HCoop / jackhill / guix / guix.git / blame
? search:
summary | shortlog | log | commit | commitdiff | tree
blob | blame (incremental) | history | HEAD
gnu: Add libdivsufsort.
[jackhill/guix/guix.git] / gnu / packages / bioinformatics.scm
CommitLineData
4e10a221 1;;; GNU Guix --- Functional package management for GNU
c3b2ab9d 2;;; Copyright © 2014, 2015, 2016, 2017, 2018 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>
ddf38ece 10;;; Copyright © 2017, 2018 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)
7edee344
RW		 496 (arguments
497 `(#:phases
498 (modify-phases %standard-phases
499 (add-after 'install 'wrap-executables
500 (lambda* (#:key inputs outputs #:allow-other-keys)
501 (let* ((out (assoc-ref outputs "out")))
502 (for-each
503 (lambda (script)
504 (wrap-program (string-append out "/bin/" script)
505 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
506 '("create_annotations_files.bash"
507 "create_metaplots.bash"
508 "Ribotaper_ORF_find.sh"
509 "Ribotaper.sh"))))))))
17dc32a4
RW		 510 (inputs
511 `(("bedtools" ,bedtools-2.18)
512 ("samtools" ,samtools-0.1)
2d7c4ae3 513 ("r-minimal" ,r-minimal)
17dc32a4
RW		 514 ("r-foreach" ,r-foreach)
515 ("r-xnomial" ,r-xnomial)
516 ("r-domc" ,r-domc)
517 ("r-multitaper" ,r-multitaper)
518 ("r-seqinr" ,r-seqinr)))
519 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
520 (synopsis "Define translated ORFs using ribosome profiling data")
521 (description
522 "Ribotaper is a method for defining translated @dfn{open reading
523frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
524provides the Ribotaper pipeline.")
525 (license license:gpl3+)))
526
769fc6bb
RW		 527(define-public ribodiff
528 (package
529 (name "ribodiff")
530 (version "0.2.2")
531 (source
532 (origin
533 (method url-fetch)
534 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
535 "archive/v" version ".tar.gz"))
536 (file-name (string-append name "-" version ".tar.gz"))
537 (sha256
538 (base32
539 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
540 (build-system python-build-system)
541 (arguments
542 `(#:python ,python-2
543 #:phases
544 (modify-phases %standard-phases
545 ;; Generate an installable executable script wrapper.
546 (add-after 'unpack 'patch-setup.py
547 (lambda _
548 (substitute* "setup.py"
549 (("^(.*)packages=.*" line prefix)
550 (string-append line "\n"
551 prefix "scripts=['scripts/TE.py'],\n")))
552 #t)))))
553 (inputs
554 `(("python-numpy" ,python2-numpy)
555 ("python-matplotlib" ,python2-matplotlib)
556 ("python-scipy" ,python2-scipy)
557 ("python-statsmodels" ,python2-statsmodels)))
2bb12f5a
MB		 558 (native-inputs
559 `(("python-mock" ,python2-mock)
560 ("python-nose" ,python2-nose)))
769fc6bb
RW		 561 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
562 (synopsis "Detect translation efficiency changes from ribosome footprints")
563 (description "RiboDiff is a statistical tool that detects the protein
564translational efficiency change from Ribo-Seq (ribosome footprinting) and
565RNA-Seq data. It uses a generalized linear model to detect genes showing
566difference in translational profile taking mRNA abundance into account. It
567facilitates us to decipher the translational regulation that behave
568independently with transcriptional regulation.")
569 (license license:gpl3+)))
570
a0a71439
RJ		 571(define-public bioawk
572 (package
573 (name "bioawk")
574 (version "1.0")
575 (source (origin
576 (method url-fetch)
577 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
578 version ".tar.gz"))
579 (file-name (string-append name "-" version ".tar.gz"))
580 (sha256
581 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
582 (build-system gnu-build-system)
583 (inputs
584 `(("zlib" ,zlib)))
585 (native-inputs
586 `(("bison" ,bison)))
587 (arguments
588 `(#:tests? #f ; There are no tests to run.
589 ;; Bison must generate files, before other targets can build.
590 #:parallel-build? #f
591 #:phases
592 (modify-phases %standard-phases
593 (delete 'configure) ; There is no configure phase.
594 (replace 'install
595 (lambda* (#:key outputs #:allow-other-keys)
596 (let* ((out (assoc-ref outputs "out"))
597 (bin (string-append out "/bin"))
598 (man (string-append out "/share/man/man1")))
599 (mkdir-p man)
600 (copy-file "awk.1" (string-append man "/bioawk.1"))
601 (install-file "bioawk" bin)))))))
602 (home-page "https://github.com/lh3/bioawk")
603 (synopsis "AWK with bioinformatics extensions")
604 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
605support of several common biological data formats, including optionally gzip'ed
606BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
607also adds a few built-in functions and a command line option to use TAB as the
608input/output delimiter. When the new functionality is not used, bioawk is
609intended to behave exactly the same as the original BWK awk.")
610 (license license:x11)))
611
a2fb1492
RW		 612(define-public python2-pybedtools
613 (package
614 (name "python2-pybedtools")
615 (version "0.6.9")
616 (source (origin
617 (method url-fetch)
618 (uri (string-append
619 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
620 version ".tar.gz"))
621 (sha256
622 (base32
623 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
624 (build-system python-build-system)
625 (arguments `(#:python ,python-2)) ; no Python 3 support
626 (inputs
f2516de2 627 `(("python-matplotlib" ,python2-matplotlib)))
a2fb1492
RW		 628 (propagated-inputs
629 `(("bedtools" ,bedtools)
630 ("samtools" ,samtools)))
631 (native-inputs
f2516de2
HG		 632 `(("python-cython" ,python2-cython)
633 ("python-pyyaml" ,python2-pyyaml)
f3b98f4f 634 ("python-nose" ,python2-nose)))
a2fb1492
RW		 635 (home-page "https://pythonhosted.org/pybedtools/")
636 (synopsis "Python wrapper for BEDtools programs")
637 (description
638 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
639which are widely used for genomic interval manipulation or \"genome algebra\".
640pybedtools extends BEDTools by offering feature-level manipulations from with
641Python.")
642 (license license:gpl2+)))
643
9e12eba8
BW		 644(define-public python-biom-format
645 (package
646 (name "python-biom-format")
abc08cba 647 (version "2.1.6")
9e12eba8
BW		 648 (source
649 (origin
650 (method url-fetch)
651 ;; Use GitHub as source because PyPI distribution does not contain
652 ;; test data: https://github.com/biocore/biom-format/issues/693
653 (uri (string-append "https://github.com/biocore/biom-format/archive/"
654 version ".tar.gz"))
655 (file-name (string-append name "-" version ".tar.gz"))
656 (sha256
657 (base32
abc08cba 658 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
9e12eba8 659 (build-system python-build-system)
de96ea28 660 (propagated-inputs
9e12eba8
BW		 661 `(("python-numpy" ,python-numpy)
662 ("python-scipy" ,python-scipy)
663 ("python-future" ,python-future)
664 ("python-click" ,python-click)
abc08cba
BW		 665 ("python-h5py" ,python-h5py)
666 ("python-pandas" ,python-pandas)))
da5ebd10
MB		 667 (native-inputs
668 `(("python-nose" ,python-nose)))
9e12eba8
BW		 669 (home-page "http://www.biom-format.org")
670 (synopsis "Biological Observation Matrix (BIOM) format utilities")
671 (description
672 "The BIOM file format is designed to be a general-use format for
673representing counts of observations e.g. operational taxonomic units, KEGG
674orthology groups or lipid types, in one or more biological samples
675e.g. microbiome samples, genomes, metagenomes.")
676 (license license:bsd-3)
677 (properties `((python2-variant . ,(delay python2-biom-format))))))
678
679(define-public python2-biom-format
680 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
681 (package
682 (inherit base)
683 (arguments
684 `(#:phases
685 (modify-phases %standard-phases
686 ;; Do not require the unmaintained pyqi library.
687 (add-after 'unpack 'remove-pyqi
688 (lambda _
689 (substitute* "setup.py"
690 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
691 #t)))
00e10c6e 692 ,@(package-arguments base))))))
9e12eba8 693
f7283db3
RW		 694(define-public bioperl-minimal
695 (let* ((inputs `(("perl-module-build" ,perl-module-build)
696 ("perl-data-stag" ,perl-data-stag)
697 ("perl-libwww" ,perl-libwww)
698 ("perl-uri" ,perl-uri)))
699 (transitive-inputs
700 (map (compose package-name cadr)
701 (delete-duplicates
702 (concatenate
703 (map (compose package-transitive-target-inputs cadr) inputs))))))
704 (package
705 (name "bioperl-minimal")
c70271ec 706 (version "1.7.0")
f7283db3
RW		 707 (source
708 (origin
709 (method url-fetch)
c70271ec
RW		 710 (uri (string-append "https://github.com/bioperl/bioperl-live/"
711 "archive/release-"
712 (string-map (lambda (c)
713 (if (char=? c #\.)
714 #\- c)) version)
715 ".tar.gz"))
f7283db3
RW		 716 (sha256
717 (base32
c70271ec 718 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
f7283db3
RW		 719 (build-system perl-build-system)
720 (arguments
721 `(#:phases
722 (modify-phases %standard-phases
723 (add-after
724 'install 'wrap-programs
725 (lambda* (#:key outputs #:allow-other-keys)
726 ;; Make sure all executables in "bin" find the required Perl
727 ;; modules at runtime. As the PERL5LIB variable contains also
728 ;; the paths of native inputs, we pick the transitive target
729 ;; inputs from %build-inputs.
730 (let* ((out (assoc-ref outputs "out"))
731 (bin (string-append out "/bin/"))
732 (path (string-join
733 (cons (string-append out "/lib/perl5/site_perl")
734 (map (lambda (name)
735 (assoc-ref %build-inputs name))
736 ',transitive-inputs))
737 ":")))
738 (for-each (lambda (file)
739 (wrap-program file
740 `("PERL5LIB" ":" prefix (,path))))
741 (find-files bin "\\.pl$"))
742 #t))))))
743 (inputs inputs)
744 (native-inputs
745 `(("perl-test-most" ,perl-test-most)))
746 (home-page "http://search.cpan.org/dist/BioPerl")
747 (synopsis "Bioinformatics toolkit")
748 (description
749 "BioPerl is the product of a community effort to produce Perl code which
750is useful in biology. Examples include Sequence objects, Alignment objects
751and database searching objects. These objects not only do what they are
752advertised to do in the documentation, but they also interact - Alignment
753objects are made from the Sequence objects, Sequence objects have access to
754Annotation and SeqFeature objects and databases, Blast objects can be
755converted to Alignment objects, and so on. This means that the objects
756provide a coordinated and extensible framework to do computational biology.")
2f3108ad 757 (license license:perl-license))))
f7283db3 758
85c37e29
RW		 759(define-public python-biopython
760 (package
761 (name "python-biopython")
af6ce610 762 (version "1.70")
85c37e29
RW		 763 (source (origin
764 (method url-fetch)
e815c094
BW		 765 ;; use PyPi rather than biopython.org to ease updating
766 (uri (pypi-uri "biopython" version))
85c37e29
RW		 767 (sha256
768 (base32
af6ce610 769 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
85c37e29 770 (build-system python-build-system)
4ce60305
BW		 771 (arguments
772 `(#:phases
773 (modify-phases %standard-phases
774 (add-before 'check 'set-home
775 ;; Some tests require a home directory to be set.
776 (lambda _ (setenv "HOME" "/tmp") #t)))))
f22efa01 777 (propagated-inputs
85c37e29 778 `(("python-numpy" ,python-numpy)))
85c37e29
RW		 779 (home-page "http://biopython.org/")
780 (synopsis "Tools for biological computation in Python")
781 (description
782 "Biopython is a set of tools for biological computation including parsers
783for bioinformatics files into Python data structures; interfaces to common
784bioinformatics programs; a standard sequence class and tools for performing
785common operations on them; code to perform data classification; code for
786dealing with alignments; code making it easy to split up parallelizable tasks
787into separate processes; and more.")
5c31f4aa 788 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
85c37e29
RW		 789
790(define-public python2-biopython
5c31f4aa 791 (package-with-python2 python-biopython))
85c37e29 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")
68565184 1442 (version "0.13.0")
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
68565184 1452 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
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")
ddf38ece 3216 (version "1.6")
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
ddf38ece 3224 "1jsca3hg4rbr6iqq6imkj4lsvgl8g9768bcmny3hlff2w25vx24m"))))
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
8057dee1
TGR		 3245data. It also provides the @command{bgzip}, @command{htsfile}, and
3246@command{tabix} utilities.")
e7c09730
RW		 3247 ;; Files under cram/ are released under the modified BSD license;
3248 ;; the rest is released under the Expat license
3249 (license (list license:expat license:bsd-3))))
3250
bca2c576
BW		 3251;; This package should be removed once no packages rely upon it.
3252(define htslib-1.3
3253 (package
3254 (inherit htslib)
3255 (version "1.3.1")
3256 (source (origin
3257 (method url-fetch)
3258 (uri (string-append
3259 "https://github.com/samtools/htslib/releases/download/"
3260 version "/htslib-" version ".tar.bz2"))
3261 (sha256
3262 (base32
3263 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3264
c4325f62
RW		 3265(define-public idr
3266 (package
3267 (name "idr")
aa33cc29 3268 (version "2.0.3")
c4325f62
RW		 3269 (source (origin
3270 (method url-fetch)
3271 (uri (string-append
3272 "https://github.com/nboley/idr/archive/"
3273 version ".tar.gz"))
3274 (file-name (string-append name "-" version ".tar.gz"))
3275 (sha256
3276 (base32
aa33cc29
RW		 3277 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3278 ;; Delete generated C code.
3279 (snippet
3280 '(begin (delete-file "idr/inv_cdf.c") #t))))
c4325f62 3281 (build-system python-build-system)
aa33cc29
RW		 3282 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3283 ;; are no longer part of this package. It also asserts False, which
3284 ;; causes the tests to always fail.
3285 (arguments `(#:tests? #f))
b7a820fc 3286 (propagated-inputs
c4325f62 3287 `(("python-scipy" ,python-scipy)
b7a820fc 3288 ("python-sympy" ,python-sympy)
c4325f62
RW		 3289 ("python-numpy" ,python-numpy)
3290 ("python-matplotlib" ,python-matplotlib)))
3291 (native-inputs
f3b98f4f 3292 `(("python-cython" ,python-cython)))
c4325f62
RW		 3293 (home-page "https://github.com/nboley/idr")
3294 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3295 (description
3296 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3297to measure the reproducibility of findings identified from replicate
3298experiments and provide highly stable thresholds based on reproducibility.")
40590caf 3299 (license license:gpl2+)))
c4325f62 3300
43c565d2
RW		 3301(define-public jellyfish
3302 (package
3303 (name "jellyfish")
117d8cc4 3304 (version "2.2.7")
43c565d2
RW		 3305 (source (origin
3306 (method url-fetch)
3307 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3308 "releases/download/v" version
3309 "/jellyfish-" version ".tar.gz"))
3310 (sha256
3311 (base32
117d8cc4 3312 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
43c565d2
RW		 3313 (build-system gnu-build-system)
3314 (outputs '("out" ;for library
3315 "ruby" ;for Ruby bindings
3316 "python")) ;for Python bindings
3317 (arguments
3318 `(#:configure-flags
3319 (list (string-append "--enable-ruby-binding="
3320 (assoc-ref %outputs "ruby"))
3321 (string-append "--enable-python-binding="
3322 (assoc-ref %outputs "python")))
3323 #:phases
3324 (modify-phases %standard-phases
3325 (add-before 'check 'set-SHELL-variable
3326 (lambda _
3327 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3328 ;; to run tests.
3329 (setenv "SHELL" (which "bash"))
3330 #t)))))
3331 (native-inputs
3332 `(("bc" ,bc)
3333 ("time" ,time)
3334 ("ruby" ,ruby)
117d8cc4
RW		 3335 ("python" ,python-2)
3336 ("pkg-config" ,pkg-config)))
3337 (inputs
3338 `(("htslib" ,htslib)))
43c565d2
RW		 3339 (synopsis "Tool for fast counting of k-mers in DNA")
3340 (description
3341 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3342DNA. A k-mer is a substring of length k, and counting the occurrences of all
3343such substrings is a central step in many analyses of DNA sequence. Jellyfish
3344is a command-line program that reads FASTA and multi-FASTA files containing
3345DNA sequences. It outputs its k-mer counts in a binary format, which can be
3346translated into a human-readable text format using the @code{jellyfish dump}
3347command, or queried for specific k-mers with @code{jellyfish query}.")
3348 (home-page "http://www.genome.umd.edu/jellyfish.html")
6e8faf77
EF		 3349 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3350 (supported-systems '("x86_64-linux"))
43c565d2
RW		 3351 ;; The combined work is published under the GPLv3 or later. Individual
3352 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3353 (license (list license:gpl3+ license:expat))))
3354
94ff3157
BW		 3355(define-public khmer
3356 (package
3357 (name "khmer")
3358 (version "2.0")
3359 (source
3360 (origin
3361 (method url-fetch)
3362 (uri (pypi-uri "khmer" version))
3363 (sha256
3364 (base32
3365 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3366 (patches (search-patches "khmer-use-libraries.patch"))))
3367 (build-system python-build-system)
3368 (arguments
3369 `(#:phases
3370 (modify-phases %standard-phases
3371 (add-after 'unpack 'set-paths
3372 (lambda* (#:key inputs outputs #:allow-other-keys)
3373 ;; Delete bundled libraries.
3374 (delete-file-recursively "third-party/zlib")
3375 (delete-file-recursively "third-party/bzip2")
3376 ;; Replace bundled seqan.
3377 (let* ((seqan-all "third-party/seqan")
3378 (seqan-include (string-append
3379 seqan-all "/core/include")))
3380 (delete-file-recursively seqan-all)
3381 (copy-recursively (string-append (assoc-ref inputs "seqan")
3382 "/include/seqan")
3383 (string-append seqan-include "/seqan")))
3384 ;; We do not replace the bundled MurmurHash as the canonical
3385 ;; repository for this code 'SMHasher' is unsuitable for
3386 ;; providing a library. See
3387 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3388 #t))
3389 (add-after 'unpack 'set-cc
3390 (lambda _
3391 (setenv "CC" "gcc")
3392 #t))
3393 ;; It is simpler to test after installation.
3394 (delete 'check)
3395 (add-after 'install 'post-install-check
3396 (lambda* (#:key inputs outputs #:allow-other-keys)
3397 (let ((out (assoc-ref outputs "out")))
3398 (setenv "PATH"
3399 (string-append
3400 (getenv "PATH")
3401 ":"
3402 (assoc-ref outputs "out")
3403 "/bin"))
3404 (setenv "PYTHONPATH"
3405 (string-append
3406 (getenv "PYTHONPATH")
3407 ":"
3408 out
3409 "/lib/python"
3410 (string-take (string-take-right
3411 (assoc-ref inputs "python") 5) 3)
3412 "/site-packages"))
3413 (with-directory-excursion "build"
3414 (zero? (system* "nosetests" "khmer" "--attr"
3415 "!known_failing")))))))))
3416 (native-inputs
3417 `(("seqan" ,seqan)
3418 ("python-nose" ,python-nose)))
3419 (inputs
3420 `(("zlib" ,zlib)
3421 ("bzip2" ,bzip2)
3422 ("python-screed" ,python-screed)
cf1d5814
BW		 3423 ("python-bz2file" ,python-bz2file)
3424 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3425 ;; until the next version of khmer (likely 2.1) is released.
3426 ("gcc" ,gcc-4.9)))
94ff3157
BW		 3427 (home-page "https://khmer.readthedocs.org/")
3428 (synopsis "K-mer counting, filtering and graph traversal library")
3429 (description "The khmer software is a set of command-line tools for
3430working with DNA shotgun sequencing data from genomes, transcriptomes,
3431metagenomes and single cells. Khmer can make de novo assemblies faster, and
3432sometimes better. Khmer can also identify and fix problems with shotgun
3433data.")
8157af2e
EF		 3434 ;; When building on i686, armhf and mips64el, we get the following error:
3435 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3436 (supported-systems '("x86_64-linux"))
94ff3157
BW		 3437 (license license:bsd-3)))
3438
b9a601d9
RJ		 3439(define-public kaiju
3440 (package
3441 (name "kaiju")
3442 (version "1.5.0")
3443 (source (origin
3444 (method url-fetch)
3445 (uri (string-append
3446 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3447 version ".tar.gz"))
3448 (file-name (string-append name "-" version ".tar.gz"))
3449 (sha256
3450 (base32
3451 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3452 (build-system gnu-build-system)
3453 (arguments
3454 `(#:tests? #f ; There are no tests.
3455 #:phases
3456 (modify-phases %standard-phases
3457 (delete 'configure)
3458 (add-before 'build 'move-to-src-dir
3459 (lambda _ (chdir "src") #t))
3460 (replace 'install
3461 (lambda* (#:key inputs outputs #:allow-other-keys)
3462 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3463 (mkdir-p bin)
3464 (chdir "..")
3465 (copy-recursively "bin" bin)
3466 (copy-recursively "util" bin))
3467 #t)))))
3468 (inputs
3469 `(("perl" ,perl)))
3470 (home-page "http://kaiju.binf.ku.dk/")
3471 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3472 (description "Kaiju is a program for sensitive taxonomic classification
3473of high-throughput sequencing reads from metagenomic whole genome sequencing
3474experiments.")
3475 (license license:gpl3+)))
3476
d57e6d0f
RW		 3477(define-public macs
3478 (package
3479 (name "macs")
0d0bcaa0 3480 (version "2.1.0.20151222")
d57e6d0f
RW		 3481 (source (origin
3482 (method url-fetch)
43ec07f1 3483 (uri (pypi-uri "MACS2" version))
d57e6d0f
RW		 3484 (sha256
3485 (base32
0d0bcaa0 3486 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
d57e6d0f
RW		 3487 (build-system python-build-system)
3488 (arguments
3489 `(#:python ,python-2 ; only compatible with Python 2.7
3490 #:tests? #f)) ; no test target
3491 (inputs
3492 `(("python-numpy" ,python2-numpy)))
7bf837fd 3493 (home-page "https://github.com/taoliu/MACS/")
d57e6d0f
RW		 3494 (synopsis "Model based analysis for ChIP-Seq data")
3495 (description
3496 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3497identifying transcript factor binding sites named Model-based Analysis of
3498ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3499the significance of enriched ChIP regions and it improves the spatial
3500resolution of binding sites through combining the information of both
3501sequencing tag position and orientation.")
3502 (license license:bsd-3)))
3503
41ddebdd
BW		 3504(define-public mafft
3505 (package
3506 (name "mafft")
3146f22d 3507 (version "7.313")
41ddebdd
BW		 3508 (source (origin
3509 (method url-fetch)
3510 (uri (string-append
3146f22d 3511 "https://mafft.cbrc.jp/alignment/software/mafft-" version
41ddebdd
BW		 3512 "-without-extensions-src.tgz"))
3513 (file-name (string-append name "-" version ".tgz"))
3514 (sha256
3515 (base32
3146f22d 3516 "0r83qmg2if8mi6jyx3xdf8ar2gcxl7r9nmj98jr7lxym97v61a2k"))))
41ddebdd
BW		 3517 (build-system gnu-build-system)
3518 (arguments
3519 `(#:tests? #f ; no automated tests, though there are tests in the read me
3520 #:make-flags (let ((out (assoc-ref %outputs "out")))
3521 (list (string-append "PREFIX=" out)
3522 (string-append "BINDIR="
3523 (string-append out "/bin"))))
3524 #:phases
3525 (modify-phases %standard-phases
3526 (add-after 'unpack 'enter-dir
101e8f71 3527 (lambda _ (chdir "core") #t))
41ddebdd 3528 (add-after 'enter-dir 'patch-makefile
101e8f71
BW		 3529 (lambda _
3530 ;; on advice from the MAFFT authors, there is no need to
3531 ;; distribute mafft-profile, mafft-distance, or
3532 ;; mafft-homologs.rb as they are too "specialised".
3533 (substitute* "Makefile"
3534 ;; remove mafft-homologs.rb from SCRIPTS
3535 (("^SCRIPTS = mafft mafft-homologs.rb")
3536 "SCRIPTS = mafft")
3537 ;; remove mafft-homologs from MANPAGES
3538 (("^MANPAGES = mafft.1 mafft-homologs.1")
3539 "MANPAGES = mafft.1")
3540 ;; remove mafft-distance from PROGS
3541 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3542 "PROGS = dvtditr dndfast7 dndblast sextet5")
3543 ;; remove mafft-profile from PROGS
3544 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3545 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3546 (("^rm -f mafft-profile mafft-profile.exe") "#")
3547 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3548 ;; do not install MAN pages in libexec folder
3549 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
41ddebdd 3550\\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
101e8f71 3551 #t))
02f35bb5
BW		 3552 (add-after 'enter-dir 'patch-paths
3553 (lambda* (#:key inputs #:allow-other-keys)
3554 (substitute* '("pairash.c"
3555 "mafft.tmpl")
3556 (("perl") (which "perl"))
3557 (("([\"`| ])awk" _ prefix)
3558 (string-append prefix (which "awk")))
3559 (("grep") (which "grep")))
3560 #t))
101e8f71
BW		 3561 (delete 'configure)
3562 (add-after 'install 'wrap-programs
3563 (lambda* (#:key outputs #:allow-other-keys)
3564 (let* ((out (assoc-ref outputs "out"))
3565 (bin (string-append out "/bin"))
3566 (path (string-append
3567 (assoc-ref %build-inputs "coreutils") "/bin:")))
3568 (for-each (lambda (file)
3569 (wrap-program file
3570 `("PATH" ":" prefix (,path))))
3571 (find-files bin)))
3572 #t)))))
41ddebdd 3573 (inputs
02f35bb5 3574 `(("perl" ,perl)
71461f88 3575 ("ruby" ,ruby)
02f35bb5 3576 ("gawk" ,gawk)
101e8f71
BW		 3577 ("grep" ,grep)
3578 ("coreutils" ,coreutils)))
41ddebdd
BW		 3579 (home-page "http://mafft.cbrc.jp/alignment/software/")
3580 (synopsis "Multiple sequence alignment program")
3581 (description
3582 "MAFFT offers a range of multiple alignment methods for nucleotide and
3583protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3584of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3585sequences).")
3586 (license (license:non-copyleft
3587 "http://mafft.cbrc.jp/alignment/software/license.txt"
3588 "BSD-3 with different formatting"))))
8fd790eb 3589
84be3b99
MB		 3590(define-public mash
3591 (package
3592 (name "mash")
3593 (version "1.1.1")
3594 (source (origin
3595 (method url-fetch)
3596 (uri (string-append
3597 "https://github.com/marbl/mash/archive/v"
3598 version ".tar.gz"))
3599 (file-name (string-append name "-" version ".tar.gz"))
3600 (sha256
3601 (base32
3602 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3603 (modules '((guix build utils)))
3604 (snippet
3605 ;; Delete bundled kseq.
3606 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3607 '(delete-file "src/mash/kseq.h"))))
3608 (build-system gnu-build-system)
3609 (arguments
3610 `(#:tests? #f ; No tests.
3611 #:configure-flags
3612 (list
3613 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3614 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3615 #:make-flags (list "CC=gcc")
3616 #:phases
3617 (modify-phases %standard-phases
3618 (add-after 'unpack 'fix-includes
3619 (lambda _
3620 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3621 (("^#include \"kseq\\.h\"")
3622 "#include \"htslib/kseq.h\""))
3623 #t))
d10092b8 3624 (add-after 'fix-includes 'autoconf
84be3b99
MB		 3625 (lambda _ (zero? (system* "autoconf")))))))
3626 (native-inputs
3627 `(("autoconf" ,autoconf)
3628 ;; Capnproto and htslib are statically embedded in the final
3629 ;; application. Therefore we also list their licenses, below.
3630 ("capnproto" ,capnproto)
3631 ("htslib" ,htslib)))
3632 (inputs
3633 `(("gsl" ,gsl)
3634 ("zlib" ,zlib)))
3635 (supported-systems '("x86_64-linux"))
3636 (home-page "https://mash.readthedocs.io")
3637 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3638 (description "Mash is a fast sequence distance estimator that uses the
3639MinHash algorithm and is designed to work with genomes and metagenomes in the
3640form of assemblies or reads.")
3641 (license (list license:bsd-3 ; Mash
3642 license:expat ; HTSlib and capnproto
3643 license:public-domain ; MurmurHash 3
3644 license:cpl1.0)))) ; Open Bloom Filter
3645
8fd790eb 3646(define-public metabat
f3f68a44
BW		 3647 (package
3648 (name "metabat")
25bd1fc1 3649 (version "2.12.1")
f3f68a44
BW		 3650 (source
3651 (origin
25bd1fc1
BW		 3652 (method url-fetch)
3653 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3654 version ".tar.gz"))
3655 (file-name (string-append name "-" version ".tar.gz"))
f3f68a44
BW		 3656 (sha256
3657 (base32
25bd1fc1
BW		 3658 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3659 (patches (search-patches "metabat-fix-compilation.patch"))))
9364a520 3660 (build-system scons-build-system)
8fd790eb 3661 (arguments
9364a520
AI		 3662 `(#:scons ,scons-python2
3663 #:scons-flags
3664 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3665 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3666 #:tests? #f ;; Tests are run during the build phase.
3667 #:phases
8fd790eb
BW		 3668 (modify-phases %standard-phases
3669 (add-after 'unpack 'fix-includes
45469ebe
BW		 3670 (lambda _
3671 (substitute* "src/BamUtils.h"
3672 (("^#include \"bam/bam\\.h\"")
3673 "#include \"samtools/bam.h\"")
3674 (("^#include \"bam/sam\\.h\"")
3675 "#include \"samtools/sam.h\""))
3676 (substitute* "src/KseqReader.h"
3677 (("^#include \"bam/kseq\\.h\"")
3678 "#include \"htslib/kseq.h\""))
3679 #t))
8fd790eb 3680 (add-after 'unpack 'fix-scons
f3f68a44
BW		 3681 (lambda* (#:key inputs #:allow-other-keys)
3682 (substitute* "SConstruct"
3683 (("^htslib_dir += 'samtools'")
3684 (string-append "htslib_dir = '"
3685 (assoc-ref inputs "htslib")
3686 "'"))
3687 (("^samtools_dir = 'samtools'")
3688 (string-append "samtools_dir = '"
3689 (assoc-ref inputs "samtools")
3690 "'"))
3691 (("^findStaticOrShared\\('bam', hts_lib")
3692 (string-append "findStaticOrShared('bam', '"
3693 (assoc-ref inputs "samtools")
3694 "/lib'"))
3695 ;; Do not distribute README.
3696 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
9364a520 3697 #t)))))
8fd790eb
BW		 3698 (inputs
3699 `(("zlib" ,zlib)
3700 ("perl" ,perl)
3701 ("samtools" ,samtools)
3702 ("htslib" ,htslib)
3703 ("boost" ,boost)))
8fd790eb
BW		 3704 (home-page "https://bitbucket.org/berkeleylab/metabat")
3705 (synopsis
3706 "Reconstruction of single genomes from complex microbial communities")
3707 (description
3708 "Grouping large genomic fragments assembled from shotgun metagenomic
3709sequences to deconvolute complex microbial communities, or metagenome binning,
3710enables the study of individual organisms and their interactions. MetaBAT is
3711an automated metagenome binning software, which integrates empirical
3712probabilistic distances of genome abundance and tetranucleotide frequency.")
d931a4bb
EF		 3713 ;; The source code contains inline assembly.
3714 (supported-systems '("x86_64-linux" "i686-linux"))
f3f68a44
BW		 3715 (license (license:non-copyleft "file://license.txt"
3716 "See license.txt in the distribution."))))
8fd790eb 3717
318c0aee
MB		 3718(define-public minced
3719 (package
3720 (name "minced")
3721 (version "0.2.0")
3722 (source (origin
3723 (method url-fetch)
3724 (uri (string-append
3725 "https://github.com/ctSkennerton/minced/archive/"
3726 version ".tar.gz"))
3727 (file-name (string-append name "-" version ".tar.gz"))
3728 (sha256
3729 (base32
3730 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3731 (build-system gnu-build-system)
3732 (arguments
3733 `(#:test-target "test"
3734 #:phases
3735 (modify-phases %standard-phases
3736 (delete 'configure)
3737 (add-before 'check 'fix-test
3738 (lambda _
3739 ;; Fix test for latest version.
3740 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3741 (("minced:0.1.6") "minced:0.2.0"))
3742 #t))
3743 (replace 'install ; No install target.
3744 (lambda* (#:key inputs outputs #:allow-other-keys)
3745 (let* ((out (assoc-ref outputs "out"))
3746 (bin (string-append out "/bin"))
3747 (wrapper (string-append bin "/minced")))
3748 ;; Minced comes with a wrapper script that tries to figure out where
3749 ;; it is located before running the JAR. Since these paths are known
3750 ;; to us, we build our own wrapper to avoid coreutils dependency.
3751 (install-file "minced.jar" bin)
3752 (with-output-to-file wrapper
3753 (lambda _
3754 (display
3755 (string-append
3756 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3757 (assoc-ref inputs "jre") "/bin/java -jar "
3758 bin "/minced.jar \"$@\"\n"))))
3759 (chmod wrapper #o555)))))))
3760 (native-inputs
3761 `(("jdk" ,icedtea "jdk")))
3762 (inputs
3763 `(("bash" ,bash)
3764 ("jre" ,icedtea "out")))
3765 (home-page "https://github.com/ctSkennerton/minced")
3766 (synopsis "Mining CRISPRs in Environmental Datasets")
3767 (description
3768 "MinCED is a program to find Clustered Regularly Interspaced Short
3769Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3770unassembled metagenomic reads, but is mainly designed for full genomes and
3771assembled metagenomic sequence.")
3772 (license license:gpl3+)))
3773
ddd82e0e
RW		 3774(define-public miso
3775 (package
3776 (name "miso")
ce4dfde0 3777 (version "0.5.4")
ddd82e0e
RW		 3778 (source (origin
3779 (method url-fetch)
34260a10 3780 (uri (pypi-uri "misopy" version))
ddd82e0e
RW		 3781 (sha256
3782 (base32
ce4dfde0 3783 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
ddd82e0e 3784 (modules '((guix build utils)))
ddd82e0e
RW		 3785 (snippet
3786 '(substitute* "setup.py"
0ec8b206
RW		 3787 ;; Use setuptools, or else the executables are not
3788 ;; installed.
3789 (("distutils.core") "setuptools")
3790 ;; use "gcc" instead of "cc" for compilation
ddd82e0e
RW		 3791 (("^defines")
3792 "cc.set_executables(
3793compiler='gcc',
3794compiler_so='gcc',
3795linker_exe='gcc',
3796linker_so='gcc -shared'); defines")))))
3797 (build-system python-build-system)
3798 (arguments
3799 `(#:python ,python-2 ; only Python 2 is supported
3800 #:tests? #f)) ; no "test" target
3801 (inputs
3802 `(("samtools" ,samtools)
3803 ("python-numpy" ,python2-numpy)
3804 ("python-pysam" ,python2-pysam)
3805 ("python-scipy" ,python2-scipy)
3806 ("python-matplotlib" ,python2-matplotlib)))
3807 (native-inputs
f3b98f4f
HG		 3808 `(("python-mock" ,python2-mock) ;for tests
3809 ("python-pytz" ,python2-pytz))) ;for tests
ddd82e0e
RW		 3810 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3811 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3812 (description
3813 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3814the expression level of alternatively spliced genes from RNA-Seq data, and
3815identifies differentially regulated isoforms or exons across samples. By
3816modeling the generative process by which reads are produced from isoforms in
3817RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3818that a read originated from a particular isoform.")
3819 (license license:gpl2)))
3820
324efb88
BW		 3821(define-public muscle
3822 (package
3823 (name "muscle")
3824 (version "3.8.1551")
3825 (source (origin
3826 (method url-fetch/tarbomb)
324efb88
BW		 3827 (uri (string-append
3828 "http://www.drive5.com/muscle/muscle_src_"
3829 version ".tar.gz"))
3830 (sha256
3831 (base32
3832 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3833 (build-system gnu-build-system)
3834 (arguments
3835 `(#:make-flags (list "LDLIBS = -lm")
3836 #:phases
3837 (modify-phases %standard-phases
3838 (delete 'configure)
3839 (replace 'check
3840 ;; There are no tests, so just test if it runs.
3841 (lambda _ (zero? (system* "./muscle" "-version"))))
3842 (replace 'install
3843 (lambda* (#:key outputs #:allow-other-keys)
3844 (let* ((out (assoc-ref outputs "out"))
3845 (bin (string-append out "/bin")))
3846 (install-file "muscle" bin)))))))
3847 (home-page "http://www.drive5.com/muscle")
3848 (synopsis "Multiple sequence alignment program")
3849 (description
3850 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3851program for nucleotide and protein sequences.")
3852 ;; License information found in 'muscle -h' and usage.cpp.
3853 (license license:public-domain)))
3854
99268755
BW		 3855(define-public newick-utils
3856 ;; There are no recent releases so we package from git.
3857 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3858 (package
3859 (name "newick-utils")
3860 (version (string-append "1.6-1." (string-take commit 8)))
3861 (source (origin
3862 (method git-fetch)
3863 (uri (git-reference
3864 (url "https://github.com/tjunier/newick_utils.git")
3865 (commit commit)))
3866 (file-name (string-append name "-" version "-checkout"))
3867 (sha256
3868 (base32
3869 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3870 (build-system gnu-build-system)
3871 (arguments
3872 `(#:phases
3873 (modify-phases %standard-phases
3874 (add-after 'unpack 'autoconf
3875 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3876 (inputs
3877 ;; XXX: TODO: Enable Lua and Guile bindings.
3878 ;; https://github.com/tjunier/newick_utils/issues/13
3879 `(("libxml2" ,libxml2)
3880 ("flex" ,flex)
3881 ("bison" ,bison)))
3882 (native-inputs
3883 `(("autoconf" ,autoconf)
3884 ("automake" ,automake)
3885 ("libtool" ,libtool)))
3886 (synopsis "Programs for working with newick format phylogenetic trees")
3887 (description
3888 "Newick-utils is a suite of utilities for processing phylogenetic trees
3889in Newick format. Functions include re-rooting, extracting subtrees,
3890trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3891 (home-page "https://github.com/tjunier/newick_utils")
3892 (license license:bsd-3))))
3893
1e44cf8b
BW		 3894(define-public orfm
3895 (package
3896 (name "orfm")
dfc83ead 3897 (version "0.7.1")
1e44cf8b
BW		 3898 (source (origin
3899 (method url-fetch)
3900 (uri (string-append
3901 "https://github.com/wwood/OrfM/releases/download/v"
3902 version "/orfm-" version ".tar.gz"))
3903 (sha256
3904 (base32
dfc83ead 3905 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
1e44cf8b
BW		 3906 (build-system gnu-build-system)
3907 (inputs `(("zlib" ,zlib)))
6b6f7d6a
BW		 3908 (native-inputs
3909 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3910 ("ruby-rspec" ,ruby-rspec)
3911 ("ruby" ,ruby)))
1e44cf8b
BW		 3912 (synopsis "Simple and not slow open reading frame (ORF) caller")
3913 (description
6b6f7d6a 3914 "An ORF caller finds stretches of DNA that, when translated, are not
1e44cf8b
BW		 3915interrupted by stop codons. OrfM finds and prints these ORFs.")
3916 (home-page "https://github.com/wwood/OrfM")
3917 (license license:lgpl3+)))
3918
c033f5d6
BW		 3919(define-public pplacer
3920 (let ((commit "g807f6f3"))
3921 (package
3922 (name "pplacer")
3923 ;; The commit should be updated with each version change.
3924 (version "1.1.alpha19")
3925 (source
3926 (origin
3927 (method url-fetch)
3928 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3929 version ".tar.gz"))
3930 (file-name (string-append name "-" version ".tar.gz"))
3931 (sha256
3932 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3933 (build-system ocaml-build-system)
3934 (arguments
3935 `(#:ocaml ,ocaml-4.01
3936 #:findlib ,ocaml4.01-findlib
3937 #:modules ((guix build ocaml-build-system)
3938 (guix build utils)
3939 (ice-9 ftw))
3940 #:phases
3941 (modify-phases %standard-phases
3942 (delete 'configure)
3943 (add-after 'unpack 'replace-bundled-cddlib
3944 (lambda* (#:key inputs #:allow-other-keys)
3945 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3946 (local-dir "cddlib_guix"))
3947 (mkdir local-dir)
3948 (with-directory-excursion local-dir
3949 (system* "tar" "xvf" cddlib-src))
3950 (let ((cddlib-src-folder
3951 (string-append local-dir "/"
3952 (list-ref (scandir local-dir) 2)
3953 "/lib-src")))
3954 (for-each
3955 (lambda (file)
3956 (copy-file file
3957 (string-append "cdd_src/" (basename file))))
3958 (find-files cddlib-src-folder ".*[ch]$")))
3959 #t)))
3960 (add-after 'unpack 'fix-makefile
3961 (lambda _
3962 ;; Remove system calls to 'git'.
3963 (substitute* "Makefile"
3964 (("^DESCRIPT:=pplacer-.*")
3965 (string-append
3966 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3967 (substitute* "myocamlbuild.ml"
3968 (("git describe --tags --long .*\\\" with")
3969 (string-append
3970 "echo -n v" ,version "-" ,commit "\" with")))
3971 #t))
3972 (replace 'install
3973 (lambda* (#:key outputs #:allow-other-keys)
3974 (let* ((out (assoc-ref outputs "out"))
3975 (bin (string-append out "/bin")))
3976 (copy-recursively "bin" bin))
3977 #t)))))
3978 (native-inputs
3979 `(("zlib" ,zlib)
3980 ("gsl" ,gsl)
3981 ("ocaml-ounit" ,ocaml4.01-ounit)
3982 ("ocaml-batteries" ,ocaml4.01-batteries)
3983 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3984 ("ocaml-csv" ,ocaml4.01-csv)
3985 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3986 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3987 ("ocaml-mcl" ,ocaml4.01-mcl)
3988 ("ocaml-gsl" ,ocaml4.01-gsl)
3989 ("cddlib-src" ,(package-source cddlib))))
3990 (propagated-inputs
3991 `(("pplacer-scripts" ,pplacer-scripts)))
3992 (synopsis "Phylogenetic placement of biological sequences")
3993 (description
3994 "Pplacer places query sequences on a fixed reference phylogenetic tree
3995to maximize phylogenetic likelihood or posterior probability according to a
3996reference alignment. Pplacer is designed to be fast, to give useful
3997information about uncertainty, and to offer advanced visualization and
3998downstream analysis.")
3999 (home-page "http://matsen.fhcrc.org/pplacer")
4000 (license license:gpl3))))
4001
4002;; This package is installed alongside 'pplacer'. It is a separate package so
4003;; that it can use the python-build-system for the scripts that are
4004;; distributed alongside the main OCaml binaries.
4005(define pplacer-scripts
4006 (package
4007 (inherit pplacer)
4008 (name "pplacer-scripts")
4009 (build-system python-build-system)
4010 (arguments
4011 `(#:python ,python-2
4012 #:phases
4013 (modify-phases %standard-phases
4014 (add-after 'unpack 'enter-scripts-dir
4015 (lambda _ (chdir "scripts")))
4016 (replace 'check
4017 (lambda _
4018 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4019 (add-after 'install 'wrap-executables
4020 (lambda* (#:key inputs outputs #:allow-other-keys)
4021 (let* ((out (assoc-ref outputs "out"))
4022 (bin (string-append out "/bin")))
4023 (let ((path (string-append
4024 (assoc-ref inputs "hmmer") "/bin:"
4025 (assoc-ref inputs "infernal") "/bin")))
4026 (display path)
4027 (wrap-program (string-append bin "/refpkg_align.py")
4028 `("PATH" ":" prefix (,path))))
4029 (let ((path (string-append
4030 (assoc-ref inputs "hmmer") "/bin")))
4031 (wrap-program (string-append bin "/hrefpkg_query.py")
4032 `("PATH" ":" prefix (,path)))))
4033 #t)))))
4034 (inputs
4035 `(("infernal" ,infernal)
4036 ("hmmer" ,hmmer)))
4037 (propagated-inputs
4038 `(("python-biopython" ,python2-biopython)
4039 ("taxtastic" ,taxtastic)))
4040 (synopsis "Pplacer Python scripts")))
4041
19ee9201
RW		 4042(define-public python2-pbcore
4043 (package
4044 (name "python2-pbcore")
e301bfc8 4045 (version "1.2.10")
19ee9201
RW		 4046 (source (origin
4047 (method url-fetch)
ddb83129 4048 (uri (pypi-uri "pbcore" version))
19ee9201
RW		 4049 (sha256
4050 (base32
e301bfc8 4051 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
19ee9201
RW		 4052 (build-system python-build-system)
4053 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
de5bc890 4054 (propagated-inputs
19ee9201
RW		 4055 `(("python-cython" ,python2-cython)
4056 ("python-numpy" ,python2-numpy)
4057 ("python-pysam" ,python2-pysam)
4058 ("python-h5py" ,python2-h5py)))
4059 (native-inputs
de5bc890
HG		 4060 `(("python-nose" ,python2-nose)
4061 ("python-sphinx" ,python2-sphinx)
4062 ("python-pyxb" ,python2-pyxb)))
19ee9201
RW		 4063 (home-page "http://pacificbiosciences.github.io/pbcore/")
4064 (synopsis "Library for reading and writing PacBio data files")
4065 (description
4066 "The pbcore package provides Python APIs for interacting with PacBio data
4067files and writing bioinformatics applications.")
4068 (license license:bsd-3)))
4069
c61fe02c
RW		 4070(define-public python2-warpedlmm
4071 (package
4072 (name "python2-warpedlmm")
4073 (version "0.21")
4074 (source
4075 (origin
4076 (method url-fetch)
4077 (uri (string-append
4078 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4079 version ".zip"))
4080 (sha256
4081 (base32
4082 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4083 (build-system python-build-system)
4084 (arguments
54c85e12 4085 `(#:python ,python-2)) ; requires Python 2.7
c61fe02c
RW		 4086 (propagated-inputs
4087 `(("python-scipy" ,python2-scipy)
4088 ("python-numpy" ,python2-numpy)
4089 ("python-matplotlib" ,python2-matplotlib)
4090 ("python-fastlmm" ,python2-fastlmm)
4091 ("python-pandas" ,python2-pandas)
4092 ("python-pysnptools" ,python2-pysnptools)))
4093 (native-inputs
f3b98f4f 4094 `(("python-mock" ,python2-mock)
c61fe02c
RW		 4095 ("python-nose" ,python2-nose)
4096 ("unzip" ,unzip)))
4097 (home-page "https://github.com/PMBio/warpedLMM")
4098 (synopsis "Implementation of warped linear mixed models")
4099 (description
4100 "WarpedLMM is a Python implementation of the warped linear mixed model,
4101which automatically learns an optimal warping function (or transformation) for
4102the phenotype as it models the data.")
4103 (license license:asl2.0)))
4104
2c16316e 4105(define-public pbtranscript-tofu
698bd297 4106 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
2c16316e
RW		 4107 (package
4108 (name "pbtranscript-tofu")
698bd297 4109 (version (string-append "2.2.3." (string-take commit 7)))
2c16316e
RW		 4110 (source (origin
4111 (method git-fetch)
4112 (uri (git-reference
4113 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4114 (commit commit)))
9a067efd 4115 (file-name (string-append name "-" version "-checkout"))
2c16316e
RW		 4116 (sha256
4117 (base32
9a067efd
RW		 4118 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4119 (modules '((guix build utils)))
4120 (snippet
4121 '(begin
4122 ;; remove bundled Cython sources
4123 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4124 #t))))
2c16316e
RW		 4125 (build-system python-build-system)
4126 (arguments
4127 `(#:python ,python-2
cdc2bb50
MB		 4128 ;; FIXME: Tests fail with "No such file or directory:
4129 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4130 #:tests? #f
2c16316e 4131 #:phases
9a067efd
RW		 4132 (modify-phases %standard-phases
4133 (add-after 'unpack 'enter-directory
4134 (lambda _
4135 (chdir "pbtranscript-tofu/pbtranscript/")
4136 #t))
4137 ;; With setuptools version 18.0 and later this setup.py hack causes
4138 ;; a build error, so we disable it.
4139 (add-after 'enter-directory 'patch-setuppy
4140 (lambda _
4141 (substitute* "setup.py"
4142 (("if 'setuptools.extension' in sys.modules:")
4143 "if False:"))
4144 #t)))))
2c16316e 4145 (inputs
9a067efd 4146 `(("python-numpy" ,python2-numpy)
2c16316e 4147 ("python-bx-python" ,python2-bx-python)
c5372108
RW		 4148 ("python-networkx" ,python2-networkx)
4149 ("python-scipy" ,python2-scipy)
9a067efd
RW		 4150 ("python-pbcore" ,python2-pbcore)
4151 ("python-h5py" ,python2-h5py)))
2c16316e 4152 (native-inputs
9a067efd 4153 `(("python-cython" ,python2-cython)
f3b98f4f 4154 ("python-nose" ,python2-nose)))
2c16316e
RW		 4155 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4156 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4157 (description
4158 "pbtranscript-tofu contains scripts to analyze transcriptome data
4159generated using the PacBio Iso-Seq protocol.")
4160 (license license:bsd-3))))
4161
024130d2
BW		 4162(define-public prank
4163 (package
4164 (name "prank")
4165 (version "150803")
4166 (source (origin
4167 (method url-fetch)
4168 (uri (string-append
4169 "http://wasabiapp.org/download/prank/prank.source."
4170 version ".tgz"))
4171 (sha256
4172 (base32
4173 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4174 (build-system gnu-build-system)
4175 (arguments
4176 `(#:phases
4177 (modify-phases %standard-phases
4178 (add-after 'unpack 'enter-src-dir
4179 (lambda _
4180 (chdir "src")
4181 #t))
62d00095
EF		 4182 (add-after 'unpack 'remove-m64-flag
4183 ;; Prank will build with the correct 'bit-ness' without this flag
4184 ;; and this allows building on 32-bit machines.
4185 (lambda _ (substitute* "src/Makefile"
4186 (("-m64") ""))
4187 #t))
024130d2
BW		 4188 (delete 'configure)
4189 (replace 'install
4190 (lambda* (#:key outputs #:allow-other-keys)
4191 (let* ((out (assoc-ref outputs "out"))
4192 (bin (string-append out "/bin"))
4193 (man (string-append out "/share/man/man1"))
4194 (path (string-append
4195 (assoc-ref %build-inputs "mafft") "/bin:"
4196 (assoc-ref %build-inputs "exonerate") "/bin:"
4197 (assoc-ref %build-inputs "bppsuite") "/bin")))
4198 (install-file "prank" bin)
4199 (wrap-program (string-append bin "/prank")
4200 `("PATH" ":" prefix (,path)))
4201 (install-file "prank.1" man))
4202 #t)))))
4203 (inputs
4204 `(("mafft" ,mafft)
4205 ("exonerate" ,exonerate)
4206 ("bppsuite" ,bppsuite)))
4207 (home-page "http://wasabiapp.org/software/prank/")
4208 (synopsis "Probabilistic multiple sequence alignment program")
4209 (description
4210 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4211codon and amino-acid sequences. It is based on a novel algorithm that treats
4212insertions correctly and avoids over-estimation of the number of deletion
4213events. In addition, PRANK borrows ideas from maximum likelihood methods used
4214in phylogenetics and correctly takes into account the evolutionary distances
4215between sequences. Lastly, PRANK allows for defining a potential structure
4216for sequences to be aligned and then, simultaneously with the alignment,
4217predicts the locations of structural units in the sequences.")
4218 (license license:gpl2+)))
4219
31a9d653
BW		 4220(define-public proteinortho
4221 (package
4222 (name "proteinortho")
8c864901 4223 (version "5.16b")
31a9d653
BW		 4224 (source
4225 (origin
4226 (method url-fetch)
4227 (uri
4228 (string-append
4229 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4230 version "_src.tar.gz"))
4231 (sha256
4232 (base32
8c864901 4233 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
31a9d653
BW		 4234 (build-system gnu-build-system)
4235 (arguments
4236 `(#:test-target "test"
4237 #:phases
4238 (modify-phases %standard-phases
4239 (replace 'configure
4240 ;; There is no configure script, so we modify the Makefile directly.
4241 (lambda* (#:key outputs #:allow-other-keys)
4242 (substitute* "Makefile"
4243 (("INSTALLDIR=.*")
4244 (string-append
4245 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4246 #t))
4247 (add-before 'install 'make-install-directory
4248 ;; The install directory is not created during 'make install'.
4249 (lambda* (#:key outputs #:allow-other-keys)
4250 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4251 #t))
4252 (add-after 'install 'wrap-programs
4253 (lambda* (#:key inputs outputs #:allow-other-keys)
4254 (let* ((path (getenv "PATH"))
4255 (out (assoc-ref outputs "out"))
4256 (binary (string-append out "/bin/proteinortho5.pl")))
4257 (wrap-program binary `("PATH" ":" prefix (,path))))
4258 #t)))))
4259 (inputs
4260 `(("perl" ,perl)
4261 ("python" ,python-2)
4262 ("blast+" ,blast+)))
4263 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4264 (synopsis "Detect orthologous genes across species")
4265 (description
4266 "Proteinortho is a tool to detect orthologous genes across different
4267species. For doing so, it compares similarities of given gene sequences and
4268clusters them to find significant groups. The algorithm was designed to handle
4269large-scale data and can be applied to hundreds of species at once.")
4270 (license license:gpl2+)))
4271
846e3409
RW		 4272(define-public pyicoteo
4273 (package
4274 (name "pyicoteo")
4275 (version "2.0.7")
4276 (source
4277 (origin
4278 (method url-fetch)
4279 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4280 "pyicoteo/get/v" version ".tar.bz2"))
4281 (file-name (string-append name "-" version ".tar.bz2"))
4282 (sha256
4283 (base32
4284 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4285 (build-system python-build-system)
4286 (arguments
4287 `(#:python ,python-2 ; does not work with Python 3
4288 #:tests? #f)) ; there are no tests
4289 (inputs
4290 `(("python2-matplotlib" ,python2-matplotlib)))
4291 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4292 (synopsis "Analyze high-throughput genetic sequencing data")
4293 (description
4294 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4295sequencing data. It works with genomic coordinates. There are currently six
4296different command-line tools:
4297
4298@enumerate
4299@item pyicoregion: for generating exploratory regions automatically;
4300@item pyicoenrich: for differential enrichment between two conditions;
4301@item pyicoclip: for calling CLIP-Seq peaks without a control;
4302@item pyicos: for genomic coordinates manipulation;
4303@item pyicoller: for peak calling on punctuated ChIP-Seq;
4304@item pyicount: to count how many reads from N experiment files overlap in a
4305 region file;
4306@item pyicotrocol: to combine operations from pyicoteo.
4307@end enumerate\n")
4308 (license license:gpl3+)))
4309
af860475
BW		 4310(define-public prodigal
4311 (package
4312 (name "prodigal")
e70f7a23 4313 (version "2.6.3")
af860475
BW		 4314 (source (origin
4315 (method url-fetch)
4316 (uri (string-append
4317 "https://github.com/hyattpd/Prodigal/archive/v"
4318 version ".tar.gz"))
4319 (file-name (string-append name "-" version ".tar.gz"))
4320 (sha256
4321 (base32
e70f7a23 4322 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
af860475
BW		 4323 (build-system gnu-build-system)
4324 (arguments
4325 `(#:tests? #f ;no check target
4326 #:make-flags (list (string-append "INSTALLDIR="
4327 (assoc-ref %outputs "out")
4328 "/bin"))
4329 #:phases
4330 (modify-phases %standard-phases
4331 (delete 'configure))))
4332 (home-page "http://prodigal.ornl.gov")
4333 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4334 (description
4335 "Prodigal runs smoothly on finished genomes, draft genomes, and
4336metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4337format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4338partial genes, and identifies translation initiation sites.")
4339 (license license:gpl3+)))
608dd932 4340
ceb62d54
BW		 4341(define-public roary
4342 (package
4343 (name "roary")
da4a707c 4344 (version "3.11.0")
ceb62d54
BW		 4345 (source
4346 (origin
4347 (method url-fetch)
4348 (uri (string-append
4349 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4350 version ".tar.gz"))
4351 (sha256
4352 (base32
da4a707c 4353 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
ceb62d54
BW		 4354 (build-system perl-build-system)
4355 (arguments
4356 `(#:phases
4357 (modify-phases %standard-phases
4358 (delete 'configure)
4359 (delete 'build)
4360 (replace 'check
4361 (lambda _
4362 ;; The tests are not run by default, so we run each test file
4363 ;; directly.
4364 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4365 (getenv "PATH")))
4366 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4367 (getenv "PERL5LIB")))
4368 (zero? (length (filter (lambda (file)
4369 (display file)(display "\n")
4370 (not (zero? (system* "perl" file))))
4371 (find-files "t" ".*\\.t$"))))))
4372 (replace 'install
4373 ;; There is no 'install' target in the Makefile.
4374 (lambda* (#:key outputs #:allow-other-keys)
4375 (let* ((out (assoc-ref outputs "out"))
4376 (bin (string-append out "/bin"))
4377 (perl (string-append out "/lib/perl5/site_perl"))
4378 (roary-plots "contrib/roary_plots"))
4379 (mkdir-p bin)
4380 (mkdir-p perl)
4381 (copy-recursively "bin" bin)
4382 (copy-recursively "lib" perl)
4383 #t)))
4384 (add-after 'install 'wrap-programs
4385 (lambda* (#:key inputs outputs #:allow-other-keys)
4386 (let* ((out (assoc-ref outputs "out"))
4387 (perl5lib (getenv "PERL5LIB"))
4388 (path (getenv "PATH")))
4389 (for-each (lambda (prog)
4390 (let ((binary (string-append out "/" prog)))
4391 (wrap-program binary
4392 `("PERL5LIB" ":" prefix
4393 (,(string-append perl5lib ":" out
4394 "/lib/perl5/site_perl"))))
4395 (wrap-program binary
4396 `("PATH" ":" prefix
4397 (,(string-append path ":" out "/bin"))))))
4398 (find-files "bin" ".*[^R]$"))
4399 (let ((file
4400 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4401 (r-site-lib (getenv "R_LIBS_SITE"))
4402 (coreutils-path
4403 (string-append (assoc-ref inputs "coreutils") "/bin")))
4404 (wrap-program file
4405 `("R_LIBS_SITE" ":" prefix
4406 (,(string-append r-site-lib ":" out "/site-library/"))))
4407 (wrap-program file
4408 `("PATH" ":" prefix
4409 (,(string-append coreutils-path ":" out "/bin"))))))
4410 #t)))))
4411 (native-inputs
4412 `(("perl-env-path" ,perl-env-path)
4413 ("perl-test-files" ,perl-test-files)
4414 ("perl-test-most" ,perl-test-most)
4415 ("perl-test-output" ,perl-test-output)))
4416 (inputs
4417 `(("perl-array-utils" ,perl-array-utils)
4418 ("bioperl" ,bioperl-minimal)
da4a707c 4419 ("perl-digest-md5-file" ,perl-digest-md5-file)
ceb62d54
BW		 4420 ("perl-exception-class" ,perl-exception-class)
4421 ("perl-file-find-rule" ,perl-file-find-rule)
4422 ("perl-file-grep" ,perl-file-grep)
4423 ("perl-file-slurper" ,perl-file-slurper)
4424 ("perl-file-which" ,perl-file-which)
4425 ("perl-graph" ,perl-graph)
4426 ("perl-graph-readwrite" ,perl-graph-readwrite)
4427 ("perl-log-log4perl" ,perl-log-log4perl)
4428 ("perl-moose" ,perl-moose)
4429 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4430 ("perl-text-csv" ,perl-text-csv)
4431 ("bedtools" ,bedtools)
4432 ("cd-hit" ,cd-hit)
4433 ("blast+" ,blast+)
4434 ("mcl" ,mcl)
4435 ("parallel" ,parallel)
4436 ("prank" ,prank)
4437 ("mafft" ,mafft)
4438 ("fasttree" ,fasttree)
4439 ("grep" ,grep)
4440 ("sed" ,sed)
4441 ("gawk" ,gawk)
2d7c4ae3 4442 ("r-minimal" ,r-minimal)
ceb62d54
BW		 4443 ("r-ggplot2" ,r-ggplot2)
4444 ("coreutils" ,coreutils)))
4445 (home-page "http://sanger-pathogens.github.io/Roary")
4446 (synopsis "High speed stand-alone pan genome pipeline")
4447 (description
4448 "Roary is a high speed stand alone pan genome pipeline, which takes
4449annotated assemblies in GFF3 format (produced by the Prokka program) and
4450calculates the pan genome. Using a standard desktop PC, it can analyse
4451datasets with thousands of samples, without compromising the quality of the
4452results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4453single processor. Roary is not intended for metagenomics or for comparing
4454extremely diverse sets of genomes.")
4455 (license license:gpl3)))
4456
608dd932
BW		 4457(define-public raxml
4458 (package
4459 (name "raxml")
e9e0fab0 4460 (version "8.2.10")
608dd932
BW		 4461 (source
4462 (origin
4463 (method url-fetch)
4464 (uri
4465 (string-append
4466 "https://github.com/stamatak/standard-RAxML/archive/v"
4467 version ".tar.gz"))
4468 (file-name (string-append name "-" version ".tar.gz"))
4469 (sha256
4470 (base32
e9e0fab0 4471 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
608dd932
BW		 4472 (build-system gnu-build-system)
4473 (arguments
4474 `(#:tests? #f ; There are no tests.
4475 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4476 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4477 #:phases
4478 (modify-phases %standard-phases
4479 (delete 'configure)
4480 (replace 'install
4481 (lambda* (#:key outputs #:allow-other-keys)
4482 (let* ((out (assoc-ref outputs "out"))
4483 (bin (string-append out "/bin"))
4484 (executable "raxmlHPC-HYBRID"))
4485 (install-file executable bin)
4486 (symlink (string-append bin "/" executable) "raxml"))
4487 #t)))))
4488 (inputs
4489 `(("openmpi" ,openmpi)))
4490 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4491 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4492 (description
4493 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4494phylogenies.")
2805f9b2
EF		 4495 ;; The source includes x86 specific code
4496 (supported-systems '("x86_64-linux" "i686-linux"))
608dd932 4497 (license license:gpl2+)))
af860475 4498
66e3eff1
RW		 4499(define-public rsem
4500 (package
4501 (name "rsem")
4502 (version "1.2.20")
4503 (source
4504 (origin
4505 (method url-fetch)
4506 (uri
4507 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4508 version ".tar.gz"))
4509 (sha256
4510 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
fc1adab1 4511 (patches (search-patches "rsem-makefile.patch"))
66e3eff1
RW		 4512 (modules '((guix build utils)))
4513 (snippet
4514 '(begin
4515 ;; remove bundled copy of boost
4516 (delete-file-recursively "boost")
4517 #t))))
4518 (build-system gnu-build-system)
4519 (arguments
4520 `(#:tests? #f ;no "check" target
4521 #:phases
4522 (modify-phases %standard-phases
4523 ;; No "configure" script.
4524 ;; Do not build bundled samtools library.
4525 (replace 'configure
4526 (lambda _
4527 (substitute* "Makefile"
4528 (("^all : sam/libbam.a") "all : "))
4529 #t))
4530 (replace 'install
4531 (lambda* (#:key outputs #:allow-other-keys)
4532 (let* ((out (string-append (assoc-ref outputs "out")))
4533 (bin (string-append out "/bin/"))
4534 (perl (string-append out "/lib/perl5/site_perl")))
4535 (mkdir-p bin)
4536 (mkdir-p perl)
4537 (for-each (lambda (file)
f3860753 4538 (install-file file bin))
66e3eff1 4539 (find-files "." "rsem-.*"))
f3860753 4540 (install-file "rsem_perl_utils.pm" perl))
66e3eff1
RW		 4541 #t))
4542 (add-after
4543 'install 'wrap-program
4544 (lambda* (#:key outputs #:allow-other-keys)
4545 (let ((out (assoc-ref outputs "out")))
4546 (for-each (lambda (prog)
4547 (wrap-program (string-append out "/bin/" prog)
4548 `("PERL5LIB" ":" prefix
4549 (,(string-append out "/lib/perl5/site_perl")))))
4550 '("rsem-plot-transcript-wiggles"
4551 "rsem-calculate-expression"
4552 "rsem-generate-ngvector"
4553 "rsem-run-ebseq"
4554 "rsem-prepare-reference")))
4555 #t)))))
4556 (inputs
4557 `(("boost" ,boost)
4558 ("ncurses" ,ncurses)
2d7c4ae3 4559 ("r-minimal" ,r-minimal)
66e3eff1
RW		 4560 ("perl" ,perl)
4561 ("samtools" ,samtools-0.1)
4562 ("zlib" ,zlib)))
4563 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4564 (synopsis "Estimate gene expression levels from RNA-Seq data")
4565 (description
4566 "RSEM is a software package for estimating gene and isoform expression
4567levels from RNA-Seq data. The RSEM package provides a user-friendly
4568interface, supports threads for parallel computation of the EM algorithm,
4569single-end and paired-end read data, quality scores, variable-length reads and
4570RSPD estimation. In addition, it provides posterior mean and 95% credibility
4571interval estimates for expression levels. For visualization, it can generate
4572BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4573 (license license:gpl3+)))
4574
8622a072
RW		 4575(define-public rseqc
4576 (package
4577 (name "rseqc")
4578 (version "2.6.1")
4579 (source
4580 (origin
4581 (method url-fetch)
4582 (uri
4583 (string-append "mirror://sourceforge/rseqc/"
de67e922 4584 "RSeQC-" version ".tar.gz"))
8622a072 4585 (sha256
8214b7fb 4586 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
8622a072
RW		 4587 (modules '((guix build utils)))
4588 (snippet
4589 '(begin
4590 ;; remove bundled copy of pysam
4591 (delete-file-recursively "lib/pysam")
4592 (substitute* "setup.py"
4593 ;; remove dependency on outdated "distribute" module
4594 (("^from distribute_setup import use_setuptools") "")
4595 (("^use_setuptools\\(\\)") "")
4596 ;; do not use bundled copy of pysam
4597 (("^have_pysam = False") "have_pysam = True"))))))
4598 (build-system python-build-system)
4599 (arguments `(#:python ,python-2))
4600 (inputs
4601 `(("python-cython" ,python2-cython)
4602 ("python-pysam" ,python2-pysam)
4603 ("python-numpy" ,python2-numpy)
8622a072
RW		 4604 ("zlib" ,zlib)))
4605 (native-inputs
4606 `(("python-nose" ,python2-nose)))
4607 (home-page "http://rseqc.sourceforge.net/")
4608 (synopsis "RNA-seq quality control package")
4609 (description
4610 "RSeQC provides a number of modules that can comprehensively evaluate
4611high throughput sequence data, especially RNA-seq data. Some basic modules
4612inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4613while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4614distribution, coverage uniformity, strand specificity, etc.")
4615 (license license:gpl3+)))
4616
ec946638
RW		 4617(define-public seek
4618 ;; There are no release tarballs. According to the installation
4619 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4620 ;; stable release is identified by this changeset ID.
4621 (let ((changeset "2329130")
4622 (revision "1"))
4623 (package
4624 (name "seek")
4625 (version (string-append "0-" revision "." changeset))
4626 (source (origin
4627 (method hg-fetch)
4628 (uri (hg-reference
4629 (url "https://bitbucket.org/libsleipnir/sleipnir")
4630 (changeset changeset)))
4631 (sha256
4632 (base32
4633 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4634 (build-system gnu-build-system)
4635 (arguments
4636 `(#:modules ((srfi srfi-1)
4637 (guix build gnu-build-system)
4638 (guix build utils))
4639 #:phases
4640 (let ((dirs '("SeekMiner"
4641 "SeekEvaluator"
4642 "SeekPrep"
4643 "Distancer"
4644 "Data2DB"
4645 "PCL2Bin")))
4646 (modify-phases %standard-phases
4561498e 4647 (add-before 'configure 'bootstrap
ec946638
RW		 4648 (lambda _
4649 (zero? (system* "bash" "gen_auto"))))
4650 (add-after 'build 'build-additional-tools
4651 (lambda* (#:key make-flags #:allow-other-keys)
4652 (every (lambda (dir)
4653 (with-directory-excursion (string-append "tools/" dir)
4654 (zero? (apply system* "make" make-flags))))
4655 dirs)))
4656 (add-after 'install 'install-additional-tools
4657 (lambda* (#:key make-flags #:allow-other-keys)
4658 (fold (lambda (dir result)
4659 (with-directory-excursion (string-append "tools/" dir)
4660 (and result
4661 (zero? (apply system*
4662 `("make" ,@make-flags "install"))))))
4663 #t dirs)))))))
4664 (inputs
4665 `(("gsl" ,gsl)
4666 ("boost" ,boost)
4667 ("libsvm" ,libsvm)
4668 ("readline" ,readline)
4669 ("gengetopt" ,gengetopt)
4670 ("log4cpp" ,log4cpp)))
4671 (native-inputs
4672 `(("autoconf" ,autoconf)
4673 ("automake" ,automake)
4674 ("perl" ,perl)))
4675 (home-page "http://seek.princeton.edu")
4676 (synopsis "Gene co-expression search engine")
4677 (description
4678 "SEEK is a computational gene co-expression search engine. SEEK provides
4679biologists with a way to navigate the massive human expression compendium that
4680now contains thousands of expression datasets. SEEK returns a robust ranking
4681of co-expressed genes in the biological area of interest defined by the user's
4682query genes. It also prioritizes thousands of expression datasets according
4683to the user's query of interest.")
4684 (license license:cc-by3.0))))
4685
4e10a221
RW		 4686(define-public samtools
4687 (package
4688 (name "samtools")
63fa0ffc 4689 (version "1.5")
4e10a221
RW		 4690 (source
4691 (origin
4692 (method url-fetch)
4693 (uri
de67e922 4694 (string-append "mirror://sourceforge/samtools/samtools/"
4e10a221
RW		 4695 version "/samtools-" version ".tar.bz2"))
4696 (sha256
4697 (base32
63fa0ffc 4698 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4e10a221
RW		 4699 (build-system gnu-build-system)
4700 (arguments
c4473411 4701 `(#:modules ((ice-9 ftw)
5bdda30b
RW		 4702 (ice-9 regex)
4703 (guix build gnu-build-system)
4704 (guix build utils))
c4473411 4705 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4ab16440 4706 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4e10a221 4707 #:phases
c842d425
BW		 4708 (modify-phases %standard-phases
4709 (add-after 'unpack 'patch-tests
4710 (lambda _
4711 (substitute* "test/test.pl"
4712 ;; The test script calls out to /bin/bash
4713 (("/bin/bash") (which "bash")))
b2d748ed 4714 #t))
c842d425
BW		 4715 (add-after 'install 'install-library
4716 (lambda* (#:key outputs #:allow-other-keys)
4717 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4718 (install-file "libbam.a" lib)
4719 #t)))
4720 (add-after 'install 'install-headers
4721 (lambda* (#:key outputs #:allow-other-keys)
4722 (let ((include (string-append (assoc-ref outputs "out")
4723 "/include/samtools/")))
4724 (for-each (lambda (file)
4725 (install-file file include))
4726 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4727 #t))))))
4e10a221 4728 (native-inputs `(("pkg-config" ,pkg-config)))
4ab16440
BW		 4729 (inputs
4730 `(("htslib" ,htslib)
4731 ("ncurses" ,ncurses)
4732 ("perl" ,perl)
4733 ("python" ,python)
4734 ("zlib" ,zlib)))
4e10a221
RW		 4735 (home-page "http://samtools.sourceforge.net")
4736 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4737 (description
4738 "Samtools implements various utilities for post-processing nucleotide
4739sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4740variant calling (in conjunction with bcftools), and a simple alignment
4741viewer.")
4742 (license license:expat)))
d3517eda 4743
0b84a0aa
RW		 4744(define-public samtools-0.1
4745 ;; This is the most recent version of the 0.1 line of samtools. The input
4746 ;; and output formats differ greatly from that used and produced by samtools
4747 ;; 1.x and is still used in many bioinformatics pipelines.
4748 (package (inherit samtools)
4749 (version "0.1.19")
4750 (source
4751 (origin
4752 (method url-fetch)
4753 (uri
de67e922 4754 (string-append "mirror://sourceforge/samtools/samtools/"
0b84a0aa
RW		 4755 version "/samtools-" version ".tar.bz2"))
4756 (sha256
4757 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4758 (arguments
2309ed68
RW		 4759 `(#:tests? #f ;no "check" target
4760 ,@(substitute-keyword-arguments (package-arguments samtools)
4761 ((#:make-flags flags)
4762 `(cons "LIBCURSES=-lncurses" ,flags))
4763 ((#:phases phases)
4764 `(modify-phases ,phases
4765 (replace 'install
4766 (lambda* (#:key outputs #:allow-other-keys)
4767 (let ((bin (string-append
4768 (assoc-ref outputs "out") "/bin")))
4769 (mkdir-p bin)
f3860753 4770 (install-file "samtools" bin)
b2d748ed 4771 #t)))
2309ed68
RW		 4772 (delete 'patch-tests)
4773 (delete 'configure))))))))
0b84a0aa 4774
fe4c37c2 4775(define-public mosaik
698bd297 4776 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
fe4c37c2
RW		 4777 (package
4778 (name "mosaik")
4779 (version "2.2.30")
4780 (source (origin
4781 ;; There are no release tarballs nor tags.
4782 (method git-fetch)
4783 (uri (git-reference
4784 (url "https://github.com/wanpinglee/MOSAIK.git")
4785 (commit commit)))
4786 (file-name (string-append name "-" version))
4787 (sha256
4788 (base32
4789 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4790 (build-system gnu-build-system)
4791 (arguments
4792 `(#:tests? #f ; no tests
4793 #:make-flags (list "CC=gcc")
4794 #:phases
4795 (modify-phases %standard-phases
4796 (replace 'configure
4797 (lambda _ (chdir "src") #t))
4798 (replace 'install
4799 (lambda* (#:key outputs #:allow-other-keys)
4800 (let ((bin (string-append (assoc-ref outputs "out")
4801 "/bin")))
4802 (mkdir-p bin)
4803 (copy-recursively "../bin" bin)
4804 #t))))))
4805 (inputs
4806 `(("perl" ,perl)
4807 ("zlib" ,zlib)))
029d9f77 4808 (supported-systems '("x86_64-linux"))
0c6c9c00 4809 (home-page "https://github.com/wanpinglee/MOSAIK")
fe4c37c2
RW		 4810 (synopsis "Map nucleotide sequence reads to reference genomes")
4811 (description
4812 "MOSAIK is a program for mapping second and third-generation sequencing
4813reads to a reference genome. MOSAIK can align reads generated by all the
4814major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4815Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4816 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4817 ;; code released into the public domain:
4818 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4819 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4820 (license (list license:gpl2+ license:public-domain)))))
4821
282c5087
RW		 4822(define-public ngs-sdk
4823 (package
4824 (name "ngs-sdk")
6c4ccf32 4825 (version "1.3.0")
282c5087
RW		 4826 (source
4827 (origin
4828 (method url-fetch)
4829 (uri
4830 (string-append "https://github.com/ncbi/ngs/archive/"
4831 version ".tar.gz"))
4832 (file-name (string-append name "-" version ".tar.gz"))
4833 (sha256
4834 (base32
6c4ccf32 4835 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
282c5087
RW		 4836 (build-system gnu-build-system)
4837 (arguments
4838 `(#:parallel-build? #f ; not supported
4839 #:tests? #f ; no "check" target
4840 #:phases
dc1d3cde
KK		 4841 (modify-phases %standard-phases
4842 (replace 'configure
4843 (lambda* (#:key outputs #:allow-other-keys)
4844 (let ((out (assoc-ref outputs "out")))
4845 ;; Allow 'konfigure.perl' to find 'package.prl'.
4846 (setenv "PERL5LIB"
4847 (string-append ".:" (getenv "PERL5LIB")))
4848
4849 ;; The 'configure' script doesn't recognize things like
4850 ;; '--enable-fast-install'.
4851 (zero? (system* "./configure"
4852 (string-append "--build-prefix=" (getcwd) "/build")
4853 (string-append "--prefix=" out))))))
4854 (add-after 'unpack 'enter-dir
4855 (lambda _ (chdir "ngs-sdk") #t)))))
282c5087 4856 (native-inputs `(("perl" ,perl)))
a0dadf0c
AE		 4857 ;; According to the test
4858 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4859 ;; in ngs-sdk/setup/konfigure.perl
ab29be81 4860 (supported-systems '("i686-linux" "x86_64-linux"))
282c5087
RW		 4861 (home-page "https://github.com/ncbi/ngs")
4862 (synopsis "API for accessing Next Generation Sequencing data")
4863 (description
4864 "NGS is a domain-specific API for accessing reads, alignments and pileups
4865produced from Next Generation Sequencing. The API itself is independent from
4866any particular back-end implementation, and supports use of multiple back-ends
4867simultaneously.")
4868 (license license:public-domain)))
4869
1ad15c16 4870(define-public java-ngs
2651a5e6 4871 (package (inherit ngs-sdk)
1ad15c16 4872 (name "java-ngs")
2651a5e6
RW		 4873 (arguments
4874 `(,@(substitute-keyword-arguments
4875 `(#:modules ((guix build gnu-build-system)
4876 (guix build utils)
4877 (srfi srfi-1)
4878 (srfi srfi-26))
4879 ,@(package-arguments ngs-sdk))
4880 ((#:phases phases)
614a8977
RW		 4881 `(modify-phases ,phases
4882 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
2651a5e6 4883 (inputs
d2540f80 4884 `(("jdk" ,icedtea "jdk")
2651a5e6
RW		 4885 ("ngs-sdk" ,ngs-sdk)))
4886 (synopsis "Java bindings for NGS SDK")))
4887
75dd2424
RW		 4888(define-public ncbi-vdb
4889 (package
4890 (name "ncbi-vdb")
5021f547 4891 (version "2.8.2")
75dd2424
RW		 4892 (source
4893 (origin
4894 (method url-fetch)
4895 (uri
4896 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4897 version ".tar.gz"))
4898 (file-name (string-append name "-" version ".tar.gz"))
4899 (sha256
4900 (base32
5021f547 4901 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
75dd2424
RW		 4902 (build-system gnu-build-system)
4903 (arguments
4904 `(#:parallel-build? #f ; not supported
4905 #:tests? #f ; no "check" target
4906 #:phases
70111198 4907 (modify-phases %standard-phases
0691851a
BW		 4908 (add-before 'configure 'set-perl-search-path
4909 (lambda _
4910 ;; Work around "dotless @INC" build failure.
4911 (setenv "PERL5LIB"
4912 (string-append (getcwd) "/setup:"
4913 (getenv "PERL5LIB")))
4914 #t))
70111198
RW		 4915 (replace 'configure
4916 (lambda* (#:key inputs outputs #:allow-other-keys)
4917 (let ((out (assoc-ref outputs "out")))
4918 ;; Override include path for libmagic
4919 (substitute* "setup/package.prl"
4920 (("name => 'magic', Include => '/usr/include'")
4921 (string-append "name=> 'magic', Include => '"
4922 (assoc-ref inputs "libmagic")
4923 "/include" "'")))
75dd2424 4924
70111198
RW		 4925 ;; Install kdf5 library (needed by sra-tools)
4926 (substitute* "build/Makefile.install"
4927 (("LIBRARIES_TO_INSTALL =")
4928 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
75dd2424 4929
70111198
RW		 4930 (substitute* "build/Makefile.env"
4931 (("CFLAGS =" prefix)
4932 (string-append prefix "-msse2 ")))
675d7ae2 4933
558e2307
RW		 4934 ;; Override search path for ngs-java
4935 (substitute* "setup/package.prl"
4936 (("/usr/local/ngs/ngs-java")
4937 (assoc-ref inputs "java-ngs")))
4938
70111198
RW		 4939 ;; The 'configure' script doesn't recognize things like
4940 ;; '--enable-fast-install'.
4941 (zero? (system*
4942 "./configure"
4943 (string-append "--build-prefix=" (getcwd) "/build")
4944 (string-append "--prefix=" (assoc-ref outputs "out"))
4945 (string-append "--debug")
4946 (string-append "--with-xml2-prefix="
4947 (assoc-ref inputs "libxml2"))
4948 (string-append "--with-ngs-sdk-prefix="
4949 (assoc-ref inputs "ngs-sdk"))
70111198
RW		 4950 (string-append "--with-hdf5-prefix="
4951 (assoc-ref inputs "hdf5")))))))
4952 (add-after 'install 'install-interfaces
4953 (lambda* (#:key outputs #:allow-other-keys)
4954 ;; Install interface libraries. On i686 the interface libraries
4955 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4956 ;; architecture name ("i386") instead of the target system prefix
4957 ;; ("i686").
4958 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4959 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4960 ,(system->linux-architecture
4961 (or (%current-target-system)
4962 (%current-system)))
4963 "/rel/ilib")
4964 (string-append (assoc-ref outputs "out")
4965 "/ilib"))
4966 ;; Install interface headers
4967 (copy-recursively "interfaces"
4968 (string-append (assoc-ref outputs "out")
4969 "/include"))
d5e17162
RW		 4970 #t))
4971 ;; These files are needed by sra-tools.
4972 (add-after 'install 'install-configuration-files
4973 (lambda* (#:key outputs #:allow-other-keys)
4974 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4975 (mkdir target)
4976 (install-file "libs/kfg/default.kfg" target)
4977 (install-file "libs/kfg/certs.kfg" target))
70111198 4978 #t)))))
75dd2424
RW		 4979 (inputs
4980 `(("libxml2" ,libxml2)
4981 ("ngs-sdk" ,ngs-sdk)
1ad15c16 4982 ("java-ngs" ,java-ngs)
75dd2424
RW		 4983 ("libmagic" ,file)
4984 ("hdf5" ,hdf5)))
4985 (native-inputs `(("perl" ,perl)))
675d7ae2
RW		 4986 ;; NCBI-VDB requires SSE capability.
4987 (supported-systems '("i686-linux" "x86_64-linux"))
75dd2424
RW		 4988 (home-page "https://github.com/ncbi/ncbi-vdb")
4989 (synopsis "Database engine for genetic information")
4990 (description
4991 "The NCBI-VDB library implements a highly compressed columnar data
4992warehousing engine that is most often used to store genetic information.
4993Databases are stored in a portable image within the file system, and can be
4994accessed/downloaded on demand across HTTP.")
4995 (license license:public-domain)))
4996
cc6ed477
RW		 4997(define-public plink
4998 (package
4999 (name "plink")
5000 (version "1.07")
5001 (source
5002 (origin
5003 (method url-fetch)
5004 (uri (string-append
5005 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5006 version "-src.zip"))
5007 (sha256
5008 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
0dbb7ac2
EF		 5009 (patches (search-patches "plink-1.07-unclobber-i.patch"
5010 "plink-endian-detection.patch"))))
cc6ed477
RW		 5011 (build-system gnu-build-system)
5012 (arguments
5013 '(#:tests? #f ;no "check" target
5014 #:make-flags (list (string-append "LIB_LAPACK="
5015 (assoc-ref %build-inputs "lapack")
5016 "/lib/liblapack.so")
5017 "WITH_LAPACK=1"
5018 "FORCE_DYNAMIC=1"
5019 ;; disable phoning home
5020 "WITH_WEBCHECK=")
5021 #:phases
5022 (modify-phases %standard-phases
5023 ;; no "configure" script
5024 (delete 'configure)
5025 (replace 'install
5026 (lambda* (#:key outputs #:allow-other-keys)
5027 (let ((bin (string-append (assoc-ref outputs "out")
5028 "/bin/")))
96c46210 5029 (install-file "plink" bin)
cc6ed477
RW		 5030 #t))))))
5031 (inputs
5032 `(("zlib" ,zlib)
5033 ("lapack" ,lapack)))
5034 (native-inputs
5035 `(("unzip" ,unzip)))
5036 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5037 (synopsis "Whole genome association analysis toolset")
5038 (description
5039 "PLINK is a whole genome association analysis toolset, designed to
5040perform a range of basic, large-scale analyses in a computationally efficient
5041manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5042so there is no support for steps prior to this (e.g. study design and
5043planning, generating genotype or CNV calls from raw data). Through
5044integration with gPLINK and Haploview, there is some support for the
5045subsequent visualization, annotation and storage of results.")
5046 ;; Code is released under GPLv2, except for fisher.h, which is under
5047 ;; LGPLv2.1+
5048 (license (list license:gpl2 license:lgpl2.1+))))
5049
dad66da4
RW		 5050(define-public plink-ng
5051 (package (inherit plink)
5052 (name "plink-ng")
5053 (version "1.90b4")
5054 (source
5055 (origin
5056 (method url-fetch)
5057 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5058 version ".tar.gz"))
5059 (file-name (string-append name "-" version ".tar.gz"))
5060 (sha256
5061 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5062 (build-system gnu-build-system)
5063 (arguments
5064 '(#:tests? #f ;no "check" target
5065 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5066 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5067 "ZLIB=-lz"
5068 "-f" "Makefile.std")
5069 #:phases
5070 (modify-phases %standard-phases
5071 (add-after 'unpack 'chdir
5072 (lambda _ (chdir "1.9") #t))
5073 (delete 'configure) ; no "configure" script
5074 (replace 'install
5075 (lambda* (#:key outputs #:allow-other-keys)
5076 (let ((bin (string-append (assoc-ref outputs "out")
5077 "/bin/")))
5078 (install-file "plink" bin)
5079 #t))))))
5080 (inputs
5081 `(("zlib" ,zlib)
5082 ("lapack" ,lapack)
5083 ("openblas" ,openblas)))
5084 (home-page "https://www.cog-genomics.org/plink/")
5085 (license license:gpl3+)))
5086
c6a24d6e
RW		 5087(define-public smithlab-cpp
5088 (let ((revision "1")
698bd297 5089 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
c6a24d6e
RW		 5090 (package
5091 (name "smithlab-cpp")
698bd297 5092 (version (string-append "0." revision "." (string-take commit 7)))
c6a24d6e
RW		 5093 (source (origin
5094 (method git-fetch)
5095 (uri (git-reference
5096 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5097 (commit commit)))
5098 (file-name (string-append name "-" version "-checkout"))
5099 (sha256
5100 (base32
5101 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5102 (build-system gnu-build-system)
5103 (arguments
5104 `(#:modules ((guix build gnu-build-system)
5105 (guix build utils)
5106 (srfi srfi-26))
5107 #:tests? #f ;no "check" target
5108 #:phases
5109 (modify-phases %standard-phases
5110 (add-after 'unpack 'use-samtools-headers
5111 (lambda _
5112 (substitute* '("SAM.cpp"
5113 "SAM.hpp")
5114 (("sam.h") "samtools/sam.h"))
5115 #t))
5116 (replace 'install
5117 (lambda* (#:key outputs #:allow-other-keys)
5118 (let* ((out (assoc-ref outputs "out"))
5119 (lib (string-append out "/lib"))
5120 (include (string-append out "/include/smithlab-cpp")))
5121 (mkdir-p lib)
5122 (mkdir-p include)
5123 (for-each (cut install-file <> lib)
5124 (find-files "." "\\.o$"))
5125 (for-each (cut install-file <> include)
5126 (find-files "." "\\.hpp$")))
5127 #t))
5128 (delete 'configure))))
5129 (inputs
5130 `(("samtools" ,samtools-0.1)
5131 ("zlib" ,zlib)))
5132 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5133 (synopsis "C++ helper library for functions used in Smith lab projects")
5134 (description
5135 "Smithlab CPP is a C++ library that includes functions used in many of
5136the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5137structures, classes for genomic regions, mapped sequencing reads, etc.")
5138 (license license:gpl3+))))
5139
56e373ef
RW		 5140(define-public preseq
5141 (package
5142 (name "preseq")
b49c5a58 5143 (version "2.0")
56e373ef
RW		 5144 (source (origin
5145 (method url-fetch)
b49c5a58
RW		 5146 (uri (string-append "https://github.com/smithlabcode/"
5147 "preseq/archive/v" version ".tar.gz"))
5148 (file-name (string-append name "-" version ".tar.gz"))
56e373ef 5149 (sha256
b49c5a58 5150 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
56e373ef
RW		 5151 (modules '((guix build utils)))
5152 (snippet
5153 ;; Remove bundled samtools.
b49c5a58 5154 '(delete-file-recursively "samtools"))))
56e373ef
RW		 5155 (build-system gnu-build-system)
5156 (arguments
5157 `(#:tests? #f ;no "check" target
5158 #:phases
5159 (modify-phases %standard-phases
56e373ef 5160 (delete 'configure))
b49c5a58
RW		 5161 #:make-flags
5162 (list (string-append "PREFIX="
5163 (assoc-ref %outputs "out"))
5164 (string-append "LIBBAM="
5165 (assoc-ref %build-inputs "samtools")
5166 "/lib/libbam.a")
5167 (string-append "SMITHLAB_CPP="
5168 (assoc-ref %build-inputs "smithlab-cpp")
5169 "/lib")
5170 "PROGS=preseq"
5171 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
56e373ef
RW		 5172 (inputs
5173 `(("gsl" ,gsl)
5174 ("samtools" ,samtools-0.1)
b49c5a58 5175 ("smithlab-cpp" ,smithlab-cpp)
56e373ef
RW		 5176 ("zlib" ,zlib)))
5177 (home-page "http://smithlabresearch.org/software/preseq/")
5178 (synopsis "Program for analyzing library complexity")
5179 (description
5180 "The preseq package is aimed at predicting and estimating the complexity
5181of a genomic sequencing library, equivalent to predicting and estimating the
5182number of redundant reads from a given sequencing depth and how many will be
5183expected from additional sequencing using an initial sequencing experiment.
5184The estimates can then be used to examine the utility of further sequencing,
5185optimize the sequencing depth, or to screen multiple libraries to avoid low
5186complexity samples.")
5187 (license license:gpl3+)))
5188
9ded1457
BW		 5189(define-public python-screed
5190 (package
5191 (name "python-screed")
5192 (version "0.9")
5193 (source
5194 (origin
5195 (method url-fetch)
5196 (uri (pypi-uri "screed" version))
5197 (sha256
5198 (base32
5199 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5200 (build-system python-build-system)
5201 (arguments
5202 `(#:phases
5203 (modify-phases %standard-phases
5204 (replace 'check
5205 (lambda _
5206 (setenv "PYTHONPATH"
5207 (string-append (getenv "PYTHONPATH") ":."))
5208 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5209 (native-inputs
5210 `(("python-nose" ,python-nose)))
5211 (inputs
5212 `(("python-bz2file" ,python-bz2file)))
7bf837fd 5213 (home-page "https://github.com/dib-lab/screed/")
9ded1457
BW		 5214 (synopsis "Short read sequence database utilities")
5215 (description "Screed parses FASTA and FASTQ files and generates databases.
5216Values such as sequence name, sequence description, sequence quality and the
5217sequence itself can be retrieved from these databases.")
5218 (license license:bsd-3)))
5219
5220(define-public python2-screed
5c31f4aa 5221 (package-with-python2 python-screed))
9ded1457 5222
51c64999
RW		 5223(define-public sra-tools
5224 (package
5225 (name "sra-tools")
79849358 5226 (version "2.8.2-1")
51c64999
RW		 5227 (source
5228 (origin
5229 (method url-fetch)
5230 (uri
5231 (string-append "https://github.com/ncbi/sra-tools/archive/"
5232 version ".tar.gz"))
5233 (file-name (string-append name "-" version ".tar.gz"))
5234 (sha256
5235 (base32
79849358 5236 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
51c64999
RW		 5237 (build-system gnu-build-system)
5238 (arguments
5239 `(#:parallel-build? #f ; not supported
5240 #:tests? #f ; no "check" target
2320e76b 5241 #:make-flags
79849358
RW		 5242 (list (string-append "DEFAULT_CRT="
5243 (assoc-ref %build-inputs "ncbi-vdb")
5244 "/kfg/certs.kfg")
5245 (string-append "DEFAULT_KFG="
5246 (assoc-ref %build-inputs "ncbi-vdb")
5247 "/kfg/default.kfg")
5248 (string-append "VDB_LIBDIR="
2320e76b
RW		 5249 (assoc-ref %build-inputs "ncbi-vdb")
5250 ,(if (string-prefix? "x86_64"
5251 (or (%current-target-system)
5252 (%current-system)))
5253 "/lib64"
5254 "/lib32")))
51c64999 5255 #:phases
beebe431 5256 (modify-phases %standard-phases
0691851a
BW		 5257 (add-before 'configure 'set-perl-search-path
5258 (lambda _
5259 ;; Work around "dotless @INC" build failure.
5260 (setenv "PERL5LIB"
5261 (string-append (getcwd) "/setup:"
5262 (getenv "PERL5LIB")))
5263 #t))
beebe431
RW		 5264 (replace 'configure
5265 (lambda* (#:key inputs outputs #:allow-other-keys)
5266 ;; The build system expects a directory containing the sources and
5267 ;; raw build output of ncbi-vdb, including files that are not
5268 ;; installed. Since we are building against an installed version of
5269 ;; ncbi-vdb, the following modifications are needed.
5270 (substitute* "setup/konfigure.perl"
5271 ;; Make the configure script look for the "ilib" directory of
5272 ;; "ncbi-vdb" without first checking for the existence of a
5273 ;; matching library in its "lib" directory.
5274 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5275 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5276 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5277 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5278 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
51c64999 5279
beebe431
RW		 5280 ;; Dynamic linking
5281 (substitute* "tools/copycat/Makefile"
5282 (("smagic-static") "lmagic"))
2320e76b 5283
beebe431
RW		 5284 ;; The 'configure' script doesn't recognize things like
5285 ;; '--enable-fast-install'.
5286 (zero? (system*
5287 "./configure"
5288 (string-append "--build-prefix=" (getcwd) "/build")
5289 (string-append "--prefix=" (assoc-ref outputs "out"))
5290 (string-append "--debug")
5291 (string-append "--with-fuse-prefix="
5292 (assoc-ref inputs "fuse"))
5293 (string-append "--with-magic-prefix="
5294 (assoc-ref inputs "libmagic"))
5295 ;; TODO: building with libxml2 fails with linker errors
5296 ;; (string-append "--with-xml2-prefix="
5297 ;; (assoc-ref inputs "libxml2"))
5298 (string-append "--with-ncbi-vdb-sources="
5299 (assoc-ref inputs "ncbi-vdb"))
5300 (string-append "--with-ncbi-vdb-build="
5301 (assoc-ref inputs "ncbi-vdb"))
5302 (string-append "--with-ngs-sdk-prefix="
5303 (assoc-ref inputs "ngs-sdk"))
5304 (string-append "--with-hdf5-prefix="
1108a920
RW		 5305 (assoc-ref inputs "hdf5"))))))
5306 ;; This version of sra-tools fails to build with glibc because of a
5307 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5308 ;; contains a definition of "canonicalize", so we rename it.
5309 ;;
5310 ;; See upstream bug report:
5311 ;; https://github.com/ncbi/sra-tools/issues/67
5312 (add-after 'unpack 'patch-away-glibc-conflict
5313 (lambda _
5314 (substitute* "tools/bam-loader/bam.c"
5315 (("canonicalize\\(" line)
5316 (string-append "sra_tools_" line)))
5317 #t)))))
51c64999
RW		 5318 (native-inputs `(("perl" ,perl)))
5319 (inputs
5320 `(("ngs-sdk" ,ngs-sdk)
5321 ("ncbi-vdb" ,ncbi-vdb)
5322 ("libmagic" ,file)
5323 ("fuse" ,fuse)
5324 ("hdf5" ,hdf5)
5325 ("zlib" ,zlib)))
5326 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5327 (synopsis "Tools and libraries for reading and writing sequencing data")
5328 (description
5329 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5330reading of sequencing files from the Sequence Read Archive (SRA) database and
5331writing files into the .sra format.")
5332 (license license:public-domain)))
5333
d3517eda
RW		 5334(define-public seqan
5335 (package
5336 (name "seqan")
5337 (version "1.4.2")
5338 (source (origin
5339 (method url-fetch)
5340 (uri (string-append "http://packages.seqan.de/seqan-library/"
5341 "seqan-library-" version ".tar.bz2"))
5342 (sha256
5343 (base32
5344 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5345 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5346 ;; makes sense to split the outputs.
5347 (outputs '("out" "doc"))
5348 (build-system trivial-build-system)
5349 (arguments
5350 `(#:modules ((guix build utils))
5351 #:builder
5352 (begin
5353 (use-modules (guix build utils))
5354 (let ((tar (assoc-ref %build-inputs "tar"))
5355 (bzip (assoc-ref %build-inputs "bzip2"))
5356 (out (assoc-ref %outputs "out"))
5357 (doc (assoc-ref %outputs "doc")))
5358 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5359 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5360 (chdir (string-append "seqan-library-" ,version))
5361 (copy-recursively "include" (string-append out "/include"))
5362 (copy-recursively "share" (string-append doc "/share"))))))
5363 (native-inputs
5364 `(("source" ,source)
5365 ("tar" ,tar)
5366 ("bzip2" ,bzip2)))
5367 (home-page "http://www.seqan.de")
5368 (synopsis "Library for nucleotide sequence analysis")
5369 (description
5370 "SeqAn is a C++ library of efficient algorithms and data structures for
5371the analysis of sequences with the focus on biological data. It contains
5372algorithms and data structures for string representation and their
5373manipulation, online and indexed string search, efficient I/O of
5374bioinformatics file formats, sequence alignment, and more.")
5375 (license license:bsd-3)))
ce7155d5 5376
d708b7a9
BW		 5377(define-public seqmagick
5378 (package
5379 (name "seqmagick")
39fb853a 5380 (version "0.7.0")
d708b7a9
BW		 5381 (source
5382 (origin
5383 (method url-fetch)
f6e2d86f 5384 (uri (pypi-uri "seqmagick" version))
d708b7a9
BW		 5385 (sha256
5386 (base32
39fb853a 5387 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
d708b7a9 5388 (build-system python-build-system)
d708b7a9 5389 (inputs
39fb853a 5390 `(("python-biopython" ,python-biopython)))
d708b7a9 5391 (native-inputs
39fb853a 5392 `(("python-nose" ,python-nose)))
7bf837fd 5393 (home-page "https://github.com/fhcrc/seqmagick")
d708b7a9
BW		 5394 (synopsis "Tools for converting and modifying sequence files")
5395 (description
5396 "Bioinformaticians often have to convert sequence files between formats
5397and do little manipulations on them, and it's not worth writing scripts for
5398that. Seqmagick is a utility to expose the file format conversion in
5399BioPython in a convenient way. Instead of having a big mess of scripts, there
5400is one that takes arguments.")
5401 (license license:gpl3)))
5402
66daf78c
BW		 5403(define-public seqtk
5404 (package
5405 (name "seqtk")
5406 (version "1.2")
5407 (source (origin
5408 (method url-fetch)
5409 (uri (string-append
5410 "https://github.com/lh3/seqtk/archive/v"
5411 version ".tar.gz"))
5412 (file-name (string-append name "-" version ".tar.gz"))
5413 (sha256
5414 (base32
5415 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5416 (modules '((guix build utils)))
5417 (snippet
5418 '(begin
5419 ;; Remove extraneous header files, as is done in the seqtk
5420 ;; master branch.
5421 (for-each (lambda (file) (delete-file file))
5422 (list "ksort.h" "kstring.h" "kvec.h"))
5423 #t))))
5424 (build-system gnu-build-system)
5425 (arguments
5426 `(#:phases
5427 (modify-phases %standard-phases
5428 (delete 'configure)
5429 (replace 'check
5430 ;; There are no tests, so we just run a sanity check.
5431 (lambda _ (zero? (system* "./seqtk" "seq"))))
5432 (replace 'install
5433 (lambda* (#:key outputs #:allow-other-keys)
5434 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5435 (install-file "seqtk" bin)))))))
5436 (inputs
5437 `(("zlib" ,zlib)))
5438 (home-page "https://github.com/lh3/seqtk")
5439 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5440 (description
5441 "Seqtk is a fast and lightweight tool for processing sequences in the
5442FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5443optionally compressed by gzip.")
5444 (license license:expat)))
5445
5f7e17be
BW		 5446(define-public snap-aligner
5447 (package
5448 (name "snap-aligner")
5449 (version "1.0beta.18")
5450 (source (origin
5451 (method url-fetch)
5452 (uri (string-append
5453 "https://github.com/amplab/snap/archive/v"
5454 version ".tar.gz"))
5455 (file-name (string-append name "-" version ".tar.gz"))
5456 (sha256
5457 (base32
5458 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5459 (build-system gnu-build-system)
5460 (arguments
5461 '(#:phases
5462 (modify-phases %standard-phases
5463 (delete 'configure)
5464 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5465 (replace 'install
5466 (lambda* (#:key outputs #:allow-other-keys)
5467 (let* ((out (assoc-ref outputs "out"))
5468 (bin (string-append out "/bin")))
5f7e17be
BW		 5469 (install-file "snap-aligner" bin)
5470 (install-file "SNAPCommand" bin)
5471 #t))))))
5472 (native-inputs
5473 `(("zlib" ,zlib)))
5474 (home-page "http://snap.cs.berkeley.edu/")
5475 (synopsis "Short read DNA sequence aligner")
5476 (description
5477 "SNAP is a fast and accurate aligner for short DNA reads. It is
5478optimized for modern read lengths of 100 bases or higher, and takes advantage
5479of these reads to align data quickly through a hash-based indexing scheme.")
3e6fdd5f
EF		 5480 ;; 32-bit systems are not supported by the unpatched code.
5481 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5482 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5483 ;; systems without a lot of memory cannot make good use of this program.
5484 (supported-systems '("x86_64-linux"))
5f7e17be
BW		 5485 (license license:asl2.0)))
5486
bcadaf00
BW		 5487(define-public sortmerna
5488 (package
5489 (name "sortmerna")
849485f5 5490 (version "2.1b")
bcadaf00
BW		 5491 (source
5492 (origin
5493 (method url-fetch)
5494 (uri (string-append
5495 "https://github.com/biocore/sortmerna/archive/"
5496 version ".tar.gz"))
5497 (file-name (string-append name "-" version ".tar.gz"))
5498 (sha256
5499 (base32
849485f5 5500 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
bcadaf00
BW		 5501 (build-system gnu-build-system)
5502 (outputs '("out" ;for binaries
5503 "db")) ;for sequence databases
5504 (arguments
5505 `(#:phases
5506 (modify-phases %standard-phases
5507 (replace 'install
5508 (lambda* (#:key outputs #:allow-other-keys)
5509 (let* ((out (assoc-ref outputs "out"))
5510 (bin (string-append out "/bin"))
5511 (db (assoc-ref outputs "db"))
5512 (share
5513 (string-append db "/share/sortmerna/rRNA_databases")))
5514 (install-file "sortmerna" bin)
5515 (install-file "indexdb_rna" bin)
5516 (for-each (lambda (file)
5517 (install-file file share))
5518 (find-files "rRNA_databases" ".*fasta"))
5519 #t))))))
849485f5
BW		 5520 (inputs
5521 `(("zlib" ,zlib)))
bcadaf00
BW		 5522 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5523 (synopsis "Biological sequence analysis tool for NGS reads")
5524 (description
5525 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5526and operational taxonomic unit (OTU) picking of next generation
5527sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5528allows for fast and sensitive analyses of nucleotide sequences. The main
5529application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
2324541b
EF		 5530 ;; The source includes x86 specific code
5531 (supported-systems '("x86_64-linux" "i686-linux"))
bcadaf00
BW		 5532 (license license:lgpl3)))
5533
ce7155d5
RW		 5534(define-public star
5535 (package
5536 (name "star")
939b6b11 5537 (version "2.5.3a")
ce7155d5
RW		 5538 (source (origin
5539 (method url-fetch)
3062d750
RW		 5540 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5541 version ".tar.gz"))
5542 (file-name (string-append name "-" version ".tar.gz"))
ce7155d5
RW		 5543 (sha256
5544 (base32
939b6b11 5545 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
ce7155d5
RW		 5546 (modules '((guix build utils)))
5547 (snippet
3062d750
RW		 5548 '(begin
5549 (substitute* "source/Makefile"
5550 (("/bin/rm") "rm"))
5551 ;; Remove pre-built binaries and bundled htslib sources.
5552 (delete-file-recursively "bin/MacOSX_x86_64")
5553 (delete-file-recursively "bin/Linux_x86_64")
c9e9154e 5554 (delete-file-recursively "bin/Linux_x86_64_static")
3062d750
RW		 5555 (delete-file-recursively "source/htslib")
5556 #t))))
ce7155d5
RW		 5557 (build-system gnu-build-system)
5558 (arguments
5559 '(#:tests? #f ;no check target
5560 #:make-flags '("STAR")
5561 #:phases
c0266e8d
RW		 5562 (modify-phases %standard-phases
5563 (add-after 'unpack 'enter-source-dir
5564 (lambda _ (chdir "source") #t))
3062d750
RW		 5565 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5566 (lambda _
5567 (substitute* "Makefile"
5568 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5569 _ prefix) prefix))
5570 (substitute* '("BAMfunctions.cpp"
5571 "signalFromBAM.h"
5572 "bam_cat.h"
5573 "bam_cat.c"
5574 "STAR.cpp"
5575 "bamRemoveDuplicates.cpp")
5576 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5577 (string-append "#include <" header ">")))
5578 (substitute* "IncludeDefine.h"
5579 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5580 (string-append "<" header ">")))
5581 #t))
c0266e8d
RW		 5582 (replace 'install
5583 (lambda* (#:key outputs #:allow-other-keys)
5584 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5585 (install-file "STAR" bin))
5586 #t))
5587 (delete 'configure))))
ce7155d5 5588 (native-inputs
9fc513ad 5589 `(("xxd" ,xxd)))
ce7155d5 5590 (inputs
3062d750
RW		 5591 `(("htslib" ,htslib)
5592 ("zlib" ,zlib)))
ce7155d5
RW		 5593 (home-page "https://github.com/alexdobin/STAR")
5594 (synopsis "Universal RNA-seq aligner")
5595 (description
5596 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5597based on a previously undescribed RNA-seq alignment algorithm that uses
5598sequential maximum mappable seed search in uncompressed suffix arrays followed
5599by seed clustering and stitching procedure. In addition to unbiased de novo
5600detection of canonical junctions, STAR can discover non-canonical splices and
5601chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5602sequences.")
c11f79a4
BW		 5603 ;; Only 64-bit systems are supported according to the README.
5604 (supported-systems '("x86_64-linux" "mips64el-linux"))
ce7155d5
RW		 5605 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5606 (license license:gpl3+)))
de07c0db 5607
dbf4ed7c
RW		 5608(define-public subread
5609 (package
5610 (name "subread")
e6debcaf 5611 (version "1.6.0")
dbf4ed7c
RW		 5612 (source (origin
5613 (method url-fetch)
de67e922
LF		 5614 (uri (string-append "mirror://sourceforge/subread/subread-"
5615 version "/subread-" version "-source.tar.gz"))
dbf4ed7c
RW		 5616 (sha256
5617 (base32
e6debcaf 5618 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
dbf4ed7c
RW		 5619 (build-system gnu-build-system)
5620 (arguments
5621 `(#:tests? #f ;no "check" target
104c1986
RW		 5622 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5623 ;; optimizations by default, so we override these flags such that x86_64
5624 ;; flags are only added when the build target is an x86_64 system.
5625 #:make-flags
5626 (list (let ((system ,(or (%current-target-system)
5627 (%current-system)))
5628 (flags '("-ggdb" "-fomit-frame-pointer"
5629 "-ffast-math" "-funroll-loops"
5630 "-fmessage-length=0"
5631 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5632 "-DMAKE_STANDALONE"
5633 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5634 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5635 (if (string-prefix? "x86_64" system)
5636 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5637 (string-append "CCFLAGS=" (string-join flags))))
5638 "-f" "Makefile.Linux"
5639 "CC=gcc ${CCFLAGS}")
dbf4ed7c 5640 #:phases
dc1d3cde
KK		 5641 (modify-phases %standard-phases
5642 (add-after 'unpack 'enter-dir
5643 (lambda _ (chdir "src") #t))
5644 (replace 'install
5645 (lambda* (#:key outputs #:allow-other-keys)
5646 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5647 (mkdir-p bin)
5648 (copy-recursively "../bin" bin))))
dbf4ed7c 5649 ;; no "configure" script
dc1d3cde 5650 (delete 'configure))))
dbf4ed7c
RW		 5651 (inputs `(("zlib" ,zlib)))
5652 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5653 (synopsis "Tool kit for processing next-gen sequencing data")
5654 (description
5655 "The subread package contains the following tools: subread aligner, a
5656general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5657and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5658features; exactSNP: a SNP caller that discovers SNPs by testing signals
5659against local background noises.")
5660 (license license:gpl3+)))
5661
d15d981e
RW		 5662(define-public stringtie
5663 (package
5664 (name "stringtie")
5665 (version "1.2.1")
5666 (source (origin
5667 (method url-fetch)
5668 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5669 "stringtie-" version ".tar.gz"))
5670 (sha256
5671 (base32
5672 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5673 (modules '((guix build utils)))
5674 (snippet
5675 '(begin
5676 (delete-file-recursively "samtools-0.1.18")
5677 #t))))
5678 (build-system gnu-build-system)
5679 (arguments
5680 `(#:tests? #f ;no test suite
5681 #:phases
5682 (modify-phases %standard-phases
5683 ;; no configure script
5684 (delete 'configure)
5685 (add-before 'build 'use-system-samtools
5686 (lambda _
5687 (substitute* "Makefile"
5688 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5689 "stringtie: "))
5690 (substitute* '("gclib/GBam.h"
5691 "gclib/GBam.cpp")
5692 (("#include \"(bam|sam|kstring).h\"" _ header)
5693 (string-append "#include <samtools/" header ".h>")))
5694 #t))
0d2c0562
RW		 5695 (add-after 'unpack 'remove-duplicate-typedef
5696 (lambda _
5697 ;; This typedef conflicts with the typedef in
5698 ;; glibc-2.25/include/bits/types.h
5699 (substitute* "gclib/GThreads.h"
5700 (("typedef long long __intmax_t;") ""))
5701 #t))
d15d981e
RW		 5702 (replace 'install
5703 (lambda* (#:key outputs #:allow-other-keys)
5704 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5705 (install-file "stringtie" bin)
5706 #t))))))
5707 (inputs
5708 `(("samtools" ,samtools-0.1)
5709 ("zlib" ,zlib)))
5710 (home-page "http://ccb.jhu.edu/software/stringtie/")
5711 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5712 (description
5713 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5714alignments into potential transcripts. It uses a novel network flow algorithm
5715as well as an optional de novo assembly step to assemble and quantitate
5716full-length transcripts representing multiple splice variants for each gene
5717locus. Its input can include not only the alignments of raw reads used by
5718other transcript assemblers, but also alignments of longer sequences that have
5719been assembled from those reads. To identify differentially expressed genes
5720between experiments, StringTie's output can be processed either by the
5721Cuffdiff or Ballgown programs.")
5722 (license license:artistic2.0)))
5723
ad0ae297
BW		 5724(define-public taxtastic
5725 (package
5726 (name "taxtastic")
3cbfc149 5727 (version "0.6.4")
ad0ae297
BW		 5728 (source (origin
5729 (method url-fetch)
3cbfc149 5730 (uri (pypi-uri "taxtastic" version))
ad0ae297
BW		 5731 (sha256
5732 (base32
3cbfc149 5733 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
ad0ae297
BW		 5734 (build-system python-build-system)
5735 (arguments
5736 `(#:python ,python-2
5737 #:phases
5738 (modify-phases %standard-phases
5739 (replace 'check
5740 (lambda _
5741 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5742 (propagated-inputs
5743 `(("python-sqlalchemy" ,python2-sqlalchemy)
5744 ("python-decorator" ,python2-decorator)
5745 ("python-biopython" ,python2-biopython)
5746 ("python-pandas" ,python2-pandas)))
5747 (home-page "https://github.com/fhcrc/taxtastic")
5748 (synopsis "Tools for taxonomic naming and annotation")
5749 (description
5750 "Taxtastic is software written in python used to build and maintain
5751reference packages i.e. collections of reference trees, reference alignments,
5752profiles, and associated taxonomic information.")
5753 (license license:gpl3+)))
5754
de07c0db
RW		 5755(define-public vcftools
5756 (package
5757 (name "vcftools")
f4322542 5758 (version "0.1.15")
de07c0db
RW		 5759 (source (origin
5760 (method url-fetch)
5761 (uri (string-append
9b36e256
RJ		 5762 "https://github.com/vcftools/vcftools/releases/download/v"
5763 version "/vcftools-" version ".tar.gz"))
de07c0db
RW		 5764 (sha256
5765 (base32
f4322542 5766 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
de07c0db
RW		 5767 (build-system gnu-build-system)
5768 (arguments
5769 `(#:tests? #f ; no "check" target
5770 #:make-flags (list
7c3958e1 5771 "CFLAGS=-O2" ; override "-m64" flag
de07c0db
RW		 5772 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5773 (string-append "MANDIR=" (assoc-ref %outputs "out")
9b36e256
RJ		 5774 "/share/man/man1"))))
5775 (native-inputs
5776 `(("pkg-config" ,pkg-config)))
de07c0db
RW		 5777 (inputs
5778 `(("perl" ,perl)
5779 ("zlib" ,zlib)))
9b36e256 5780 (home-page "https://vcftools.github.io/")
de07c0db
RW		 5781 (synopsis "Tools for working with VCF files")
5782 (description
5783 "VCFtools is a program package designed for working with VCF files, such
5784as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5785provide easily accessible methods for working with complex genetic variation
5786data in the form of VCF files.")
5787 ;; The license is declared as LGPLv3 in the README and
9b36e256 5788 ;; at https://vcftools.github.io/license.html
de07c0db 5789 (license license:lgpl3)))
9c38b540 5790
35aa90a1
RW		 5791(define-public infernal
5792 (package
5793 (name "infernal")
5794 (version "1.1.2")
5795 (source (origin
5796 (method url-fetch)
5797 (uri (string-append "http://eddylab.org/software/infernal/"
5798 "infernal-" version ".tar.gz"))
5799 (sha256
5800 (base32
5801 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5802 (build-system gnu-build-system)
5803 (native-inputs
5804 `(("perl" ,perl))) ; for tests
5805 (home-page "http://eddylab.org/infernal/")
5806 (synopsis "Inference of RNA alignments")
5807 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5808searching DNA sequence databases for RNA structure and sequence similarities.
5809It is an implementation of a special case of profile stochastic context-free
5810grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5811profile, but it scores a combination of sequence consensus and RNA secondary
5812structure consensus, so in many cases, it is more capable of identifying RNA
5813homologs that conserve their secondary structure more than their primary
5814sequence.")
48409ef2
EF		 5815 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5816 (supported-systems '("i686-linux" "x86_64-linux"))
35aa90a1
RW		 5817 (license license:bsd-3)))
5818
b91cfa22
RW		 5819(define-public r-centipede
5820 (package
5821 (name "r-centipede")
5822 (version "1.2")
5823 (source (origin
5824 (method url-fetch)
5825 (uri (string-append "http://download.r-forge.r-project.org/"
5826 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5827 (sha256
5828 (base32
5829 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5830 (build-system r-build-system)
5831 (home-page "http://centipede.uchicago.edu/")
5832 (synopsis "Predict transcription factor binding sites")
5833 (description
5834 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5835of the genome that are bound by particular transcription factors. It starts
5836by identifying a set of candidate binding sites, and then aims to classify the
5837sites according to whether each site is bound or not bound by a transcription
5838factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5839between two different types of motif instances using as much relevant
5840information as possible.")
5841 (license (list license:gpl2+ license:gpl3+))))
5842
7b3df1e5
BW		 5843(define-public r-vegan
5844 (package
5845 (name "r-vegan")
8d11ef44 5846 (version "2.4-5")
7b3df1e5
BW		 5847 (source
5848 (origin
5849 (method url-fetch)
5850 (uri (cran-uri "vegan" version))
5851 (sha256
5852 (base32
8d11ef44 5853 "0cyyvn3xsjn24w590jn6z4xajafv7yzvj6c51vqi9q6m8v5831ya"))))
7b3df1e5 5854 (build-system r-build-system)
7b3df1e5 5855 (native-inputs
db2e4386 5856 `(("gfortran" ,gfortran)))
7b3df1e5
BW		 5857 (propagated-inputs
5858 `(("r-cluster" ,r-cluster)
5859 ("r-lattice" ,r-lattice)
aeb64f3c 5860 ("r-mass" ,r-mass)
7b3df1e5
BW		 5861 ("r-mgcv" ,r-mgcv)
5862 ("r-permute" ,r-permute)))
5863 (home-page "https://cran.r-project.org/web/packages/vegan")
5864 (synopsis "Functions for community ecology")
5865 (description
5866 "The vegan package provides tools for descriptive community ecology. It
5867has most basic functions of diversity analysis, community ordination and
5868dissimilarity analysis. Most of its multivariate tools can be used for other
5869data types as well.")
5870 (license license:gpl2+)))
5871
8c6de588
RW		 5872(define-public r-annotate
5873 (package
5874 (name "r-annotate")
654c29ac 5875 (version "1.56.1")
8c6de588
RW		 5876 (source
5877 (origin
5878 (method url-fetch)
5879 (uri (bioconductor-uri "annotate" version))
5880 (sha256
5881 (base32
654c29ac 5882 "14c5xd9kasvcwg5gbjys2c1vizxhlqlzxakqc2kml0kw97hmx0rq"))))
8c6de588
RW		 5883 (build-system r-build-system)
5884 (propagated-inputs
5885 `(("r-annotationdbi" ,r-annotationdbi)
5886 ("r-biobase" ,r-biobase)
5887 ("r-biocgenerics" ,r-biocgenerics)
5888 ("r-dbi" ,r-dbi)
d0f0579e 5889 ("r-rcurl" ,r-rcurl)
8c6de588
RW		 5890 ("r-xml" ,r-xml)
5891 ("r-xtable" ,r-xtable)))
5892 (home-page
5713bbf1 5893 "https://bioconductor.org/packages/annotate")
8c6de588 5894 (synopsis "Annotation for microarrays")
d1e4ad1b 5895 (description "This package provides R environments for the annotation of
8c6de588
RW		 5896microarrays.")
5897 (license license:artistic2.0)))
5898
efa6a1dd
RJ		 5899(define-public r-copynumber
5900 (package
5901 (name "r-copynumber")
5902 (version "1.18.0")
5903 (source (origin
5904 (method url-fetch)
5905 (uri (bioconductor-uri "copynumber" version))
5906 (sha256
5907 (base32
5908 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
5909 (build-system r-build-system)
5910 (propagated-inputs
5911 `(("r-s4vectors" ,r-s4vectors)
5912 ("r-iranges" ,r-iranges)
5913 ("r-genomicranges" ,r-genomicranges)
5914 ("r-biocgenerics" ,r-biocgenerics)))
5915 (home-page "https://bioconductor.org/packages/copynumber")
5916 (synopsis "Segmentation of single- and multi-track copy number data")
5917 (description
5918 "This package segments single- and multi-track copy number data by a
5919penalized least squares regression method.")
5920 (license license:artistic2.0)))
5921
07a664cd
RW		 5922(define-public r-geneplotter
5923 (package
5924 (name "r-geneplotter")
cb4d3ff2 5925 (version "1.56.0")
07a664cd
RW		 5926 (source
5927 (origin
5928 (method url-fetch)
5929 (uri (bioconductor-uri "geneplotter" version))
5930 (sha256
5931 (base32
cb4d3ff2 5932 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
07a664cd
RW		 5933 (build-system r-build-system)
5934 (propagated-inputs
5935 `(("r-annotate" ,r-annotate)
5936 ("r-annotationdbi" ,r-annotationdbi)
5937 ("r-biobase" ,r-biobase)
5938 ("r-biocgenerics" ,r-biocgenerics)
5939 ("r-lattice" ,r-lattice)
5940 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5713bbf1 5941 (home-page "https://bioconductor.org/packages/geneplotter")
07a664cd
RW		 5942 (synopsis "Graphics functions for genomic data")
5943 (description
5944 "This package provides functions for plotting genomic data.")
5945 (license license:artistic2.0)))
5946
2301fd3e
RW		 5947(define-public r-genefilter
5948 (package
5949 (name "r-genefilter")
554fac74 5950 (version "1.60.0")
2301fd3e
RW		 5951 (source
5952 (origin
5953 (method url-fetch)
5954 (uri (bioconductor-uri "genefilter" version))
5955 (sha256
5956 (base32
554fac74 5957 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
2301fd3e
RW		 5958 (build-system r-build-system)
5959 (native-inputs
5960 `(("gfortran" ,gfortran)))
5961 (propagated-inputs
5962 `(("r-annotate" ,r-annotate)
5963 ("r-annotationdbi" ,r-annotationdbi)
5964 ("r-biobase" ,r-biobase)
aeb64f3c
RW		 5965 ("r-s4vectors" ,r-s4vectors)
5966 ("r-survival" ,r-survival)))
5713bbf1 5967 (home-page "https://bioconductor.org/packages/genefilter")
2301fd3e
RW		 5968 (synopsis "Filter genes from high-throughput experiments")
5969 (description
5970 "This package provides basic functions for filtering genes from
5971high-throughput sequencing experiments.")
5972 (license license:artistic2.0)))
5973
ad34f0ac
RW		 5974(define-public r-deseq2
5975 (package
5976 (name "r-deseq2")
058644c0 5977 (version "1.18.1")
ad34f0ac
RW		 5978 (source
5979 (origin
5980 (method url-fetch)
5981 (uri (bioconductor-uri "DESeq2" version))
5982 (sha256
5983 (base32
058644c0 5984 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
ad34f0ac
RW		 5985 (properties `((upstream-name . "DESeq2")))
5986 (build-system r-build-system)
ad34f0ac
RW		 5987 (propagated-inputs
5988 `(("r-biobase" ,r-biobase)
5989 ("r-biocgenerics" ,r-biocgenerics)
5990 ("r-biocparallel" ,r-biocparallel)
5991 ("r-genefilter" ,r-genefilter)
5992 ("r-geneplotter" ,r-geneplotter)
5993 ("r-genomicranges" ,r-genomicranges)
5994 ("r-ggplot2" ,r-ggplot2)
5995 ("r-hmisc" ,r-hmisc)
5996 ("r-iranges" ,r-iranges)
5997 ("r-locfit" ,r-locfit)
5998 ("r-rcpp" ,r-rcpp)
5999 ("r-rcpparmadillo" ,r-rcpparmadillo)
6000 ("r-s4vectors" ,r-s4vectors)
6001 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5713bbf1 6002 (home-page "https://bioconductor.org/packages/DESeq2")
ad34f0ac
RW		 6003 (synopsis "Differential gene expression analysis")
6004 (description
6005 "This package provides functions to estimate variance-mean dependence in
6006count data from high-throughput nucleotide sequencing assays and test for
6007differential expression based on a model using the negative binomial
6008distribution.")
6009 (license license:lgpl3+)))
6010
86763fdd
RW		 6011(define-public r-dexseq
6012 (package
6013 (name "r-dexseq")
756ac725 6014 (version "1.24.2")
86763fdd
RW		 6015 (source
6016 (origin
6017 (method url-fetch)
6018 (uri (bioconductor-uri "DEXSeq" version))
6019 (sha256
6020 (base32
756ac725 6021 "18nh8ynxirfwkmc4sawdxgl7w1sl9ny5zpv8zbhv9vi5vgb8pxmj"))))
86763fdd
RW		 6022 (properties `((upstream-name . "DEXSeq")))
6023 (build-system r-build-system)
6024 (propagated-inputs
6025 `(("r-annotationdbi" ,r-annotationdbi)
6026 ("r-biobase" ,r-biobase)
6027 ("r-biocgenerics" ,r-biocgenerics)
6028 ("r-biocparallel" ,r-biocparallel)
6029 ("r-biomart" ,r-biomart)
6030 ("r-deseq2" ,r-deseq2)
6031 ("r-genefilter" ,r-genefilter)
6032 ("r-geneplotter" ,r-geneplotter)
6033 ("r-genomicranges" ,r-genomicranges)
6034 ("r-hwriter" ,r-hwriter)
6035 ("r-iranges" ,r-iranges)
6036 ("r-rcolorbrewer" ,r-rcolorbrewer)
6037 ("r-rsamtools" ,r-rsamtools)
6038 ("r-s4vectors" ,r-s4vectors)
6039 ("r-statmod" ,r-statmod)
6040 ("r-stringr" ,r-stringr)
6041 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5713bbf1 6042 (home-page "https://bioconductor.org/packages/DEXSeq")
86763fdd
RW		 6043 (synopsis "Inference of differential exon usage in RNA-Seq")
6044 (description
6045 "This package is focused on finding differential exon usage using RNA-seq
6046exon counts between samples with different experimental designs. It provides
6047functions that allows the user to make the necessary statistical tests based
6048on a model that uses the negative binomial distribution to estimate the
6049variance between biological replicates and generalized linear models for
6050testing. The package also provides functions for the visualization and
6051exploration of the results.")
6052 (license license:gpl3+)))
6053
e8163773
RW		 6054(define-public r-annotationforge
6055 (package
6056 (name "r-annotationforge")
727706ad 6057 (version "1.20.0")
e8163773
RW		 6058 (source
6059 (origin
6060 (method url-fetch)
6061 (uri (bioconductor-uri "AnnotationForge" version))
6062 (sha256
6063 (base32
727706ad 6064 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
e8163773
RW		 6065 (properties
6066 `((upstream-name . "AnnotationForge")))
6067 (build-system r-build-system)
6068 (propagated-inputs
6069 `(("r-annotationdbi" ,r-annotationdbi)
6070 ("r-biobase" ,r-biobase)
6071 ("r-biocgenerics" ,r-biocgenerics)
6072 ("r-dbi" ,r-dbi)
55cd914c 6073 ("r-rcurl" ,r-rcurl)
e8163773
RW		 6074 ("r-rsqlite" ,r-rsqlite)
6075 ("r-s4vectors" ,r-s4vectors)
6076 ("r-xml" ,r-xml)))
5713bbf1 6077 (home-page "https://bioconductor.org/packages/AnnotationForge")
e8163773
RW		 6078 (synopsis "Code for building annotation database packages")
6079 (description
6080 "This package provides code for generating Annotation packages and their
6081databases. Packages produced are intended to be used with AnnotationDbi.")
6082 (license license:artistic2.0)))
6083
cd9e7dc7
RW		 6084(define-public r-rbgl
6085 (package
6086 (name "r-rbgl")
c25154e5 6087 (version "1.54.0")
cd9e7dc7
RW		 6088 (source
6089 (origin
6090 (method url-fetch)
6091 (uri (bioconductor-uri "RBGL" version))
6092 (sha256
6093 (base32
c25154e5 6094 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
cd9e7dc7
RW		 6095 (properties `((upstream-name . "RBGL")))
6096 (build-system r-build-system)
6097 (propagated-inputs `(("r-graph" ,r-graph)))
5713bbf1 6098 (home-page "https://www.bioconductor.org/packages/RBGL")
cd9e7dc7
RW		 6099 (synopsis "Interface to the Boost graph library")
6100 (description
6101 "This package provides a fairly extensive and comprehensive interface to
6102the graph algorithms contained in the Boost library.")
6103 (license license:artistic2.0)))
6104
ad740ff8
RW		 6105(define-public r-gseabase
6106 (package
6107 (name "r-gseabase")
4220ab0c 6108 (version "1.40.1")
ad740ff8
RW		 6109 (source
6110 (origin
6111 (method url-fetch)
6112 (uri (bioconductor-uri "GSEABase" version))
6113 (sha256
6114 (base32
4220ab0c 6115 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
ad740ff8
RW		 6116 (properties `((upstream-name . "GSEABase")))
6117 (build-system r-build-system)
6118 (propagated-inputs
6119 `(("r-annotate" ,r-annotate)
6120 ("r-annotationdbi" ,r-annotationdbi)
6121 ("r-biobase" ,r-biobase)
6122 ("r-biocgenerics" ,r-biocgenerics)
6123 ("r-graph" ,r-graph)
6124 ("r-xml" ,r-xml)))
5713bbf1 6125 (home-page "https://bioconductor.org/packages/GSEABase")
ad740ff8
RW		 6126 (synopsis "Gene set enrichment data structures and methods")
6127 (description
6128 "This package provides classes and methods to support @dfn{Gene Set
6129Enrichment Analysis} (GSEA).")
6130 (license license:artistic2.0)))
6131
1a1931f7
RW		 6132(define-public r-category
6133 (package
6134 (name "r-category")
2404cc42 6135 (version "2.44.0")
1a1931f7
RW		 6136 (source
6137 (origin
6138 (method url-fetch)
6139 (uri (bioconductor-uri "Category" version))
6140 (sha256
6141 (base32
2404cc42 6142 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
1a1931f7
RW		 6143 (properties `((upstream-name . "Category")))
6144 (build-system r-build-system)
6145 (propagated-inputs
6146 `(("r-annotate" ,r-annotate)
6147 ("r-annotationdbi" ,r-annotationdbi)
6148 ("r-biobase" ,r-biobase)
6149 ("r-biocgenerics" ,r-biocgenerics)
6150 ("r-genefilter" ,r-genefilter)
6151 ("r-graph" ,r-graph)
6152 ("r-gseabase" ,r-gseabase)
6153 ("r-matrix" ,r-matrix)
6154 ("r-rbgl" ,r-rbgl)
2404cc42 6155 ("r-dbi" ,r-dbi)))
5713bbf1 6156 (home-page "https://bioconductor.org/packages/Category")
1a1931f7
RW		 6157 (synopsis "Category analysis")
6158 (description
6159 "This package provides a collection of tools for performing category
6160analysis.")
6161 (license license:artistic2.0)))
6162
89f40c5e
RW		 6163(define-public r-gostats
6164 (package
6165 (name "r-gostats")
eb3f5cc7 6166 (version "2.44.0")
89f40c5e
RW		 6167 (source
6168 (origin
6169 (method url-fetch)
6170 (uri (bioconductor-uri "GOstats" version))
6171 (sha256
6172 (base32
eb3f5cc7 6173 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
89f40c5e
RW		 6174 (properties `((upstream-name . "GOstats")))
6175 (build-system r-build-system)
6176 (propagated-inputs
6177 `(("r-annotate" ,r-annotate)
6178 ("r-annotationdbi" ,r-annotationdbi)
6179 ("r-annotationforge" ,r-annotationforge)
6180 ("r-biobase" ,r-biobase)
6181 ("r-category" ,r-category)
6182 ("r-go-db" ,r-go-db)
6183 ("r-graph" ,r-graph)
eb3f5cc7 6184 ("r-rgraphviz" ,r-rgraphviz)
89f40c5e 6185 ("r-rbgl" ,r-rbgl)))
5713bbf1 6186 (home-page "https://bioconductor.org/packages/GOstats")
89f40c5e
RW		 6187 (synopsis "Tools for manipulating GO and microarrays")
6188 (description
6189 "This package provides a set of tools for interacting with GO and
6190microarray data. A variety of basic manipulation tools for graphs, hypothesis
6191testing and other simple calculations.")
6192 (license license:artistic2.0)))
6193
cb99d457
RW		 6194(define-public r-shortread
6195 (package
6196 (name "r-shortread")
843826e2 6197 (version "1.36.0")
cb99d457
RW		 6198 (source
6199 (origin
6200 (method url-fetch)
6201 (uri (bioconductor-uri "ShortRead" version))
6202 (sha256
6203 (base32
843826e2 6204 "06mknlsmd4hnaxzdjapgvp2kgdnf9w103y500dsac5jgsz4vwzcz"))))
cb99d457
RW		 6205 (properties `((upstream-name . "ShortRead")))
6206 (build-system r-build-system)
6207 (inputs
6208 `(("zlib" ,zlib)))
6209 (propagated-inputs
6210 `(("r-biobase" ,r-biobase)
6211 ("r-biocgenerics" ,r-biocgenerics)
6212 ("r-biocparallel" ,r-biocparallel)
6213 ("r-biostrings" ,r-biostrings)
6214 ("r-genomeinfodb" ,r-genomeinfodb)
6215 ("r-genomicalignments" ,r-genomicalignments)
6216 ("r-genomicranges" ,r-genomicranges)
6217 ("r-hwriter" ,r-hwriter)
6218 ("r-iranges" ,r-iranges)
6219 ("r-lattice" ,r-lattice)
6220 ("r-latticeextra" ,r-latticeextra)
6221 ("r-rsamtools" ,r-rsamtools)
6222 ("r-s4vectors" ,r-s4vectors)
6223 ("r-xvector" ,r-xvector)
6224 ("r-zlibbioc" ,r-zlibbioc)))
5713bbf1 6225 (home-page "https://bioconductor.org/packages/ShortRead")
cb99d457
RW		 6226 (synopsis "FASTQ input and manipulation tools")
6227 (description
6228 "This package implements sampling, iteration, and input of FASTQ files.
6229It includes functions for filtering and trimming reads, and for generating a
6230quality assessment report. Data are represented as
6231@code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6232purposes. The package also contains legacy support for early single-end,
6233ungapped alignment formats.")
6234 (license license:artistic2.0)))
6235
7f903d73
RW		 6236(define-public r-systempiper
6237 (package
6238 (name "r-systempiper")
b5375525 6239 (version "1.12.0")
7f903d73
RW		 6240 (source
6241 (origin
6242 (method url-fetch)
6243 (uri (bioconductor-uri "systemPipeR" version))
6244 (sha256
6245 (base32
b5375525 6246 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
7f903d73
RW		 6247 (properties `((upstream-name . "systemPipeR")))
6248 (build-system r-build-system)
6249 (propagated-inputs
6250 `(("r-annotate" ,r-annotate)
6251 ("r-batchjobs" ,r-batchjobs)
6252 ("r-biocgenerics" ,r-biocgenerics)
6253 ("r-biostrings" ,r-biostrings)
6254 ("r-deseq2" ,r-deseq2)
6255 ("r-edger" ,r-edger)
6256 ("r-genomicfeatures" ,r-genomicfeatures)
6257 ("r-genomicranges" ,r-genomicranges)
6258 ("r-ggplot2" ,r-ggplot2)
6259 ("r-go-db" ,r-go-db)
6260 ("r-gostats" ,r-gostats)
6261 ("r-limma" ,r-limma)
6262 ("r-pheatmap" ,r-pheatmap)
6263 ("r-rjson" ,r-rjson)
6264 ("r-rsamtools" ,r-rsamtools)
6265 ("r-shortread" ,r-shortread)
6266 ("r-summarizedexperiment" ,r-summarizedexperiment)
6267 ("r-variantannotation" ,r-variantannotation)))
6268 (home-page "https://github.com/tgirke/systemPipeR")
6269 (synopsis "Next generation sequencing workflow and reporting environment")
6270 (description
6271 "This R package provides tools for building and running automated
6272end-to-end analysis workflows for a wide range of @dfn{next generation
6273sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6274Important features include a uniform workflow interface across different NGS
6275applications, automated report generation, and support for running both R and
6276command-line software, such as NGS aligners or peak/variant callers, on local
6277computers or compute clusters. Efficient handling of complex sample sets and
6278experimental designs is facilitated by a consistently implemented sample
6279annotation infrastructure.")
6280 (license license:artistic2.0)))
6281
684f29bd
RW		 6282(define-public r-grohmm
6283 (package
6284 (name "r-grohmm")
704fe4d1 6285 (version "1.12.0")
684f29bd
RW		 6286 (source
6287 (origin
6288 (method url-fetch)
6289 (uri (bioconductor-uri "groHMM" version))
6290 (sha256
6291 (base32
704fe4d1 6292 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
684f29bd
RW		 6293 (properties `((upstream-name . "groHMM")))
6294 (build-system r-build-system)
6295 (propagated-inputs
6296 `(("r-genomeinfodb" ,r-genomeinfodb)
6297 ("r-genomicalignments" ,r-genomicalignments)
6298 ("r-genomicranges" ,r-genomicranges)
6299 ("r-iranges" ,r-iranges)
aeb64f3c 6300 ("r-mass" ,r-mass)
684f29bd
RW		 6301 ("r-rtracklayer" ,r-rtracklayer)
6302 ("r-s4vectors" ,r-s4vectors)))
6303 (home-page "https://github.com/Kraus-Lab/groHMM")
6304 (synopsis "GRO-seq analysis pipeline")
6305 (description
6306 "This package provides a pipeline for the analysis of GRO-seq data.")
6307 (license license:gpl3+)))
6308
f3cfe451
RW		 6309(define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6310 (package
6311 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6312 (version "3.2.2")
6313 (source (origin
6314 (method url-fetch)
6315 ;; We cannot use bioconductor-uri here because this tarball is
6316 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 6317 (uri (string-append "https://bioconductor.org/packages/"
f3cfe451
RW		 6318 "release/data/annotation/src/contrib"
6319 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6320 version ".tar.gz"))
6321 (sha256
6322 (base32
6323 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6324 (properties
6325 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6326 (build-system r-build-system)
6327 ;; As this package provides little more than a very large data file it
6328 ;; doesn't make sense to build substitutes.
6329 (arguments `(#:substitutable? #f))
6330 (propagated-inputs
6331 `(("r-genomicfeatures" ,r-genomicfeatures)))
6332 (home-page
5713bbf1 6333 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
f3cfe451
RW		 6334 (synopsis "Annotation package for human genome in TxDb format")
6335 (description
6336 "This package provides an annotation database of Homo sapiens genome
6337data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6338track. The database is exposed as a @code{TxDb} object.")
6339 (license license:artistic2.0)))
6340
325c039c
RJ		 6341(define-public r-sparql
6342 (package
6343 (name "r-sparql")
6344 (version "1.16")
6345 (source (origin
6346 (method url-fetch)
6347 (uri (cran-uri "SPARQL" version))
6348 (sha256
6349 (base32
6350 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6351 (properties `((upstream-name . "SPARQL")))
6352 (build-system r-build-system)
6353 (propagated-inputs
6354 `(("r-rcurl" ,r-rcurl)
6355 ("r-xml" ,r-xml)))
e9960d8c 6356 (home-page "https://cran.r-project.org/web/packages/SPARQL")
325c039c
RJ		 6357 (synopsis "SPARQL client for R")
6358 (description "This package provides an interface to use SPARQL to pose
6359SELECT or UPDATE queries to an end-point.")
6360 ;; The only license indication is found in the DESCRIPTION file,
6361 ;; which states GPL-3. So we cannot assume GPLv3+.
6362 (license license:gpl3)))
6363
a2950fa4
BW		 6364(define-public vsearch
6365 (package
6366 (name "vsearch")
f14a6586 6367 (version "2.6.2")
a2950fa4
BW		 6368 (source
6369 (origin
6370 (method url-fetch)
6371 (uri (string-append
6372 "https://github.com/torognes/vsearch/archive/v"
6373 version ".tar.gz"))
6374 (file-name (string-append name "-" version ".tar.gz"))
6375 (sha256
6376 (base32
f14a6586 6377 "02khrgh8hm11cgww2f9mqc6886zqli9ss4pd4kfpqzd0d31vbzv5"))
206af46f 6378 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
a2950fa4
BW		 6379 (snippet
6380 '(begin
206af46f
BW		 6381 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6382 ;; for this in the patch.
cf6edaba
BW		 6383 (delete-file "src/city.h")
6384 (delete-file "src/citycrc.h")
6385 (delete-file "src/city.cc")
a2950fa4
BW		 6386 #t))))
6387 (build-system gnu-build-system)
6388 (arguments
6389 `(#:phases
6390 (modify-phases %standard-phases
d10092b8
KK		 6391 (add-after 'unpack 'autogen
6392 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
a2950fa4
BW		 6393 (inputs
6394 `(("zlib" ,zlib)
6395 ("bzip2" ,bzip2)
6396 ("cityhash" ,cityhash)))
6397 (native-inputs
6398 `(("autoconf" ,autoconf)
6399 ("automake" ,automake)))
6400 (synopsis "Sequence search tools for metagenomics")
6401 (description
6402 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6403dereplication, pairwise alignment, shuffling, subsampling, sorting and
6404masking. The tool takes advantage of parallelism in the form of SIMD
6405vectorization as well as multiple threads to perform accurate alignments at
6406high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6407Needleman-Wunsch).")
6408 (home-page "https://github.com/torognes/vsearch")
6f04e515
BW		 6409 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6410 ;; platforms.
6411 (supported-systems '("x86_64-linux"))
a2950fa4
BW		 6412 ;; Dual licensed; also includes public domain source.
6413 (license (list license:gpl3 license:bsd-2))))
6414
07837874
RW		 6415(define-public pardre
6416 (package
6417 (name "pardre")
7922ab8f
BW		 6418 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6419 (version "1.1.5-1")
07837874
RW		 6420 (source
6421 (origin
6422 (method url-fetch)
6423 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7922ab8f 6424 "1.1.5" ".tar.gz"))
07837874
RW		 6425 (sha256
6426 (base32
7922ab8f 6427 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
07837874
RW		 6428 (build-system gnu-build-system)
6429 (arguments
6430 `(#:tests? #f ; no tests included
6431 #:phases
6432 (modify-phases %standard-phases
6433 (delete 'configure)
6434 (replace 'install
6435 (lambda* (#:key outputs #:allow-other-keys)
6436 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
07837874
RW		 6437 (install-file "ParDRe" bin)
6438 #t))))))
6439 (inputs
6440 `(("openmpi" ,openmpi)
6441 ("zlib" ,zlib)))
6442 (synopsis "Parallel tool to remove duplicate DNA reads")
6443 (description
6444 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6445Duplicate reads can be seen as identical or nearly identical sequences with
6446some mismatches. This tool lets users avoid the analysis of unnecessary
6447reads, reducing the time of subsequent procedures with the
6448dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6449in order to exploit the parallel capabilities of multicore clusters. It is
6450faster than multithreaded counterparts (end of 2015) for the same number of
6451cores and, thanks to the message-passing technology, it can be executed on
6452clusters.")
6453 (home-page "https://sourceforge.net/projects/pardre/")
6454 (license license:gpl3+)))
6455
e4a44a6a
BW		 6456(define-public ruby-bio-kseq
6457 (package
6458 (name "ruby-bio-kseq")
6459 (version "0.0.2")
6460 (source
6461 (origin
6462 (method url-fetch)
6463 (uri (rubygems-uri "bio-kseq" version))
6464 (sha256
6465 (base32
6466 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6467 (build-system ruby-build-system)
6468 (arguments
6469 `(#:test-target "spec"))
6470 (native-inputs
6471 `(("bundler" ,bundler)
6472 ("ruby-rspec" ,ruby-rspec)
6473 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6474 (inputs
6475 `(("zlib" ,zlib)))
6476 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6477 (description
6478 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6479FASTQ parsing code. It provides a fast iterator over sequences and their
6480quality scores.")
6481 (home-page "https://github.com/gusevfe/bio-kseq")
6482 (license license:expat)))
6483
9c38b540
PP		 6484(define-public bio-locus
6485 (package
6486 (name "bio-locus")
6487 (version "0.0.7")
6488 (source
6489 (origin
6490 (method url-fetch)
6491 (uri (rubygems-uri "bio-locus" version))
6492 (sha256
6493 (base32
6494 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6495 (build-system ruby-build-system)
6496 (native-inputs
6497 `(("ruby-rspec" ,ruby-rspec)))
6498 (synopsis "Tool for fast querying of genome locations")
6499 (description
6500 "Bio-locus is a tabix-like tool for fast querying of genome
6501locations. Many file formats in bioinformatics contain records that
6502start with a chromosome name and a position for a SNP, or a start-end
6503position for indels. Bio-locus allows users to store this chr+pos or
6504chr+pos+alt information in a database.")
6505 (home-page "https://github.com/pjotrp/bio-locus")
6506 (license license:expat)))
edb15985 6507
b2bddb07
PP		 6508(define-public bio-blastxmlparser
6509 (package
6510 (name "bio-blastxmlparser")
6511 (version "2.0.4")
6512 (source (origin
6513 (method url-fetch)
6514 (uri (rubygems-uri "bio-blastxmlparser" version))
6515 (sha256
6516 (base32
6517 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6518 (build-system ruby-build-system)
6519 (propagated-inputs
6520 `(("ruby-bio-logger" ,ruby-bio-logger)
6521 ("ruby-nokogiri" ,ruby-nokogiri)))
6522 (inputs
6523 `(("ruby-rspec" ,ruby-rspec)))
6524 (synopsis "Fast big data BLAST XML parser and library")
6525 (description
6526 "Very fast parallel big-data BLAST XML file parser which can be used as
6527command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6528generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7bf837fd 6529 (home-page "https://github.com/pjotrp/blastxmlparser")
b2bddb07
PP		 6530 (license license:expat)))
6531
edb15985
PP		 6532(define-public bioruby
6533 (package
6534 (name "bioruby")
dbf9d371 6535 (version "1.5.1")
edb15985
PP		 6536 (source
6537 (origin
6538 (method url-fetch)
6539 (uri (rubygems-uri "bio" version))
6540 (sha256
6541 (base32
dbf9d371 6542 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
edb15985
PP		 6543 (build-system ruby-build-system)
6544 (propagated-inputs
6545 `(("ruby-libxml" ,ruby-libxml)))
6546 (native-inputs
6547 `(("which" ,which))) ; required for test phase
6548 (arguments
6549 `(#:phases
6550 (modify-phases %standard-phases
6551 (add-before 'build 'patch-test-command
6552 (lambda _
6553 (substitute* '("test/functional/bio/test_command.rb")
6554 (("/bin/sh") (which "sh")))
6555 (substitute* '("test/functional/bio/test_command.rb")
6556 (("/bin/ls") (which "ls")))
6557 (substitute* '("test/functional/bio/test_command.rb")
6558 (("which") (which "which")))
6559 (substitute* '("test/functional/bio/test_command.rb",
6560 "test/data/command/echoarg2.sh")
6561 (("/bin/echo") (which "echo")))
6562 #t)))))
6563 (synopsis "Ruby library, shell and utilities for bioinformatics")
6564 (description "BioRuby comes with a comprehensive set of Ruby development
6565tools and libraries for bioinformatics and molecular biology. BioRuby has
6566components for sequence analysis, pathway analysis, protein modelling and
6567phylogenetic analysis; it supports many widely used data formats and provides
6568easy access to databases, external programs and public web services, including
6569BLAST, KEGG, GenBank, MEDLINE and GO.")
6570 (home-page "http://bioruby.org/")
6571 ;; Code is released under Ruby license, except for setup
6572 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6573 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
a5002ae7 6574
9fba89e8
RW		 6575(define-public r-acsnminer
6576 (package
6577 (name "r-acsnminer")
0b54b4c9 6578 (version "0.16.8.25")
9fba89e8
RW		 6579 (source (origin
6580 (method url-fetch)
6581 (uri (cran-uri "ACSNMineR" version))
6582 (sha256
6583 (base32
0b54b4c9 6584 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
9fba89e8
RW		 6585 (properties `((upstream-name . "ACSNMineR")))
6586 (build-system r-build-system)
6587 (propagated-inputs
6588 `(("r-ggplot2" ,r-ggplot2)
6589 ("r-gridextra" ,r-gridextra)))
e9960d8c 6590 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
9fba89e8
RW		 6591 (synopsis "Gene enrichment analysis")
6592 (description
6593 "This package provides tools to compute and represent gene set enrichment
6594or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6595Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6596enrichment can be run with hypergeometric test or Fisher exact test, and can
6597use multiple corrections. Visualization of data can be done either by
6598barplots or heatmaps.")
6599 (license license:gpl2+)))
6600
d29b25c4
RW		 6601(define-public r-biocgenerics
6602 (package
6603 (name "r-biocgenerics")
d61fc4e1 6604 (version "0.24.0")
d29b25c4
RW		 6605 (source (origin
6606 (method url-fetch)
6607 (uri (bioconductor-uri "BiocGenerics" version))
6608 (sha256
6609 (base32
d61fc4e1 6610 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
d29b25c4 6611 (properties
1d216b6e 6612 `((upstream-name . "BiocGenerics")))
d29b25c4 6613 (build-system r-build-system)
5713bbf1 6614 (home-page "https://bioconductor.org/packages/BiocGenerics")
d29b25c4
RW		 6615 (synopsis "S4 generic functions for Bioconductor")
6616 (description
6617 "This package provides S4 generic functions needed by many Bioconductor
6618packages.")
6619 (license license:artistic2.0)))
6620
eb24341f
RJ		 6621(define-public r-biocinstaller
6622 (package
6623 (name "r-biocinstaller")
32414616 6624 (version "1.28.0")
eb24341f
RJ		 6625 (source (origin
6626 (method url-fetch)
6627 (uri (bioconductor-uri "BiocInstaller" version))
6628 (sha256
6629 (base32
32414616 6630 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
eb24341f
RJ		 6631 (properties
6632 `((upstream-name . "BiocInstaller")))
6633 (build-system r-build-system)
5713bbf1 6634 (home-page "https://bioconductor.org/packages/BiocInstaller")
eb24341f
RJ		 6635 (synopsis "Install Bioconductor packages")
6636 (description "This package is used to install and update R packages from
6637Bioconductor, CRAN, and Github.")
6638 (license license:artistic2.0)))
6639
207ce8fb
RJ		 6640(define-public r-biocviews
6641 (package
6642 (name "r-biocviews")
c7782c3f 6643 (version "1.46.0")
207ce8fb
RJ		 6644 (source (origin
6645 (method url-fetch)
6646 (uri (bioconductor-uri "biocViews" version))
6647 (sha256
6648 (base32
c7782c3f 6649 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
207ce8fb
RJ		 6650 (properties
6651 `((upstream-name . "biocViews")))
6652 (build-system r-build-system)
6653 (propagated-inputs
6654 `(("r-biobase" ,r-biobase)
6655 ("r-graph" ,r-graph)
6656 ("r-rbgl" ,r-rbgl)
6657 ("r-rcurl" ,r-rcurl)
6658 ("r-xml" ,r-xml)
207ce8fb 6659 ("r-runit" ,r-runit)))
5713bbf1 6660 (home-page "https://bioconductor.org/packages/biocViews")
207ce8fb
RJ		 6661 (synopsis "Bioconductor package categorization helper")
6662 (description "The purpose of biocViews is to create HTML pages that
6663categorize packages in a Bioconductor package repository according to keywords,
6664also known as views, in a controlled vocabulary.")
6665 (license license:artistic2.0)))
6666
2abfc5b8
RJ		 6667(define-public r-bookdown
6668 (package
6669 (name "r-bookdown")
6bd27981 6670 (version "0.5")
2abfc5b8
RJ		 6671 (source (origin
6672 (method url-fetch)
6673 (uri (cran-uri "bookdown" version))
6674 (sha256
6675 (base32
6bd27981 6676 "0zm63kr4f4kja4qpwkzl119zzyciqj7ihajfqgfjpgb4dzaiycxp"))))
2abfc5b8
RJ		 6677 (build-system r-build-system)
6678 (propagated-inputs
6679 `(("r-htmltools" ,r-htmltools)
6680 ("r-knitr" ,r-knitr)
6681 ("r-rmarkdown" ,r-rmarkdown)
6682 ("r-yaml" ,r-yaml)))
6683 (home-page "https://github.com/rstudio/bookdown")
6684 (synopsis "Authoring books and technical documents with R markdown")
6685 (description "This package provides output formats and utilities for
6686authoring books and technical documents with R Markdown.")
6687 (license license:gpl3)))
6688
99df12cd
RJ		 6689(define-public r-biocstyle
6690 (package
6691 (name "r-biocstyle")
7665fb39 6692 (version "2.6.1")
99df12cd
RJ		 6693 (source (origin
6694 (method url-fetch)
6695 (uri (bioconductor-uri "BiocStyle" version))
6696 (sha256
6697 (base32
7665fb39 6698 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
99df12cd
RJ		 6699 (properties
6700 `((upstream-name . "BiocStyle")))
6701 (build-system r-build-system)
3bef24c9
RJ		 6702 (propagated-inputs
6703 `(("r-bookdown" ,r-bookdown)
6704 ("r-knitr" ,r-knitr)
6705 ("r-rmarkdown" ,r-rmarkdown)
6706 ("r-yaml" ,r-yaml)))
5713bbf1 6707 (home-page "https://bioconductor.org/packages/BiocStyle")
99df12cd
RJ		 6708 (synopsis "Bioconductor formatting styles")
6709 (description "This package provides standard formatting styles for
6710Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6711functionality.")
6712 (license license:artistic2.0)))
6713
4644644a
RJ		 6714(define-public r-bioccheck
6715 (package
6716 (name "r-bioccheck")
7373b416 6717 (version "1.14.0")
4644644a
RJ		 6718 (source (origin
6719 (method url-fetch)
6720 (uri (bioconductor-uri "BiocCheck" version))
6721 (sha256
6722 (base32
7373b416 6723 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
4644644a
RJ		 6724 (properties
6725 `((upstream-name . "BiocCheck")))
6726 (build-system r-build-system)
6727 (arguments
6728 '(#:phases
6729 (modify-phases %standard-phases
6730 ;; This package can be used by calling BiocCheck(<package>) from
6731 ;; within R, or by running R CMD BiocCheck <package>. This phase
6732 ;; makes sure the latter works. For this to work, the BiocCheck
6733 ;; script must be somewhere on the PATH (not the R bin directory).
6734 (add-after 'install 'install-bioccheck-subcommand
6735 (lambda* (#:key outputs #:allow-other-keys)
6736 (let* ((out (assoc-ref outputs "out"))
6737 (dest-dir (string-append out "/bin"))
6738 (script-dir
6739 (string-append out "/site-library/BiocCheck/script/")))
6740 (mkdir-p dest-dir)
6741 (symlink (string-append script-dir "/checkBadDeps.R")
6742 (string-append dest-dir "/checkBadDeps.R"))
6743 (symlink (string-append script-dir "/BiocCheck")
6744 (string-append dest-dir "/BiocCheck")))
6745 #t)))))
4644644a 6746 (propagated-inputs
aeb64f3c
RW		 6747 `(("r-codetools" ,r-codetools)
6748 ("r-graph" ,r-graph)
4644644a
RJ		 6749 ("r-httr" ,r-httr)
6750 ("r-optparse" ,r-optparse)
4644644a 6751 ("r-biocinstaller" ,r-biocinstaller)
7373b416
RW		 6752 ("r-biocviews" ,r-biocviews)
6753 ("r-stringdist" ,r-stringdist)))
5713bbf1 6754 (home-page "https://bioconductor.org/packages/BiocCheck")
4644644a
RJ		 6755 (synopsis "Executes Bioconductor-specific package checks")
6756 (description "This package contains tools to perform additional quality
6757checks on R packages that are to be submitted to the Bioconductor repository.")
6758 (license license:artistic2.0)))
6759
2acaaee5
RJ		 6760(define-public r-getopt
6761 (package
6762 (name "r-getopt")
d2081a17 6763 (version "1.20.1")
2acaaee5
RJ		 6764 (source
6765 (origin
6766 (method url-fetch)
6767 (uri (cran-uri "getopt" version))
6768 (sha256
6769 (base32
d2081a17 6770 "0m463mcvixh54i3ng42n0vxmdlf97dgbfs2sf9wnjm782ddw68hm"))))
2acaaee5
RJ		 6771 (build-system r-build-system)
6772 (home-page "https://github.com/trevorld/getopt")
6773 (synopsis "Command-line option processor for R")
6774 (description
6775 "This package is designed to be used with Rscript to write shebang
6776scripts that accept short and long options. Many users will prefer to
6777use the packages @code{optparse} or @code{argparse} which add extra
6778features like automatically generated help options and usage texts,
6779support for default values, positional argument support, etc.")
6780 (license license:gpl2+)))
6781
c79ad57a
RJ		 6782(define-public r-optparse
6783 (package
6784 (name "r-optparse")
7150f1c3 6785 (version "1.4.4")
c79ad57a
RJ		 6786 (source
6787 (origin
6788 (method url-fetch)
6789 (uri (cran-uri "optparse" version))
6790 (sha256
6791 (base32
7150f1c3 6792 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
c79ad57a
RJ		 6793 (build-system r-build-system)
6794 (propagated-inputs
6795 `(("r-getopt" ,r-getopt)))
6796 (home-page
6797 "https://github.com/trevorld/optparse")
6798 (synopsis "Command line option parser")
6799 (description
6800 "This package provides a command line parser inspired by Python's
6801@code{optparse} library to be used with Rscript to write shebang scripts
6802that accept short and long options.")
6803 (license license:gpl2+)))
6804
247d498a
RJ		 6805(define-public r-dnacopy
6806 (package
6807 (name "r-dnacopy")
94fd86e5 6808 (version "1.52.0")
247d498a
RJ		 6809 (source (origin
6810 (method url-fetch)
6811 (uri (bioconductor-uri "DNAcopy" version))
6812 (sha256
6813 (base32
94fd86e5 6814 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
247d498a
RJ		 6815 (properties
6816 `((upstream-name . "DNAcopy")))
6817 (build-system r-build-system)
6818 (inputs
6819 `(("gfortran" ,gfortran)))
5697fdc3 6820 (home-page "https://bioconductor.org/packages/DNAcopy")
247d498a
RJ		 6821 (synopsis "Implementation of a circular binary segmentation algorithm")
6822 (description "This package implements the circular binary segmentation (CBS)
6823algorithm to segment DNA copy number data and identify genomic regions with
6824abnormal copy number.")
6825 (license license:gpl2+)))
6826
7485129e
RW		 6827(define-public r-s4vectors
6828 (package
6829 (name "r-s4vectors")
41f0f949 6830 (version "0.16.0")
7485129e
RW		 6831 (source (origin
6832 (method url-fetch)
6833 (uri (bioconductor-uri "S4Vectors" version))
6834 (sha256
6835 (base32
41f0f949 6836 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
7485129e 6837 (properties
1d216b6e 6838 `((upstream-name . "S4Vectors")))
7485129e
RW		 6839 (build-system r-build-system)
6840 (propagated-inputs
6841 `(("r-biocgenerics" ,r-biocgenerics)))
5713bbf1 6842 (home-page "https://bioconductor.org/packages/S4Vectors")
7485129e
RW		 6843 (synopsis "S4 implementation of vectors and lists")
6844 (description
6845 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6846classes and a set of generic functions that extend the semantic of ordinary
6847vectors and lists in R. Package developers can easily implement vector-like
6848or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6849In addition, a few low-level concrete subclasses of general interest (e.g.
6850@code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6851S4Vectors package itself.")
6852 (license license:artistic2.0)))
6853
274da826
RW		 6854(define-public r-seqinr
6855 (package
6856 (name "r-seqinr")
023aa8ff 6857 (version "3.4-5")
274da826
RW		 6858 (source
6859 (origin
6860 (method url-fetch)
6861 (uri (cran-uri "seqinr" version))
6862 (sha256
6863 (base32
023aa8ff 6864 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
274da826
RW		 6865 (build-system r-build-system)
6866 (propagated-inputs
3b851cd4
RW		 6867 `(("r-ade4" ,r-ade4)
6868 ("r-segmented" ,r-segmented)))
274da826
RW		 6869 (inputs
6870 `(("zlib" ,zlib)))
6871 (home-page "http://seqinr.r-forge.r-project.org/")
6872 (synopsis "Biological sequences retrieval and analysis")
6873 (description
6874 "This package provides tools for exploratory data analysis and data
6875visualization of biological sequence (DNA and protein) data. It also includes
6876utilities for sequence data management under the ACNUC system.")
6877 (license license:gpl2+)))
6878
78addcb0
RW		 6879(define-public r-iranges
6880 (package
6881 (name "r-iranges")
9e482c20 6882 (version "2.12.0")
78addcb0
RW		 6883 (source (origin
6884 (method url-fetch)
6885 (uri (bioconductor-uri "IRanges" version))
6886 (sha256
6887 (base32
9e482c20 6888 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
78addcb0 6889 (properties
1d216b6e 6890 `((upstream-name . "IRanges")))
78addcb0
RW		 6891 (build-system r-build-system)
6892 (propagated-inputs
6893 `(("r-biocgenerics" ,r-biocgenerics)
6894 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 6895 (home-page "https://bioconductor.org/packages/IRanges")
78addcb0
RW		 6896 (synopsis "Infrastructure for manipulating intervals on sequences")
6897 (description
6898 "This package provides efficient low-level and highly reusable S4 classes
6899for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6900generally, data that can be organized sequentially (formally defined as
6901@code{Vector} objects), as well as views on these @code{Vector} objects.
6902Efficient list-like classes are also provided for storing big collections of
6903instances of the basic classes. All classes in the package use consistent
6904naming and share the same rich and consistent \"Vector API\" as much as
6905possible.")
6906 (license license:artistic2.0)))
6907
ffef27f3
RJ		 6908(define-public r-genomeinfodbdata
6909 (package
6910 (name "r-genomeinfodbdata")
261b38a9 6911 (version "0.99.1")
ffef27f3
RJ		 6912 (source (origin
6913 (method url-fetch)
90f83099
EF		 6914 ;; We cannot use bioconductor-uri here because this tarball is
6915 ;; located under "data/annotation/" instead of "bioc/".
6916 (uri (string-append "https://bioconductor.org/packages/release/"
6917 "data/annotation/src/contrib/GenomeInfoDbData_"
6918 version ".tar.gz"))
ffef27f3
RJ		 6919 (sha256
6920 (base32
261b38a9 6921 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
ffef27f3
RJ		 6922 (properties
6923 `((upstream-name . "GenomeInfoDbData")))
6924 (build-system r-build-system)
5713bbf1 6925 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
ffef27f3
RJ		 6926 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6927 (description "This package contains data for mapping between NCBI taxonomy
6928ID and species. It is used by functions in the GenomeInfoDb package.")
6929 (license license:artistic2.0)))
6930
bf7764b7
RW		 6931(define-public r-genomeinfodb
6932 (package
6933 (name "r-genomeinfodb")
8aab0235 6934 (version "1.14.0")
bf7764b7
RW		 6935 (source (origin
6936 (method url-fetch)
6937 (uri (bioconductor-uri "GenomeInfoDb" version))
6938 (sha256
6939 (base32
8aab0235 6940 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
bf7764b7 6941 (properties
1d216b6e 6942 `((upstream-name . "GenomeInfoDb")))
bf7764b7
RW		 6943 (build-system r-build-system)
6944 (propagated-inputs
6945 `(("r-biocgenerics" ,r-biocgenerics)
38b99ccc 6946 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
bf7764b7 6947 ("r-iranges" ,r-iranges)
4cd07e48 6948 ("r-rcurl" ,r-rcurl)
bf7764b7 6949 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 6950 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
bf7764b7
RW		 6951 (synopsis "Utilities for manipulating chromosome identifiers")
6952 (description
6953 "This package contains data and functions that define and allow
6954translation between different chromosome sequence naming conventions (e.g.,
6955\"chr1\" versus \"1\"), including a function that attempts to place sequence
6956names in their natural, rather than lexicographic, order.")
6957 (license license:artistic2.0)))
6958
744004a3
RJ		 6959(define-public r-edger
6960 (package
6961 (name "r-edger")
ab0dd8ac 6962 (version "3.20.2")
744004a3
RJ		 6963 (source (origin
6964 (method url-fetch)
6965 (uri (bioconductor-uri "edgeR" version))
6966 (sha256
6967 (base32
ab0dd8ac 6968 "0j5s3i33qmld9l7gs1rzpv601zxyqz711x8mq35hml088c8s99w9"))))
744004a3
RJ		 6969 (properties `((upstream-name . "edgeR")))
6970 (build-system r-build-system)
6971 (propagated-inputs
5e48005f 6972 `(("r-limma" ,r-limma)
47055b27 6973 ("r-locfit" ,r-locfit)
010ab2ff 6974 ("r-rcpp" ,r-rcpp)
47055b27 6975 ("r-statmod" ,r-statmod))) ;for estimateDisp
744004a3
RJ		 6976 (home-page "http://bioinf.wehi.edu.au/edgeR")
6977 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6978 (description "This package can do differential expression analysis of
6979RNA-seq expression profiles with biological replication. It implements a range
6980of statistical methodology based on the negative binomial distributions,
6981including empirical Bayes estimation, exact tests, generalized linear models
6982and quasi-likelihood tests. It be applied to differential signal analysis of
6983other types of genomic data that produce counts, including ChIP-seq, SAGE and
6984CAGE.")
6985 (license license:gpl2+)))
6986
b669d9c4
RJ		 6987(define-public r-variantannotation
6988 (package
6989 (name "r-variantannotation")
8131cf41 6990 (version "1.24.2")
b669d9c4
RJ		 6991 (source (origin
6992 (method url-fetch)
6993 (uri (bioconductor-uri "VariantAnnotation" version))
6994 (sha256
6995 (base32
8131cf41 6996 "19wgb2kcqy97pm3xgqc781id9fbmzp1hdwzkkhdzpvyf29w4n29j"))))
b669d9c4
RJ		 6997 (properties
6998 `((upstream-name . "VariantAnnotation")))
6999 (inputs
7000 `(("zlib" ,zlib)))
7001 (propagated-inputs
7002 `(("r-annotationdbi" ,r-annotationdbi)
37d96f1d 7003 ("r-biobase" ,r-biobase)
b669d9c4 7004 ("r-biocgenerics" ,r-biocgenerics)
37d96f1d 7005 ("r-biostrings" ,r-biostrings)
b669d9c4
RJ		 7006 ("r-bsgenome" ,r-bsgenome)
7007 ("r-dbi" ,r-dbi)
7008 ("r-genomeinfodb" ,r-genomeinfodb)
7009 ("r-genomicfeatures" ,r-genomicfeatures)
7010 ("r-genomicranges" ,r-genomicranges)
37d96f1d 7011 ("r-iranges" ,r-iranges)
b669d9c4
RJ		 7012 ("r-summarizedexperiment" ,r-summarizedexperiment)
7013 ("r-rsamtools" ,r-rsamtools)
37d96f1d
RW		 7014 ("r-rtracklayer" ,r-rtracklayer)
7015 ("r-s4vectors" ,r-s4vectors)
7016 ("r-xvector" ,r-xvector)
b669d9c4
RJ		 7017 ("r-zlibbioc" ,r-zlibbioc)))
7018 (build-system r-build-system)
7019 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7020 (synopsis "Package for annotation of genetic variants")
7021 (description "This R package can annotate variants, compute amino acid
7022coding changes and predict coding outcomes.")
7023 (license license:artistic2.0)))
7024
7d4224d7
RJ		 7025(define-public r-limma
7026 (package
7027 (name "r-limma")
d41f6784 7028 (version "3.34.4")
7d4224d7
RJ		 7029 (source (origin
7030 (method url-fetch)
7031 (uri (bioconductor-uri "limma" version))
7032 (sha256
7033 (base32
d41f6784 7034 "1vcxf9jg8xngxg5kb9bp8rw5sghpnkpj320iq309m2fp41ahsk3f"))))
7d4224d7
RJ		 7035 (build-system r-build-system)
7036 (home-page "http://bioinf.wehi.edu.au/limma")
7037 (synopsis "Package for linear models for microarray and RNA-seq data")
7038 (description "This package can be used for the analysis of gene expression
7039studies, especially the use of linear models for analysing designed experiments
7040and the assessment of differential expression. The analysis methods apply to
7041different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7042 (license license:gpl2+)))
7043
0e7d5560
RW		 7044(define-public r-xvector
7045 (package
7046 (name "r-xvector")
2b6ae8bf 7047 (version "0.18.0")
0e7d5560
RW		 7048 (source (origin
7049 (method url-fetch)
7050 (uri (bioconductor-uri "XVector" version))
7051 (sha256
7052 (base32
2b6ae8bf 7053 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
0e7d5560 7054 (properties
1d216b6e 7055 `((upstream-name . "XVector")))
0e7d5560
RW		 7056 (build-system r-build-system)
7057 (arguments
7058 `(#:phases
7059 (modify-phases %standard-phases
7060 (add-after 'unpack 'use-system-zlib
7061 (lambda _
7062 (substitute* "DESCRIPTION"
7063 (("zlibbioc, ") ""))
7064 (substitute* "NAMESPACE"
7065 (("import\\(zlibbioc\\)") ""))
7066 #t)))))
7067 (inputs
7068 `(("zlib" ,zlib)))
7069 (propagated-inputs
7070 `(("r-biocgenerics" ,r-biocgenerics)
7071 ("r-iranges" ,r-iranges)
7072 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 7073 (home-page "https://bioconductor.org/packages/XVector")
0e7d5560
RW		 7074 (synopsis "Representation and manpulation of external sequences")
7075 (description
7076 "This package provides memory efficient S4 classes for storing sequences
7077\"externally\" (behind an R external pointer, or on disk).")
7078 (license license:artistic2.0)))
7079
e2cd1d0f
RW		 7080(define-public r-genomicranges
7081 (package
7082 (name "r-genomicranges")
aa5c1f61 7083 (version "1.30.0")
e2cd1d0f
RW		 7084 (source (origin
7085 (method url-fetch)
7086 (uri (bioconductor-uri "GenomicRanges" version))
7087 (sha256
7088 (base32
aa5c1f61 7089 "10ra2sjn17h6gilm9iz0cygp9ijpgbirljlc4drwrnivnw9cmi2a"))))
e2cd1d0f 7090 (properties
1d216b6e 7091 `((upstream-name . "GenomicRanges")))
e2cd1d0f
RW		 7092 (build-system r-build-system)
7093 (propagated-inputs
7094 `(("r-biocgenerics" ,r-biocgenerics)
7095 ("r-genomeinfodb" ,r-genomeinfodb)
92a740af
RW		 7096 ("r-iranges" ,r-iranges)
7097 ("r-s4vectors" ,r-s4vectors)
e2cd1d0f 7098 ("r-xvector" ,r-xvector)))
5713bbf1 7099 (home-page "https://bioconductor.org/packages/GenomicRanges")
e2cd1d0f
RW		 7100 (synopsis "Representation and manipulation of genomic intervals")
7101 (description
7102 "This package provides tools to efficiently represent and manipulate
7103genomic annotations and alignments is playing a central role when it comes to
7104analyzing high-throughput sequencing data (a.k.a. NGS data). The
7105GenomicRanges package defines general purpose containers for storing and
7106manipulating genomic intervals and variables defined along a genome.")
7107 (license license:artistic2.0)))
7108
555e3399
RW		 7109(define-public r-biobase
7110 (package
7111 (name "r-biobase")
ca521236 7112 (version "2.38.0")
555e3399
RW		 7113 (source (origin
7114 (method url-fetch)
7115 (uri (bioconductor-uri "Biobase" version))
7116 (sha256
7117 (base32
ca521236 7118 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
555e3399
RW		 7119 (properties
7120 `((upstream-name . "Biobase")))
7121 (build-system r-build-system)
7122 (propagated-inputs
7123 `(("r-biocgenerics" ,r-biocgenerics)))
5713bbf1 7124 (home-page "https://bioconductor.org/packages/Biobase")
555e3399
RW		 7125 (synopsis "Base functions for Bioconductor")
7126 (description
7127 "This package provides functions that are needed by many other packages
7128on Bioconductor or which replace R functions.")
7129 (license license:artistic2.0)))
7130
8b7bce74
RW		 7131(define-public r-annotationdbi
7132 (package
7133 (name "r-annotationdbi")
0f8d98f2 7134 (version "1.40.0")
8b7bce74
RW		 7135 (source (origin
7136 (method url-fetch)
7137 (uri (bioconductor-uri "AnnotationDbi" version))
7138 (sha256
7139 (base32
0f8d98f2 7140 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
8b7bce74
RW		 7141 (properties
7142 `((upstream-name . "AnnotationDbi")))
7143 (build-system r-build-system)
7144 (propagated-inputs
7145 `(("r-biobase" ,r-biobase)
7146 ("r-biocgenerics" ,r-biocgenerics)
7147 ("r-dbi" ,r-dbi)
7148 ("r-iranges" ,r-iranges)
7149 ("r-rsqlite" ,r-rsqlite)
7150 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 7151 (home-page "https://bioconductor.org/packages/AnnotationDbi")
8b7bce74
RW		 7152 (synopsis "Annotation database interface")
7153 (description
7154 "This package provides user interface and database connection code for
7155annotation data packages using SQLite data storage.")
7156 (license license:artistic2.0)))
7157
c465fa72
RW		 7158(define-public r-biomart
7159 (package
7160 (name "r-biomart")
b9e8a5c5 7161 (version "2.34.1")
c465fa72
RW		 7162 (source (origin
7163 (method url-fetch)
7164 (uri (bioconductor-uri "biomaRt" version))
7165 (sha256
7166 (base32
b9e8a5c5 7167 "0jzv8b86vpvavwnzi5xf7y18xmn72zkabkn2kclg1mgl847cq13k"))))
c465fa72
RW		 7168 (properties
7169 `((upstream-name . "biomaRt")))
7170 (build-system r-build-system)
7171 (propagated-inputs
7172 `(("r-annotationdbi" ,r-annotationdbi)
b9e8a5c5 7173 ("r-httr" ,r-httr)
42e11d33 7174 ("r-progress" ,r-progress)
c465fa72 7175 ("r-rcurl" ,r-rcurl)
42e11d33 7176 ("r-stringr" ,r-stringr)
c465fa72 7177 ("r-xml" ,r-xml)))
5713bbf1 7178 (home-page "https://bioconductor.org/packages/biomaRt")
c465fa72
RW		 7179 (synopsis "Interface to BioMart databases")
7180 (description
7181 "biomaRt provides an interface to a growing collection of databases
7182implementing the @url{BioMart software suite, http://www.biomart.org}. The
7183package enables retrieval of large amounts of data in a uniform way without
7184the need to know the underlying database schemas or write complex SQL queries.
7185Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7186Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7187users direct access to a diverse set of data and enable a wide range of
7188powerful online queries from gene annotation to database mining.")
7189 (license license:artistic2.0)))
7190
e91d362e
RW		 7191(define-public r-biocparallel
7192 (package
7193 (name "r-biocparallel")
a044c7f4 7194 (version "1.12.0")
e91d362e
RW		 7195 (source (origin
7196 (method url-fetch)
7197 (uri (bioconductor-uri "BiocParallel" version))
7198 (sha256
7199 (base32
a044c7f4 7200 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
e91d362e
RW		 7201 (properties
7202 `((upstream-name . "BiocParallel")))
7203 (build-system r-build-system)
7204 (propagated-inputs
7205 `(("r-futile-logger" ,r-futile-logger)
a044c7f4
RW		 7206 ("r-snow" ,r-snow)
7207 ("r-bh" ,r-bh)))
5713bbf1 7208 (home-page "https://bioconductor.org/packages/BiocParallel")
e91d362e
RW		 7209 (synopsis "Bioconductor facilities for parallel evaluation")
7210 (description
7211 "This package provides modified versions and novel implementation of
7212functions for parallel evaluation, tailored to use with Bioconductor
7213objects.")
7214 (license (list license:gpl2+ license:gpl3+))))
7215
bf159353
RW		 7216(define-public r-biostrings
7217 (package
7218 (name "r-biostrings")
b719435e 7219 (version "2.46.0")
bf159353
RW		 7220 (source (origin
7221 (method url-fetch)
7222 (uri (bioconductor-uri "Biostrings" version))
7223 (sha256
7224 (base32
b719435e 7225 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
bf159353
RW		 7226 (properties
7227 `((upstream-name . "Biostrings")))
7228 (build-system r-build-system)
7229 (propagated-inputs
7230 `(("r-biocgenerics" ,r-biocgenerics)
7231 ("r-iranges" ,r-iranges)
7232 ("r-s4vectors" ,r-s4vectors)
7233 ("r-xvector" ,r-xvector)))
5713bbf1 7234 (home-page "https://bioconductor.org/packages/Biostrings")
bf159353
RW		 7235 (synopsis "String objects and algorithms for biological sequences")
7236 (description
7237 "This package provides memory efficient string containers, string
7238matching algorithms, and other utilities, for fast manipulation of large
7239biological sequences or sets of sequences.")
7240 (license license:artistic2.0)))
7241
f8d74f70
RW		 7242(define-public r-rsamtools
7243 (package
7244 (name "r-rsamtools")
f8068419 7245 (version "1.30.0")
f8d74f70
RW		 7246 (source (origin
7247 (method url-fetch)
7248 (uri (bioconductor-uri "Rsamtools" version))
7249 (sha256
7250 (base32
f8068419 7251 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
f8d74f70
RW		 7252 (properties
7253 `((upstream-name . "Rsamtools")))
7254 (build-system r-build-system)
7255 (arguments
7256 `(#:phases
7257 (modify-phases %standard-phases
7258 (add-after 'unpack 'use-system-zlib
7259 (lambda _
7260 (substitute* "DESCRIPTION"
7261 (("zlibbioc, ") ""))
7262 (substitute* "NAMESPACE"
7263 (("import\\(zlibbioc\\)") ""))
7264 #t)))))
7265 (inputs
7266 `(("zlib" ,zlib)))
7267 (propagated-inputs
7268 `(("r-biocgenerics" ,r-biocgenerics)
7269 ("r-biocparallel" ,r-biocparallel)
7270 ("r-biostrings" ,r-biostrings)
7271 ("r-bitops" ,r-bitops)
7272 ("r-genomeinfodb" ,r-genomeinfodb)
7273 ("r-genomicranges" ,r-genomicranges)
7274 ("r-iranges" ,r-iranges)
7275 ("r-s4vectors" ,r-s4vectors)
7276 ("r-xvector" ,r-xvector)))
5713bbf1 7277 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
f8d74f70
RW		 7278 (synopsis "Interface to samtools, bcftools, and tabix")
7279 (description
7280 "This package provides an interface to the 'samtools', 'bcftools', and
7281'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7282binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7283files.")
7284 (license license:expat)))
7285
71e34e6b
RJ		 7286(define-public r-delayedarray
7287 (package
7288 (name "r-delayedarray")
cb0a9a74 7289 (version "0.4.1")
71e34e6b
RJ		 7290 (source (origin
7291 (method url-fetch)
7292 (uri (bioconductor-uri "DelayedArray" version))
7293 (sha256
7294 (base32
cb0a9a74 7295 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
71e34e6b
RJ		 7296 (properties
7297 `((upstream-name . "DelayedArray")))
7298 (build-system r-build-system)
7299 (propagated-inputs
7300 `(("r-biocgenerics" ,r-biocgenerics)
7301 ("r-s4vectors" ,r-s4vectors)
7302 ("r-iranges" ,r-iranges)
7303 ("r-matrixstats" ,r-matrixstats)))
5713bbf1 7304 (home-page "https://bioconductor.org/packages/DelayedArray")
71e34e6b
RJ		 7305 (synopsis "Delayed operations on array-like objects")
7306 (description
7307 "Wrapping an array-like object (typically an on-disk object) in a
7308@code{DelayedArray} object allows one to perform common array operations on it
7309without loading the object in memory. In order to reduce memory usage and
7310optimize performance, operations on the object are either delayed or executed
7311using a block processing mechanism. Note that this also works on in-memory
7312array-like objects like @code{DataFrame} objects (typically with Rle columns),
7313@code{Matrix} objects, and ordinary arrays and data frames.")
7314 (license license:artistic2.0)))
7315
6e76dda2
RW		 7316(define-public r-summarizedexperiment
7317 (package
7318 (name "r-summarizedexperiment")
6fcbed73 7319 (version "1.8.0")
6e76dda2
RW		 7320 (source (origin
7321 (method url-fetch)
7322 (uri (bioconductor-uri "SummarizedExperiment" version))
7323 (sha256
7324 (base32
6fcbed73 7325 "1011r8l0k8420j31bmh4xdcp6ka5bzf4bqhip84v5b6alpkcbvmf"))))
6e76dda2
RW		 7326 (properties
7327 `((upstream-name . "SummarizedExperiment")))
7328 (build-system r-build-system)
7329 (propagated-inputs
7330 `(("r-biobase" ,r-biobase)
7331 ("r-biocgenerics" ,r-biocgenerics)
d006ee31 7332 ("r-delayedarray" ,r-delayedarray)
6e76dda2
RW		 7333 ("r-genomeinfodb" ,r-genomeinfodb)
7334 ("r-genomicranges" ,r-genomicranges)
7335 ("r-iranges" ,r-iranges)
aeb64f3c 7336 ("r-matrix" ,r-matrix)
6e76dda2 7337 ("r-s4vectors" ,r-s4vectors)))
5713bbf1 7338 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
6e76dda2
RW		 7339 (synopsis "Container for representing genomic ranges by sample")
7340 (description
7341 "The SummarizedExperiment container contains one or more assays, each
7342represented by a matrix-like object of numeric or other mode. The rows
7343typically represent genomic ranges of interest and the columns represent
7344samples.")
7345 (license license:artistic2.0)))
7346
d8a828af
RW		 7347(define-public r-genomicalignments
7348 (package
7349 (name "r-genomicalignments")
06e8e0fc 7350 (version "1.14.1")
d8a828af
RW		 7351 (source (origin
7352 (method url-fetch)
7353 (uri (bioconductor-uri "GenomicAlignments" version))
7354 (sha256
7355 (base32
06e8e0fc 7356 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
d8a828af
RW		 7357 (properties
7358 `((upstream-name . "GenomicAlignments")))
7359 (build-system r-build-system)
7360 (propagated-inputs
7361 `(("r-biocgenerics" ,r-biocgenerics)
7362 ("r-biocparallel" ,r-biocparallel)
7363 ("r-biostrings" ,r-biostrings)
7364 ("r-genomeinfodb" ,r-genomeinfodb)
7365 ("r-genomicranges" ,r-genomicranges)
7366 ("r-iranges" ,r-iranges)
7367 ("r-rsamtools" ,r-rsamtools)
7368 ("r-s4vectors" ,r-s4vectors)
7369 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5713bbf1 7370 (home-page "https://bioconductor.org/packages/GenomicAlignments")
d8a828af
RW		 7371 (synopsis "Representation and manipulation of short genomic alignments")
7372 (description
7373 "This package provides efficient containers for storing and manipulating
7374short genomic alignments (typically obtained by aligning short reads to a
7375reference genome). This includes read counting, computing the coverage,
7376junction detection, and working with the nucleotide content of the
7377alignments.")
7378 (license license:artistic2.0)))
7379
317755ff
RW		 7380(define-public r-rtracklayer
7381 (package
7382 (name "r-rtracklayer")
28d25d03 7383 (version "1.38.2")
317755ff
RW		 7384 (source (origin
7385 (method url-fetch)
7386 (uri (bioconductor-uri "rtracklayer" version))
7387 (sha256
7388 (base32
28d25d03 7389 "1sjn3976f1sqvrq6jq2hgc60ffxgfr3jlklaxfrk3xad5cv2kr2d"))))
317755ff
RW		 7390 (build-system r-build-system)
7391 (arguments
7392 `(#:phases
7393 (modify-phases %standard-phases
7394 (add-after 'unpack 'use-system-zlib
7395 (lambda _
7396 (substitute* "DESCRIPTION"
4dd469ef 7397 ((" zlibbioc,") ""))
317755ff
RW		 7398 (substitute* "NAMESPACE"
7399 (("import\\(zlibbioc\\)") ""))
7400 #t)))))
7401 (inputs
7402 `(("zlib" ,zlib)))
7403 (propagated-inputs
7404 `(("r-biocgenerics" ,r-biocgenerics)
7405 ("r-biostrings" ,r-biostrings)
7406 ("r-genomeinfodb" ,r-genomeinfodb)
7407 ("r-genomicalignments" ,r-genomicalignments)
7408 ("r-genomicranges" ,r-genomicranges)
7409 ("r-iranges" ,r-iranges)
7410 ("r-rcurl" ,r-rcurl)
7411 ("r-rsamtools" ,r-rsamtools)
7412 ("r-s4vectors" ,r-s4vectors)
7413 ("r-xml" ,r-xml)
7414 ("r-xvector" ,r-xvector)))
5713bbf1 7415 (home-page "https://bioconductor.org/packages/rtracklayer")
317755ff
RW		 7416 (synopsis "R interface to genome browsers and their annotation tracks")
7417 (description
7418 "rtracklayer is an extensible framework for interacting with multiple
7419genome browsers (currently UCSC built-in) and manipulating annotation tracks
7420in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7421built-in). The user may export/import tracks to/from the supported browsers,
7422as well as query and modify the browser state, such as the current viewport.")
7423 (license license:artistic2.0)))
7424
2fd7c049
RW		 7425(define-public r-genomicfeatures
7426 (package
7427 (name "r-genomicfeatures")
158b6743 7428 (version "1.30.0")
2fd7c049
RW		 7429 (source (origin
7430 (method url-fetch)
7431 (uri (bioconductor-uri "GenomicFeatures" version))
7432 (sha256
7433 (base32
158b6743 7434 "1khjvq1ffhqavkwf8n7bilknci60lxbg52icrcf2vnb9k8rlpghs"))))
2fd7c049
RW		 7435 (properties
7436 `((upstream-name . "GenomicFeatures")))
7437 (build-system r-build-system)
7438 (propagated-inputs
7439 `(("r-annotationdbi" ,r-annotationdbi)
7440 ("r-biobase" ,r-biobase)
7441 ("r-biocgenerics" ,r-biocgenerics)
7442 ("r-biomart" ,r-biomart)
7443 ("r-biostrings" ,r-biostrings)
7444 ("r-dbi" ,r-dbi)
7445 ("r-genomeinfodb" ,r-genomeinfodb)
7446 ("r-genomicranges" ,r-genomicranges)
7447 ("r-iranges" ,r-iranges)
7448 ("r-rcurl" ,r-rcurl)
7449 ("r-rsqlite" ,r-rsqlite)
158b6743 7450 ("r-rmysql" ,r-rmysql)
2fd7c049
RW		 7451 ("r-rtracklayer" ,r-rtracklayer)
7452 ("r-s4vectors" ,r-s4vectors)
7453 ("r-xvector" ,r-xvector)))
5713bbf1 7454 (home-page "https://bioconductor.org/packages/GenomicFeatures")
2fd7c049
RW		 7455 (synopsis "Tools for working with transcript centric annotations")
7456 (description
7457 "This package provides a set of tools and methods for making and
7458manipulating transcript centric annotations. With these tools the user can
7459easily download the genomic locations of the transcripts, exons and cds of a
7460given organism, from either the UCSC Genome Browser or a BioMart
7461database (more sources will be supported in the future). This information is
7462then stored in a local database that keeps track of the relationship between
7463transcripts, exons, cds and genes. Flexible methods are provided for
7464extracting the desired features in a convenient format.")
7465 (license license:artistic2.0)))
7466
fb25d880
RW		 7467(define-public r-go-db
7468 (package
7469 (name "r-go-db")
592f4a94 7470 (version "3.5.0")
fb25d880
RW		 7471 (source (origin
7472 (method url-fetch)
5713bbf1 7473 (uri (string-append "https://www.bioconductor.org/packages/"
f82c8c3c
PP		 7474 "release/data/annotation/src/contrib/GO.db_"
7475 version ".tar.gz"))
fb25d880
RW		 7476 (sha256
7477 (base32
592f4a94 7478 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
fb25d880
RW		 7479 (properties
7480 `((upstream-name . "GO.db")))
7481 (build-system r-build-system)
3141b83d
RW		 7482 (propagated-inputs
7483 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7484 (home-page "https://bioconductor.org/packages/GO.db")
fb25d880
RW		 7485 (synopsis "Annotation maps describing the entire Gene Ontology")
7486 (description
7487 "The purpose of this GO.db annotation package is to provide detailed
7488information about the latest version of the Gene Ontologies.")
7489 (license license:artistic2.0)))
7490
d1dbde6a
RW		 7491(define-public r-graph
7492 (package
7493 (name "r-graph")
aeb73879 7494 (version "1.56.0")
d1dbde6a
RW		 7495 (source (origin
7496 (method url-fetch)
7497 (uri (bioconductor-uri "graph" version))
7498 (sha256
7499 (base32
aeb73879 7500 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
d1dbde6a
RW		 7501 (build-system r-build-system)
7502 (propagated-inputs
7503 `(("r-biocgenerics" ,r-biocgenerics)))
5713bbf1 7504 (home-page "https://bioconductor.org/packages/graph")
d1dbde6a
RW		 7505 (synopsis "Handle graph data structures in R")
7506 (description
7507 "This package implements some simple graph handling capabilities for R.")
7508 (license license:artistic2.0)))
7509
d547ce5e
RW		 7510(define-public r-topgo
7511 (package
7512 (name "r-topgo")
d13a3fea 7513 (version "2.30.0")
d547ce5e
RW		 7514 (source (origin
7515 (method url-fetch)
7516 (uri (bioconductor-uri "topGO" version))
7517 (sha256
7518 (base32
d13a3fea 7519 "1hqffz5qp7glxdvjp37005g8qk5nam3f9wpf6d1wjnzpar04f3dz"))))
d547ce5e
RW		 7520 (properties
7521 `((upstream-name . "topGO")))
7522 (build-system r-build-system)
7523 (propagated-inputs
7524 `(("r-annotationdbi" ,r-annotationdbi)
30ec4de7 7525 ("r-dbi" ,r-dbi)
d547ce5e
RW		 7526 ("r-biobase" ,r-biobase)
7527 ("r-biocgenerics" ,r-biocgenerics)
7528 ("r-go-db" ,r-go-db)
6d415db2 7529 ("r-graph" ,r-graph)
aeb64f3c
RW		 7530 ("r-lattice" ,r-lattice)
7531 ("r-matrixstats" ,r-matrixstats)
d547ce5e 7532 ("r-sparsem" ,r-sparsem)))
5713bbf1 7533 (home-page "https://bioconductor.org/packages/topGO")
d547ce5e
RW		 7534 (synopsis "Enrichment analysis for gene ontology")
7535 (description
7536 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7537terms while accounting for the topology of the GO graph. Different test
7538statistics and different methods for eliminating local similarities and
7539dependencies between GO terms can be implemented and applied.")
7540 ;; Any version of the LGPL applies.
7541 (license license:lgpl2.1+)))
7542
c63cef66
RW		 7543(define-public r-bsgenome
7544 (package
7545 (name "r-bsgenome")
e67850b4 7546 (version "1.46.0")
c63cef66
RW		 7547 (source (origin
7548 (method url-fetch)
7549 (uri (bioconductor-uri "BSgenome" version))
7550 (sha256
7551 (base32
e67850b4 7552 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
c63cef66
RW		 7553 (properties
7554 `((upstream-name . "BSgenome")))
7555 (build-system r-build-system)
7556 (propagated-inputs
7557 `(("r-biocgenerics" ,r-biocgenerics)
7558 ("r-biostrings" ,r-biostrings)
7559 ("r-genomeinfodb" ,r-genomeinfodb)
7560 ("r-genomicranges" ,r-genomicranges)
7561 ("r-iranges" ,r-iranges)
7562 ("r-rsamtools" ,r-rsamtools)
7563 ("r-rtracklayer" ,r-rtracklayer)
7564 ("r-s4vectors" ,r-s4vectors)
7565 ("r-xvector" ,r-xvector)))
5713bbf1 7566 (home-page "https://bioconductor.org/packages/BSgenome")
c63cef66
RW		 7567 (synopsis "Infrastructure for Biostrings-based genome data packages")
7568 (description
7569 "This package provides infrastructure shared by all Biostrings-based
7570genome data packages and support for efficient SNP representation.")
7571 (license license:artistic2.0)))
7572
aa3eeeb5
RJ		 7573(define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7574 (package
7575 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7576 (version "0.99.1")
7577 (source (origin
7578 (method url-fetch)
7579 ;; We cannot use bioconductor-uri here because this tarball is
7580 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7581 (uri (string-append "https://www.bioconductor.org/packages/"
aa3eeeb5
RJ		 7582 "release/data/annotation/src/contrib/"
7583 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7584 version ".tar.gz"))
7585 (sha256
7586 (base32
7587 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7588 (properties
7589 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7590 (build-system r-build-system)
7591 ;; As this package provides little more than a very large data file it
7592 ;; doesn't make sense to build substitutes.
7593 (arguments `(#:substitutable? #f))
7594 (propagated-inputs
7595 `(("r-bsgenome" ,r-bsgenome)))
7596 (home-page
5713bbf1 7597 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
aa3eeeb5
RJ		 7598 (synopsis "Full genome sequences for Homo sapiens")
7599 (description
7600 "This package provides full genome sequences for Homo sapiens from
76011000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7602 (license license:artistic2.0)))
7603
c43a011d
RW		 7604(define-public r-impute
7605 (package
7606 (name "r-impute")
e6ce4bf0 7607 (version "1.52.0")
c43a011d
RW		 7608 (source (origin
7609 (method url-fetch)
7610 (uri (bioconductor-uri "impute" version))
7611 (sha256
7612 (base32
e6ce4bf0 7613 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
c43a011d
RW		 7614 (inputs
7615 `(("gfortran" ,gfortran)))
7616 (build-system r-build-system)
5713bbf1 7617 (home-page "https://bioconductor.org/packages/impute")
c43a011d
RW		 7618 (synopsis "Imputation for microarray data")
7619 (description
7620 "This package provides a function to impute missing gene expression
7621microarray data, using nearest neighbor averaging.")
7622 (license license:gpl2+)))
7623
03ea5a35
RW		 7624(define-public r-seqpattern
7625 (package
7626 (name "r-seqpattern")
0f948b11 7627 (version "1.10.0")
03ea5a35
RW		 7628 (source (origin
7629 (method url-fetch)
7630 (uri (bioconductor-uri "seqPattern" version))
7631 (sha256
7632 (base32
0f948b11 7633 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
03ea5a35
RW		 7634 (properties
7635 `((upstream-name . "seqPattern")))
7636 (build-system r-build-system)
7637 (propagated-inputs
7638 `(("r-biostrings" ,r-biostrings)
7639 ("r-genomicranges" ,r-genomicranges)
7640 ("r-iranges" ,r-iranges)
e92dd6f5 7641 ("r-kernsmooth" ,r-kernsmooth)
03ea5a35 7642 ("r-plotrix" ,r-plotrix)))
5713bbf1 7643 (home-page "https://bioconductor.org/packages/seqPattern")
03ea5a35
RW		 7644 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7645 (description
7646 "This package provides tools to visualize oligonucleotide patterns and
7647sequence motif occurrences across a large set of sequences centred at a common
7648reference point and sorted by a user defined feature.")
7649 (license license:gpl3+)))
7650
cb933df6
RW		 7651(define-public r-genomation
7652 (package
7653 (name "r-genomation")
e127c918 7654 (version "1.10.0")
cb933df6
RW		 7655 (source (origin
7656 (method url-fetch)
7657 (uri (bioconductor-uri "genomation" version))
7658 (sha256
7659 (base32
e127c918 7660 "1ddd8c9w1f1i1ga9rpbwiic8rsaws1chdxx4j38bpyaiy4zhz1ca"))))
cb933df6
RW		 7661 (build-system r-build-system)
7662 (propagated-inputs
7663 `(("r-biostrings" ,r-biostrings)
7664 ("r-bsgenome" ,r-bsgenome)
7665 ("r-data-table" ,r-data-table)
7666 ("r-genomeinfodb" ,r-genomeinfodb)
7667 ("r-genomicalignments" ,r-genomicalignments)
7668 ("r-genomicranges" ,r-genomicranges)
7669 ("r-ggplot2" ,r-ggplot2)
7670 ("r-gridbase" ,r-gridbase)
7671 ("r-impute" ,r-impute)
7672 ("r-iranges" ,r-iranges)
7673 ("r-matrixstats" ,r-matrixstats)
7674 ("r-plotrix" ,r-plotrix)
7675 ("r-plyr" ,r-plyr)
51c3c490 7676 ("r-rcpp" ,r-rcpp)
cb933df6
RW		 7677 ("r-readr" ,r-readr)
7678 ("r-reshape2" ,r-reshape2)
7679 ("r-rsamtools" ,r-rsamtools)
7680 ("r-rtracklayer" ,r-rtracklayer)
51c3c490
RW		 7681 ("r-runit" ,r-runit)
7682 ("r-s4vectors" ,r-s4vectors)
cb933df6
RW		 7683 ("r-seqpattern" ,r-seqpattern)))
7684 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7685 (synopsis "Summary, annotation and visualization of genomic data")
7686 (description
7687 "This package provides a package for summary and annotation of genomic
7688intervals. Users can visualize and quantify genomic intervals over
7689pre-defined functional regions, such as promoters, exons, introns, etc. The
7690genomic intervals represent regions with a defined chromosome position, which
7691may be associated with a score, such as aligned reads from HT-seq experiments,
7692TF binding sites, methylation scores, etc. The package can use any tabular
7693genomic feature data as long as it has minimal information on the locations of
7694genomic intervals. In addition, it can use BAM or BigWig files as input.")
7695 (license license:artistic2.0)))
7696
64efa307
RW		 7697(define-public r-genomationdata
7698 (package
7699 (name "r-genomationdata")
57dc9b58 7700 (version "1.10.0")
64efa307
RW		 7701 (source (origin
7702 (method url-fetch)
7703 ;; We cannot use bioconductor-uri here because this tarball is
7704 ;; located under "data/annotation/" instead of "bioc/".
7705 (uri (string-append "https://bioconductor.org/packages/"
7706 "release/data/experiment/src/contrib/"
7707 "genomationData_" version ".tar.gz"))
7708 (sha256
7709 (base32
57dc9b58 7710 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
64efa307
RW		 7711 (build-system r-build-system)
7712 ;; As this package provides little more than large data files, it doesn't
7713 ;; make sense to build substitutes.
7714 (arguments `(#:substitutable? #f))
7715 (native-inputs
7716 `(("r-knitr" ,r-knitr)))
7717 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7718 (synopsis "Experimental data for use with the genomation package")
7719 (description
7720 "This package contains experimental genetic data for use with the
7721genomation package. Included are Chip Seq, Methylation and Cage data,
7722downloaded from Encode.")
7723 (license license:gpl3+)))
7724
486da491
RW		 7725(define-public r-org-hs-eg-db
7726 (package
7727 (name "r-org-hs-eg-db")
d595fed3 7728 (version "3.5.0")
486da491
RW		 7729 (source (origin
7730 (method url-fetch)
7731 ;; We cannot use bioconductor-uri here because this tarball is
7732 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7733 (uri (string-append "https://www.bioconductor.org/packages/"
486da491
RW		 7734 "release/data/annotation/src/contrib/"
7735 "org.Hs.eg.db_" version ".tar.gz"))
7736 (sha256
7737 (base32
d595fed3 7738 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
486da491
RW		 7739 (properties
7740 `((upstream-name . "org.Hs.eg.db")))
7741 (build-system r-build-system)
7742 (propagated-inputs
7743 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7744 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
486da491
RW		 7745 (synopsis "Genome wide annotation for Human")
7746 (description
676507e3
RW		 7747 "This package contains genome-wide annotations for Human, primarily based
7748on mapping using Entrez Gene identifiers.")
486da491
RW		 7749 (license license:artistic2.0)))
7750
fefedf98
RW		 7751(define-public r-org-ce-eg-db
7752 (package
7753 (name "r-org-ce-eg-db")
e4664290 7754 (version "3.5.0")
fefedf98
RW		 7755 (source (origin
7756 (method url-fetch)
7757 ;; We cannot use bioconductor-uri here because this tarball is
7758 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7759 (uri (string-append "https://www.bioconductor.org/packages/"
fefedf98
RW		 7760 "release/data/annotation/src/contrib/"
7761 "org.Ce.eg.db_" version ".tar.gz"))
7762 (sha256
7763 (base32
e4664290 7764 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
fefedf98
RW		 7765 (properties
7766 `((upstream-name . "org.Ce.eg.db")))
7767 (build-system r-build-system)
7768 (propagated-inputs
7769 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7770 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
fefedf98
RW		 7771 (synopsis "Genome wide annotation for Worm")
7772 (description
7773 "This package provides mappings from Entrez gene identifiers to various
7774annotations for the genome of the model worm Caenorhabditis elegans.")
7775 (license license:artistic2.0)))
7776
16c53a1e
RW		 7777(define-public r-org-dm-eg-db
7778 (package
7779 (name "r-org-dm-eg-db")
19fc299f 7780 (version "3.5.0")
16c53a1e
RW		 7781 (source (origin
7782 (method url-fetch)
7783 ;; We cannot use bioconductor-uri here because this tarball is
7784 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7785 (uri (string-append "https://www.bioconductor.org/packages/"
16c53a1e
RW		 7786 "release/data/annotation/src/contrib/"
7787 "org.Dm.eg.db_" version ".tar.gz"))
7788 (sha256
7789 (base32
19fc299f 7790 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
16c53a1e
RW		 7791 (properties
7792 `((upstream-name . "org.Dm.eg.db")))
7793 (build-system r-build-system)
7794 (propagated-inputs
7795 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7796 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
16c53a1e
RW		 7797 (synopsis "Genome wide annotation for Fly")
7798 (description
7799 "This package provides mappings from Entrez gene identifiers to various
7800annotations for the genome of the model fruit fly Drosophila melanogaster.")
7801 (license license:artistic2.0)))
7802
e761beb9
RW		 7803(define-public r-org-mm-eg-db
7804 (package
7805 (name "r-org-mm-eg-db")
f3569f52 7806 (version "3.5.0")
e761beb9
RW		 7807 (source (origin
7808 (method url-fetch)
7809 ;; We cannot use bioconductor-uri here because this tarball is
7810 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7811 (uri (string-append "https://www.bioconductor.org/packages/"
e761beb9
RW		 7812 "release/data/annotation/src/contrib/"
7813 "org.Mm.eg.db_" version ".tar.gz"))
7814 (sha256
7815 (base32
f3569f52 7816 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
e761beb9
RW		 7817 (properties
7818 `((upstream-name . "org.Mm.eg.db")))
7819 (build-system r-build-system)
7820 (propagated-inputs
7821 `(("r-annotationdbi" ,r-annotationdbi)))
5713bbf1 7822 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
e761beb9
RW		 7823 (synopsis "Genome wide annotation for Mouse")
7824 (description
7825 "This package provides mappings from Entrez gene identifiers to various
7826annotations for the genome of the model mouse Mus musculus.")
7827 (license license:artistic2.0)))
7828
936e7d67
RW		 7829(define-public r-seqlogo
7830 (package
7831 (name "r-seqlogo")
61770089 7832 (version "1.44.0")
936e7d67
RW		 7833 (source
7834 (origin
7835 (method url-fetch)
7836 (uri (bioconductor-uri "seqLogo" version))
7837 (sha256
7838 (base32
61770089 7839 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
936e7d67
RW		 7840 (properties `((upstream-name . "seqLogo")))
7841 (build-system r-build-system)
5713bbf1 7842 (home-page "https://bioconductor.org/packages/seqLogo")
936e7d67
RW		 7843 (synopsis "Sequence logos for DNA sequence alignments")
7844 (description
7845 "seqLogo takes the position weight matrix of a DNA sequence motif and
7846plots the corresponding sequence logo as introduced by Schneider and
7847Stephens (1990).")
7848 (license license:lgpl2.0+)))
7849
c90a4baf
RW		 7850(define-public r-bsgenome-hsapiens-ucsc-hg19
7851 (package
7852 (name "r-bsgenome-hsapiens-ucsc-hg19")
7853 (version "1.4.0")
7854 (source (origin
7855 (method url-fetch)
7856 ;; We cannot use bioconductor-uri here because this tarball is
7857 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7858 (uri (string-append "https://www.bioconductor.org/packages/"
c90a4baf
RW		 7859 "release/data/annotation/src/contrib/"
7860 "BSgenome.Hsapiens.UCSC.hg19_"
7861 version ".tar.gz"))
7862 (sha256
7863 (base32
9d217d27 7864 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
c90a4baf
RW		 7865 (properties
7866 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7867 (build-system r-build-system)
7868 ;; As this package provides little more than a very large data file it
7869 ;; doesn't make sense to build substitutes.
7870 (arguments `(#:substitutable? #f))
7871 (propagated-inputs
7872 `(("r-bsgenome" ,r-bsgenome)))
7873 (home-page
5713bbf1 7874 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
c90a4baf
RW		 7875 (synopsis "Full genome sequences for Homo sapiens")
7876 (description
7877 "This package provides full genome sequences for Homo sapiens as provided
7878by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7879 (license license:artistic2.0)))
7880
a3e90287
RW		 7881(define-public r-bsgenome-mmusculus-ucsc-mm9
7882 (package
7883 (name "r-bsgenome-mmusculus-ucsc-mm9")
7884 (version "1.4.0")
7885 (source (origin
7886 (method url-fetch)
7887 ;; We cannot use bioconductor-uri here because this tarball is
7888 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7889 (uri (string-append "https://www.bioconductor.org/packages/"
a3e90287
RW		 7890 "release/data/annotation/src/contrib/"
7891 "BSgenome.Mmusculus.UCSC.mm9_"
7892 version ".tar.gz"))
7893 (sha256
7894 (base32
7895 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7896 (properties
7897 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7898 (build-system r-build-system)
7899 ;; As this package provides little more than a very large data file it
7900 ;; doesn't make sense to build substitutes.
7901 (arguments `(#:substitutable? #f))
7902 (propagated-inputs
7903 `(("r-bsgenome" ,r-bsgenome)))
7904 (home-page
5713bbf1 7905 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
a3e90287
RW		 7906 (synopsis "Full genome sequences for Mouse")
7907 (description
7908 "This package provides full genome sequences for Mus musculus (Mouse) as
7909provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7910 (license license:artistic2.0)))
7911
4714d521
RW		 7912(define-public r-bsgenome-mmusculus-ucsc-mm10
7913 (package
7914 (name "r-bsgenome-mmusculus-ucsc-mm10")
7915 (version "1.4.0")
7916 (source (origin
7917 (method url-fetch)
7918 ;; We cannot use bioconductor-uri here because this tarball is
7919 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7920 (uri (string-append "https://www.bioconductor.org/packages/"
4714d521
RW		 7921 "release/data/annotation/src/contrib/"
7922 "BSgenome.Mmusculus.UCSC.mm10_"
7923 version ".tar.gz"))
7924 (sha256
7925 (base32
7926 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7927 (properties
7928 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7929 (build-system r-build-system)
7930 ;; As this package provides little more than a very large data file it
7931 ;; doesn't make sense to build substitutes.
7932 (arguments `(#:substitutable? #f))
7933 (propagated-inputs
7934 `(("r-bsgenome" ,r-bsgenome)))
7935 (home-page
5713bbf1 7936 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
4714d521
RW		 7937 (synopsis "Full genome sequences for Mouse")
7938 (description
7939 "This package provides full genome sequences for Mus
7940musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7941in Biostrings objects.")
7942 (license license:artistic2.0)))
7943
c5173d74
RJ		 7944(define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7945 (package
7946 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7947 (version "3.4.0")
7948 (source (origin
7949 (method url-fetch)
7950 ;; We cannot use bioconductor-uri here because this tarball is
7951 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7952 (uri (string-append "https://www.bioconductor.org/packages/"
c5173d74
RJ		 7953 "release/data/annotation/src/contrib/"
7954 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7955 version ".tar.gz"))
7956 (sha256
7957 (base32
7958 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7959 (properties
7960 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7961 (build-system r-build-system)
7962 ;; As this package provides little more than a very large data file it
7963 ;; doesn't make sense to build substitutes.
7964 (arguments `(#:substitutable? #f))
7965 (propagated-inputs
7966 `(("r-bsgenome" ,r-bsgenome)
7967 ("r-genomicfeatures" ,r-genomicfeatures)
7968 ("r-annotationdbi" ,r-annotationdbi)))
7969 (home-page
5713bbf1 7970 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
c5173d74
RJ		 7971 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7972 (description
7973 "This package loads a TxDb object, which is an R interface to
7974prefabricated databases contained in this package. This package provides
7975the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7976based on the knownGene track.")
7977 (license license:artistic2.0)))
7978
943bd627
RW		 7979(define-public r-bsgenome-celegans-ucsc-ce6
7980 (package
7981 (name "r-bsgenome-celegans-ucsc-ce6")
7982 (version "1.4.0")
7983 (source (origin
7984 (method url-fetch)
7985 ;; We cannot use bioconductor-uri here because this tarball is
7986 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 7987 (uri (string-append "https://www.bioconductor.org/packages/"
943bd627
RW		 7988 "release/data/annotation/src/contrib/"
7989 "BSgenome.Celegans.UCSC.ce6_"
7990 version ".tar.gz"))
7991 (sha256
7992 (base32
7993 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7994 (properties
7995 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7996 (build-system r-build-system)
7997 ;; As this package provides little more than a very large data file it
7998 ;; doesn't make sense to build substitutes.
7999 (arguments `(#:substitutable? #f))
8000 (propagated-inputs
8001 `(("r-bsgenome" ,r-bsgenome)))
8002 (home-page
5713bbf1 8003 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
943bd627
RW		 8004 (synopsis "Full genome sequences for Worm")
8005 (description
8006 "This package provides full genome sequences for Caenorhabditis
8007elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8008objects.")
8009 (license license:artistic2.0)))
8010
fc47c7d6
RW		 8011(define-public r-bsgenome-celegans-ucsc-ce10
8012 (package
8013 (name "r-bsgenome-celegans-ucsc-ce10")
8014 (version "1.4.0")
8015 (source (origin
8016 (method url-fetch)
8017 ;; We cannot use bioconductor-uri here because this tarball is
8018 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 8019 (uri (string-append "https://www.bioconductor.org/packages/"
fc47c7d6
RW		 8020 "release/data/annotation/src/contrib/"
8021 "BSgenome.Celegans.UCSC.ce10_"
8022 version ".tar.gz"))
8023 (sha256
8024 (base32
8025 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8026 (properties
8027 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8028 (build-system r-build-system)
8029 ;; As this package provides little more than a very large data file it
8030 ;; doesn't make sense to build substitutes.
8031 (arguments `(#:substitutable? #f))
8032 (propagated-inputs
8033 `(("r-bsgenome" ,r-bsgenome)))
8034 (home-page
5713bbf1 8035 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
fc47c7d6
RW		 8036 (synopsis "Full genome sequences for Worm")
8037 (description
8038 "This package provides full genome sequences for Caenorhabditis
8039elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8040objects.")
8041 (license license:artistic2.0)))
8042
6dc60998
RW		 8043(define-public r-bsgenome-dmelanogaster-ucsc-dm3
8044 (package
8045 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8046 (version "1.4.0")
8047 (source (origin
8048 (method url-fetch)
8049 ;; We cannot use bioconductor-uri here because this tarball is
8050 ;; located under "data/annotation/" instead of "bioc/".
5713bbf1 8051 (uri (string-append "https://www.bioconductor.org/packages/"
6dc60998
RW		 8052 "release/data/annotation/src/contrib/"
8053 "BSgenome.Dmelanogaster.UCSC.dm3_"
8054 version ".tar.gz"))
8055 (sha256
8056 (base32
8057 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8058 (properties
8059 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8060 (build-system r-build-system)
8061 ;; As this package provides little more than a very large data file it
8062 ;; doesn't make sense to build substitutes.
8063 (arguments `(#:substitutable? #f))
8064 (propagated-inputs
8065 `(("r-bsgenome" ,r-bsgenome)))
8066 (home-page
5713bbf1 8067 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
6dc60998
RW		 8068 (synopsis "Full genome sequences for Fly")
8069 (description
8070 "This package provides full genome sequences for Drosophila
8071melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8072Biostrings objects.")
8073 (license license:artistic2.0)))
8074
ae2462f7
RW		 8075(define-public r-motifrg
8076 (package
8077 (name "r-motifrg")
ce59d625 8078 (version "1.22.0")
ae2462f7
RW		 8079 (source
8080 (origin
8081 (method url-fetch)
8082 (uri (bioconductor-uri "motifRG" version))
8083 (sha256
8084 (base32
ce59d625 8085 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
ae2462f7
RW		 8086 (properties `((upstream-name . "motifRG")))
8087 (build-system r-build-system)
8088 (propagated-inputs
8089 `(("r-biostrings" ,r-biostrings)
8090 ("r-bsgenome" ,r-bsgenome)
007424b5 8091 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
ae2462f7
RW		 8092 ("r-iranges" ,r-iranges)
8093 ("r-seqlogo" ,r-seqlogo)
8094 ("r-xvector" ,r-xvector)))
5713bbf1 8095 (home-page "https://bioconductor.org/packages/motifRG")
ae2462f7
RW		 8096 (synopsis "Discover motifs in high throughput sequencing data")
8097 (description
8098 "This package provides tools for discriminative motif discovery in high
8099throughput genetic sequencing data sets using regression methods.")
8100 (license license:artistic2.0)))
8101
a5002ae7
AE		 8102(define-public r-qtl
8103 (package
8104 (name "r-qtl")
c8a9b2bc 8105 (version "1.41-6")
a5002ae7
AE		 8106 (source
8107 (origin
8108 (method url-fetch)
8109 (uri (string-append "mirror://cran/src/contrib/qtl_"
8110 version ".tar.gz"))
8111 (sha256
8112 (base32
c8a9b2bc 8113 "067az4v432zxp6lxck8d7vlh9w4r13r0mvw5zsglyaqwsh3d9sad"))))
a5002ae7
AE		 8114 (build-system r-build-system)
8115 (home-page "http://rqtl.org/")
8116 (synopsis "R package for analyzing QTL experiments in genetics")
8117 (description "R/qtl is an extension library for the R statistics
8118system. It is used to analyze experimental crosses for identifying
8119genes contributing to variation in quantitative traits (so-called
8120quantitative trait loci, QTLs).
8121
8122Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8123identify genotyping errors, and to perform single-QTL and two-QTL,
8124two-dimensional genome scans.")
8125 (license license:gpl3)))
d1e32822 8126
9e3ba31c
RJ		 8127(define-public r-zlibbioc
8128 (package
8129 (name "r-zlibbioc")
5c184700 8130 (version "1.24.0")
9e3ba31c
RJ		 8131 (source (origin
8132 (method url-fetch)
8133 (uri (bioconductor-uri "zlibbioc" version))
8134 (sha256
8135 (base32
5c184700 8136 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
9e3ba31c
RJ		 8137 (properties
8138 `((upstream-name . "zlibbioc")))
8139 (build-system r-build-system)
8140 (home-page "https://bioconductor.org/packages/zlibbioc")
8141 (synopsis "Provider for zlib-1.2.5 to R packages")
8142 (description "This package uses the source code of zlib-1.2.5 to create
8143libraries for systems that do not have these available via other means.")
8144 (license license:artistic2.0)))
8145
e619a5c2
RW		 8146(define-public r-r4rna
8147 (package
8148 (name "r-r4rna")
8149 (version "0.1.4")
8150 (source
8151 (origin
8152 (method url-fetch)
8153 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8154 version ".tar.gz"))
8155 (sha256
8156 (base32
8157 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8158 (build-system r-build-system)
8159 (propagated-inputs
8160 `(("r-optparse" ,r-optparse)
8161 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8162 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8163 (synopsis "Analysis framework for RNA secondary structure")
8164 (description
8165 "The R4RNA package aims to be a general framework for the analysis of RNA
8166secondary structure and comparative analysis in R.")
8167 (license license:gpl3+)))
8168
52765a63
RW		 8169(define-public r-rhtslib
8170 (package
8171 (name "r-rhtslib")
1d0263b4 8172 (version "1.10.0")
52765a63
RW		 8173 (source
8174 (origin
8175 (method url-fetch)
8176 (uri (bioconductor-uri "Rhtslib" version))
8177 (sha256
8178 (base32
1d0263b4 8179 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
52765a63
RW		 8180 (properties `((upstream-name . "Rhtslib")))
8181 (build-system r-build-system)
8182 (propagated-inputs
8183 `(("r-zlibbioc" ,r-zlibbioc)))
8184 (inputs
8185 `(("zlib" ,zlib)))
53ca52f0
RW		 8186 (native-inputs
8187 `(("autoconf" ,autoconf)))
52765a63
RW		 8188 (home-page "https://github.com/nhayden/Rhtslib")
8189 (synopsis "High-throughput sequencing library as an R package")
8190 (description
8191 "This package provides the HTSlib C library for high-throughput
8192nucleotide sequence analysis. The package is primarily useful to developers
8193of other R packages who wish to make use of HTSlib.")
8194 (license license:lgpl2.0+)))
8195
fe02c4c9
RW		 8196(define-public r-bamsignals
8197 (package
8198 (name "r-bamsignals")
da153b7f 8199 (version "1.10.0")
fe02c4c9
RW		 8200 (source
8201 (origin
8202 (method url-fetch)
8203 (uri (bioconductor-uri "bamsignals" version))
8204 (sha256
8205 (base32
da153b7f 8206 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
fe02c4c9
RW		 8207 (build-system r-build-system)
8208 (propagated-inputs
8209 `(("r-biocgenerics" ,r-biocgenerics)
8210 ("r-genomicranges" ,r-genomicranges)
8211 ("r-iranges" ,r-iranges)
8212 ("r-rcpp" ,r-rcpp)
8213 ("r-rhtslib" ,r-rhtslib)
8214 ("r-zlibbioc" ,r-zlibbioc)))
8215 (inputs
8216 `(("zlib" ,zlib)))
5713bbf1 8217 (home-page "https://bioconductor.org/packages/bamsignals")
fe02c4c9
RW		 8218 (synopsis "Extract read count signals from bam files")
8219 (description
8220 "This package allows to efficiently obtain count vectors from indexed bam
8221files. It counts the number of nucleotide sequence reads in given genomic
8222ranges and it computes reads profiles and coverage profiles. It also handles
8223paired-end data.")
8224 (license license:gpl2+)))
8225
89984be4
RW		 8226(define-public r-rcas
8227 (package
8228 (name "r-rcas")
d82937fb 8229 (version "1.3.4")
89984be4
RW		 8230 (source (origin
8231 (method url-fetch)
8232 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8233 version ".tar.gz"))
8234 (file-name (string-append name "-" version ".tar.gz"))
8235 (sha256
8236 (base32
d82937fb 8237 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
89984be4
RW		 8238 (build-system r-build-system)
8239 (native-inputs
8240 `(("r-knitr" ,r-knitr)
8241 ("r-testthat" ,r-testthat)
8242 ;; During vignette building knitr checks that "pandoc-citeproc"
8243 ;; is in the PATH.
8244 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8245 (propagated-inputs
8246 `(("r-data-table" ,r-data-table)
8247 ("r-biomart" ,r-biomart)
8248 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8249 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8250 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8251 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8252 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8253 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8254 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8255 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8256 ("r-topgo" ,r-topgo)
8257 ("r-dt" ,r-dt)
ebfd6a71 8258 ("r-pbapply" ,r-pbapply)
89984be4 8259 ("r-plotly" ,r-plotly)
2c8d6c0b 8260 ("r-plotrix" ,r-plotrix)
89984be4
RW		 8261 ("r-motifrg" ,r-motifrg)
8262 ("r-genomation" ,r-genomation)
8263 ("r-genomicfeatures" ,r-genomicfeatures)
8264 ("r-rtracklayer" ,r-rtracklayer)
8265 ("r-rmarkdown" ,r-rmarkdown)))
8266 (synopsis "RNA-centric annotation system")
8267 (description
8268 "RCAS aims to be a standalone RNA-centric annotation system that provides
8269intuitive reports and publication-ready graphics. This package provides the R
8270library implementing most of the pipeline's features.")
8271 (home-page "https://github.com/BIMSBbioinfo/RCAS")
75690c9f 8272 (license license:artistic2.0)))
89984be4 8273
50937297
RW		 8274(define-public rcas-web
8275 (package
8276 (name "rcas-web")
01d87d3c 8277 (version "0.0.4")
50937297
RW		 8278 (source
8279 (origin
8280 (method url-fetch)
8281 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8282 "releases/download/v" version
8283 "/rcas-web-" version ".tar.gz"))
8284 (sha256
8285 (base32
01d87d3c 8286 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
50937297
RW		 8287 (build-system gnu-build-system)
8288 (arguments
8289 `(#:phases
8290 (modify-phases %standard-phases
8291 (add-after 'install 'wrap-executable
8292 (lambda* (#:key inputs outputs #:allow-other-keys)
8293 (let* ((out (assoc-ref outputs "out"))
8294 (json (assoc-ref inputs "guile-json"))
8295 (redis (assoc-ref inputs "guile-redis"))
8296 (path (string-append
8297 json "/share/guile/site/2.2:"
8298 redis "/share/guile/site/2.2")))
8299 (wrap-program (string-append out "/bin/rcas-web")
8300 `("GUILE_LOAD_PATH" ":" = (,path))
8301 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8302 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8303 #t)))))
8304 (inputs
2d7c4ae3 8305 `(("r-minimal" ,r-minimal)
50937297 8306 ("r-rcas" ,r-rcas)
f6396d86 8307 ("guile-next" ,guile-2.2)
2252f087 8308 ("guile-json" ,guile-json)
50937297
RW		 8309 ("guile-redis" ,guile2.2-redis)))
8310 (native-inputs
8311 `(("pkg-config" ,pkg-config)))
8312 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8313 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8314 (description "This package provides a simple web interface for the
8315@dfn{RNA-centric annotation system} (RCAS).")
8316 (license license:agpl3+)))
8317
7500e42b
RJ		 8318(define-public r-mutationalpatterns
8319 (package
8320 (name "r-mutationalpatterns")
b9bf2b89 8321 (version "1.4.2")
7500e42b
RJ		 8322 (source
8323 (origin
8324 (method url-fetch)
8325 (uri (bioconductor-uri "MutationalPatterns" version))
8326 (sha256
8327 (base32
b9bf2b89 8328 "08ay9h5cqsi8ypb6r0g4rfa5l1g06jgfzl64wmhgz134yqbl7vfv"))))
7500e42b
RJ		 8329 (build-system r-build-system)
8330 (propagated-inputs
8331 `(("r-biocgenerics" ,r-biocgenerics)
8332 ("r-biostrings" ,r-biostrings)
cf4ac4e4
RJ		 8333 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8334 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7500e42b
RJ		 8335 ("r-genomicranges" ,r-genomicranges)
8336 ("r-genomeinfodb" ,r-genomeinfodb)
8337 ("r-ggplot2" ,r-ggplot2)
8338 ("r-gridextra" ,r-gridextra)
8339 ("r-iranges" ,r-iranges)
8340 ("r-nmf" ,r-nmf)
8341 ("r-plyr" ,r-plyr)
8342 ("r-pracma" ,r-pracma)
8343 ("r-reshape2" ,r-reshape2)
39d9098d
RW		 8344 ("r-cowplot" ,r-cowplot)
8345 ("r-ggdendro" ,r-ggdendro)
8346 ("r-s4vectors" ,r-s4vectors)
7500e42b
RJ		 8347 ("r-summarizedexperiment" ,r-summarizedexperiment)
8348 ("r-variantannotation" ,r-variantannotation)))
5713bbf1 8349 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
7500e42b
RJ		 8350 (synopsis "Extract and visualize mutational patterns in genomic data")
8351 (description "This package provides an extensive toolset for the
8352characterization and visualization of a wide range of mutational patterns
8353in SNV base substitution data.")
8354 (license license:expat)))
8355
d7160529
RW		 8356(define-public r-wgcna
8357 (package
8358 (name "r-wgcna")
1b22ecda 8359 (version "1.61")
d7160529
RW		 8360 (source
8361 (origin
8362 (method url-fetch)
8363 (uri (cran-uri "WGCNA" version))
8364 (sha256
8365 (base32
1b22ecda 8366 "1vrc2k33a196hrrl7k0z534fp96vv0shmigcr65ny1q0v6lq0h6i"))))
d7160529
RW		 8367 (properties `((upstream-name . "WGCNA")))
8368 (build-system r-build-system)
8369 (propagated-inputs
8370 `(("r-annotationdbi" ,r-annotationdbi)
8371 ("r-doparallel" ,r-doparallel)
8372 ("r-dynamictreecut" ,r-dynamictreecut)
8373 ("r-fastcluster" ,r-fastcluster)
8374 ("r-foreach" ,r-foreach)
8375 ("r-go-db" ,r-go-db)
8376 ("r-hmisc" ,r-hmisc)
8377 ("r-impute" ,r-impute)
1b22ecda
RW		 8378 ("r-rcpp" ,r-rcpp)
8379 ("r-robust" ,r-robust)
8380 ("r-survival" ,r-survival)
d7160529
RW		 8381 ("r-matrixstats" ,r-matrixstats)
8382 ("r-preprocesscore" ,r-preprocesscore)))
8383 (home-page
8384 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8385 (synopsis "Weighted correlation network analysis")
8386 (description
8387 "This package provides functions necessary to perform Weighted
8388Correlation Network Analysis on high-dimensional data. It includes functions
8389for rudimentary data cleaning, construction and summarization of correlation
8390networks, module identification and functions for relating both variables and
8391modules to sample traits. It also includes a number of utility functions for
8392data manipulation and visualization.")
8393 (license license:gpl2+)))
8394
c827f202
RW		 8395(define-public r-chipkernels
8396 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8397 (revision "1"))
8398 (package
8399 (name "r-chipkernels")
8400 (version (string-append "1.1-" revision "." (string-take commit 9)))
8401 (source
8402 (origin
8403 (method git-fetch)
8404 (uri (git-reference
8405 (url "https://github.com/ManuSetty/ChIPKernels.git")
8406 (commit commit)))
8407 (file-name (string-append name "-" version))
8408 (sha256
8409 (base32
8410 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8411 (build-system r-build-system)
8412 (propagated-inputs
8413 `(("r-iranges" ,r-iranges)
8414 ("r-xvector" ,r-xvector)
8415 ("r-biostrings" ,r-biostrings)
8416 ("r-bsgenome" ,r-bsgenome)
8417 ("r-gtools" ,r-gtools)
8418 ("r-genomicranges" ,r-genomicranges)
8419 ("r-sfsmisc" ,r-sfsmisc)
8420 ("r-kernlab" ,r-kernlab)
8421 ("r-s4vectors" ,r-s4vectors)
8422 ("r-biocgenerics" ,r-biocgenerics)))
8423 (home-page "https://github.com/ManuSetty/ChIPKernels")
8424 (synopsis "Build string kernels for DNA Sequence analysis")
8425 (description "ChIPKernels is an R package for building different string
8426kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8427must be built and this dictionary can be used for determining kernels for DNA
8428Sequences.")
8429 (license license:gpl2+))))
8430
2d9fb170
RW		 8431(define-public r-seqgl
8432 (package
8433 (name "r-seqgl")
8434 (version "1.1.4")
8435 (source
8436 (origin
8437 (method url-fetch)
8438 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8439 "archive/" version ".tar.gz"))
8440 (file-name (string-append name "-" version ".tar.gz"))
8441 (sha256
8442 (base32
8443 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8444 (build-system r-build-system)
8445 (propagated-inputs
8446 `(("r-biostrings" ,r-biostrings)
8447 ("r-chipkernels" ,r-chipkernels)
8448 ("r-genomicranges" ,r-genomicranges)
8449 ("r-spams" ,r-spams)
8450 ("r-wgcna" ,r-wgcna)
8451 ("r-fastcluster" ,r-fastcluster)))
8452 (home-page "https://github.com/ManuSetty/SeqGL")
8453 (synopsis "Group lasso for Dnase/ChIP-seq data")
8454 (description "SeqGL is a group lasso based algorithm to extract
8455transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8456This package presents a method which uses group lasso to discriminate between
8457bound and non bound genomic regions to accurately identify transcription
8458factors bound at the specific regions.")
8459 (license license:gpl2+)))
8460
bd3be46e
RW		 8461(define-public r-gkmsvm
8462 (package
8463 (name "r-gkmsvm")
8464 (version "0.71.0")
8465 (source
8466 (origin
8467 (method url-fetch)
8468 (uri (cran-uri "gkmSVM" version))
8469 (sha256
8470 (base32
8471 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8472 (properties `((upstream-name . "gkmSVM")))
8473 (build-system r-build-system)
8474 (propagated-inputs
8475 `(("r-biocgenerics" ,r-biocgenerics)
8476 ("r-biostrings" ,r-biostrings)
8477 ("r-genomeinfodb" ,r-genomeinfodb)
8478 ("r-genomicranges" ,r-genomicranges)
8479 ("r-iranges" ,r-iranges)
8480 ("r-kernlab" ,r-kernlab)
8481 ("r-rcpp" ,r-rcpp)
8482 ("r-rocr" ,r-rocr)
8483 ("r-rtracklayer" ,r-rtracklayer)
8484 ("r-s4vectors" ,r-s4vectors)
8485 ("r-seqinr" ,r-seqinr)))
e9960d8c 8486 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
bd3be46e
RW		 8487 (synopsis "Gapped-kmer support vector machine")
8488 (description
8489 "This R package provides tools for training gapped-kmer SVM classifiers
8490for DNA and protein sequences. This package supports several sequence
8491kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8492 (license license:gpl2+)))
8493
d4af25b5
RJPB		 8494(define-public r-tximport
8495 (package
8496 (name "r-tximport")
19e8929c 8497 (version "1.6.0")
d4af25b5
RJPB		 8498 (source (origin
8499 (method url-fetch)
8500 (uri (bioconductor-uri "tximport" version))
8501 (sha256
8502 (base32
19e8929c 8503 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
d4af25b5 8504 (build-system r-build-system)
5713bbf1 8505 (home-page "https://bioconductor.org/packages/tximport")
d4af25b5
RJPB		 8506 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8507 (description
8508 "This package provides tools to import transcript-level abundance,
8509estimated counts and transcript lengths, and to summarize them into matrices
8510for use with downstream gene-level analysis packages. Average transcript
8511length, weighted by sample-specific transcript abundance estimates, is
8512provided as a matrix which can be used as an offset for different expression
8513of gene-level counts.")
8514 (license license:gpl2+)))
8515
69f2b3bd
RJPB		 8516(define-public r-rhdf5
8517 (package
8518 (name "r-rhdf5")
e6b332d4 8519 (version "2.22.0")
69f2b3bd
RJPB		 8520 (source (origin
8521 (method url-fetch)
8522 (uri (bioconductor-uri "rhdf5" version))
8523 (sha256
8524 (base32
e6b332d4 8525 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
69f2b3bd
RJPB		 8526 (build-system r-build-system)
8527 (arguments
8528 `(#:phases
8529 (modify-phases %standard-phases
8530 (add-after 'unpack 'unpack-smallhdf5
8531 (lambda* (#:key outputs #:allow-other-keys)
8532 (system* "tar" "-xzvf"
8533 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
69f2b3bd
RJPB		 8534 (substitute* "src/hdf5/configure"
8535 (("/bin/mv") "mv"))
8536 #t)))))
8537 (propagated-inputs
8538 `(("r-zlibbioc" ,r-zlibbioc)))
8539 (inputs
8540 `(("perl" ,perl)
8541 ("zlib" ,zlib)))
5713bbf1 8542 (home-page "https://bioconductor.org/packages/rhdf5")
69f2b3bd
RJPB		 8543 (synopsis "HDF5 interface to R")
8544 (description
8545 "This R/Bioconductor package provides an interface between HDF5 and R.
8546HDF5's main features are the ability to store and access very large and/or
8547complex datasets and a wide variety of metadata on mass storage (disk) through
8548a completely portable file format. The rhdf5 package is thus suited for the
8549exchange of large and/or complex datasets between R and other software
8550package, and for letting R applications work on datasets that are larger than
8551the available RAM.")
8552 (license license:artistic2.0)))
8553
17cddc17
RW		 8554(define-public r-annotationfilter
8555 (package
8556 (name "r-annotationfilter")
598dacf6 8557 (version "1.2.0")
17cddc17
RW		 8558 (source (origin
8559 (method url-fetch)
8560 (uri (bioconductor-uri "AnnotationFilter" version))
8561 (sha256
8562 (base32
598dacf6 8563 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
17cddc17
RW		 8564 (properties
8565 `((upstream-name . "AnnotationFilter")))
8566 (build-system r-build-system)
8567 (propagated-inputs
8568 `(("r-genomicranges" ,r-genomicranges)
8569 ("r-lazyeval" ,r-lazyeval)))
8570 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8571 (synopsis "Facilities for filtering Bioconductor annotation resources")
8572 (description
8573 "This package provides classes and other infrastructure to implement
8574filters for manipulating Bioconductor annotation resources. The filters are
8575used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8576 (license license:artistic2.0)))
8577
66e40e00
RW		 8578(define-public emboss
8579 (package
8580 (name "emboss")
8581 (version "6.5.7")
8582 (source (origin
8583 (method url-fetch)
8584 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8585 (version-major+minor version) ".0/"
8586 "EMBOSS-" version ".tar.gz"))
8587 (sha256
8588 (base32
8589 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8590 (build-system gnu-build-system)
8591 (arguments
8592 `(#:configure-flags
8593 (list (string-append "--with-hpdf="
8594 (assoc-ref %build-inputs "libharu")))
8595 #:phases
8596 (modify-phases %standard-phases
8597 (add-after 'unpack 'fix-checks
8598 (lambda _
8599 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8600 ;; and zlib, but assume that they are all found at the same
8601 ;; prefix.
8602 (substitute* "configure.in"
8603 (("CHECK_PNGDRIVER")
8604 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8605AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8606AM_CONDITIONAL(AMPNG, true)"))
8607 #t))
d10092b8 8608 (add-after 'fix-checks 'disable-update-check
66e40e00
RW		 8609 (lambda _
8610 ;; At build time there is no connection to the Internet, so
8611 ;; looking for updates will not work.
8612 (substitute* "Makefile.am"
8613 (("\\$\\(bindir\\)/embossupdate") ""))
8614 #t))
d10092b8 8615 (add-after 'disable-update-check 'autogen
66e40e00
RW		 8616 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8617 (inputs
8618 `(("perl" ,perl)
8619 ("libpng" ,libpng)
8620 ("gd" ,gd)
8621 ("libx11" ,libx11)
8622 ("libharu" ,libharu)
8623 ("zlib" ,zlib)))
8624 (native-inputs
8625 `(("autoconf" ,autoconf)
8626 ("automake" ,automake)
8627 ("libtool" ,libtool)
8628 ("pkg-config" ,pkg-config)))
8629 (home-page "http://emboss.sourceforge.net")
8630 (synopsis "Molecular biology analysis suite")
8631 (description "EMBOSS is the \"European Molecular Biology Open Software
8632Suite\". EMBOSS is an analysis package specially developed for the needs of
8633the molecular biology (e.g. EMBnet) user community. The software
8634automatically copes with data in a variety of formats and even allows
8635transparent retrieval of sequence data from the web. It also provides a
8636number of libraries for the development of software in the field of molecular
8637biology. EMBOSS also integrates a range of currently available packages and
8638tools for sequence analysis into a seamless whole.")
8639 (license license:gpl2+)))
8640
1f1b20b8
RW		 8641(define-public bits
8642 (let ((revision "1")
8643 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8644 (package
8645 (name "bits")
8646 ;; The version is 2.13.0 even though no release archives have been
8647 ;; published as yet.
8648 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8649 (source (origin
8650 (method git-fetch)
8651 (uri (git-reference
8652 (url "https://github.com/arq5x/bits.git")
8653 (commit commit)))
8654 (file-name (string-append name "-" version "-checkout"))
8655 (sha256
8656 (base32
8657 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8658 (build-system gnu-build-system)
8659 (arguments
8660 `(#:tests? #f ;no tests included
8661 #:phases
8662 (modify-phases %standard-phases
8663 (delete 'configure)
8664 (add-after 'unpack 'remove-cuda
8665 (lambda _
8666 (substitute* "Makefile"
8667 ((".*_cuda") "")
8668 (("(bits_test_intersections) \\\\" _ match) match))
8669 #t))
8670 (replace 'install
8671 (lambda* (#:key outputs #:allow-other-keys)
8672 (copy-recursively
8673 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8674 #t)))))
8675 (inputs
8676 `(("gsl" ,gsl)
8677 ("zlib" ,zlib)))
8678 (home-page "https://github.com/arq5x/bits")
8679 (synopsis "Implementation of binary interval search algorithm")
8680 (description "This package provides an implementation of the
8681BITS (Binary Interval Search) algorithm, an approach to interval set
8682intersection. It is especially suited for the comparison of diverse genomic
8683datasets and the exploration of large datasets of genome
8684intervals (e.g. genes, sequence alignments).")
8685 (license license:gpl2))))
8686
e62ffce5 8687(define-public piranha
883302da
RW		 8688 ;; There is no release tarball for the latest version. The latest commit is
8689 ;; older than one year at the time of this writing.
8690 (let ((revision "1")
8691 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8692 (package
8693 (name "piranha")
8694 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8695 (source (origin
8696 (method git-fetch)
8697 (uri (git-reference
8698 (url "https://github.com/smithlabcode/piranha.git")
8699 (commit commit)))
8700 (sha256
8701 (base32
8702 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8703 (build-system gnu-build-system)
8704 (arguments
8705 `(#:test-target "test"
8706 #:phases
8707 (modify-phases %standard-phases
8708 (add-after 'unpack 'copy-smithlab-cpp
8709 (lambda* (#:key inputs #:allow-other-keys)
e62ffce5 8710 (for-each (lambda (file)
883302da
RW		 8711 (install-file file "./src/smithlab_cpp/"))
8712 (find-files (assoc-ref inputs "smithlab-cpp")))
8713 #t))
8714 (add-after 'install 'install-to-store
8715 (lambda* (#:key outputs #:allow-other-keys)
8716 (let* ((out (assoc-ref outputs "out"))
8717 (bin (string-append out "/bin")))
883302da
RW		 8718 (for-each (lambda (file)
8719 (install-file file bin))
8720 (find-files "bin" ".*")))
8721 #t)))
8722 #:configure-flags
8723 (list (string-append "--with-bam_tools_headers="
8724 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8725 (string-append "--with-bam_tools_library="
8726 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8727 (inputs
8728 `(("bamtools" ,bamtools)
8729 ("samtools" ,samtools-0.1)
8730 ("gsl" ,gsl)
8731 ("smithlab-cpp"
8732 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8733 (origin
8734 (method git-fetch)
8735 (uri (git-reference
8736 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8737 (commit commit)))
8738 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8739 (sha256
8740 (base32
8741 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8742 (native-inputs
8743 `(("python" ,python-2)))
8744 (home-page "https://github.com/smithlabcode/piranha")
8745 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8746 (description
8747 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
e62ffce5
RW		 8748RIP-seq experiments. It takes input in BED or BAM format and identifies
8749regions of statistically significant read enrichment. Additional covariates
8750may optionally be provided to further inform the peak-calling process.")
883302da 8751 (license license:gpl3+))))
e62ffce5 8752
d1e32822
RW		 8753(define-public pepr
8754 (package
8755 (name "pepr")
8756 (version "1.0.9")
8757 (source (origin
8758 (method url-fetch)
8759 (uri (string-append "https://pypi.python.org/packages/source/P"
8760 "/PePr/PePr-" version ".tar.gz"))
8761 (sha256
8762 (base32
8763 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8764 (build-system python-build-system)
8765 (arguments
8766 `(#:python ,python-2 ; python2 only
b41a05ce 8767 #:tests? #f)) ; no tests included
d1e32822
RW		 8768 (propagated-inputs
8769 `(("python2-numpy" ,python2-numpy)
8770 ("python2-scipy" ,python2-scipy)
8771 ("python2-pysam" ,python2-pysam)))
0c6c9c00 8772 (home-page "https://github.com/shawnzhangyx/PePr")
d1e32822
RW		 8773 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8774 (description
8775 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8776that is primarily designed for data with biological replicates. It uses a
8777negative binomial distribution to model the read counts among the samples in
8778the same group, and look for consistent differences between ChIP and control
8779group or two ChIP groups run under different conditions.")
8780 (license license:gpl3+)))
6b49a37e
RJ		 8781
8782(define-public filevercmp
8783 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8784 (package
8785 (name "filevercmp")
8786 (version (string-append "0-1." (string-take commit 7)))
8787 (source (origin
8788 (method url-fetch)
8789 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8790 commit ".tar.gz"))
8791 (file-name (string-append name "-" version ".tar.gz"))
8792 (sha256
8793 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8794 (build-system gnu-build-system)
8795 (arguments
8796 `(#:tests? #f ; There are no tests to run.
8797 #:phases
8798 (modify-phases %standard-phases
8799 (delete 'configure) ; There is no configure phase.
8800 (replace 'install
8801 (lambda* (#:key outputs #:allow-other-keys)
8802 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8803 (install-file "filevercmp" bin)))))))
8804 (home-page "https://github.com/ekg/filevercmp")
8805 (synopsis "This program compares version strings")
8806 (description "This program compares version strings. It intends to be a
8807replacement for strverscmp.")
8808 (license license:gpl3+))))
5fb5dffb
RW		 8809
8810(define-public multiqc
8811 (package
8812 (name "multiqc")
66865ab8 8813 (version "1.3")
5fb5dffb
RW		 8814 (source
8815 (origin
8816 (method url-fetch)
8817 (uri (pypi-uri "multiqc" version))
8818 (sha256
8819 (base32
66865ab8 8820 "0fx1sx53znbgzfhbbiyd8j6cg5llpcsl5q5c45jy2c81d12piqfd"))))
5fb5dffb
RW		 8821 (build-system python-build-system)
8822 (propagated-inputs
66865ab8
RW		 8823 `(("python-enum34" ,python-enum34)
8824 ("python-jinja2" ,python-jinja2)
5fb5dffb
RW		 8825 ("python-simplejson" ,python-simplejson)
8826 ("python-pyyaml" ,python-pyyaml)
8827 ("python-click" ,python-click)
799247d2
RW		 8828 ("python-spectra" ,python-spectra)
8829 ("python-requests" ,python-requests)
8830 ("python-markdown" ,python-markdown)
8831 ("python-lzstring" ,python-lzstring)
5fb5dffb 8832 ("python-matplotlib" ,python-matplotlib)
1778ea74
RW		 8833 ("python-numpy" ,python-numpy)
8834 ;; MultQC checks for the presence of nose at runtime.
8835 ("python-nose" ,python-nose)))
5fb5dffb
RW		 8836 (home-page "http://multiqc.info")
8837 (synopsis "Aggregate bioinformatics analysis reports")
8838 (description
8839 "MultiQC is a tool to aggregate bioinformatics results across many
8840samples into a single report. It contains modules for a large number of
8841common bioinformatics tools.")
66865ab8 8842 (license license:gpl3+)))
6193563a
RW		 8843
8844(define-public r-chipseq
8845 (package
8846 (name "r-chipseq")
eeaa6967 8847 (version "1.28.0")
6193563a
RW		 8848 (source
8849 (origin
8850 (method url-fetch)
8851 (uri (bioconductor-uri "chipseq" version))
8852 (sha256
8853 (base32
eeaa6967 8854 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
6193563a
RW		 8855 (build-system r-build-system)
8856 (propagated-inputs
8857 `(("r-biocgenerics" ,r-biocgenerics)
8858 ("r-genomicranges" ,r-genomicranges)
8859 ("r-iranges" ,r-iranges)
eeaa6967 8860 ("r-lattice" ,r-lattice)
6193563a
RW		 8861 ("r-s4vectors" ,r-s4vectors)
8862 ("r-shortread" ,r-shortread)))
5713bbf1 8863 (home-page "https://bioconductor.org/packages/chipseq")
6193563a
RW		 8864 (synopsis "Package for analyzing ChIPseq data")
8865 (description
8866 "This package provides tools for processing short read data from ChIPseq
8867experiments.")
8868 (license license:artistic2.0)))
d407bdb9
RW		 8869
8870(define-public r-copyhelper
8871 (package
8872 (name "r-copyhelper")
8873 (version "1.6.0")
8874 (source
8875 (origin
8876 (method url-fetch)
5713bbf1 8877 (uri (string-append "https://bioconductor.org/packages/release/"
d407bdb9
RW		 8878 "data/experiment/src/contrib/CopyhelpeR_"
8879 version ".tar.gz"))
8880 (sha256
8881 (base32
8882 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8883 (properties `((upstream-name . "CopyhelpeR")))
8884 (build-system r-build-system)
5713bbf1 8885 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
d407bdb9
RW		 8886 (synopsis "Helper files for CopywriteR")
8887 (description
8888 "This package contains the helper files that are required to run the
8889Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8890and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8891mm10. In addition, it contains a blacklist filter to remove regions that
8892display copy number variation. Files are stored as GRanges objects from the
8893GenomicRanges Bioconductor package.")
8894 (license license:gpl2)))
3a3bf2f8
RW		 8895
8896(define-public r-copywriter
8897 (package
8898 (name "r-copywriter")
c126ba69 8899 (version "2.10.0")
3a3bf2f8
RW		 8900 (source
8901 (origin
8902 (method url-fetch)
8903 (uri (bioconductor-uri "CopywriteR" version))
8904 (sha256
8905 (base32
c126ba69 8906 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
3a3bf2f8
RW		 8907 (properties `((upstream-name . "CopywriteR")))
8908 (build-system r-build-system)
8909 (propagated-inputs
8910 `(("r-biocparallel" ,r-biocparallel)
8911 ("r-chipseq" ,r-chipseq)
8912 ("r-copyhelper" ,r-copyhelper)
8913 ("r-data-table" ,r-data-table)
8914 ("r-dnacopy" ,r-dnacopy)
8915 ("r-futile-logger" ,r-futile-logger)
8916 ("r-genomeinfodb" ,r-genomeinfodb)
8917 ("r-genomicalignments" ,r-genomicalignments)
8918 ("r-genomicranges" ,r-genomicranges)
8919 ("r-gtools" ,r-gtools)
8920 ("r-iranges" ,r-iranges)
8921 ("r-matrixstats" ,r-matrixstats)
8922 ("r-rsamtools" ,r-rsamtools)
8923 ("r-s4vectors" ,r-s4vectors)))
8924 (home-page "https://github.com/PeeperLab/CopywriteR")
8925 (synopsis "Copy number information from targeted sequencing")
8926 (description
8927 "CopywriteR extracts DNA copy number information from targeted sequencing
8928by utilizing off-target reads. It allows for extracting uniformly distributed
8929copy number information, can be used without reference, and can be applied to
8930sequencing data obtained from various techniques including chromatin
8931immunoprecipitation and target enrichment on small gene panels. Thereby,
8932CopywriteR constitutes a widely applicable alternative to available copy
8933number detection tools.")
8934 (license license:gpl2)))
dd42a330 8935
bf3fa996
RW		 8936(define-public r-methylkit
8937 (package
8938 (name "r-methylkit")
91e18679 8939 (version "1.4.0")
bf3fa996
RW		 8940 (source (origin
8941 (method url-fetch)
8942 (uri (bioconductor-uri "methylKit" version))
8943 (sha256
8944 (base32
91e18679 8945 "0h53w2mrjrg2n0ndi12k9j6cwclgwcgpy25nz7nyj971aisw02xn"))))
bf3fa996
RW		 8946 (properties `((upstream-name . "methylKit")))
8947 (build-system r-build-system)
8948 (propagated-inputs
8949 `(("r-data-table" ,r-data-table)
8950 ("r-emdbook" ,r-emdbook)
8951 ("r-fastseg" ,r-fastseg)
8952 ("r-genomeinfodb" ,r-genomeinfodb)
8953 ("r-genomicranges" ,r-genomicranges)
8954 ("r-gtools" ,r-gtools)
8955 ("r-iranges" ,r-iranges)
8956 ("r-kernsmooth" ,r-kernsmooth)
8957 ("r-limma" ,r-limma)
8958 ("r-mclust" ,r-mclust)
8959 ("r-qvalue" ,r-qvalue)
8960 ("r-r-utils" ,r-r-utils)
8961 ("r-rcpp" ,r-rcpp)
8962 ("r-rhtslib" ,r-rhtslib)
8963 ("r-rsamtools" ,r-rsamtools)
8964 ("r-rtracklayer" ,r-rtracklayer)
8965 ("r-s4vectors" ,r-s4vectors)
8966 ("r-zlibbioc" ,r-zlibbioc)))
8967 (inputs
8968 `(("zlib" ,zlib)))
11ed4108 8969 (home-page "https://github.com/al2na/methylKit")
bf3fa996
RW		 8970 (synopsis
8971 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8972 (description
8973 "MethylKit is an R package for DNA methylation analysis and annotation
8974from high-throughput bisulfite sequencing. The package is designed to deal
8975with sequencing data from @dfn{Reduced representation bisulfite
8976sequencing} (RRBS) and its variants, but also target-capture methods and whole
8977genome bisulfite sequencing. It also has functions to analyze base-pair
8978resolution 5hmC data from experimental protocols such as oxBS-Seq and
8979TAB-Seq.")
8980 (license license:artistic2.0)))
8981
dd42a330
RJPB		 8982(define-public r-sva
8983 (package
8984 (name "r-sva")
fad7c0c7 8985 (version "3.26.0")
dd42a330
RJPB		 8986 (source
8987 (origin
8988 (method url-fetch)
8989 (uri (bioconductor-uri "sva" version))
8990 (sha256
8991 (base32
fad7c0c7 8992 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
dd42a330
RJPB		 8993 (build-system r-build-system)
8994 (propagated-inputs
aeb64f3c 8995 `(("r-genefilter" ,r-genefilter)
bfa0d1e7
RJ		 8996 ("r-mgcv" ,r-mgcv)
8997 ("r-biocparallel" ,r-biocparallel)
8998 ("r-matrixstats" ,r-matrixstats)
8999 ("r-limma" ,r-limma)))
5713bbf1 9000 (home-page "https://bioconductor.org/packages/sva")
dd42a330
RJPB		 9001 (synopsis "Surrogate variable analysis")
9002 (description
9003 "This package contains functions for removing batch effects and other
9004unwanted variation in high-throughput experiment. It also contains functions
9005for identifying and building surrogate variables for high-dimensional data
9006sets. Surrogate variables are covariates constructed directly from
9007high-dimensional data like gene expression/RNA sequencing/methylation/brain
9008imaging data that can be used in subsequent analyses to adjust for unknown,
9009unmodeled, or latent sources of noise.")
9010 (license license:artistic2.0)))
fb1e528e
RW		 9011
9012(define-public r-seqminer
9013 (package
9014 (name "r-seqminer")
5e0de298 9015 (version "6.0")
fb1e528e
RW		 9016 (source
9017 (origin
9018 (method url-fetch)
9019 (uri (cran-uri "seqminer" version))
9020 (sha256
9021 (base32
5e0de298 9022 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
fb1e528e
RW		 9023 (build-system r-build-system)
9024 (inputs
9025 `(("zlib" ,zlib)))
9026 (home-page "http://seqminer.genomic.codes")
9027 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9028 (description
9029 "This package provides tools to integrate nucleotide sequencing
9030data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9031 ;; Any version of the GPL is acceptable
9032 (license (list license:gpl2+ license:gpl3+))))
1f40e73c
RW		 9033
9034(define-public r-raremetals2
9035 (package
9036 (name "r-raremetals2")
9037 (version "0.1")
9038 (source
9039 (origin
9040 (method url-fetch)
9041 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9042 "b/b7/RareMETALS2_" version ".tar.gz"))
9043 (sha256
9044 (base32
9045 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9046 (properties `((upstream-name . "RareMETALS2")))
9047 (build-system r-build-system)
9048 (propagated-inputs
9049 `(("r-seqminer" ,r-seqminer)
9050 ("r-mvtnorm" ,r-mvtnorm)
aeb64f3c 9051 ("r-mass" ,r-mass)
1f40e73c
RW		 9052 ("r-compquadform" ,r-compquadform)
9053 ("r-getopt" ,r-getopt)))
9054 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9055 (synopsis "Analyze gene-level association tests for binary trait")
9056 (description
9057 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9058It was designed to meta-analyze gene-level association tests for binary trait.
9059While rareMETALS offers a near-complete solution for meta-analysis of
9060gene-level tests for quantitative trait, it does not offer the optimal
9061solution for binary trait. The package rareMETALS2 offers improved features
9062for analyzing gene-level association tests in meta-analyses for binary
9063trait.")
9064 (license license:gpl3)))
0e7d058e
RW		 9065
9066(define-public r-maldiquant
9067 (package
9068 (name "r-maldiquant")
43949265 9069 (version "1.17")
0e7d058e
RW		 9070 (source
9071 (origin
9072 (method url-fetch)
9073 (uri (cran-uri "MALDIquant" version))
9074 (sha256
9075 (base32
43949265 9076 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
0e7d058e
RW		 9077 (properties `((upstream-name . "MALDIquant")))
9078 (build-system r-build-system)
e9960d8c 9079 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
0e7d058e
RW		 9080 (synopsis "Quantitative analysis of mass spectrometry data")
9081 (description
9082 "This package provides a complete analysis pipeline for matrix-assisted
9083laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9084two-dimensional mass spectrometry data. In addition to commonly used plotting
9085and processing methods it includes distinctive features, namely baseline
9086subtraction methods such as morphological filters (TopHat) or the
9087statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9088alignment using warping functions, handling of replicated measurements as well
9089as allowing spectra with different resolutions.")
9090 (license license:gpl3+)))
ae262174
RW		 9091
9092(define-public r-protgenerics
9093 (package
9094 (name "r-protgenerics")
9a665dfb 9095 (version "1.10.0")
ae262174
RW		 9096 (source
9097 (origin
9098 (method url-fetch)
9099 (uri (bioconductor-uri "ProtGenerics" version))
9100 (sha256
9101 (base32
9a665dfb 9102 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
ae262174
RW		 9103 (properties `((upstream-name . "ProtGenerics")))
9104 (build-system r-build-system)
9105 (home-page "https://github.com/lgatto/ProtGenerics")
9106 (synopsis "S4 generic functions for proteomics infrastructure")
9107 (description
9108 "This package provides S4 generic functions needed by Bioconductor
9109proteomics packages.")
9110 (license license:artistic2.0)))
71676a1f
RW		 9111
9112(define-public r-mzr
9113 (package
9114 (name "r-mzr")
34b96754 9115 (version "2.12.0")
71676a1f
RW		 9116 (source
9117 (origin
9118 (method url-fetch)
9119 (uri (bioconductor-uri "mzR" version))
9120 (sha256
9121 (base32
15ca1959
RW		 9122 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9123 (modules '((guix build utils)))
9124 (snippet
9125 '(begin
9126 (delete-file-recursively "src/boost")
9127 #t))))
71676a1f
RW		 9128 (properties `((upstream-name . "mzR")))
9129 (build-system r-build-system)
15ca1959
RW		 9130 (arguments
9131 `(#:phases
9132 (modify-phases %standard-phases
9133 (add-after 'unpack 'use-system-boost
9134 (lambda _
9135 (substitute* "src/Makevars"
9136 (("\\./boost/libs.*") "")
9137 (("ARCH_OBJS=" line)
9138 (string-append line
9139 "\nARCH_LIBS=-lboost_system -lboost_regex \
9140-lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9141 #t)))))
71676a1f 9142 (inputs
34b96754 9143 `(("boost" ,boost) ; use this instead of the bundled boost sources
d534f3a4 9144 ("netcdf" ,netcdf)))
71676a1f
RW		 9145 (propagated-inputs
9146 `(("r-biobase" ,r-biobase)
9147 ("r-biocgenerics" ,r-biocgenerics)
9148 ("r-protgenerics" ,r-protgenerics)
9149 ("r-rcpp" ,r-rcpp)
9150 ("r-zlibbioc" ,r-zlibbioc)))
9151 (home-page "https://github.com/sneumann/mzR/")
9152 (synopsis "Parser for mass spectrometry data files")
9153 (description
9154 "The mzR package provides a unified API to the common file formats and
9155parsers available for mass spectrometry data. It comes with a wrapper for the
9156ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9157The package contains the original code written by the ISB, and a subset of the
9158proteowizard library for mzML and mzIdentML. The netCDF reading code has
9159previously been used in XCMS.")
9160 (license license:artistic2.0)))
5c9d1505
RW		 9161
9162(define-public r-affyio
9163 (package
9164 (name "r-affyio")
8a8138d2 9165 (version "1.48.0")
5c9d1505
RW		 9166 (source
9167 (origin
9168 (method url-fetch)
9169 (uri (bioconductor-uri "affyio" version))
9170 (sha256
9171 (base32
8a8138d2 9172 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
5c9d1505
RW		 9173 (build-system r-build-system)
9174 (propagated-inputs
9175 `(("r-zlibbioc" ,r-zlibbioc)))
9176 (inputs
9177 `(("zlib" ,zlib)))
9178 (home-page "https://github.com/bmbolstad/affyio")
9179 (synopsis "Tools for parsing Affymetrix data files")
9180 (description
9181 "This package provides routines for parsing Affymetrix data files based
9182upon file format information. The primary focus is on accessing the CEL and
9183CDF file formats.")
9184 (license license:lgpl2.0+)))
05c7e5fb
RW		 9185
9186(define-public r-affy
9187 (package
9188 (name "r-affy")
dad5f838 9189 (version "1.56.0")
05c7e5fb
RW		 9190 (source
9191 (origin
9192 (method url-fetch)
9193 (uri (bioconductor-uri "affy" version))
9194 (sha256
9195 (base32
dad5f838 9196 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
05c7e5fb
RW		 9197 (build-system r-build-system)
9198 (propagated-inputs
9199 `(("r-affyio" ,r-affyio)
9200 ("r-biobase" ,r-biobase)
9201 ("r-biocgenerics" ,r-biocgenerics)
9202 ("r-biocinstaller" ,r-biocinstaller)
9203 ("r-preprocesscore" ,r-preprocesscore)
9204 ("r-zlibbioc" ,r-zlibbioc)))
5713bbf1 9205 (home-page "https://bioconductor.org/packages/affy")
05c7e5fb
RW		 9206 (synopsis "Methods for affymetrix oligonucleotide arrays")
9207 (description
9208 "This package contains functions for exploratory oligonucleotide array
9209analysis.")
9210 (license license:lgpl2.0+)))
7c08afaf
RW		 9211
9212(define-public r-vsn
9213 (package
9214 (name "r-vsn")
1be0f536 9215 (version "3.46.0")
7c08afaf
RW		 9216 (source
9217 (origin
9218 (method url-fetch)
9219 (uri (bioconductor-uri "vsn" version))
9220 (sha256
9221 (base32
1be0f536 9222 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
7c08afaf
RW		 9223 (build-system r-build-system)
9224 (propagated-inputs
9225 `(("r-affy" ,r-affy)
9226 ("r-biobase" ,r-biobase)
9227 ("r-ggplot2" ,r-ggplot2)
aeb64f3c 9228 ("r-lattice" ,r-lattice)
7c08afaf 9229 ("r-limma" ,r-limma)))
5713bbf1 9230 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
7c08afaf
RW		 9231 (synopsis "Variance stabilization and calibration for microarray data")
9232 (description
9233 "The package implements a method for normalising microarray intensities,
9234and works for single- and multiple-color arrays. It can also be used for data
9235from other technologies, as long as they have similar format. The method uses
9236a robust variant of the maximum-likelihood estimator for an
9237additive-multiplicative error model and affine calibration. The model
9238incorporates data calibration step (a.k.a. normalization), a model for the
9239dependence of the variance on the mean intensity and a variance stabilizing
9240data transformation. Differences between transformed intensities are
9241analogous to \"normalized log-ratios\". However, in contrast to the latter,
9242their variance is independent of the mean, and they are usually more sensitive
9243and specific in detecting differential transcription.")
9244 (license license:artistic2.0)))
4aa7d592
RW		 9245
9246(define-public r-mzid
9247 (package
9248 (name "r-mzid")
b500dbcd 9249 (version "1.16.0")
4aa7d592
RW		 9250 (source
9251 (origin
9252 (method url-fetch)
9253 (uri (bioconductor-uri "mzID" version))
9254 (sha256
9255 (base32
b500dbcd 9256 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
4aa7d592
RW		 9257 (properties `((upstream-name . "mzID")))
9258 (build-system r-build-system)
9259 (propagated-inputs
9260 `(("r-doparallel" ,r-doparallel)
9261 ("r-foreach" ,r-foreach)
9262 ("r-iterators" ,r-iterators)
9263 ("r-plyr" ,r-plyr)
9264 ("r-protgenerics" ,r-protgenerics)
9265 ("r-rcpp" ,r-rcpp)
9266 ("r-xml" ,r-xml)))
5713bbf1 9267 (home-page "https://bioconductor.org/packages/mzID")
4aa7d592
RW		 9268 (synopsis "Parser for mzIdentML files")
9269 (description
9270 "This package provides a parser for mzIdentML files implemented using the
9271XML package. The parser tries to be general and able to handle all types of
9272mzIdentML files with the drawback of having less pretty output than a vendor
9273specific parser.")
9274 (license license:gpl2+)))
6a67e181
RW		 9275
9276(define-public r-pcamethods
9277 (package
9278 (name "r-pcamethods")
a998c9a4 9279 (version "1.70.0")
6a67e181
RW		 9280 (source
9281 (origin
9282 (method url-fetch)
9283 (uri (bioconductor-uri "pcaMethods" version))
9284 (sha256
9285 (base32
a998c9a4 9286 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
6a67e181
RW		 9287 (properties `((upstream-name . "pcaMethods")))
9288 (build-system r-build-system)
9289 (propagated-inputs
9290 `(("r-biobase" ,r-biobase)
9291 ("r-biocgenerics" ,r-biocgenerics)
aeb64f3c 9292 ("r-mass" ,r-mass)
6a67e181
RW		 9293 ("r-rcpp" ,r-rcpp)))
9294 (home-page "https://github.com/hredestig/pcamethods")
9295 (synopsis "Collection of PCA methods")
9296 (description
9297 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9298Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9299for missing value estimation is included for comparison. BPCA, PPCA and
9300NipalsPCA may be used to perform PCA on incomplete data as well as for
9301accurate missing value estimation. A set of methods for printing and plotting
9302the results is also provided. All PCA methods make use of the same data
9303structure (pcaRes) to provide a common interface to the PCA results.")
9304 (license license:gpl3+)))
11879284
RW		 9305
9306(define-public r-msnbase
9307 (package
9308 (name "r-msnbase")
baa00ee9 9309 (version "2.4.0")
11879284
RW		 9310 (source
9311 (origin
9312 (method url-fetch)
9313 (uri (bioconductor-uri "MSnbase" version))
9314 (sha256
9315 (base32
baa00ee9 9316 "0dqfimljhrx3gac8d1k72gppx27lz8yckyb12v4604nbviw7xd3r"))))
11879284
RW		 9317 (properties `((upstream-name . "MSnbase")))
9318 (build-system r-build-system)
9319 (propagated-inputs
9320 `(("r-affy" ,r-affy)
9321 ("r-biobase" ,r-biobase)
9322 ("r-biocgenerics" ,r-biocgenerics)
9323 ("r-biocparallel" ,r-biocparallel)
9324 ("r-digest" ,r-digest)
9325 ("r-ggplot2" ,r-ggplot2)
9326 ("r-impute" ,r-impute)
9327 ("r-iranges" ,r-iranges)
baa00ee9 9328 ("r-lattice" ,r-lattice)
11879284
RW		 9329 ("r-maldiquant" ,r-maldiquant)
9330 ("r-mzid" ,r-mzid)
9331 ("r-mzr" ,r-mzr)
9332 ("r-pcamethods" ,r-pcamethods)
9333 ("r-plyr" ,r-plyr)
9334 ("r-preprocesscore" ,r-preprocesscore)
9335 ("r-protgenerics" ,r-protgenerics)
9336 ("r-rcpp" ,r-rcpp)
11879284
RW		 9337 ("r-s4vectors" ,r-s4vectors)
9338 ("r-vsn" ,r-vsn)
9339 ("r-xml" ,r-xml)))
9340 (home-page "https://github.com/lgatto/MSnbase")
9341 (synopsis "Base functions and classes for MS-based proteomics")
9342 (description
9343 "This package provides basic plotting, data manipulation and processing
e614d639 9344of mass spectrometry based proteomics data.")
11879284 9345 (license license:artistic2.0)))
66da3a9f
RW		 9346
9347(define-public r-msnid
9348 (package
9349 (name "r-msnid")
87e91a9f 9350 (version "1.12.1")
66da3a9f
RW		 9351 (source
9352 (origin
9353 (method url-fetch)
9354 (uri (bioconductor-uri "MSnID" version))
9355 (sha256
9356 (base32
87e91a9f 9357 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
66da3a9f
RW		 9358 (properties `((upstream-name . "MSnID")))
9359 (build-system r-build-system)
9360 (propagated-inputs
9361 `(("r-biobase" ,r-biobase)
9362 ("r-data-table" ,r-data-table)
9363 ("r-doparallel" ,r-doparallel)
9364 ("r-dplyr" ,r-dplyr)
9365 ("r-foreach" ,r-foreach)
9366 ("r-iterators" ,r-iterators)
9367 ("r-msnbase" ,r-msnbase)
9368 ("r-mzid" ,r-mzid)
9369 ("r-mzr" ,r-mzr)
9370 ("r-protgenerics" ,r-protgenerics)
9371 ("r-r-cache" ,r-r-cache)
9372 ("r-rcpp" ,r-rcpp)
9373 ("r-reshape2" ,r-reshape2)))
5713bbf1 9374 (home-page "https://bioconductor.org/packages/MSnID")
66da3a9f
RW		 9375 (synopsis "Utilities for LC-MSn proteomics identifications")
9376 (description
2923f3e5
RW		 9377 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9378from mzIdentML (leveraging the mzID package) or text files. After collating
9379the search results from multiple datasets it assesses their identification
9380quality and optimize filtering criteria to achieve the maximum number of
9381identifications while not exceeding a specified false discovery rate. It also
9382contains a number of utilities to explore the MS/MS results and assess missed
9383and irregular enzymatic cleavages, mass measurement accuracy, etc.")
66da3a9f 9384 (license license:artistic2.0)))
5ded35d8 9385
2441c284 9386(define-public r-seurat
f1a2b1cb
RW		 9387 (package
9388 (name "r-seurat")
9389 (version "2.1.0")
9390 (source (origin
9391 (method url-fetch)
9392 (uri (cran-uri "Seurat" version))
9393 (sha256
9394 (base32
9395 "1hqaq6bciikrsyw157w8fn4jw885air7xbkxrmism93rp4qx483x"))
9396 ;; Delete pre-built jar.
9397 (snippet
9398 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9399 #t))))
9400 (properties `((upstream-name . "Seurat")))
9401 (build-system r-build-system)
9402 (arguments
9403 `(#:phases
9404 (modify-phases %standard-phases
9405 (add-after 'unpack 'build-jar
9406 (lambda* (#:key inputs #:allow-other-keys)
9407 (let ((classesdir "tmp-classes"))
9408 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9409 (mkdir classesdir)
9410 (with-output-to-file "manifest"
8271b8d2
RW		 9411 (lambda _
9412 (display "Manifest-Version: 1.0
9413Main-Class: ModularityOptimizer\n")))
9414 (and (zero? (apply system* `("javac" "-d" ,classesdir
9415 ,@(find-files "java" "\\.java$"))))
9416 (zero? (system* "jar"
9417 "-cmf" "manifest"
9418 "inst/java/ModularityOptimizer.jar"
f1a2b1cb
RW		 9419 "-C" classesdir ".")))))))))
9420 (native-inputs
9421 `(("jdk" ,icedtea "jdk")))
9422 (propagated-inputs
9423 `(("r-ape" ,r-ape)
9424 ("r-caret" ,r-caret)
9425 ("r-cowplot" ,r-cowplot)
9426 ("r-diffusionmap" ,r-diffusionmap)
9427 ("r-dplyr" ,r-dplyr)
9428 ("r-dtw" ,r-dtw)
9429 ("r-fnn" ,r-fnn)
9430 ("r-fpc" ,r-fpc)
9431 ("r-gdata" ,r-gdata)
9432 ("r-ggjoy" ,r-ggjoy)
9433 ("r-ggplot2" ,r-ggplot2)
9434 ("r-gplots" ,r-gplots)
9435 ("r-gridextra" ,r-gridextra)
9436 ("r-hmisc" ,r-hmisc)
9437 ("r-ica" ,r-ica)
9438 ("r-igraph" ,r-igraph)
9439 ("r-irlba" ,r-irlba)
9440 ("r-lars" ,r-lars)
9441 ("r-mass" ,r-mass)
9442 ("r-matrix" ,r-matrix)
9443 ("r-mixtools" ,r-mixtools)
9444 ("r-nmf" ,r-nmf)
9445 ("r-pbapply" ,r-pbapply)
9446 ("r-plotly" ,r-plotly)
9447 ("r-ranger" ,r-ranger)
9448 ("r-rcolorbrewer" ,r-rcolorbrewer)
9449 ("r-rcpp" ,r-rcpp)
9450 ("r-rcppprogress" ,r-rcppprogress)
9451 ("r-reshape2" ,r-reshape2)
9452 ("r-rocr" ,r-rocr)
9453 ("r-rtsne" ,r-rtsne)
9454 ("r-sdmtools" ,r-sdmtools)
9455 ("r-stringr" ,r-stringr)
9456 ("r-tclust" ,r-tclust)
9457 ("r-tidyr" ,r-tidyr)
9458 ("r-tsne" ,r-tsne)
9459 ("r-vgam" ,r-vgam)))
9460 (home-page "http://www.satijalab.org/seurat")
9461 (synopsis "Seurat is an R toolkit for single cell genomics")
9462 (description
9463 "This package is an R package designed for QC, analysis, and
2441c284
RJPB		 9464exploration of single cell RNA-seq data. It easily enables widely-used
9465analytical techniques, including the identification of highly variable genes,
9466dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9467algorithms; density clustering, hierarchical clustering, k-means, and the
9468discovery of differentially expressed genes and markers.")
f1a2b1cb 9469 (license license:gpl3)))
2441c284 9470
d4b83651
RW		 9471(define-public r-aroma-light
9472 (package
9473 (name "r-aroma-light")
531e8090 9474 (version "3.8.0")
d4b83651
RW		 9475 (source
9476 (origin
9477 (method url-fetch)
9478 (uri (bioconductor-uri "aroma.light" version))
9479 (sha256
9480 (base32
531e8090 9481 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
d4b83651
RW		 9482 (properties `((upstream-name . "aroma.light")))
9483 (build-system r-build-system)
9484 (propagated-inputs
9485 `(("r-matrixstats" ,r-matrixstats)
9486 ("r-r-methodss3" ,r-r-methodss3)
9487 ("r-r-oo" ,r-r-oo)
9488 ("r-r-utils" ,r-r-utils)))
9489 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9490 (synopsis "Methods for normalization and visualization of microarray data")
9491 (description
9492 "This package provides methods for microarray analysis that take basic
9493data types such as matrices and lists of vectors. These methods can be used
9494standalone, be utilized in other packages, or be wrapped up in higher-level
9495classes.")
9496 (license license:gpl2+)))
9497
7b465327
RW		 9498(define-public r-deseq
9499 (package
9500 (name "r-deseq")
8140f680 9501 (version "1.30.0")
7b465327
RW		 9502 (source
9503 (origin
9504 (method url-fetch)
9505 (uri (bioconductor-uri "DESeq" version))
9506 (sha256
9507 (base32
8140f680 9508 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
7b465327
RW		 9509 (properties `((upstream-name . "DESeq")))
9510 (build-system r-build-system)
9511 (propagated-inputs
9512 `(("r-biobase" ,r-biobase)
9513 ("r-biocgenerics" ,r-biocgenerics)
9514 ("r-genefilter" ,r-genefilter)
9515 ("r-geneplotter" ,r-geneplotter)
9516 ("r-lattice" ,r-lattice)
9517 ("r-locfit" ,r-locfit)
9518 ("r-mass" ,r-mass)
9519 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9520 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9521 (synopsis "Differential gene expression analysis")
9522 (description
9523 "This package provides tools for estimating variance-mean dependence in
9524count data from high-throughput genetic sequencing assays and for testing for
9525differential expression based on a model using the negative binomial
9526distribution.")
9527 (license license:gpl3+)))
9528
296b3c63
RW		 9529(define-public r-edaseq
9530 (package
9531 (name "r-edaseq")
00961279 9532 (version "2.12.0")
296b3c63
RW		 9533 (source
9534 (origin
9535 (method url-fetch)
9536 (uri (bioconductor-uri "EDASeq" version))
9537 (sha256
9538 (base32
00961279 9539 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
296b3c63
RW		 9540 (properties `((upstream-name . "EDASeq")))
9541 (build-system r-build-system)
9542 (propagated-inputs
9543 `(("r-annotationdbi" ,r-annotationdbi)
9544 ("r-aroma-light" ,r-aroma-light)
9545 ("r-biobase" ,r-biobase)
9546 ("r-biocgenerics" ,r-biocgenerics)
9547 ("r-biomart" ,r-biomart)
9548 ("r-biostrings" ,r-biostrings)
9549 ("r-deseq" ,r-deseq)
9550 ("r-genomicfeatures" ,r-genomicfeatures)
9551 ("r-genomicranges" ,r-genomicranges)
9552 ("r-iranges" ,r-iranges)
9553 ("r-rsamtools" ,r-rsamtools)
9554 ("r-shortread" ,r-shortread)))
9555 (home-page "https://github.com/drisso/EDASeq")
9556 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9557 (description
9558 "This package provides support for numerical and graphical summaries of
9559RNA-Seq genomic read data. Provided within-lane normalization procedures to
9560adjust for GC-content effect (or other gene-level effects) on read counts:
9561loess robust local regression, global-scaling, and full-quantile
9562normalization. Between-lane normalization procedures to adjust for
9563distributional differences between lanes (e.g., sequencing depth):
9564global-scaling and full-quantile normalization.")
9565 (license license:artistic2.0)))
9566
5f96f30f
RW		 9567(define-public r-interactivedisplaybase
9568 (package
9569 (name "r-interactivedisplaybase")
1567c8d9 9570 (version "1.16.0")
5f96f30f
RW		 9571 (source
9572 (origin
9573 (method url-fetch)
9574 (uri (bioconductor-uri "interactiveDisplayBase" version))
9575 (sha256
9576 (base32
1567c8d9 9577 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
5f96f30f
RW		 9578 (properties
9579 `((upstream-name . "interactiveDisplayBase")))
9580 (build-system r-build-system)
9581 (propagated-inputs
9582 `(("r-biocgenerics" ,r-biocgenerics)
9583 ("r-shiny" ,r-shiny)))
5713bbf1 9584 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
5f96f30f
RW		 9585 (synopsis "Base package for web displays of Bioconductor objects")
9586 (description
9587 "This package contains the basic methods needed to generate interactive
9588Shiny-based display methods for Bioconductor objects.")
9589 (license license:artistic2.0)))
9590
4a007ffa
RW		 9591(define-public r-annotationhub
9592 (package
9593 (name "r-annotationhub")
9b8d0201 9594 (version "2.10.1")
4a007ffa
RW		 9595 (source
9596 (origin
9597 (method url-fetch)
9598 (uri (bioconductor-uri "AnnotationHub" version))
9599 (sha256
9600 (base32
9b8d0201 9601 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
4a007ffa
RW		 9602 (properties `((upstream-name . "AnnotationHub")))
9603 (build-system r-build-system)
9604 (propagated-inputs
9605 `(("r-annotationdbi" ,r-annotationdbi)
9606 ("r-biocgenerics" ,r-biocgenerics)
9607 ("r-biocinstaller" ,r-biocinstaller)
14b3c719 9608 ("r-curl" ,r-curl)
4a007ffa
RW		 9609 ("r-httr" ,r-httr)
9610 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9611 ("r-rsqlite" ,r-rsqlite)
9612 ("r-s4vectors" ,r-s4vectors)
9613 ("r-yaml" ,r-yaml)))
5713bbf1 9614 (home-page "https://bioconductor.org/packages/AnnotationHub")
4a007ffa
RW		 9615 (synopsis "Client to access AnnotationHub resources")
9616 (description
9617 "This package provides a client for the Bioconductor AnnotationHub web
9618resource. The AnnotationHub web resource provides a central location where
9619genomic files (e.g. VCF, bed, wig) and other resources from standard
9620locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9621metadata about each resource, e.g., a textual description, tags, and date of
9622modification. The client creates and manages a local cache of files retrieved
9623by the user, helping with quick and reproducible access.")
9624 (license license:artistic2.0)))
9625
d4a1e918
RW		 9626(define-public r-fastseg
9627 (package
9628 (name "r-fastseg")
87fa5afa 9629 (version "1.24.0")
d4a1e918
RW		 9630 (source
9631 (origin
9632 (method url-fetch)
9633 (uri (bioconductor-uri "fastseg" version))
9634 (sha256
9635 (base32
87fa5afa 9636 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
d4a1e918
RW		 9637 (build-system r-build-system)
9638 (propagated-inputs
9639 `(("r-biobase" ,r-biobase)
9640 ("r-biocgenerics" ,r-biocgenerics)
9641 ("r-genomicranges" ,r-genomicranges)
9642 ("r-iranges" ,r-iranges)
9643 ("r-s4vectors" ,r-s4vectors)))
9644 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9645 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9646 (description
9647 "Fastseg implements a very fast and efficient segmentation algorithm.
9648It can segment data from DNA microarrays and data from next generation
9649sequencing for example to detect copy number segments. Further it can segment
9650data from RNA microarrays like tiling arrays to identify transcripts. Most
9651generally, it can segment data given as a matrix or as a vector. Various data
9652formats can be used as input to fastseg like expression set objects for
9653microarrays or GRanges for sequencing data.")
9654 (license license:lgpl2.0+)))
9655
3121814e
RW		 9656(define-public r-keggrest
9657 (package
9658 (name "r-keggrest")
9659 (version "1.18.0")
9660 (source
9661 (origin
9662 (method url-fetch)
9663 (uri (bioconductor-uri "KEGGREST" version))
9664 (sha256
9665 (base32
9666 "1i3i88lj57wvpgjf75a23msgfsjv8pr2b4j1faga276p4fsblkhj"))))
9667 (properties `((upstream-name . "KEGGREST")))
9668 (build-system r-build-system)
9669 (propagated-inputs
9670 `(("r-biostrings" ,r-biostrings)
9671 ("r-httr" ,r-httr)
9672 ("r-png" ,r-png)))
9673 (home-page "https://bioconductor.org/packages/KEGGREST")
9674 (synopsis "Client-side REST access to KEGG")
9675 (description
9676 "This package provides a package that provides a client interface to the
9677@dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9678 (license license:artistic2.0)))
9679
e160aa1f
RW		 9680(define-public r-gage
9681 (package
9682 (name "r-gage")
9683 (version "2.28.0")
9684 (source
9685 (origin
9686 (method url-fetch)
9687 (uri (bioconductor-uri "gage" version))
9688 (sha256
9689 (base32
9690 "1r14p88q3y736pkqm4pdimf1izy1xy3xgivmj3cr4dv65kjny1zk"))))
9691 (build-system r-build-system)
9692 (propagated-inputs
9693 `(("r-annotationdbi" ,r-annotationdbi)
9694 ("r-graph" ,r-graph)
9695 ("r-keggrest" ,r-keggrest)))
9696 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9697 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9698 (description
9699 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9700analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9701data attributes including sample sizes, experimental designs, assay platforms,
9702and other types of heterogeneity. The gage package provides functions for
9703basic GAGE analysis, result processing and presentation. In addition, it
9704provides demo microarray data and commonly used gene set data based on KEGG
9705pathways and GO terms. These funtions and data are also useful for gene set
9706analysis using other methods.")
9707 (license license:gpl2+)))
9708
902fb15d
RW		 9709(define-public r-genomicfiles
9710 (package
9711 (name "r-genomicfiles")
9712 (version "1.14.0")
9713 (source
9714 (origin
9715 (method url-fetch)
9716 (uri (bioconductor-uri "GenomicFiles" version))
9717 (sha256
9718 (base32
9719 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9720 (properties `((upstream-name . "GenomicFiles")))
9721 (build-system r-build-system)
9722 (propagated-inputs
9723 `(("r-biocgenerics" ,r-biocgenerics)
9724 ("r-biocparallel" ,r-biocparallel)
9725 ("r-genomeinfodb" ,r-genomeinfodb)
9726 ("r-genomicalignments" ,r-genomicalignments)
9727 ("r-genomicranges" ,r-genomicranges)
9728 ("r-iranges" ,r-iranges)
9729 ("r-rsamtools" ,r-rsamtools)
9730 ("r-rtracklayer" ,r-rtracklayer)
9731 ("r-s4vectors" ,r-s4vectors)
9732 ("r-summarizedexperiment" ,r-summarizedexperiment)
9733 ("r-variantannotation" ,r-variantannotation)))
9734 (home-page "https://bioconductor.org/packages/GenomicFiles")
9735 (synopsis "Distributed computing by file or by range")
9736 (description
9737 "This package provides infrastructure for parallel computations
9738distributed by file or by range. User defined mapper and reducer functions
9739provide added flexibility for data combination and manipulation.")
9740 (license license:artistic2.0)))
9741
3af149f5
RW		 9742(define-public r-complexheatmap
9743 (package
9744 (name "r-complexheatmap")
9745 (version "1.17.1")
9746 (source
9747 (origin
9748 (method url-fetch)
9749 (uri (bioconductor-uri "ComplexHeatmap" version))
9750 (sha256
9751 (base32
9752 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9753 (properties
9754 `((upstream-name . "ComplexHeatmap")))
9755 (build-system r-build-system)
9756 (propagated-inputs
9757 `(("r-circlize" ,r-circlize)
9758 ("r-colorspace" ,r-colorspace)
9759 ("r-getoptlong" ,r-getoptlong)
9760 ("r-globaloptions" ,r-globaloptions)
9761 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9762 (home-page
9763 "https://github.com/jokergoo/ComplexHeatmap")
9764 (synopsis "Making Complex Heatmaps")
9765 (description
9766 "Complex heatmaps are efficient to visualize associations between
9767different sources of data sets and reveal potential structures. This package
9768provides a highly flexible way to arrange multiple heatmaps and supports
9769self-defined annotation graphics.")
9770 (license license:gpl2+)))
9771
04e2a2e9
RW		 9772(define-public r-dirichletmultinomial
9773 (package
9774 (name "r-dirichletmultinomial")
9775 (version "1.20.0")
9776 (source
9777 (origin
9778 (method url-fetch)
9779 (uri (bioconductor-uri "DirichletMultinomial" version))
9780 (sha256
9781 (base32
9782 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9783 (properties
9784 `((upstream-name . "DirichletMultinomial")))
9785 (build-system r-build-system)
9786 (inputs
9787 `(("gsl" ,gsl)))
9788 (propagated-inputs
9789 `(("r-biocgenerics" ,r-biocgenerics)
9790 ("r-iranges" ,r-iranges)
9791 ("r-s4vectors" ,r-s4vectors)))
9792 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9793 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9794 (description
9795 "Dirichlet-multinomial mixture models can be used to describe variability
9796in microbial metagenomic data. This package is an interface to code
9797originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
97981-15.")
9799 (license license:lgpl3)))
9800
aa30ab5a
RW		 9801(define-public r-ensembldb
9802 (package
9803 (name "r-ensembldb")
9804 (version "2.2.0")
9805 (source
9806 (origin
9807 (method url-fetch)
9808 (uri (bioconductor-uri "ensembldb" version))
9809 (sha256
9810 (base32
9811 "1w0lca3ws5j770bmls91cn93lznvv2pc8s42nybdzz3vdxjvb4m1"))))
9812 (build-system r-build-system)
9813 (propagated-inputs
9814 `(("r-annotationdbi" ,r-annotationdbi)
9815 ("r-annotationfilter" ,r-annotationfilter)
9816 ("r-annotationhub" ,r-annotationhub)
9817 ("r-biobase" ,r-biobase)
9818 ("r-biocgenerics" ,r-biocgenerics)
9819 ("r-biostrings" ,r-biostrings)
9820 ("r-curl" ,r-curl)
9821 ("r-dbi" ,r-dbi)
9822 ("r-genomeinfodb" ,r-genomeinfodb)
9823 ("r-genomicfeatures" ,r-genomicfeatures)
9824 ("r-genomicranges" ,r-genomicranges)
9825 ("r-iranges" ,r-iranges)
9826 ("r-protgenerics" ,r-protgenerics)
9827 ("r-rsamtools" ,r-rsamtools)
9828 ("r-rsqlite" ,r-rsqlite)
9829 ("r-rtracklayer" ,r-rtracklayer)
9830 ("r-s4vectors" ,r-s4vectors)))
9831 (home-page "https://github.com/jotsetung/ensembldb")
9832 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9833 (description
9834 "The package provides functions to create and use transcript-centric
9835annotation databases/packages. The annotation for the databases are directly
9836fetched from Ensembl using their Perl API. The functionality and data is
9837similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9838but, in addition to retrieve all gene/transcript models and annotations from
9839the database, the @code{ensembldb} package also provides a filter framework
9840allowing to retrieve annotations for specific entries like genes encoded on a
9841chromosome region or transcript models of lincRNA genes.")
9842 ;; No version specified
9843 (license license:lgpl3+)))
9844
2f6f61fd
RW		 9845(define-public r-organismdbi
9846 (package
9847 (name "r-organismdbi")
9848 (version "1.20.0")
9849 (source
9850 (origin
9851 (method url-fetch)
9852 (uri (bioconductor-uri "OrganismDbi" version))
9853 (sha256
9854 (base32
9855 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
9856 (properties `((upstream-name . "OrganismDbi")))
9857 (build-system r-build-system)
9858 (propagated-inputs
9859 `(("r-annotationdbi" ,r-annotationdbi)
9860 ("r-biobase" ,r-biobase)
9861 ("r-biocgenerics" ,r-biocgenerics)
9862 ("r-biocinstaller" ,r-biocinstaller)
9863 ("r-dbi" ,r-dbi)
9864 ("r-genomicfeatures" ,r-genomicfeatures)
9865 ("r-genomicranges" ,r-genomicranges)
9866 ("r-graph" ,r-graph)
9867 ("r-iranges" ,r-iranges)
9868 ("r-rbgl" ,r-rbgl)
9869 ("r-s4vectors" ,r-s4vectors)))
9870 (home-page "https://bioconductor.org/packages/OrganismDbi")
9871 (synopsis "Software to enable the smooth interfacing of database packages")
9872 (description "The package enables a simple unified interface to several
9873annotation packages each of which has its own schema by taking advantage of
9874the fact that each of these packages implements a select methods.")
9875 (license license:artistic2.0)))
9876
7af1f403
RW		 9877(define-public r-biovizbase
9878 (package
9879 (name "r-biovizbase")
9880 (version "1.26.0")
9881 (source
9882 (origin
9883 (method url-fetch)
9884 (uri (bioconductor-uri "biovizBase" version))
9885 (sha256
9886 (base32
9887 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
9888 (properties `((upstream-name . "biovizBase")))
9889 (build-system r-build-system)
9890 (propagated-inputs
9891 `(("r-annotationdbi" ,r-annotationdbi)
9892 ("r-annotationfilter" ,r-annotationfilter)
9893 ("r-biocgenerics" ,r-biocgenerics)
9894 ("r-biostrings" ,r-biostrings)
9895 ("r-dichromat" ,r-dichromat)
9896 ("r-ensembldb" ,r-ensembldb)
9897 ("r-genomeinfodb" ,r-genomeinfodb)
9898 ("r-genomicalignments" ,r-genomicalignments)
9899 ("r-genomicfeatures" ,r-genomicfeatures)
9900 ("r-genomicranges" ,r-genomicranges)
9901 ("r-hmisc" ,r-hmisc)
9902 ("r-iranges" ,r-iranges)
9903 ("r-rcolorbrewer" ,r-rcolorbrewer)
9904 ("r-rsamtools" ,r-rsamtools)
9905 ("r-s4vectors" ,r-s4vectors)
9906 ("r-scales" ,r-scales)
9907 ("r-summarizedexperiment" ,r-summarizedexperiment)
9908 ("r-variantannotation" ,r-variantannotation)))
9909 (home-page "https://bioconductor.org/packages/biovizBase")
9910 (synopsis "Basic graphic utilities for visualization of genomic data")
9911 (description
9912 "The biovizBase package is designed to provide a set of utilities, color
9913schemes and conventions for genomic data. It serves as the base for various
9914high-level packages for biological data visualization. This saves development
9915effort and encourages consistency.")
9916 (license license:artistic2.0)))
9917
60faf945
RW		 9918(define-public r-ggbio
9919 (package
9920 (name "r-ggbio")
9921 (version "1.26.0")
9922 (source
9923 (origin
9924 (method url-fetch)
9925 (uri (bioconductor-uri "ggbio" version))
9926 (sha256
9927 (base32
9928 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
9929 (build-system r-build-system)
9930 (propagated-inputs
9931 `(("r-annotationdbi" ,r-annotationdbi)
9932 ("r-annotationfilter" ,r-annotationfilter)
9933 ("r-biobase" ,r-biobase)
9934 ("r-biocgenerics" ,r-biocgenerics)
9935 ("r-biostrings" ,r-biostrings)
9936 ("r-biovizbase" ,r-biovizbase)
9937 ("r-bsgenome" ,r-bsgenome)
9938 ("r-ensembldb" ,r-ensembldb)
9939 ("r-genomeinfodb" ,r-genomeinfodb)
9940 ("r-genomicalignments" ,r-genomicalignments)
9941 ("r-genomicfeatures" ,r-genomicfeatures)
9942 ("r-genomicranges" ,r-genomicranges)
9943 ("r-ggally" ,r-ggally)
9944 ("r-ggplot2" ,r-ggplot2)
9945 ("r-gridextra" ,r-gridextra)
9946 ("r-gtable" ,r-gtable)
9947 ("r-hmisc" ,r-hmisc)
9948 ("r-iranges" ,r-iranges)
9949 ("r-organismdbi" ,r-organismdbi)
9950 ("r-reshape2" ,r-reshape2)
9951 ("r-rsamtools" ,r-rsamtools)
9952 ("r-rtracklayer" ,r-rtracklayer)
9953 ("r-s4vectors" ,r-s4vectors)
9954 ("r-scales" ,r-scales)
9955 ("r-summarizedexperiment" ,r-summarizedexperiment)
9956 ("r-variantannotation" ,r-variantannotation)))
9957 (home-page "http://www.tengfei.name/ggbio/")
9958 (synopsis "Visualization tools for genomic data")
9959 (description
9960 "The ggbio package extends and specializes the grammar of graphics for
9961biological data. The graphics are designed to answer common scientific
9962questions, in particular those often asked of high throughput genomics data.
9963All core Bioconductor data structures are supported, where appropriate. The
9964package supports detailed views of particular genomic regions, as well as
9965genome-wide overviews. Supported overviews include ideograms and grand linear
9966views. High-level plots include sequence fragment length, edge-linked
9967interval to data view, mismatch pileup, and several splicing summaries.")
9968 (license license:artistic2.0)))
9969
96a392a0
RW		 9970(define-public r-gprofiler
9971 (package
9972 (name "r-gprofiler")
9973 (version "0.6.1")
9974 (source
9975 (origin
9976 (method url-fetch)
9977 (uri (cran-uri "gProfileR" version))
9978 (sha256
9979 (base32
9980 "1qix15d0wa9nspdclcawml94mng4qmr2jciv7d24py315wfsvv8p"))))
9981 (properties `((upstream-name . "gProfileR")))
9982 (build-system r-build-system)
9983 (propagated-inputs
9984 `(("r-plyr" ,r-plyr)
9985 ("r-rcurl" ,r-rcurl)))
e9960d8c 9986 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
96a392a0
RW		 9987 (synopsis "Interface to the g:Profiler toolkit")
9988 (description
9989 "This package provides tools for functional enrichment analysis,
9990gene identifier conversion and mapping homologous genes across related
9991organisms via the @code{g:Profiler} toolkit.")
9992 (license license:gpl2+)))
9993
e2b92799
RW		 9994(define-public r-gqtlbase
9995 (package
9996 (name "r-gqtlbase")
9997 (version "1.10.0")
9998 (source
9999 (origin
10000 (method url-fetch)
10001 (uri (bioconductor-uri "gQTLBase" version))
10002 (sha256
10003 (base32
10004 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10005 (properties `((upstream-name . "gQTLBase")))
10006 (build-system r-build-system)
10007 (propagated-inputs
10008 `(("r-batchjobs" ,r-batchjobs)
10009 ("r-bbmisc" ,r-bbmisc)
10010 ("r-biocgenerics" ,r-biocgenerics)
10011 ("r-bit" ,r-bit)
10012 ("r-doparallel" ,r-doparallel)
10013 ("r-ff" ,r-ff)
10014 ("r-ffbase" ,r-ffbase)
10015 ("r-foreach" ,r-foreach)
10016 ("r-genomicfiles" ,r-genomicfiles)
10017 ("r-genomicranges" ,r-genomicranges)
10018 ("r-rtracklayer" ,r-rtracklayer)
10019 ("r-s4vectors" ,r-s4vectors)
10020 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10021 (home-page "https://bioconductor.org/packages/gQTLBase")
10022 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10023 (description
10024 "The purpose of this package is to simplify the storage and interrogation
10025of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10026and more.")
10027 (license license:artistic2.0)))
10028
dd5fc8b7
RW		 10029(define-public r-snpstats
10030 (package
10031 (name "r-snpstats")
10032 (version "1.28.0")
10033 (source
10034 (origin
10035 (method url-fetch)
10036 (uri (bioconductor-uri "snpStats" version))
10037 (sha256
10038 (base32
10039 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10040 (properties `((upstream-name . "snpStats")))
10041 (build-system r-build-system)
10042 (inputs `(("zlib" ,zlib)))
10043 (propagated-inputs
10044 `(("r-biocgenerics" ,r-biocgenerics)
10045 ("r-matrix" ,r-matrix)
10046 ("r-survival" ,r-survival)
10047 ("r-zlibbioc" ,r-zlibbioc)))
10048 (home-page "https://bioconductor.org/packages/snpStats")
10049 (synopsis "Methods for SNP association studies")
10050 (description
10051 "This package provides classes and statistical methods for large
10052@dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10053the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10054 (license license:gpl3)))
10055
421c68e3
RW		 10056(define-public r-homo-sapiens
10057 (package
10058 (name "r-homo-sapiens")
10059 (version "1.3.1")
10060 (source (origin
10061 (method url-fetch)
10062 ;; We cannot use bioconductor-uri here because this tarball is
10063 ;; located under "data/annotation/" instead of "bioc/".
10064 (uri (string-append "http://www.bioconductor.org/packages/"
10065 "release/data/annotation/src/contrib/"
10066 "Homo.sapiens_"
10067 version ".tar.gz"))
10068 (sha256
10069 (base32
10070 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10071 (properties
10072 `((upstream-name . "Homo.sapiens")))
10073 (build-system r-build-system)
10074 (propagated-inputs
10075 `(("r-genomicfeatures" ,r-genomicfeatures)
10076 ("r-go-db" ,r-go-db)
10077 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10078 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10079 ("r-organismdbi" ,r-organismdbi)
10080 ("r-annotationdbi" ,r-annotationdbi)))
10081 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10082 (synopsis "Annotation package for the Homo.sapiens object")
10083 (description
10084 "This package contains the Homo.sapiens object to access data from
10085several related annotation packages.")
10086 (license license:artistic2.0)))
10087
15f98b0d
RW		 10088(define-public r-erma
10089 (package
10090 (name "r-erma")
10091 (version "0.10.0")
10092 (source
10093 (origin
10094 (method url-fetch)
10095 (uri (bioconductor-uri "erma" version))
10096 (sha256
10097 (base32
10098 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10099 (build-system r-build-system)
10100 (propagated-inputs
10101 `(("r-annotationdbi" ,r-annotationdbi)
10102 ("r-biobase" ,r-biobase)
10103 ("r-biocgenerics" ,r-biocgenerics)
10104 ("r-foreach" ,r-foreach)
10105 ("r-genomicfiles" ,r-genomicfiles)
10106 ("r-genomicranges" ,r-genomicranges)
10107 ("r-ggplot2" ,r-ggplot2)
10108 ("r-homo-sapiens" ,r-homo-sapiens)
10109 ("r-rtracklayer" ,r-rtracklayer)
10110 ("r-s4vectors" ,r-s4vectors)
10111 ("r-shiny" ,r-shiny)
10112 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10113 (home-page "https://bioconductor.org/packages/erma")
10114 (synopsis "Epigenomic road map adventures")
10115 (description
10116 "The epigenomics road map describes locations of epigenetic marks in DNA
10117from a variety of cell types. Of interest are locations of histone
10118modifications, sites of DNA methylation, and regions of accessible chromatin.
10119This package presents a selection of elements of the road map including
10120metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10121by Ernst and Kellis.")
10122 (license license:artistic2.0)))
10123
66c39102
RW		 10124(define-public r-ldblock
10125 (package
10126 (name "r-ldblock")
10127 (version "1.8.0")
10128 (source
10129 (origin
10130 (method url-fetch)
10131 (uri (bioconductor-uri "ldblock" version))
10132 (sha256
10133 (base32
10134 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10135 (build-system r-build-system)
10136 (propagated-inputs
10137 `(("r-erma" ,r-erma)
10138 ("r-genomeinfodb" ,r-genomeinfodb)
10139 ("r-genomicfiles" ,r-genomicfiles)
10140 ("r-go-db" ,r-go-db)
10141 ("r-homo-sapiens" ,r-homo-sapiens)
10142 ("r-matrix" ,r-matrix)
10143 ("r-rsamtools" ,r-rsamtools)
10144 ("r-snpstats" ,r-snpstats)
10145 ("r-variantannotation" ,r-variantannotation)))
10146 (home-page "https://bioconductor.org/packages/ldblock")
10147 (synopsis "Data structures for linkage disequilibrium measures in populations")
10148 (description
10149 "This package defines data structures for @dfn{linkage
10150disequilibrium} (LD) measures in populations. Its purpose is to simplify
10151handling of existing population-level data for the purpose of flexibly
10152defining LD blocks.")
10153 (license license:artistic2.0)))
10154
794ff347
RW		 10155(define-public r-gqtlstats
10156 (package
10157 (name "r-gqtlstats")
2ccd8501 10158 (version "1.10.1")
794ff347
RW		 10159 (source
10160 (origin
10161 (method url-fetch)
10162 (uri (bioconductor-uri "gQTLstats" version))
10163 (sha256
10164 (base32
2ccd8501 10165 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
794ff347
RW		 10166 (properties `((upstream-name . "gQTLstats")))
10167 (build-system r-build-system)
10168 (propagated-inputs
10169 `(("r-annotationdbi" ,r-annotationdbi)
10170 ("r-batchjobs" ,r-batchjobs)
10171 ("r-bbmisc" ,r-bbmisc)
10172 ("r-beeswarm" ,r-beeswarm)
10173 ("r-biobase" ,r-biobase)
10174 ("r-biocgenerics" ,r-biocgenerics)
10175 ("r-doparallel" ,r-doparallel)
10176 ("r-dplyr" ,r-dplyr)
10177 ("r-erma" ,r-erma)
10178 ("r-ffbase" ,r-ffbase)
10179 ("r-foreach" ,r-foreach)
10180 ("r-genomeinfodb" ,r-genomeinfodb)
10181 ("r-genomicfeatures" ,r-genomicfeatures)
10182 ("r-genomicfiles" ,r-genomicfiles)
10183 ("r-genomicranges" ,r-genomicranges)
10184 ("r-ggbeeswarm" ,r-ggbeeswarm)
10185 ("r-ggplot2" ,r-ggplot2)
10186 ("r-gqtlbase" ,r-gqtlbase)
10187 ("r-hardyweinberg" ,r-hardyweinberg)
10188 ("r-iranges" ,r-iranges)
10189 ("r-ldblock" ,r-ldblock)
10190 ("r-limma" ,r-limma)
10191 ("r-mgcv" ,r-mgcv)
10192 ("r-plotly" ,r-plotly)
10193 ("r-reshape2" ,r-reshape2)
10194 ("r-s4vectors" ,r-s4vectors)
10195 ("r-shiny" ,r-shiny)
10196 ("r-snpstats" ,r-snpstats)
10197 ("r-summarizedexperiment" ,r-summarizedexperiment)
10198 ("r-variantannotation" ,r-variantannotation)))
10199 (home-page "https://bioconductor.org/packages/gQTLstats")
10200 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10201 (description
10202 "This package provides tools for the computationally efficient analysis
10203of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10204The software in this package aims to support refinements and functional
10205interpretation of members of a collection of association statistics on a
10206family of feature/genome hypotheses.")
10207 (license license:artistic2.0)))
10208
42720006
RW		 10209(define-public r-gviz
10210 (package
10211 (name "r-gviz")
11e42209 10212 (version "1.22.2")
42720006
RW		 10213 (source
10214 (origin
10215 (method url-fetch)
10216 (uri (bioconductor-uri "Gviz" version))
10217 (sha256
10218 (base32
11e42209 10219 "173n99mc95sij2vb8n3xd016x7mxhjs961q3l29xkg1lrnnm2sva"))))
42720006
RW		 10220 (properties `((upstream-name . "Gviz")))
10221 (build-system r-build-system)
10222 (propagated-inputs
10223 `(("r-annotationdbi" ,r-annotationdbi)
10224 ("r-biobase" ,r-biobase)
10225 ("r-biocgenerics" ,r-biocgenerics)
10226 ("r-biomart" ,r-biomart)
10227 ("r-biostrings" ,r-biostrings)
10228 ("r-biovizbase" ,r-biovizbase)
10229 ("r-bsgenome" ,r-bsgenome)
10230 ("r-digest" ,r-digest)
10231 ("r-genomeinfodb" ,r-genomeinfodb)
10232 ("r-genomicalignments" ,r-genomicalignments)
10233 ("r-genomicfeatures" ,r-genomicfeatures)
10234 ("r-genomicranges" ,r-genomicranges)
10235 ("r-iranges" ,r-iranges)
10236 ("r-lattice" ,r-lattice)
10237 ("r-latticeextra" ,r-latticeextra)
10238 ("r-matrixstats" ,r-matrixstats)
10239 ("r-rcolorbrewer" ,r-rcolorbrewer)
10240 ("r-rsamtools" ,r-rsamtools)
10241 ("r-rtracklayer" ,r-rtracklayer)
10242 ("r-s4vectors" ,r-s4vectors)
10243 ("r-xvector" ,r-xvector)))
10244 (home-page "https://bioconductor.org/packages/Gviz")
10245 (synopsis "Plotting data and annotation information along genomic coordinates")
10246 (description
10247 "Genomic data analyses requires integrated visualization of known genomic
10248information and new experimental data. Gviz uses the biomaRt and the
10249rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10250and translates this to e.g. gene/transcript structures in viewports of the
10251grid graphics package. This results in genomic information plotted together
10252with your data.")
10253 (license license:artistic2.0)))
10254
2e4ce60e
RW		 10255(define-public r-gwascat
10256 (package
10257 (name "r-gwascat")
10258 (version "2.10.0")
10259 (source
10260 (origin
10261 (method url-fetch)
10262 (uri (bioconductor-uri "gwascat" version))
10263 (sha256
10264 (base32
10265 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10266 (build-system r-build-system)
10267 (propagated-inputs
10268 `(("r-annotationdbi" ,r-annotationdbi)
10269 ("r-annotationhub" ,r-annotationhub)
10270 ("r-biocgenerics" ,r-biocgenerics)
10271 ("r-biostrings" ,r-biostrings)
10272 ("r-genomeinfodb" ,r-genomeinfodb)
10273 ("r-genomicfeatures" ,r-genomicfeatures)
10274 ("r-genomicranges" ,r-genomicranges)
10275 ("r-ggbio" ,r-ggbio)
10276 ("r-ggplot2" ,r-ggplot2)
10277 ("r-gqtlstats" ,r-gqtlstats)
10278 ("r-graph" ,r-graph)
10279 ("r-gviz" ,r-gviz)
10280 ("r-homo-sapiens" ,r-homo-sapiens)
10281 ("r-iranges" ,r-iranges)
10282 ("r-rsamtools" ,r-rsamtools)
10283 ("r-rtracklayer" ,r-rtracklayer)
10284 ("r-s4vectors" ,r-s4vectors)
10285 ("r-snpstats" ,r-snpstats)
10286 ("r-summarizedexperiment" ,r-summarizedexperiment)
10287 ("r-variantannotation" ,r-variantannotation)))
10288 (home-page "https://bioconductor.org/packages/gwascat")
10289 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10290 (description
10291 "This package provides tools for representing and modeling data in the
10292EMBL-EBI GWAS catalog.")
10293 (license license:artistic2.0)))
10294
fbf54406
RW		 10295(define-public r-sushi
10296 (package
10297 (name "r-sushi")
10298 (version "1.16.0")
10299 (source (origin
10300 (method url-fetch)
10301 (uri (bioconductor-uri "Sushi" version))
10302 (sha256
10303 (base32
10304 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10305 (properties `((upstream-name . "Sushi")))
10306 (build-system r-build-system)
10307 (propagated-inputs
10308 `(("r-biomart" ,r-biomart)
10309 ("r-zoo" ,r-zoo)))
10310 (home-page "https://bioconductor.org/packages/Sushi")
10311 (synopsis "Tools for visualizing genomics data")
10312 (description
10313 "This package provides flexible, quantitative, and integrative genomic
10314visualizations for publication-quality multi-panel figures.")
10315 (license license:gpl2+)))
10316
30eb4e37
RW		 10317(define-public r-fithic
10318 (package
10319 (name "r-fithic")
10320 (version "1.4.0")
10321 (source (origin
10322 (method url-fetch)
10323 (uri (bioconductor-uri "FitHiC" version))
10324 (sha256
10325 (base32
10326 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10327 (properties `((upstream-name . "FitHiC")))
10328 (build-system r-build-system)
10329 (propagated-inputs
10330 `(("r-data-table" ,r-data-table)
10331 ("r-fdrtool" ,r-fdrtool)
10332 ("r-rcpp" ,r-rcpp)))
10333 (home-page "https://bioconductor.org/packages/FitHiC")
10334 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10335 (description
10336 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10337intra-chromosomal contact maps produced by genome-wide genome architecture
10338assays such as Hi-C.")
10339 (license license:gpl2+)))
10340
c49102ec
RW		 10341(define-public r-hitc
10342 (package
10343 (name "r-hitc")
10344 (version "1.22.0")
10345 (source (origin
10346 (method url-fetch)
10347 (uri (bioconductor-uri "HiTC" version))
10348 (sha256
10349 (base32
10350 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10351 (properties `((upstream-name . "HiTC")))
10352 (build-system r-build-system)
10353 (propagated-inputs
10354 `(("r-biostrings" ,r-biostrings)
10355 ("r-genomeinfodb" ,r-genomeinfodb)
10356 ("r-genomicranges" ,r-genomicranges)
10357 ("r-iranges" ,r-iranges)
10358 ("r-matrix" ,r-matrix)
10359 ("r-rcolorbrewer" ,r-rcolorbrewer)
10360 ("r-rtracklayer" ,r-rtracklayer)))
10361 (home-page "https://bioconductor.org/packages/HiTC")
10362 (synopsis "High throughput chromosome conformation capture analysis")
10363 (description
10364 "The HiTC package was developed to explore high-throughput \"C\" data
10365such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10366quality controls, normalization, visualization, and further analysis are also
10367provided.")
10368 (license license:artistic2.0)))
10369
212f6120
RW		 10370(define-public r-qvalue
10371 (package
10372 (name "r-qvalue")
98791c25 10373 (version "2.10.0")
212f6120
RW		 10374 (source
10375 (origin
10376 (method url-fetch)
10377 (uri (bioconductor-uri "qvalue" version))
10378 (sha256
10379 (base32
98791c25 10380 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
212f6120
RW		 10381 (build-system r-build-system)
10382 (propagated-inputs
10383 `(("r-ggplot2" ,r-ggplot2)
10384 ("r-reshape2" ,r-reshape2)))
10385 (home-page "http://github.com/jdstorey/qvalue")
10386 (synopsis "Q-value estimation for false discovery rate control")
10387 (description
10388 "This package takes a list of p-values resulting from the simultaneous
10389testing of many hypotheses and estimates their q-values and local @dfn{false
10390discovery rate} (FDR) values. The q-value of a test measures the proportion
10391of false positives incurred when that particular test is called significant.
10392The local FDR measures the posterior probability the null hypothesis is true
10393given the test's p-value. Various plots are automatically generated, allowing
10394one to make sensible significance cut-offs. The software can be applied to
10395problems in genomics, brain imaging, astrophysics, and data mining.")
10396 ;; Any version of the LGPL.
10397 (license license:lgpl3+)))
10398
5ded35d8
RW		 10399(define htslib-for-sambamba
10400 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10401 (package
10402 (inherit htslib)
10403 (name "htslib-for-sambamba")
10404 (version (string-append "1.3.1-1." (string-take commit 9)))
10405 (source
10406 (origin
10407 (method git-fetch)
10408 (uri (git-reference
10409 (url "https://github.com/lomereiter/htslib.git")
10410 (commit commit)))
10411 (file-name (string-append "htslib-" version "-checkout"))
10412 (sha256
10413 (base32
10414 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10415 (arguments
10416 (substitute-keyword-arguments (package-arguments htslib)
10417 ((#:phases phases)
10418 `(modify-phases ,phases
d10092b8 10419 (add-after 'unpack 'bootstrap
5ded35d8
RW		 10420 (lambda _
10421 (zero? (system* "autoreconf" "-vif"))))))))
10422 (native-inputs
10423 `(("autoconf" ,autoconf)
10424 ("automake" ,automake)
10425 ,@(package-native-inputs htslib))))))
10426
10427(define-public sambamba
10428 (package
10429 (name "sambamba")
10430 (version "0.6.5")
10431 (source
10432 (origin
10433 (method url-fetch)
10434 (uri (string-append "https://github.com/lomereiter/sambamba/"
10435 "archive/v" version ".tar.gz"))
10436 (file-name (string-append name "-" version ".tar.gz"))
10437 (sha256
10438 (base32
10439 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10440 (build-system gnu-build-system)
10441 (arguments
10442 `(#:tests? #f ; there is no test target
10443 #:make-flags
10444 '("D_COMPILER=ldc2"
10445 ;; Override "--compiler" flag only.
10446 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10447 "sambamba-ldmd2-64")
10448 #:phases
10449 (modify-phases %standard-phases
10450 (delete 'configure)
10451 (add-after 'unpack 'place-biod
10452 (lambda* (#:key inputs #:allow-other-keys)
10453 (copy-recursively (assoc-ref inputs "biod") "BioD")
10454 #t))
10455 (add-after 'unpack 'unbundle-prerequisites
10456 (lambda _
10457 (substitute* "Makefile"
10458 ((" htslib-static lz4-static") ""))
10459 #t))
10460 (replace 'install
10461 (lambda* (#:key outputs #:allow-other-keys)
10462 (let* ((out (assoc-ref outputs "out"))
10463 (bin (string-append out "/bin")))
10464 (mkdir-p bin)
10465 (install-file "build/sambamba" bin)
10466 #t))))))
10467 (native-inputs
10468 `(("ldc" ,ldc)
10469 ("rdmd" ,rdmd)
10470 ("biod"
10471 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10472 (origin
10473 (method git-fetch)
10474 (uri (git-reference
10475 (url "https://github.com/biod/BioD.git")
10476 (commit commit)))
10477 (file-name (string-append "biod-"
10478 (string-take commit 9)
10479 "-checkout"))
10480 (sha256
10481 (base32
10482 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
10483 (inputs
10484 `(("lz4" ,lz4)
10485 ("htslib" ,htslib-for-sambamba)))
10486 (home-page "http://lomereiter.github.io/sambamba")
10487 (synopsis "Tools for working with SAM/BAM data")
10488 (description "Sambamba is a high performance modern robust and
10489fast tool (and library), written in the D programming language, for
10490working with SAM and BAM files. Current parallelised functionality is
10491an important subset of samtools functionality, including view, index,
10492sort, markdup, and depth.")
10493 (license license:gpl2+)))
b8fffd3a
RW		 10494
10495(define-public ritornello
10496 (package
10497 (name "ritornello")
10498 (version "1.0.0")
10499 (source (origin
10500 (method url-fetch)
10501 (uri (string-append "https://github.com/KlugerLab/"
10502 "Ritornello/archive/v"
10503 version ".tar.gz"))
10504 (file-name (string-append name "-" version ".tar.gz"))
10505 (sha256
10506 (base32
10507 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
10508 (build-system gnu-build-system)
10509 (arguments
10510 `(#:tests? #f ; there are no tests
10511 #:phases
10512 (modify-phases %standard-phases
10513 (add-after 'unpack 'patch-samtools-references
10514 (lambda* (#:key inputs #:allow-other-keys)
10515 (substitute* '("src/SamStream.h"
10516 "src/BufferedGenomeReader.h")
10517 (("<sam.h>") "<samtools/sam.h>"))
10518 #t))
10519 (delete 'configure)
10520 (replace 'install
10521 (lambda* (#:key inputs outputs #:allow-other-keys)
10522 (let* ((out (assoc-ref outputs "out"))
10523 (bin (string-append out "/bin/")))
10524 (mkdir-p bin)
10525 (install-file "bin/Ritornello" bin)
10526 #t))))))
10527 (inputs
10528 `(("samtools" ,samtools-0.1)
10529 ("fftw" ,fftw)
10530 ("boost" ,boost)
10531 ("zlib" ,zlib)))
10532 (home-page "https://github.com/KlugerLab/Ritornello")
10533 (synopsis "Control-free peak caller for ChIP-seq data")
10534 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10535signal processing that can accurately call binding events without the need to
10536do a pair total DNA input or IgG control sample. It has been tested for use
10537with narrow binding events such as transcription factor ChIP-seq.")
10538 (license license:gpl3+)))
44f6c889
RW		 10539
10540(define-public trim-galore
10541 (package
10542 (name "trim-galore")
10543 (version "0.4.2")
10544 (source
10545 (origin
10546 (method url-fetch)
10547 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
10548 "projects/trim_galore/trim_galore_v"
10549 version ".zip"))
10550 (sha256
10551 (base32
10552 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
10553 (build-system gnu-build-system)
10554 (arguments
10555 `(#:tests? #f ; no tests
10556 #:phases
10557 (modify-phases %standard-phases
10558 ;; The archive contains plain files.
10559 (replace 'unpack
10560 (lambda* (#:key source #:allow-other-keys)
10561 (zero? (system* "unzip" source))))
10562 (delete 'configure)
10563 (delete 'build)
10564 (add-after 'unpack 'hardcode-tool-references
10565 (lambda* (#:key inputs #:allow-other-keys)
10566 (substitute* "trim_galore"
10567 (("\\$path_to_cutadapt = 'cutadapt'")
10568 (string-append "$path_to_cutadapt = '"
10569 (assoc-ref inputs "cutadapt")
10570 "/bin/cutadapt'"))
10571 (("\\| gzip")
10572 (string-append "| "
10573 (assoc-ref inputs "gzip")
10574 "/bin/gzip"))
10575 (("\"gunzip")
10576 (string-append "\""
10577 (assoc-ref inputs "gzip")
10578 "/bin/gunzip")))
10579 #t))
10580 (replace 'install
10581 (lambda* (#:key outputs #:allow-other-keys)
10582 (let ((bin (string-append (assoc-ref outputs "out")
10583 "/bin")))
10584 (mkdir-p bin)
10585 (install-file "trim_galore" bin)
10586 #t))))))
10587 (inputs
10588 `(("gzip" ,gzip)
10589 ("perl" ,perl)
10590 ("cutadapt" ,cutadapt)))
10591 (native-inputs
10592 `(("unzip" ,unzip)))
10593 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10594 (synopsis "Wrapper around Cutadapt and FastQC")
10595 (description "Trim Galore! is a wrapper script to automate quality and
10596adapter trimming as well as quality control, with some added functionality to
10597remove biased methylation positions for RRBS sequence files.")
10598 (license license:gpl3+)))
3420c905
RW		 10599
10600(define-public gess
10601 (package
10602 (name "gess")
10603 (version "1.0")
10604 (source (origin
10605 (method url-fetch)
10606 (uri (string-append "http://compbio.uthscsa.edu/"
10607 "GESS_Web/files/"
10608 "gess-" version ".src.tar.gz"))
10609 (sha256
10610 (base32
10611 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10612 (build-system gnu-build-system)
10613 (arguments
10614 `(#:tests? #f ; no tests
10615 #:phases
10616 (modify-phases %standard-phases
10617 (delete 'configure)
10618 (delete 'build)
10619 (replace 'install
10620 (lambda* (#:key inputs outputs #:allow-other-keys)
10621 (let* ((python (assoc-ref inputs "python"))
10622 (out (assoc-ref outputs "out"))
10623 (bin (string-append out "/bin/"))
10624 (target (string-append
10625 out "/lib/python2.7/site-packages/gess/")))
10626 (mkdir-p target)
10627 (copy-recursively "." target)
10628 ;; Make GESS.py executable
10629 (chmod (string-append target "GESS.py") #o555)
10630 ;; Add Python shebang to the top and make Matplotlib
10631 ;; usable.
10632 (substitute* (string-append target "GESS.py")
10633 (("\"\"\"Description:" line)
10634 (string-append "#!" (which "python") "
10635import matplotlib
10636matplotlib.use('Agg')
10637" line)))
10638 ;; Make sure GESS has all modules in its path
10639 (wrap-program (string-append target "GESS.py")
10640 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
10641 (mkdir-p bin)
10642 (symlink (string-append target "GESS.py")
10643 (string-append bin "GESS.py"))
10644 #t))))))
10645 (inputs
10646 `(("python" ,python-2)
10647 ("python2-pysam" ,python2-pysam)
10648 ("python2-scipy" ,python2-scipy)
10649 ("python2-numpy" ,python2-numpy)
10650 ("python2-networkx" ,python2-networkx)
10651 ("python2-biopython" ,python2-biopython)))
10652 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
10653 (synopsis "Detect exon-skipping events from raw RNA-seq data")
10654 (description
10655 "GESS is an implementation of a novel computational method to detect de
10656novo exon-skipping events directly from raw RNA-seq data without the prior
10657knowledge of gene annotation information. GESS stands for the graph-based
10658exon-skipping scanner detection scheme.")
10659 (license license:bsd-3)))
282b0151
RW		 10660
10661(define-public phylip
10662 (package
10663 (name "phylip")
10664 (version "3.696")
10665 (source
10666 (origin
10667 (method url-fetch)
10668 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
10669 "download/phylip-" version ".tar.gz"))
10670 (sha256
10671 (base32
10672 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
10673 (build-system gnu-build-system)
10674 (arguments
10675 `(#:tests? #f ; no check target
10676 #:make-flags (list "-f" "Makefile.unx" "install")
10677 #:parallel-build? #f ; not supported
10678 #:phases
10679 (modify-phases %standard-phases
10680 (add-after 'unpack 'enter-dir
10681 (lambda _ (chdir "src") #t))
10682 (delete 'configure)
10683 (replace 'install
10684 (lambda* (#:key inputs outputs #:allow-other-keys)
10685 (let ((target (string-append (assoc-ref outputs "out")
10686 "/bin")))
10687 (mkdir-p target)
10688 (for-each (lambda (file)
10689 (install-file file target))
10690 (find-files "../exe" ".*")))
10691 #t)))))
10692 (home-page "http://evolution.genetics.washington.edu/phylip/")
10693 (synopsis "Tools for inferring phylogenies")
10694 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
10695programs for inferring phylogenies (evolutionary trees).")
10696 (license license:bsd-2)))
aa163424
RW		 10697
10698(define-public imp
10699 (package
10700 (name "imp")
10701 (version "2.6.2")
10702 (source
10703 (origin
10704 (method url-fetch)
10705 (uri (string-append "https://integrativemodeling.org/"
10706 version "/download/imp-" version ".tar.gz"))
10707 (sha256
10708 (base32
10709 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
10710 (build-system cmake-build-system)
10711 (arguments
10712 `(;; FIXME: Some tests fail because they produce warnings, others fail
10713 ;; because the PYTHONPATH does not include the modeller's directory.
10714 #:tests? #f
10715 ;; Do not place libraries in an architecture-specific directory.
10716 #:configure-flags
10717 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
10718 (inputs
10719 `(("boost" ,boost)
10720 ("gsl" ,gsl)
10721 ("swig" ,swig)
10722 ("hdf5" ,hdf5)
10723 ("fftw" ,fftw)
10724 ("python" ,python-2)))
10725 (propagated-inputs
10726 `(("python2-numpy" ,python2-numpy)
10727 ("python2-scipy" ,python2-scipy)
10728 ("python2-pandas" ,python2-pandas)
10729 ("python2-scikit-learn" ,python2-scikit-learn)
10730 ("python2-networkx" ,python2-networkx)))
10731 (home-page "https://integrativemodeling.org")
10732 (synopsis "Integrative modeling platform")
10733 (description "IMP's broad goal is to contribute to a comprehensive
10734structural characterization of biomolecules ranging in size and complexity
10735from small peptides to large macromolecular assemblies, by integrating data
10736from diverse biochemical and biophysical experiments. IMP provides a C++ and
10737Python toolbox for solving complex modeling problems, and a number of
10738applications for tackling some common problems in a user-friendly way.")
10739 ;; IMP is largely available under the GNU Lesser GPL; see the file
10740 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
10741 ;; available under the GNU GPL (see the file COPYING.GPL).
10742 (license (list license:lgpl2.1+
10743 license:gpl3+))))
8befd094
RW		 10744
10745(define-public tadbit
10746 (package
10747 (name "tadbit")
10748 (version "0.2")
10749 (source (origin
10750 (method url-fetch)
10751 (uri (string-append "https://github.com/3DGenomes/TADbit/"
10752 "archive/v" version ".tar.gz"))
10753 (file-name (string-append name "-" version ".tar.gz"))
10754 (sha256
10755 (base32
10756 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
10757 (build-system python-build-system)
10758 (arguments
10759 `(;; Tests are included and must be run after installation, but
10760 ;; they are incomplete and thus cannot be run.
10761 #:tests? #f
10762 #:python ,python-2
10763 #:phases
10764 (modify-phases %standard-phases
10765 (add-after 'unpack 'fix-problems-with-setup.py
10766 (lambda* (#:key outputs #:allow-other-keys)
10767 ;; setup.py opens these files for writing
10768 (chmod "_pytadbit/_version.py" #o664)
10769 (chmod "README.rst" #o664)
10770
10771 ;; Don't attempt to install the bash completions to
10772 ;; the home directory.
10773 (rename-file "extras/.bash_completion"
10774 "extras/tadbit")
10775 (substitute* "setup.py"
10776 (("\\(path.expanduser\\('~'\\)")
10777 (string-append "(\""
10778 (assoc-ref outputs "out")
10779 "/etc/bash_completion.d\""))
10780 (("extras/\\.bash_completion")
10781 "extras/tadbit"))
10782 #t)))))
10783 (inputs
10784 ;; TODO: add Chimera for visualization
10785 `(("imp" ,imp)
10786 ("mcl" ,mcl)
10787 ("python2-scipy" ,python2-scipy)
10788 ("python2-numpy" ,python2-numpy)
10789 ("python2-matplotlib" ,python2-matplotlib)
10790 ("python2-pysam" ,python2-pysam)))
10791 (home-page "http://3dgenomes.github.io/TADbit/")
10792 (synopsis "Analyze, model, and explore 3C-based data")
10793 (description
10794 "TADbit is a complete Python library to deal with all steps to analyze,
10795model, and explore 3C-based data. With TADbit the user can map FASTQ files to
10796obtain raw interaction binned matrices (Hi-C like matrices), normalize and
a147fadd 10797correct interaction matrices, identify and compare the so-called
8befd094
RW		 10798@dfn{Topologically Associating Domains} (TADs), build 3D models from the
10799interaction matrices, and finally, extract structural properties from the
10800models. TADbit is complemented by TADkit for visualizing 3D models.")
10801 (license license:gpl3+)))
94820951
RW		 10802
10803(define-public kentutils
10804 (package
10805 (name "kentutils")
10806 ;; 302.1.0 is out, but the only difference is the inclusion of
10807 ;; pre-built binaries.
10808 (version "302.0.0")
10809 (source
10810 (origin
10811 (method url-fetch)
10812 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
10813 "archive/v" version ".tar.gz"))
10814 (file-name (string-append name "-" version ".tar.gz"))
10815 (sha256
10816 (base32
10817 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
10818 (modules '((guix build utils)
10819 (srfi srfi-26)
10820 (ice-9 ftw)))
10821 (snippet
10822 '(begin
10823 ;; Only the contents of the specified directories are free
10824 ;; for all uses, so we remove the rest. "hg/autoSql" and
10825 ;; "hg/autoXml" are nominally free, but they depend on a
10826 ;; library that is built from the sources in "hg/lib",
10827 ;; which is nonfree.
10828 (let ((free (list "." ".."
10829 "utils" "lib" "inc" "tagStorm"
10830 "parasol" "htslib"))
10831 (directory? (lambda (file)
10832 (eq? 'directory (stat:type (stat file))))))
10833 (for-each (lambda (file)
10834 (and (directory? file)
10835 (delete-file-recursively file)))
10836 (map (cut string-append "src/" <>)
10837 (scandir "src"
10838 (lambda (file)
10839 (not (member file free)))))))
10840 ;; Only make the utils target, not the userApps target,
10841 ;; because that requires libraries we won't build.
10842 (substitute* "Makefile"
10843 ((" userApps") " utils"))
10844 ;; Only build libraries that are free.
10845 (substitute* "src/makefile"
10846 (("DIRS =.*") "DIRS =\n")
10847 (("cd jkOwnLib.*") "")
10848 ((" hgLib") "")
10849 (("cd hg.*") ""))
10850 (substitute* "src/utils/makefile"
10851 ;; These tools depend on "jkhgap.a", which is part of the
10852 ;; nonfree "src/hg/lib" directory.
10853 (("raSqlQuery") "")
10854 (("pslLiftSubrangeBlat") "")
10855
10856 ;; Do not build UCSC tools, which may require nonfree
10857 ;; components.
10858 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
10859 #t))))
10860 (build-system gnu-build-system)
10861 (arguments
10862 `( ;; There is no global test target and the test target for
10863 ;; individual tools depends on input files that are not
10864 ;; included.
10865 #:tests? #f
10866 #:phases
10867 (modify-phases %standard-phases
10868 (add-after 'unpack 'fix-paths
10869 (lambda _
10870 (substitute* "Makefile"
10871 (("/bin/echo") (which "echo")))
10872 #t))
10873 (add-after 'unpack 'prepare-samtabix
10874 (lambda* (#:key inputs #:allow-other-keys)
10875 (copy-recursively (assoc-ref inputs "samtabix")
10876 "samtabix")
10877 #t))
10878 (delete 'configure)
10879 (replace 'install
10880 (lambda* (#:key outputs #:allow-other-keys)
10881 (let ((bin (string-append (assoc-ref outputs "out")
10882 "/bin")))
10883 (copy-recursively "bin" bin))
10884 #t)))))
10885 (native-inputs
10886 `(("samtabix"
10887 ,(origin
10888 (method git-fetch)
10889 (uri (git-reference
10890 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
10891 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
10892 (sha256
10893 (base32
10894 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
10895 (inputs
10896 `(("zlib" ,zlib)
10897 ("tcsh" ,tcsh)
10898 ("perl" ,perl)
10899 ("libpng" ,libpng)
10900 ("mysql" ,mysql)
10901 ("openssl" ,openssl)))
10902 (home-page "http://genome.cse.ucsc.edu/index.html")
10903 (synopsis "Assorted bioinformatics utilities")
10904 (description "This package provides the kentUtils, a selection of
10905bioinformatics utilities used in combination with the UCSC genome
10906browser.")
10907 ;; Only a subset of the sources are released under a non-copyleft
10908 ;; free software license. All other sources are removed in a
10909 ;; snippet. See this bug report for an explanation of how the
10910 ;; license statements apply:
10911 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
10912 (license (license:non-copyleft
10913 "http://genome.ucsc.edu/license/"
10914 "The contents of this package are free for all uses."))))
7ceb0a83
RW		 10915
10916(define-public f-seq
10917 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
10918 (revision "1"))
10919 (package
10920 (name "f-seq")
c6643f2d 10921 (version (string-append "1.1-" revision "." (string-take commit 7)))
7ceb0a83
RW		 10922 (source (origin
10923 (method git-fetch)
10924 (uri (git-reference
10925 (url "https://github.com/aboyle/F-seq.git")
10926 (commit commit)))
10927 (file-name (string-append name "-" version))
10928 (sha256
10929 (base32
10930 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
10931 (modules '((guix build utils)))
10932 ;; Remove bundled Java library archives.
10933 (snippet
10934 '(begin
10935 (for-each delete-file (find-files "lib" ".*"))
10936 #t))))
10937 (build-system ant-build-system)
10938 (arguments
10939 `(#:tests? #f ; no tests included
10940 #:phases
10941 (modify-phases %standard-phases
10942 (replace 'install
c0770fee 10943 (lambda* (#:key inputs outputs #:allow-other-keys)
7ceb0a83
RW		 10944 (let* ((target (assoc-ref outputs "out"))
10945 (doc (string-append target "/share/doc/f-seq/")))
10946 (mkdir-p target)
10947 (mkdir-p doc)
10948 (substitute* "bin/linux/fseq"
c0770fee
RW		 10949 (("java") (which "java"))
10950 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
10951 (string-append (assoc-ref inputs "java-commons-cli")
10952 "/share/java/commons-cli.jar"))
10953 (("REALDIR=.*")
10954 (string-append "REALDIR=" target "/bin\n")))
7ceb0a83
RW		 10955 (install-file "README.txt" doc)
10956 (install-file "bin/linux/fseq" (string-append target "/bin"))
10957 (install-file "build~/fseq.jar" (string-append target "/lib"))
10958 (copy-recursively "lib" (string-append target "/lib"))
10959 #t))))))
10960 (inputs
10961 `(("perl" ,perl)
10962 ("java-commons-cli" ,java-commons-cli)))
10963 (home-page "http://fureylab.web.unc.edu/software/fseq/")
10964 (synopsis "Feature density estimator for high-throughput sequence tags")
10965 (description
10966 "F-Seq is a software package that generates a continuous tag sequence
10967density estimation allowing identification of biologically meaningful sites
10968such as transcription factor binding sites (ChIP-seq) or regions of open
10969chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
10970Browser.")
10971 (license license:gpl3+))))
96348048
RW		 10972
10973(define-public bismark
10974 (package
10975 (name "bismark")
10976 (version "0.16.3")
10977 (source
10978 (origin
10979 (method url-fetch)
10980 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
10981 "archive/" version ".tar.gz"))
10982 (file-name (string-append name "-" version ".tar.gz"))
10983 (sha256
10984 (base32
10985 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
10986 (build-system perl-build-system)
10987 (arguments
10988 `(#:tests? #f ; there are no tests
10989 #:phases
10990 (modify-phases %standard-phases
10991 (delete 'configure)
10992 (delete 'build)
10993 (replace 'install
10994 (lambda* (#:key outputs #:allow-other-keys)
10995 (let ((bin (string-append (assoc-ref outputs "out")
10996 "/bin"))
10997 (docdir (string-append (assoc-ref outputs "out")
10998 "/share/doc/bismark"))
10999 (docs '("Bismark_User_Guide.pdf"
11000 "RELEASE_NOTES.txt"))
11001 (scripts '("bismark"
11002 "bismark_genome_preparation"
11003 "bismark_methylation_extractor"
11004 "bismark2bedGraph"
11005 "bismark2report"
11006 "coverage2cytosine"
11007 "deduplicate_bismark"
11008 "bismark_sitrep.tpl"
11009 "bam2nuc"
11010 "bismark2summary")))
11011 (mkdir-p docdir)
11012 (mkdir-p bin)
11013 (for-each (lambda (file) (install-file file bin))
11014 scripts)
11015 (for-each (lambda (file) (install-file file docdir))
11016 docs)
11017 #t))))))
11018 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11019 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11020 (description "Bismark is a program to map bisulfite treated sequencing
11021reads to a genome of interest and perform methylation calls in a single step.
11022The output can be easily imported into a genome viewer, such as SeqMonk, and
11023enables a researcher to analyse the methylation levels of their samples
11024straight away. Its main features are:
11025
11026@itemize
11027@item Bisulfite mapping and methylation calling in one single step
11028@item Supports single-end and paired-end read alignments
11029@item Supports ungapped and gapped alignments
11030@item Alignment seed length, number of mismatches etc are adjustable
11031@item Output discriminates between cytosine methylation in CpG, CHG
11032 and CHH context
11033@end itemize\n")
11034 (license license:gpl3+)))
dc8ddbfb
RW		 11035
11036(define-public paml
11037 (package
11038 (name "paml")
11039 (version "4.9e")
11040 (source (origin
11041 (method url-fetch)
11042 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11043 "paml" version ".tgz"))
11044 (sha256
11045 (base32
11046 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11047 (modules '((guix build utils)))
11048 ;; Remove Windows binaries
11049 (snippet
11050 '(begin
11051 (for-each delete-file (find-files "." "\\.exe$"))
11052 #t))))
11053 (build-system gnu-build-system)
11054 (arguments
11055 `(#:tests? #f ; there are no tests
11056 #:make-flags '("CC=gcc")
11057 #:phases
11058 (modify-phases %standard-phases
11059 (replace 'configure
11060 (lambda _
11061 (substitute* "src/BFdriver.c"
11062 (("/bin/bash") (which "bash")))
11063 (chdir "src")
11064 #t))
11065 (replace 'install
11066 (lambda* (#:key outputs #:allow-other-keys)
11067 (let ((tools '("baseml" "basemlg" "codeml"
11068 "pamp" "evolver" "yn00" "chi2"))
11069 (bin (string-append (assoc-ref outputs "out") "/bin"))
11070 (docdir (string-append (assoc-ref outputs "out")
11071 "/share/doc/paml")))
11072 (mkdir-p bin)
11073 (for-each (lambda (file) (install-file file bin)) tools)
11074 (copy-recursively "../doc" docdir)
11075 #t))))))
11076 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11077 (synopsis "Phylogentic analysis by maximum likelihood")
11078 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11079contains a few programs for model fitting and phylogenetic tree reconstruction
11080using nucleotide or amino-acid sequence data.")
11081 ;; GPLv3 only
11082 (license license:gpl3)))
d112e5a8
RW		 11083
11084(define-public kallisto
11085 (package
11086 (name "kallisto")
11087 (version "0.43.1")
11088 (source (origin
11089 (method url-fetch)
11090 (uri (string-append "https://github.com/pachterlab/"
11091 "kallisto/archive/v" version ".tar.gz"))
11092 (file-name (string-append name "-" version ".tar.gz"))
11093 (sha256
11094 (base32
11095 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11096 (build-system cmake-build-system)
11097 (arguments `(#:tests? #f)) ; no "check" target
11098 (inputs
11099 `(("hdf5" ,hdf5)
11100 ("zlib" ,zlib)))
11101 (home-page "http://pachterlab.github.io/kallisto/")
11102 (synopsis "Near-optimal RNA-Seq quantification")
11103 (description
11104 "Kallisto is a program for quantifying abundances of transcripts from
11105RNA-Seq data, or more generally of target sequences using high-throughput
11106sequencing reads. It is based on the novel idea of pseudoalignment for
11107rapidly determining the compatibility of reads with targets, without the need
11108for alignment. Pseudoalignment of reads preserves the key information needed
11109for quantification, and kallisto is therefore not only fast, but also as
11110accurate as existing quantification tools.")
11111 (license license:bsd-2)))
c3b2ab9d
RW		 11112
11113(define-public libgff
11114 (package
11115 (name "libgff")
11116 (version "1.0")
11117 (source (origin
11118 (method url-fetch)
11119 (uri (string-append
11120 "https://github.com/Kingsford-Group/"
11121 "libgff/archive/v" version ".tar.gz"))
11122 (file-name (string-append name "-" version ".tar.gz"))
11123 (sha256
11124 (base32
11125 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11126 (build-system cmake-build-system)
11127 (arguments `(#:tests? #f)) ; no tests included
11128 (home-page "https://github.com/Kingsford-Group/libgff")
11129 (synopsis "Parser library for reading/writing GFF files")
11130 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11131code that is used in the Cufflinks codebase. The goal of this library is to
11132provide this functionality without the necessity of drawing in a heavy-weight
11133dependency like SeqAn.")
11134 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
1fe0bde3
RW		 11135
11136(define-public libdivsufsort
11137 (package
11138 (name "libdivsufsort")
11139 (version "2.0.1")
11140 (source (origin
11141 (method git-fetch)
11142 (uri (git-reference
11143 (url "https://github.com/y-256/libdivsufsort.git")
11144 (commit version)))
11145 (sha256
11146 (base32
11147 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11148 (build-system cmake-build-system)
11149 (arguments
11150 '(#:tests? #f ; there are no tests
11151 #:configure-flags
11152 ;; Needed for rapmap and sailfish.
11153 '("-DBUILD_DIVSUFSORT64=ON")))
11154 (home-page "https://github.com/y-256/libdivsufsort")
11155 (synopsis "Lightweight suffix-sorting library")
11156 (description "libdivsufsort is a software library that implements a
11157lightweight suffix array construction algorithm. This library provides a
11158simple and an efficient C API to construct a suffix array and a
11159Burrows-Wheeler transformed string from a given string over a constant-size
11160alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11161bytes of memory space, where n is the length of the string.")
11162 (license license:expat)))
jackhill's copy of GNU Guix: https://guix.gnu.org/