Jellyfish
3343is a command-line program that reads FASTA and multi-FASTA files containing
3344DNA sequences. It outputs its k-mer counts in a binary format, which can be
3345translated into a human-readable text format using the @code{jellyfish dump}
3346command, or queried for specific k-mers with @code{jellyfish query}.")
3347 (home-page "http://www.genome.umd.edu/jellyfish.html")
6e8faf77
EF		 3348 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3349 (supported-systems '("x86_64-linux"))
43c565d2
RW		 3350 ;; The combined work is published under the GPLv3 or later. Individual
3351 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3352 (license (list license:gpl3+ license:expat))))
3353
94ff3157
BW		 3354(define-public khmer
3355 (package
3356 (name "khmer")
3357 (version "2.0")
3358 (source
3359 (origin
3360 (method url-fetch)
3361 (uri (pypi-uri "khmer" version))
3362 (sha256
3363 (base32
3364 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3365 (patches (search-patches "khmer-use-libraries.patch"))))
3366 (build-system python-build-system)
3367 (arguments
3368 `(#:phases
3369 (modify-phases %standard-phases
3370 (add-after 'unpack 'set-paths
3371 (lambda* (#:key inputs outputs #:allow-other-keys)
3372 ;; Delete bundled libraries.
3373 (delete-file-recursively "third-party/zlib")
3374 (delete-file-recursively "third-party/bzip2")
3375 ;; Replace bundled seqan.
3376 (let* ((seqan-all "third-party/seqan")
3377 (seqan-include (string-append
3378 seqan-all "/core/include")))
3379 (delete-file-recursively seqan-all)
3380 (copy-recursively (string-append (assoc-ref inputs "seqan")
3381 "/include/seqan")
3382 (string-append seqan-include "/seqan")))
3383 ;; We do not replace the bundled MurmurHash as the canonical
3384 ;; repository for this code 'SMHasher' is unsuitable for
3385 ;; providing a library. See
3386 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3387 #t))
3388 (add-after 'unpack 'set-cc
3389 (lambda _
3390 (setenv "CC" "gcc")
3391 #t))
3392 ;; It is simpler to test after installation.
3393 (delete 'check)
3394 (add-after 'install 'post-install-check
3395 (lambda* (#:key inputs outputs #:allow-other-keys)
3396 (let ((out (assoc-ref outputs "out")))
3397 (setenv "PATH"
3398 (string-append
3399 (getenv "PATH")
3400 ":"
3401 (assoc-ref outputs "out")
3402 "/bin"))
3403 (setenv "PYTHONPATH"
3404 (string-append
3405 (getenv "PYTHONPATH")
3406 ":"
3407 out
3408 "/lib/python"
3409 (string-take (string-take-right
3410 (assoc-ref inputs "python") 5) 3)
3411 "/site-packages"))
3412 (with-directory-excursion "build"
3413 (zero? (system* "nosetests" "khmer" "--attr"
3414 "!known_failing")))))))))
3415 (native-inputs
3416 `(("seqan" ,seqan)
3417 ("python-nose" ,python-nose)))
3418 (inputs
3419 `(("zlib" ,zlib)
3420 ("bzip2" ,bzip2)
3421 ("python-screed" ,python-screed)
cf1d5814
BW		 3422 ("python-bz2file" ,python-bz2file)
3423 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3424 ;; until the next version of khmer (likely 2.1) is released.
3425 ("gcc" ,gcc-4.9)))
94ff3157
BW		 3426 (home-page "https://khmer.readthedocs.org/")
3427 (synopsis "K-mer counting, filtering and graph traversal library")
3428 (description "The khmer software is a set of command-line tools for
3429working with DNA shotgun sequencing data from genomes, transcriptomes,
3430metagenomes and single cells. Khmer can make de novo assemblies faster, and
3431sometimes better. Khmer can also identify and fix problems with shotgun
3432data.")
8157af2e
EF		 3433 ;; When building on i686, armhf and mips64el, we get the following error:
3434 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3435 (supported-systems '("x86_64-linux"))
94ff3157
BW		 3436 (license license:bsd-3)))
3437
b9a601d9
RJ		 3438(define-public kaiju
3439 (package
3440 (name "kaiju")
3441 (version "1.5.0")
3442 (source (origin
3443 (method url-fetch)
3444 (uri (string-append
3445 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3446 version ".tar.gz"))
3447 (file-name (string-append name "-" version ".tar.gz"))
3448 (sha256
3449 (base32
3450 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3451 (build-system gnu-build-system)
3452 (arguments
3453 `(#:tests? #f ; There are no tests.
3454 #:phases
3455 (modify-phases %standard-phases
3456 (delete 'configure)
3457 (add-before 'build 'move-to-src-dir
3458 (lambda _ (chdir "src") #t))
3459 (replace 'install
3460 (lambda* (#:key inputs outputs #:allow-other-keys)
3461 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3462 (mkdir-p bin)
3463 (chdir "..")
3464 (copy-recursively "bin" bin)
3465 (copy-recursively "util" bin))
3466 #t)))))
3467 (inputs
3468 `(("perl" ,perl)))
3469 (home-page "http://kaiju.binf.ku.dk/")
3470 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3471 (description "Kaiju is a program for sensitive taxonomic classification
3472of high-throughput sequencing reads from metagenomic whole genome sequencing
3473experiments.")
3474 (license license:gpl3+)))
3475
d57e6d0f
RW		 3476(define-public macs
3477 (package
3478 (name "macs")
0d0bcaa0 3479 (version "2.1.0.20151222")
d57e6d0f
RW		 3480 (source (origin
3481 (method url-fetch)
43ec07f1 3482 (uri (pypi-uri "MACS2" version))
d57e6d0f
RW		 3483 (sha256
3484 (base32
0d0bcaa0 3485 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
d57e6d0f
RW		 3486 (build-system python-build-system)
3487 (arguments
3488 `(#:python ,python-2 ; only compatible with Python 2.7
3489 #:tests? #f)) ; no test target
3490 (inputs
3491 `(("python-numpy" ,python2-numpy)))
7bf837fd 3492 (home-page "https://github.com/taoliu/MACS/")
d57e6d0f
RW		 3493 (synopsis "Model based analysis for ChIP-Seq data")
3494 (description
3495 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3496identifying transcript factor binding sites named Model-based Analysis of
3497ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3498the significance of enriched ChIP regions and it improves the spatial
3499resolution of binding sites through combining the information of both
3500sequencing tag position and orientation.")
3501 (license license:bsd-3)))
3502
41ddebdd
BW		 3503(define-public mafft
3504 (package
3505 (name "mafft")
88eb119f 3506 (version "7.310")
41ddebdd
BW		 3507 (source (origin
3508 (method url-fetch)
3509 (uri (string-append
3510 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3511 "-without-extensions-src.tgz"))
3512 (file-name (string-append name "-" version ".tgz"))
3513 (sha256
3514 (base32
88eb119f 3515 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
41ddebdd
BW		 3516 (build-system gnu-build-system)
3517 (arguments
3518 `(#:tests? #f ; no automated tests, though there are tests in the read me
3519 #:make-flags (let ((out (assoc-ref %outputs "out")))
3520 (list (string-append "PREFIX=" out)
3521 (string-append "BINDIR="
3522 (string-append out "/bin"))))
3523 #:phases
3524 (modify-phases %standard-phases
3525 (add-after 'unpack 'enter-dir
101e8f71 3526 (lambda _ (chdir "core") #t))
41ddebdd 3527 (add-after 'enter-dir 'patch-makefile
101e8f71
BW		 3528 (lambda _
3529 ;; on advice from the MAFFT authors, there is no need to
3530 ;; distribute mafft-profile, mafft-distance, or
3531 ;; mafft-homologs.rb as they are too "specialised".
3532 (substitute* "Makefile"
3533 ;; remove mafft-homologs.rb from SCRIPTS
3534 (("^SCRIPTS = mafft mafft-homologs.rb")
3535 "SCRIPTS = mafft")
3536 ;; remove mafft-homologs from MANPAGES
3537 (("^MANPAGES = mafft.1 mafft-homologs.1")
3538 "MANPAGES = mafft.1")
3539 ;; remove mafft-distance from PROGS
3540 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3541 "PROGS = dvtditr dndfast7 dndblast sextet5")
3542 ;; remove mafft-profile from PROGS
3543 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3544 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3545 (("^rm -f mafft-profile mafft-profile.exe") "#")
3546 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3547 ;; do not install MAN pages in libexec folder
3548 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
41ddebdd 3549\\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
101e8f71 3550 #t))
02f35bb5
BW		 3551 (add-after 'enter-dir 'patch-paths
3552 (lambda* (#:key inputs #:allow-other-keys)
3553 (substitute* '("pairash.c"
3554 "mafft.tmpl")
3555 (("perl") (which "perl"))
3556 (("([\"`| ])awk" _ prefix)
3557 (string-append prefix (which "awk")))
3558 (("grep") (which "grep")))
3559 #t))
101e8f71
BW		 3560 (delete 'configure)
3561 (add-after 'install 'wrap-programs
3562 (lambda* (#:key outputs #:allow-other-keys)
3563 (let* ((out (assoc-ref outputs "out"))
3564 (bin (string-append out "/bin"))
3565 (path (string-append
3566 (assoc-ref %build-inputs "coreutils") "/bin:")))
3567 (for-each (lambda (file)
3568 (wrap-program file
3569 `("PATH" ":" prefix (,path))))
3570 (find-files bin)))
3571 #t)))))
41ddebdd 3572 (inputs
02f35bb5 3573 `(("perl" ,perl)
71461f88 3574 ("ruby" ,ruby)
02f35bb5 3575 ("gawk" ,gawk)
101e8f71
BW		 3576 ("grep" ,grep)
3577 ("coreutils" ,coreutils)))
41ddebdd
BW		 3578 (home-page "http://mafft.cbrc.jp/alignment/software/")
3579 (synopsis "Multiple sequence alignment program")
3580 (description
3581 "MAFFT offers a range of multiple alignment methods for nucleotide and
3582protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3583of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3584sequences).")
3585 (license (license:non-copyleft
3586 "http://mafft.cbrc.jp/alignment/software/license.txt"
3587 "BSD-3 with different formatting"))))
8fd790eb 3588
84be3b99
MB		 3589(define-public mash
3590 (package
3591 (name "mash")
3592 (version "1.1.1")
3593 (source (origin
3594 (method url-fetch)
3595 (uri (string-append
3596 "https://github.com/marbl/mash/archive/v"
3597 version ".tar.gz"))
3598 (file-name (string-append name "-" version ".tar.gz"))
3599 (sha256
3600 (base32
3601 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3602 (modules '((guix build utils)))
3603 (snippet
3604 ;; Delete bundled kseq.
3605 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3606 '(delete-file "src/mash/kseq.h"))))
3607 (build-system gnu-build-system)
3608 (arguments
3609 `(#:tests? #f ; No tests.
3610 #:configure-flags
3611 (list
3612 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3613 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3614 #:make-flags (list "CC=gcc")
3615 #:phases
3616 (modify-phases %standard-phases
3617 (add-after 'unpack 'fix-includes
3618 (lambda _
3619 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3620 (("^#include \"kseq\\.h\"")
3621 "#include \"htslib/kseq.h\""))
3622 #t))
d10092b8 3623 (add-after 'fix-includes 'autoconf
84be3b99
MB		 3624 (lambda _ (zero? (system* "autoconf")))))))
3625 (native-inputs
3626 `(("autoconf" ,autoconf)
3627 ;; Capnproto and htslib are statically embedded in the final
3628 ;; application. Therefore we also list their licenses, below.
3629 ("capnproto" ,capnproto)
3630 ("htslib" ,htslib)))
3631 (inputs
3632 `(("gsl" ,gsl)
3633 ("zlib" ,zlib)))
3634 (supported-systems '("x86_64-linux"))
3635 (home-page "https://mash.readthedocs.io")
3636 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3637 (description "Mash is a fast sequence distance estimator that uses the
3638MinHash algorithm and is designed to work with genomes and metagenomes in the
3639form of assemblies or reads.")
3640 (license (list license:bsd-3 ; Mash
3641 license:expat ; HTSlib and capnproto
3642 license:public-domain ; MurmurHash 3
3643 license:cpl1.0)))) ; Open Bloom Filter
3644
8fd790eb 3645(define-public metabat
f3f68a44
BW		 3646 (package
3647 (name "metabat")
25bd1fc1 3648 (version "2.12.1")
f3f68a44
BW		 3649 (source
3650 (origin
25bd1fc1
BW		 3651 (method url-fetch)
3652 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3653 version ".tar.gz"))
3654 (file-name (string-append name "-" version ".tar.gz"))
f3f68a44
BW		 3655 (sha256
3656 (base32
25bd1fc1
BW		 3657 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3658 (patches (search-patches "metabat-fix-compilation.patch"))))
9364a520 3659 (build-system scons-build-system)
8fd790eb 3660 (arguments
9364a520
AI		 3661 `(#:scons ,scons-python2
3662 #:scons-flags
3663 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3664 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3665 #:tests? #f ;; Tests are run during the build phase.
3666 #:phases
8fd790eb
BW		 3667 (modify-phases %standard-phases
3668 (add-after 'unpack 'fix-includes
45469ebe
BW		 3669 (lambda _
3670 (substitute* "src/BamUtils.h"
3671 (("^#include \"bam/bam\\.h\"")
3672 "#include \"samtools/bam.h\"")
3673 (("^#include \"bam/sam\\.h\"")
3674 "#include \"samtools/sam.h\""))
3675 (substitute* "src/KseqReader.h"
3676 (("^#include \"bam/kseq\\.h\"")
3677 "#include \"htslib/kseq.h\""))
3678 #t))
8fd790eb 3679 (add-after 'unpack 'fix-scons
f3f68a44
BW		 3680 (lambda* (#:key inputs #:allow-other-keys)
3681 (substitute* "SConstruct"
3682 (("^htslib_dir += 'samtools'")
3683 (string-append "htslib_dir = '"
3684 (assoc-ref inputs "htslib")
3685 "'"))
3686 (("^samtools_dir = 'samtools'")
3687 (string-append "samtools_dir = '"
3688 (assoc-ref inputs "samtools")
3689 "'"))
3690 (("^findStaticOrShared\\('bam', hts_lib")
3691 (string-append "findStaticOrShared('bam', '"
3692 (assoc-ref inputs "samtools")
3693 "/lib'"))
3694 ;; Do not distribute README.
3695 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
9364a520 3696 #t)))))
8fd790eb
BW		 3697 (inputs
3698 `(("zlib" ,zlib)
3699 ("perl" ,perl)
3700 ("samtools" ,samtools)
3701 ("htslib" ,htslib)
3702 ("boost" ,boost)))
8fd790eb
BW		 3703 (home-page "https://bitbucket.org/berkeleylab/metabat")
3704 (synopsis
3705 "Reconstruction of single genomes from complex microbial communities")
3706 (description
3707 "Grouping large genomic fragments assembled from shotgun metagenomic
3708sequences to deconvolute complex microbial communities, or metagenome binning,
3709enables the study of individual organisms and their interactions. MetaBAT is
3710an automated metagenome binning software, which integrates empirical
3711probabilistic distances of genome abundance and tetranucleotide frequency.")
d931a4bb
EF		 3712 ;; The source code contains inline assembly.
3713 (supported-systems '("x86_64-linux" "i686-linux"))
f3f68a44
BW		 3714 (license (license:non-copyleft "file://license.txt"
3715 "See license.txt in the distribution."))))
8fd790eb 3716
318c0aee
MB		 3717(define-public minced
3718 (package
3719 (name "minced")
3720 (version "0.2.0")
3721 (source (origin
3722 (method url-fetch)
3723 (uri (string-append
3724 "https://github.com/ctSkennerton/minced/archive/"
3725 version ".tar.gz"))
3726 (file-name (string-append name "-" version ".tar.gz"))
3727 (sha256
3728 (base32
3729 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3730 (build-system gnu-build-system)
3731 (arguments
3732 `(#:test-target "test"
3733 #:phases
3734 (modify-phases %standard-phases
3735 (delete 'configure)
3736 (add-before 'check 'fix-test
3737 (lambda _
3738 ;; Fix test for latest version.
3739 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3740 (("minced:0.1.6") "minced:0.2.0"))
3741 #t))
3742 (replace 'install ; No install target.
3743 (lambda* (#:key inputs outputs #:allow-other-keys)
3744 (let* ((out (assoc-ref outputs "out"))
3745 (bin (string-append out "/bin"))
3746 (wrapper (string-append bin "/minced")))
3747 ;; Minced comes with a wrapper script that tries to figure out where
3748 ;; it is located before running the JAR. Since these paths are known
3749 ;; to us, we build our own wrapper to avoid coreutils dependency.
3750 (install-file "minced.jar" bin)
3751 (with-output-to-file wrapper
3752 (lambda _
3753 (display
3754 (string-append
3755 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3756 (assoc-ref inputs "jre") "/bin/java -jar "
3757 bin "/minced.jar \"$@\"\n"))))
3758 (chmod wrapper #o555)))))))
3759 (native-inputs
3760 `(("jdk" ,icedtea "jdk")))
3761 (inputs
3762 `(("bash" ,bash)
3763 ("jre" ,icedtea "out")))
3764 (home-page "https://github.com/ctSkennerton/minced")
3765 (synopsis "Mining CRISPRs in Environmental Datasets")
3766 (description
3767 "MinCED is a program to find Clustered Regularly Interspaced Short
3768Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3769unassembled metagenomic reads, but is mainly designed for full genomes and
3770assembled metagenomic sequence.")
3771 (license license:gpl3+)))
3772
ddd82e0e
RW		 3773(define-public miso
3774 (package
3775 (name "miso")
ce4dfde0 3776 (version "0.5.4")
ddd82e0e
RW		 3777 (source (origin
3778 (method url-fetch)
34260a10 3779 (uri (pypi-uri "misopy" version))
ddd82e0e
RW		 3780 (sha256
3781 (base32
ce4dfde0 3782 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
ddd82e0e 3783 (modules '((guix build utils)))
ddd82e0e
RW		 3784 (snippet
3785 '(substitute* "setup.py"
0ec8b206
RW		 3786 ;; Use setuptools, or else the executables are not
3787 ;; installed.
3788 (("distutils.core") "setuptools")
3789 ;; use "gcc" instead of "cc" for compilation
ddd82e0e
RW		 3790 (("^defines")
3791 "cc.set_executables(
3792compiler='gcc',
3793compiler_so='gcc',
3794linker_exe='gcc',
3795linker_so='gcc -shared'); defines")))))
3796 (build-system python-build-system)
3797 (arguments
3798 `(#:python ,python-2 ; only Python 2 is supported
3799 #:tests? #f)) ; no "test" target
3800 (inputs
3801 `(("samtools" ,samtools)
3802 ("python-numpy" ,python2-numpy)
3803 ("python-pysam" ,python2-pysam)
3804 ("python-scipy" ,python2-scipy)
3805 ("python-matplotlib" ,python2-matplotlib)))
3806 (native-inputs
f3b98f4f
HG		 3807 `(("python-mock" ,python2-mock) ;for tests
3808 ("python-pytz" ,python2-pytz))) ;for tests
ddd82e0e
RW		 3809 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3810 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3811 (description
3812 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3813the expression level of alternatively spliced genes from RNA-Seq data, and
3814identifies differentially regulated isoforms or exons across samples. By
3815modeling the generative process by which reads are produced from isoforms in
3816RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3817that a read originated from a particular isoform.")
3818 (license license:gpl2)))
3819
324efb88
BW		 3820(define-public muscle
3821 (package
3822 (name "muscle")
3823 (version "3.8.1551")
3824 (source (origin
3825 (method url-fetch/tarbomb)
324efb88
BW		 3826 (uri (string-append
3827 "http://www.drive5.com/muscle/muscle_src_"
3828 version ".tar.gz"))
3829 (sha256
3830 (base32
3831 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3832 (build-system gnu-build-system)
3833 (arguments
3834 `(#:make-flags (list "LDLIBS = -lm")
3835 #:phases
3836 (modify-phases %standard-phases
3837 (delete 'configure)
3838 (replace 'check
3839 ;; There are no tests, so just test if it runs.
3840 (lambda _ (zero? (system* "./muscle" "-version"))))
3841 (replace 'install
3842 (lambda* (#:key outputs #:allow-other-keys)
3843 (let* ((out (assoc-ref outputs "out"))
3844 (bin (string-append out "/bin")))
3845 (install-file "muscle" bin)))))))
3846 (home-page "http://www.drive5.com/muscle")
3847 (synopsis "Multiple sequence alignment program")
3848 (description
3849 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3850program for nucleotide and protein sequences.")
3851 ;; License information found in 'muscle -h' and usage.cpp.
3852 (license license:public-domain)))
3853
99268755
BW		 3854(define-public newick-utils
3855 ;; There are no recent releases so we package from git.
3856 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3857 (package
3858 (name "newick-utils")
3859 (version (string-append "1.6-1." (string-take commit 8)))
3860 (source (origin
3861 (method git-fetch)
3862 (uri (git-reference
3863 (url "https://github.com/tjunier/newick_utils.git")
3864 (commit commit)))
3865 (file-name (string-append name "-" version "-checkout"))
3866 (sha256
3867 (base32
3868 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3869 (build-system gnu-build-system)
3870 (arguments
3871 `(#:phases
3872 (modify-phases %standard-phases
3873 (add-after 'unpack 'autoconf
3874 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3875 (inputs
3876 ;; XXX: TODO: Enable Lua and Guile bindings.
3877 ;; https://github.com/tjunier/newick_utils/issues/13
3878 `(("libxml2" ,libxml2)
3879 ("flex" ,flex)
3880 ("bison" ,bison)))
3881 (native-inputs
3882 `(("autoconf" ,autoconf)
3883 ("automake" ,automake)
3884 ("libtool" ,libtool)))
3885 (synopsis "Programs for working with newick format phylogenetic trees")
3886 (description
3887 "Newick-utils is a suite of utilities for processing phylogenetic trees
3888in Newick format. Functions include re-rooting, extracting subtrees,
3889trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3890 (home-page "https://github.com/tjunier/newick_utils")
3891 (license license:bsd-3))))
3892
1e44cf8b
BW		 3893(define-public orfm
3894 (package
3895 (name "orfm")
dfc83ead 3896 (version "0.7.1")
1e44cf8b
BW		 3897 (source (origin
3898 (method url-fetch)
3899 (uri (string-append
3900 "https://github.com/wwood/OrfM/releases/download/v"
3901 version "/orfm-" version ".tar.gz"))
3902 (sha256
3903 (base32
dfc83ead 3904 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
1e44cf8b
BW		 3905 (build-system gnu-build-system)
3906 (inputs `(("zlib" ,zlib)))
6b6f7d6a
BW		 3907 (native-inputs
3908 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3909 ("ruby-rspec" ,ruby-rspec)
3910 ("ruby" ,ruby)))
1e44cf8b
BW		 3911 (synopsis "Simple and not slow open reading frame (ORF) caller")
3912 (description
6b6f7d6a 3913 "An ORF caller finds stretches of DNA that, when translated, are not
1e44cf8b
BW		 3914interrupted by stop codons. OrfM finds and prints these ORFs.")
3915 (home-page "https://github.com/wwood/OrfM")
3916 (license license:lgpl3+)))
3917
c033f5d6
BW		 3918(define-public pplacer
3919 (let ((commit "g807f6f3"))
3920 (package
3921 (name "pplacer")
3922 ;; The commit should be updated with each version change.
3923 (version "1.1.alpha19")
3924 (source
3925 (origin
3926 (method url-fetch)
3927 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3928 version ".tar.gz"))
3929 (file-name (string-append name "-" version ".tar.gz"))
3930 (sha256
3931 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3932 (build-system ocaml-build-system)
3933 (arguments
3934 `(#:ocaml ,ocaml-4.01
3935 #:findlib ,ocaml4.01-findlib
3936 #:modules ((guix build ocaml-build-system)
3937 (guix build utils)
3938 (ice-9 ftw))
3939 #:phases
3940 (modify-phases %standard-phases
3941 (delete 'configure)
3942 (add-after 'unpack 'replace-bundled-cddlib
3943 (lambda* (#:key inputs #:allow-other-keys)
3944 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3945 (local-dir "cddlib_guix"))
3946 (mkdir local-dir)
3947 (with-directory-excursion local-dir
3948 (system* "tar" "xvf" cddlib-src))
3949 (let ((cddlib-src-folder
3950 (string-append local-dir "/"
3951 (list-ref (scandir local-dir) 2)
3952 "/lib-src")))
3953 (for-each
3954 (lambda (file)
3955 (copy-file file
3956 (string-append "cdd_src/" (basename file))))
3957 (find-files cddlib-src-folder ".*[ch]$")))
3958 #t)))
3959 (add-after 'unpack 'fix-makefile
3960 (lambda _
3961 ;; Remove system calls to 'git'.
3962 (substitute* "Makefile"
3963 (("^DESCRIPT:=pplacer-.*")
3964 (string-append
3965 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3966 (substitute* "myocamlbuild.ml"
3967 (("git describe --tags --long .*\\\" with")
3968 (string-append
3969 "echo -n v" ,version "-" ,commit "\" with")))
3970 #t))
3971 (replace 'install
3972 (lambda* (#:key outputs #:allow-other-keys)
3973 (let* ((out (assoc-ref outputs "out"))
3974 (bin (string-append out "/bin")))
3975 (copy-recursively "bin" bin))
3976 #t)))))
3977 (native-inputs
3978 `(("zlib" ,zlib)
3979 ("gsl" ,gsl)
3980 ("ocaml-ounit" ,ocaml4.01-ounit)
3981 ("ocaml-batteries" ,ocaml4.01-batteries)
3982 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3983 ("ocaml-csv" ,ocaml4.01-csv)
3984 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3985 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3986 ("ocaml-mcl" ,ocaml4.01-mcl)
3987 ("ocaml-gsl" ,ocaml4.01-gsl)
3988 ("cddlib-src" ,(package-source cddlib))))
3989 (propagated-inputs
3990 `(("pplacer-scripts" ,pplacer-scripts)))
3991 (synopsis "Phylogenetic placement of biological sequences")
3992 (description
3993 "Pplacer places query sequences on a fixed reference phylogenetic tree
3994to maximize phylogenetic likelihood or posterior probability according to a
3995reference alignment. Pplacer is designed to be fast, to give useful
3996information about uncertainty, and to offer advanced visualization and
3997downstream analysis.")
3998 (home-page "http://matsen.fhcrc.org/pplacer")
3999 (license license:gpl3))))
4000
4001;; This package is installed alongside 'pplacer'. It is a separate package so
4002;; that it can use the python-build-system for the scripts that are
4003;; distributed alongside the main OCaml binaries.
4004(define pplacer-scripts
4005 (package
4006 (inherit pplacer)
4007 (name "pplacer-scripts")
4008 (build-system python-build-system)
4009 (arguments
4010 `(#:python ,python-2
4011 #:phases
4012 (modify-phases %standard-phases
4013 (add-after 'unpack 'enter-scripts-dir
4014 (lambda _ (chdir "scripts")))
4015 (replace 'check
4016 (lambda _
4017 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4018 (add-after 'install 'wrap-executables
4019 (lambda* (#:key inputs outputs #:allow-other-keys)
4020 (let* ((out (assoc-ref outputs "out"))
4021 (bin (string-append out "/bin")))
4022 (let ((path (string-append
4023 (assoc-ref inputs "hmmer") "/bin:"
4024 (assoc-ref inputs "infernal") "/bin")))
4025 (display path)
4026 (wrap-program (string-append bin "/refpkg_align.py")
4027 `("PATH" ":" prefix (,path))))
4028 (let ((path (string-append
4029 (assoc-ref inputs "hmmer") "/bin")))
4030 (wrap-program (string-append bin "/hrefpkg_query.py")
4031 `("PATH" ":" prefix (,path)))))
4032 #t)))))
4033 (inputs
4034 `(("infernal" ,infernal)
4035 ("hmmer" ,hmmer)))
4036 (propagated-inputs
4037 `(("python-biopython" ,python2-biopython)
4038 ("taxtastic" ,taxtastic)))
4039 (synopsis "Pplacer Python scripts")))
4040
19ee9201
RW		 4041(define-public python2-pbcore
4042 (package
4043 (name "python2-pbcore")
e301bfc8 4044 (version "1.2.10")
19ee9201
RW		 4045 (source (origin
4046 (method url-fetch)
ddb83129 4047 (uri (pypi-uri "pbcore" version))
19ee9201
RW		 4048 (sha256
4049 (base32
e301bfc8 4050 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
19ee9201
RW		 4051 (build-system python-build-system)
4052 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
de5bc890 4053 (propagated-inputs
19ee9201
RW		 4054 `(("python-cython" ,python2-cython)
4055 ("python-numpy" ,python2-numpy)
4056 ("python-pysam" ,python2-pysam)
4057 ("python-h5py" ,python2-h5py)))
4058 (native-inputs
de5bc890
HG		 4059 `(("python-nose" ,python2-nose)
4060 ("python-sphinx" ,python2-sphinx)
4061 ("python-pyxb" ,python2-pyxb)))
19ee9201
RW		 4062 (home-page "http://pacificbiosciences.github.io/pbcore/")
4063 (synopsis "Library for reading and writing PacBio data files")
4064 (description
4065 "The pbcore package provides Python APIs for interacting with PacBio data
4066files and writing bioinformatics applications.")
4067 (license license:bsd-3)))
4068
c61fe02c
RW		 4069(define-public python2-warpedlmm
4070 (package
4071 (name "python2-warpedlmm")
4072 (version "0.21")
4073 (source
4074 (origin
4075 (method url-fetch)
4076 (uri (string-append
4077 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4078 version ".zip"))
4079 (sha256
4080 (base32
4081 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4082 (build-system python-build-system)
4083 (arguments
54c85e12 4084 `(#:python ,python-2)) ; requires Python 2.7
c61fe02c
RW		 4085 (propagated-inputs
4086 `(("python-scipy" ,python2-scipy)
4087 ("python-numpy" ,python2-numpy)
4088 ("python-matplotlib" ,python2-matplotlib)
4089 ("python-fastlmm" ,python2-fastlmm)
4090 ("python-pandas" ,python2-pandas)
4091 ("python-pysnptools" ,python2-pysnptools)))
4092 (native-inputs
f3b98f4f 4093 `(("python-mock" ,python2-mock)
c61fe02c
RW		 4094 ("python-nose" ,python2-nose)
4095 ("unzip" ,unzip)))
4096 (home-page "https://github.com/PMBio/warpedLMM")
4097 (synopsis "Implementation of warped linear mixed models")
4098 (description
4099 "WarpedLMM is a Python implementation of the warped linear mixed model,
4100which automatically learns an optimal warping function (or transformation) for
4101the phenotype as it models the data.")
4102 (license license:asl2.0)))
4103
2c16316e 4104(define-public pbtranscript-tofu
698bd297 4105 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
2c16316e
RW		 4106 (package
4107 (name "pbtranscript-tofu")
698bd297 4108 (version (string-append "2.2.3." (string-take commit 7)))
2c16316e
RW		 4109 (source (origin
4110 (method git-fetch)
4111 (uri (git-reference
4112 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4113 (commit commit)))
9a067efd 4114 (file-name (string-append name "-" version "-checkout"))
2c16316e
RW		 4115 (sha256
4116 (base32
9a067efd
RW		 4117 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4118 (modules '((guix build utils)))
4119 (snippet
4120 '(begin
4121 ;; remove bundled Cython sources
4122 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4123 #t))))
2c16316e
RW		 4124 (build-system python-build-system)
4125 (arguments
4126 `(#:python ,python-2
cdc2bb50
MB		 4127 ;; FIXME: Tests fail with "No such file or directory:
4128 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4129 #:tests? #f
2c16316e 4130 #:phases
9a067efd
RW		 4131 (modify-phases %standard-phases
4132 (add-after 'unpack 'enter-directory
4133 (lambda _
4134 (chdir "pbtranscript-tofu/pbtranscript/")
4135 #t))
4136 ;; With setuptools version 18.0 and later this setup.py hack causes
4137 ;; a build error, so we disable it.
4138 (add-after 'enter-directory 'patch-setuppy
4139 (lambda _
4140 (substitute* "setup.py"
4141 (("if 'setuptools.extension' in sys.modules:")
4142 "if False:"))
4143 #t)))))
2c16316e 4144 (inputs
9a067efd 4145 `(("python-numpy" ,python2-numpy)
2c16316e 4146 ("python-bx-python" ,python2-bx-python)
c5372108
RW		 4147 ("python-networkx" ,python2-networkx)
4148 ("python-scipy" ,python2-scipy)
9a067efd
RW		 4149 ("python-pbcore" ,python2-pbcore)
4150 ("python-h5py" ,python2-h5py)))
2c16316e 4151 (native-inputs
9a067efd 4152 `(("python-cython" ,python2-cython)
f3b98f4f 4153 ("python-nose" ,python2-nose)))
2c16316e
RW		 4154 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4155 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4156 (description
4157 "pbtranscript-tofu contains scripts to analyze transcriptome data
4158generated using the PacBio Iso-Seq protocol.")
4159 (license license:bsd-3))))
4160
024130d2
BW		 4161(define-public prank
4162 (package
4163 (name "prank")
4164 (version "150803")
4165 (source (origin
4166 (method url-fetch)
4167 (uri (string-append
4168 "http://wasabiapp.org/download/prank/prank.source."
4169 version ".tgz"))
4170 (sha256
4171 (base32
4172 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4173 (build-system gnu-build-system)
4174 (arguments
4175 `(#:phases
4176 (modify-phases %standard-phases
4177 (add-after 'unpack 'enter-src-dir
4178 (lambda _
4179 (chdir "src")
4180 #t))
62d00095
EF		 4181 (add-after 'unpack 'remove-m64-flag
4182 ;; Prank will build with the correct 'bit-ness' without this flag
4183 ;; and this allows building on 32-bit machines.
4184 (lambda _ (substitute* "src/Makefile"
4185 (("-m64") ""))
4186 #t))
024130d2
BW		 4187 (delete 'configure)
4188 (replace 'install
4189 (lambda* (#:key outputs #:allow-other-keys)
4190 (let* ((out (assoc-ref outputs "out"))
4191 (bin (string-append out "/bin"))
4192 (man (string-append out "/share/man/man1"))
4193 (path (string-append
4194 (assoc-ref %build-inputs "mafft") "/bin:"
4195 (assoc-ref %build-inputs "exonerate") "/bin:"
4196 (assoc-ref %build-inputs "bppsuite") "/bin")))
4197 (install-file "prank" bin)
4198 (wrap-program (string-append bin "/prank")
4199 `("PATH" ":" prefix (,path)))
4200 (install-file "prank.1" man))
4201 #t)))))
4202 (inputs
4203 `(("mafft" ,mafft)
4204 ("exonerate" ,exonerate)
4205 ("bppsuite" ,bppsuite)))
4206 (home-page "http://wasabiapp.org/software/prank/")
4207 (synopsis "Probabilistic multiple sequence alignment program")
4208 (description
4209 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4210codon and amino-acid sequences. It is based on a novel algorithm that treats
4211insertions correctly and avoids over-estimation of the number of deletion
4212events. In addition, PRANK borrows ideas from maximum likelihood methods used
4213in phylogenetics and correctly takes into account the evolutionary distances
4214between sequences. Lastly, PRANK allows for defining a potential structure
4215for sequences to be aligned and then, simultaneously with the alignment,
4216predicts the locations of structural units in the sequences.")
4217 (license license:gpl2+)))
4218
31a9d653
BW		 4219(define-public proteinortho
4220 (package
4221 (name "proteinortho")
8c864901 4222 (version "5.16b")
31a9d653
BW		 4223 (source
4224 (origin
4225 (method url-fetch)
4226 (uri
4227 (string-append
4228 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4229 version "_src.tar.gz"))
4230 (sha256
4231 (base32
8c864901 4232 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
31a9d653
BW		 4233 (build-system gnu-build-system)
4234 (arguments
4235 `(#:test-target "test"
4236 #:phases
4237 (modify-phases %standard-phases
4238 (replace 'configure
4239 ;; There is no configure script, so we modify the Makefile directly.
4240 (lambda* (#:key outputs #:allow-other-keys)
4241 (substitute* "Makefile"
4242 (("INSTALLDIR=.*")
4243 (string-append
4244 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4245 #t))
4246 (add-before 'install 'make-install-directory
4247 ;; The install directory is not created during 'make install'.
4248 (lambda* (#:key outputs #:allow-other-keys)
4249 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4250 #t))
4251 (add-after 'install 'wrap-programs
4252 (lambda* (#:key inputs outputs #:allow-other-keys)
4253 (let* ((path (getenv "PATH"))
4254 (out (assoc-ref outputs "out"))
4255 (binary (string-append out "/bin/proteinortho5.pl")))
4256 (wrap-program binary `("PATH" ":" prefix (,path))))
4257 #t)))))
4258 (inputs
4259 `(("perl" ,perl)
4260 ("python" ,python-2)
4261 ("blast+" ,blast+)))
4262 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4263 (synopsis "Detect orthologous genes across species")
4264 (description
4265 "Proteinortho is a tool to detect orthologous genes across different
4266species. For doing so, it compares similarities of given gene sequences and
4267clusters them to find significant groups. The algorithm was designed to handle
4268large-scale data and can be applied to hundreds of species at once.")
4269 (license license:gpl2+)))
4270
846e3409
RW		 4271(define-public pyicoteo
4272 (package
4273 (name "pyicoteo")
4274 (version "2.0.7")
4275 (source
4276 (origin
4277 (method url-fetch)
4278 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4279 "pyicoteo/get/v" version ".tar.bz2"))
4280 (file-name (string-append name "-" version ".tar.bz2"))
4281 (sha256
4282 (base32
4283 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4284 (build-system python-build-system)
4285 (arguments
4286 `(#:python ,python-2 ; does not work with Python 3
4287 #:tests? #f)) ; there are no tests
4288 (inputs
4289 `(("python2-matplotlib" ,python2-matplotlib)))
4290 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4291 (synopsis "Analyze high-throughput genetic sequencing data")
4292 (description
4293 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4294sequencing data. It works with genomic coordinates. There are currently six
4295different command-line tools:
4296
4297@enumerate
4298@item pyicoregion: for generating exploratory regions automatically;
4299@item pyicoenrich: for differential enrichment between two conditions;
4300@item pyicoclip: for calling CLIP-Seq peaks without a control;
4301@item pyicos: for genomic coordinates manipulation;
4302@item pyicoller: for peak calling on punctuated ChIP-Seq;
4303@item pyicount: to count how many reads from N experiment files overlap in a
4304 region file;
4305@item pyicotrocol: to combine operations from pyicoteo.
4306@end enumerate\n")
4307 (license license:gpl3+)))
4308
af860475
BW		 4309(define-public prodigal
4310 (package
4311 (name "prodigal")
e70f7a23 4312 (version "2.6.3")
af860475
BW		 4313 (source (origin
4314 (method url-fetch)
4315 (uri (string-append
4316 "https://github.com/hyattpd/Prodigal/archive/v"
4317 version ".tar.gz"))
4318 (file-name (string-append name "-" version ".tar.gz"))
4319 (sha256
4320 (base32
e70f7a23 4321 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
af860475
BW		 4322 (build-system gnu-build-system)
4323 (arguments
4324 `(#:tests? #f ;no check target
4325 #:make-flags (list (string-append "INSTALLDIR="
4326 (assoc-ref %outputs "out")
4327 "/bin"))
4328 #:phases
4329 (modify-phases %standard-phases
4330 (delete 'configure))))
4331 (home-page "http://prodigal.ornl.gov")
4332 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4333 (description
4334 "Prodigal runs smoothly on finished genomes, draft genomes, and
4335metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4336format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4337partial genes, and identifies translation initiation sites.")
4338 (license license:gpl3+)))
608dd932 4339
ceb62d54
BW		 4340(define-public roary
4341 (package
4342 (name "roary")
da4a707c 4343 (version "3.11.0")
ceb62d54
BW		 4344 (source
4345 (origin
4346 (method url-fetch)
4347 (uri (string-append
4348 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4349 version ".tar.gz"))
4350 (sha256
4351 (base32
da4a707c 4352 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
ceb62d54
BW		 4353 (build-system perl-build-system)
4354 (arguments
4355 `(#:phases
4356 (modify-phases %standard-phases
4357 (delete 'configure)
4358 (delete 'build)
4359 (replace 'check
4360 (lambda _
4361 ;; The tests are not run by default, so we run each test file
4362 ;; directly.
4363 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4364 (getenv "PATH")))
4365 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4366 (getenv "PERL5LIB")))
4367 (zero? (length (filter (lambda (file)
4368 (display file)(display "\n")
4369 (not (zero? (system* "perl" file))))
4370 (find-files "t" ".*\\.t$"))))))
4371 (replace 'install
4372 ;; There is no 'install' target in the Makefile.
4373 (lambda* (#:key outputs #:allow-other-keys)
4374 (let* ((out (assoc-ref outputs "out"))
4375 (bin (string-append out "/bin"))
4376 (perl (string-append out "/lib/perl5/site_perl"))
4377 (roary-plots "contrib/roary_plots"))
4378 (mkdir-p bin)
4379 (mkdir-p perl)
4380 (copy-recursively "bin" bin)
4381 (copy-recursively "lib" perl)
4382 #t)))
4383 (add-after 'install 'wrap-programs
4384 (lambda* (#:key inputs outputs #:allow-other-keys)
4385 (let* ((out (assoc-ref outputs "out"))
4386 (perl5lib (getenv "PERL5LIB"))
4387 (path (getenv "PATH")))
4388 (for-each (lambda (prog)
4389 (let ((binary (string-append out "/" prog)))
4390 (wrap-program binary
4391 `("PERL5LIB" ":" prefix
4392 (,(string-append perl5lib ":" out
4393 "/lib/perl5/site_perl"))))
4394 (wrap-program binary
4395 `("PATH" ":" prefix
4396 (,(string-append path ":" out "/bin"))))))
4397 (find-files "bin" ".*[^R]$"))
4398 (let ((file
4399 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4400 (r-site-lib (getenv "R_LIBS_SITE"))
4401 (coreutils-path
4402 (string-append (assoc-ref inputs "coreutils") "/bin")))
4403 (wrap-program file
4404 `("R_LIBS_SITE" ":" prefix
4405 (,(string-append r-site-lib ":" out "/site-library/"))))
4406 (wrap-program file
4407 `("PATH" ":" prefix
4408 (,(string-append coreutils-path ":" out "/bin"))))))
4409 #t)))))
4410 (native-inputs
4411 `(("perl-env-path" ,perl-env-path)
4412 ("perl-test-files" ,perl-test-files)
4413 ("perl-test-most" ,perl-test-most)
4414 ("perl-test-output" ,perl-test-output)))
4415 (inputs
4416 `(("perl-array-utils" ,perl-array-utils)
4417 ("bioperl" ,bioperl-minimal)
da4a707c 4418 ("perl-digest-md5-file" ,perl-digest-md5-file)
ceb62d54
BW		 4419 ("perl-exception-class" ,perl-exception-class)
4420 ("perl-file-find-rule" ,perl-file-find-rule)
4421 ("perl-file-grep" ,perl-file-grep)
4422 ("perl-file-slurper" ,perl-file-slurper)
4423 ("perl-file-which" ,perl-file-which)
4424 ("perl-graph" ,perl-graph)
4425 ("perl-graph-readwrite" ,perl-graph-readwrite)
4426 ("perl-log-log4perl" ,perl-log-log4perl)
4427 ("perl-moose" ,perl-moose)
4428 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4429 ("perl-text-csv" ,perl-text-csv)
4430 ("bedtools" ,bedtools)
4431 ("cd-hit" ,cd-hit)
4432 ("blast+" ,blast+)
4433 ("mcl" ,mcl)
4434 ("parallel" ,parallel)
4435 ("prank" ,prank)
4436 ("mafft" ,mafft)
4437 ("fasttree" ,fasttree)
4438 ("grep" ,grep)
4439 ("sed" ,sed)
4440 ("gawk" ,gawk)
2d7c4ae3 4441 ("r-minimal" ,r-minimal)
ceb62d54
BW		 4442 ("r-ggplot2" ,r-ggplot2)
4443 ("coreutils" ,coreutils)))
4444 (home-page "http://sanger-pathogens.github.io/Roary")
4445 (synopsis "High speed stand-alone pan genome pipeline")
4446 (description
4447 "Roary is a high speed stand alone pan genome pipeline, which takes
4448annotated assemblies in GFF3 format (produced by the Prokka program) and
4449calculates the pan genome. Using a standard desktop PC, it can analyse
4450datasets with thousands of samples, without compromising the quality of the
4451results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4452single processor. Roary is not intended for metagenomics or for comparing
4453extremely diverse sets of genomes.")
4454 (license license:gpl3)))
4455
608dd932
BW		 4456(define-public raxml
4457 (package
4458 (name "raxml")
e9e0fab0 4459 (version "8.2.10")
608dd932
BW		 4460 (source
4461 (origin
4462 (method url-fetch)
4463 (uri
4464 (string-append
4465 "https://github.com/stamatak/standard-RAxML/archive/v"
4466 version ".tar.gz"))
4467 (file-name (string-append name "-" version ".tar.gz"))
4468 (sha256
4469 (base32
e9e0fab0 4470 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
608dd932
BW		 4471 (build-system gnu-build-system)
4472 (arguments
4473 `(#:tests? #f ; There are no tests.
4474 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4475 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4476 #:phases
4477 (modify-phases %standard-phases
4478 (delete 'configure)
4479 (replace 'install
4480 (lambda* (#:key outputs #:allow-other-keys)
4481 (let* ((out (assoc-ref outputs "out"))
4482 (bin (string-append out "/bin"))
4483 (executable "raxmlHPC-HYBRID"))
4484 (install-file executable bin)
4485 (symlink (string-append bin "/" executable) "raxml"))
4486 #t)))))
4487 (inputs
4488 `(("openmpi" ,openmpi)))
4489 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4490 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4491 (description
4492 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4493phylogenies.")
2805f9b2
EF		 4494 ;; The source includes x86 specific code
4495 (supported-systems '("x86_64-linux" "i686-linux"))
608dd932 4496 (license license:gpl2+)))
af860475 4497
66e3eff1
RW		 4498(define-public rsem
4499 (package
4500 (name "rsem")
4501 (version "1.2.20")
4502 (source
4503 (origin
4504 (method url-fetch)
4505 (uri
4506 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4507 version ".tar.gz"))
4508 (sha256
4509 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
fc1adab1 4510 (patches (search-patches "rsem-makefile.patch"))
66e3eff1
RW		 4511 (modules '((guix build utils)))
4512 (snippet
4513 '(begin
4514 ;; remove bundled copy of boost
4515 (delete-file-recursively "boost")
4516 #t))))
4517 (build-system gnu-build-system)
4518 (arguments
4519 `(#:tests? #f ;no "check" target
4520 #:phases
4521 (modify-phases %standard-phases
4522 ;; No "configure" script.
4523 ;; Do not build bundled samtools library.
4524 (replace 'configure
4525 (lambda _
4526 (substitute* "Makefile"
4527 (("^all : sam/libbam.a") "all : "))
4528 #t))
4529 (replace 'install
4530 (lambda* (#:key outputs #:allow-other-keys)
4531 (let* ((out (string-append (assoc-ref outputs "out")))
4532 (bin (string-append out "/bin/"))
4533 (perl (string-append out "/lib/perl5/site_perl")))
4534 (mkdir-p bin)
4535 (mkdir-p perl)
4536 (for-each (lambda (file)
f3860753 4537 (install-file file bin))
66e3eff1 4538 (find-files "." "rsem-.*"))
f3860753 4539 (install-file "rsem_perl_utils.pm" perl))
66e3eff1
RW		 4540 #t))
4541 (add-after
4542 'install 'wrap-program
4543 (lambda* (#:key outputs #:allow-other-keys)
4544 (let ((out (assoc-ref outputs "out")))
4545 (for-each (lambda (prog)
4546 (wrap-program (string-append out "/bin/" prog)
4547 `("PERL5LIB" ":" prefix
4548 (,(string-append out "/lib/perl5/site_perl")))))
4549 '("rsem-plot-transcript-wiggles"
4550 "rsem-calculate-expression"
4551 "rsem-generate-ngvector"
4552 "rsem-run-ebseq"
4553 "rsem-prepare-reference")))
4554 #t)))))
4555 (inputs
4556 `(("boost" ,boost)
4557 ("ncurses" ,ncurses)
2d7c4ae3 4558 ("r-minimal" ,r-minimal)
66e3eff1
RW		 4559 ("perl" ,perl)
4560 ("samtools" ,samtools-0.1)
4561 ("zlib" ,zlib)))
4562 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4563 (synopsis "Estimate gene expression levels from RNA-Seq data")
4564 (description
4565 "RSEM is a software package for estimating gene and isoform expression
4566levels from RNA-Seq data. The RSEM package provides a user-friendly
4567interface, supports threads for parallel computation of the EM algorithm,
4568single-end and paired-end read data, quality scores, variable-length reads and
4569RSPD estimation. In addition, it provides posterior mean and 95% credibility
4570interval estimates for expression levels. For visualization, it can generate
4571BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4572 (license license:gpl3+)))
4573
8622a072
RW		 4574(define-public rseqc
4575 (package
4576 (name "rseqc")
4577 (version "2.6.1")
4578 (source
4579 (origin
4580 (method url-fetch)
4581 (uri
4582 (string-append "mirror://sourceforge/rseqc/"
de67e922 4583 "RSeQC-" version ".tar.gz"))
8622a072 4584 (sha256
8214b7fb 4585 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
8622a072
RW		 4586 (modules '((guix build utils)))
4587 (snippet
4588 '(begin
4589 ;; remove bundled copy of pysam
4590 (delete-file-recursively "lib/pysam")
4591 (substitute* "setup.py"
4592 ;; remove dependency on outdated "distribute" module
4593 (("^from distribute_setup import use_setuptools") "")
4594 (("^use_setuptools\\(\\)") "")
4595 ;; do not use bundled copy of pysam
4596 (("^have_pysam = False") "have_pysam = True"))))))
4597 (build-system python-build-system)
4598 (arguments `(#:python ,python-2))
4599 (inputs
4600 `(("python-cython" ,python2-cython)
4601 ("python-pysam" ,python2-pysam)
4602 ("python-numpy" ,python2-numpy)
8622a072
RW		 4603 ("zlib" ,zlib)))
4604 (native-inputs
4605 `(("python-nose" ,python2-nose)))
4606 (home-page "http://rseqc.sourceforge.net/")
4607 (synopsis "RNA-seq quality control package")
4608 (description
4609 "RSeQC provides a number of modules that can comprehensively evaluate
4610high throughput sequence data, especially RNA-seq data. Some basic modules
4611inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4612while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4613distribution, coverage uniformity, strand specificity, etc.")
4614 (license license:gpl3+)))
4615
ec946638
RW		 4616(define-public seek
4617 ;; There are no release tarballs. According to the installation
4618 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4619 ;; stable release is identified by this changeset ID.
4620 (let ((changeset "2329130")
4621 (revision "1"))
4622 (package
4623 (name "seek")
4624 (version (string-append "0-" revision "." changeset))
4625 (source (origin
4626 (method hg-fetch)
4627 (uri (hg-reference
4628 (url "https://bitbucket.org/libsleipnir/sleipnir")
4629 (changeset changeset)))
4630 (sha256
4631 (base32
4632 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4633 (build-system gnu-build-system)
4634 (arguments
4635 `(#:modules ((srfi srfi-1)
4636 (guix build gnu-build-system)
4637 (guix build utils))
4638 #:phases
4639 (let ((dirs '("SeekMiner"
4640 "SeekEvaluator"
4641 "SeekPrep"
4642 "Distancer"
4643 "Data2DB"
4644 "PCL2Bin")))
4645 (modify-phases %standard-phases
4561498e 4646 (add-before 'configure 'bootstrap
ec946638
RW		 4647 (lambda _
4648 (zero? (system* "bash" "gen_auto"))))
4649 (add-after 'build 'build-additional-tools
4650 (lambda* (#:key make-flags #:allow-other-keys)
4651 (every (lambda (dir)
4652 (with-directory-excursion (string-append "tools/" dir)
4653 (zero? (apply system* "make" make-flags))))
4654 dirs)))
4655 (add-after 'install 'install-additional-tools
4656 (lambda* (#:key make-flags #:allow-other-keys)
4657 (fold (lambda (dir result)
4658 (with-directory-excursion (string-append "tools/" dir)
4659 (and result
4660 (zero? (apply system*
4661 `("make" ,@make-flags "install"))))))
4662 #t dirs)))))))
4663 (inputs
4664 `(("gsl" ,gsl)
4665 ("boost" ,boost)
4666 ("libsvm" ,libsvm)
4667 ("readline" ,readline)
4668 ("gengetopt" ,gengetopt)
4669 ("log4cpp" ,log4cpp)))
4670 (native-inputs
4671 `(("autoconf" ,autoconf)
4672 ("automake" ,automake)
4673 ("perl" ,perl)))
4674 (home-page "http://seek.princeton.edu")
4675 (synopsis "Gene co-expression search engine")
4676 (description
4677 "SEEK is a computational gene co-expression search engine. SEEK provides
4678biologists with a way to navigate the massive human expression compendium that
4679now contains thousands of expression datasets. SEEK returns a robust ranking
4680of co-expressed genes in the biological area of interest defined by the user's
4681query genes. It also prioritizes thousands of expression datasets according
4682to the user's query of interest.")
4683 (license license:cc-by3.0))))
4684
4e10a221
RW		 4685(define-public samtools
4686 (package
4687 (name "samtools")
63fa0ffc 4688 (version "1.5")
4e10a221
RW		 4689 (source
4690 (origin
4691 (method url-fetch)
4692 (uri
de67e922 4693 (string-append "mirror://sourceforge/samtools/samtools/"
4e10a221
RW		 4694 version "/samtools-" version ".tar.bz2"))
4695 (sha256
4696 (base32
63fa0ffc 4697 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4e10a221
RW		 4698 (build-system gnu-build-system)
4699 (arguments
c4473411 4700 `(#:modules ((ice-9 ftw)
5bdda30b
RW		 4701 (ice-9 regex)
4702 (guix build gnu-build-system)
4703 (guix build utils))
c4473411 4704 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4ab16440 4705 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4e10a221 4706 #:phases
c842d425
BW		 4707 (modify-phases %standard-phases
4708 (add-after 'unpack 'patch-tests
4709 (lambda _
4710 (substitute* "test/test.pl"
4711 ;; The test script calls out to /bin/bash
4712 (("/bin/bash") (which "bash")))
b2d748ed 4713 #t))
c842d425
BW		 4714 (add-after 'install 'install-library
4715 (lambda* (#:key outputs #:allow-other-keys)
4716 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4717 (install-file "libbam.a" lib)
4718 #t)))
4719 (add-after 'install 'install-headers
4720 (lambda* (#:key outputs #:allow-other-keys)
4721 (let ((include (string-append (assoc-ref outputs "out")
4722 "/include/samtools/")))
4723 (for-each (lambda (file)
4724 (install-file file include))
4725 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4726 #t))))))
4e10a221 4727 (native-inputs `(("pkg-config" ,pkg-config)))
4ab16440
BW		 4728 (inputs
4729 `(("htslib" ,htslib)
4730 ("ncurses" ,ncurses)
4731 ("perl" ,perl)
4732 ("python" ,python)
4733 ("zlib" ,zlib)))
4e10a221
RW		 4734 (home-page "http://samtools.sourceforge.net")
4735 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4736 (description
4737 "Samtools implements various utilities for post-processing nucleotide
4738sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4739variant calling (in conjunction with bcftools), and a simple alignment
4740viewer.")
4741 (license license:expat)))
d3517eda 4742
0b84a0aa
RW		 4743(define-public samtools-0.1
4744 ;; This is the most recent version of the 0.1 line of samtools. The input
4745 ;; and output formats differ greatly from that used and produced by samtools
4746 ;; 1.x and is still used in many bioinformatics pipelines.
4747 (package (inherit samtools)
4748 (version "0.1.19")
4749 (source
4750 (origin
4751 (method url-fetch)
4752 (uri
de67e922 4753 (string-append "mirror://sourceforge/samtools/samtools/"
0b84a0aa
RW		 4754 version "/samtools-" version ".tar.bz2"))
4755 (sha256
4756 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4757 (arguments
2309ed68
RW		 4758 `(#:tests? #f ;no "check" target
4759 ,@(substitute-keyword-arguments (package-arguments samtools)
4760 ((#:make-flags flags)
4761 `(cons "LIBCURSES=-lncurses" ,flags))
4762 ((#:phases phases)
4763 `(modify-phases ,phases
4764 (replace 'install
4765 (lambda* (#:key outputs #:allow-other-keys)
4766 (let ((bin (string-append
4767 (assoc-ref outputs "out") "/bin")))
4768 (mkdir-p bin)
f3860753 4769 (install-file "samtools" bin)
b2d748ed 4770 #t)))
2309ed68
RW		 4771 (delete 'patch-tests)
4772 (delete 'configure))))))))
0b84a0aa 4773
fe4c37c2 4774(define-public mosaik
698bd297 4775 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
fe4c37c2
RW		 4776 (package
4777 (name "mosaik")
4778 (version "2.2.30")
4779 (source (origin
4780 ;; There are no release tarballs nor tags.
4781 (method git-fetch)
4782 (uri (git-reference
4783 (url "https://github.com/wanpinglee/MOSAIK.git")
4784 (commit commit)))
4785 (file-name (string-append name "-" version))
4786 (sha256
4787 (base32
4788 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4789 (build-system gnu-build-system)
4790 (arguments
4791 `(#:tests? #f ; no tests
4792 #:make-flags (list "CC=gcc")
4793 #:phases
4794 (modify-phases %standard-phases
4795 (replace 'configure
4796 (lambda _ (chdir "src") #t))
4797 (replace 'install
4798 (lambda* (#:key outputs #:allow-other-keys)
4799 (let ((bin (string-append (assoc-ref outputs "out")
4800 "/bin")))
4801 (mkdir-p bin)
4802 (copy-recursively "../bin" bin)
4803 #t))))))
4804 (inputs
4805 `(("perl" ,perl)
4806 ("zlib" ,zlib)))
029d9f77 4807 (supported-systems '("x86_64-linux"))
0c6c9c00 4808 (home-page "https://github.com/wanpinglee/MOSAIK")
fe4c37c2
RW		 4809 (synopsis "Map nucleotide sequence reads to reference genomes")
4810 (description
4811 "MOSAIK is a program for mapping second and third-generation sequencing
4812reads to a reference genome. MOSAIK can align reads generated by all the
4813major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4814Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4815 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4816 ;; code released into the public domain:
4817 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4818 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4819 (license (list license:gpl2+ license:public-domain)))))
4820
282c5087
RW		 4821(define-public ngs-sdk
4822 (package
4823 (name "ngs-sdk")
6c4ccf32 4824 (version "1.3.0")
282c5087
RW		 4825 (source
4826 (origin
4827 (method url-fetch)
4828 (uri
4829 (string-append "https://github.com/ncbi/ngs/archive/"
4830 version ".tar.gz"))
4831 (file-name (string-append name "-" version ".tar.gz"))
4832 (sha256
4833 (base32
6c4ccf32 4834 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
282c5087
RW		 4835 (build-system gnu-build-system)
4836 (arguments
4837 `(#:parallel-build? #f ; not supported
4838 #:tests? #f ; no "check" target
4839 #:phases
dc1d3cde
KK		 4840 (modify-phases %standard-phases
4841 (replace 'configure
4842 (lambda* (#:key outputs #:allow-other-keys)
4843 (let ((out (assoc-ref outputs "out")))
4844 ;; Allow 'konfigure.perl' to find 'package.prl'.
4845 (setenv "PERL5LIB"
4846 (string-append ".:" (getenv "PERL5LIB")))
4847
4848 ;; The 'configure' script doesn't recognize things like
4849 ;; '--enable-fast-install'.
4850 (zero? (system* "./configure"
4851 (string-append "--build-prefix=" (getcwd) "/build")
4852 (string-append "--prefix=" out))))))
4853 (add-after 'unpack 'enter-dir
4854 (lambda _ (chdir "ngs-sdk") #t)))))
282c5087 4855 (native-inputs `(("perl" ,perl)))
a0dadf0c
AE		 4856 ;; According to the test
4857 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4858 ;; in ngs-sdk/setup/konfigure.perl
ab29be81 4859 (supported-systems '("i686-linux" "x86_64-linux"))
282c5087
RW		 4860 (home-page "https://github.com/ncbi/ngs")
4861 (synopsis "API for accessing Next Generation Sequencing data")
4862 (description
4863 "NGS is a domain-specific API for accessing reads, alignments and pileups
4864produced from Next Generation Sequencing. The API itself is independent from
4865any particular back-end implementation, and supports use of multiple back-ends
4866simultaneously.")
4867 (license license:public-domain)))
4868
1ad15c16 4869(define-public java-ngs
2651a5e6 4870 (package (inherit ngs-sdk)
1ad15c16 4871 (name "java-ngs")
2651a5e6
RW		 4872 (arguments
4873 `(,@(substitute-keyword-arguments
4874 `(#:modules ((guix build gnu-build-system)
4875 (guix build utils)
4876 (srfi srfi-1)
4877 (srfi srfi-26))
4878 ,@(package-arguments ngs-sdk))
4879 ((#:phases phases)
614a8977
RW		 4880 `(modify-phases ,phases
4881 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
2651a5e6 4882 (inputs
d2540f80 4883 `(("jdk" ,icedtea "jdk")
2651a5e6
RW		 4884 ("ngs-sdk" ,ngs-sdk)))
4885 (synopsis "Java bindings for NGS SDK")))
4886
75dd2424
RW		 4887(define-public ncbi-vdb
4888 (package
4889 (name "ncbi-vdb")
5021f547 4890 (version "2.8.2")
75dd2424
RW		 4891 (source
4892 (origin
4893 (method url-fetch)
4894 (uri
4895 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4896 version ".tar.gz"))
4897 (file-name (string-append name "-" version ".tar.gz"))
4898 (sha256
4899 (base32
5021f547 4900 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
75dd2424
RW		 4901 (build-system gnu-build-system)
4902 (arguments
4903 `(#:parallel-build? #f ; not supported
4904 #:tests? #f ; no "check" target
4905 #:phases
70111198 4906 (modify-phases %standard-phases
0691851a
BW		 4907 (add-before 'configure 'set-perl-search-path
4908 (lambda _
4909 ;; Work around "dotless @INC" build failure.
4910 (setenv "PERL5LIB"
4911 (string-append (getcwd) "/setup:"
4912 (getenv "PERL5LIB")))
4913 #t))
70111198
RW		 4914 (replace 'configure
4915 (lambda* (#:key inputs outputs #:allow-other-keys)
4916 (let ((out (assoc-ref outputs "out")))
4917 ;; Override include path for libmagic
4918 (substitute* "setup/package.prl"
4919 (("name => 'magic', Include => '/usr/include'")
4920 (string-append "name=> 'magic', Include => '"
4921 (assoc-ref inputs "libmagic")
4922 "/include" "'")))
75dd2424 4923
70111198
RW		 4924 ;; Install kdf5 library (needed by sra-tools)
4925 (substitute* "build/Makefile.install"
4926 (("LIBRARIES_TO_INSTALL =")
4927 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
75dd2424 4928
70111198
RW		 4929 (substitute* "build/Makefile.env"
4930 (("CFLAGS =" prefix)
4931 (string-append prefix "-msse2 ")))
675d7ae2 4932
558e2307
RW		 4933 ;; Override search path for ngs-java
4934 (substitute* "setup/package.prl"
4935 (("/usr/local/ngs/ngs-java")
4936 (assoc-ref inputs "java-ngs")))
4937
70111198
RW		 4938 ;; The 'configure' script doesn't recognize things like
4939 ;; '--enable-fast-install'.
4940 (zero? (system*
4941 "./configure"
4942 (string-append "--build-prefix=" (getcwd) "/build")
4943 (string-append "--prefix=" (assoc-ref outputs "out"))
4944 (string-append "--debug")
4945 (string-append "--with-xml2-prefix="
4946 (assoc-ref inputs "libxml2"))
4947 (string-append "--with-ngs-sdk-prefix="
4948 (assoc-ref inputs "ngs-sdk"))
70111198
RW		 4949 (string-append "--with-hdf5-prefix="
4950 (assoc-ref inputs "hdf5")))))))
4951 (add-after 'install 'install-interfaces
4952 (lambda* (#:key outputs #:allow-other-keys)
4953 ;; Install interface libraries. On i686 the interface libraries
4954 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4955 ;; architecture name ("i386") instead of the target system prefix
4956 ;; ("i686").
4957 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4958 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4959 ,(system->linux-architecture
4960 (or (%current-target-system)
4961 (%current-system)))
4962 "/rel/ilib")
4963 (string-append (assoc-ref outputs "out")
4964 "/ilib"))
4965 ;; Install interface headers
4966 (copy-recursively "interfaces"
4967 (string-append (assoc-ref outputs "out")
4968 "/include"))
d5e17162
RW		 4969 #t))
4970 ;; These files are needed by sra-tools.
4971 (add-after 'install 'install-configuration-files
4972 (lambda* (#:key outputs #:allow-other-keys)
4973 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4974 (mkdir target)
4975 (install-file "libs/kfg/default.kfg" target)
4976 (install-file "libs/kfg/certs.kfg" target))
70111198 4977 #t)))))
75dd2424
RW		 4978 (inputs
4979 `(("libxml2" ,libxml2)
4980 ("ngs-sdk" ,ngs-sdk)
1ad15c16 4981 ("java-ngs" ,java-ngs)
75dd2424
RW		 4982 ("libmagic" ,file)
4983 ("hdf5" ,hdf5)))
4984 (native-inputs `(("perl" ,perl)))
675d7ae2
RW		 4985 ;; NCBI-VDB requires SSE capability.
4986 (supported-systems '("i686-linux" "x86_64-linux"))
75dd2424
RW		 4987 (home-page "https://github.com/ncbi/ncbi-vdb")
4988 (synopsis "Database engine for genetic information")
4989 (description
4990 "The NCBI-VDB library implements a highly compressed columnar data
4991warehousing engine that is most often used to store genetic information.
4992Databases are stored in a portable image within the file system, and can be
4993accessed/downloaded on demand across HTTP.")
4994 (license license:public-domain)))
4995
cc6ed477
RW		 4996(define-public plink
4997 (package
4998 (name "plink")
4999 (version "1.07")
5000 (source
5001 (origin
5002 (method url-fetch)
5003 (uri (string-append
5004 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5005 version "-src.zip"))
5006 (sha256
5007 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
0dbb7ac2
EF		 5008 (patches (search-patches "plink-1.07-unclobber-i.patch"
5009 "plink-endian-detection.patch"))))
cc6ed477
RW		 5010 (build-system gnu-build-system)
5011 (arguments
5012 '(#:tests? #f ;no "check" target
5013 #:make-flags (list (string-append "LIB_LAPACK="
5014 (assoc-ref %build-inputs "lapack")
5015 "/lib/liblapack.so")
5016 "WITH_LAPACK=1"
5017 "FORCE_DYNAMIC=1"
5018 ;; disable phoning home
5019 "WITH_WEBCHECK=")
5020 #:phases
5021 (modify-phases %standard-phases
5022 ;; no "configure" script
5023 (delete 'configure)
5024 (replace 'install
5025 (lambda* (#:key outputs #:allow-other-keys)
5026 (let ((bin (string-append (assoc-ref outputs "out")
5027 "/bin/")))
96c46210 5028 (install-file "plink" bin)
cc6ed477
RW		 5029 #t))))))
5030 (inputs
5031 `(("zlib" ,zlib)
5032 ("lapack" ,lapack)))
5033 (native-inputs
5034 `(("unzip" ,unzip)))
5035 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5036 (synopsis "Whole genome association analysis toolset")
5037 (description
5038 "PLINK is a whole genome association analysis toolset, designed to
5039perform a range of basic, large-scale analyses in a computationally efficient
5040manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5041so there is no support for steps prior to this (e.g. study design and
5042planning, generating genotype or CNV calls from raw data). Through
5043integration with gPLINK and Haploview, there is some support for the
5044subsequent visualization, annotation and storage of results.")
5045 ;; Code is released under GPLv2, except for fisher.h, which is under
5046 ;; LGPLv2.1+
5047 (license (list license:gpl2 license:lgpl2.1+))))
5048
dad66da4
RW		 5049(define-public plink-ng
5050 (package (inherit plink)
5051 (name "plink-ng")
5052 (version "1.90b4")
5053 (source
5054 (origin
5055 (method url-fetch)
5056 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5057 version ".tar.gz"))
5058 (file-name (string-append name "-" version ".tar.gz"))
5059 (sha256
5060 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5061 (build-system gnu-build-system)
5062 (arguments
5063 '(#:tests? #f ;no "check" target
5064 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5065 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5066 "ZLIB=-lz"
5067 "-f" "Makefile.std")
5068 #:phases
5069 (modify-phases %standard-phases
5070 (add-after 'unpack 'chdir
5071 (lambda _ (chdir "1.9") #t))
5072 (delete 'configure) ; no "configure" script
5073 (replace 'install
5074 (lambda* (#:key outputs #:allow-other-keys)
5075 (let ((bin (string-append (assoc-ref outputs "out")
5076 "/bin/")))
5077 (install-file "plink" bin)
5078 #t))))))
5079 (inputs
5080 `(("zlib" ,zlib)
5081 ("lapack" ,lapack)
5082 ("openblas" ,openblas)))
5083 (home-page "https://www.cog-genomics.org/plink/")
5084 (license license:gpl3+)))
5085
c6a24d6e
RW		 5086(define-public smithlab-cpp
5087 (let ((revision "1")
698bd297 5088 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
c6a24d6e
RW		 5089 (package
5090 (name "smithlab-cpp")
698bd297 5091 (version (string-append "0." revision "." (string-take commit 7)))
c6a24d6e
RW		 5092 (source (origin
5093 (method git-fetch)
5094 (uri (git-reference
5095 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5096 (commit commit)))
5097 (file-name (string-append name "-" version "-checkout"))
5098 (sha256
5099 (base32
5100 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5101 (build-system gnu-build-system)
5102 (arguments
5103 `(#:modules ((guix build gnu-build-system)
5104 (guix build utils)
5105 (srfi srfi-26))
5106 #:tests? #f ;no "check" target
5107 #:phases
5108 (modify-phases %standard-phases
5109 (add-after 'unpack 'use-samtools-headers
5110 (lambda _
5111 (substitute* '("SAM.cpp"
5112 "SAM.hpp")
5113 (("sam.h") "samtools/sam.h"))
5114 #t))
5115 (replace 'install
5116 (lambda* (#:key outputs #:allow-other-keys)
5117 (let* ((out (assoc-ref outputs "out"))
5118 (lib (string-append out "/lib"))
5119 (include (string-append out "/include/smithlab-cpp")))
5120 (mkdir-p lib)
5121 (mkdir-p include)
5122 (for-each (cut install-file <> lib)
5123 (find-files "." "\\.o$"))
5124 (for-each (cut install-file <> include)
5125 (find-files "." "\\.hpp$")))
5126 #t))
5127 (delete 'configure))))
5128 (inputs
5129 `(("samtools" ,samtools-0.1)
5130 ("zlib" ,zlib)))
5131 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5132 (synopsis "C++ helper library for functions used in Smith lab projects")
5133 (description
5134 "Smithlab CPP is a C++ library that includes functions used in many of
5135the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5136structures, classes for genomic regions, mapped sequencing reads, etc.")
5137 (license license:gpl3+))))
5138
56e373ef
RW		 5139(define-public preseq
5140 (package
5141 (name "preseq")
b49c5a58 5142 (version "2.0")
56e373ef
RW		 5143 (source (origin
5144 (method url-fetch)
b49c5a58
RW		 5145 (uri (string-append "https://github.com/smithlabcode/"
5146 "preseq/archive/v" version ".tar.gz"))
5147 (file-name (string-append name "-" version ".tar.gz"))
56e373ef 5148 (sha256
b49c5a58 5149 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
56e373ef
RW		 5150 (modules '((guix build utils)))
5151 (snippet
5152 ;; Remove bundled samtools.
b49c5a58 5153 '(delete-file-recursively "samtools"))))
56e373ef
RW		 5154 (build-system gnu-build-system)
5155 (arguments
5156 `(#:tests? #f ;no "check" target
5157 #:phases
5158 (modify-phases %standard-phases
56e373ef 5159 (delete 'configure))
b49c5a58
RW		 5160 #:make-flags
5161 (list (string-append "PREFIX="
5162 (assoc-ref %outputs "out"))
5163 (string-append "LIBBAM="
5164 (assoc-ref %build-inputs "samtools")
5165 "/lib/libbam.a")
5166 (string-append "SMITHLAB_CPP="
5167 (assoc-ref %build-inputs "smithlab-cpp")
5168 "/lib")
5169 "PROGS=preseq"
5170 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
56e373ef
RW		 5171 (inputs
5172 `(("gsl" ,gsl)
5173 ("samtools" ,samtools-0.1)
b49c5a58 5174 ("smithlab-cpp" ,smithlab-cpp)
56e373ef
RW		 5175 ("zlib" ,zlib)))
5176 (home-page "http://smithlabresearch.org/software/preseq/")
5177 (synopsis "Program for analyzing library complexity")
5178 (description
5179 "The preseq package is aimed at predicting and estimating the complexity
5180of a genomic sequencing library, equivalent to predicting and estimating the
5181number of redundant reads from a given sequencing depth and how many will be
5182expected from additional sequencing using an initial sequencing experiment.
5183The estimates can then be used to examine the utility of further sequencing,
5184optimize the sequencing depth, or to screen multiple libraries to avoid low
5185complexity samples.")
5186 (license license:gpl3+)))
5187
9ded1457
BW		 5188(define-public python-screed
5189 (package
5190 (name "python-screed")
5191 (version "0.9")
5192 (source
5193 (origin
5194 (method url-fetch)
5195 (uri (pypi-uri "screed" version))
5196 (sha256
5197 (base32
5198 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5199 (build-system python-build-system)
5200 (arguments
5201 `(#:phases
5202 (modify-phases %standard-phases
5203 (replace 'check
5204 (lambda _
5205 (setenv "PYTHONPATH"
5206 (string-append (getenv "PYTHONPATH") ":."))
5207 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5208 (native-inputs
5209 `(("python-nose" ,python-nose)))
5210 (inputs
5211 `(("python-bz2file" ,python-bz2file)))
7bf837fd 5212 (home-page "https://github.com/dib-lab/screed/")
9ded1457
BW		 5213 (synopsis "Short read sequence database utilities")
5214 (description "Screed parses FASTA and FASTQ files and generates databases.
5215Values such as sequence name, sequence description, sequence quality and the
5216sequence itself can be retrieved from these databases.")
5217 (license license:bsd-3)))
5218
5219(define-public python2-screed
5c31f4aa 5220 (package-with-python2 python-screed))
9ded1457 5221
51c64999
RW		 5222(define-public sra-tools
5223 (package
5224 (name "sra-tools")
79849358 5225 (version "2.8.2-1")
51c64999
RW		 5226 (source
5227 (origin
5228 (method url-fetch)
5229 (uri
5230 (string-append "https://github.com/ncbi/sra-tools/archive/"
5231 version ".tar.gz"))
5232 (file-name (string-append name "-" version ".tar.gz"))
5233 (sha256
5234 (base32
79849358 5235 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
51c64999
RW		 5236 (build-system gnu-build-system)
5237 (arguments
5238 `(#:parallel-build? #f ; not supported
5239 #:tests? #f ; no "check" target
2320e76b 5240 #:make-flags
79849358
RW		 5241 (list (string-append "DEFAULT_CRT="
5242 (assoc-ref %build-inputs "ncbi-vdb")
5243 "/kfg/certs.kfg")
5244 (string-append "DEFAULT_KFG="
5245 (assoc-ref %build-inputs "ncbi-vdb")
5246 "/kfg/default.kfg")
5247 (string-append "VDB_LIBDIR="
2320e76b
RW		 5248 (assoc-ref %build-inputs "ncbi-vdb")
5249 ,(if (string-prefix? "x86_64"
5250 (or (%current-target-system)
5251 (%current-system)))
5252 "/lib64"
5253 "/lib32")))
51c64999 5254 #:phases
beebe431 5255 (modify-phases %standard-phases
0691851a
BW		 5256 (add-before 'configure 'set-perl-search-path
5257 (lambda _
5258 ;; Work around "dotless @INC" build failure.
5259 (setenv "PERL5LIB"
5260 (string-append (getcwd) "/setup:"
5261 (getenv "PERL5LIB")))
5262 #t))
beebe431
RW		 5263 (replace 'configure
5264 (lambda* (#:key inputs outputs #:allow-other-keys)
5265 ;; The build system expects a directory containing the sources and
5266 ;; raw build output of ncbi-vdb, including files that are not
5267 ;; installed. Since we are building against an installed version of
5268 ;; ncbi-vdb, the following modifications are needed.
5269 (substitute* "setup/konfigure.perl"
5270 ;; Make the configure script look for the "ilib" directory of
5271 ;; "ncbi-vdb" without first checking for the existence of a
5272 ;; matching library in its "lib" directory.
5273 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5274 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5275 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5276 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5277 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
51c64999 5278
beebe431
RW		 5279 ;; Dynamic linking
5280 (substitute* "tools/copycat/Makefile"
5281 (("smagic-static") "lmagic"))
2320e76b 5282
beebe431
RW		 5283 ;; The 'configure' script doesn't recognize things like
5284 ;; '--enable-fast-install'.
5285 (zero? (system*
5286 "./configure"
5287 (string-append "--build-prefix=" (getcwd) "/build")
5288 (string-append "--prefix=" (assoc-ref outputs "out"))
5289 (string-append "--debug")
5290 (string-append "--with-fuse-prefix="
5291 (assoc-ref inputs "fuse"))
5292 (string-append "--with-magic-prefix="
5293 (assoc-ref inputs "libmagic"))
5294 ;; TODO: building with libxml2 fails with linker errors
5295 ;; (string-append "--with-xml2-prefix="
5296 ;; (assoc-ref inputs "libxml2"))
5297 (string-append "--with-ncbi-vdb-sources="
5298 (assoc-ref inputs "ncbi-vdb"))
5299 (string-append "--with-ncbi-vdb-build="
5300 (assoc-ref inputs "ncbi-vdb"))
5301 (string-append "--with-ngs-sdk-prefix="
5302 (assoc-ref inputs "ngs-sdk"))
5303 (string-append "--with-hdf5-prefix="
1108a920
RW		 5304 (assoc-ref inputs "hdf5"))))))
5305 ;; This version of sra-tools fails to build with glibc because of a
5306 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5307 ;; contains a definition of "canonicalize", so we rename it.
5308 ;;
5309 ;; See upstream bug report:
5310 ;; https://github.com/ncbi/sra-tools/issues/67
5311 (add-after 'unpack 'patch-away-glibc-conflict
5312 (lambda _
5313 (substitute* "tools/bam-loader/bam.c"
5314 (("canonicalize\\(" line)
5315 (string-append "sra_tools_" line)))
5316 #t)))))
51c64999
RW		 5317 (native-inputs `(("perl" ,perl)))
5318 (inputs
5319 `(("ngs-sdk" ,ngs-sdk)
5320 ("ncbi-vdb" ,ncbi-vdb)
5321 ("libmagic" ,file)
5322 ("fuse" ,fuse)
5323 ("hdf5" ,hdf5)
5324 ("zlib" ,zlib)))
5325 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5326 (synopsis "Tools and libraries for reading and writing sequencing data")
5327 (description
5328 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5329reading of sequencing files from the Sequence Read Archive (SRA) database and
5330writing files into the .sra format.")
5331 (license license:public-domain)))
5332
d3517eda
RW		 5333(define-public seqan
5334 (package
5335 (name "seqan")
5336 (version "1.4.2")
5337 (source (origin
5338 (method url-fetch)
5339 (uri (string-append "http://packages.seqan.de/seqan-library/"
5340 "seqan-library-" version ".tar.bz2"))
5341 (sha256
5342 (base32
5343 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5344 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5345 ;; makes sense to split the outputs.
5346 (outputs '("out" "doc"))
5347 (build-system trivial-build-system)
5348 (arguments
5349 `(#:modules ((guix build utils))
5350 #:builder
5351 (begin
5352 (use-modules (guix build utils))
5353 (let ((tar (assoc-ref %build-inputs "tar"))
5354 (bzip (assoc-ref %build-inputs "bzip2"))
5355 (out (assoc-ref %outputs "out"))
5356 (doc (assoc-ref %outputs "doc")))
5357 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5358 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5359 (chdir (string-append "seqan-library-" ,version))
5360 (copy-recursively "include" (string-append out "/include"))
5361 (copy-recursively "share" (string-append doc "/share"))))))
5362 (native-inputs
5363 `(("source" ,source)
5364 ("tar" ,tar)
5365 ("bzip2" ,bzip2)))
5366 (home-page "http://www.seqan.de")
5367 (synopsis "Library for nucleotide sequence analysis")
5368 (description
5369 "SeqAn is a C++ library of efficient algorithms and data structures for
5370the analysis of sequences with the focus on biological data. It contains
5371algorithms and data structures for string representation and their
5372manipulation, online and indexed string search, efficient I/O of
5373bioinformatics file formats, sequence alignment, and more.")
5374 (license license:bsd-3)))
ce7155d5 5375
d708b7a9
BW		 5376(define-public seqmagick
5377 (package
5378 (name "seqmagick")
5379 (version "0.6.1")
5380 (source
5381 (origin
5382 (method url-fetch)
5383 (uri (string-append
5384 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5385 version ".tar.gz"))
5386 (sha256
5387 (base32
5388 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5389 (build-system python-build-system)
5390 (arguments
5391 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5392 `(#:python ,python-2
5393 #:phases
5394 (modify-phases %standard-phases
5395 ;; Current test in setup.py does not work as of 0.6.1,
5396 ;; so use nose to run tests instead for now. See
5397 ;; https://github.com/fhcrc/seqmagick/issues/55
5398 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5399 (inputs
7bba95b7
BW		 5400 ;; biopython-1.66 is required due to
5401 ;; https://github.com/fhcrc/seqmagick/issues/59
5402 ;; When that issue is resolved the 'python2-biopython-1.66' package
5403 ;; should be removed.
5404 `(("python-biopython" ,python2-biopython-1.66)))
d708b7a9 5405 (native-inputs
f3b98f4f 5406 `(("python-nose" ,python2-nose)))
7bf837fd 5407 (home-page "https://github.com/fhcrc/seqmagick")
d708b7a9
BW		 5408 (synopsis "Tools for converting and modifying sequence files")
5409 (description
5410 "Bioinformaticians often have to convert sequence files between formats
5411and do little manipulations on them, and it's not worth writing scripts for
5412that. Seqmagick is a utility to expose the file format conversion in
5413BioPython in a convenient way. Instead of having a big mess of scripts, there
5414is one that takes arguments.")
5415 (license license:gpl3)))
5416
66daf78c
BW		 5417(define-public seqtk
5418 (package
5419 (name "seqtk")
5420 (version "1.2")
5421 (source (origin
5422 (method url-fetch)
5423 (uri (string-append
5424 "https://github.com/lh3/seqtk/archive/v"
5425 version ".tar.gz"))
5426 (file-name (string-append name "-" version ".tar.gz"))
5427 (sha256
5428 (base32
5429 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5430 (modules '((guix build utils)))
5431 (snippet
5432 '(begin
5433 ;; Remove extraneous header files, as is done in the seqtk
5434 ;; master branch.
5435 (for-each (lambda (file) (delete-file file))
5436 (list "ksort.h" "kstring.h" "kvec.h"))
5437 #t))))
5438 (build-system gnu-build-system)
5439 (arguments
5440 `(#:phases
5441 (modify-phases %standard-phases
5442 (delete 'configure)
5443 (replace 'check
5444 ;; There are no tests, so we just run a sanity check.
5445 (lambda _ (zero? (system* "./seqtk" "seq"))))
5446 (replace 'install
5447 (lambda* (#:key outputs #:allow-other-keys)
5448 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5449 (install-file "seqtk" bin)))))))
5450 (inputs
5451 `(("zlib" ,zlib)))
5452 (home-page "https://github.com/lh3/seqtk")
5453 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5454 (description
5455 "Seqtk is a fast and lightweight tool for processing sequences in the
5456FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5457optionally compressed by gzip.")
5458 (license license:expat)))
5459
5f7e17be
BW		 5460(define-public snap-aligner
5461 (package
5462 (name "snap-aligner")
5463 (version "1.0beta.18")
5464 (source (origin
5465 (method url-fetch)
5466 (uri (string-append
5467 "https://github.com/amplab/snap/archive/v"
5468 version ".tar.gz"))
5469 (file-name (string-append name "-" version ".tar.gz"))
5470 (sha256
5471 (base32
5472 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5473 (build-system gnu-build-system)
5474 (arguments
5475 '(#:phases
5476 (modify-phases %standard-phases
5477 (delete 'configure)
5478 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5479 (replace 'install
5480 (lambda* (#:key outputs #:allow-other-keys)
5481 (let* ((out (assoc-ref outputs "out"))
5482 (bin (string-append out "/bin")))
5f7e17be
BW		 5483 (install-file "snap-aligner" bin)
5484 (install-file "SNAPCommand" bin)
5485 #t))))))
5486 (native-inputs
5487 `(("zlib" ,zlib)))
5488 (home-page "http://snap.cs.berkeley.edu/")
5489 (synopsis "Short read DNA sequence aligner")
5490 (description
5491 "SNAP is a fast and accurate aligner for short DNA reads. It is
5492optimized for modern read lengths of 100 bases or higher, and takes advantage
5493of these reads to align data quickly through a hash-based indexing scheme.")
3e6fdd5f
EF		 5494 ;; 32-bit systems are not supported by the unpatched code.
5495 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5496 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5497 ;; systems without a lot of memory cannot make good use of this program.
5498 (supported-systems '("x86_64-linux"))
5f7e17be
BW		 5499 (license license:asl2.0)))
5500
bcadaf00
BW		 5501(define-public sortmerna
5502 (package
5503 (name "sortmerna")
849485f5 5504 (version "2.1b")
bcadaf00
BW		 5505 (source
5506 (origin
5507 (method url-fetch)
5508 (uri (string-append
5509 "https://github.com/biocore/sortmerna/archive/"
5510 version ".tar.gz"))
5511 (file-name (string-append name "-" version ".tar.gz"))
5512 (sha256
5513 (base32
849485f5 5514 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
bcadaf00
BW		 5515 (build-system gnu-build-system)
5516 (outputs '("out" ;for binaries
5517 "db")) ;for sequence databases
5518 (arguments
5519 `(#:phases
5520 (modify-phases %standard-phases
5521 (replace 'install
5522 (lambda* (#:key outputs #:allow-other-keys)
5523 (let* ((out (assoc-ref outputs "out"))
5524 (bin (string-append out "/bin"))
5525 (db (assoc-ref outputs "db"))
5526 (share
5527 (string-append db "/share/sortmerna/rRNA_databases")))
5528 (install-file "sortmerna" bin)
5529 (install-file "indexdb_rna" bin)
5530 (for-each (lambda (file)
5531 (install-file file share))
5532 (find-files "rRNA_databases" ".*fasta"))
5533 #t))))))
849485f5
BW		 5534 (inputs
5535 `(("zlib" ,zlib)))
bcadaf00
BW		 5536 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5537 (synopsis "Biological sequence analysis tool for NGS reads")
5538 (description
5539 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5540and operational taxonomic unit (OTU) picking of next generation
5541sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5542allows for fast and sensitive analyses of nucleotide sequences. The main
5543application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
2324541b
EF		 5544 ;; The source includes x86 specific code
5545 (supported-systems '("x86_64-linux" "i686-linux"))
bcadaf00
BW		 5546 (license license:lgpl3)))
5547
ce7155d5
RW		 5548(define-public star
5549 (package
5550 (name "star")
939b6b11 5551 (version "2.5.3a")
ce7155d5
RW		 5552 (source (origin
5553 (method url-fetch)
3062d750
RW		 5554 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5555 version ".tar.gz"))
5556 (file-name (string-append name "-" version ".tar.gz"))
ce7155d5
RW		 5557 (sha256
5558 (base32
939b6b11 5559 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
ce7155d5
RW		 5560 (modules '((guix build utils)))
5561 (snippet
3062d750
RW		 5562 '(begin
5563 (substitute* "source/Makefile"
5564 (("/bin/rm") "rm"))
5565 ;; Remove pre-built binaries and bundled htslib sources.
5566 (delete-file-recursively "bin/MacOSX_x86_64")
5567 (delete-file-recursively "bin/Linux_x86_64")
c9e9154e 5568 (delete-file-recursively "bin/Linux_x86_64_static")
3062d750
RW		 5569 (delete-file-recursively "source/htslib")
5570 #t))))
ce7155d5
RW		 5571 (build-system gnu-build-system)
5572 (arguments
5573 '(#:tests? #f ;no check target
5574 #:make-flags '("STAR")
5575 #:phases
c0266e8d
RW		 5576 (modify-phases %standard-phases
5577 (add-after 'unpack 'enter-source-dir
5578 (lambda _ (chdir "source") #t))
3062d750
RW		 5579 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5580 (lambda _
5581 (substitute* "Makefile"
5582 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5583 _ prefix) prefix))
5584 (substitute* '("BAMfunctions.cpp"
5585 "signalFromBAM.h"
5586 "bam_cat.h"
5587 "bam_cat.c"
5588 "STAR.cpp"
5589 "bamRemoveDuplicates.cpp")
5590 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5591 (string-append "#include <" header ">")))
5592 (substitute* "IncludeDefine.h"
5593 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5594 (string-append "<" header ">")))
5595 #t))
c0266e8d
RW		 5596 (replace 'install
5597 (lambda* (#:key outputs #:allow-other-keys)
5598 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5599 (install-file "STAR" bin))
5600 #t))
5601 (delete 'configure))))
ce7155d5 5602 (native-inputs
9fc513ad 5603 `(("xxd" ,xxd)))
ce7155d5 5604 (inputs
3062d750
RW		 5605 `(("htslib" ,htslib)
5606 ("zlib" ,zlib)))
ce7155d5
RW		 5607 (home-page "https://github.com/alexdobin/STAR")
5608 (synopsis "Universal RNA-seq aligner")
5609 (description
5610 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5611based on a previously undescribed RNA-seq alignment algorithm that uses
5612sequential maximum mappable seed search in uncompressed suffix arrays followed
5613by seed clustering and stitching procedure. In addition to unbiased de novo
5614detection of canonical junctions, STAR can discover non-canonical splices and
5615chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5616sequences.")
c11f79a4
BW		 5617 ;; Only 64-bit systems are supported according to the README.
5618 (supported-systems '("x86_64-linux" "mips64el-linux"))
ce7155d5
RW		 5619 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5620 (license license:gpl3+)))
de07c0db 5621
dbf4ed7c
RW		 5622(define-public subread
5623 (package
5624 (name "subread")
e6debcaf 5625 (version "1.6.0")
dbf4ed7c
RW		 5626 (source (origin
5627 (method url-fetch)
de67e922
LF		 5628 (uri (string-append "mirror://sourceforge/subread/subread-"
5629 version "/subread-" version "-source.tar.gz"))
dbf4ed7c
RW		 5630 (sha256
5631 (base32
e6debcaf 5632 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
dbf4ed7c
RW		 5633 (build-system gnu-build-system)
5634 (arguments
5635 `(#:tests? #f ;no "check" target
104c1986
RW		 5636 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5637 ;; optimizations by default, so we override these flags such that x86_64
5638 ;; flags are only added when the build target is an x86_64 system.
5639 #:make-flags
5640 (list (let ((system ,(or (%current-target-system)
5641 (%current-system)))
5642 (flags '("-ggdb" "-fomit-frame-pointer"
5643 "-ffast-math" "-funroll-loops"
5644 "-fmessage-length=0"
5645 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5646 "-DMAKE_STANDALONE"
5647 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5648 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5649 (if (string-prefix? "x86_64" system)
5650 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5651 (string-append "CCFLAGS=" (string-join flags))))
5652 "-f" "Makefile.Linux"
5653 "CC=gcc ${CCFLAGS}")
dbf4ed7c 5654 #:phases
dc1d3cde
KK		 5655 (modify-phases %standard-phases
5656 (add-after 'unpack 'enter-dir
5657 (lambda _ (chdir "src") #t))
5658 (replace 'install
5659 (lambda* (#:key outputs #:allow-other-keys)
5660 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5661 (mkdir-p bin)
5662 (copy-recursively "../bin" bin))))
dbf4ed7c 5663 ;; no "configure" script
dc1d3cde 5664 (delete 'configure))))
dbf4ed7c
RW		 5665 (inputs `(("zlib" ,zlib)))
5666 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5667 (synopsis "Tool kit for processing next-gen sequencing data")
5668 (description
5669 "The subread package contains the following tools: subread aligner, a
5670general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5671and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5672features; exactSNP: a SNP caller that discovers SNPs by testing signals
5673against local background noises.")
5674 (license license:gpl3+)))
5675
d15d981e
RW		 5676(define-public stringtie
5677 (package
5678 (name "stringtie")
5679 (version "1.2.1")
5680 (source (origin
5681 (method url-fetch)
5682 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5683 "stringtie-" version ".tar.gz"))
5684 (sha256
5685 (base32
5686 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5687 (modules '((guix build utils)))
5688 (snippet
5689 '(begin
5690 (delete-file-recursively "samtools-0.1.18")
5691 #t))))
5692 (build-system gnu-build-system)
5693 (arguments
5694 `(#:tests? #f ;no test suite
5695 #:phases
5696 (modify-phases %standard-phases
5697 ;; no configure script
5698 (delete 'configure)
5699 (add-before 'build 'use-system-samtools
5700 (lambda _
5701 (substitute* "Makefile"
5702 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5703 "stringtie: "))
5704 (substitute* '("gclib/GBam.h"
5705 "gclib/GBam.cpp")
5706 (("#include \"(bam|sam|kstring).h\"" _ header)
5707 (string-append "#include <samtools/" header ".h>")))
5708 #t))
0d2c0562
RW		 5709 (add-after 'unpack 'remove-duplicate-typedef
5710 (lambda _
5711 ;; This typedef conflicts with the typedef in
5712 ;; glibc-2.25/include/bits/types.h
5713 (substitute* "gclib/GThreads.h"
5714 (("typedef long long __intmax_t;") ""))
5715 #t))
d15d981e
RW		 5716 (replace 'install
5717 (lambda* (#:key outputs #:allow-other-keys)
5718 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5719 (install-file "stringtie" bin)
5720 #t))))))
5721 (inputs
5722 `(("samtools" ,samtools-0.1)
5723 ("zlib" ,zlib)))
5724 (home-page "http://ccb.jhu.edu/software/stringtie/")
5725 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5726 (description
5727 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5728alignments into potential transcripts. It uses a novel network flow algorithm
5729as well as an optional de novo assembly step to assemble and quantitate
5730full-length transcripts representing multiple splice variants for each gene
5731locus. Its input can include not only the alignments of raw reads used by
5732other transcript assemblers, but also alignments of longer sequences that have
5733been assembled from those reads. To identify differentially expressed genes
5734between experiments, StringTie's output can be processed either by the
5735Cuffdiff or Ballgown programs.")
5736 (license license:artistic2.0)))
5737
ad0ae297
BW		 5738(define-public taxtastic
5739 (package
5740 (name "taxtastic")
3cbfc149 5741 (version "0.6.4")
ad0ae297
BW		 5742 (source (origin
5743 (method url-fetch)
3cbfc149 5744 (uri (pypi-uri "taxtastic" version))
ad0ae297
BW		 5745 (sha256
5746 (base32
3cbfc149 5747 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
ad0ae297
BW		 5748 (build-system python-build-system)
5749 (arguments
5750 `(#:python ,python-2
5751 #:phases
5752 (modify-phases %standard-phases
5753 (replace 'check
5754 (lambda _
5755 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5756 (propagated-inputs
5757 `(("python-sqlalchemy" ,python2-sqlalchemy)
5758 ("python-decorator" ,python2-decorator)
5759 ("python-biopython" ,python2-biopython)
5760 ("python-pandas" ,python2-pandas)))
5761 (home-page "https://github.com/fhcrc/taxtastic")
5762 (synopsis "Tools for taxonomic naming and annotation")
5763 (description
5764 "Taxtastic is software written in python used to build and maintain
5765reference packages i.e. collections of reference trees, reference alignments,
5766profiles, and associated taxonomic information.")
5767 (license license:gpl3+)))
5768
de07c0db
RW		 5769(define-public vcftools
5770 (package
5771 (name "vcftools")
f4322542 5772 (version "0.1.15")
de07c0db
RW		 5773 (source (origin
5774 (method url-fetch)
5775 (uri (string-append
9b36e256
RJ		 5776 "https://github.com/vcftools/vcftools/releases/download/v"
5777 version "/vcftools-" version ".tar.gz"))
de07c0db
RW		 5778 (sha256
5779 (base32
f4322542 5780 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
de07c0db
RW		 5781 (build-system gnu-build-system)
5782 (arguments
5783 `(#:tests? #f ; no "check" target
5784 #:make-flags (list
7c3958e1 5785 "CFLAGS=-O2" ; override "-m64" flag
de07c0db
RW		 5786 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5787 (string-append "MANDIR=" (assoc-ref %outputs "out")
9b36e256
RJ		 5788 "/share/man/man1"))))
5789 (native-inputs
5790 `(("pkg-config" ,pkg-config)))
de07c0db
RW		 5791 (inputs
5792 `(("perl" ,perl)
5793 ("zlib" ,zlib)))
9b36e256 5794 (home-page "https://vcftools.github.io/")
de07c0db
RW		 5795 (synopsis "Tools for working with VCF files")
5796 (description
5797 "VCFtools is a program package designed for working with VCF files, such
5798as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5799provide easily accessible methods for working with complex genetic variation
5800data in the form of VCF files.")
5801 ;; The license is declared as LGPLv3 in the README and
9b36e256 5802 ;; at https://vcftools.github.io/license.html
de07c0db 5803 (license license:lgpl3)))
9c38b540 5804
35aa90a1
RW		 5805(define-public infernal
5806 (package
5807 (name "infernal")
5808 (version "1.1.2")
5809 (source (origin
5810 (method url-fetch)
5811 (uri (string-append "http://eddylab.org/software/infernal/"
5812 "infernal-" version ".tar.gz"))
5813 (sha256
5814 (base32
5815 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5816 (build-system gnu-build-system)
5817 (native-inputs
5818 `(("perl" ,perl))) ; for tests
5819 (home-page "http://eddylab.org/infernal/")
5820 (synopsis "Inference of RNA alignments")
5821 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5822searching DNA sequence databases for RNA structure and sequence similarities.
5823It is an implementation of a special case of profile stochastic context-free
5824grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5825profile, but it scores a combination of sequence consensus and RNA secondary
5826structure consensus, so in many cases, it is more capable of identifying RNA
5827homologs that conserve their secondary structure more than their primary
5828sequence.")
48409ef2
EF		 5829 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5830 (supported-systems '("i686-linux" "x86_64-linux"))
35aa90a1
RW		 5831 (license license:bsd-3)))
5832
b91cfa22
RW		 5833(define-public r-centipede
5834 (package
5835 (name "r-centipede")
5836 (version "1.2")
5837 (source (origin
5838 (method url-fetch)
5839 (uri (string-append "http://download.r-forge.r-project.org/"
5840 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5841 (sha256
5842 (base32
5843 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5844 (build-system r-build-system)
5845 (home-page "http://centipede.uchicago.edu/")
5846 (synopsis "Predict transcription factor binding sites")
5847 (description
5848 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5849of the genome that are bound by particular transcription factors. It starts
5850by identifying a set of candidate binding sites, and then aims to classify the
5851sites according to whether each site is bound or not bound by a transcription
5852factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5853between two different types of motif instances using as much relevant
5854information as possible.")
5855 (license (list license:gpl2+ license:gpl3+))))
5856
7b3df1e5
BW		 5857(define-public r-vegan
5858 (package
5859 (name "r-vegan")
8d11ef44 5860 (version "2.4-5")
7b3df1e5
BW		 5861 (source
5862 (origin
5863 (method url-fetch)
5864 (uri (cran-uri "vegan" version))
5865 (sha256
5866 (base32
8d11ef44 5867 "0cyyvn3xsjn24w590jn6z4xajafv7yzvj6c51vqi9q6m8v5831ya"))))
7b3df1e5 5868 (build-system r-build-system)
7b3df1e5 5869 (native-inputs
db2e4386 5870 `(("gfortran" ,gfortran)))
7b3df1e5
BW		 5871 (propagated-inputs
5872 `(("r-cluster" ,r-cluster)
5873 ("r-lattice" ,r-lattice)
aeb64f3c 5874 ("r-mass" ,r-mass)
7b3df1e5
BW		 5875 ("r-mgcv" ,r-mgcv)
5876 ("r-permute" ,r-permute)))
5877 (home-page "https://cran.r-project.org/web/packages/vegan")
5878 (synopsis "Functions for community ecology")
5879 (description
5880 "The vegan package provides tools for descriptive community ecology. It
5881has most basic functions of diversity analysis, community ordination and
5882dissimilarity analysis. Most of its multivariate tools can be used for other
5883data types as well.")
5884 (license license:gpl2+)))
5885
8c6de588
RW		 5886(define-public r-annotate
5887 (package
5888 (name "r-annotate")
654c29ac 5889 (version "1.56.1")
8c6de588
RW		 5890 (source
5891 (origin
5892 (method url-fetch)
5893 (uri (bioconductor-uri "annotate" version))
5894 (sha256
5895 (base32
654c29ac 5896 "14c5xd9kasvcwg5gbjys2c1vizxhlqlzxakqc2kml0kw97hmx0rq"))))
8c6de588
RW		 5897 (build-system r-build-system)
5898 (propagated-inputs
5899 `(("r-annotationdbi" ,r-annotationdbi)
5900 ("r-biobase" ,r-biobase)
5901 ("r-biocgenerics" ,r-biocgenerics)
5902 ("r-dbi" ,r-dbi)
d0f0579e 5903 ("r-rcurl" ,r-rcurl)
8c6de588
RW		 5904 ("r-xml" ,r-xml)
5905 ("r-xtable" ,r-xtable)))
5906 (home-page
5713bbf1 5907 "https://bioconductor.org/packages/annotate")
8c6de588 5908 (synopsis "Annotation for microarrays")
d1e4ad1b 5909 (description "This package provides R environments for the annotation of
8c6de588
RW		 5910microarrays.")
5911 (license license:artistic2.0)))
5912
efa6a1dd
RJ		 5913(define-public r-copynumber
5914 (package
5915 (name "r-copynumber")
5916 (version "1.18.0")
5917 (source (origin
5918 (method url-fetch)
5919 (uri (bioconductor-uri "copynumber" version))
5920 (sha256
5921 (base32
5922 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
5923 (build-system r-build-system)
5924 (propagated-inputs
5925 `(("r-s4vectors" ,r-s4vectors)
5926 ("r-iranges" ,r-iranges)
5927 ("r-genomicranges" ,r-genomicranges)
5928 ("r-biocgenerics" ,r-biocgenerics)))
5929 (home-page "https://bioconductor.org/packages/copynumber")
5930 (synopsis "Segmentation of single- and multi-track copy number data")
5931 (description
5932 "This package segments single- and multi-track copy number data by a
5933penalized least squares regression method.")
5934 (license license:artistic2.0)))
5935
07a664cd
RW		 5936(define-public r-geneplotter
5937 (package
5938 (name "r-geneplotter")
cb4d3ff2 5939 (version "1.56.0")
07a664cd
RW		 5940 (source
5941 (origin
5942 (method url-fetch)
5943 (uri (bioconductor-uri "geneplotter" version))
5944 (sha256
5945 (base32
cb4d3ff2 5946 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
07a664cd
RW		 5947 (build-system r-build-system)
5948 (propagated-inputs
5949 `(("r-annotate" ,r-annotate)
5950 ("r-annotationdbi" ,r-annotationdbi)
5951 ("r-biobase" ,r-biobase)
5952 ("r-biocgenerics" ,r-biocgenerics)
5953 ("r-lattice" ,r-lattice)
5954 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5713bbf1 5955 (home-page "https://bioconductor.org/packages/geneplotter")
07a664cd
RW		 5956 (synopsis "Graphics functions for genomic data")
5957 (description
5958 "This package provides functions for plotting genomic data.")
5959 (license license:artistic2.0)))
5960
2301fd3e
RW		 5961(define-public r-genefilter
5962 (package
5963 (name "r-genefilter")
554fac74 5964 (version "1.60.0")
2301fd3e
RW		 5965 (source
5966 (origin
5967 (method url-fetch)
5968 (uri (bioconductor-uri "genefilter" version))
5969 (sha256
5970 (base32
554fac74 5971 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
2301fd3e
RW		 5972 (build-system r-build-system)
5973 (native-inputs
5974 `(("gfortran" ,gfortran)))
5975 (propagated-inputs
5976 `(("r-annotate" ,r-annotate)
5977 ("r-annotationdbi" ,r-annotationdbi)
5978 ("r-biobase" ,r-biobase)
aeb64f3c
RW		 5979 ("r-s4vectors" ,r-s4vectors)
5980 ("r-survival" ,r-survival)))
5713bbf1 5981 (home-page "https://bioconductor.org/packages/genefilter")
2301fd3e
RW		 5982 (synopsis "Filter genes from high-throughput experiments")
5983 (description
5984 "This package provides basic functions for filtering genes from
5985high-throughput sequencing experiments.")
5986 (license license:artistic2.0)))
5987
ad34f0ac
RW		 5988(define-public r-deseq2
5989 (package
5990 (name "r-deseq2")
058644c0 5991 (version "1.18.1")
ad34f0ac
RW		 5992 (source
5993 (origin
5994 (method url-fetch)
5995 (uri (bioconductor-uri "DESeq2" version))
5996 (sha256
5997 (base32
058644c0 5998 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
ad34f0ac
RW		 5999 (properties `((upstream-name . "DESeq2")))
6000 (build-system r-build-system)
ad34f0ac
RW		 6001 (propagated-inputs
6002 `(("r-biobase" ,r-biobase)
6003 ("r-biocgenerics" ,r-biocgenerics)
6004 ("r-biocparallel" ,r-biocparallel)
6005 ("r-genefilter" ,r-genefilter)
6006 ("r-geneplotter" ,r-geneplotter)
6007 ("r-genomicranges" ,r-genomicranges)
6008 ("r-ggplot2" ,r-ggplot2)
6009 ("r-hmisc" ,r-hmisc)
6010 ("r-iranges" ,r-iranges)
6011 ("r-locfit" ,r-locfit)
6012 ("r-rcpp" ,r-rcpp)
6013 ("r-rcpparmadillo" ,r-rcpparmadillo)
6014 ("r-s4vectors" ,r-s4vectors)
6015 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5713bbf1 6016 (home-page "https://bioconductor.org/packages/DESeq2")
ad34f0ac
RW		 6017 (synopsis "Differential gene expression analysis")
6018 (description
6019 "This package provides functions to estimate variance-mean dependence in
6020count data from high-throughput nucleotide sequencing assays and test for
6021differential expression based on a model using the negative binomial
6022distribution.")
6023 (license license:lgpl3+)))
6024
86763fdd
RW		 6025(define-public r-dexseq
6026 (package
6027 (name "r-dexseq")
756ac725 6028 (version "1.24.2")
86763fdd
RW		 6029 (source
6030 (origin
6031 (method url-fetch)
6032 (uri (bioconductor-uri "DEXSeq" version))
6033 (sha256
6034 (base32
756ac725 6035 "18nh8ynxirfwkmc4sawdxgl7w1sl9ny5zpv8zbhv9vi5vgb8pxmj"))))
86763fdd
RW		 6036 (properties `((upstream-name . "DEXSeq")))
6037 (build-system r-build-system)
6038 (propagated-inputs
6039 `(("r-annotationdbi" ,r-annotationdbi)
6040 ("r-biobase" ,r-biobase)
6041 ("r-biocgenerics" ,r-biocgenerics)
6042 ("r-biocparallel" ,r-biocparallel)
6043 ("r-biomart" ,r-biomart)
6044 ("r-deseq2" ,r-deseq2)
6045 ("r-genefilter" ,r-genefilter)
6046 ("r-geneplotter" ,r-geneplotter)
6047 ("r-genomicranges" ,r-genomicranges)
6048 ("r-hwriter" ,r-hwriter)
6049 ("r-iranges" ,r-iranges)
6050 ("r-rcolorbrewer" ,r-rcolorbrewer)
6051 ("r-rsamtools" ,r-rsamtools)
6052 ("r-s4vectors" ,r-s4vectors)
6053 ("r-statmod" ,r-statmod)
6054 ("r-stringr" ,r-stringr)
6055 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5713bbf1 6056 (home-page "https://bioconductor.org/packages/DEXSeq")
86763fdd
RW		 6057 (synopsis "Inference of differential exon usage in RNA-Seq")
6058 (description
6059 "This package is focused on finding differential exon usage using RNA-seq
6060exon counts between samples with different experimental designs. It provides
6061functions that allows the user to make the necessary statistical tests based
6062on a model that uses the negative binomial distribution to estimate the
6063variance between biological replicates and generalized linear models for
6064testing. The package also provides functions for the visualization and
6065exploration of the results.")
6066 (license license:gpl3+)))
6067
e8163773
RW		 6068(define-public r-annotationforge
6069 (package
6070 (name "r-annotationforge")
727706ad 6071 (version "1.20.0")
e8163773
RW		 6072 (source
6073 (origin
6074 (method url-fetch)
6075 (uri (bioconductor-uri "AnnotationForge" version))
6076 (sha256
6077 (base32
727706ad 6078 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
e8163773
RW		 6079 (properties
6080 `((upstream-name . "AnnotationForge")))
6081 (build-system r-build-system)
6082 (propagated-inputs
6083 `(("r-annotationdbi" ,r-annotationdbi)
6084 ("r-biobase" ,r-biobase)
6085 ("r-biocgenerics" ,r-biocgenerics)
6086 ("r-dbi" ,r-dbi)
55cd914c 6087 ("r-rcurl" ,r-rcurl)
e8163773
RW		 6088 ("r-rsqlite" ,r-rsqlite)
6089 ("r-s4vectors" ,r-s4vectors)
6090 ("r-xml" ,r-xml)))
5713bbf1 6091 (home-page "https://bioconductor.org/packages/AnnotationForge")
e8163773
RW		 6092 (synopsis "Code for building annotation database packages")
6093 (description
6094 "This package provides code for generating Annotation packages and their
6095databases. Packages produced are intended to be used with AnnotationDbi.")
6096 (license license:artistic2.0)))
6097
cd9e7dc7
RW		 6098(define-public r-rbgl
6099 (package
6100 (name "r-rbgl")
c25154e5 6101 (version "1.54.0")
cd9e7dc7
RW		 6102 (source
6103 (origin
6104 (method url-fetch)
6105 (uri (bioconductor-uri "RBGL" version))
6106 (sha256
6107 (base32
c25154e5 6108 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
cd9e7dc7
RW		 6109 (properties `((upstream-name . "RBGL")))
6110 (build-system r-build-system)
6111 (propagated-inputs `(("r-graph" ,r-graph)))
5713bbf1 6112 (home-page "https://www.bioconductor.org/packages/RBGL")
cd9e7dc7
RW		 6113 (synopsis "Interface to the Boost graph library")
6114 (description
6115 "This package provides a fairly extensive and comprehensive interface to
6116the graph algorithms contained in the Boost library.")
6117 (license license:artistic2.0)))
6118
ad740ff8
RW		 6119(define-public r-gseabase
6120 (package
6121 (name "r-gseabase")
4220ab0c 6122 (version "1.40.1")
ad740ff8
RW		 6123 (source
6124 (origin
6125 (method url-fetch)
6126 (uri (bioconductor-uri "GSEABase" version))
6127 (sha256
6128 (base32
4220ab0c 6129 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
ad740ff8
RW		 6130 (properties `((upstream-name . "GSEABase")))
6131 (build-system r-build-system)
6132 (propagated-inputs
6133 `(("r-annotate" ,r-annotate)
6134 ("r-annotationdbi" ,r-annotationdbi)
6135 ("r-biobase" ,r-biobase)
6136 ("r-biocgenerics" ,r-biocgenerics)
6137 ("r-graph" ,r-graph)
6138 ("r-xml" ,r-xml)))
5713bbf1 6139 (home-page "https://bioconductor.org/packages/GSEABase")
ad740ff8
RW		 6140 (synopsis "Gene set enrichment data structures and methods")
6141 (description
6142 "This package provides classes and methods to support @dfn{Gene Set
6143Enrichment Analysis} (GSEA).")
6144 (license license:artistic2.0)))
6145
1a1931f7
RW		 6146(define-public r-category
6147 (package
6148 (name "r-category")
2404cc42 6149 (version "2.44.0")
1a1931f7
RW		 6150 (source
6151 (origin
6152 (method url-fetch)
6153 (uri (bioconductor-uri "Category" version))
6154 (sha256
6155 (base32
2404cc42 6156 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
1a1931f7
RW		 6157 (properties `((upstream-name . "Category")))
6158 (build-system r-build-system)
6159 (propagated-inputs
6160 `(("r-annotate" ,r-annotate)
6161 ("r-annotationdbi" ,r-annotationdbi)
6162 ("r-biobase" ,r-biobase)
6163 ("r-biocgenerics" ,r-biocgenerics)
6164 ("r-genefilter" ,r-genefilter)
6165 ("r-graph" ,r-graph)
6166 ("r-gseabase" ,r-gseabase)
6167 ("r-matrix" ,r-matrix)
6168 ("r-rbgl" ,r-rbgl)
2404cc42 6169 ("r-dbi" ,r-dbi)))
5713bbf1 6170 (home-page "https://bioconductor.org/packages/Category")
1a1931f7
RW		 6171 (synopsis "Category analysis")
6172 (description
6173 "This package provides a collection of tools for performing category
6174analysis.")
6175 (license license:artistic2.0)))
6176
89f40c5e
RW		 6177(define-public r-gostats
6178 (package
6179 (name "r-gostats")
eb3f5cc7 6180 (version "2.44.0")
89f40c5e
RW		 6181 (source
6182 (origin
6183 (method url-fetch)
6184 (uri (bioconductor-uri "GOstats" version))
6185 (sha256
6186 (base32
eb3f5cc7 6187 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
89f40c5e
RW		 6188 (properties `((upstream-name . "GOstats")))
6189 (build-system r-build-system)
6190 (propagated-inputs
6191 `(("r-annotate" ,r-annotate)
6192 ("r-annotationdbi" ,r-annotationdbi)
6193 ("r-annotationforge" ,r-annotationforge)
6194 ("r-biobase" ,r-biobase)
6195 ("r-category" ,r-category)
6196 ("r-go-db" ,r-go-db)
6197 ("r-graph" ,r-graph)
eb3f5cc7 6198 ("r-rgraphviz" ,r-rgraphviz)
89f40c5e 6199 ("r-rbgl" ,r-rbgl)))
5713bbf1 6200 (home-page "https://bioconductor.org/packages/GOstats")
89f40c5e
RW		 6201 (synopsis "Tools for manipulating GO and microarrays")
6202 (description
6203 "This package provides a set of tools for interacting with GO and
6204microarray data. A variety of basic manipulation tools for graphs, hypothesis
6205testing and other simple calculations.")
6206 (license license:artistic2.0)))
6207
cb99d457
RW		 6208(define-public r-shortread
6209 (package
6210 (name "r-shortread")
843826e2 6211 (version "1.36.0")
cb99d457
RW		 6212 (source
6213 (origin
6214 (method url-fetch)
6215 (uri (bioconductor-uri "ShortRead" version))
6216 (sha256
6217 (base32
843826e2 6218 "06mknlsmd4hnaxzdjapgvp2kgdnf9w103y500dsac5jgsz4vwzcz"))))
cb99d457
RW		 6219 (properties `((upstream-name . "ShortRead")))
6220 (build-system r-build-system)
6221 (inputs
6222 `(("zlib" ,zlib)))
6223 (propagated-inputs
6224 `(("r-biobase" ,r-biobase)
6225 ("r-biocgenerics" ,r-biocgenerics)
6226 ("r-biocparallel" ,r-biocparallel)
6227 ("r-biostrings" ,r-biostrings)
6228 ("r-genomeinfodb" ,r-genomeinfodb)
6229 ("r-genomicalignments" ,r-genomicalignments)
6230 ("r-genomicranges" ,r-genomicranges)
6231 ("r-hwriter" ,r-hwriter)
6232 ("r-iranges" ,r-iranges)
6233 ("r-lattice" ,r-lattice)
6234 ("r-latticeextra" ,r-latticeextra)
6235 ("r-rsamtools" ,r-rsamtools)
6236 ("r-s4vectors" ,r-s4vectors)
6237 ("r-xvector" ,r-xvector)
6238 ("r-zlibbioc" ,r-zlibbioc)))
5713bbf1 6239 (home-page "https://bioconductor.org/packages/ShortRead")
cb99d457
RW		 6240 (synopsis "FASTQ input and manipulation tools")
6241 (description
6242 "This package implements sampling, iteration, and input of FASTQ files.
6243It includes functions for filtering and trimming reads, and for generating a
6244quality assessment report. Data are represented as
6245@code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6246purposes. The package also contains legacy support for early single-end,
6247ungapped alignment formats.")
6248 (license license:artistic2.0)))
6249
7f903d73
RW		 6250(define-public r-systempiper
6251 (package
6252 (name "r-systempiper")
b5375525 6253 (version "1.12.0")
7f903d73
RW		 6254 (source
6255 (origin
6256 (method url-fetch)
6257 (uri (bioconductor-uri "systemPipeR" version))
6258 (sha256
6259 (base32
b5375525 6260 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
7f903d73
RW		 6261 (properties `((upstream-name . "systemPipeR")))
6262 (build-system r-build-system)
6263 (propagated-inputs
6264 `(("r-annotate" ,r-annotate)
6265 ("r-batchjobs" ,r-batchjobs)
6266 ("r-biocgenerics" ,r-biocgenerics)
6267 ("r-biostrings" ,r-biostrings)
6268 ("r-deseq2" ,r-deseq2)
6269 ("r-edger" ,r-edger)
6270 ("r-genomicfeatures" ,r-genomicfeatures)
6271 ("r-genomicranges" ,r-genomicranges)
6272 ("r-ggplot2" ,r-ggplot2)
6273 ("r-go-db" ,r-go-db)
6274 ("r-gostats" ,r-gostats)
6275 ("r-limma" ,r-limma)
6276 ("r-pheatmap" ,r-pheatmap)
6277 ("r-rjson" ,r-rjson)
6278 ("r-rsamtools" ,r-rsamtools)
6279 ("r-shortread" ,r-shortread)
6280 ("r-summarizedexperiment" ,r-summarizedexperiment)
6281 ("r-variantannotation" ,r-variantannotation)))
6282 (home-page "https://github.com/tgirke/systemPipeR")
6283 (synopsis "Next generation sequencing workflow and reporting environment")
6284 (description
6285 "This R package provides tools for building and running automated
6286end-to-end analysis workflows for a wide range of @dfn{next generation
6287sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6288Important features include a uniform workflow interface across different NGS
6289applications, automated report generation, and support for running both R and
6290command-line software, such as NGS aligners or peak/variant callers, on local
6291computers or compute clusters. Efficient handling of complex sample sets and
6292experimental designs is facilitated by a consistently implemented sample
6293annotation infrastructure.")
6294 (license license:artistic2.0)))
6295
684f29bd
RW		 6296(define-public r-grohmm
6297 (package
6298 (name "r-grohmm")
704fe4d1 6299 (version "1.12.0")
684f29bd
RW		 6300 (source
6301 (origin
6302 (method url-fetch)
6303 (uri (bioconductor-uri "groHMM" version))
6304 (sha256
6305 (base32
704fe4d1 6306 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
684f29bd
RW		 6307 (properties `((upstream-name . "groHMM")))
6308 (build-system r-build-system)
6309 (propagated-inputs
6310 `(("r-genomeinfodb" ,r-genomeinfodb)
6311 ("r-genomicalignments" ,r-genomicalignments)
6312 ("r-genomicranges" ,r-genomicranges)
6313 ("r-iranges" ,r-iranges)
aeb64f3c 6314 ("r-mass" ,r-mass)
684f29bd
RW		 6315 ("r-rtracklayer" ,r-rtracklayer)
6316 ("r-s4vectors" ,r-s4vectors)))
6317 (home-page "https://github.com/Kraus-Lab/groHMM")
6318 (synopsis "GRO-seq analysis pipeline")
6319 (description
6320 "This package provides a pipeline for the analysis of GRO-seq data.")
6321 (license license:gpl3+)))
6322
f3cfe451
RW		 6323(define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6324 (package
6325 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6326 (version "3.2.2")
6327 (source (origin
6328 (method url-fetch)
6329 ;; We cannot use bioconductor-uri here because this tarball is
6330 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 6331 (uri (string-append "https://bioconductor.org/packages/"
f3cfe451
RW		 6332 "release/data/annotation/src/contrib"
6333 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6334 version ".tar.gz"))
6335 (sha256
6336 (base32
6337 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6338 (properties
6339 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6340 (build-system r-build-system)
6341 ;; As this package provides little more than a very large data file it
6342 ;; doesn't make sense to build substitutes.
6343 (arguments `(#:substitutable? #f))
6344 (propagated-inputs
6345 `(("r-genomicfeatures" ,r-genomicfeatures)))
6346 (home-page
5713bbf1 6347 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
f3cfe451
RW		 6348 (synopsis "Annotation package for human genome in TxDb format")
6349 (description
6350 "This package provides an annotation database of Homo sapiens genome
6351data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6352track. The database is exposed as a @code{TxDb} object.")
6353 (license license:artistic2.0)))
6354
325c039c
RJ		 6355(define-public r-sparql
6356 (package
6357 (name "r-sparql")
6358 (version "1.16")
6359 (source (origin
6360 (method url-fetch)
6361 (uri (cran-uri "SPARQL" version))
6362 (sha256
6363 (base32
6364 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6365 (properties `((upstream-name . "SPARQL")))
6366 (build-system r-build-system)
6367 (propagated-inputs
6368 `(("r-rcurl" ,r-rcurl)
6369 ("r-xml" ,r-xml)))
6370 (home-page "http://cran.r-project.org/web/packages/SPARQL")
6371 (synopsis "SPARQL client for R")
6372 (description "This package provides an interface to use SPARQL to pose
6373SELECT or UPDATE queries to an end-point.")
6374 ;; The only license indication is found in the DESCRIPTION file,
6375 ;; which states GPL-3. So we cannot assume GPLv3+.
6376 (license license:gpl3)))
6377
a2950fa4
BW		 6378(define-public vsearch
6379 (package
6380 (name "vsearch")
7c087150 6381 (version "2.6.0")
a2950fa4
BW		 6382 (source
6383 (origin
6384 (method url-fetch)
6385 (uri (string-append
6386 "https://github.com/torognes/vsearch/archive/v"
6387 version ".tar.gz"))
6388 (file-name (string-append name "-" version ".tar.gz"))
6389 (sha256
6390 (base32
7c087150 6391 "0rplgpvsdkxw0k371ckxrp6i77jn93ckhslaazwbyd85m83nkynr"))
206af46f 6392 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
a2950fa4
BW		 6393 (snippet
6394 '(begin
206af46f
BW		 6395 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6396 ;; for this in the patch.
cf6edaba
BW		 6397 (delete-file "src/city.h")
6398 (delete-file "src/citycrc.h")
6399 (delete-file "src/city.cc")
a2950fa4
BW		 6400 #t))))
6401 (build-system gnu-build-system)
6402 (arguments
6403 `(#:phases
6404 (modify-phases %standard-phases
d10092b8
KK		 6405 (add-after 'unpack 'autogen
6406 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
a2950fa4
BW		 6407 (inputs
6408 `(("zlib" ,zlib)
6409 ("bzip2" ,bzip2)
6410 ("cityhash" ,cityhash)))
6411 (native-inputs
6412 `(("autoconf" ,autoconf)
6413 ("automake" ,automake)))
6414 (synopsis "Sequence search tools for metagenomics")
6415 (description
6416 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6417dereplication, pairwise alignment, shuffling, subsampling, sorting and
6418masking. The tool takes advantage of parallelism in the form of SIMD
6419vectorization as well as multiple threads to perform accurate alignments at
6420high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6421Needleman-Wunsch).")
6422 (home-page "https://github.com/torognes/vsearch")
6f04e515
BW		 6423 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6424 ;; platforms.
6425 (supported-systems '("x86_64-linux"))
a2950fa4
BW		 6426 ;; Dual licensed; also includes public domain source.
6427 (license (list license:gpl3 license:bsd-2))))
6428
07837874
RW		 6429(define-public pardre
6430 (package
6431 (name "pardre")
7922ab8f
BW		 6432 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6433 (version "1.1.5-1")
07837874
RW		 6434 (source
6435 (origin
6436 (method url-fetch)
6437 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7922ab8f 6438 "1.1.5" ".tar.gz"))
07837874
RW		 6439 (sha256
6440 (base32
7922ab8f 6441 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
07837874
RW		 6442 (build-system gnu-build-system)
6443 (arguments
6444 `(#:tests? #f ; no tests included
6445 #:phases
6446 (modify-phases %standard-phases
6447 (delete 'configure)
6448 (replace 'install
6449 (lambda* (#:key outputs #:allow-other-keys)
6450 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
07837874
RW		 6451 (install-file "ParDRe" bin)
6452 #t))))))
6453 (inputs
6454 `(("openmpi" ,openmpi)
6455 ("zlib" ,zlib)))
6456 (synopsis "Parallel tool to remove duplicate DNA reads")
6457 (description
6458 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6459Duplicate reads can be seen as identical or nearly identical sequences with
6460some mismatches. This tool lets users avoid the analysis of unnecessary
6461reads, reducing the time of subsequent procedures with the
6462dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6463in order to exploit the parallel capabilities of multicore clusters. It is
6464faster than multithreaded counterparts (end of 2015) for the same number of
6465cores and, thanks to the message-passing technology, it can be executed on
6466clusters.")
6467 (home-page "https://sourceforge.net/projects/pardre/")
6468 (license license:gpl3+)))
6469
e4a44a6a
BW		 6470(define-public ruby-bio-kseq
6471 (package
6472 (name "ruby-bio-kseq")
6473 (version "0.0.2")
6474 (source
6475 (origin
6476 (method url-fetch)
6477 (uri (rubygems-uri "bio-kseq" version))
6478 (sha256
6479 (base32
6480 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6481 (build-system ruby-build-system)
6482 (arguments
6483 `(#:test-target "spec"))
6484 (native-inputs
6485 `(("bundler" ,bundler)
6486 ("ruby-rspec" ,ruby-rspec)
6487 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6488 (inputs
6489 `(("zlib" ,zlib)))
6490 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6491 (description
6492 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6493FASTQ parsing code. It provides a fast iterator over sequences and their
6494quality scores.")
6495 (home-page "https://github.com/gusevfe/bio-kseq")
6496 (license license:expat)))
6497
9c38b540
PP		 6498(define-public bio-locus
6499 (package
6500 (name "bio-locus")
6501 (version "0.0.7")
6502 (source
6503 (origin
6504 (method url-fetch)
6505 (uri (rubygems-uri "bio-locus" version))
6506 (sha256
6507 (base32
6508 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6509 (build-system ruby-build-system)
6510 (native-inputs
6511 `(("ruby-rspec" ,ruby-rspec)))
6512 (synopsis "Tool for fast querying of genome locations")
6513 (description
6514 "Bio-locus is a tabix-like tool for fast querying of genome
6515locations. Many file formats in bioinformatics contain records that
6516start with a chromosome name and a position for a SNP, or a start-end
6517position for indels. Bio-locus allows users to store this chr+pos or
6518chr+pos+alt information in a database.")
6519 (home-page "https://github.com/pjotrp/bio-locus")
6520 (license license:expat)))
edb15985 6521
b2bddb07
PP		 6522(define-public bio-blastxmlparser
6523 (package
6524 (name "bio-blastxmlparser")
6525 (version "2.0.4")
6526 (source (origin
6527 (method url-fetch)
6528 (uri (rubygems-uri "bio-blastxmlparser" version))
6529 (sha256
6530 (base32
6531 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6532 (build-system ruby-build-system)
6533 (propagated-inputs
6534 `(("ruby-bio-logger" ,ruby-bio-logger)
6535 ("ruby-nokogiri" ,ruby-nokogiri)))
6536 (inputs
6537 `(("ruby-rspec" ,ruby-rspec)))
6538 (synopsis "Fast big data BLAST XML parser and library")
6539 (description
6540 "Very fast parallel big-data BLAST XML file parser which can be used as
6541command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6542generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7bf837fd 6543 (home-page "https://github.com/pjotrp/blastxmlparser")
b2bddb07
PP		 6544 (license license:expat)))
6545
edb15985
PP		 6546(define-public bioruby
6547 (package
6548 (name "bioruby")
dbf9d371 6549 (version "1.5.1")
edb15985
PP		 6550 (source
6551 (origin
6552 (method url-fetch)
6553 (uri (rubygems-uri "bio" version))
6554 (sha256
6555 (base32
dbf9d371 6556 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
edb15985
PP		 6557 (build-system ruby-build-system)
6558 (propagated-inputs
6559 `(("ruby-libxml" ,ruby-libxml)))
6560 (native-inputs
6561 `(("which" ,which))) ; required for test phase
6562 (arguments
6563 `(#:phases
6564 (modify-phases %standard-phases
6565 (add-before 'build 'patch-test-command
6566 (lambda _
6567 (substitute* '("test/functional/bio/test_command.rb")
6568 (("/bin/sh") (which "sh")))
6569 (substitute* '("test/functional/bio/test_command.rb")
6570 (("/bin/ls") (which "ls")))
6571 (substitute* '("test/functional/bio/test_command.rb")
6572 (("which") (which "which")))
6573 (substitute* '("test/functional/bio/test_command.rb",
6574 "test/data/command/echoarg2.sh")
6575 (("/bin/echo") (which "echo")))
6576 #t)))))
6577 (synopsis "Ruby library, shell and utilities for bioinformatics")
6578 (description "BioRuby comes with a comprehensive set of Ruby development
6579tools and libraries for bioinformatics and molecular biology. BioRuby has
6580components for sequence analysis, pathway analysis, protein modelling and
6581phylogenetic analysis; it supports many widely used data formats and provides
6582easy access to databases, external programs and public web services, including
6583BLAST, KEGG, GenBank, MEDLINE and GO.")
6584 (home-page "http://bioruby.org/")
6585 ;; Code is released under Ruby license, except for setup
6586 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6587 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
a5002ae7 6588
9fba89e8
RW		 6589(define-public r-acsnminer
6590 (package
6591 (name "r-acsnminer")
0b54b4c9 6592 (version "0.16.8.25")
9fba89e8
RW		 6593 (source (origin
6594 (method url-fetch)
6595 (uri (cran-uri "ACSNMineR" version))
6596 (sha256
6597 (base32
0b54b4c9 6598 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
9fba89e8
RW		 6599 (properties `((upstream-name . "ACSNMineR")))
6600 (build-system r-build-system)
6601 (propagated-inputs
6602 `(("r-ggplot2" ,r-ggplot2)
6603 ("r-gridextra" ,r-gridextra)))
6604 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6605 (synopsis "Gene enrichment analysis")
6606 (description
6607 "This package provides tools to compute and represent gene set enrichment
6608or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6609Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6610enrichment can be run with hypergeometric test or Fisher exact test, and can
6611use multiple corrections. Visualization of data can be done either by
6612barplots or heatmaps.")
6613 (license license:gpl2+)))
6614
d29b25c4
RW		 6615(define-public r-biocgenerics
6616 (package
6617 (name "r-biocgenerics")
d61fc4e1 6618 (version "0.24.0")
d29b25c4
RW		 6619 (source (origin
6620 (method url-fetch)
6621 (uri (bioconductor-uri "BiocGenerics" version))
6622 (sha256
6623 (base32
d61fc4e1 6624 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
d29b25c4 6625 (properties
1d216b6e 6626 `((upstream-name . "BiocGenerics")))
d29b25c4 6627 (build-system r-build-system)
5713bbf1 6628 (home-page "https://bioconductor.org/packages/BiocGenerics")
d29b25c4
RW		 6629 (synopsis "S4 generic functions for Bioconductor")
6630 (description
6631 "This package provides S4 generic functions needed by many Bioconductor
6632packages.")
6633 (license license:artistic2.0)))
6634
eb24341f
RJ		 6635(define-public r-biocinstaller
6636 (package
6637 (name "r-biocinstaller")
32414616 6638 (version "1.28.0")
eb24341f
RJ		 6639 (source (origin
6640 (method url-fetch)
6641 (uri (bioconductor-uri "BiocInstaller" version))
6642 (sha256
6643 (base32
32414616 6644 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
eb24341f
RJ		 6645 (properties
6646 `((upstream-name . "BiocInstaller")))
6647 (build-system r-build-system)
5713bbf1 6648 (home-page "https://bioconductor.org/packages/BiocInstaller")
eb24341f
RJ		 6649 (synopsis "Install Bioconductor packages")
6650 (description "This package is used to install and update R packages from
6651Bioconductor, CRAN, and Github.")
6652 (license license:artistic2.0)))
6653
207ce8fb
RJ		 6654(define-public r-biocviews
6655 (package
6656 (name "r-biocviews")
c7782c3f 6657 (version "1.46.0")
207ce8fb
RJ		 6658 (source (origin
6659 (method url-fetch)
6660 (uri (bioconductor-uri "biocViews" version))
6661 (sha256
6662 (base32
c7782c3f 6663 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
207ce8fb
RJ		 6664 (properties
6665 `((upstream-name . "biocViews")))
6666 (build-system r-build-system)
6667 (propagated-inputs
6668 `(("r-biobase" ,r-biobase)
6669 ("r-graph" ,r-graph)
6670 ("r-rbgl" ,r-rbgl)
6671 ("r-rcurl" ,r-rcurl)
6672 ("r-xml" ,r-xml)
207ce8fb 6673 ("r-runit" ,r-runit)))
5713bbf1 6674 (home-page "https://bioconductor.org/packages/biocViews")
207ce8fb
RJ		 6675 (synopsis "Bioconductor package categorization helper")
6676 (description "The purpose of biocViews is to create HTML pages that
6677categorize packages in a Bioconductor package repository according to keywords,
6678also known as views, in a controlled vocabulary.")
6679 (license license:artistic2.0)))
6680
2abfc5b8
RJ		 6681(define-public r-bookdown
6682 (package
6683 (name "r-bookdown")
6bd27981 6684 (version "0.5")
2abfc5b8
RJ		 6685 (source (origin
6686 (method url-fetch)
6687 (uri (cran-uri "bookdown" version))
6688 (sha256
6689 (base32
6bd27981 6690 "0zm63kr4f4kja4qpwkzl119zzyciqj7ihajfqgfjpgb4dzaiycxp"))))
2abfc5b8
RJ		 6691 (build-system r-build-system)
6692 (propagated-inputs
6693 `(("r-htmltools" ,r-htmltools)
6694 ("r-knitr" ,r-knitr)
6695 ("r-rmarkdown" ,r-rmarkdown)
6696 ("r-yaml" ,r-yaml)))
6697 (home-page "https://github.com/rstudio/bookdown")
6698 (synopsis "Authoring books and technical documents with R markdown")
6699 (description "This package provides output formats and utilities for
6700authoring books and technical documents with R Markdown.")
6701 (license license:gpl3)))
6702
99df12cd
RJ		 6703(define-public r-biocstyle
6704 (package
6705 (name "r-biocstyle")
7665fb39 6706 (version "2.6.1")
99df12cd
RJ		 6707 (source (origin
6708 (method url-fetch)
6709 (uri (bioconductor-uri "BiocStyle" version))
6710 (sha256
6711 (base32
7665fb39 6712 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
99df12cd
RJ		 6713 (properties
6714 `((upstream-name . "BiocStyle")))
6715 (build-system r-build-system)
3bef24c9
RJ		 6716 (propagated-inputs
6717 `(("r-bookdown" ,r-bookdown)
6718 ("r-knitr" ,r-knitr)
6719 ("r-rmarkdown" ,r-rmarkdown)
6720 ("r-yaml" ,r-yaml)))
5713bbf1 6721 (home-page "https://bioconductor.org/packages/BiocStyle")
99df12cd
RJ		 6722 (synopsis "Bioconductor formatting styles")
6723 (description "This package provides standard formatting styles for
6724Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6725functionality.")
6726 (license license:artistic2.0)))
6727
4644644a
RJ		 6728(define-public r-bioccheck
6729 (package
6730 (name "r-bioccheck")
7373b416 6731 (version "1.14.0")
4644644a
RJ		 6732 (source (origin
6733 (method url-fetch)
6734 (uri (bioconductor-uri "BiocCheck" version))
6735 (sha256
6736 (base32
7373b416 6737 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
4644644a
RJ		 6738 (properties
6739 `((upstream-name . "BiocCheck")))
6740 (build-system r-build-system)
6741 (arguments
6742 '(#:phases
6743 (modify-phases %standard-phases
6744 ;; This package can be used by calling BiocCheck(<package>) from
6745 ;; within R, or by running R CMD BiocCheck <package>. This phase
6746 ;; makes sure the latter works. For this to work, the BiocCheck
6747 ;; script must be somewhere on the PATH (not the R bin directory).
6748 (add-after 'install 'install-bioccheck-subcommand
6749 (lambda* (#:key outputs #:allow-other-keys)
6750 (let* ((out (assoc-ref outputs "out"))
6751 (dest-dir (string-append out "/bin"))
6752 (script-dir
6753 (string-append out "/site-library/BiocCheck/script/")))
6754 (mkdir-p dest-dir)
6755 (symlink (string-append script-dir "/checkBadDeps.R")
6756 (string-append dest-dir "/checkBadDeps.R"))
6757 (symlink (string-append script-dir "/BiocCheck")
6758 (string-append dest-dir "/BiocCheck")))
6759 #t)))))
4644644a 6760 (propagated-inputs
aeb64f3c
RW		 6761 `(("r-codetools" ,r-codetools)
6762 ("r-graph" ,r-graph)
4644644a
RJ		 6763 ("r-httr" ,r-httr)
6764 ("r-optparse" ,r-optparse)
4644644a 6765 ("r-biocinstaller" ,r-biocinstaller)
7373b416
RW		 6766 ("r-biocviews" ,r-biocviews)
6767 ("r-stringdist" ,r-stringdist)))
5713bbf1 6768 (home-page "https://bioconductor.org/packages/BiocCheck")
4644644a
RJ		 6769 (synopsis "Executes Bioconductor-specific package checks")
6770 (description "This package contains tools to perform additional quality
6771checks on R packages that are to be submitted to the Bioconductor repository.")
6772 (license license:artistic2.0)))
6773
2acaaee5
RJ		 6774(define-public r-getopt
6775 (package
6776 (name "r-getopt")
d2081a17 6777 (version "1.20.1")
2acaaee5
RJ		 6778 (source
6779 (origin
6780 (method url-fetch)
6781 (uri (cran-uri "getopt" version))
6782 (sha256
6783 (base32
d2081a17 6784 "0m463mcvixh54i3ng42n0vxmdlf97dgbfs2sf9wnjm782ddw68hm"))))
2acaaee5
RJ		 6785 (build-system r-build-system)
6786 (home-page "https://github.com/trevorld/getopt")
6787 (synopsis "Command-line option processor for R")
6788 (description
6789 "This package is designed to be used with Rscript to write shebang
6790scripts that accept short and long options. Many users will prefer to
6791use the packages @code{optparse} or @code{argparse} which add extra
6792features like automatically generated help options and usage texts,
6793support for default values, positional argument support, etc.")
6794 (license license:gpl2+)))
6795
c79ad57a
RJ		 6796(define-public r-optparse
6797 (package
6798 (name "r-optparse")
7150f1c3 6799 (version "1.4.4")
c79ad57a
RJ		 6800 (source
6801 (origin
6802 (method url-fetch)
6803 (uri (cran-uri "optparse" version))
6804 (sha256
6805 (base32
7150f1c3 6806 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
c79ad57a
RJ		 6807 (build-system r-build-system)
6808 (propagated-inputs
6809 `(("r-getopt" ,r-getopt)))
6810 (home-page
6811 "https://github.com/trevorld/optparse")
6812 (synopsis "Command line option parser")
6813 (description
6814 "This package provides a command line parser inspired by Python's
6815@code{optparse} library to be used with Rscript to write shebang scripts
6816that accept short and long options.")
6817 (license license:gpl2+)))
6818
247d498a
RJ		 6819(define-public r-dnacopy
6820 (package
6821 (name "r-dnacopy")
94fd86e5 6822 (version "1.52.0")
247d498a
RJ		 6823 (source (origin
6824 (method url-fetch)
6825 (uri (bioconductor-uri "DNAcopy" version))
6826 (sha256
6827 (base32
94fd86e5 6828 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
247d498a
RJ		 6829 (properties
6830 `((upstream-name . "DNAcopy")))
6831 (build-system r-build-system)
6832 (inputs
6833 `(("gfortran" ,gfortran)))
5697fdc3 6834 (home-page "https://bioconductor.org/packages/DNAcopy")
247d498a
RJ		 6835 (synopsis "Implementation of a circular binary segmentation algorithm")
6836 (description "This package implements the circular binary segmentation (CBS)
6837algorithm to segment DNA copy number data and identify genomic regions with
6838abnormal copy number.")
6839 (license license:gpl2+)))
6840
7485129e
RW		 6841(define-public r-s4vectors
6842 (package
6843 (name "r-s4vectors")
41f0f949 6844 (version "0.16.0")
7485129e
RW		 6845 (source (origin
6846 (method url-fetch)
6847 (uri (bioconductor-uri "S4Vectors" version))
6848 (sha256
6849 (base32
41f0f949 6850 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
7485129e 6851 (properties
1d216b6e 6852 `((upstream-name . "S4Vectors")))
7485129e
RW		 6853 (build-system r-build-system)
6854 (propagated-inputs
6855 `(("r-biocgenerics" ,r-biocgenerics)))
5713bbf1 6856 (home-page "https://bioconductor.org/packages/S4Vectors")
7485129e
RW		 6857 (synopsis "S4 implementation of vectors and lists")
6858 (description
6859 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6860classes and a set of generic functions that extend the semantic of ordinary
6861vectors and lists in R. Package developers can easily implement vector-like
6862or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6863In addition, a few low-level concrete subclasses of general interest (e.g.
6864@code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6865S4Vectors package itself.")
6866 (license license:artistic2.0)))
6867
274da826
RW		 6868(define-public r-seqinr
6869 (package
6870 (name "r-seqinr")
023aa8ff 6871 (version "3.4-5")
274da826
RW		 6872 (source
6873 (origin
6874 (method url-fetch)
6875 (uri (cran-uri "seqinr" version))
6876 (sha256
6877 (base32
023aa8ff 6878 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
274da826
RW		 6879 (build-system r-build-system)
6880 (propagated-inputs
3b851cd4
RW		 6881 `(("r-ade4" ,r-ade4)
6882 ("r-segmented" ,r-segmented)))
274da826
RW		 6883 (inputs
6884 `(("zlib" ,zlib)))
6885 (home-page "http://seqinr.r-forge.r-project.org/")
6886 (synopsis "Biological sequences retrieval and analysis")
6887 (description
6888 "This package provides tools for exploratory data analysis and data
6889visualization of biological sequence (DNA and protein) data. It also includes
6890utilities for sequence data management under the ACNUC system.")
6891 (license license:gpl2+)))
6892
78addcb0
RW		 6893(define-public r-iranges
6894 (package
6895 (name "r-iranges")
9e482c20 6896 (version "2.12.0")
78addcb0
RW		 6897 (source (origin
6898 (method url-fetch)
6899 (uri (bioconductor-uri "IRanges" version))
6900 (sha256
6901 (base32
9e482c20 6902 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
78addcb0 6903 (properties
1d216b6e 6904 `((upstream-name . "IRanges")))
78addcb0
RW		 6905 (build-system r-build-system)
6906 (propagated-inputs
6907 `(("r-biocgenerics" ,r-biocgenerics)
6908 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 6909 (home-page "https://bioconductor.org/packages/IRanges")
78addcb0
RW		 6910 (synopsis "Infrastructure for manipulating intervals on sequences")
6911 (description
6912 "This package provides efficient low-level and highly reusable S4 classes
6913for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6914generally, data that can be organized sequentially (formally defined as
6915@code{Vector} objects), as well as views on these @code{Vector} objects.
6916Efficient list-like classes are also provided for storing big collections of
6917instances of the basic classes. All classes in the package use consistent
6918naming and share the same rich and consistent \"Vector API\" as much as
6919possible.")
6920 (license license:artistic2.0)))
6921
ffef27f3
RJ		 6922(define-public r-genomeinfodbdata
6923 (package
6924 (name "r-genomeinfodbdata")
261b38a9 6925 (version "0.99.1")
ffef27f3
RJ		 6926 (source (origin
6927 (method url-fetch)
90f83099
EF		 6928 ;; We cannot use bioconductor-uri here because this tarball is
6929 ;; located under "data/annotation/" instead of "bioc/".
6930 (uri (string-append "https://bioconductor.org/packages/release/"
6931 "data/annotation/src/contrib/GenomeInfoDbData_"
6932 version ".tar.gz"))
ffef27f3
RJ		 6933 (sha256
6934 (base32
261b38a9 6935 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
ffef27f3
RJ		 6936 (properties
6937 `((upstream-name . "GenomeInfoDbData")))
6938 (build-system r-build-system)
5713bbf1 6939 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
ffef27f3
RJ		 6940 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6941 (description "This package contains data for mapping between NCBI taxonomy
6942ID and species. It is used by functions in the GenomeInfoDb package.")
6943 (license license:artistic2.0)))
6944
bf7764b7
RW		 6945(define-public r-genomeinfodb
6946 (package
6947 (name "r-genomeinfodb")
8aab0235 6948 (version "1.14.0")
bf7764b7
RW		 6949 (source (origin
6950 (method url-fetch)
6951 (uri (bioconductor-uri "GenomeInfoDb" version))
6952 (sha256
6953 (base32
8aab0235 6954 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
bf7764b7 6955 (properties
1d216b6e 6956 `((upstream-name . "GenomeInfoDb")))
bf7764b7
RW		 6957 (build-system r-build-system)
6958 (propagated-inputs
6959 `(("r-biocgenerics" ,r-biocgenerics)
38b99ccc 6960 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
bf7764b7 6961 ("r-iranges" ,r-iranges)
4cd07e48 6962 ("r-rcurl" ,r-rcurl)
bf7764b7 6963 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 6964 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
bf7764b7
RW		 6965 (synopsis "Utilities for manipulating chromosome identifiers")
6966 (description
6967 "This package contains data and functions that define and allow
6968translation between different chromosome sequence naming conventions (e.g.,
6969\"chr1\" versus \"1\"), including a function that attempts to place sequence
6970names in their natural, rather than lexicographic, order.")
6971 (license license:artistic2.0)))
6972
744004a3
RJ		 6973(define-public r-edger
6974 (package
6975 (name "r-edger")
ab0dd8ac 6976 (version "3.20.2")
744004a3
RJ		 6977 (source (origin
6978 (method url-fetch)
6979 (uri (bioconductor-uri "edgeR" version))
6980 (sha256
6981 (base32
ab0dd8ac 6982 "0j5s3i33qmld9l7gs1rzpv601zxyqz711x8mq35hml088c8s99w9"))))
744004a3
RJ		 6983 (properties `((upstream-name . "edgeR")))
6984 (build-system r-build-system)
6985 (propagated-inputs
5e48005f 6986 `(("r-limma" ,r-limma)
47055b27 6987 ("r-locfit" ,r-locfit)
010ab2ff 6988 ("r-rcpp" ,r-rcpp)
47055b27 6989 ("r-statmod" ,r-statmod))) ;for estimateDisp
744004a3
RJ		 6990 (home-page "http://bioinf.wehi.edu.au/edgeR")
6991 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6992 (description "This package can do differential expression analysis of
6993RNA-seq expression profiles with biological replication. It implements a range
6994of statistical methodology based on the negative binomial distributions,
6995including empirical Bayes estimation, exact tests, generalized linear models
6996and quasi-likelihood tests. It be applied to differential signal analysis of
6997other types of genomic data that produce counts, including ChIP-seq, SAGE and
6998CAGE.")
6999 (license license:gpl2+)))
7000
b669d9c4
RJ		 7001(define-public r-variantannotation
7002 (package
7003 (name "r-variantannotation")
8131cf41 7004 (version "1.24.2")
b669d9c4
RJ		 7005 (source (origin
7006 (method url-fetch)
7007 (uri (bioconductor-uri "VariantAnnotation" version))
7008 (sha256
7009 (base32
8131cf41 7010 "19wgb2kcqy97pm3xgqc781id9fbmzp1hdwzkkhdzpvyf29w4n29j"))))
b669d9c4
RJ		 7011 (properties
7012 `((upstream-name . "VariantAnnotation")))
7013 (inputs
7014 `(("zlib" ,zlib)))
7015 (propagated-inputs
7016 `(("r-annotationdbi" ,r-annotationdbi)
37d96f1d 7017 ("r-biobase" ,r-biobase)
b669d9c4 7018 ("r-biocgenerics" ,r-biocgenerics)
37d96f1d 7019 ("r-biostrings" ,r-biostrings)
b669d9c4
RJ		 7020 ("r-bsgenome" ,r-bsgenome)
7021 ("r-dbi" ,r-dbi)
7022 ("r-genomeinfodb" ,r-genomeinfodb)
7023 ("r-genomicfeatures" ,r-genomicfeatures)
7024 ("r-genomicranges" ,r-genomicranges)
37d96f1d 7025 ("r-iranges" ,r-iranges)
b669d9c4
RJ		 7026 ("r-summarizedexperiment" ,r-summarizedexperiment)
7027 ("r-rsamtools" ,r-rsamtools)
37d96f1d
RW		 7028 ("r-rtracklayer" ,r-rtracklayer)
7029 ("r-s4vectors" ,r-s4vectors)
7030 ("r-xvector" ,r-xvector)
b669d9c4
RJ		 7031 ("r-zlibbioc" ,r-zlibbioc)))
7032 (build-system r-build-system)
7033 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7034 (synopsis "Package for annotation of genetic variants")
7035 (description "This R package can annotate variants, compute amino acid
7036coding changes and predict coding outcomes.")
7037 (license license:artistic2.0)))
7038
7d4224d7
RJ		 7039(define-public r-limma
7040 (package
7041 (name "r-limma")
d41f6784 7042 (version "3.34.4")
7d4224d7
RJ		 7043 (source (origin
7044 (method url-fetch)
7045 (uri (bioconductor-uri "limma" version))
7046 (sha256
7047 (base32
d41f6784 7048 "1vcxf9jg8xngxg5kb9bp8rw5sghpnkpj320iq309m2fp41ahsk3f"))))
7d4224d7
RJ		 7049 (build-system r-build-system)
7050 (home-page "http://bioinf.wehi.edu.au/limma")
7051 (synopsis "Package for linear models for microarray and RNA-seq data")
7052 (description "This package can be used for the analysis of gene expression
7053studies, especially the use of linear models for analysing designed experiments
7054and the assessment of differential expression. The analysis methods apply to
7055different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7056 (license license:gpl2+)))
7057
0e7d5560
RW		 7058(define-public r-xvector
7059 (package
7060 (name "r-xvector")
2b6ae8bf 7061 (version "0.18.0")
0e7d5560
RW		 7062 (source (origin
7063 (method url-fetch)
7064 (uri (bioconductor-uri "XVector" version))
7065 (sha256
7066 (base32
2b6ae8bf 7067 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
0e7d5560 7068 (properties
1d216b6e 7069 `((upstream-name . "XVector")))
0e7d5560
RW		 7070 (build-system r-build-system)
7071 (arguments
7072 `(#:phases
7073 (modify-phases %standard-phases
7074 (add-after 'unpack 'use-system-zlib
7075 (lambda _
7076 (substitute* "DESCRIPTION"
7077 (("zlibbioc, ") ""))
7078 (substitute* "NAMESPACE"
7079 (("import\\(zlibbioc\\)") ""))
7080 #t)))))
7081 (inputs
7082 `(("zlib" ,zlib)))
7083 (propagated-inputs
7084 `(("r-biocgenerics" ,r-biocgenerics)
7085 ("r-iranges" ,r-iranges)
7086 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 7087 (home-page "https://bioconductor.org/packages/XVector")
0e7d5560
RW		 7088 (synopsis "Representation and manpulation of external sequences")
7089 (description
7090 "This package provides memory efficient S4 classes for storing sequences
7091\"externally\" (behind an R external pointer, or on disk).")
7092 (license license:artistic2.0)))
7093
e2cd1d0f
RW		 7094(define-public r-genomicranges
7095 (package
7096 (name "r-genomicranges")
aa5c1f61 7097 (version "1.30.0")
e2cd1d0f
RW		 7098 (source (origin
7099 (method url-fetch)
7100 (uri (bioconductor-uri "GenomicRanges" version))
7101 (sha256
7102 (base32
aa5c1f61 7103 "10ra2sjn17h6gilm9iz0cygp9ijpgbirljlc4drwrnivnw9cmi2a"))))
e2cd1d0f 7104 (properties
1d216b6e 7105 `((upstream-name . "GenomicRanges")))
e2cd1d0f
RW		 7106 (build-system r-build-system)
7107 (propagated-inputs
7108 `(("r-biocgenerics" ,r-biocgenerics)
7109 ("r-genomeinfodb" ,r-genomeinfodb)
92a740af
RW		 7110 ("r-iranges" ,r-iranges)
7111 ("r-s4vectors" ,r-s4vectors)
e2cd1d0f 7112 ("r-xvector" ,r-xvector)))
5713bbf1 7113 (home-page "https://bioconductor.org/packages/GenomicRanges")
e2cd1d0f
RW		 7114 (synopsis "Representation and manipulation of genomic intervals")
7115 (description
7116 "This package provides tools to efficiently represent and manipulate
7117genomic annotations and alignments is playing a central role when it comes to
7118analyzing high-throughput sequencing data (a.k.a. NGS data). The
7119GenomicRanges package defines general purpose containers for storing and
7120manipulating genomic intervals and variables defined along a genome.")
7121 (license license:artistic2.0)))
7122
555e3399
RW		 7123(define-public r-biobase
7124 (package
7125 (name "r-biobase")
ca521236 7126 (version "2.38.0")
555e3399
RW		 7127 (source (origin
7128 (method url-fetch)
7129 (uri (bioconductor-uri "Biobase" version))
7130 (sha256
7131 (base32
ca521236 7132 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
555e3399
RW		 7133 (properties
7134 `((upstream-name . "Biobase")))
7135 (build-system r-build-system)
7136 (propagated-inputs
7137 `(("r-biocgenerics" ,r-biocgenerics)))
5713bbf1 7138 (home-page "https://bioconductor.org/packages/Biobase")
555e3399
RW		 7139 (synopsis "Base functions for Bioconductor")
7140 (description
7141 "This package provides functions that are needed by many other packages
7142on Bioconductor or which replace R functions.")
7143 (license license:artistic2.0)))
7144
8b7bce74
RW		 7145(define-public r-annotationdbi
7146 (package
7147 (name "r-annotationdbi")
0f8d98f2 7148 (version "1.40.0")
8b7bce74
RW		 7149 (source (origin
7150 (method url-fetch)
7151 (uri (bioconductor-uri "AnnotationDbi" version))
7152 (sha256
7153 (base32
0f8d98f2 7154 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
8b7bce74
RW		 7155 (properties
7156 `((upstream-name . "AnnotationDbi")))
7157 (build-system r-build-system)
7158 (propagated-inputs
7159 `(("r-biobase" ,r-biobase)
7160 ("r-biocgenerics" ,r-biocgenerics)
7161 ("r-dbi" ,r-dbi)
7162 ("r-iranges" ,r-iranges)
7163 ("r-rsqlite" ,r-rsqlite)
7164 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 7165 (home-page "https://bioconductor.org/packages/AnnotationDbi")
8b7bce74
RW		 7166 (synopsis "Annotation database interface")
7167 (description
7168 "This package provides user interface and database connection code for
7169annotation data packages using SQLite data storage.")
7170 (license license:artistic2.0)))
7171
c465fa72
RW		 7172(define-public r-biomart
7173 (package
7174 (name "r-biomart")
42e11d33 7175 (version "2.34.0")
c465fa72
RW		 7176 (source (origin
7177 (method url-fetch)
7178 (uri (bioconductor-uri "biomaRt" version))
7179 (sha256
7180 (base32
42e11d33 7181 "1dn3ysf0vb3mmg2b3380g0j1ajf88x4rh7fddfp990h2xlnsy2cx"))))
c465fa72
RW		 7182 (properties
7183 `((upstream-name . "biomaRt")))
7184 (build-system r-build-system)
7185 (propagated-inputs
7186 `(("r-annotationdbi" ,r-annotationdbi)
42e11d33 7187 ("r-progress" ,r-progress)
c465fa72 7188 ("r-rcurl" ,r-rcurl)
42e11d33 7189 ("r-stringr" ,r-stringr)
c465fa72 7190 ("r-xml" ,r-xml)))
5713bbf1 7191 (home-page "https://bioconductor.org/packages/biomaRt")
c465fa72
RW		 7192 (synopsis "Interface to BioMart databases")
7193 (description
7194 "biomaRt provides an interface to a growing collection of databases
7195implementing the @url{BioMart software suite, http://www.biomart.org}. The
7196package enables retrieval of large amounts of data in a uniform way without
7197the need to know the underlying database schemas or write complex SQL queries.
7198Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7199Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7200users direct access to a diverse set of data and enable a wide range of
7201powerful online queries from gene annotation to database mining.")
7202 (license license:artistic2.0)))
7203
e91d362e
RW		 7204(define-public r-biocparallel
7205 (package
7206 (name "r-biocparallel")
a044c7f4 7207 (version "1.12.0")
e91d362e
RW		 7208 (source (origin
7209 (method url-fetch)
7210 (uri (bioconductor-uri "BiocParallel" version))
7211 (sha256
7212 (base32
a044c7f4 7213 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
e91d362e
RW		 7214 (properties
7215 `((upstream-name . "BiocParallel")))
7216 (build-system r-build-system)
7217 (propagated-inputs
7218 `(("r-futile-logger" ,r-futile-logger)
a044c7f4
RW		 7219 ("r-snow" ,r-snow)
7220 ("r-bh" ,r-bh)))
5713bbf1 7221 (home-page "https://bioconductor.org/packages/BiocParallel")
e91d362e
RW		 7222 (synopsis "Bioconductor facilities for parallel evaluation")
7223 (description
7224 "This package provides modified versions and novel implementation of
7225functions for parallel evaluation, tailored to use with Bioconductor
7226objects.")
7227 (license (list license:gpl2+ license:gpl3+))))
7228
bf159353
RW		 7229(define-public r-biostrings
7230 (package
7231 (name "r-biostrings")
b719435e 7232 (version "2.46.0")
bf159353
RW		 7233 (source (origin
7234 (method url-fetch)
7235 (uri (bioconductor-uri "Biostrings" version))
7236 (sha256
7237 (base32
b719435e 7238 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
bf159353
RW		 7239 (properties
7240 `((upstream-name . "Biostrings")))
7241 (build-system r-build-system)
7242 (propagated-inputs
7243 `(("r-biocgenerics" ,r-biocgenerics)
7244 ("r-iranges" ,r-iranges)
7245 ("r-s4vectors" ,r-s4vectors)
7246 ("r-xvector" ,r-xvector)))
5713bbf1 7247 (home-page "https://bioconductor.org/packages/Biostrings")
bf159353
RW		 7248 (synopsis "String objects and algorithms for biological sequences")
7249 (description
7250 "This package provides memory efficient string containers, string
7251matching algorithms, and other utilities, for fast manipulation of large
7252biological sequences or sets of sequences.")
7253 (license license:artistic2.0)))
7254
f8d74f70
RW		 7255(define-public r-rsamtools
7256 (package
7257 (name "r-rsamtools")
f8068419 7258 (version "1.30.0")
f8d74f70
RW		 7259 (source (origin
7260 (method url-fetch)
7261 (uri (bioconductor-uri "Rsamtools" version))
7262 (sha256
7263 (base32
f8068419 7264 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
f8d74f70
RW		 7265 (properties
7266 `((upstream-name . "Rsamtools")))
7267 (build-system r-build-system)
7268 (arguments
7269 `(#:phases
7270 (modify-phases %standard-phases
7271 (add-after 'unpack 'use-system-zlib
7272 (lambda _
7273 (substitute* "DESCRIPTION"
7274 (("zlibbioc, ") ""))
7275 (substitute* "NAMESPACE"
7276 (("import\\(zlibbioc\\)") ""))
7277 #t)))))
7278 (inputs
7279 `(("zlib" ,zlib)))
7280 (propagated-inputs
7281 `(("r-biocgenerics" ,r-biocgenerics)
7282 ("r-biocparallel" ,r-biocparallel)
7283 ("r-biostrings" ,r-biostrings)
7284 ("r-bitops" ,r-bitops)
7285 ("r-genomeinfodb" ,r-genomeinfodb)
7286 ("r-genomicranges" ,r-genomicranges)
7287 ("r-iranges" ,r-iranges)
7288 ("r-s4vectors" ,r-s4vectors)
7289 ("r-xvector" ,r-xvector)))
5713bbf1 7290 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
f8d74f70
RW		 7291 (synopsis "Interface to samtools, bcftools, and tabix")
7292 (description
7293 "This package provides an interface to the 'samtools', 'bcftools', and
7294'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7295binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7296files.")
7297 (license license:expat)))
7298
71e34e6b
RJ		 7299(define-public r-delayedarray
7300 (package
7301 (name "r-delayedarray")
cb0a9a74 7302 (version "0.4.1")
71e34e6b
RJ		 7303 (source (origin
7304 (method url-fetch)
7305 (uri (bioconductor-uri "DelayedArray" version))
7306 (sha256
7307 (base32
cb0a9a74 7308 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
71e34e6b
RJ		 7309 (properties
7310 `((upstream-name . "DelayedArray")))
7311 (build-system r-build-system)
7312 (propagated-inputs
7313 `(("r-biocgenerics" ,r-biocgenerics)
7314 ("r-s4vectors" ,r-s4vectors)
7315 ("r-iranges" ,r-iranges)
7316 ("r-matrixstats" ,r-matrixstats)))
5713bbf1 7317 (home-page "https://bioconductor.org/packages/DelayedArray")
71e34e6b
RJ		 7318 (synopsis "Delayed operations on array-like objects")
7319 (description
7320 "Wrapping an array-like object (typically an on-disk object) in a
7321@code{DelayedArray} object allows one to perform common array operations on it
7322without loading the object in memory. In order to reduce memory usage and
7323optimize performance, operations on the object are either delayed or executed
7324using a block processing mechanism. Note that this also works on in-memory
7325array-like objects like @code{DataFrame} objects (typically with Rle columns),
7326@code{Matrix} objects, and ordinary arrays and data frames.")
7327 (license license:artistic2.0)))
7328
6e76dda2
RW		 7329(define-public r-summarizedexperiment
7330 (package
7331 (name "r-summarizedexperiment")
6fcbed73 7332 (version "1.8.0")
6e76dda2
RW		 7333 (source (origin
7334 (method url-fetch)
7335 (uri (bioconductor-uri "SummarizedExperiment" version))
7336 (sha256
7337 (base32
6fcbed73 7338 "1011r8l0k8420j31bmh4xdcp6ka5bzf4bqhip84v5b6alpkcbvmf"))))
6e76dda2
RW		 7339 (properties
7340 `((upstream-name . "SummarizedExperiment")))
7341 (build-system r-build-system)
7342 (propagated-inputs
7343 `(("r-biobase" ,r-biobase)
7344 ("r-biocgenerics" ,r-biocgenerics)
d006ee31 7345 ("r-delayedarray" ,r-delayedarray)
6e76dda2
RW		 7346 ("r-genomeinfodb" ,r-genomeinfodb)
7347 ("r-genomicranges" ,r-genomicranges)
7348 ("r-iranges" ,r-iranges)
aeb64f3c 7349 ("r-matrix" ,r-matrix)
6e76dda2 7350 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 7351 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
6e76dda2
RW		 7352 (synopsis "Container for representing genomic ranges by sample")
7353 (description
7354 "The SummarizedExperiment container contains one or more assays, each
7355represented by a matrix-like object of numeric or other mode. The rows
7356typically represent genomic ranges of interest and the columns represent
7357samples.")
7358 (license license:artistic2.0)))
7359
d8a828af
RW		 7360(define-public r-genomicalignments
7361 (package
7362 (name "r-genomicalignments")
06e8e0fc 7363 (version "1.14.1")
d8a828af
RW		 7364 (source (origin
7365 (method url-fetch)
7366 (uri (bioconductor-uri "GenomicAlignments" version))
7367 (sha256
7368 (base32
06e8e0fc 7369 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
d8a828af
RW		 7370 (properties
7371 `((upstream-name . "GenomicAlignments")))
7372 (build-system r-build-system)
7373 (propagated-inputs
7374 `(("r-biocgenerics" ,r-biocgenerics)
7375 ("r-biocparallel" ,r-biocparallel)
7376 ("r-biostrings" ,r-biostrings)
7377 ("r-genomeinfodb" ,r-genomeinfodb)
7378 ("r-genomicranges" ,r-genomicranges)
7379 ("r-iranges" ,r-iranges)
7380 ("r-rsamtools" ,r-rsamtools)
7381 ("r-s4vectors" ,r-s4vectors)
7382 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5713bbf1 7383 (home-page "https://bioconductor.org/packages/GenomicAlignments")
d8a828af
RW		 7384 (synopsis "Representation and manipulation of short genomic alignments")
7385 (description
7386 "This package provides efficient containers for storing and manipulating
7387short genomic alignments (typically obtained by aligning short reads to a
7388reference genome). This includes read counting, computing the coverage,
7389junction detection, and working with the nucleotide content of the
7390alignments.")
7391 (license license:artistic2.0)))
7392
317755ff
RW		 7393(define-public r-rtracklayer
7394 (package
7395 (name "r-rtracklayer")
28d25d03 7396 (version "1.38.2")
317755ff
RW		 7397 (source (origin
7398 (method url-fetch)
7399 (uri (bioconductor-uri "rtracklayer" version))
7400 (sha256
7401 (base32
28d25d03 7402 "1sjn3976f1sqvrq6jq2hgc60ffxgfr3jlklaxfrk3xad5cv2kr2d"))))
317755ff
RW		 7403 (build-system r-build-system)
7404 (arguments
7405 `(#:phases
7406 (modify-phases %standard-phases
7407 (add-after 'unpack 'use-system-zlib
7408 (lambda _
7409 (substitute* "DESCRIPTION"
4dd469ef 7410 ((" zlibbioc,") ""))
317755ff
RW		 7411 (substitute* "NAMESPACE"
7412 (("import\\(zlibbioc\\)") ""))
7413 #t)))))
7414 (inputs
7415 `(("zlib" ,zlib)))
7416 (propagated-inputs
7417 `(("r-biocgenerics" ,r-biocgenerics)
7418 ("r-biostrings" ,r-biostrings)
7419 ("r-genomeinfodb" ,r-genomeinfodb)
7420 ("r-genomicalignments" ,r-genomicalignments)
7421 ("r-genomicranges" ,r-genomicranges)
7422 ("r-iranges" ,r-iranges)
7423 ("r-rcurl" ,r-rcurl)
7424 ("r-rsamtools" ,r-rsamtools)
7425 ("r-s4vectors" ,r-s4vectors)
7426 ("r-xml" ,r-xml)
7427 ("r-xvector" ,r-xvector)))
5713bbf1 7428 (home-page "https://bioconductor.org/packages/rtracklayer")
317755ff
RW		 7429 (synopsis "R interface to genome browsers and their annotation tracks")
7430 (description
7431 "rtracklayer is an extensible framework for interacting with multiple
7432genome browsers (currently UCSC built-in) and manipulating annotation tracks
7433in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7434built-in). The user may export/import tracks to/from the supported browsers,
7435as well as query and modify the browser state, such as the current viewport.")
7436 (license license:artistic2.0)))
7437
2fd7c049
RW		 7438(define-public r-genomicfeatures
7439 (package
7440 (name "r-genomicfeatures")
158b6743 7441 (version "1.30.0")
2fd7c049
RW		 7442 (source (origin
7443 (method url-fetch)
7444 (uri (bioconductor-uri "GenomicFeatures" version))
7445 (sha256
7446 (base32
158b6743 7447 "1khjvq1ffhqavkwf8n7bilknci60lxbg52icrcf2vnb9k8rlpghs"))))
2fd7c049
RW		 7448 (properties
7449 `((upstream-name . "GenomicFeatures")))
7450 (build-system r-build-system)
7451 (propagated-inputs
7452 `(("r-annotationdbi" ,r-annotationdbi)
7453 ("r-biobase" ,r-biobase)
7454 ("r-biocgenerics" ,r-biocgenerics)
7455 ("r-biomart" ,r-biomart)
7456 ("r-biostrings" ,r-biostrings)
7457 ("r-dbi" ,r-dbi)
7458 ("r-genomeinfodb" ,r-genomeinfodb)
7459 ("r-genomicranges" ,r-genomicranges)
7460 ("r-iranges" ,r-iranges)
7461 ("r-rcurl" ,r-rcurl)
7462 ("r-rsqlite" ,r-rsqlite)
158b6743 7463 ("r-rmysql" ,r-rmysql)
2fd7c049
RW		 7464 ("r-rtracklayer" ,r-rtracklayer)
7465 ("r-s4vectors" ,r-s4vectors)
7466 ("r-xvector" ,r-xvector)))
5713bbf1 7467 (home-page "https://bioconductor.org/packages/GenomicFeatures")
2fd7c049
RW		 7468 (synopsis "Tools for working with transcript centric annotations")
7469 (description
7470 "This package provides a set of tools and methods for making and
7471manipulating transcript centric annotations. With these tools the user can
7472easily download the genomic locations of the transcripts, exons and cds of a
7473given organism, from either the UCSC Genome Browser or a BioMart
7474database (more sources will be supported in the future). This information is
7475then stored in a local database that keeps track of the relationship between
7476transcripts, exons, cds and genes. Flexible methods are provided for
7477extracting the desired features in a convenient format.")
7478 (license license:artistic2.0)))
7479
fb25d880
RW		 7480(define-public r-go-db
7481 (package
7482 (name "r-go-db")
592f4a94 7483 (version "3.5.0")
fb25d880
RW		 7484 (source (origin
7485 (method url-fetch)
5713bbf1 7486 (uri (string-append "https://www.bioconductor.org/packages/"
f82c8c3c
PP		 7487 "release/data/annotation/src/contrib/GO.db_"
7488 version ".tar.gz"))
fb25d880
RW		 7489 (sha256
7490 (base32
592f4a94 7491 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
fb25d880
RW		 7492 (properties
7493 `((upstream-name . "GO.db")))
7494 (build-system r-build-system)
3141b83d
RW		 7495 (propagated-inputs
7496 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7497 (home-page "https://bioconductor.org/packages/GO.db")
fb25d880
RW		 7498 (synopsis "Annotation maps describing the entire Gene Ontology")
7499 (description
7500 "The purpose of this GO.db annotation package is to provide detailed
7501information about the latest version of the Gene Ontologies.")
7502 (license license:artistic2.0)))
7503
d1dbde6a
RW		 7504(define-public r-graph
7505 (package
7506 (name "r-graph")
aeb73879 7507 (version "1.56.0")
d1dbde6a
RW		 7508 (source (origin
7509 (method url-fetch)
7510 (uri (bioconductor-uri "graph" version))
7511 (sha256
7512 (base32
aeb73879 7513 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
d1dbde6a
RW		 7514 (build-system r-build-system)
7515 (propagated-inputs
7516 `(("r-biocgenerics" ,r-biocgenerics)))
5713bbf1 7517 (home-page "https://bioconductor.org/packages/graph")
d1dbde6a
RW		 7518 (synopsis "Handle graph data structures in R")
7519 (description
7520 "This package implements some simple graph handling capabilities for R.")
7521 (license license:artistic2.0)))
7522
d547ce5e
RW		 7523(define-public r-topgo
7524 (package
7525 (name "r-topgo")
d13a3fea 7526 (version "2.30.0")
d547ce5e
RW		 7527 (source (origin
7528 (method url-fetch)
7529 (uri (bioconductor-uri "topGO" version))
7530 (sha256
7531 (base32
d13a3fea 7532 "1hqffz5qp7glxdvjp37005g8qk5nam3f9wpf6d1wjnzpar04f3dz"))))
d547ce5e
RW		 7533 (properties
7534 `((upstream-name . "topGO")))
7535 (build-system r-build-system)
7536 (propagated-inputs
7537 `(("r-annotationdbi" ,r-annotationdbi)
30ec4de7 7538 ("r-dbi" ,r-dbi)
d547ce5e
RW		 7539 ("r-biobase" ,r-biobase)
7540 ("r-biocgenerics" ,r-biocgenerics)
7541 ("r-go-db" ,r-go-db)
6d415db2 7542 ("r-graph" ,r-graph)
aeb64f3c
RW		 7543 ("r-lattice" ,r-lattice)
7544 ("r-matrixstats" ,r-matrixstats)
d547ce5e 7545 ("r-sparsem" ,r-sparsem)))
5713bbf1 7546 (home-page "https://bioconductor.org/packages/topGO")
d547ce5e
RW		 7547 (synopsis "Enrichment analysis for gene ontology")
7548 (description
7549 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7550terms while accounting for the topology of the GO graph. Different test
7551statistics and different methods for eliminating local similarities and
7552dependencies between GO terms can be implemented and applied.")
7553 ;; Any version of the LGPL applies.
7554 (license license:lgpl2.1+)))
7555
c63cef66
RW		 7556(define-public r-bsgenome
7557 (package
7558 (name "r-bsgenome")
e67850b4 7559 (version "1.46.0")
c63cef66
RW		 7560 (source (origin
7561 (method url-fetch)
7562 (uri (bioconductor-uri "BSgenome" version))
7563 (sha256
7564 (base32
e67850b4 7565 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
c63cef66
RW		 7566 (properties
7567 `((upstream-name . "BSgenome")))
7568 (build-system r-build-system)
7569 (propagated-inputs
7570 `(("r-biocgenerics" ,r-biocgenerics)
7571 ("r-biostrings" ,r-biostrings)
7572 ("r-genomeinfodb" ,r-genomeinfodb)
7573 ("r-genomicranges" ,r-genomicranges)
7574 ("r-iranges" ,r-iranges)
7575 ("r-rsamtools" ,r-rsamtools)
7576 ("r-rtracklayer" ,r-rtracklayer)
7577 ("r-s4vectors" ,r-s4vectors)
7578 ("r-xvector" ,r-xvector)))
5713bbf1 7579 (home-page "https://bioconductor.org/packages/BSgenome")
c63cef66
RW		 7580 (synopsis "Infrastructure for Biostrings-based genome data packages")
7581 (description
7582 "This package provides infrastructure shared by all Biostrings-based
7583genome data packages and support for efficient SNP representation.")
7584 (license license:artistic2.0)))
7585
aa3eeeb5
RJ		 7586(define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7587 (package
7588 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7589 (version "0.99.1")
7590 (source (origin
7591 (method url-fetch)
7592 ;; We cannot use bioconductor-uri here because this tarball is
7593 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7594 (uri (string-append "https://www.bioconductor.org/packages/"
aa3eeeb5
RJ		 7595 "release/data/annotation/src/contrib/"
7596 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7597 version ".tar.gz"))
7598 (sha256
7599 (base32
7600 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7601 (properties
7602 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7603 (build-system r-build-system)
7604 ;; As this package provides little more than a very large data file it
7605 ;; doesn't make sense to build substitutes.
7606 (arguments `(#:substitutable? #f))
7607 (propagated-inputs
7608 `(("r-bsgenome" ,r-bsgenome)))
7609 (home-page
5713bbf1 7610 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
aa3eeeb5
RJ		 7611 (synopsis "Full genome sequences for Homo sapiens")
7612 (description
7613 "This package provides full genome sequences for Homo sapiens from
76141000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7615 (license license:artistic2.0)))
7616
c43a011d
RW		 7617(define-public r-impute
7618 (package
7619 (name "r-impute")
e6ce4bf0 7620 (version "1.52.0")
c43a011d
RW		 7621 (source (origin
7622 (method url-fetch)
7623 (uri (bioconductor-uri "impute" version))
7624 (sha256
7625 (base32
e6ce4bf0 7626 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
c43a011d
RW		 7627 (inputs
7628 `(("gfortran" ,gfortran)))
7629 (build-system r-build-system)
5713bbf1 7630 (home-page "https://bioconductor.org/packages/impute")
c43a011d
RW		 7631 (synopsis "Imputation for microarray data")
7632 (description
7633 "This package provides a function to impute missing gene expression
7634microarray data, using nearest neighbor averaging.")
7635 (license license:gpl2+)))
7636
03ea5a35
RW		 7637(define-public r-seqpattern
7638 (package
7639 (name "r-seqpattern")
0f948b11 7640 (version "1.10.0")
03ea5a35
RW		 7641 (source (origin
7642 (method url-fetch)
7643 (uri (bioconductor-uri "seqPattern" version))
7644 (sha256
7645 (base32
0f948b11 7646 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
03ea5a35
RW		 7647 (properties
7648 `((upstream-name . "seqPattern")))
7649 (build-system r-build-system)
7650 (propagated-inputs
7651 `(("r-biostrings" ,r-biostrings)
7652 ("r-genomicranges" ,r-genomicranges)
7653 ("r-iranges" ,r-iranges)
e92dd6f5 7654 ("r-kernsmooth" ,r-kernsmooth)
03ea5a35 7655 ("r-plotrix" ,r-plotrix)))
5713bbf1 7656 (home-page "https://bioconductor.org/packages/seqPattern")
03ea5a35
RW		 7657 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7658 (description
7659 "This package provides tools to visualize oligonucleotide patterns and
7660sequence motif occurrences across a large set of sequences centred at a common
7661reference point and sorted by a user defined feature.")
7662 (license license:gpl3+)))
7663
cb933df6
RW		 7664(define-public r-genomation
7665 (package
7666 (name "r-genomation")
e127c918 7667 (version "1.10.0")
cb933df6
RW		 7668 (source (origin
7669 (method url-fetch)
7670 (uri (bioconductor-uri "genomation" version))
7671 (sha256
7672 (base32
e127c918 7673 "1ddd8c9w1f1i1ga9rpbwiic8rsaws1chdxx4j38bpyaiy4zhz1ca"))))
cb933df6
RW		 7674 (build-system r-build-system)
7675 (propagated-inputs
7676 `(("r-biostrings" ,r-biostrings)
7677 ("r-bsgenome" ,r-bsgenome)
7678 ("r-data-table" ,r-data-table)
7679 ("r-genomeinfodb" ,r-genomeinfodb)
7680 ("r-genomicalignments" ,r-genomicalignments)
7681 ("r-genomicranges" ,r-genomicranges)
7682 ("r-ggplot2" ,r-ggplot2)
7683 ("r-gridbase" ,r-gridbase)
7684 ("r-impute" ,r-impute)
7685 ("r-iranges" ,r-iranges)
7686 ("r-matrixstats" ,r-matrixstats)
7687 ("r-plotrix" ,r-plotrix)
7688 ("r-plyr" ,r-plyr)
51c3c490 7689 ("r-rcpp" ,r-rcpp)
cb933df6
RW		 7690 ("r-readr" ,r-readr)
7691 ("r-reshape2" ,r-reshape2)
7692 ("r-rsamtools" ,r-rsamtools)
7693 ("r-rtracklayer" ,r-rtracklayer)
51c3c490
RW		 7694 ("r-runit" ,r-runit)
7695 ("r-s4vectors" ,r-s4vectors)
cb933df6
RW		 7696 ("r-seqpattern" ,r-seqpattern)))
7697 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7698 (synopsis "Summary, annotation and visualization of genomic data")
7699 (description
7700 "This package provides a package for summary and annotation of genomic
7701intervals. Users can visualize and quantify genomic intervals over
7702pre-defined functional regions, such as promoters, exons, introns, etc. The
7703genomic intervals represent regions with a defined chromosome position, which
7704may be associated with a score, such as aligned reads from HT-seq experiments,
7705TF binding sites, methylation scores, etc. The package can use any tabular
7706genomic feature data as long as it has minimal information on the locations of
7707genomic intervals. In addition, it can use BAM or BigWig files as input.")
7708 (license license:artistic2.0)))
7709
64efa307
RW		 7710(define-public r-genomationdata
7711 (package
7712 (name "r-genomationdata")
57dc9b58 7713 (version "1.10.0")
64efa307
RW		 7714 (source (origin
7715 (method url-fetch)
7716 ;; We cannot use bioconductor-uri here because this tarball is
7717 ;; located under "data/annotation/" instead of "bioc/".
7718 (uri (string-append "https://bioconductor.org/packages/"
7719 "release/data/experiment/src/contrib/"
7720 "genomationData_" version ".tar.gz"))
7721 (sha256
7722 (base32
57dc9b58 7723 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
64efa307
RW		 7724 (build-system r-build-system)
7725 ;; As this package provides little more than large data files, it doesn't
7726 ;; make sense to build substitutes.
7727 (arguments `(#:substitutable? #f))
7728 (native-inputs
7729 `(("r-knitr" ,r-knitr)))
7730 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7731 (synopsis "Experimental data for use with the genomation package")
7732 (description
7733 "This package contains experimental genetic data for use with the
7734genomation package. Included are Chip Seq, Methylation and Cage data,
7735downloaded from Encode.")
7736 (license license:gpl3+)))
7737
486da491
RW		 7738(define-public r-org-hs-eg-db
7739 (package
7740 (name "r-org-hs-eg-db")
d595fed3 7741 (version "3.5.0")
486da491
RW		 7742 (source (origin
7743 (method url-fetch)
7744 ;; We cannot use bioconductor-uri here because this tarball is
7745 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7746 (uri (string-append "https://www.bioconductor.org/packages/"
486da491
RW		 7747 "release/data/annotation/src/contrib/"
7748 "org.Hs.eg.db_" version ".tar.gz"))
7749 (sha256
7750 (base32
d595fed3 7751 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
486da491
RW		 7752 (properties
7753 `((upstream-name . "org.Hs.eg.db")))
7754 (build-system r-build-system)
7755 (propagated-inputs
7756 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7757 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
486da491
RW		 7758 (synopsis "Genome wide annotation for Human")
7759 (description
676507e3
RW		 7760 "This package contains genome-wide annotations for Human, primarily based
7761on mapping using Entrez Gene identifiers.")
486da491
RW		 7762 (license license:artistic2.0)))
7763
fefedf98
RW		 7764(define-public r-org-ce-eg-db
7765 (package
7766 (name "r-org-ce-eg-db")
e4664290 7767 (version "3.5.0")
fefedf98
RW		 7768 (source (origin
7769 (method url-fetch)
7770 ;; We cannot use bioconductor-uri here because this tarball is
7771 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7772 (uri (string-append "https://www.bioconductor.org/packages/"
fefedf98
RW		 7773 "release/data/annotation/src/contrib/"
7774 "org.Ce.eg.db_" version ".tar.gz"))
7775 (sha256
7776 (base32
e4664290 7777 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
fefedf98
RW		 7778 (properties
7779 `((upstream-name . "org.Ce.eg.db")))
7780 (build-system r-build-system)
7781 (propagated-inputs
7782 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7783 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
fefedf98
RW		 7784 (synopsis "Genome wide annotation for Worm")
7785 (description
7786 "This package provides mappings from Entrez gene identifiers to various
7787annotations for the genome of the model worm Caenorhabditis elegans.")
7788 (license license:artistic2.0)))
7789
16c53a1e
RW		 7790(define-public r-org-dm-eg-db
7791 (package
7792 (name "r-org-dm-eg-db")
19fc299f 7793 (version "3.5.0")
16c53a1e
RW		 7794 (source (origin
7795 (method url-fetch)
7796 ;; We cannot use bioconductor-uri here because this tarball is
7797 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7798 (uri (string-append "https://www.bioconductor.org/packages/"
16c53a1e
RW		 7799 "release/data/annotation/src/contrib/"
7800 "org.Dm.eg.db_" version ".tar.gz"))
7801 (sha256
7802 (base32
19fc299f 7803 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
16c53a1e
RW		 7804 (properties
7805 `((upstream-name . "org.Dm.eg.db")))
7806 (build-system r-build-system)
7807 (propagated-inputs
7808 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7809 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
16c53a1e
RW		 7810 (synopsis "Genome wide annotation for Fly")
7811 (description
7812 "This package provides mappings from Entrez gene identifiers to various
7813annotations for the genome of the model fruit fly Drosophila melanogaster.")
7814 (license license:artistic2.0)))
7815
e761beb9
RW		 7816(define-public r-org-mm-eg-db
7817 (package
7818 (name "r-org-mm-eg-db")
f3569f52 7819 (version "3.5.0")
e761beb9
RW		 7820 (source (origin
7821 (method url-fetch)
7822 ;; We cannot use bioconductor-uri here because this tarball is
7823 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7824 (uri (string-append "https://www.bioconductor.org/packages/"
e761beb9
RW		 7825 "release/data/annotation/src/contrib/"
7826 "org.Mm.eg.db_" version ".tar.gz"))
7827 (sha256
7828 (base32
f3569f52 7829 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
e761beb9
RW		 7830 (properties
7831 `((upstream-name . "org.Mm.eg.db")))
7832 (build-system r-build-system)
7833 (propagated-inputs
7834 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7835 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
e761beb9
RW		 7836 (synopsis "Genome wide annotation for Mouse")
7837 (description
7838 "This package provides mappings from Entrez gene identifiers to various
7839annotations for the genome of the model mouse Mus musculus.")
7840 (license license:artistic2.0)))
7841
936e7d67
RW		 7842(define-public r-seqlogo
7843 (package
7844 (name "r-seqlogo")
61770089 7845 (version "1.44.0")
936e7d67
RW		 7846 (source
7847 (origin
7848 (method url-fetch)
7849 (uri (bioconductor-uri "seqLogo" version))
7850 (sha256
7851 (base32
61770089 7852 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
936e7d67
RW		 7853 (properties `((upstream-name . "seqLogo")))
7854 (build-system r-build-system)
5713bbf1 7855 (home-page "https://bioconductor.org/packages/seqLogo")
936e7d67
RW		 7856 (synopsis "Sequence logos for DNA sequence alignments")
7857 (description
7858 "seqLogo takes the position weight matrix of a DNA sequence motif and
7859plots the corresponding sequence logo as introduced by Schneider and
7860Stephens (1990).")
7861 (license license:lgpl2.0+)))
7862
c90a4baf
RW		 7863(define-public r-bsgenome-hsapiens-ucsc-hg19
7864 (package
7865 (name "r-bsgenome-hsapiens-ucsc-hg19")
7866 (version "1.4.0")
7867 (source (origin
7868 (method url-fetch)
7869 ;; We cannot use bioconductor-uri here because this tarball is
7870 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7871 (uri (string-append "https://www.bioconductor.org/packages/"
c90a4baf
RW		 7872 "release/data/annotation/src/contrib/"
7873 "BSgenome.Hsapiens.UCSC.hg19_"
7874 version ".tar.gz"))
7875 (sha256
7876 (base32
9d217d27 7877 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
c90a4baf
RW		 7878 (properties
7879 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7880 (build-system r-build-system)
7881 ;; As this package provides little more than a very large data file it
7882 ;; doesn't make sense to build substitutes.
7883 (arguments `(#:substitutable? #f))
7884 (propagated-inputs
7885 `(("r-bsgenome" ,r-bsgenome)))
7886 (home-page
5713bbf1 7887 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
c90a4baf
RW		 7888 (synopsis "Full genome sequences for Homo sapiens")
7889 (description
7890 "This package provides full genome sequences for Homo sapiens as provided
7891by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7892 (license license:artistic2.0)))
7893
a3e90287
RW		 7894(define-public r-bsgenome-mmusculus-ucsc-mm9
7895 (package
7896 (name "r-bsgenome-mmusculus-ucsc-mm9")
7897 (version "1.4.0")
7898 (source (origin
7899 (method url-fetch)
7900 ;; We cannot use bioconductor-uri here because this tarball is
7901 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7902 (uri (string-append "https://www.bioconductor.org/packages/"
a3e90287
RW		 7903 "release/data/annotation/src/contrib/"
7904 "BSgenome.Mmusculus.UCSC.mm9_"
7905 version ".tar.gz"))
7906 (sha256
7907 (base32
7908 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7909 (properties
7910 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7911 (build-system r-build-system)
7912 ;; As this package provides little more than a very large data file it
7913 ;; doesn't make sense to build substitutes.
7914 (arguments `(#:substitutable? #f))
7915 (propagated-inputs
7916 `(("r-bsgenome" ,r-bsgenome)))
7917 (home-page
5713bbf1 7918 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
a3e90287
RW		 7919 (synopsis "Full genome sequences for Mouse")
7920 (description
7921 "This package provides full genome sequences for Mus musculus (Mouse) as
7922provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7923 (license license:artistic2.0)))
7924
4714d521
RW		 7925(define-public r-bsgenome-mmusculus-ucsc-mm10
7926 (package
7927 (name "r-bsgenome-mmusculus-ucsc-mm10")
7928 (version "1.4.0")
7929 (source (origin
7930 (method url-fetch)
7931 ;; We cannot use bioconductor-uri here because this tarball is
7932 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7933 (uri (string-append "https://www.bioconductor.org/packages/"
4714d521
RW		 7934 "release/data/annotation/src/contrib/"
7935 "BSgenome.Mmusculus.UCSC.mm10_"
7936 version ".tar.gz"))
7937 (sha256
7938 (base32
7939 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7940 (properties
7941 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7942 (build-system r-build-system)
7943 ;; As this package provides little more than a very large data file it
7944 ;; doesn't make sense to build substitutes.
7945 (arguments `(#:substitutable? #f))
7946 (propagated-inputs
7947 `(("r-bsgenome" ,r-bsgenome)))
7948 (home-page
5713bbf1 7949 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
4714d521
RW		 7950 (synopsis "Full genome sequences for Mouse")
7951 (description
7952 "This package provides full genome sequences for Mus
7953musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7954in Biostrings objects.")
7955 (license license:artistic2.0)))
7956
c5173d74
RJ		 7957(define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7958 (package
7959 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7960 (version "3.4.0")
7961 (source (origin
7962 (method url-fetch)
7963 ;; We cannot use bioconductor-uri here because this tarball is
7964 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7965 (uri (string-append "https://www.bioconductor.org/packages/"
c5173d74
RJ		 7966 "release/data/annotation/src/contrib/"
7967 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7968 version ".tar.gz"))
7969 (sha256
7970 (base32
7971 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7972 (properties
7973 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7974 (build-system r-build-system)
7975 ;; As this package provides little more than a very large data file it
7976 ;; doesn't make sense to build substitutes.
7977 (arguments `(#:substitutable? #f))
7978 (propagated-inputs
7979 `(("r-bsgenome" ,r-bsgenome)
7980 ("r-genomicfeatures" ,r-genomicfeatures)
7981 ("r-annotationdbi" ,r-annotationdbi)))
7982 (home-page
5713bbf1 7983 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
c5173d74
RJ		 7984 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7985 (description
7986 "This package loads a TxDb object, which is an R interface to
7987prefabricated databases contained in this package. This package provides
7988the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7989based on the knownGene track.")
7990 (license license:artistic2.0)))
7991
943bd627
RW		 7992(define-public r-bsgenome-celegans-ucsc-ce6
7993 (package
7994 (name "r-bsgenome-celegans-ucsc-ce6")
7995 (version "1.4.0")
7996 (source (origin
7997 (method url-fetch)
7998 ;; We cannot use bioconductor-uri here because this tarball is
7999 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 8000 (uri (string-append "https://www.bioconductor.org/packages/"
943bd627
RW		 8001 "release/data/annotation/src/contrib/"
8002 "BSgenome.Celegans.UCSC.ce6_"
8003 version ".tar.gz"))
8004 (sha256
8005 (base32
8006 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8007 (properties
8008 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8009 (build-system r-build-system)
8010 ;; As this package provides little more than a very large data file it
8011 ;; doesn't make sense to build substitutes.
8012 (arguments `(#:substitutable? #f))
8013 (propagated-inputs
8014 `(("r-bsgenome" ,r-bsgenome)))
8015 (home-page
5713bbf1 8016 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
943bd627
RW		 8017 (synopsis "Full genome sequences for Worm")
8018 (description
8019 "This package provides full genome sequences for Caenorhabditis
8020elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8021objects.")
8022 (license license:artistic2.0)))
8023
fc47c7d6
RW		 8024(define-public r-bsgenome-celegans-ucsc-ce10
8025 (package
8026 (name "r-bsgenome-celegans-ucsc-ce10")
8027 (version "1.4.0")
8028 (source (origin
8029 (method url-fetch)
8030 ;; We cannot use bioconductor-uri here because this tarball is
8031 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 8032 (uri (string-append "https://www.bioconductor.org/packages/"
fc47c7d6
RW		 8033 "release/data/annotation/src/contrib/"
8034 "BSgenome.Celegans.UCSC.ce10_"
8035 version ".tar.gz"))
8036 (sha256
8037 (base32
8038 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8039 (properties
8040 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8041 (build-system r-build-system)
8042 ;; As this package provides little more than a very large data file it
8043 ;; doesn't make sense to build substitutes.
8044 (arguments `(#:substitutable? #f))
8045 (propagated-inputs
8046 `(("r-bsgenome" ,r-bsgenome)))
8047 (home-page
5713bbf1 8048 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
fc47c7d6
RW		 8049 (synopsis "Full genome sequences for Worm")
8050 (description
8051 "This package provides full genome sequences for Caenorhabditis
8052elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8053objects.")
8054 (license license:artistic2.0)))
8055
6dc60998
RW		 8056(define-public r-bsgenome-dmelanogaster-ucsc-dm3
8057 (package
8058 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8059 (version "1.4.0")
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/"
6dc60998
RW		 8065 "release/data/annotation/src/contrib/"
8066 "BSgenome.Dmelanogaster.UCSC.dm3_"
8067 version ".tar.gz"))
8068 (sha256
8069 (base32
8070 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8071 (properties
8072 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8073 (build-system r-build-system)
8074 ;; As this package provides little more than a very large data file it
8075 ;; doesn't make sense to build substitutes.
8076 (arguments `(#:substitutable? #f))
8077 (propagated-inputs
8078 `(("r-bsgenome" ,r-bsgenome)))
8079 (home-page
5713bbf1 8080 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
6dc60998
RW		 8081 (synopsis "Full genome sequences for Fly")
8082 (description
8083 "This package provides full genome sequences for Drosophila
8084melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8085Biostrings objects.")
8086 (license license:artistic2.0)))
8087
ae2462f7
RW		 8088(define-public r-motifrg
8089 (package
8090 (name "r-motifrg")
ce59d625 8091 (version "1.22.0")
ae2462f7
RW		 8092 (source
8093 (origin
8094 (method url-fetch)
8095 (uri (bioconductor-uri "motifRG" version))
8096 (sha256
8097 (base32
ce59d625 8098 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
ae2462f7
RW		 8099 (properties `((upstream-name . "motifRG")))
8100 (build-system r-build-system)
8101 (propagated-inputs
8102 `(("r-biostrings" ,r-biostrings)
8103 ("r-bsgenome" ,r-bsgenome)
007424b5 8104 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
ae2462f7
RW		 8105 ("r-iranges" ,r-iranges)
8106 ("r-seqlogo" ,r-seqlogo)
8107 ("r-xvector" ,r-xvector)))
5713bbf1 8108 (home-page "https://bioconductor.org/packages/motifRG")
ae2462f7
RW		 8109 (synopsis "Discover motifs in high throughput sequencing data")
8110 (description
8111 "This package provides tools for discriminative motif discovery in high
8112throughput genetic sequencing data sets using regression methods.")
8113 (license license:artistic2.0)))
8114
a5002ae7
AE		 8115(define-public r-qtl
8116 (package
8117 (name "r-qtl")
c8a9b2bc 8118 (version "1.41-6")
a5002ae7
AE		 8119 (source
8120 (origin
8121 (method url-fetch)
8122 (uri (string-append "mirror://cran/src/contrib/qtl_"
8123 version ".tar.gz"))
8124 (sha256
8125 (base32
c8a9b2bc 8126 "067az4v432zxp6lxck8d7vlh9w4r13r0mvw5zsglyaqwsh3d9sad"))))
a5002ae7
AE		 8127 (build-system r-build-system)
8128 (home-page "http://rqtl.org/")
8129 (synopsis "R package for analyzing QTL experiments in genetics")
8130 (description "R/qtl is an extension library for the R statistics
8131system. It is used to analyze experimental crosses for identifying
8132genes contributing to variation in quantitative traits (so-called
8133quantitative trait loci, QTLs).
8134
8135Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8136identify genotyping errors, and to perform single-QTL and two-QTL,
8137two-dimensional genome scans.")
8138 (license license:gpl3)))
d1e32822 8139
9e3ba31c
RJ		 8140(define-public r-zlibbioc
8141 (package
8142 (name "r-zlibbioc")
5c184700 8143 (version "1.24.0")
9e3ba31c
RJ		 8144 (source (origin
8145 (method url-fetch)
8146 (uri (bioconductor-uri "zlibbioc" version))
8147 (sha256
8148 (base32
5c184700 8149 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
9e3ba31c
RJ		 8150 (properties
8151 `((upstream-name . "zlibbioc")))
8152 (build-system r-build-system)
8153 (home-page "https://bioconductor.org/packages/zlibbioc")
8154 (synopsis "Provider for zlib-1.2.5 to R packages")
8155 (description "This package uses the source code of zlib-1.2.5 to create
8156libraries for systems that do not have these available via other means.")
8157 (license license:artistic2.0)))
8158
e619a5c2
RW		 8159(define-public r-r4rna
8160 (package
8161 (name "r-r4rna")
8162 (version "0.1.4")
8163 (source
8164 (origin
8165 (method url-fetch)
8166 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8167 version ".tar.gz"))
8168 (sha256
8169 (base32
8170 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8171 (build-system r-build-system)
8172 (propagated-inputs
8173 `(("r-optparse" ,r-optparse)
8174 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8175 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8176 (synopsis "Analysis framework for RNA secondary structure")
8177 (description
8178 "The R4RNA package aims to be a general framework for the analysis of RNA
8179secondary structure and comparative analysis in R.")
8180 (license license:gpl3+)))
8181
52765a63
RW		 8182(define-public r-rhtslib
8183 (package
8184 (name "r-rhtslib")
1d0263b4 8185 (version "1.10.0")
52765a63
RW		 8186 (source
8187 (origin
8188 (method url-fetch)
8189 (uri (bioconductor-uri "Rhtslib" version))
8190 (sha256
8191 (base32
1d0263b4 8192 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
52765a63
RW		 8193 (properties `((upstream-name . "Rhtslib")))
8194 (build-system r-build-system)
8195 (propagated-inputs
8196 `(("r-zlibbioc" ,r-zlibbioc)))
8197 (inputs
8198 `(("zlib" ,zlib)))
53ca52f0
RW		 8199 (native-inputs
8200 `(("autoconf" ,autoconf)))
52765a63
RW		 8201 (home-page "https://github.com/nhayden/Rhtslib")
8202 (synopsis "High-throughput sequencing library as an R package")
8203 (description
8204 "This package provides the HTSlib C library for high-throughput
8205nucleotide sequence analysis. The package is primarily useful to developers
8206of other R packages who wish to make use of HTSlib.")
8207 (license license:lgpl2.0+)))
8208
fe02c4c9
RW		 8209(define-public r-bamsignals
8210 (package
8211 (name "r-bamsignals")
da153b7f 8212 (version "1.10.0")
fe02c4c9
RW		 8213 (source
8214 (origin
8215 (method url-fetch)
8216 (uri (bioconductor-uri "bamsignals" version))
8217 (sha256
8218 (base32
da153b7f 8219 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
fe02c4c9
RW		 8220 (build-system r-build-system)
8221 (propagated-inputs
8222 `(("r-biocgenerics" ,r-biocgenerics)
8223 ("r-genomicranges" ,r-genomicranges)
8224 ("r-iranges" ,r-iranges)
8225 ("r-rcpp" ,r-rcpp)
8226 ("r-rhtslib" ,r-rhtslib)
8227 ("r-zlibbioc" ,r-zlibbioc)))
8228 (inputs
8229 `(("zlib" ,zlib)))
5713bbf1 8230 (home-page "https://bioconductor.org/packages/bamsignals")
fe02c4c9
RW		 8231 (synopsis "Extract read count signals from bam files")
8232 (description
8233 "This package allows to efficiently obtain count vectors from indexed bam
8234files. It counts the number of nucleotide sequence reads in given genomic
8235ranges and it computes reads profiles and coverage profiles. It also handles
8236paired-end data.")
8237 (license license:gpl2+)))
8238
89984be4
RW		 8239(define-public r-rcas
8240 (package
8241 (name "r-rcas")
d82937fb 8242 (version "1.3.4")
89984be4
RW		 8243 (source (origin
8244 (method url-fetch)
8245 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8246 version ".tar.gz"))
8247 (file-name (string-append name "-" version ".tar.gz"))
8248 (sha256
8249 (base32
d82937fb 8250 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
89984be4
RW		 8251 (build-system r-build-system)
8252 (native-inputs
8253 `(("r-knitr" ,r-knitr)
8254 ("r-testthat" ,r-testthat)
8255 ;; During vignette building knitr checks that "pandoc-citeproc"
8256 ;; is in the PATH.
8257 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8258 (propagated-inputs
8259 `(("r-data-table" ,r-data-table)
8260 ("r-biomart" ,r-biomart)
8261 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8262 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8263 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8264 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8265 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8266 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8267 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8268 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8269 ("r-topgo" ,r-topgo)
8270 ("r-dt" ,r-dt)
ebfd6a71 8271 ("r-pbapply" ,r-pbapply)
89984be4 8272 ("r-plotly" ,r-plotly)
2c8d6c0b 8273 ("r-plotrix" ,r-plotrix)
89984be4
RW		 8274 ("r-motifrg" ,r-motifrg)
8275 ("r-genomation" ,r-genomation)
8276 ("r-genomicfeatures" ,r-genomicfeatures)
8277 ("r-rtracklayer" ,r-rtracklayer)
8278 ("r-rmarkdown" ,r-rmarkdown)))
8279 (synopsis "RNA-centric annotation system")
8280 (description
8281 "RCAS aims to be a standalone RNA-centric annotation system that provides
8282intuitive reports and publication-ready graphics. This package provides the R
8283library implementing most of the pipeline's features.")
8284 (home-page "https://github.com/BIMSBbioinfo/RCAS")
75690c9f 8285 (license license:artistic2.0)))
89984be4 8286
50937297
RW		 8287(define-public rcas-web
8288 (package
8289 (name "rcas-web")
01d87d3c 8290 (version "0.0.4")
50937297
RW		 8291 (source
8292 (origin
8293 (method url-fetch)
8294 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8295 "releases/download/v" version
8296 "/rcas-web-" version ".tar.gz"))
8297 (sha256
8298 (base32
01d87d3c 8299 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
50937297
RW		 8300 (build-system gnu-build-system)
8301 (arguments
8302 `(#:phases
8303 (modify-phases %standard-phases
8304 (add-after 'install 'wrap-executable
8305 (lambda* (#:key inputs outputs #:allow-other-keys)
8306 (let* ((out (assoc-ref outputs "out"))
8307 (json (assoc-ref inputs "guile-json"))
8308 (redis (assoc-ref inputs "guile-redis"))
8309 (path (string-append
8310 json "/share/guile/site/2.2:"
8311 redis "/share/guile/site/2.2")))
8312 (wrap-program (string-append out "/bin/rcas-web")
8313 `("GUILE_LOAD_PATH" ":" = (,path))
8314 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8315 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8316 #t)))))
8317 (inputs
2d7c4ae3 8318 `(("r-minimal" ,r-minimal)
50937297 8319 ("r-rcas" ,r-rcas)
f6396d86 8320 ("guile-next" ,guile-2.2)
2252f087 8321 ("guile-json" ,guile-json)
50937297
RW		 8322 ("guile-redis" ,guile2.2-redis)))
8323 (native-inputs
8324 `(("pkg-config" ,pkg-config)))
8325 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8326 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8327 (description "This package provides a simple web interface for the
8328@dfn{RNA-centric annotation system} (RCAS).")
8329 (license license:agpl3+)))
8330
7500e42b
RJ		 8331(define-public r-mutationalpatterns
8332 (package
8333 (name "r-mutationalpatterns")
1fd904fb 8334 (version "1.4.1")
7500e42b
RJ		 8335 (source
8336 (origin
8337 (method url-fetch)
8338 (uri (bioconductor-uri "MutationalPatterns" version))
8339 (sha256
8340 (base32
1fd904fb 8341 "1qhxlfl85ifr30wrsidcn3kca3vs8fd8cmwd82gvgx9ppww8vs06"))))
7500e42b
RJ		 8342 (build-system r-build-system)
8343 (propagated-inputs
8344 `(("r-biocgenerics" ,r-biocgenerics)
8345 ("r-biostrings" ,r-biostrings)
cf4ac4e4
RJ		 8346 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8347 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7500e42b
RJ		 8348 ("r-genomicranges" ,r-genomicranges)
8349 ("r-genomeinfodb" ,r-genomeinfodb)
8350 ("r-ggplot2" ,r-ggplot2)
8351 ("r-gridextra" ,r-gridextra)
8352 ("r-iranges" ,r-iranges)
8353 ("r-nmf" ,r-nmf)
8354 ("r-plyr" ,r-plyr)
8355 ("r-pracma" ,r-pracma)
8356 ("r-reshape2" ,r-reshape2)
39d9098d
RW		 8357 ("r-cowplot" ,r-cowplot)
8358 ("r-ggdendro" ,r-ggdendro)
8359 ("r-s4vectors" ,r-s4vectors)
7500e42b
RJ		 8360 ("r-summarizedexperiment" ,r-summarizedexperiment)
8361 ("r-variantannotation" ,r-variantannotation)))
5713bbf1 8362 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
7500e42b
RJ		 8363 (synopsis "Extract and visualize mutational patterns in genomic data")
8364 (description "This package provides an extensive toolset for the
8365characterization and visualization of a wide range of mutational patterns
8366in SNV base substitution data.")
8367 (license license:expat)))
8368
d7160529
RW		 8369(define-public r-wgcna
8370 (package
8371 (name "r-wgcna")
1b22ecda 8372 (version "1.61")
d7160529
RW		 8373 (source
8374 (origin
8375 (method url-fetch)
8376 (uri (cran-uri "WGCNA" version))
8377 (sha256
8378 (base32
1b22ecda 8379 "1vrc2k33a196hrrl7k0z534fp96vv0shmigcr65ny1q0v6lq0h6i"))))
d7160529
RW		 8380 (properties `((upstream-name . "WGCNA")))
8381 (build-system r-build-system)
8382 (propagated-inputs
8383 `(("r-annotationdbi" ,r-annotationdbi)
8384 ("r-doparallel" ,r-doparallel)
8385 ("r-dynamictreecut" ,r-dynamictreecut)
8386 ("r-fastcluster" ,r-fastcluster)
8387 ("r-foreach" ,r-foreach)
8388 ("r-go-db" ,r-go-db)
8389 ("r-hmisc" ,r-hmisc)
8390 ("r-impute" ,r-impute)
1b22ecda
RW		 8391 ("r-rcpp" ,r-rcpp)
8392 ("r-robust" ,r-robust)
8393 ("r-survival" ,r-survival)
d7160529
RW		 8394 ("r-matrixstats" ,r-matrixstats)
8395 ("r-preprocesscore" ,r-preprocesscore)))
8396 (home-page
8397 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8398 (synopsis "Weighted correlation network analysis")
8399 (description
8400 "This package provides functions necessary to perform Weighted
8401Correlation Network Analysis on high-dimensional data. It includes functions
8402for rudimentary data cleaning, construction and summarization of correlation
8403networks, module identification and functions for relating both variables and
8404modules to sample traits. It also includes a number of utility functions for
8405data manipulation and visualization.")
8406 (license license:gpl2+)))
8407
c827f202
RW		 8408(define-public r-chipkernels
8409 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8410 (revision "1"))
8411 (package
8412 (name "r-chipkernels")
8413 (version (string-append "1.1-" revision "." (string-take commit 9)))
8414 (source
8415 (origin
8416 (method git-fetch)
8417 (uri (git-reference
8418 (url "https://github.com/ManuSetty/ChIPKernels.git")
8419 (commit commit)))
8420 (file-name (string-append name "-" version))
8421 (sha256
8422 (base32
8423 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8424 (build-system r-build-system)
8425 (propagated-inputs
8426 `(("r-iranges" ,r-iranges)
8427 ("r-xvector" ,r-xvector)
8428 ("r-biostrings" ,r-biostrings)
8429 ("r-bsgenome" ,r-bsgenome)
8430 ("r-gtools" ,r-gtools)
8431 ("r-genomicranges" ,r-genomicranges)
8432 ("r-sfsmisc" ,r-sfsmisc)
8433 ("r-kernlab" ,r-kernlab)
8434 ("r-s4vectors" ,r-s4vectors)
8435 ("r-biocgenerics" ,r-biocgenerics)))
8436 (home-page "https://github.com/ManuSetty/ChIPKernels")
8437 (synopsis "Build string kernels for DNA Sequence analysis")
8438 (description "ChIPKernels is an R package for building different string
8439kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8440must be built and this dictionary can be used for determining kernels for DNA
8441Sequences.")
8442 (license license:gpl2+))))
8443
2d9fb170
RW		 8444(define-public r-seqgl
8445 (package
8446 (name "r-seqgl")
8447 (version "1.1.4")
8448 (source
8449 (origin
8450 (method url-fetch)
8451 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8452 "archive/" version ".tar.gz"))
8453 (file-name (string-append name "-" version ".tar.gz"))
8454 (sha256
8455 (base32
8456 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8457 (build-system r-build-system)
8458 (propagated-inputs
8459 `(("r-biostrings" ,r-biostrings)
8460 ("r-chipkernels" ,r-chipkernels)
8461 ("r-genomicranges" ,r-genomicranges)
8462 ("r-spams" ,r-spams)
8463 ("r-wgcna" ,r-wgcna)
8464 ("r-fastcluster" ,r-fastcluster)))
8465 (home-page "https://github.com/ManuSetty/SeqGL")
8466 (synopsis "Group lasso for Dnase/ChIP-seq data")
8467 (description "SeqGL is a group lasso based algorithm to extract
8468transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8469This package presents a method which uses group lasso to discriminate between
8470bound and non bound genomic regions to accurately identify transcription
8471factors bound at the specific regions.")
8472 (license license:gpl2+)))
8473
bd3be46e
RW		 8474(define-public r-gkmsvm
8475 (package
8476 (name "r-gkmsvm")
8477 (version "0.71.0")
8478 (source
8479 (origin
8480 (method url-fetch)
8481 (uri (cran-uri "gkmSVM" version))
8482 (sha256
8483 (base32
8484 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8485 (properties `((upstream-name . "gkmSVM")))
8486 (build-system r-build-system)
8487 (propagated-inputs
8488 `(("r-biocgenerics" ,r-biocgenerics)
8489 ("r-biostrings" ,r-biostrings)
8490 ("r-genomeinfodb" ,r-genomeinfodb)
8491 ("r-genomicranges" ,r-genomicranges)
8492 ("r-iranges" ,r-iranges)
8493 ("r-kernlab" ,r-kernlab)
8494 ("r-rcpp" ,r-rcpp)
8495 ("r-rocr" ,r-rocr)
8496 ("r-rtracklayer" ,r-rtracklayer)
8497 ("r-s4vectors" ,r-s4vectors)
8498 ("r-seqinr" ,r-seqinr)))
8499 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8500 (synopsis "Gapped-kmer support vector machine")
8501 (description
8502 "This R package provides tools for training gapped-kmer SVM classifiers
8503for DNA and protein sequences. This package supports several sequence
8504kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8505 (license license:gpl2+)))
8506
d4af25b5
RJPB		 8507(define-public r-tximport
8508 (package
8509 (name "r-tximport")
19e8929c 8510 (version "1.6.0")
d4af25b5
RJPB		 8511 (source (origin
8512 (method url-fetch)
8513 (uri (bioconductor-uri "tximport" version))
8514 (sha256
8515 (base32
19e8929c 8516 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
d4af25b5 8517 (build-system r-build-system)
5713bbf1 8518 (home-page "https://bioconductor.org/packages/tximport")
d4af25b5
RJPB		 8519 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8520 (description
8521 "This package provides tools to import transcript-level abundance,
8522estimated counts and transcript lengths, and to summarize them into matrices
8523for use with downstream gene-level analysis packages. Average transcript
8524length, weighted by sample-specific transcript abundance estimates, is
8525provided as a matrix which can be used as an offset for different expression
8526of gene-level counts.")
8527 (license license:gpl2+)))
8528
69f2b3bd
RJPB		 8529(define-public r-rhdf5
8530 (package
8531 (name "r-rhdf5")
e6b332d4 8532 (version "2.22.0")
69f2b3bd
RJPB		 8533 (source (origin
8534 (method url-fetch)
8535 (uri (bioconductor-uri "rhdf5" version))
8536 (sha256
8537 (base32
e6b332d4 8538 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
69f2b3bd
RJPB		 8539 (build-system r-build-system)
8540 (arguments
8541 `(#:phases
8542 (modify-phases %standard-phases
8543 (add-after 'unpack 'unpack-smallhdf5
8544 (lambda* (#:key outputs #:allow-other-keys)
8545 (system* "tar" "-xzvf"
8546 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
69f2b3bd
RJPB		 8547 (substitute* "src/hdf5/configure"
8548 (("/bin/mv") "mv"))
8549 #t)))))
8550 (propagated-inputs
8551 `(("r-zlibbioc" ,r-zlibbioc)))
8552 (inputs
8553 `(("perl" ,perl)
8554 ("zlib" ,zlib)))
5713bbf1 8555 (home-page "https://bioconductor.org/packages/rhdf5")
69f2b3bd
RJPB		 8556 (synopsis "HDF5 interface to R")
8557 (description
8558 "This R/Bioconductor package provides an interface between HDF5 and R.
8559HDF5's main features are the ability to store and access very large and/or
8560complex datasets and a wide variety of metadata on mass storage (disk) through
8561a completely portable file format. The rhdf5 package is thus suited for the
8562exchange of large and/or complex datasets between R and other software
8563package, and for letting R applications work on datasets that are larger than
8564the available RAM.")
8565 (license license:artistic2.0)))
8566
17cddc17
RW		 8567(define-public r-annotationfilter
8568 (package
8569 (name "r-annotationfilter")
598dacf6 8570 (version "1.2.0")
17cddc17
RW		 8571 (source (origin
8572 (method url-fetch)
8573 (uri (bioconductor-uri "AnnotationFilter" version))
8574 (sha256
8575 (base32
598dacf6 8576 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
17cddc17
RW		 8577 (properties
8578 `((upstream-name . "AnnotationFilter")))
8579 (build-system r-build-system)
8580 (propagated-inputs
8581 `(("r-genomicranges" ,r-genomicranges)
8582 ("r-lazyeval" ,r-lazyeval)))
8583 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8584 (synopsis "Facilities for filtering Bioconductor annotation resources")
8585 (description
8586 "This package provides classes and other infrastructure to implement
8587filters for manipulating Bioconductor annotation resources. The filters are
8588used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8589 (license license:artistic2.0)))
8590
66e40e00
RW		 8591(define-public emboss
8592 (package
8593 (name "emboss")
8594 (version "6.5.7")
8595 (source (origin
8596 (method url-fetch)
8597 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8598 (version-major+minor version) ".0/"
8599 "EMBOSS-" version ".tar.gz"))
8600 (sha256
8601 (base32
8602 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8603 (build-system gnu-build-system)
8604 (arguments
8605 `(#:configure-flags
8606 (list (string-append "--with-hpdf="
8607 (assoc-ref %build-inputs "libharu")))
8608 #:phases
8609 (modify-phases %standard-phases
8610 (add-after 'unpack 'fix-checks
8611 (lambda _
8612 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8613 ;; and zlib, but assume that they are all found at the same
8614 ;; prefix.
8615 (substitute* "configure.in"
8616 (("CHECK_PNGDRIVER")
8617 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8618AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8619AM_CONDITIONAL(AMPNG, true)"))
8620 #t))
d10092b8 8621 (add-after 'fix-checks 'disable-update-check
66e40e00
RW		 8622 (lambda _
8623 ;; At build time there is no connection to the Internet, so
8624 ;; looking for updates will not work.
8625 (substitute* "Makefile.am"
8626 (("\\$\\(bindir\\)/embossupdate") ""))
8627 #t))
d10092b8 8628 (add-after 'disable-update-check 'autogen
66e40e00
RW		 8629 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8630 (inputs
8631 `(("perl" ,perl)
8632 ("libpng" ,libpng)
8633 ("gd" ,gd)
8634 ("libx11" ,libx11)
8635 ("libharu" ,libharu)
8636 ("zlib" ,zlib)))
8637 (native-inputs
8638 `(("autoconf" ,autoconf)
8639 ("automake" ,automake)
8640 ("libtool" ,libtool)
8641 ("pkg-config" ,pkg-config)))
8642 (home-page "http://emboss.sourceforge.net")
8643 (synopsis "Molecular biology analysis suite")
8644 (description "EMBOSS is the \"European Molecular Biology Open Software
8645Suite\". EMBOSS is an analysis package specially developed for the needs of
8646the molecular biology (e.g. EMBnet) user community. The software
8647automatically copes with data in a variety of formats and even allows
8648transparent retrieval of sequence data from the web. It also provides a
8649number of libraries for the development of software in the field of molecular
8650biology. EMBOSS also integrates a range of currently available packages and
8651tools for sequence analysis into a seamless whole.")
8652 (license license:gpl2+)))
8653
1f1b20b8
RW		 8654(define-public bits
8655 (let ((revision "1")
8656 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8657 (package
8658 (name "bits")
8659 ;; The version is 2.13.0 even though no release archives have been
8660 ;; published as yet.
8661 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8662 (source (origin
8663 (method git-fetch)
8664 (uri (git-reference
8665 (url "https://github.com/arq5x/bits.git")
8666 (commit commit)))
8667 (file-name (string-append name "-" version "-checkout"))
8668 (sha256
8669 (base32
8670 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8671 (build-system gnu-build-system)
8672 (arguments
8673 `(#:tests? #f ;no tests included
8674 #:phases
8675 (modify-phases %standard-phases
8676 (delete 'configure)
8677 (add-after 'unpack 'remove-cuda
8678 (lambda _
8679 (substitute* "Makefile"
8680 ((".*_cuda") "")
8681 (("(bits_test_intersections) \\\\" _ match) match))
8682 #t))
8683 (replace 'install
8684 (lambda* (#:key outputs #:allow-other-keys)
8685 (copy-recursively
8686 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8687 #t)))))
8688 (inputs
8689 `(("gsl" ,gsl)
8690 ("zlib" ,zlib)))
8691 (home-page "https://github.com/arq5x/bits")
8692 (synopsis "Implementation of binary interval search algorithm")
8693 (description "This package provides an implementation of the
8694BITS (Binary Interval Search) algorithm, an approach to interval set
8695intersection. It is especially suited for the comparison of diverse genomic
8696datasets and the exploration of large datasets of genome
8697intervals (e.g. genes, sequence alignments).")
8698 (license license:gpl2))))
8699
e62ffce5 8700(define-public piranha
883302da
RW		 8701 ;; There is no release tarball for the latest version. The latest commit is
8702 ;; older than one year at the time of this writing.
8703 (let ((revision "1")
8704 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8705 (package
8706 (name "piranha")
8707 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8708 (source (origin
8709 (method git-fetch)
8710 (uri (git-reference
8711 (url "https://github.com/smithlabcode/piranha.git")
8712 (commit commit)))
8713 (sha256
8714 (base32
8715 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8716 (build-system gnu-build-system)
8717 (arguments
8718 `(#:test-target "test"
8719 #:phases
8720 (modify-phases %standard-phases
8721 (add-after 'unpack 'copy-smithlab-cpp
8722 (lambda* (#:key inputs #:allow-other-keys)
e62ffce5 8723 (for-each (lambda (file)
883302da
RW		 8724 (install-file file "./src/smithlab_cpp/"))
8725 (find-files (assoc-ref inputs "smithlab-cpp")))
8726 #t))
8727 (add-after 'install 'install-to-store
8728 (lambda* (#:key outputs #:allow-other-keys)
8729 (let* ((out (assoc-ref outputs "out"))
8730 (bin (string-append out "/bin")))
883302da
RW		 8731 (for-each (lambda (file)
8732 (install-file file bin))
8733 (find-files "bin" ".*")))
8734 #t)))
8735 #:configure-flags
8736 (list (string-append "--with-bam_tools_headers="
8737 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8738 (string-append "--with-bam_tools_library="
8739 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8740 (inputs
8741 `(("bamtools" ,bamtools)
8742 ("samtools" ,samtools-0.1)
8743 ("gsl" ,gsl)
8744 ("smithlab-cpp"
8745 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8746 (origin
8747 (method git-fetch)
8748 (uri (git-reference
8749 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8750 (commit commit)))
8751 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8752 (sha256
8753 (base32
8754 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8755 (native-inputs
8756 `(("python" ,python-2)))
8757 (home-page "https://github.com/smithlabcode/piranha")
8758 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8759 (description
8760 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
e62ffce5
RW		 8761RIP-seq experiments. It takes input in BED or BAM format and identifies
8762regions of statistically significant read enrichment. Additional covariates
8763may optionally be provided to further inform the peak-calling process.")
883302da 8764 (license license:gpl3+))))
e62ffce5 8765
d1e32822
RW		 8766(define-public pepr
8767 (package
8768 (name "pepr")
8769 (version "1.0.9")
8770 (source (origin
8771 (method url-fetch)
8772 (uri (string-append "https://pypi.python.org/packages/source/P"
8773 "/PePr/PePr-" version ".tar.gz"))
8774 (sha256
8775 (base32
8776 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8777 (build-system python-build-system)
8778 (arguments
8779 `(#:python ,python-2 ; python2 only
b41a05ce 8780 #:tests? #f)) ; no tests included
d1e32822
RW		 8781 (propagated-inputs
8782 `(("python2-numpy" ,python2-numpy)
8783 ("python2-scipy" ,python2-scipy)
8784 ("python2-pysam" ,python2-pysam)))
0c6c9c00 8785 (home-page "https://github.com/shawnzhangyx/PePr")
d1e32822
RW		 8786 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8787 (description
8788 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8789that is primarily designed for data with biological replicates. It uses a
8790negative binomial distribution to model the read counts among the samples in
8791the same group, and look for consistent differences between ChIP and control
8792group or two ChIP groups run under different conditions.")
8793 (license license:gpl3+)))
6b49a37e
RJ		 8794
8795(define-public filevercmp
8796 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8797 (package
8798 (name "filevercmp")
8799 (version (string-append "0-1." (string-take commit 7)))
8800 (source (origin
8801 (method url-fetch)
8802 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8803 commit ".tar.gz"))
8804 (file-name (string-append name "-" version ".tar.gz"))
8805 (sha256
8806 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8807 (build-system gnu-build-system)
8808 (arguments
8809 `(#:tests? #f ; There are no tests to run.
8810 #:phases
8811 (modify-phases %standard-phases
8812 (delete 'configure) ; There is no configure phase.
8813 (replace 'install
8814 (lambda* (#:key outputs #:allow-other-keys)
8815 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8816 (install-file "filevercmp" bin)))))))
8817 (home-page "https://github.com/ekg/filevercmp")
8818 (synopsis "This program compares version strings")
8819 (description "This program compares version strings. It intends to be a
8820replacement for strverscmp.")
8821 (license license:gpl3+))))
5fb5dffb
RW		 8822
8823(define-public multiqc
8824 (package
8825 (name "multiqc")
66865ab8 8826 (version "1.3")
5fb5dffb
RW		 8827 (source
8828 (origin
8829 (method url-fetch)
8830 (uri (pypi-uri "multiqc" version))
8831 (sha256
8832 (base32
66865ab8 8833 "0fx1sx53znbgzfhbbiyd8j6cg5llpcsl5q5c45jy2c81d12piqfd"))))
5fb5dffb
RW		 8834 (build-system python-build-system)
8835 (propagated-inputs
66865ab8
RW		 8836 `(("python-enum34" ,python-enum34)
8837 ("python-jinja2" ,python-jinja2)
5fb5dffb
RW		 8838 ("python-simplejson" ,python-simplejson)
8839 ("python-pyyaml" ,python-pyyaml)
8840 ("python-click" ,python-click)
799247d2
RW		 8841 ("python-spectra" ,python-spectra)
8842 ("python-requests" ,python-requests)
8843 ("python-markdown" ,python-markdown)
8844 ("python-lzstring" ,python-lzstring)
5fb5dffb 8845 ("python-matplotlib" ,python-matplotlib)
1778ea74
RW		 8846 ("python-numpy" ,python-numpy)
8847 ;; MultQC checks for the presence of nose at runtime.
8848 ("python-nose" ,python-nose)))
5fb5dffb
RW		 8849 (home-page "http://multiqc.info")
8850 (synopsis "Aggregate bioinformatics analysis reports")
8851 (description
8852 "MultiQC is a tool to aggregate bioinformatics results across many
8853samples into a single report. It contains modules for a large number of
8854common bioinformatics tools.")
66865ab8 8855 (license license:gpl3+)))
6193563a
RW		 8856
8857(define-public r-chipseq
8858 (package
8859 (name "r-chipseq")
eeaa6967 8860 (version "1.28.0")
6193563a
RW		 8861 (source
8862 (origin
8863 (method url-fetch)
8864 (uri (bioconductor-uri "chipseq" version))
8865 (sha256
8866 (base32
eeaa6967 8867 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
6193563a
RW		 8868 (build-system r-build-system)
8869 (propagated-inputs
8870 `(("r-biocgenerics" ,r-biocgenerics)
8871 ("r-genomicranges" ,r-genomicranges)
8872 ("r-iranges" ,r-iranges)
eeaa6967 8873 ("r-lattice" ,r-lattice)
6193563a
RW		 8874 ("r-s4vectors" ,r-s4vectors)
8875 ("r-shortread" ,r-shortread)))
5713bbf1 8876 (home-page "https://bioconductor.org/packages/chipseq")
6193563a
RW		 8877 (synopsis "Package for analyzing ChIPseq data")
8878 (description
8879 "This package provides tools for processing short read data from ChIPseq
8880experiments.")
8881 (license license:artistic2.0)))
d407bdb9
RW		 8882
8883(define-public r-copyhelper
8884 (package
8885 (name "r-copyhelper")
8886 (version "1.6.0")
8887 (source
8888 (origin
8889 (method url-fetch)
5713bbf1 8890 (uri (string-append "https://bioconductor.org/packages/release/"
d407bdb9
RW		 8891 "data/experiment/src/contrib/CopyhelpeR_"
8892 version ".tar.gz"))
8893 (sha256
8894 (base32
8895 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8896 (properties `((upstream-name . "CopyhelpeR")))
8897 (build-system r-build-system)
5713bbf1 8898 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
d407bdb9
RW		 8899 (synopsis "Helper files for CopywriteR")
8900 (description
8901 "This package contains the helper files that are required to run the
8902Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8903and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8904mm10. In addition, it contains a blacklist filter to remove regions that
8905display copy number variation. Files are stored as GRanges objects from the
8906GenomicRanges Bioconductor package.")
8907 (license license:gpl2)))
3a3bf2f8
RW		 8908
8909(define-public r-copywriter
8910 (package
8911 (name "r-copywriter")
c126ba69 8912 (version "2.10.0")
3a3bf2f8
RW		 8913 (source
8914 (origin
8915 (method url-fetch)
8916 (uri (bioconductor-uri "CopywriteR" version))
8917 (sha256
8918 (base32
c126ba69 8919 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
3a3bf2f8
RW		 8920 (properties `((upstream-name . "CopywriteR")))
8921 (build-system r-build-system)
8922 (propagated-inputs
8923 `(("r-biocparallel" ,r-biocparallel)
8924 ("r-chipseq" ,r-chipseq)
8925 ("r-copyhelper" ,r-copyhelper)
8926 ("r-data-table" ,r-data-table)
8927 ("r-dnacopy" ,r-dnacopy)
8928 ("r-futile-logger" ,r-futile-logger)
8929 ("r-genomeinfodb" ,r-genomeinfodb)
8930 ("r-genomicalignments" ,r-genomicalignments)
8931 ("r-genomicranges" ,r-genomicranges)
8932 ("r-gtools" ,r-gtools)
8933 ("r-iranges" ,r-iranges)
8934 ("r-matrixstats" ,r-matrixstats)
8935 ("r-rsamtools" ,r-rsamtools)
8936 ("r-s4vectors" ,r-s4vectors)))
8937 (home-page "https://github.com/PeeperLab/CopywriteR")
8938 (synopsis "Copy number information from targeted sequencing")
8939 (description
8940 "CopywriteR extracts DNA copy number information from targeted sequencing
8941by utilizing off-target reads. It allows for extracting uniformly distributed
8942copy number information, can be used without reference, and can be applied to
8943sequencing data obtained from various techniques including chromatin
8944immunoprecipitation and target enrichment on small gene panels. Thereby,
8945CopywriteR constitutes a widely applicable alternative to available copy
8946number detection tools.")
8947 (license license:gpl2)))
dd42a330 8948
bf3fa996
RW		 8949(define-public r-methylkit
8950 (package
8951 (name "r-methylkit")
91e18679 8952 (version "1.4.0")
bf3fa996
RW		 8953 (source (origin
8954 (method url-fetch)
8955 (uri (bioconductor-uri "methylKit" version))
8956 (sha256
8957 (base32
91e18679 8958 "0h53w2mrjrg2n0ndi12k9j6cwclgwcgpy25nz7nyj971aisw02xn"))))
bf3fa996
RW		 8959 (properties `((upstream-name . "methylKit")))
8960 (build-system r-build-system)
8961 (propagated-inputs
8962 `(("r-data-table" ,r-data-table)
8963 ("r-emdbook" ,r-emdbook)
8964 ("r-fastseg" ,r-fastseg)
8965 ("r-genomeinfodb" ,r-genomeinfodb)
8966 ("r-genomicranges" ,r-genomicranges)
8967 ("r-gtools" ,r-gtools)
8968 ("r-iranges" ,r-iranges)
8969 ("r-kernsmooth" ,r-kernsmooth)
8970 ("r-limma" ,r-limma)
8971 ("r-mclust" ,r-mclust)
8972 ("r-qvalue" ,r-qvalue)
8973 ("r-r-utils" ,r-r-utils)
8974 ("r-rcpp" ,r-rcpp)
8975 ("r-rhtslib" ,r-rhtslib)
8976 ("r-rsamtools" ,r-rsamtools)
8977 ("r-rtracklayer" ,r-rtracklayer)
8978 ("r-s4vectors" ,r-s4vectors)
8979 ("r-zlibbioc" ,r-zlibbioc)))
8980 (inputs
8981 `(("zlib" ,zlib)))
11ed4108 8982 (home-page "https://github.com/al2na/methylKit")
bf3fa996
RW		 8983 (synopsis
8984 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8985 (description
8986 "MethylKit is an R package for DNA methylation analysis and annotation
8987from high-throughput bisulfite sequencing. The package is designed to deal
8988with sequencing data from @dfn{Reduced representation bisulfite
8989sequencing} (RRBS) and its variants, but also target-capture methods and whole
8990genome bisulfite sequencing. It also has functions to analyze base-pair
8991resolution 5hmC data from experimental protocols such as oxBS-Seq and
8992TAB-Seq.")
8993 (license license:artistic2.0)))
8994
dd42a330
RJPB		 8995(define-public r-sva
8996 (package
8997 (name "r-sva")
fad7c0c7 8998 (version "3.26.0")
dd42a330
RJPB		 8999 (source
9000 (origin
9001 (method url-fetch)
9002 (uri (bioconductor-uri "sva" version))
9003 (sha256
9004 (base32
fad7c0c7 9005 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
dd42a330
RJPB		 9006 (build-system r-build-system)
9007 (propagated-inputs
aeb64f3c 9008 `(("r-genefilter" ,r-genefilter)
bfa0d1e7
RJ		 9009 ("r-mgcv" ,r-mgcv)
9010 ("r-biocparallel" ,r-biocparallel)
9011 ("r-matrixstats" ,r-matrixstats)
9012 ("r-limma" ,r-limma)))
5713bbf1 9013 (home-page "https://bioconductor.org/packages/sva")
dd42a330
RJPB		 9014 (synopsis "Surrogate variable analysis")
9015 (description
9016 "This package contains functions for removing batch effects and other
9017unwanted variation in high-throughput experiment. It also contains functions
9018for identifying and building surrogate variables for high-dimensional data
9019sets. Surrogate variables are covariates constructed directly from
9020high-dimensional data like gene expression/RNA sequencing/methylation/brain
9021imaging data that can be used in subsequent analyses to adjust for unknown,
9022unmodeled, or latent sources of noise.")
9023 (license license:artistic2.0)))
fb1e528e
RW		 9024
9025(define-public r-seqminer
9026 (package
9027 (name "r-seqminer")
5e0de298 9028 (version "6.0")
fb1e528e
RW		 9029 (source
9030 (origin
9031 (method url-fetch)
9032 (uri (cran-uri "seqminer" version))
9033 (sha256
9034 (base32
5e0de298 9035 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
fb1e528e
RW		 9036 (build-system r-build-system)
9037 (inputs
9038 `(("zlib" ,zlib)))
9039 (home-page "http://seqminer.genomic.codes")
9040 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9041 (description
9042 "This package provides tools to integrate nucleotide sequencing
9043data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9044 ;; Any version of the GPL is acceptable
9045 (license (list license:gpl2+ license:gpl3+))))
1f40e73c
RW		 9046
9047(define-public r-raremetals2
9048 (package
9049 (name "r-raremetals2")
9050 (version "0.1")
9051 (source
9052 (origin
9053 (method url-fetch)
9054 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9055 "b/b7/RareMETALS2_" version ".tar.gz"))
9056 (sha256
9057 (base32
9058 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9059 (properties `((upstream-name . "RareMETALS2")))
9060 (build-system r-build-system)
9061 (propagated-inputs
9062 `(("r-seqminer" ,r-seqminer)
9063 ("r-mvtnorm" ,r-mvtnorm)
aeb64f3c 9064 ("r-mass" ,r-mass)
1f40e73c
RW		 9065 ("r-compquadform" ,r-compquadform)
9066 ("r-getopt" ,r-getopt)))
9067 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9068 (synopsis "Analyze gene-level association tests for binary trait")
9069 (description
9070 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9071It was designed to meta-analyze gene-level association tests for binary trait.
9072While rareMETALS offers a near-complete solution for meta-analysis of
9073gene-level tests for quantitative trait, it does not offer the optimal
9074solution for binary trait. The package rareMETALS2 offers improved features
9075for analyzing gene-level association tests in meta-analyses for binary
9076trait.")
9077 (license license:gpl3)))
0e7d058e
RW		 9078
9079(define-public r-maldiquant
9080 (package
9081 (name "r-maldiquant")
43949265 9082 (version "1.17")
0e7d058e
RW		 9083 (source
9084 (origin
9085 (method url-fetch)
9086 (uri (cran-uri "MALDIquant" version))
9087 (sha256
9088 (base32
43949265 9089 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
0e7d058e
RW		 9090 (properties `((upstream-name . "MALDIquant")))
9091 (build-system r-build-system)
9092 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
9093 (synopsis "Quantitative analysis of mass spectrometry data")
9094 (description
9095 "This package provides a complete analysis pipeline for matrix-assisted
9096laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9097two-dimensional mass spectrometry data. In addition to commonly used plotting
9098and processing methods it includes distinctive features, namely baseline
9099subtraction methods such as morphological filters (TopHat) or the
9100statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9101alignment using warping functions, handling of replicated measurements as well
9102as allowing spectra with different resolutions.")
9103 (license license:gpl3+)))
ae262174
RW		 9104
9105(define-public r-protgenerics
9106 (package
9107 (name "r-protgenerics")
9a665dfb 9108 (version "1.10.0")
ae262174
RW		 9109 (source
9110 (origin
9111 (method url-fetch)
9112 (uri (bioconductor-uri "ProtGenerics" version))
9113 (sha256
9114 (base32
9a665dfb 9115 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
ae262174
RW		 9116 (properties `((upstream-name . "ProtGenerics")))
9117 (build-system r-build-system)
9118 (home-page "https://github.com/lgatto/ProtGenerics")
9119 (synopsis "S4 generic functions for proteomics infrastructure")
9120 (description
9121 "This package provides S4 generic functions needed by Bioconductor
9122proteomics packages.")
9123 (license license:artistic2.0)))
71676a1f
RW		 9124
9125(define-public r-mzr
9126 (package
9127 (name "r-mzr")
34b96754 9128 (version "2.12.0")
71676a1f
RW		 9129 (source
9130 (origin
9131 (method url-fetch)
9132 (uri (bioconductor-uri "mzR" version))
9133 (sha256
9134 (base32
15ca1959
RW		 9135 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9136 (modules '((guix build utils)))
9137 (snippet
9138 '(begin
9139 (delete-file-recursively "src/boost")
9140 #t))))
71676a1f
RW		 9141 (properties `((upstream-name . "mzR")))
9142 (build-system r-build-system)
15ca1959
RW		 9143 (arguments
9144 `(#:phases
9145 (modify-phases %standard-phases
9146 (add-after 'unpack 'use-system-boost
9147 (lambda _
9148 (substitute* "src/Makevars"
9149 (("\\./boost/libs.*") "")
9150 (("ARCH_OBJS=" line)
9151 (string-append line
9152 "\nARCH_LIBS=-lboost_system -lboost_regex \
9153-lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9154 #t)))))
71676a1f 9155 (inputs
34b96754 9156 `(("boost" ,boost) ; use this instead of the bundled boost sources
d534f3a4 9157 ("netcdf" ,netcdf)))
71676a1f
RW		 9158 (propagated-inputs
9159 `(("r-biobase" ,r-biobase)
9160 ("r-biocgenerics" ,r-biocgenerics)
9161 ("r-protgenerics" ,r-protgenerics)
9162 ("r-rcpp" ,r-rcpp)
9163 ("r-zlibbioc" ,r-zlibbioc)))
9164 (home-page "https://github.com/sneumann/mzR/")
9165 (synopsis "Parser for mass spectrometry data files")
9166 (description
9167 "The mzR package provides a unified API to the common file formats and
9168parsers available for mass spectrometry data. It comes with a wrapper for the
9169ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9170The package contains the original code written by the ISB, and a subset of the
9171proteowizard library for mzML and mzIdentML. The netCDF reading code has
9172previously been used in XCMS.")
9173 (license license:artistic2.0)))
5c9d1505
RW		 9174
9175(define-public r-affyio
9176 (package
9177 (name "r-affyio")
8a8138d2 9178 (version "1.48.0")
5c9d1505
RW		 9179 (source
9180 (origin
9181 (method url-fetch)
9182 (uri (bioconductor-uri "affyio" version))
9183 (sha256
9184 (base32
8a8138d2 9185 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
5c9d1505
RW		 9186 (build-system r-build-system)
9187 (propagated-inputs
9188 `(("r-zlibbioc" ,r-zlibbioc)))
9189 (inputs
9190 `(("zlib" ,zlib)))
9191 (home-page "https://github.com/bmbolstad/affyio")
9192 (synopsis "Tools for parsing Affymetrix data files")
9193 (description
9194 "This package provides routines for parsing Affymetrix data files based
9195upon file format information. The primary focus is on accessing the CEL and
9196CDF file formats.")
9197 (license license:lgpl2.0+)))
05c7e5fb
RW		 9198
9199(define-public r-affy
9200 (package
9201 (name "r-affy")
dad5f838 9202 (version "1.56.0")
05c7e5fb
RW		 9203 (source
9204 (origin
9205 (method url-fetch)
9206 (uri (bioconductor-uri "affy" version))
9207 (sha256
9208 (base32
dad5f838 9209 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
05c7e5fb
RW		 9210 (build-system r-build-system)
9211 (propagated-inputs
9212 `(("r-affyio" ,r-affyio)
9213 ("r-biobase" ,r-biobase)
9214 ("r-biocgenerics" ,r-biocgenerics)
9215 ("r-biocinstaller" ,r-biocinstaller)
9216 ("r-preprocesscore" ,r-preprocesscore)
9217 ("r-zlibbioc" ,r-zlibbioc)))
5713bbf1 9218 (home-page "https://bioconductor.org/packages/affy")
05c7e5fb
RW		 9219 (synopsis "Methods for affymetrix oligonucleotide arrays")
9220 (description
9221 "This package contains functions for exploratory oligonucleotide array
9222analysis.")
9223 (license license:lgpl2.0+)))
7c08afaf
RW		 9224
9225(define-public r-vsn
9226 (package
9227 (name "r-vsn")
1be0f536 9228 (version "3.46.0")
7c08afaf
RW		 9229 (source
9230 (origin
9231 (method url-fetch)
9232 (uri (bioconductor-uri "vsn" version))
9233 (sha256
9234 (base32
1be0f536 9235 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
7c08afaf
RW		 9236 (build-system r-build-system)
9237 (propagated-inputs
9238 `(("r-affy" ,r-affy)
9239 ("r-biobase" ,r-biobase)
9240 ("r-ggplot2" ,r-ggplot2)
aeb64f3c 9241 ("r-lattice" ,r-lattice)
7c08afaf 9242 ("r-limma" ,r-limma)))
5713bbf1 9243 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
7c08afaf
RW		 9244 (synopsis "Variance stabilization and calibration for microarray data")
9245 (description
9246 "The package implements a method for normalising microarray intensities,
9247and works for single- and multiple-color arrays. It can also be used for data
9248from other technologies, as long as they have similar format. The method uses
9249a robust variant of the maximum-likelihood estimator for an
9250additive-multiplicative error model and affine calibration. The model
9251incorporates data calibration step (a.k.a. normalization), a model for the
9252dependence of the variance on the mean intensity and a variance stabilizing
9253data transformation. Differences between transformed intensities are
9254analogous to \"normalized log-ratios\". However, in contrast to the latter,
9255their variance is independent of the mean, and they are usually more sensitive
9256and specific in detecting differential transcription.")
9257 (license license:artistic2.0)))
4aa7d592
RW		 9258
9259(define-public r-mzid
9260 (package
9261 (name "r-mzid")
b500dbcd 9262 (version "1.16.0")
4aa7d592
RW		 9263 (source
9264 (origin
9265 (method url-fetch)
9266 (uri (bioconductor-uri "mzID" version))
9267 (sha256
9268 (base32
b500dbcd 9269 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
4aa7d592
RW		 9270 (properties `((upstream-name . "mzID")))
9271 (build-system r-build-system)
9272 (propagated-inputs
9273 `(("r-doparallel" ,r-doparallel)
9274 ("r-foreach" ,r-foreach)
9275 ("r-iterators" ,r-iterators)
9276 ("r-plyr" ,r-plyr)
9277 ("r-protgenerics" ,r-protgenerics)
9278 ("r-rcpp" ,r-rcpp)
9279 ("r-xml" ,r-xml)))
5713bbf1 9280 (home-page "https://bioconductor.org/packages/mzID")
4aa7d592
RW		 9281 (synopsis "Parser for mzIdentML files")
9282 (description
9283 "This package provides a parser for mzIdentML files implemented using the
9284XML package. The parser tries to be general and able to handle all types of
9285mzIdentML files with the drawback of having less pretty output than a vendor
9286specific parser.")
9287 (license license:gpl2+)))
6a67e181
RW		 9288
9289(define-public r-pcamethods
9290 (package
9291 (name "r-pcamethods")
a998c9a4 9292 (version "1.70.0")
6a67e181
RW		 9293 (source
9294 (origin
9295 (method url-fetch)
9296 (uri (bioconductor-uri "pcaMethods" version))
9297 (sha256
9298 (base32
a998c9a4 9299 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
6a67e181
RW		 9300 (properties `((upstream-name . "pcaMethods")))
9301 (build-system r-build-system)
9302 (propagated-inputs
9303 `(("r-biobase" ,r-biobase)
9304 ("r-biocgenerics" ,r-biocgenerics)
aeb64f3c 9305 ("r-mass" ,r-mass)
6a67e181
RW		 9306 ("r-rcpp" ,r-rcpp)))
9307 (home-page "https://github.com/hredestig/pcamethods")
9308 (synopsis "Collection of PCA methods")
9309 (description
9310 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9311Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9312for missing value estimation is included for comparison. BPCA, PPCA and
9313NipalsPCA may be used to perform PCA on incomplete data as well as for
9314accurate missing value estimation. A set of methods for printing and plotting
9315the results is also provided. All PCA methods make use of the same data
9316structure (pcaRes) to provide a common interface to the PCA results.")
9317 (license license:gpl3+)))
11879284
RW		 9318
9319(define-public r-msnbase
9320 (package
9321 (name "r-msnbase")
baa00ee9 9322 (version "2.4.0")
11879284
RW		 9323 (source
9324 (origin
9325 (method url-fetch)
9326 (uri (bioconductor-uri "MSnbase" version))
9327 (sha256
9328 (base32
baa00ee9 9329 "0dqfimljhrx3gac8d1k72gppx27lz8yckyb12v4604nbviw7xd3r"))))
11879284
RW		 9330 (properties `((upstream-name . "MSnbase")))
9331 (build-system r-build-system)
9332 (propagated-inputs
9333 `(("r-affy" ,r-affy)
9334 ("r-biobase" ,r-biobase)
9335 ("r-biocgenerics" ,r-biocgenerics)
9336 ("r-biocparallel" ,r-biocparallel)
9337 ("r-digest" ,r-digest)
9338 ("r-ggplot2" ,r-ggplot2)
9339 ("r-impute" ,r-impute)
9340 ("r-iranges" ,r-iranges)
baa00ee9 9341 ("r-lattice" ,r-lattice)
11879284
RW		 9342 ("r-maldiquant" ,r-maldiquant)
9343 ("r-mzid" ,r-mzid)
9344 ("r-mzr" ,r-mzr)
9345 ("r-pcamethods" ,r-pcamethods)
9346 ("r-plyr" ,r-plyr)
9347 ("r-preprocesscore" ,r-preprocesscore)
9348 ("r-protgenerics" ,r-protgenerics)
9349 ("r-rcpp" ,r-rcpp)
11879284
RW		 9350 ("r-s4vectors" ,r-s4vectors)
9351 ("r-vsn" ,r-vsn)
9352 ("r-xml" ,r-xml)))
9353 (home-page "https://github.com/lgatto/MSnbase")
9354 (synopsis "Base functions and classes for MS-based proteomics")
9355 (description
9356 "This package provides basic plotting, data manipulation and processing
e614d639 9357of mass spectrometry based proteomics data.")
11879284 9358 (license license:artistic2.0)))
66da3a9f
RW		 9359
9360(define-public r-msnid
9361 (package
9362 (name "r-msnid")
87e91a9f 9363 (version "1.12.1")
66da3a9f
RW		 9364 (source
9365 (origin
9366 (method url-fetch)
9367 (uri (bioconductor-uri "MSnID" version))
9368 (sha256
9369 (base32
87e91a9f 9370 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
66da3a9f
RW		 9371 (properties `((upstream-name . "MSnID")))
9372 (build-system r-build-system)
9373 (propagated-inputs
9374 `(("r-biobase" ,r-biobase)
9375 ("r-data-table" ,r-data-table)
9376 ("r-doparallel" ,r-doparallel)
9377 ("r-dplyr" ,r-dplyr)
9378 ("r-foreach" ,r-foreach)
9379 ("r-iterators" ,r-iterators)
9380 ("r-msnbase" ,r-msnbase)
9381 ("r-mzid" ,r-mzid)
9382 ("r-mzr" ,r-mzr)
9383 ("r-protgenerics" ,r-protgenerics)
9384 ("r-r-cache" ,r-r-cache)
9385 ("r-rcpp" ,r-rcpp)
9386 ("r-reshape2" ,r-reshape2)))
5713bbf1 9387 (home-page "https://bioconductor.org/packages/MSnID")
66da3a9f
RW		 9388 (synopsis "Utilities for LC-MSn proteomics identifications")
9389 (description
2923f3e5
RW		 9390 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9391from mzIdentML (leveraging the mzID package) or text files. After collating
9392the search results from multiple datasets it assesses their identification
9393quality and optimize filtering criteria to achieve the maximum number of
9394identifications while not exceeding a specified false discovery rate. It also
9395contains a number of utilities to explore the MS/MS results and assess missed
9396and irregular enzymatic cleavages, mass measurement accuracy, etc.")
66da3a9f 9397 (license license:artistic2.0)))
5ded35d8 9398
2441c284 9399(define-public r-seurat
f1a2b1cb
RW		 9400 (package
9401 (name "r-seurat")
9402 (version "2.1.0")
9403 (source (origin
9404 (method url-fetch)
9405 (uri (cran-uri "Seurat" version))
9406 (sha256
9407 (base32
9408 "1hqaq6bciikrsyw157w8fn4jw885air7xbkxrmism93rp4qx483x"))
9409 ;; Delete pre-built jar.
9410 (snippet
9411 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9412 #t))))
9413 (properties `((upstream-name . "Seurat")))
9414 (build-system r-build-system)
9415 (arguments
9416 `(#:phases
9417 (modify-phases %standard-phases
9418 (add-after 'unpack 'build-jar
9419 (lambda* (#:key inputs #:allow-other-keys)
9420 (let ((classesdir "tmp-classes"))
9421 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9422 (mkdir classesdir)
9423 (with-output-to-file "manifest"
8271b8d2
RW		 9424 (lambda _
9425 (display "Manifest-Version: 1.0
9426Main-Class: ModularityOptimizer\n")))
9427 (and (zero? (apply system* `("javac" "-d" ,classesdir
9428 ,@(find-files "java" "\\.java$"))))
9429 (zero? (system* "jar"
9430 "-cmf" "manifest"
9431 "inst/java/ModularityOptimizer.jar"
f1a2b1cb
RW		 9432 "-C" classesdir ".")))))))))
9433 (native-inputs
9434 `(("jdk" ,icedtea "jdk")))
9435 (propagated-inputs
9436 `(("r-ape" ,r-ape)
9437 ("r-caret" ,r-caret)
9438 ("r-cowplot" ,r-cowplot)
9439 ("r-diffusionmap" ,r-diffusionmap)
9440 ("r-dplyr" ,r-dplyr)
9441 ("r-dtw" ,r-dtw)
9442 ("r-fnn" ,r-fnn)
9443 ("r-fpc" ,r-fpc)
9444 ("r-gdata" ,r-gdata)
9445 ("r-ggjoy" ,r-ggjoy)
9446 ("r-ggplot2" ,r-ggplot2)
9447 ("r-gplots" ,r-gplots)
9448 ("r-gridextra" ,r-gridextra)
9449 ("r-hmisc" ,r-hmisc)
9450 ("r-ica" ,r-ica)
9451 ("r-igraph" ,r-igraph)
9452 ("r-irlba" ,r-irlba)
9453 ("r-lars" ,r-lars)
9454 ("r-mass" ,r-mass)
9455 ("r-matrix" ,r-matrix)
9456 ("r-mixtools" ,r-mixtools)
9457 ("r-nmf" ,r-nmf)
9458 ("r-pbapply" ,r-pbapply)
9459 ("r-plotly" ,r-plotly)
9460 ("r-ranger" ,r-ranger)
9461 ("r-rcolorbrewer" ,r-rcolorbrewer)
9462 ("r-rcpp" ,r-rcpp)
9463 ("r-rcppprogress" ,r-rcppprogress)
9464 ("r-reshape2" ,r-reshape2)
9465 ("r-rocr" ,r-rocr)
9466 ("r-rtsne" ,r-rtsne)
9467 ("r-sdmtools" ,r-sdmtools)
9468 ("r-stringr" ,r-stringr)
9469 ("r-tclust" ,r-tclust)
9470 ("r-tidyr" ,r-tidyr)
9471 ("r-tsne" ,r-tsne)
9472 ("r-vgam" ,r-vgam)))
9473 (home-page "http://www.satijalab.org/seurat")
9474 (synopsis "Seurat is an R toolkit for single cell genomics")
9475 (description
9476 "This package is an R package designed for QC, analysis, and
2441c284
RJPB		 9477exploration of single cell RNA-seq data. It easily enables widely-used
9478analytical techniques, including the identification of highly variable genes,
9479dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9480algorithms; density clustering, hierarchical clustering, k-means, and the
9481discovery of differentially expressed genes and markers.")
f1a2b1cb 9482 (license license:gpl3)))
2441c284 9483
d4b83651
RW		 9484(define-public r-aroma-light
9485 (package
9486 (name "r-aroma-light")
531e8090 9487 (version "3.8.0")
d4b83651
RW		 9488 (source
9489 (origin
9490 (method url-fetch)
9491 (uri (bioconductor-uri "aroma.light" version))
9492 (sha256
9493 (base32
531e8090 9494 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
d4b83651
RW		 9495 (properties `((upstream-name . "aroma.light")))
9496 (build-system r-build-system)
9497 (propagated-inputs
9498 `(("r-matrixstats" ,r-matrixstats)
9499 ("r-r-methodss3" ,r-r-methodss3)
9500 ("r-r-oo" ,r-r-oo)
9501 ("r-r-utils" ,r-r-utils)))
9502 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9503 (synopsis "Methods for normalization and visualization of microarray data")
9504 (description
9505 "This package provides methods for microarray analysis that take basic
9506data types such as matrices and lists of vectors. These methods can be used
9507standalone, be utilized in other packages, or be wrapped up in higher-level
9508classes.")
9509 (license license:gpl2+)))
9510
7b465327
RW		 9511(define-public r-deseq
9512 (package
9513 (name "r-deseq")
8140f680 9514 (version "1.30.0")
7b465327
RW		 9515 (source
9516 (origin
9517 (method url-fetch)
9518 (uri (bioconductor-uri "DESeq" version))
9519 (sha256
9520 (base32
8140f680 9521 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
7b465327
RW		 9522 (properties `((upstream-name . "DESeq")))
9523 (build-system r-build-system)
9524 (propagated-inputs
9525 `(("r-biobase" ,r-biobase)
9526 ("r-biocgenerics" ,r-biocgenerics)
9527 ("r-genefilter" ,r-genefilter)
9528 ("r-geneplotter" ,r-geneplotter)
9529 ("r-lattice" ,r-lattice)
9530 ("r-locfit" ,r-locfit)
9531 ("r-mass" ,r-mass)
9532 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9533 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9534 (synopsis "Differential gene expression analysis")
9535 (description
9536 "This package provides tools for estimating variance-mean dependence in
9537count data from high-throughput genetic sequencing assays and for testing for
9538differential expression based on a model using the negative binomial
9539distribution.")
9540 (license license:gpl3+)))
9541
296b3c63
RW		 9542(define-public r-edaseq
9543 (package
9544 (name "r-edaseq")
00961279 9545 (version "2.12.0")
296b3c63
RW		 9546 (source
9547 (origin
9548 (method url-fetch)
9549 (uri (bioconductor-uri "EDASeq" version))
9550 (sha256
9551 (base32
00961279 9552 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
296b3c63
RW		 9553 (properties `((upstream-name . "EDASeq")))
9554 (build-system r-build-system)
9555 (propagated-inputs
9556 `(("r-annotationdbi" ,r-annotationdbi)
9557 ("r-aroma-light" ,r-aroma-light)
9558 ("r-biobase" ,r-biobase)
9559 ("r-biocgenerics" ,r-biocgenerics)
9560 ("r-biomart" ,r-biomart)
9561 ("r-biostrings" ,r-biostrings)
9562 ("r-deseq" ,r-deseq)
9563 ("r-genomicfeatures" ,r-genomicfeatures)
9564 ("r-genomicranges" ,r-genomicranges)
9565 ("r-iranges" ,r-iranges)
9566 ("r-rsamtools" ,r-rsamtools)
9567 ("r-shortread" ,r-shortread)))
9568 (home-page "https://github.com/drisso/EDASeq")
9569 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9570 (description
9571 "This package provides support for numerical and graphical summaries of
9572RNA-Seq genomic read data. Provided within-lane normalization procedures to
9573adjust for GC-content effect (or other gene-level effects) on read counts:
9574loess robust local regression, global-scaling, and full-quantile
9575normalization. Between-lane normalization procedures to adjust for
9576distributional differences between lanes (e.g., sequencing depth):
9577global-scaling and full-quantile normalization.")
9578 (license license:artistic2.0)))
9579
5f96f30f
RW		 9580(define-public r-interactivedisplaybase
9581 (package
9582 (name "r-interactivedisplaybase")
1567c8d9 9583 (version "1.16.0")
5f96f30f
RW		 9584 (source
9585 (origin
9586 (method url-fetch)
9587 (uri (bioconductor-uri "interactiveDisplayBase" version))
9588 (sha256
9589 (base32
1567c8d9 9590 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
5f96f30f
RW		 9591 (properties
9592 `((upstream-name . "interactiveDisplayBase")))
9593 (build-system r-build-system)
9594 (propagated-inputs
9595 `(("r-biocgenerics" ,r-biocgenerics)
9596 ("r-shiny" ,r-shiny)))
5713bbf1 9597 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
5f96f30f
RW		 9598 (synopsis "Base package for web displays of Bioconductor objects")
9599 (description
9600 "This package contains the basic methods needed to generate interactive
9601Shiny-based display methods for Bioconductor objects.")
9602 (license license:artistic2.0)))
9603
4a007ffa
RW		 9604(define-public r-annotationhub
9605 (package
9606 (name "r-annotationhub")
9b8d0201 9607 (version "2.10.1")
4a007ffa
RW		 9608 (source
9609 (origin
9610 (method url-fetch)
9611 (uri (bioconductor-uri "AnnotationHub" version))
9612 (sha256
9613 (base32
9b8d0201 9614 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
4a007ffa
RW		 9615 (properties `((upstream-name . "AnnotationHub")))
9616 (build-system r-build-system)
9617 (propagated-inputs
9618 `(("r-annotationdbi" ,r-annotationdbi)
9619 ("r-biocgenerics" ,r-biocgenerics)
9620 ("r-biocinstaller" ,r-biocinstaller)
14b3c719 9621 ("r-curl" ,r-curl)
4a007ffa
RW		 9622 ("r-httr" ,r-httr)
9623 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9624 ("r-rsqlite" ,r-rsqlite)
9625 ("r-s4vectors" ,r-s4vectors)
9626 ("r-yaml" ,r-yaml)))
5713bbf1 9627 (home-page "https://bioconductor.org/packages/AnnotationHub")
4a007ffa
RW		 9628 (synopsis "Client to access AnnotationHub resources")
9629 (description
9630 "This package provides a client for the Bioconductor AnnotationHub web
9631resource. The AnnotationHub web resource provides a central location where
9632genomic files (e.g. VCF, bed, wig) and other resources from standard
9633locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9634metadata about each resource, e.g., a textual description, tags, and date of
9635modification. The client creates and manages a local cache of files retrieved
9636by the user, helping with quick and reproducible access.")
9637 (license license:artistic2.0)))
9638
d4a1e918
RW		 9639(define-public r-fastseg
9640 (package
9641 (name "r-fastseg")
87fa5afa 9642 (version "1.24.0")
d4a1e918
RW		 9643 (source
9644 (origin
9645 (method url-fetch)
9646 (uri (bioconductor-uri "fastseg" version))
9647 (sha256
9648 (base32
87fa5afa 9649 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
d4a1e918
RW		 9650 (build-system r-build-system)
9651 (propagated-inputs
9652 `(("r-biobase" ,r-biobase)
9653 ("r-biocgenerics" ,r-biocgenerics)
9654 ("r-genomicranges" ,r-genomicranges)
9655 ("r-iranges" ,r-iranges)
9656 ("r-s4vectors" ,r-s4vectors)))
9657 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9658 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9659 (description
9660 "Fastseg implements a very fast and efficient segmentation algorithm.
9661It can segment data from DNA microarrays and data from next generation
9662sequencing for example to detect copy number segments. Further it can segment
9663data from RNA microarrays like tiling arrays to identify transcripts. Most
9664generally, it can segment data given as a matrix or as a vector. Various data
9665formats can be used as input to fastseg like expression set objects for
9666microarrays or GRanges for sequencing data.")
9667 (license license:lgpl2.0+)))
9668
3121814e
RW		 9669(define-public r-keggrest
9670 (package
9671 (name "r-keggrest")
9672 (version "1.18.0")
9673 (source
9674 (origin
9675 (method url-fetch)
9676 (uri (bioconductor-uri "KEGGREST" version))
9677 (sha256
9678 (base32
9679 "1i3i88lj57wvpgjf75a23msgfsjv8pr2b4j1faga276p4fsblkhj"))))
9680 (properties `((upstream-name . "KEGGREST")))
9681 (build-system r-build-system)
9682 (propagated-inputs
9683 `(("r-biostrings" ,r-biostrings)
9684 ("r-httr" ,r-httr)
9685 ("r-png" ,r-png)))
9686 (home-page "https://bioconductor.org/packages/KEGGREST")
9687 (synopsis "Client-side REST access to KEGG")
9688 (description
9689 "This package provides a package that provides a client interface to the
9690@dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9691 (license license:artistic2.0)))
9692
e160aa1f
RW		 9693(define-public r-gage
9694 (package
9695 (name "r-gage")
9696 (version "2.28.0")
9697 (source
9698 (origin
9699 (method url-fetch)
9700 (uri (bioconductor-uri "gage" version))
9701 (sha256
9702 (base32
9703 "1r14p88q3y736pkqm4pdimf1izy1xy3xgivmj3cr4dv65kjny1zk"))))
9704 (build-system r-build-system)
9705 (propagated-inputs
9706 `(("r-annotationdbi" ,r-annotationdbi)
9707 ("r-graph" ,r-graph)
9708 ("r-keggrest" ,r-keggrest)))
9709 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9710 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9711 (description
9712 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9713analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9714data attributes including sample sizes, experimental designs, assay platforms,
9715and other types of heterogeneity. The gage package provides functions for
9716basic GAGE analysis, result processing and presentation. In addition, it
9717provides demo microarray data and commonly used gene set data based on KEGG
9718pathways and GO terms. These funtions and data are also useful for gene set
9719analysis using other methods.")
9720 (license license:gpl2+)))
9721
902fb15d
RW		 9722(define-public r-genomicfiles
9723 (package
9724 (name "r-genomicfiles")
9725 (version "1.14.0")
9726 (source
9727 (origin
9728 (method url-fetch)
9729 (uri (bioconductor-uri "GenomicFiles" version))
9730 (sha256
9731 (base32
9732 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9733 (properties `((upstream-name . "GenomicFiles")))
9734 (build-system r-build-system)
9735 (propagated-inputs
9736 `(("r-biocgenerics" ,r-biocgenerics)
9737 ("r-biocparallel" ,r-biocparallel)
9738 ("r-genomeinfodb" ,r-genomeinfodb)
9739 ("r-genomicalignments" ,r-genomicalignments)
9740 ("r-genomicranges" ,r-genomicranges)
9741 ("r-iranges" ,r-iranges)
9742 ("r-rsamtools" ,r-rsamtools)
9743 ("r-rtracklayer" ,r-rtracklayer)
9744 ("r-s4vectors" ,r-s4vectors)
9745 ("r-summarizedexperiment" ,r-summarizedexperiment)
9746 ("r-variantannotation" ,r-variantannotation)))
9747 (home-page "https://bioconductor.org/packages/GenomicFiles")
9748 (synopsis "Distributed computing by file or by range")
9749 (description
9750 "This package provides infrastructure for parallel computations
9751distributed by file or by range. User defined mapper and reducer functions
9752provide added flexibility for data combination and manipulation.")
9753 (license license:artistic2.0)))
9754
3af149f5
RW		 9755(define-public r-complexheatmap
9756 (package
9757 (name "r-complexheatmap")
9758 (version "1.17.1")
9759 (source
9760 (origin
9761 (method url-fetch)
9762 (uri (bioconductor-uri "ComplexHeatmap" version))
9763 (sha256
9764 (base32
9765 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9766 (properties
9767 `((upstream-name . "ComplexHeatmap")))
9768 (build-system r-build-system)
9769 (propagated-inputs
9770 `(("r-circlize" ,r-circlize)
9771 ("r-colorspace" ,r-colorspace)
9772 ("r-getoptlong" ,r-getoptlong)
9773 ("r-globaloptions" ,r-globaloptions)
9774 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9775 (home-page
9776 "https://github.com/jokergoo/ComplexHeatmap")
9777 (synopsis "Making Complex Heatmaps")
9778 (description
9779 "Complex heatmaps are efficient to visualize associations between
9780different sources of data sets and reveal potential structures. This package
9781provides a highly flexible way to arrange multiple heatmaps and supports
9782self-defined annotation graphics.")
9783 (license license:gpl2+)))
9784
04e2a2e9
RW		 9785(define-public r-dirichletmultinomial
9786 (package
9787 (name "r-dirichletmultinomial")
9788 (version "1.20.0")
9789 (source
9790 (origin
9791 (method url-fetch)
9792 (uri (bioconductor-uri "DirichletMultinomial" version))
9793 (sha256
9794 (base32
9795 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9796 (properties
9797 `((upstream-name . "DirichletMultinomial")))
9798 (build-system r-build-system)
9799 (inputs
9800 `(("gsl" ,gsl)))
9801 (propagated-inputs
9802 `(("r-biocgenerics" ,r-biocgenerics)
9803 ("r-iranges" ,r-iranges)
9804 ("r-s4vectors" ,r-s4vectors)))
9805 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9806 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9807 (description
9808 "Dirichlet-multinomial mixture models can be used to describe variability
9809in microbial metagenomic data. This package is an interface to code
9810originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
98111-15.")
9812 (license license:lgpl3)))
9813
aa30ab5a
RW		 9814(define-public r-ensembldb
9815 (package
9816 (name "r-ensembldb")
9817 (version "2.2.0")
9818 (source
9819 (origin
9820 (method url-fetch)
9821 (uri (bioconductor-uri "ensembldb" version))
9822 (sha256
9823 (base32
9824 "1w0lca3ws5j770bmls91cn93lznvv2pc8s42nybdzz3vdxjvb4m1"))))
9825 (build-system r-build-system)
9826 (propagated-inputs
9827 `(("r-annotationdbi" ,r-annotationdbi)
9828 ("r-annotationfilter" ,r-annotationfilter)
9829 ("r-annotationhub" ,r-annotationhub)
9830 ("r-biobase" ,r-biobase)
9831 ("r-biocgenerics" ,r-biocgenerics)
9832 ("r-biostrings" ,r-biostrings)
9833 ("r-curl" ,r-curl)
9834 ("r-dbi" ,r-dbi)
9835 ("r-genomeinfodb" ,r-genomeinfodb)
9836 ("r-genomicfeatures" ,r-genomicfeatures)
9837 ("r-genomicranges" ,r-genomicranges)
9838 ("r-iranges" ,r-iranges)
9839 ("r-protgenerics" ,r-protgenerics)
9840 ("r-rsamtools" ,r-rsamtools)
9841 ("r-rsqlite" ,r-rsqlite)
9842 ("r-rtracklayer" ,r-rtracklayer)
9843 ("r-s4vectors" ,r-s4vectors)))
9844 (home-page "https://github.com/jotsetung/ensembldb")
9845 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9846 (description
9847 "The package provides functions to create and use transcript-centric
9848annotation databases/packages. The annotation for the databases are directly
9849fetched from Ensembl using their Perl API. The functionality and data is
9850similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9851but, in addition to retrieve all gene/transcript models and annotations from
9852the database, the @code{ensembldb} package also provides a filter framework
9853allowing to retrieve annotations for specific entries like genes encoded on a
9854chromosome region or transcript models of lincRNA genes.")
9855 ;; No version specified
9856 (license license:lgpl3+)))
9857
2f6f61fd
RW		 9858(define-public r-organismdbi
9859 (package
9860 (name "r-organismdbi")
9861 (version "1.20.0")
9862 (source
9863 (origin
9864 (method url-fetch)
9865 (uri (bioconductor-uri "OrganismDbi" version))
9866 (sha256
9867 (base32
9868 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
9869 (properties `((upstream-name . "OrganismDbi")))
9870 (build-system r-build-system)
9871 (propagated-inputs
9872 `(("r-annotationdbi" ,r-annotationdbi)
9873 ("r-biobase" ,r-biobase)
9874 ("r-biocgenerics" ,r-biocgenerics)
9875 ("r-biocinstaller" ,r-biocinstaller)
9876 ("r-dbi" ,r-dbi)
9877 ("r-genomicfeatures" ,r-genomicfeatures)
9878 ("r-genomicranges" ,r-genomicranges)
9879 ("r-graph" ,r-graph)
9880 ("r-iranges" ,r-iranges)
9881 ("r-rbgl" ,r-rbgl)
9882 ("r-s4vectors" ,r-s4vectors)))
9883 (home-page "https://bioconductor.org/packages/OrganismDbi")
9884 (synopsis "Software to enable the smooth interfacing of database packages")
9885 (description "The package enables a simple unified interface to several
9886annotation packages each of which has its own schema by taking advantage of
9887the fact that each of these packages implements a select methods.")
9888 (license license:artistic2.0)))
9889
7af1f403
RW		 9890(define-public r-biovizbase
9891 (package
9892 (name "r-biovizbase")
9893 (version "1.26.0")
9894 (source
9895 (origin
9896 (method url-fetch)
9897 (uri (bioconductor-uri "biovizBase" version))
9898 (sha256
9899 (base32
9900 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
9901 (properties `((upstream-name . "biovizBase")))
9902 (build-system r-build-system)
9903 (propagated-inputs
9904 `(("r-annotationdbi" ,r-annotationdbi)
9905 ("r-annotationfilter" ,r-annotationfilter)
9906 ("r-biocgenerics" ,r-biocgenerics)
9907 ("r-biostrings" ,r-biostrings)
9908 ("r-dichromat" ,r-dichromat)
9909 ("r-ensembldb" ,r-ensembldb)
9910 ("r-genomeinfodb" ,r-genomeinfodb)
9911 ("r-genomicalignments" ,r-genomicalignments)
9912 ("r-genomicfeatures" ,r-genomicfeatures)
9913 ("r-genomicranges" ,r-genomicranges)
9914 ("r-hmisc" ,r-hmisc)
9915 ("r-iranges" ,r-iranges)
9916 ("r-rcolorbrewer" ,r-rcolorbrewer)
9917 ("r-rsamtools" ,r-rsamtools)
9918 ("r-s4vectors" ,r-s4vectors)
9919 ("r-scales" ,r-scales)
9920 ("r-summarizedexperiment" ,r-summarizedexperiment)
9921 ("r-variantannotation" ,r-variantannotation)))
9922 (home-page "https://bioconductor.org/packages/biovizBase")
9923 (synopsis "Basic graphic utilities for visualization of genomic data")
9924 (description
9925 "The biovizBase package is designed to provide a set of utilities, color
9926schemes and conventions for genomic data. It serves as the base for various
9927high-level packages for biological data visualization. This saves development
9928effort and encourages consistency.")
9929 (license license:artistic2.0)))
9930
60faf945
RW		 9931(define-public r-ggbio
9932 (package
9933 (name "r-ggbio")
9934 (version "1.26.0")
9935 (source
9936 (origin
9937 (method url-fetch)
9938 (uri (bioconductor-uri "ggbio" version))
9939 (sha256
9940 (base32
9941 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
9942 (build-system r-build-system)
9943 (propagated-inputs
9944 `(("r-annotationdbi" ,r-annotationdbi)
9945 ("r-annotationfilter" ,r-annotationfilter)
9946 ("r-biobase" ,r-biobase)
9947 ("r-biocgenerics" ,r-biocgenerics)
9948 ("r-biostrings" ,r-biostrings)
9949 ("r-biovizbase" ,r-biovizbase)
9950 ("r-bsgenome" ,r-bsgenome)
9951 ("r-ensembldb" ,r-ensembldb)
9952 ("r-genomeinfodb" ,r-genomeinfodb)
9953 ("r-genomicalignments" ,r-genomicalignments)
9954 ("r-genomicfeatures" ,r-genomicfeatures)
9955 ("r-genomicranges" ,r-genomicranges)
9956 ("r-ggally" ,r-ggally)
9957 ("r-ggplot2" ,r-ggplot2)
9958 ("r-gridextra" ,r-gridextra)
9959 ("r-gtable" ,r-gtable)
9960 ("r-hmisc" ,r-hmisc)
9961 ("r-iranges" ,r-iranges)
9962 ("r-organismdbi" ,r-organismdbi)
9963 ("r-reshape2" ,r-reshape2)
9964 ("r-rsamtools" ,r-rsamtools)
9965 ("r-rtracklayer" ,r-rtracklayer)
9966 ("r-s4vectors" ,r-s4vectors)
9967 ("r-scales" ,r-scales)
9968 ("r-summarizedexperiment" ,r-summarizedexperiment)
9969 ("r-variantannotation" ,r-variantannotation)))
9970 (home-page "http://www.tengfei.name/ggbio/")
9971 (synopsis "Visualization tools for genomic data")
9972 (description
9973 "The ggbio package extends and specializes the grammar of graphics for
9974biological data. The graphics are designed to answer common scientific
9975questions, in particular those often asked of high throughput genomics data.
9976All core Bioconductor data structures are supported, where appropriate. The
9977package supports detailed views of particular genomic regions, as well as
9978genome-wide overviews. Supported overviews include ideograms and grand linear
9979views. High-level plots include sequence fragment length, edge-linked
9980interval to data view, mismatch pileup, and several splicing summaries.")
9981 (license license:artistic2.0)))
9982
96a392a0
RW		 9983(define-public r-gprofiler
9984 (package
9985 (name "r-gprofiler")
9986 (version "0.6.1")
9987 (source
9988 (origin
9989 (method url-fetch)
9990 (uri (cran-uri "gProfileR" version))
9991 (sha256
9992 (base32
9993 "1qix15d0wa9nspdclcawml94mng4qmr2jciv7d24py315wfsvv8p"))))
9994 (properties `((upstream-name . "gProfileR")))
9995 (build-system r-build-system)
9996 (propagated-inputs
9997 `(("r-plyr" ,r-plyr)
9998 ("r-rcurl" ,r-rcurl)))
9999 (home-page "http://cran.r-project.org/web/packages/gProfileR/")
10000 (synopsis "Interface to the g:Profiler toolkit")
10001 (description
10002 "This package provides tools for functional enrichment analysis,
10003gene identifier conversion and mapping homologous genes across related
10004organisms via the @code{g:Profiler} toolkit.")
10005 (license license:gpl2+)))
10006
e2b92799
RW		 10007(define-public r-gqtlbase
10008 (package
10009 (name "r-gqtlbase")
10010 (version "1.10.0")
10011 (source
10012 (origin
10013 (method url-fetch)
10014 (uri (bioconductor-uri "gQTLBase" version))
10015 (sha256
10016 (base32
10017 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10018 (properties `((upstream-name . "gQTLBase")))
10019 (build-system r-build-system)
10020 (propagated-inputs
10021 `(("r-batchjobs" ,r-batchjobs)
10022 ("r-bbmisc" ,r-bbmisc)
10023 ("r-biocgenerics" ,r-biocgenerics)
10024 ("r-bit" ,r-bit)
10025 ("r-doparallel" ,r-doparallel)
10026 ("r-ff" ,r-ff)
10027 ("r-ffbase" ,r-ffbase)
10028 ("r-foreach" ,r-foreach)
10029 ("r-genomicfiles" ,r-genomicfiles)
10030 ("r-genomicranges" ,r-genomicranges)
10031 ("r-rtracklayer" ,r-rtracklayer)
10032 ("r-s4vectors" ,r-s4vectors)
10033 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10034 (home-page "https://bioconductor.org/packages/gQTLBase")
10035 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10036 (description
10037 "The purpose of this package is to simplify the storage and interrogation
10038of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10039and more.")
10040 (license license:artistic2.0)))
10041
dd5fc8b7
RW		 10042(define-public r-snpstats
10043 (package
10044 (name "r-snpstats")
10045 (version "1.28.0")
10046 (source
10047 (origin
10048 (method url-fetch)
10049 (uri (bioconductor-uri "snpStats" version))
10050 (sha256
10051 (base32
10052 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10053 (properties `((upstream-name . "snpStats")))
10054 (build-system r-build-system)
10055 (inputs `(("zlib" ,zlib)))
10056 (propagated-inputs
10057 `(("r-biocgenerics" ,r-biocgenerics)
10058 ("r-matrix" ,r-matrix)
10059 ("r-survival" ,r-survival)
10060 ("r-zlibbioc" ,r-zlibbioc)))
10061 (home-page "https://bioconductor.org/packages/snpStats")
10062 (synopsis "Methods for SNP association studies")
10063 (description
10064 "This package provides classes and statistical methods for large
10065@dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10066the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10067 (license license:gpl3)))
10068
421c68e3
RW		 10069(define-public r-homo-sapiens
10070 (package
10071 (name "r-homo-sapiens")
10072 (version "1.3.1")
10073 (source (origin
10074 (method url-fetch)
10075 ;; We cannot use bioconductor-uri here because this tarball is
10076 ;; located under "data/annotation/" instead of "bioc/".
10077 (uri (string-append "http://www.bioconductor.org/packages/"
10078 "release/data/annotation/src/contrib/"
10079 "Homo.sapiens_"
10080 version ".tar.gz"))
10081 (sha256
10082 (base32
10083 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10084 (properties
10085 `((upstream-name . "Homo.sapiens")))
10086 (build-system r-build-system)
10087 (propagated-inputs
10088 `(("r-genomicfeatures" ,r-genomicfeatures)
10089 ("r-go-db" ,r-go-db)
10090 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10091 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10092 ("r-organismdbi" ,r-organismdbi)
10093 ("r-annotationdbi" ,r-annotationdbi)))
10094 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10095 (synopsis "Annotation package for the Homo.sapiens object")
10096 (description
10097 "This package contains the Homo.sapiens object to access data from
10098several related annotation packages.")
10099 (license license:artistic2.0)))
10100
15f98b0d
RW		 10101(define-public r-erma
10102 (package
10103 (name "r-erma")
10104 (version "0.10.0")
10105 (source
10106 (origin
10107 (method url-fetch)
10108 (uri (bioconductor-uri "erma" version))
10109 (sha256
10110 (base32
10111 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10112 (build-system r-build-system)
10113 (propagated-inputs
10114 `(("r-annotationdbi" ,r-annotationdbi)
10115 ("r-biobase" ,r-biobase)
10116 ("r-biocgenerics" ,r-biocgenerics)
10117 ("r-foreach" ,r-foreach)
10118 ("r-genomicfiles" ,r-genomicfiles)
10119 ("r-genomicranges" ,r-genomicranges)
10120 ("r-ggplot2" ,r-ggplot2)
10121 ("r-homo-sapiens" ,r-homo-sapiens)
10122 ("r-rtracklayer" ,r-rtracklayer)
10123 ("r-s4vectors" ,r-s4vectors)
10124 ("r-shiny" ,r-shiny)
10125 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10126 (home-page "https://bioconductor.org/packages/erma")
10127 (synopsis "Epigenomic road map adventures")
10128 (description
10129 "The epigenomics road map describes locations of epigenetic marks in DNA
10130from a variety of cell types. Of interest are locations of histone
10131modifications, sites of DNA methylation, and regions of accessible chromatin.
10132This package presents a selection of elements of the road map including
10133metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10134by Ernst and Kellis.")
10135 (license license:artistic2.0)))
10136
66c39102
RW		 10137(define-public r-ldblock
10138 (package
10139 (name "r-ldblock")
10140 (version "1.8.0")
10141 (source
10142 (origin
10143 (method url-fetch)
10144 (uri (bioconductor-uri "ldblock" version))
10145 (sha256
10146 (base32
10147 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10148 (build-system r-build-system)
10149 (propagated-inputs
10150 `(("r-erma" ,r-erma)
10151 ("r-genomeinfodb" ,r-genomeinfodb)
10152 ("r-genomicfiles" ,r-genomicfiles)
10153 ("r-go-db" ,r-go-db)
10154 ("r-homo-sapiens" ,r-homo-sapiens)
10155 ("r-matrix" ,r-matrix)
10156 ("r-rsamtools" ,r-rsamtools)
10157 ("r-snpstats" ,r-snpstats)
10158 ("r-variantannotation" ,r-variantannotation)))
10159 (home-page "https://bioconductor.org/packages/ldblock")
10160 (synopsis "Data structures for linkage disequilibrium measures in populations")
10161 (description
10162 "This package defines data structures for @dfn{linkage
10163disequilibrium} (LD) measures in populations. Its purpose is to simplify
10164handling of existing population-level data for the purpose of flexibly
10165defining LD blocks.")
10166 (license license:artistic2.0)))
10167
794ff347
RW		 10168(define-public r-gqtlstats
10169 (package
10170 (name "r-gqtlstats")
10171 (version "1.10.0")
10172 (source
10173 (origin
10174 (method url-fetch)
10175 (uri (bioconductor-uri "gQTLstats" version))
10176 (sha256
10177 (base32
10178 "1cbdqawxzgna8rrgj3siph5sw4d2pb57qc0gn6ibfkhyk45f8gdv"))))
10179 (properties `((upstream-name . "gQTLstats")))
10180 (build-system r-build-system)
10181 (propagated-inputs
10182 `(("r-annotationdbi" ,r-annotationdbi)
10183 ("r-batchjobs" ,r-batchjobs)
10184 ("r-bbmisc" ,r-bbmisc)
10185 ("r-beeswarm" ,r-beeswarm)
10186 ("r-biobase" ,r-biobase)
10187 ("r-biocgenerics" ,r-biocgenerics)
10188 ("r-doparallel" ,r-doparallel)
10189 ("r-dplyr" ,r-dplyr)
10190 ("r-erma" ,r-erma)
10191 ("r-ffbase" ,r-ffbase)
10192 ("r-foreach" ,r-foreach)
10193 ("r-genomeinfodb" ,r-genomeinfodb)
10194 ("r-genomicfeatures" ,r-genomicfeatures)
10195 ("r-genomicfiles" ,r-genomicfiles)
10196 ("r-genomicranges" ,r-genomicranges)
10197 ("r-ggbeeswarm" ,r-ggbeeswarm)
10198 ("r-ggplot2" ,r-ggplot2)
10199 ("r-gqtlbase" ,r-gqtlbase)
10200 ("r-hardyweinberg" ,r-hardyweinberg)
10201 ("r-iranges" ,r-iranges)
10202 ("r-ldblock" ,r-ldblock)
10203 ("r-limma" ,r-limma)
10204 ("r-mgcv" ,r-mgcv)
10205 ("r-plotly" ,r-plotly)
10206 ("r-reshape2" ,r-reshape2)
10207 ("r-s4vectors" ,r-s4vectors)
10208 ("r-shiny" ,r-shiny)
10209 ("r-snpstats" ,r-snpstats)
10210 ("r-summarizedexperiment" ,r-summarizedexperiment)
10211 ("r-variantannotation" ,r-variantannotation)))
10212 (home-page "https://bioconductor.org/packages/gQTLstats")
10213 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10214 (description
10215 "This package provides tools for the computationally efficient analysis
10216of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10217The software in this package aims to support refinements and functional
10218interpretation of members of a collection of association statistics on a
10219family of feature/genome hypotheses.")
10220 (license license:artistic2.0)))
10221
42720006
RW		 10222(define-public r-gviz
10223 (package
10224 (name "r-gviz")
10225 (version "1.22.0")
10226 (source
10227 (origin
10228 (method url-fetch)
10229 (uri (bioconductor-uri "Gviz" version))
10230 (sha256
10231 (base32
10232 "1lrw65a8426wpxw975wjcaiacpp6fqa00nif1yxigyankbfs23c8"))))
10233 (properties `((upstream-name . "Gviz")))
10234 (build-system r-build-system)
10235 (propagated-inputs
10236 `(("r-annotationdbi" ,r-annotationdbi)
10237 ("r-biobase" ,r-biobase)
10238 ("r-biocgenerics" ,r-biocgenerics)
10239 ("r-biomart" ,r-biomart)
10240 ("r-biostrings" ,r-biostrings)
10241 ("r-biovizbase" ,r-biovizbase)
10242 ("r-bsgenome" ,r-bsgenome)
10243 ("r-digest" ,r-digest)
10244 ("r-genomeinfodb" ,r-genomeinfodb)
10245 ("r-genomicalignments" ,r-genomicalignments)
10246 ("r-genomicfeatures" ,r-genomicfeatures)
10247 ("r-genomicranges" ,r-genomicranges)
10248 ("r-iranges" ,r-iranges)
10249 ("r-lattice" ,r-lattice)
10250 ("r-latticeextra" ,r-latticeextra)
10251 ("r-matrixstats" ,r-matrixstats)
10252 ("r-rcolorbrewer" ,r-rcolorbrewer)
10253 ("r-rsamtools" ,r-rsamtools)
10254 ("r-rtracklayer" ,r-rtracklayer)
10255 ("r-s4vectors" ,r-s4vectors)
10256 ("r-xvector" ,r-xvector)))
10257 (home-page "https://bioconductor.org/packages/Gviz")
10258 (synopsis "Plotting data and annotation information along genomic coordinates")
10259 (description
10260 "Genomic data analyses requires integrated visualization of known genomic
10261information and new experimental data. Gviz uses the biomaRt and the
10262rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10263and translates this to e.g. gene/transcript structures in viewports of the
10264grid graphics package. This results in genomic information plotted together
10265with your data.")
10266 (license license:artistic2.0)))
10267
2e4ce60e
RW		 10268(define-public r-gwascat
10269 (package
10270 (name "r-gwascat")
10271 (version "2.10.0")
10272 (source
10273 (origin
10274 (method url-fetch)
10275 (uri (bioconductor-uri "gwascat" version))
10276 (sha256
10277 (base32
10278 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10279 (build-system r-build-system)
10280 (propagated-inputs
10281 `(("r-annotationdbi" ,r-annotationdbi)
10282 ("r-annotationhub" ,r-annotationhub)
10283 ("r-biocgenerics" ,r-biocgenerics)
10284 ("r-biostrings" ,r-biostrings)
10285 ("r-genomeinfodb" ,r-genomeinfodb)
10286 ("r-genomicfeatures" ,r-genomicfeatures)
10287 ("r-genomicranges" ,r-genomicranges)
10288 ("r-ggbio" ,r-ggbio)
10289 ("r-ggplot2" ,r-ggplot2)
10290 ("r-gqtlstats" ,r-gqtlstats)
10291 ("r-graph" ,r-graph)
10292 ("r-gviz" ,r-gviz)
10293 ("r-homo-sapiens" ,r-homo-sapiens)
10294 ("r-iranges" ,r-iranges)
10295 ("r-rsamtools" ,r-rsamtools)
10296 ("r-rtracklayer" ,r-rtracklayer)
10297 ("r-s4vectors" ,r-s4vectors)
10298 ("r-snpstats" ,r-snpstats)
10299 ("r-summarizedexperiment" ,r-summarizedexperiment)
10300 ("r-variantannotation" ,r-variantannotation)))
10301 (home-page "https://bioconductor.org/packages/gwascat")
10302 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10303 (description
10304 "This package provides tools for representing and modeling data in the
10305EMBL-EBI GWAS catalog.")
10306 (license license:artistic2.0)))
10307
fbf54406
RW		 10308(define-public r-sushi
10309 (package
10310 (name "r-sushi")
10311 (version "1.16.0")
10312 (source (origin
10313 (method url-fetch)
10314 (uri (bioconductor-uri "Sushi" version))
10315 (sha256
10316 (base32
10317 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10318 (properties `((upstream-name . "Sushi")))
10319 (build-system r-build-system)
10320 (propagated-inputs
10321 `(("r-biomart" ,r-biomart)
10322 ("r-zoo" ,r-zoo)))
10323 (home-page "https://bioconductor.org/packages/Sushi")
10324 (synopsis "Tools for visualizing genomics data")
10325 (description
10326 "This package provides flexible, quantitative, and integrative genomic
10327visualizations for publication-quality multi-panel figures.")
10328 (license license:gpl2+)))
10329
30eb4e37
RW		 10330(define-public r-fithic
10331 (package
10332 (name "r-fithic")
10333 (version "1.4.0")
10334 (source (origin
10335 (method url-fetch)
10336 (uri (bioconductor-uri "FitHiC" version))
10337 (sha256
10338 (base32
10339 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10340 (properties `((upstream-name . "FitHiC")))
10341 (build-system r-build-system)
10342 (propagated-inputs
10343 `(("r-data-table" ,r-data-table)
10344 ("r-fdrtool" ,r-fdrtool)
10345 ("r-rcpp" ,r-rcpp)))
10346 (home-page "https://bioconductor.org/packages/FitHiC")
10347 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10348 (description
10349 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10350intra-chromosomal contact maps produced by genome-wide genome architecture
10351assays such as Hi-C.")
10352 (license license:gpl2+)))
10353
c49102ec
RW		 10354(define-public r-hitc
10355 (package
10356 (name "r-hitc")
10357 (version "1.22.0")
10358 (source (origin
10359 (method url-fetch)
10360 (uri (bioconductor-uri "HiTC" version))
10361 (sha256
10362 (base32
10363 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10364 (properties `((upstream-name . "HiTC")))
10365 (build-system r-build-system)
10366 (propagated-inputs
10367 `(("r-biostrings" ,r-biostrings)
10368 ("r-genomeinfodb" ,r-genomeinfodb)
10369 ("r-genomicranges" ,r-genomicranges)
10370 ("r-iranges" ,r-iranges)
10371 ("r-matrix" ,r-matrix)
10372 ("r-rcolorbrewer" ,r-rcolorbrewer)
10373 ("r-rtracklayer" ,r-rtracklayer)))
10374 (home-page "https://bioconductor.org/packages/HiTC")
10375 (synopsis "High throughput chromosome conformation capture analysis")
10376 (description
10377 "The HiTC package was developed to explore high-throughput \"C\" data
10378such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10379quality controls, normalization, visualization, and further analysis are also
10380provided.")
10381 (license license:artistic2.0)))
10382
212f6120
RW		 10383(define-public r-qvalue
10384 (package
10385 (name "r-qvalue")
98791c25 10386 (version "2.10.0")
212f6120
RW		 10387 (source
10388 (origin
10389 (method url-fetch)
10390 (uri (bioconductor-uri "qvalue" version))
10391 (sha256
10392 (base32
98791c25 10393 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
212f6120
RW		 10394 (build-system r-build-system)
10395 (propagated-inputs
10396 `(("r-ggplot2" ,r-ggplot2)
10397 ("r-reshape2" ,r-reshape2)))
10398 (home-page "http://github.com/jdstorey/qvalue")
10399 (synopsis "Q-value estimation for false discovery rate control")
10400 (description
10401 "This package takes a list of p-values resulting from the simultaneous
10402testing of many hypotheses and estimates their q-values and local @dfn{false
10403discovery rate} (FDR) values. The q-value of a test measures the proportion
10404of false positives incurred when that particular test is called significant.
10405The local FDR measures the posterior probability the null hypothesis is true
10406given the test's p-value. Various plots are automatically generated, allowing
10407one to make sensible significance cut-offs. The software can be applied to
10408problems in genomics, brain imaging, astrophysics, and data mining.")
10409 ;; Any version of the LGPL.
10410 (license license:lgpl3+)))
10411
5ded35d8
RW		 10412(define htslib-for-sambamba
10413 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10414 (package
10415 (inherit htslib)
10416 (name "htslib-for-sambamba")
10417 (version (string-append "1.3.1-1." (string-take commit 9)))
10418 (source
10419 (origin
10420 (method git-fetch)
10421 (uri (git-reference
10422 (url "https://github.com/lomereiter/htslib.git")
10423 (commit commit)))
10424 (file-name (string-append "htslib-" version "-checkout"))
10425 (sha256
10426 (base32
10427 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10428 (arguments
10429 (substitute-keyword-arguments (package-arguments htslib)
10430 ((#:phases phases)
10431 `(modify-phases ,phases
d10092b8 10432 (add-after 'unpack 'bootstrap
5ded35d8
RW		 10433 (lambda _
10434 (zero? (system* "autoreconf" "-vif"))))))))
10435 (native-inputs
10436 `(("autoconf" ,autoconf)
10437 ("automake" ,automake)
10438 ,@(package-native-inputs htslib))))))
10439
10440(define-public sambamba
10441 (package
10442 (name "sambamba")
10443 (version "0.6.5")
10444 (source
10445 (origin
10446 (method url-fetch)
10447 (uri (string-append "https://github.com/lomereiter/sambamba/"
10448 "archive/v" version ".tar.gz"))
10449 (file-name (string-append name "-" version ".tar.gz"))
10450 (sha256
10451 (base32
10452 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10453 (build-system gnu-build-system)
10454 (arguments
10455 `(#:tests? #f ; there is no test target
10456 #:make-flags
10457 '("D_COMPILER=ldc2"
10458 ;; Override "--compiler" flag only.
10459 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10460 "sambamba-ldmd2-64")
10461 #:phases
10462 (modify-phases %standard-phases
10463 (delete 'configure)
10464 (add-after 'unpack 'place-biod
10465 (lambda* (#:key inputs #:allow-other-keys)
10466 (copy-recursively (assoc-ref inputs "biod") "BioD")
10467 #t))
10468 (add-after 'unpack 'unbundle-prerequisites
10469 (lambda _
10470 (substitute* "Makefile"
10471 ((" htslib-static lz4-static") ""))
10472 #t))
10473 (replace 'install
10474 (lambda* (#:key outputs #:allow-other-keys)
10475 (let* ((out (assoc-ref outputs "out"))
10476 (bin (string-append out "/bin")))
10477 (mkdir-p bin)
10478 (install-file "build/sambamba" bin)
10479 #t))))))
10480 (native-inputs
10481 `(("ldc" ,ldc)
10482 ("rdmd" ,rdmd)
10483 ("biod"
10484 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10485 (origin
10486 (method git-fetch)
10487 (uri (git-reference
10488 (url "https://github.com/biod/BioD.git")
10489 (commit commit)))
10490 (file-name (string-append "biod-"
10491 (string-take commit 9)
10492 "-checkout"))
10493 (sha256
10494 (base32
10495 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
10496 (inputs
10497 `(("lz4" ,lz4)
10498 ("htslib" ,htslib-for-sambamba)))
10499 (home-page "http://lomereiter.github.io/sambamba")
10500 (synopsis "Tools for working with SAM/BAM data")
10501 (description "Sambamba is a high performance modern robust and
10502fast tool (and library), written in the D programming language, for
10503working with SAM and BAM files. Current parallelised functionality is
10504an important subset of samtools functionality, including view, index,
10505sort, markdup, and depth.")
10506 (license license:gpl2+)))
b8fffd3a
RW		 10507
10508(define-public ritornello
10509 (package
10510 (name "ritornello")
10511 (version "1.0.0")
10512 (source (origin
10513 (method url-fetch)
10514 (uri (string-append "https://github.com/KlugerLab/"
10515 "Ritornello/archive/v"
10516 version ".tar.gz"))
10517 (file-name (string-append name "-" version ".tar.gz"))
10518 (sha256
10519 (base32
10520 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
10521 (build-system gnu-build-system)
10522 (arguments
10523 `(#:tests? #f ; there are no tests
10524 #:phases
10525 (modify-phases %standard-phases
10526 (add-after 'unpack 'patch-samtools-references
10527 (lambda* (#:key inputs #:allow-other-keys)
10528 (substitute* '("src/SamStream.h"
10529 "src/BufferedGenomeReader.h")
10530 (("<sam.h>") "<samtools/sam.h>"))
10531 #t))
10532 (delete 'configure)
10533 (replace 'install
10534 (lambda* (#:key inputs outputs #:allow-other-keys)
10535 (let* ((out (assoc-ref outputs "out"))
10536 (bin (string-append out "/bin/")))
10537 (mkdir-p bin)
10538 (install-file "bin/Ritornello" bin)
10539 #t))))))
10540 (inputs
10541 `(("samtools" ,samtools-0.1)
10542 ("fftw" ,fftw)
10543 ("boost" ,boost)
10544 ("zlib" ,zlib)))
10545 (home-page "https://github.com/KlugerLab/Ritornello")
10546 (synopsis "Control-free peak caller for ChIP-seq data")
10547 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10548signal processing that can accurately call binding events without the need to
10549do a pair total DNA input or IgG control sample. It has been tested for use
10550with narrow binding events such as transcription factor ChIP-seq.")
10551 (license license:gpl3+)))
44f6c889
RW		 10552
10553(define-public trim-galore
10554 (package
10555 (name "trim-galore")
10556 (version "0.4.2")
10557 (source
10558 (origin
10559 (method url-fetch)
10560 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
10561 "projects/trim_galore/trim_galore_v"
10562 version ".zip"))
10563 (sha256
10564 (base32
10565 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
10566 (build-system gnu-build-system)
10567 (arguments
10568 `(#:tests? #f ; no tests
10569 #:phases
10570 (modify-phases %standard-phases
10571 ;; The archive contains plain files.
10572 (replace 'unpack
10573 (lambda* (#:key source #:allow-other-keys)
10574 (zero? (system* "unzip" source))))
10575 (delete 'configure)
10576 (delete 'build)
10577 (add-after 'unpack 'hardcode-tool-references
10578 (lambda* (#:key inputs #:allow-other-keys)
10579 (substitute* "trim_galore"
10580 (("\\$path_to_cutadapt = 'cutadapt'")
10581 (string-append "$path_to_cutadapt = '"
10582 (assoc-ref inputs "cutadapt")
10583 "/bin/cutadapt'"))
10584 (("\\| gzip")
10585 (string-append "| "
10586 (assoc-ref inputs "gzip")
10587 "/bin/gzip"))
10588 (("\"gunzip")
10589 (string-append "\""
10590 (assoc-ref inputs "gzip")
10591 "/bin/gunzip")))
10592 #t))
10593 (replace 'install
10594 (lambda* (#:key outputs #:allow-other-keys)
10595 (let ((bin (string-append (assoc-ref outputs "out")
10596 "/bin")))
10597 (mkdir-p bin)
10598 (install-file "trim_galore" bin)
10599 #t))))))
10600 (inputs
10601 `(("gzip" ,gzip)
10602 ("perl" ,perl)
10603 ("cutadapt" ,cutadapt)))
10604 (native-inputs
10605 `(("unzip" ,unzip)))
10606 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10607 (synopsis "Wrapper around Cutadapt and FastQC")
10608 (description "Trim Galore! is a wrapper script to automate quality and
10609adapter trimming as well as quality control, with some added functionality to
10610remove biased methylation positions for RRBS sequence files.")
10611 (license license:gpl3+)))
3420c905
RW		 10612
10613(define-public gess
10614 (package
10615 (name "gess")
10616 (version "1.0")
10617 (source (origin
10618 (method url-fetch)
10619 (uri (string-append "http://compbio.uthscsa.edu/"
10620 "GESS_Web/files/"
10621 "gess-" version ".src.tar.gz"))
10622 (sha256
10623 (base32
10624 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10625 (build-system gnu-build-system)
10626 (arguments
10627 `(#:tests? #f ; no tests
10628 #:phases
10629 (modify-phases %standard-phases
10630 (delete 'configure)
10631 (delete 'build)
10632 (replace 'install
10633 (lambda* (#:key inputs outputs #:allow-other-keys)
10634 (let* ((python (assoc-ref inputs "python"))
10635 (out (assoc-ref outputs "out"))
10636 (bin (string-append out "/bin/"))
10637 (target (string-append
10638 out "/lib/python2.7/site-packages/gess/")))
10639 (mkdir-p target)
10640 (copy-recursively "." target)
10641 ;; Make GESS.py executable
10642 (chmod (string-append target "GESS.py") #o555)
10643 ;; Add Python shebang to the top and make Matplotlib
10644 ;; usable.
10645 (substitute* (string-append target "GESS.py")
10646 (("\"\"\"Description:" line)
10647 (string-append "#!" (which "python") "
10648import matplotlib
10649matplotlib.use('Agg')
10650" line)))
10651 ;; Make sure GESS has all modules in its path
10652 (wrap-program (string-append target "GESS.py")
10653 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
10654 (mkdir-p bin)
10655 (symlink (string-append target "GESS.py")
10656 (string-append bin "GESS.py"))
10657 #t))))))
10658 (inputs
10659 `(("python" ,python-2)
10660 ("python2-pysam" ,python2-pysam)
10661 ("python2-scipy" ,python2-scipy)
10662 ("python2-numpy" ,python2-numpy)
10663 ("python2-networkx" ,python2-networkx)
10664 ("python2-biopython" ,python2-biopython)))
10665 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
10666 (synopsis "Detect exon-skipping events from raw RNA-seq data")
10667 (description
10668 "GESS is an implementation of a novel computational method to detect de
10669novo exon-skipping events directly from raw RNA-seq data without the prior
10670knowledge of gene annotation information. GESS stands for the graph-based
10671exon-skipping scanner detection scheme.")
10672 (license license:bsd-3)))
282b0151
RW		 10673
10674(define-public phylip
10675 (package
10676 (name "phylip")
10677 (version "3.696")
10678 (source
10679 (origin
10680 (method url-fetch)
10681 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
10682 "download/phylip-" version ".tar.gz"))
10683 (sha256
10684 (base32
10685 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
10686 (build-system gnu-build-system)
10687 (arguments
10688 `(#:tests? #f ; no check target
10689 #:make-flags (list "-f" "Makefile.unx" "install")
10690 #:parallel-build? #f ; not supported
10691 #:phases
10692 (modify-phases %standard-phases
10693 (add-after 'unpack 'enter-dir
10694 (lambda _ (chdir "src") #t))
10695 (delete 'configure)
10696 (replace 'install
10697 (lambda* (#:key inputs outputs #:allow-other-keys)
10698 (let ((target (string-append (assoc-ref outputs "out")
10699 "/bin")))
10700 (mkdir-p target)
10701 (for-each (lambda (file)
10702 (install-file file target))
10703 (find-files "../exe" ".*")))
10704 #t)))))
10705 (home-page "http://evolution.genetics.washington.edu/phylip/")
10706 (synopsis "Tools for inferring phylogenies")
10707 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
10708programs for inferring phylogenies (evolutionary trees).")
10709 (license license:bsd-2)))
aa163424
RW		 10710
10711(define-public imp
10712 (package
10713 (name "imp")
10714 (version "2.6.2")
10715 (source
10716 (origin
10717 (method url-fetch)
10718 (uri (string-append "https://integrativemodeling.org/"
10719 version "/download/imp-" version ".tar.gz"))
10720 (sha256
10721 (base32
10722 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
10723 (build-system cmake-build-system)
10724 (arguments
10725 `(;; FIXME: Some tests fail because they produce warnings, others fail
10726 ;; because the PYTHONPATH does not include the modeller's directory.
10727 #:tests? #f
10728 ;; Do not place libraries in an architecture-specific directory.
10729 #:configure-flags
10730 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
10731 (inputs
10732 `(("boost" ,boost)
10733 ("gsl" ,gsl)
10734 ("swig" ,swig)
10735 ("hdf5" ,hdf5)
10736 ("fftw" ,fftw)
10737 ("python" ,python-2)))
10738 (propagated-inputs
10739 `(("python2-numpy" ,python2-numpy)
10740 ("python2-scipy" ,python2-scipy)
10741 ("python2-pandas" ,python2-pandas)
10742 ("python2-scikit-learn" ,python2-scikit-learn)
10743 ("python2-networkx" ,python2-networkx)))
10744 (home-page "https://integrativemodeling.org")
10745 (synopsis "Integrative modeling platform")
10746 (description "IMP's broad goal is to contribute to a comprehensive
10747structural characterization of biomolecules ranging in size and complexity
10748from small peptides to large macromolecular assemblies, by integrating data
10749from diverse biochemical and biophysical experiments. IMP provides a C++ and
10750Python toolbox for solving complex modeling problems, and a number of
10751applications for tackling some common problems in a user-friendly way.")
10752 ;; IMP is largely available under the GNU Lesser GPL; see the file
10753 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
10754 ;; available under the GNU GPL (see the file COPYING.GPL).
10755 (license (list license:lgpl2.1+
10756 license:gpl3+))))
8befd094
RW		 10757
10758(define-public tadbit
10759 (package
10760 (name "tadbit")
10761 (version "0.2")
10762 (source (origin
10763 (method url-fetch)
10764 (uri (string-append "https://github.com/3DGenomes/TADbit/"
10765 "archive/v" version ".tar.gz"))
10766 (file-name (string-append name "-" version ".tar.gz"))
10767 (sha256
10768 (base32
10769 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
10770 (build-system python-build-system)
10771 (arguments
10772 `(;; Tests are included and must be run after installation, but
10773 ;; they are incomplete and thus cannot be run.
10774 #:tests? #f
10775 #:python ,python-2
10776 #:phases
10777 (modify-phases %standard-phases
10778 (add-after 'unpack 'fix-problems-with-setup.py
10779 (lambda* (#:key outputs #:allow-other-keys)
10780 ;; setup.py opens these files for writing
10781 (chmod "_pytadbit/_version.py" #o664)
10782 (chmod "README.rst" #o664)
10783
10784 ;; Don't attempt to install the bash completions to
10785 ;; the home directory.
10786 (rename-file "extras/.bash_completion"
10787 "extras/tadbit")
10788 (substitute* "setup.py"
10789 (("\\(path.expanduser\\('~'\\)")
10790 (string-append "(\""
10791 (assoc-ref outputs "out")
10792 "/etc/bash_completion.d\""))
10793 (("extras/\\.bash_completion")
10794 "extras/tadbit"))
10795 #t)))))
10796 (inputs
10797 ;; TODO: add Chimera for visualization
10798 `(("imp" ,imp)
10799 ("mcl" ,mcl)
10800 ("python2-scipy" ,python2-scipy)
10801 ("python2-numpy" ,python2-numpy)
10802 ("python2-matplotlib" ,python2-matplotlib)
10803 ("python2-pysam" ,python2-pysam)))
10804 (home-page "http://3dgenomes.github.io/TADbit/")
10805 (synopsis "Analyze, model, and explore 3C-based data")
10806 (description
10807 "TADbit is a complete Python library to deal with all steps to analyze,
10808model, and explore 3C-based data. With TADbit the user can map FASTQ files to
10809obtain raw interaction binned matrices (Hi-C like matrices), normalize and
a147fadd 10810correct interaction matrices, identify and compare the so-called
8befd094
RW		 10811@dfn{Topologically Associating Domains} (TADs), build 3D models from the
10812interaction matrices, and finally, extract structural properties from the
10813models. TADbit is complemented by TADkit for visualizing 3D models.")
10814 (license license:gpl3+)))
94820951
RW		 10815
10816(define-public kentutils
10817 (package
10818 (name "kentutils")
10819 ;; 302.1.0 is out, but the only difference is the inclusion of
10820 ;; pre-built binaries.
10821 (version "302.0.0")
10822 (source
10823 (origin
10824 (method url-fetch)
10825 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
10826 "archive/v" version ".tar.gz"))
10827 (file-name (string-append name "-" version ".tar.gz"))
10828 (sha256
10829 (base32
10830 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
10831 (modules '((guix build utils)
10832 (srfi srfi-26)
10833 (ice-9 ftw)))
10834 (snippet
10835 '(begin
10836 ;; Only the contents of the specified directories are free
10837 ;; for all uses, so we remove the rest. "hg/autoSql" and
10838 ;; "hg/autoXml" are nominally free, but they depend on a
10839 ;; library that is built from the sources in "hg/lib",
10840 ;; which is nonfree.
10841 (let ((free (list "." ".."
10842 "utils" "lib" "inc" "tagStorm"
10843 "parasol" "htslib"))
10844 (directory? (lambda (file)
10845 (eq? 'directory (stat:type (stat file))))))
10846 (for-each (lambda (file)
10847 (and (directory? file)
10848 (delete-file-recursively file)))
10849 (map (cut string-append "src/" <>)
10850 (scandir "src"
10851 (lambda (file)
10852 (not (member file free)))))))
10853 ;; Only make the utils target, not the userApps target,
10854 ;; because that requires libraries we won't build.
10855 (substitute* "Makefile"
10856 ((" userApps") " utils"))
10857 ;; Only build libraries that are free.
10858 (substitute* "src/makefile"
10859 (("DIRS =.*") "DIRS =\n")
10860 (("cd jkOwnLib.*") "")
10861 ((" hgLib") "")
10862 (("cd hg.*") ""))
10863 (substitute* "src/utils/makefile"
10864 ;; These tools depend on "jkhgap.a", which is part of the
10865 ;; nonfree "src/hg/lib" directory.
10866 (("raSqlQuery") "")
10867 (("pslLiftSubrangeBlat") "")
10868
10869 ;; Do not build UCSC tools, which may require nonfree
10870 ;; components.
10871 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
10872 #t))))
10873 (build-system gnu-build-system)
10874 (arguments
10875 `( ;; There is no global test target and the test target for
10876 ;; individual tools depends on input files that are not
10877 ;; included.
10878 #:tests? #f
10879 #:phases
10880 (modify-phases %standard-phases
10881 (add-after 'unpack 'fix-paths
10882 (lambda _
10883 (substitute* "Makefile"
10884 (("/bin/echo") (which "echo")))
10885 #t))
10886 (add-after 'unpack 'prepare-samtabix
10887 (lambda* (#:key inputs #:allow-other-keys)
10888 (copy-recursively (assoc-ref inputs "samtabix")
10889 "samtabix")
10890 #t))
10891 (delete 'configure)
10892 (replace 'install
10893 (lambda* (#:key outputs #:allow-other-keys)
10894 (let ((bin (string-append (assoc-ref outputs "out")
10895 "/bin")))
10896 (copy-recursively "bin" bin))
10897 #t)))))
10898 (native-inputs
10899 `(("samtabix"
10900 ,(origin
10901 (method git-fetch)
10902 (uri (git-reference
10903 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
10904 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
10905 (sha256
10906 (base32
10907 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
10908 (inputs
10909 `(("zlib" ,zlib)
10910 ("tcsh" ,tcsh)
10911 ("perl" ,perl)
10912 ("libpng" ,libpng)
10913 ("mysql" ,mysql)
10914 ("openssl" ,openssl)))
10915 (home-page "http://genome.cse.ucsc.edu/index.html")
10916 (synopsis "Assorted bioinformatics utilities")
10917 (description "This package provides the kentUtils, a selection of
10918bioinformatics utilities used in combination with the UCSC genome
10919browser.")
10920 ;; Only a subset of the sources are released under a non-copyleft
10921 ;; free software license. All other sources are removed in a
10922 ;; snippet. See this bug report for an explanation of how the
10923 ;; license statements apply:
10924 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
10925 (license (license:non-copyleft
10926 "http://genome.ucsc.edu/license/"
10927 "The contents of this package are free for all uses."))))
7ceb0a83
RW		 10928
10929(define-public f-seq
10930 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
10931 (revision "1"))
10932 (package
10933 (name "f-seq")
c6643f2d 10934 (version (string-append "1.1-" revision "." (string-take commit 7)))
7ceb0a83
RW		 10935 (source (origin
10936 (method git-fetch)
10937 (uri (git-reference
10938 (url "https://github.com/aboyle/F-seq.git")
10939 (commit commit)))
10940 (file-name (string-append name "-" version))
10941 (sha256
10942 (base32
10943 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
10944 (modules '((guix build utils)))
10945 ;; Remove bundled Java library archives.
10946 (snippet
10947 '(begin
10948 (for-each delete-file (find-files "lib" ".*"))
10949 #t))))
10950 (build-system ant-build-system)
10951 (arguments
10952 `(#:tests? #f ; no tests included
10953 #:phases
10954 (modify-phases %standard-phases
10955 (replace 'install
c0770fee 10956 (lambda* (#:key inputs outputs #:allow-other-keys)
7ceb0a83
RW		 10957 (let* ((target (assoc-ref outputs "out"))
10958 (doc (string-append target "/share/doc/f-seq/")))
10959 (mkdir-p target)
10960 (mkdir-p doc)
10961 (substitute* "bin/linux/fseq"
c0770fee
RW		 10962 (("java") (which "java"))
10963 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
10964 (string-append (assoc-ref inputs "java-commons-cli")
10965 "/share/java/commons-cli.jar"))
10966 (("REALDIR=.*")
10967 (string-append "REALDIR=" target "/bin\n")))
7ceb0a83
RW		 10968 (install-file "README.txt" doc)
10969 (install-file "bin/linux/fseq" (string-append target "/bin"))
10970 (install-file "build~/fseq.jar" (string-append target "/lib"))
10971 (copy-recursively "lib" (string-append target "/lib"))
10972 #t))))))
10973 (inputs
10974 `(("perl" ,perl)
10975 ("java-commons-cli" ,java-commons-cli)))
10976 (home-page "http://fureylab.web.unc.edu/software/fseq/")
10977 (synopsis "Feature density estimator for high-throughput sequence tags")
10978 (description
10979 "F-Seq is a software package that generates a continuous tag sequence
10980density estimation allowing identification of biologically meaningful sites
10981such as transcription factor binding sites (ChIP-seq) or regions of open
10982chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
10983Browser.")
10984 (license license:gpl3+))))
96348048
RW		 10985
10986(define-public bismark
10987 (package
10988 (name "bismark")
10989 (version "0.16.3")
10990 (source
10991 (origin
10992 (method url-fetch)
10993 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
10994 "archive/" version ".tar.gz"))
10995 (file-name (string-append name "-" version ".tar.gz"))
10996 (sha256
10997 (base32
10998 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
10999 (build-system perl-build-system)
11000 (arguments
11001 `(#:tests? #f ; there are no tests
11002 #:phases
11003 (modify-phases %standard-phases
11004 (delete 'configure)
11005 (delete 'build)
11006 (replace 'install
11007 (lambda* (#:key outputs #:allow-other-keys)
11008 (let ((bin (string-append (assoc-ref outputs "out")
11009 "/bin"))
11010 (docdir (string-append (assoc-ref outputs "out")
11011 "/share/doc/bismark"))
11012 (docs '("Bismark_User_Guide.pdf"
11013 "RELEASE_NOTES.txt"))
11014 (scripts '("bismark"
11015 "bismark_genome_preparation"
11016 "bismark_methylation_extractor"
11017 "bismark2bedGraph"
11018 "bismark2report"
11019 "coverage2cytosine"
11020 "deduplicate_bismark"
11021 "bismark_sitrep.tpl"
11022 "bam2nuc"
11023 "bismark2summary")))
11024 (mkdir-p docdir)
11025 (mkdir-p bin)
11026 (for-each (lambda (file) (install-file file bin))
11027 scripts)
11028 (for-each (lambda (file) (install-file file docdir))
11029 docs)
11030 #t))))))
11031 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11032 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11033 (description "Bismark is a program to map bisulfite treated sequencing
11034reads to a genome of interest and perform methylation calls in a single step.
11035The output can be easily imported into a genome viewer, such as SeqMonk, and
11036enables a researcher to analyse the methylation levels of their samples
11037straight away. Its main features are:
11038
11039@itemize
11040@item Bisulfite mapping and methylation calling in one single step
11041@item Supports single-end and paired-end read alignments
11042@item Supports ungapped and gapped alignments
11043@item Alignment seed length, number of mismatches etc are adjustable
11044@item Output discriminates between cytosine methylation in CpG, CHG
11045 and CHH context
11046@end itemize\n")
11047 (license license:gpl3+)))
dc8ddbfb
RW		 11048
11049(define-public paml
11050 (package
11051 (name "paml")
11052 (version "4.9e")
11053 (source (origin
11054 (method url-fetch)
11055 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11056 "paml" version ".tgz"))
11057 (sha256
11058 (base32
11059 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11060 (modules '((guix build utils)))
11061 ;; Remove Windows binaries
11062 (snippet
11063 '(begin
11064 (for-each delete-file (find-files "." "\\.exe$"))
11065 #t))))
11066 (build-system gnu-build-system)
11067 (arguments
11068 `(#:tests? #f ; there are no tests
11069 #:make-flags '("CC=gcc")
11070 #:phases
11071 (modify-phases %standard-phases
11072 (replace 'configure
11073 (lambda _
11074 (substitute* "src/BFdriver.c"
11075 (("/bin/bash") (which "bash")))
11076 (chdir "src")
11077 #t))
11078 (replace 'install
11079 (lambda* (#:key outputs #:allow-other-keys)
11080 (let ((tools '("baseml" "basemlg" "codeml"
11081 "pamp" "evolver" "yn00" "chi2"))
11082 (bin (string-append (assoc-ref outputs "out") "/bin"))
11083 (docdir (string-append (assoc-ref outputs "out")
11084 "/share/doc/paml")))
11085 (mkdir-p bin)
11086 (for-each (lambda (file) (install-file file bin)) tools)
11087 (copy-recursively "../doc" docdir)
11088 #t))))))
11089 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11090 (synopsis "Phylogentic analysis by maximum likelihood")
11091 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11092contains a few programs for model fitting and phylogenetic tree reconstruction
11093using nucleotide or amino-acid sequence data.")
11094 ;; GPLv3 only
11095 (license license:gpl3)))
d112e5a8
RW		 11096
11097(define-public kallisto
11098 (package
11099 (name "kallisto")
11100 (version "0.43.1")
11101 (source (origin
11102 (method url-fetch)
11103 (uri (string-append "https://github.com/pachterlab/"
11104 "kallisto/archive/v" version ".tar.gz"))
11105 (file-name (string-append name "-" version ".tar.gz"))
11106 (sha256
11107 (base32
11108 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11109 (build-system cmake-build-system)
11110 (arguments `(#:tests? #f)) ; no "check" target
11111 (inputs
11112 `(("hdf5" ,hdf5)
11113 ("zlib" ,zlib)))
11114 (home-page "http://pachterlab.github.io/kallisto/")
11115 (synopsis "Near-optimal RNA-Seq quantification")
11116 (description
11117 "Kallisto is a program for quantifying abundances of transcripts from
11118RNA-Seq data, or more generally of target sequences using high-throughput
11119sequencing reads. It is based on the novel idea of pseudoalignment for
11120rapidly determining the compatibility of reads with targets, without the need
11121for alignment. Pseudoalignment of reads preserves the key information needed
11122for quantification, and kallisto is therefore not only fast, but also as
11123accurate as existing quantification tools.")
11124 (license license:bsd-2)))
jackhill's copy of GNU Guix: https://guix.gnu.org/