HCoop / jackhill / guix / guix.git / blame
? search:
summary | shortlog | log | commit | commitdiff | tree
blob | blame (incremental) | history | HEAD
gnu: r-edger: Update to 3.16.5.
[jackhill/guix/guix.git] / gnu / packages / bioinformatics.scm
CommitLineData
4e10a221 1;;; GNU Guix --- Functional package management for GNU
0047d26a 2;;; Copyright © 2014, 2015, 2016 Ricardo Wurmus <rekado@elephly.net>
9b9b7ffd 3;;; Copyright © 2015, 2016 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>
ddb83129 7;;; Copyright © 2016 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>
4e10a221
RW		 10;;;
11;;; This file is part of GNU Guix.
12;;;
13;;; GNU Guix is free software; you can redistribute it and/or modify it
14;;; under the terms of the GNU General Public License as published by
15;;; the Free Software Foundation; either version 3 of the License, or (at
16;;; your option) any later version.
17;;;
18;;; GNU Guix is distributed in the hope that it will be useful, but
19;;; WITHOUT ANY WARRANTY; without even the implied warranty of
20;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21;;; GNU General Public License for more details.
22;;;
23;;; You should have received a copy of the GNU General Public License
24;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
25
26(define-module (gnu packages bioinformatics)
27 #:use-module ((guix licenses) #:prefix license:)
28 #:use-module (guix packages)
8e913213 29 #:use-module (guix utils)
4e10a221 30 #:use-module (guix download)
2c16316e 31 #:use-module (guix git-download)
ec946638 32 #:use-module (guix hg-download)
10b4a969 33 #:use-module (guix build-system ant)
4e10a221 34 #:use-module (guix build-system gnu)
d7678942 35 #:use-module (guix build-system cmake)
365c8153 36 #:use-module (guix build-system perl)
8622a072 37 #:use-module (guix build-system python)
a5002ae7 38 #:use-module (guix build-system r)
9c38b540 39 #:use-module (guix build-system ruby)
d3517eda 40 #:use-module (guix build-system trivial)
4e10a221 41 #:use-module (gnu packages)
a2950fa4 42 #:use-module (gnu packages autotools)
684bf7c7 43 #:use-module (gnu packages algebra)
d3517eda 44 #:use-module (gnu packages base)
318c0aee 45 #:use-module (gnu packages bash)
a0a71439 46 #:use-module (gnu packages bison)
e4e5a4d8 47 #:use-module (gnu packages boost)
4e10a221 48 #:use-module (gnu packages compression)
82c370de 49 #:use-module (gnu packages cpio)
1baee943 50 #:use-module (gnu packages curl)
99828fa7 51 #:use-module (gnu packages documentation)
d29150b5 52 #:use-module (gnu packages datastructures)
75dd2424 53 #:use-module (gnu packages file)
99268755 54 #:use-module (gnu packages flex)
02f35bb5 55 #:use-module (gnu packages gawk)
2409f37f 56 #:use-module (gnu packages gcc)
66e40e00 57 #:use-module (gnu packages gd)
97b9da68 58 #:use-module (gnu packages gtk)
b16728b0 59 #:use-module (gnu packages glib)
db7a3444 60 #:use-module (gnu packages groff)
50937297 61 #:use-module (gnu packages guile)
89984be4 62 #:use-module (gnu packages haskell)
66e40e00 63 #:use-module (gnu packages image)
97b9da68 64 #:use-module (gnu packages imagemagick)
15a3c3d4 65 #:use-module (gnu packages java)
51c64999 66 #:use-module (gnu packages linux)
ec946638 67 #:use-module (gnu packages logging)
36742f43 68 #:use-module (gnu packages machine-learning)
db7a3444 69 #:use-module (gnu packages man)
c833ab55 70 #:use-module (gnu packages maths)
6c2b26e2 71 #:use-module (gnu packages mpi)
4e10a221 72 #:use-module (gnu packages ncurses)
81f3e0c1 73 #:use-module (gnu packages pcre)
ceb62d54 74 #:use-module (gnu packages parallel)
66e40e00 75 #:use-module (gnu packages pdf)
4e10a221
RW		 76 #:use-module (gnu packages perl)
77 #:use-module (gnu packages pkg-config)
bfe3c685 78 #:use-module (gnu packages popt)
e4e5a4d8 79 #:use-module (gnu packages protobuf)
346a829a 80 #:use-module (gnu packages python)
ec946638 81 #:use-module (gnu packages readline)
9c38b540 82 #:use-module (gnu packages ruby)
84be3b99 83 #:use-module (gnu packages serialization)
c833ab55 84 #:use-module (gnu packages statistics)
d7678942 85 #:use-module (gnu packages tbb)
97b9da68 86 #:use-module (gnu packages tex)
db7a3444 87 #:use-module (gnu packages texinfo)
2127cedb 88 #:use-module (gnu packages textutils)
43c565d2 89 #:use-module (gnu packages time)
a2950fa4 90 #:use-module (gnu packages tls)
ce7155d5 91 #:use-module (gnu packages vim)
365c8153 92 #:use-module (gnu packages web)
c833ab55 93 #:use-module (gnu packages xml)
66e40e00 94 #:use-module (gnu packages xorg)
f7283db3
RW		 95 #:use-module (gnu packages zip)
96 #:use-module (srfi srfi-1))
4e10a221 97
8dc797fa
BW		 98(define-public aragorn
99 (package
100 (name "aragorn")
e990c81d 101 (version "1.2.38")
8dc797fa
BW		 102 (source (origin
103 (method url-fetch)
104 (uri (string-append
105 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
106 version ".tgz"))
107 (sha256
108 (base32
e990c81d 109 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
8dc797fa
BW		 110 (build-system gnu-build-system)
111 (arguments
112 `(#:tests? #f ; there are no tests
113 #:phases
114 (modify-phases %standard-phases
115 (delete 'configure)
116 (replace 'build
117 (lambda _
118 (zero? (system* "gcc"
119 "-O3"
120 "-ffast-math"
121 "-finline-functions"
122 "-o"
123 "aragorn"
124 (string-append "aragorn" ,version ".c")))))
125 (replace 'install
126 (lambda* (#:key outputs #:allow-other-keys)
127 (let* ((out (assoc-ref outputs "out"))
128 (bin (string-append out "/bin"))
129 (man (string-append out "/share/man/man1")))
130 (mkdir-p bin)
131 (copy-file "aragorn"
132 (string-append bin "/aragorn"))
133 (mkdir-p man)
134 (copy-file "aragorn.1"
135 (string-append man "/aragorn.1")))
136 #t)))))
137 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
138 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
139 (description
140 "Aragorn identifies transfer RNA, mitochondrial RNA and
141transfer-messenger RNA from nucleotide sequences, based on homology to known
142tRNA consensus sequences and RNA structure. It also outputs the secondary
143structure of the predicted RNA.")
144 (license license:gpl2)))
145
a12ba6e8
BW		 146(define-public bamm
147 (package
148 (name "bamm")
4b6da268 149 (version "1.7.3")
a12ba6e8
BW		 150 (source (origin
151 (method url-fetch)
152 ;; BamM is not available on pypi.
153 (uri (string-append
4b6da268 154 "https://github.com/Ecogenomics/BamM/archive/"
a12ba6e8
BW		 155 version ".tar.gz"))
156 (file-name (string-append name "-" version ".tar.gz"))
157 (sha256
158 (base32
4b6da268 159 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
a12ba6e8
BW		 160 (modules '((guix build utils)))
161 (snippet
162 `(begin
163 ;; Delete bundled htslib.
164 (delete-file-recursively "c/htslib-1.3.1")
165 #t))))
166 (build-system python-build-system)
167 (arguments
168 `(#:python ,python-2 ; BamM is Python 2 only.
169 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
170 ;; been modified from its original form.
171 #:configure-flags
172 (let ((htslib (assoc-ref %build-inputs "htslib")))
173 (list "--with-libhts-lib" (string-append htslib "/lib")
174 "--with-libhts-inc" (string-append htslib "/include/htslib")))
175 #:phases
176 (modify-phases %standard-phases
177 (add-after 'unpack 'autogen
178 (lambda _
179 (with-directory-excursion "c"
180 (let ((sh (which "sh")))
181 ;; Use autogen so that 'configure' works.
182 (substitute* "autogen.sh" (("/bin/sh") sh))
183 (setenv "CONFIG_SHELL" sh)
184 (substitute* "configure" (("/bin/sh") sh))
185 (zero? (system* "./autogen.sh"))))))
186 (delete 'build)
187 ;; Run tests after installation so compilation only happens once.
188 (delete 'check)
189 (add-after 'install 'wrap-executable
190 (lambda* (#:key outputs #:allow-other-keys)
191 (let* ((out (assoc-ref outputs "out"))
192 (path (getenv "PATH")))
193 (wrap-program (string-append out "/bin/bamm")
194 `("PATH" ":" prefix (,path))))
195 #t))
196 (add-after 'wrap-executable 'post-install-check
197 (lambda* (#:key inputs outputs #:allow-other-keys)
198 (setenv "PATH"
199 (string-append (assoc-ref outputs "out")
200 "/bin:"
201 (getenv "PATH")))
202 (setenv "PYTHONPATH"
203 (string-append
204 (assoc-ref outputs "out")
205 "/lib/python"
206 (string-take (string-take-right
207 (assoc-ref inputs "python") 5) 3)
208 "/site-packages:"
209 (getenv "PYTHONPATH")))
210 ;; There are 2 errors printed, but they are safe to ignore:
211 ;; 1) [E::hts_open_format] fail to open file ...
212 ;; 2) samtools view: failed to open ...
213 (zero? (system* "nosetests")))))))
214 (native-inputs
215 `(("autoconf" ,autoconf)
216 ("automake" ,automake)
217 ("libtool" ,libtool)
218 ("zlib" ,zlib)
219 ("python-nose" ,python2-nose)
f3b98f4f 220 ("python-pysam" ,python2-pysam)))
a12ba6e8
BW		 221 (inputs
222 `(("htslib" ,htslib)
223 ("samtools" ,samtools)
224 ("bwa" ,bwa)
225 ("grep" ,grep)
226 ("sed" ,sed)
227 ("coreutils" ,coreutils)))
228 (propagated-inputs
229 `(("python-numpy" ,python2-numpy)))
230 (home-page "http://ecogenomics.github.io/BamM/")
231 (synopsis "Metagenomics-focused BAM file manipulator")
232 (description
233 "BamM is a C library, wrapped in python, to efficiently generate and
234parse BAM files, specifically for the analysis of metagenomic data. For
235instance, it implements several methods to assess contig-wise read coverage.")
236 (license license:lgpl3+)))
237
9794180d
RW		 238(define-public bamtools
239 (package
240 (name "bamtools")
241 (version "2.3.0")
242 (source (origin
243 (method url-fetch)
244 (uri (string-append
245 "https://github.com/pezmaster31/bamtools/archive/v"
246 version ".tar.gz"))
247 (file-name (string-append name "-" version ".tar.gz"))
248 (sha256
249 (base32
250 "1brry29bw2xr2l9pqn240rkqwayg85b8qq78zk2zs6nlspk4d018"))))
251 (build-system cmake-build-system)
4702cec2
RW		 252 (arguments
253 `(#:tests? #f ;no "check" target
254 #:phases
255 (modify-phases %standard-phases
256 (add-before
257 'configure 'set-ldflags
258 (lambda* (#:key outputs #:allow-other-keys)
259 (setenv "LDFLAGS"
260 (string-append
261 "-Wl,-rpath="
262 (assoc-ref outputs "out") "/lib/bamtools")))))))
9794180d
RW		 263 (inputs `(("zlib" ,zlib)))
264 (home-page "https://github.com/pezmaster31/bamtools")
265 (synopsis "C++ API and command-line toolkit for working with BAM data")
266 (description
267 "BamTools provides both a C++ API and a command-line toolkit for handling
268BAM files.")
269 (license license:expat)))
270
bdc7be59
MB		 271(define-public bcftools
272 (package
273 (name "bcftools")
274 (version "1.3.1")
275 (source (origin
276 (method url-fetch)
277 (uri (string-append
278 "https://github.com/samtools/bcftools/releases/download/"
279 version "/bcftools-" version ".tar.bz2"))
280 (sha256
281 (base32
282 "095ry68vmz9q5s1scjsa698dhgyvgw5aicz24c19iwfbai07mhqj"))
283 (modules '((guix build utils)))
284 (snippet
285 ;; Delete bundled htslib.
286 '(delete-file-recursively "htslib-1.3.1"))))
287 (build-system gnu-build-system)
288 (arguments
289 `(#:test-target "test"
290 #:make-flags
291 (list
292 "USE_GPL=1"
293 (string-append "prefix=" (assoc-ref %outputs "out"))
294 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
295 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.a")
296 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
297 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix"))
298 #:phases
299 (modify-phases %standard-phases
300 (add-after 'unpack 'patch-Makefile
301 (lambda _
302 (substitute* "Makefile"
303 ;; Do not attempt to build htslib.
304 (("^include \\$\\(HTSDIR\\)/htslib\\.mk") "")
305 ;; Link against GSL cblas.
306 (("-lcblas") "-lgslcblas"))
307 #t))
308 (delete 'configure)
309 (add-before 'check 'patch-tests
310 (lambda _
311 (substitute* "test/test.pl"
312 (("/bin/bash") (which "bash")))
313 #t)))))
314 (native-inputs
315 `(("htslib" ,htslib)
316 ("perl" ,perl)))
317 (inputs
318 `(("gsl" ,gsl)
319 ("zlib" ,zlib)))
320 (home-page "https://samtools.github.io/bcftools/")
321 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
322 (description
323 "BCFtools is a set of utilities that manipulate variant calls in the
324Variant Call Format (VCF) and its binary counterpart BCF. All commands work
325transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
326 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
327 (license (list license:gpl3+ license:expat))))
328
8dd4ff11
RW		 329(define-public bedops
330 (package
331 (name "bedops")
1bbc3b1d 332 (version "2.4.14")
8dd4ff11
RW		 333 (source (origin
334 (method url-fetch)
335 (uri (string-append "https://github.com/bedops/bedops/archive/v"
336 version ".tar.gz"))
f586c877 337 (file-name (string-append name "-" version ".tar.gz"))
8dd4ff11
RW		 338 (sha256
339 (base32
1bbc3b1d 340 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
8dd4ff11
RW		 341 (build-system gnu-build-system)
342 (arguments
343 '(#:tests? #f
344 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
345 #:phases
346 (alist-cons-after
347 'unpack 'unpack-tarballs
348 (lambda _
349 ;; FIXME: Bedops includes tarballs of minimally patched upstream
350 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
351 ;; libraries because at least one of the libraries (zlib) is
352 ;; patched to add a C++ function definition (deflateInit2cpp).
353 ;; Until the Bedops developers offer a way to link against system
354 ;; libraries we have to build the in-tree copies of these three
355 ;; libraries.
356
357 ;; See upstream discussion:
358 ;; https://github.com/bedops/bedops/issues/124
359
360 ;; Unpack the tarballs to benefit from shebang patching.
361 (with-directory-excursion "third-party"
362 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
363 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
364 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
365 ;; Disable unpacking of tarballs in Makefile.
366 (substitute* "system.mk/Makefile.linux"
367 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
368 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
369 (substitute* "third-party/zlib-1.2.7/Makefile.in"
370 (("^SHELL=.*$") "SHELL=bash\n")))
371 (alist-delete 'configure %standard-phases))))
372 (home-page "https://github.com/bedops/bedops")
373 (synopsis "Tools for high-performance genomic feature operations")
374 (description
375 "BEDOPS is a suite of tools to address common questions raised in genomic
376studies---mostly with regard to overlap and proximity relationships between
377data sets. It aims to be scalable and flexible, facilitating the efficient
378and accurate analysis and management of large-scale genomic data.
379
380BEDOPS provides tools that perform highly efficient and scalable Boolean and
381other set operations, statistical calculations, archiving, conversion and
382other management of genomic data of arbitrary scale. Tasks can be easily
383split by chromosome for distributing whole-genome analyses across a
384computational cluster.")
385 (license license:gpl2+)))
386
81de5647
RW		 387(define-public bedtools
388 (package
389 (name "bedtools")
d285657e 390 (version "2.26.0")
81de5647
RW		 391 (source (origin
392 (method url-fetch)
393 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
394 version ".tar.gz"))
f586c877 395 (file-name (string-append name "-" version ".tar.gz"))
81de5647
RW		 396 (sha256
397 (base32
d285657e 398 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
81de5647
RW		 399 (build-system gnu-build-system)
400 (native-inputs `(("python" ,python-2)))
401 (inputs `(("samtools" ,samtools)
402 ("zlib" ,zlib)))
403 (arguments
404 '(#:test-target "test"
405 #:phases
6573ac82 406 (modify-phases %standard-phases
6573ac82
BW		 407 (delete 'configure)
408 (replace 'install
409 (lambda* (#:key outputs #:allow-other-keys)
410 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
411 (for-each (lambda (file)
412 (install-file file bin))
413 (find-files "bin" ".*")))
414 #t)))))
81de5647
RW		 415 (home-page "https://github.com/arq5x/bedtools2")
416 (synopsis "Tools for genome analysis and arithmetic")
417 (description
418 "Collectively, the bedtools utilities are a swiss-army knife of tools for
419a wide-range of genomics analysis tasks. The most widely-used tools enable
420genome arithmetic: that is, set theory on the genome. For example, bedtools
421allows one to intersect, merge, count, complement, and shuffle genomic
422intervals from multiple files in widely-used genomic file formats such as BAM,
423BED, GFF/GTF, VCF.")
424 (license license:gpl2)))
425
9a8f309c
RW		 426;; Later releases of bedtools produce files with more columns than
427;; what Ribotaper expects.
428(define-public bedtools-2.18
429 (package (inherit bedtools)
430 (name "bedtools")
431 (version "2.18.0")
432 (source (origin
433 (method url-fetch)
434 (uri (string-append "https://github.com/arq5x/bedtools2/"
435 "archive/v" version ".tar.gz"))
436 (file-name (string-append name "-" version ".tar.gz"))
437 (sha256
438 (base32
439 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
440
17dc32a4
RW		 441(define-public ribotaper
442 (package
443 (name "ribotaper")
444 (version "1.3.1")
445 (source (origin
446 (method url-fetch)
447 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
448 "files/RiboTaper/RiboTaper_Version_"
449 version ".tar.gz"))
450 (sha256
451 (base32
452 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
453 (build-system gnu-build-system)
454 (inputs
455 `(("bedtools" ,bedtools-2.18)
456 ("samtools" ,samtools-0.1)
457 ("r" ,r)
458 ("r-foreach" ,r-foreach)
459 ("r-xnomial" ,r-xnomial)
460 ("r-domc" ,r-domc)
461 ("r-multitaper" ,r-multitaper)
462 ("r-seqinr" ,r-seqinr)))
463 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
464 (synopsis "Define translated ORFs using ribosome profiling data")
465 (description
466 "Ribotaper is a method for defining translated @dfn{open reading
467frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
468provides the Ribotaper pipeline.")
469 (license license:gpl3+)))
470
a0a71439
RJ		 471(define-public bioawk
472 (package
473 (name "bioawk")
474 (version "1.0")
475 (source (origin
476 (method url-fetch)
477 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
478 version ".tar.gz"))
479 (file-name (string-append name "-" version ".tar.gz"))
480 (sha256
481 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
482 (build-system gnu-build-system)
483 (inputs
484 `(("zlib" ,zlib)))
485 (native-inputs
486 `(("bison" ,bison)))
487 (arguments
488 `(#:tests? #f ; There are no tests to run.
489 ;; Bison must generate files, before other targets can build.
490 #:parallel-build? #f
491 #:phases
492 (modify-phases %standard-phases
493 (delete 'configure) ; There is no configure phase.
494 (replace 'install
495 (lambda* (#:key outputs #:allow-other-keys)
496 (let* ((out (assoc-ref outputs "out"))
497 (bin (string-append out "/bin"))
498 (man (string-append out "/share/man/man1")))
499 (mkdir-p man)
500 (copy-file "awk.1" (string-append man "/bioawk.1"))
501 (install-file "bioawk" bin)))))))
502 (home-page "https://github.com/lh3/bioawk")
503 (synopsis "AWK with bioinformatics extensions")
504 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
505support of several common biological data formats, including optionally gzip'ed
506BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
507also adds a few built-in functions and a command line option to use TAB as the
508input/output delimiter. When the new functionality is not used, bioawk is
509intended to behave exactly the same as the original BWK awk.")
510 (license license:x11)))
511
a2fb1492
RW		 512(define-public python2-pybedtools
513 (package
514 (name "python2-pybedtools")
515 (version "0.6.9")
516 (source (origin
517 (method url-fetch)
518 (uri (string-append
519 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
520 version ".tar.gz"))
521 (sha256
522 (base32
523 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
524 (build-system python-build-system)
525 (arguments `(#:python ,python-2)) ; no Python 3 support
526 (inputs
f2516de2 527 `(("python-matplotlib" ,python2-matplotlib)))
a2fb1492
RW		 528 (propagated-inputs
529 `(("bedtools" ,bedtools)
530 ("samtools" ,samtools)))
531 (native-inputs
f2516de2
HG		 532 `(("python-cython" ,python2-cython)
533 ("python-pyyaml" ,python2-pyyaml)
f3b98f4f 534 ("python-nose" ,python2-nose)))
a2fb1492
RW		 535 (home-page "https://pythonhosted.org/pybedtools/")
536 (synopsis "Python wrapper for BEDtools programs")
537 (description
538 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
539which are widely used for genomic interval manipulation or \"genome algebra\".
540pybedtools extends BEDTools by offering feature-level manipulations from with
541Python.")
542 (license license:gpl2+)))
543
9e12eba8
BW		 544(define-public python-biom-format
545 (package
546 (name "python-biom-format")
547 (version "2.1.5")
548 (source
549 (origin
550 (method url-fetch)
551 ;; Use GitHub as source because PyPI distribution does not contain
552 ;; test data: https://github.com/biocore/biom-format/issues/693
553 (uri (string-append "https://github.com/biocore/biom-format/archive/"
554 version ".tar.gz"))
555 (file-name (string-append name "-" version ".tar.gz"))
556 (sha256
557 (base32
558 "1n25w3p1rixbpac8iysmzcja6m4ip5r6sz19l8y6wlwi49hxn278"))))
559 (build-system python-build-system)
de96ea28 560 (propagated-inputs
9e12eba8
BW		 561 `(("python-numpy" ,python-numpy)
562 ("python-scipy" ,python-scipy)
563 ("python-future" ,python-future)
564 ("python-click" ,python-click)
565 ("python-h5py" ,python-h5py)))
566 (home-page "http://www.biom-format.org")
567 (synopsis "Biological Observation Matrix (BIOM) format utilities")
568 (description
569 "The BIOM file format is designed to be a general-use format for
570representing counts of observations e.g. operational taxonomic units, KEGG
571orthology groups or lipid types, in one or more biological samples
572e.g. microbiome samples, genomes, metagenomes.")
573 (license license:bsd-3)
574 (properties `((python2-variant . ,(delay python2-biom-format))))))
575
576(define-public python2-biom-format
577 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
578 (package
579 (inherit base)
580 (arguments
581 `(#:phases
582 (modify-phases %standard-phases
583 ;; Do not require the unmaintained pyqi library.
584 (add-after 'unpack 'remove-pyqi
585 (lambda _
586 (substitute* "setup.py"
587 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
588 #t)))
00e10c6e 589 ,@(package-arguments base))))))
9e12eba8 590
f7283db3
RW		 591(define-public bioperl-minimal
592 (let* ((inputs `(("perl-module-build" ,perl-module-build)
593 ("perl-data-stag" ,perl-data-stag)
594 ("perl-libwww" ,perl-libwww)
595 ("perl-uri" ,perl-uri)))
596 (transitive-inputs
597 (map (compose package-name cadr)
598 (delete-duplicates
599 (concatenate
600 (map (compose package-transitive-target-inputs cadr) inputs))))))
601 (package
602 (name "bioperl-minimal")
c70271ec 603 (version "1.7.0")
f7283db3
RW		 604 (source
605 (origin
606 (method url-fetch)
c70271ec
RW		 607 (uri (string-append "https://github.com/bioperl/bioperl-live/"
608 "archive/release-"
609 (string-map (lambda (c)
610 (if (char=? c #\.)
611 #\- c)) version)
612 ".tar.gz"))
f7283db3
RW		 613 (sha256
614 (base32
c70271ec 615 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
f7283db3
RW		 616 (build-system perl-build-system)
617 (arguments
618 `(#:phases
619 (modify-phases %standard-phases
620 (add-after
621 'install 'wrap-programs
622 (lambda* (#:key outputs #:allow-other-keys)
623 ;; Make sure all executables in "bin" find the required Perl
624 ;; modules at runtime. As the PERL5LIB variable contains also
625 ;; the paths of native inputs, we pick the transitive target
626 ;; inputs from %build-inputs.
627 (let* ((out (assoc-ref outputs "out"))
628 (bin (string-append out "/bin/"))
629 (path (string-join
630 (cons (string-append out "/lib/perl5/site_perl")
631 (map (lambda (name)
632 (assoc-ref %build-inputs name))
633 ',transitive-inputs))
634 ":")))
635 (for-each (lambda (file)
636 (wrap-program file
637 `("PERL5LIB" ":" prefix (,path))))
638 (find-files bin "\\.pl$"))
639 #t))))))
640 (inputs inputs)
641 (native-inputs
642 `(("perl-test-most" ,perl-test-most)))
643 (home-page "http://search.cpan.org/dist/BioPerl")
644 (synopsis "Bioinformatics toolkit")
645 (description
646 "BioPerl is the product of a community effort to produce Perl code which
647is useful in biology. Examples include Sequence objects, Alignment objects
648and database searching objects. These objects not only do what they are
649advertised to do in the documentation, but they also interact - Alignment
650objects are made from the Sequence objects, Sequence objects have access to
651Annotation and SeqFeature objects and databases, Blast objects can be
652converted to Alignment objects, and so on. This means that the objects
653provide a coordinated and extensible framework to do computational biology.")
654 (license (package-license perl)))))
655
85c37e29
RW		 656(define-public python-biopython
657 (package
658 (name "python-biopython")
4ce60305 659 (version "1.68")
85c37e29
RW		 660 (source (origin
661 (method url-fetch)
e815c094
BW		 662 ;; use PyPi rather than biopython.org to ease updating
663 (uri (pypi-uri "biopython" version))
85c37e29
RW		 664 (sha256
665 (base32
4ce60305 666 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
85c37e29 667 (build-system python-build-system)
4ce60305
BW		 668 (arguments
669 `(#:phases
670 (modify-phases %standard-phases
671 (add-before 'check 'set-home
672 ;; Some tests require a home directory to be set.
673 (lambda _ (setenv "HOME" "/tmp") #t)))))
f22efa01 674 (propagated-inputs
85c37e29 675 `(("python-numpy" ,python-numpy)))
85c37e29
RW		 676 (home-page "http://biopython.org/")
677 (synopsis "Tools for biological computation in Python")
678 (description
679 "Biopython is a set of tools for biological computation including parsers
680for bioinformatics files into Python data structures; interfaces to common
681bioinformatics programs; a standard sequence class and tools for performing
682common operations on them; code to perform data classification; code for
683dealing with alignments; code making it easy to split up parallelizable tasks
684into separate processes; and more.")
5c31f4aa 685 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
85c37e29
RW		 686
687(define-public python2-biopython
5c31f4aa 688 (package-with-python2 python-biopython))
85c37e29 689
4b1a1528
BW		 690;; An outdated version of biopython is required for seqmagick, see
691;; https://github.com/fhcrc/seqmagick/issues/59
692;; When that issue has been resolved this package should be removed.
693(define python2-biopython-1.66
694 (package
695 (inherit python2-biopython)
696 (version "1.66")
697 (source (origin
698 (method url-fetch)
699 (uri (pypi-uri "biopython" version))
700 (sha256
701 (base32
702 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
703
985d8411
BW		 704(define-public bpp-core
705 ;; The last release was in 2014 and the recommended way to install from source
706 ;; is to clone the git repository, so we do this.
707 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
708 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
709 (package
710 (name "bpp-core")
711 (version (string-append "2.2.0-1." (string-take commit 7)))
712 (source (origin
713 (method git-fetch)
714 (uri (git-reference
715 (url "http://biopp.univ-montp2.fr/git/bpp-core")
716 (commit commit)))
717 (file-name (string-append name "-" version "-checkout"))
718 (sha256
719 (base32
720 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
721 (build-system cmake-build-system)
722 (arguments
723 `(#:parallel-build? #f))
724 (inputs
725 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
726 ; compile all of the bpp packages with GCC 5.
727 (home-page "http://biopp.univ-montp2.fr")
728 (synopsis "C++ libraries for Bioinformatics")
729 (description
730 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
731analysis, phylogenetics, molecular evolution and population genetics. It is
732Object Oriented and is designed to be both easy to use and computer efficient.
733Bio++ intends to help programmers to write computer expensive programs, by
734providing them a set of re-usable tools.")
735 (license license:cecill-c))))
736
8b5f4d57
BW		 737(define-public bpp-phyl
738 ;; The last release was in 2014 and the recommended way to install from source
739 ;; is to clone the git repository, so we do this.
740 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
741 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
742 (package
743 (name "bpp-phyl")
744 (version (string-append "2.2.0-1." (string-take commit 7)))
745 (source (origin
746 (method git-fetch)
747 (uri (git-reference
748 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
749 (commit commit)))
750 (file-name (string-append name "-" version "-checkout"))
751 (sha256
752 (base32
753 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
754 (build-system cmake-build-system)
755 (arguments
756 `(#:parallel-build? #f
757 ;; If out-of-source, test data is not copied into the build directory
758 ;; so the tests fail.
759 #:out-of-source? #f))
760 (inputs
761 `(("bpp-core" ,bpp-core)
762 ("bpp-seq" ,bpp-seq)
763 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
764 ;; modern GCC.
765 ("gcc" ,gcc-5)))
766 (home-page "http://biopp.univ-montp2.fr")
767 (synopsis "Bio++ phylogenetic Library")
768 (description
769 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
770analysis, phylogenetics, molecular evolution and population genetics. This
771library provides phylogenetics-related modules.")
772 (license license:cecill-c))))
773
159a7016
BW		 774(define-public bpp-popgen
775 ;; The last release was in 2014 and the recommended way to install from source
776 ;; is to clone the git repository, so we do this.
777 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
778 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
779 (package
780 (name "bpp-popgen")
781 (version (string-append "2.2.0-1." (string-take commit 7)))
782 (source (origin
783 (method git-fetch)
784 (uri (git-reference
785 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
786 (commit commit)))
787 (file-name (string-append name "-" version "-checkout"))
788 (sha256
789 (base32
790 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
791 (build-system cmake-build-system)
792 (arguments
793 `(#:parallel-build? #f
794 #:tests? #f)) ; There are no tests.
795 (inputs
796 `(("bpp-core" ,bpp-core)
797 ("bpp-seq" ,bpp-seq)
798 ("gcc" ,gcc-5)))
799 (home-page "http://biopp.univ-montp2.fr")
800 (synopsis "Bio++ population genetics library")
801 (description
802 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
803analysis, phylogenetics, molecular evolution and population genetics. This
804library provides population genetics-related modules.")
805 (license license:cecill-c))))
806
70f1bc05
BW		 807(define-public bpp-seq
808 ;; The last release was in 2014 and the recommended way to install from source
809 ;; is to clone the git repository, so we do this.
810 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
811 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
812 (package
813 (name "bpp-seq")
814 (version (string-append "2.2.0-1." (string-take commit 7)))
815 (source (origin
816 (method git-fetch)
817 (uri (git-reference
818 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
819 (commit commit)))
820 (file-name (string-append name "-" version "-checkout"))
821 (sha256
822 (base32
823 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
824 (build-system cmake-build-system)
825 (arguments
826 `(#:parallel-build? #f
827 ;; If out-of-source, test data is not copied into the build directory
828 ;; so the tests fail.
829 #:out-of-source? #f))
830 (inputs
831 `(("bpp-core" ,bpp-core)
832 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
833 (home-page "http://biopp.univ-montp2.fr")
834 (synopsis "Bio++ sequence library")
835 (description
836 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
837analysis, phylogenetics, molecular evolution and population genetics. This
838library provides sequence-related modules.")
839 (license license:cecill-c))))
840
db7a3444
BW		 841(define-public bppsuite
842 ;; The last release was in 2014 and the recommended way to install from source
843 ;; is to clone the git repository, so we do this.
844 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
845 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
846 (package
847 (name "bppsuite")
848 (version (string-append "2.2.0-1." (string-take commit 7)))
849 (source (origin
850 (method git-fetch)
851 (uri (git-reference
852 (url "http://biopp.univ-montp2.fr/git/bppsuite")
853 (commit commit)))
854 (file-name (string-append name "-" version "-checkout"))
855 (sha256
856 (base32
857 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
858 (build-system cmake-build-system)
859 (arguments
860 `(#:parallel-build? #f
861 #:tests? #f)) ; There are no tests.
862 (native-inputs
863 `(("groff" ,groff)
864 ("man-db" ,man-db)
865 ("texinfo" ,texinfo)))
866 (inputs
867 `(("bpp-core" ,bpp-core)
868 ("bpp-seq" ,bpp-seq)
869 ("bpp-phyl" ,bpp-phyl)
870 ("bpp-phyl" ,bpp-popgen)
871 ("gcc" ,gcc-5)))
872 (home-page "http://biopp.univ-montp2.fr")
873 (synopsis "Bioinformatics tools written with the Bio++ libraries")
874 (description
875 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
876analysis, phylogenetics, molecular evolution and population genetics. This
877package provides command line tools using the Bio++ library.")
878 (license license:cecill-c))))
879
82c370de
RW		 880(define-public blast+
881 (package
882 (name "blast+")
8dec2229 883 (version "2.4.0")
82c370de
RW		 884 (source (origin
885 (method url-fetch)
886 (uri (string-append
887 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
888 version "/ncbi-blast-" version "+-src.tar.gz"))
889 (sha256
890 (base32
8dec2229 891 "14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
82c370de
RW		 892 (modules '((guix build utils)))
893 (snippet
894 '(begin
895 ;; Remove bundled bzip2 and zlib
896 (delete-file-recursively "c++/src/util/compress/bzip2")
897 (delete-file-recursively "c++/src/util/compress/zlib")
898 (substitute* "c++/src/util/compress/Makefile.in"
899 (("bzip2 zlib api") "api"))
900 ;; Remove useless msbuild directory
901 (delete-file-recursively
902 "c++/src/build-system/project_tree_builder/msbuild")
903 #t))))
904 (build-system gnu-build-system)
905 (arguments
906 `(;; There are three(!) tests for this massive library, and all fail with
907 ;; "unparsable timing stats".
908 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
909 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
910 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
911 #:tests? #f
912 #:out-of-source? #t
913 #:parallel-build? #f ; not supported
914 #:phases
915 (modify-phases %standard-phases
916 (add-before
917 'configure 'set-HOME
918 ;; $HOME needs to be set at some point during the configure phase
919 (lambda _ (setenv "HOME" "/tmp") #t))
920 (add-after
921 'unpack 'enter-dir
922 (lambda _ (chdir "c++") #t))
923 (add-after
924 'enter-dir 'fix-build-system
925 (lambda _
926 (define (which* cmd)
927 (cond ((string=? cmd "date")
928 ;; make call to "date" deterministic
929 "date -d @0")
930 ((which cmd)
931 => identity)
932 (else
933 (format (current-error-port)
934 "WARNING: Unable to find absolute path for ~s~%"
935 cmd)
936 #f)))
937
938 ;; Rewrite hardcoded paths to various tools
939 (substitute* (append '("src/build-system/configure.ac"
940 "src/build-system/configure"
941 "scripts/common/impl/if_diff.sh"
942 "scripts/common/impl/run_with_lock.sh"
943 "src/build-system/Makefile.configurables.real"
944 "src/build-system/Makefile.in.top"
945 "src/build-system/Makefile.meta.gmake=no"
946 "src/build-system/Makefile.meta.in"
947 "src/build-system/Makefile.meta_l"
948 "src/build-system/Makefile.meta_p"
949 "src/build-system/Makefile.meta_r"
950 "src/build-system/Makefile.mk.in"
951 "src/build-system/Makefile.requirements"
952 "src/build-system/Makefile.rules_with_autodep.in")
953 (find-files "scripts/common/check" "\\.sh$"))
954 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
955 (or (which* cmd) all)))
956
957 (substitute* (find-files "src/build-system" "^config.*")
958 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
959 (("^PATH=.*") ""))
960
961 ;; rewrite "/var/tmp" in check script
962 (substitute* "scripts/common/check/check_make_unix.sh"
963 (("/var/tmp") "/tmp"))
964
965 ;; do not reset PATH
966 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
967 (("^ *PATH=.*") "")
968 (("action=/bin/") "action=")
969 (("export PATH") ":"))
970 #t))
971 (replace
972 'configure
973 (lambda* (#:key inputs outputs #:allow-other-keys)
974 (let ((out (assoc-ref outputs "out"))
975 (lib (string-append (assoc-ref outputs "lib") "/lib"))
976 (include (string-append (assoc-ref outputs "include")
977 "/include/ncbi-tools++")))
978 ;; The 'configure' script doesn't recognize things like
979 ;; '--enable-fast-install'.
980 (zero? (system* "./configure.orig"
981 (string-append "--with-build-root=" (getcwd) "/build")
982 (string-append "--prefix=" out)
983 (string-append "--libdir=" lib)
984 (string-append "--includedir=" include)
985 (string-append "--with-bz2="
986 (assoc-ref inputs "bzip2"))
987 (string-append "--with-z="
988 (assoc-ref inputs "zlib"))
989 ;; Each library is built twice by default, once
990 ;; with "-static" in its name, and again
991 ;; without.
992 "--without-static"
993 "--with-dll"))))))))
994 (outputs '("out" ; 19 MB
995 "lib" ; 203 MB
996 "include")) ; 32 MB
997 (inputs
998 `(("bzip2" ,bzip2)
999 ("zlib" ,zlib)))
1000 (native-inputs
1001 `(("cpio" ,cpio)))
1002 (home-page "http://blast.ncbi.nlm.nih.gov")
1003 (synopsis "Basic local alignment search tool")
1004 (description
1005 "BLAST is a popular method of performing a DNA or protein sequence
1006similarity search, using heuristics to produce results quickly. It also
1007calculates an “expect value” that estimates how many matches would have
1008occurred at a given score by chance, which can aid a user in judging how much
1009confidence to have in an alignment.")
1010 ;; Most of the sources are in the public domain, with the following
1011 ;; exceptions:
1012 ;; * Expat:
1013 ;; * ./c++/include/util/bitset/
1014 ;; * ./c++/src/html/ncbi_menu*.js
1015 ;; * Boost license:
1016 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1017 ;; * LGPL 2+:
1018 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1019 ;; * ASL 2.0:
1020 ;; * ./c++/src/corelib/teamcity_*
1021 (license (list license:public-domain
1022 license:expat
1023 license:boost1.0
1024 license:lgpl2.0+
1025 license:asl2.0))))
1026
6c2b26e2
RW		 1027(define-public bless
1028 (package
1029 (name "bless")
1030 (version "1p02")
1031 (source (origin
1032 (method url-fetch)
1033 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1034 version ".tgz"))
1035 (sha256
1036 (base32
4d75e03a
RW		 1037 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1038 (modules '((guix build utils)))
6c2b26e2
RW		 1039 (snippet
1040 `(begin
1041 ;; Remove bundled boost, pigz, zlib, and .git directory
953c1223
RW		 1042 ;; FIXME: also remove bundled sources for murmurhash3 and
1043 ;; kmc once packaged.
6c2b26e2
RW		 1044 (delete-file-recursively "boost")
1045 (delete-file-recursively "pigz")
953c1223 1046 (delete-file-recursively "google-sparsehash")
6c2b26e2
RW		 1047 (delete-file-recursively "zlib")
1048 (delete-file-recursively ".git")
1049 #t))))
1050 (build-system gnu-build-system)
1051 (arguments
1052 '(#:tests? #f ;no "check" target
1053 #:make-flags
1054 (list (string-append "ZLIB="
1055 (assoc-ref %build-inputs "zlib")
1056 "/lib/libz.a")
1057 (string-append "LDFLAGS="
1058 (string-join '("-lboost_filesystem"
1059 "-lboost_system"
1060 "-lboost_iostreams"
1061 "-lz"
1062 "-fopenmp"
1063 "-std=c++11"))))
1064 #:phases
1065 (modify-phases %standard-phases
1066 (add-after 'unpack 'do-not-build-bundled-pigz
1067 (lambda* (#:key inputs outputs #:allow-other-keys)
1068 (substitute* "Makefile"
1069 (("cd pigz/pigz-2.3.3; make") ""))
1070 #t))
1071 (add-after 'unpack 'patch-paths-to-executables
1072 (lambda* (#:key inputs outputs #:allow-other-keys)
1073 (substitute* "parse_args.cpp"
1074 (("kmc_binary = .*")
1075 (string-append "kmc_binary = \""
1076 (assoc-ref outputs "out")
1077 "/bin/kmc\";"))
1078 (("pigz_binary = .*")
1079 (string-append "pigz_binary = \""
1080 (assoc-ref inputs "pigz")
1081 "/bin/pigz\";")))
1082 #t))
1083 (replace 'install
1084 (lambda* (#:key outputs #:allow-other-keys)
1085 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1086 (for-each (lambda (file)
1087 (install-file file bin))
1088 '("bless" "kmc/bin/kmc"))
1089 #t)))
1090 (delete 'configure))))
1091 (native-inputs
1092 `(("perl" ,perl)))
1093 (inputs
1094 `(("openmpi" ,openmpi)
1095 ("boost" ,boost)
953c1223 1096 ("sparsehash" ,sparsehash)
6c2b26e2
RW		 1097 ("pigz" ,pigz)
1098 ("zlib" ,zlib)))
9641a899 1099 (supported-systems '("x86_64-linux"))
4d75e03a 1100 (home-page "http://sourceforge.net/p/bless-ec/wiki/Home/")
6c2b26e2
RW		 1101 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1102 (description
1103 "@dfn{Bloom-filter-based error correction solution for high-throughput
1104sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1105correction tool for genomic reads produced by @dfn{Next-generation
1106sequencing} (NGS). BLESS produces accurate correction results with much less
1107memory compared with previous solutions and is also able to tolerate a higher
1108false-positive rate. BLESS can extend reads like DNA assemblers to correct
1109errors at the end of reads.")
1110 (license license:gpl3+)))
1111
2c7ee167
RW		 1112(define-public bowtie
1113 (package
1114 (name "bowtie")
2642231b 1115 (version "2.2.9")
2c7ee167
RW		 1116 (source (origin
1117 (method url-fetch)
1118 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1119 version ".tar.gz"))
f586c877 1120 (file-name (string-append name "-" version ".tar.gz"))
2c7ee167
RW		 1121 (sha256
1122 (base32
2642231b 1123 "1vp5db8i7is57iwjybcdg18f5ivyzlj5g1ix1nlvxainzivhz55g"))
2c7ee167
RW		 1124 (modules '((guix build utils)))
1125 (snippet
1126 '(substitute* "Makefile"
2c7ee167
RW		 1127 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1128 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
0047d26a 1129 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
2c7ee167
RW		 1130 (build-system gnu-build-system)
1131 (inputs `(("perl" ,perl)
1132 ("perl-clone" ,perl-clone)
1133 ("perl-test-deep" ,perl-test-deep)
1134 ("perl-test-simple" ,perl-test-simple)
0047d26a
RW		 1135 ("python" ,python-2)
1136 ("tbb" ,tbb)))
2c7ee167 1137 (arguments
0047d26a
RW		 1138 '(#:make-flags
1139 (list "allall"
1140 "WITH_TBB=1"
1141 (string-append "prefix=" (assoc-ref %outputs "out")))
2c7ee167
RW		 1142 #:phases
1143 (alist-delete
1144 'configure
1145 (alist-replace
0047d26a 1146 'check
2c7ee167 1147 (lambda* (#:key outputs #:allow-other-keys)
0047d26a
RW		 1148 (system* "perl"
1149 "scripts/test/simple_tests.pl"
1150 "--bowtie2=./bowtie2"
1151 "--bowtie2-build=./bowtie2-build"))
1152 %standard-phases))))
2c7ee167
RW		 1153 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1154 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1155 (description
1156 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1157reads to long reference sequences. It is particularly good at aligning reads
1158of about 50 up to 100s or 1,000s of characters, and particularly good at
1159aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1160genome with an FM Index to keep its memory footprint small: for the human
1161genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1162gapped, local, and paired-end alignment modes.")
241e1221 1163 (supported-systems '("x86_64-linux"))
2c7ee167
RW		 1164 (license license:gpl3+)))
1165
94ce537e
RW		 1166(define-public tophat
1167 (package
1168 (name "tophat")
1169 (version "2.1.0")
1170 (source (origin
1171 (method url-fetch)
1172 (uri (string-append
1173 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1174 version ".tar.gz"))
1175 (sha256
1176 (base32
1177 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
fc1adab1 1178 (patches (search-patches "tophat-build-with-later-seqan.patch"))
94ce537e
RW		 1179 (modules '((guix build utils)))
1180 (snippet
1181 '(begin
1182 ;; Remove bundled SeqAn and samtools
1183 (delete-file-recursively "src/SeqAn-1.3")
1184 (delete-file-recursively "src/samtools-0.1.18")
1185 #t))))
1186 (build-system gnu-build-system)
1187 (arguments
1188 '(#:parallel-build? #f ; not supported
1189 #:phases
1190 (modify-phases %standard-phases
1191 (add-after 'unpack 'use-system-samtools
1192 (lambda* (#:key inputs #:allow-other-keys)
1193 (substitute* "src/Makefile.in"
1194 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1195 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1196 (("SAMPROG = samtools_0\\.1\\.18") "")
1197 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1198 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1199 (substitute* '("src/common.cpp"
1200 "src/tophat.py")
1201 (("samtools_0.1.18") (which "samtools")))
1202 (substitute* '("src/common.h"
1203 "src/bam2fastx.cpp")
1204 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1205 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1206 (substitute* '("src/bwt_map.h"
1207 "src/map2gtf.h"
1208 "src/align_status.h")
1209 (("#include <bam.h>") "#include <samtools/bam.h>")
1210 (("#include <sam.h>") "#include <samtools/sam.h>"))
1211 #t)))))
1212 (inputs
1213 `(("boost" ,boost)
1214 ("bowtie" ,bowtie)
1215 ("samtools" ,samtools-0.1)
1216 ("ncurses" ,ncurses)
1217 ("python" ,python-2)
1218 ("perl" ,perl)
1219 ("zlib" ,zlib)
1220 ("seqan" ,seqan)))
1221 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1222 (synopsis "Spliced read mapper for RNA-Seq data")
1223 (description
1224 "TopHat is a fast splice junction mapper for nucleotide sequence
1225reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1226mammalian-sized genomes using the ultra high-throughput short read
1227aligner Bowtie, and then analyzes the mapping results to identify
1228splice junctions between exons.")
1229 ;; TopHat is released under the Boost Software License, Version 1.0
1230 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1231 (license license:boost1.0)))
1232
9a8336d8
RW		 1233(define-public bwa
1234 (package
1235 (name "bwa")
1236 (version "0.7.12")
1237 (source (origin
1238 (method url-fetch)
1239 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1240 version ".tar.bz2"))
1241 (sha256
1242 (base32
1243 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
1244 (build-system gnu-build-system)
1245 (arguments
1246 '(#:tests? #f ;no "check" target
1247 #:phases
1248 (alist-replace
1249 'install
1250 (lambda* (#:key outputs #:allow-other-keys)
1251 (let ((bin (string-append
1252 (assoc-ref outputs "out") "/bin"))
1253 (doc (string-append
1254 (assoc-ref outputs "out") "/share/doc/bwa"))
1255 (man (string-append
1256 (assoc-ref outputs "out") "/share/man/man1")))
96c46210
LC		 1257 (install-file "bwa" bin)
1258 (install-file "README.md" doc)
1259 (install-file "bwa.1" man)))
9a8336d8
RW		 1260 ;; no "configure" script
1261 (alist-delete 'configure %standard-phases))))
1262 (inputs `(("zlib" ,zlib)))
db94f8c7
RW		 1263 ;; Non-portable SSE instructions are used so building fails on platforms
1264 ;; other than x86_64.
1265 (supported-systems '("x86_64-linux"))
9a8336d8
RW		 1266 (home-page "http://bio-bwa.sourceforge.net/")
1267 (synopsis "Burrows-Wheeler sequence aligner")
1268 (description
1269 "BWA is a software package for mapping low-divergent sequences against a
1270large reference genome, such as the human genome. It consists of three
1271algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1272designed for Illumina sequence reads up to 100bp, while the rest two for
1273longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1274features such as long-read support and split alignment, but BWA-MEM, which is
1275the latest, is generally recommended for high-quality queries as it is faster
1276and more accurate. BWA-MEM also has better performance than BWA-backtrack for
127770-100bp Illumina reads.")
1278 (license license:gpl3+)))
1279
d29150b5
RW		 1280(define-public bwa-pssm
1281 (package (inherit bwa)
1282 (name "bwa-pssm")
1283 (version "0.5.11")
1284 (source (origin
1285 (method url-fetch)
1286 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1287 "archive/" version ".tar.gz"))
1288 (file-name (string-append name "-" version ".tar.gz"))
1289 (sha256
1290 (base32
1291 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1292 (build-system gnu-build-system)
1293 (inputs
1294 `(("gdsl" ,gdsl)
1295 ("zlib" ,zlib)
1296 ("perl" ,perl)))
1297 (home-page "http://bwa-pssm.binf.ku.dk/")
1298 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1299 (description
1300 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1301the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1302existing aligners it is fast and sensitive. Unlike most other aligners,
1303however, it is also adaptible in the sense that one can direct the alignment
1304based on known biases within the data set. It is coded as a modification of
1305the original BWA alignment program and shares the genome index structure as
1306well as many of the command line options.")
1307 (license license:gpl3+)))
1308
ad641d53
RW		 1309(define-public python2-bx-python
1310 (package
1311 (name "python2-bx-python")
1312 (version "0.7.2")
1313 (source (origin
1314 (method url-fetch)
1315 (uri (string-append
1316 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
1317 version ".tar.gz"))
1318 (sha256
1319 (base32
1320 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
1321 (modules '((guix build utils)))
1322 (snippet
1323 '(substitute* "setup.py"
1324 ;; remove dependency on outdated "distribute" module
1325 (("^from distribute_setup import use_setuptools") "")
1326 (("^use_setuptools\\(\\)") "")))))
1327 (build-system python-build-system)
1328 (arguments
1329 `(#:tests? #f ;tests fail because test data are not included
1330 #:python ,python-2))
1331 (inputs
1332 `(("python-numpy" ,python2-numpy)
1333 ("zlib" ,zlib)))
1334 (native-inputs
f3b98f4f 1335 `(("python-nose" ,python2-nose)))
ad641d53
RW		 1336 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1337 (synopsis "Tools for manipulating biological data")
1338 (description
1339 "bx-python provides tools for manipulating biological data, particularly
1340multiple sequence alignments.")
1341 (license license:expat)))
1342
55a9a8c2
RW		 1343(define-public python-pysam
1344 (package
1345 (name "python-pysam")
fd49eb21 1346 (version "0.9.1.4")
d454640c
RW		 1347 (source (origin
1348 (method url-fetch)
f536dce5
MB		 1349 ;; Test data is missing on PyPi.
1350 (uri (string-append
1351 "https://github.com/pysam-developers/pysam/archive/v"
1352 version ".tar.gz"))
1353 (file-name (string-append name "-" version ".tar.gz"))
d454640c
RW		 1354 (sha256
1355 (base32
f536dce5 1356 "0y41ssbg6nvn2jgcbnrvkzblpjcwszaiv1rgyd8dwzjkrbfsgsmc"))
dff26b23
MB		 1357 (modules '((guix build utils)))
1358 (snippet
1359 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1360 '(delete-file-recursively "htslib"))))
55a9a8c2
RW		 1361 (build-system python-build-system)
1362 (arguments
f536dce5 1363 `(#:phases
397d463a
MB		 1364 (modify-phases %standard-phases
1365 (add-before 'build 'set-flags
dff26b23
MB		 1366 (lambda* (#:key inputs #:allow-other-keys)
1367 (setenv "HTSLIB_MODE" "external")
1368 (setenv "HTSLIB_LIBRARY_DIR"
1369 (string-append (assoc-ref inputs "htslib") "/lib"))
1370 (setenv "HTSLIB_INCLUDE_DIR"
1371 (string-append (assoc-ref inputs "htslib") "/include"))
397d463a
MB		 1372 (setenv "LDFLAGS" "-lncurses")
1373 (setenv "CFLAGS" "-D_CURSES_LIB=1")
f536dce5
MB		 1374 #t))
1375 (delete 'check)
1376 (add-after 'install 'check
1377 (lambda* (#:key inputs outputs #:allow-other-keys)
1378 (setenv "PYTHONPATH"
1379 (string-append
1380 (getenv "PYTHONPATH")
1381 ":" (assoc-ref outputs "out")
1382 "/lib/python"
1383 (string-take (string-take-right
1384 (assoc-ref inputs "python") 5) 3)
1385 "/site-packages"))
1386 ;; Step out of source dir so python does not import from CWD.
1387 (chdir "tests")
1388 (setenv "HOME" "/tmp")
1389 (and (zero? (system* "make" "-C" "pysam_data"))
1390 (zero? (system* "make" "-C" "cbcf_data"))
1391 (zero? (system* "nosetests" "-v"))))))))
dff26b23
MB		 1392 (propagated-inputs
1393 `(("htslib" ,htslib))) ; Included from installed header files.
55a9a8c2 1394 (inputs
649e9b3b 1395 `(("ncurses" ,ncurses)
55a9a8c2 1396 ("zlib" ,zlib)))
649e9b3b
RW		 1397 (native-inputs
1398 `(("python-cython" ,python-cython)
f536dce5
MB		 1399 ;; Dependencies below are are for tests only.
1400 ("samtools" ,samtools)
1401 ("bcftools" ,bcftools)
1402 ("python-nose" ,python-nose)))
55a9a8c2
RW		 1403 (home-page "https://github.com/pysam-developers/pysam")
1404 (synopsis "Python bindings to the SAMtools C API")
1405 (description
1406 "Pysam is a Python module for reading and manipulating files in the
1407SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1408also includes an interface for tabix.")
1409 (license license:expat)))
1410
1411(define-public python2-pysam
1412 (package-with-python2 python-pysam))
1413
4db9433a
RW		 1414(define-public python-twobitreader
1415 (package
1416 (name "python-twobitreader")
044ac8d2 1417 (version "3.1.4")
4db9433a
RW		 1418 (source (origin
1419 (method url-fetch)
1420 (uri (pypi-uri "twobitreader" version))
1421 (sha256
1422 (base32
044ac8d2 1423 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
4db9433a 1424 (build-system python-build-system)
900fb8d0
LF		 1425 (arguments
1426 '(;; Tests are not distributed in the PyPi release.
1427 ;; TODO Try building from the Git repo or asking the upstream maintainer
1428 ;; to distribute the tests on PyPi.
1429 #:tests? #f))
4db9433a
RW		 1430 (native-inputs
1431 `(("python-sphinx" ,python-sphinx)))
1432 (home-page "https://github.com/benjschiller/twobitreader")
1433 (synopsis "Python library for reading .2bit files")
1434 (description
1435 "twobitreader is a Python library for reading .2bit files as used by the
1436UCSC genome browser.")
1437 (license license:artistic2.0)))
1438
1439(define-public python2-twobitreader
5c31f4aa 1440 (package-with-python2 python-twobitreader))
4db9433a 1441
f94bf198
RW		 1442(define-public python-plastid
1443 (package
1444 (name "python-plastid")
99caa6f7 1445 (version "0.4.6")
f94bf198
RW		 1446 (source (origin
1447 (method url-fetch)
1448 (uri (pypi-uri "plastid" version))
1449 (sha256
1450 (base32
99caa6f7 1451 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
f94bf198
RW		 1452 (build-system python-build-system)
1453 (arguments
1454 ;; Some test files are not included.
1455 `(#:tests? #f))
1456 (propagated-inputs
1457 `(("python-numpy" ,python-numpy)
1458 ("python-scipy" ,python-scipy)
1459 ("python-pandas" ,python-pandas)
1460 ("python-pysam" ,python-pysam)
1461 ("python-matplotlib" ,python-matplotlib)
1462 ("python-biopython" ,python-biopython)
99caa6f7
BW		 1463 ("python-twobitreader" ,python-twobitreader)
1464 ("python-termcolor" ,python-termcolor)))
f94bf198
RW		 1465 (native-inputs
1466 `(("python-cython" ,python-cython)
1467 ("python-nose" ,python-nose)))
1468 (home-page "https://github.com/joshuagryphon/plastid")
1469 (synopsis "Python library for genomic analysis")
1470 (description
1471 "plastid is a Python library for genomic analysis – in particular,
1472high-throughput sequencing data – with an emphasis on simplicity.")
1473 (license license:bsd-3)))
1474
1475(define-public python2-plastid
5c31f4aa 1476 (package-with-python2 python-plastid))
f94bf198 1477
6c1305f9
RW		 1478(define-public cd-hit
1479 (package
1480 (name "cd-hit")
1481 (version "4.6.5")
1482 (source (origin
1483 (method url-fetch)
1484 (uri (string-append "https://github.com/weizhongli/cdhit"
1485 "/releases/download/V" version
1486 "/cd-hit-v" version "-2016-0304.tar.gz"))
1487 (sha256
1488 (base32
1489 "15db0hq38yyifwqx9b6l34z14jcq576dmjavhj8a426c18lvnhp3"))))
1490 (build-system gnu-build-system)
1491 (arguments
1492 `(#:tests? #f ; there are no tests
1493 #:make-flags
1494 ;; Executables are copied directly to the PREFIX.
1495 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1496 #:phases
1497 (modify-phases %standard-phases
1498 ;; No "configure" script
1499 (delete 'configure)
1500 ;; Remove sources of non-determinism
1501 (add-after 'unpack 'be-timeless
1502 (lambda _
1503 (substitute* "cdhit-utility.c++"
1504 ((" \\(built on \" __DATE__ \"\\)") ""))
1505 (substitute* "cdhit-common.c++"
1506 (("__DATE__") "\"0\"")
1507 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1508 #t))
1509 ;; The "install" target does not create the target directory
1510 (add-before 'install 'create-target-dir
1511 (lambda* (#:key outputs #:allow-other-keys)
1512 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1513 #t)))))
1514 (inputs
1515 `(("perl" ,perl)))
1516 (home-page "http://weizhongli-lab.org/cd-hit/")
1517 (synopsis "Cluster and compare protein or nucleotide sequences")
1518 (description
1519 "CD-HIT is a program for clustering and comparing protein or nucleotide
1520sequences. CD-HIT is designed to be fast and handle extremely large
1521databases.")
1522 ;; The manual says: "It can be copied under the GNU General Public License
1523 ;; version 2 (GPLv2)."
1524 (license license:gpl2)))
1525
810cff85
RW		 1526(define-public clipper
1527 (package
1528 (name "clipper")
433530a5 1529 (version "1.1")
810cff85
RW		 1530 (source (origin
1531 (method url-fetch)
1532 (uri (string-append
1533 "https://github.com/YeoLab/clipper/archive/"
1534 version ".tar.gz"))
9ab5ea44 1535 (file-name (string-append name "-" version ".tar.gz"))
810cff85
RW		 1536 (sha256
1537 (base32
433530a5 1538 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
810cff85
RW		 1539 (modules '((guix build utils)))
1540 (snippet
433530a5
RW		 1541 '(begin
1542 ;; remove unnecessary setup dependency
1543 (substitute* "setup.py"
1544 (("setup_requires = .*") ""))
1545 (for-each delete-file
1546 '("clipper/src/peaks.so"
1547 "clipper/src/readsToWiggle.so"))
1548 (delete-file-recursively "dist/")
1549 #t))))
810cff85
RW		 1550 (build-system python-build-system)
1551 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1552 (inputs
1553 `(("htseq" ,htseq)
1554 ("python-pybedtools" ,python2-pybedtools)
1555 ("python-cython" ,python2-cython)
1556 ("python-scikit-learn" ,python2-scikit-learn)
1557 ("python-matplotlib" ,python2-matplotlib)
433530a5 1558 ("python-pandas" ,python2-pandas)
810cff85
RW		 1559 ("python-pysam" ,python2-pysam)
1560 ("python-numpy" ,python2-numpy)
1561 ("python-scipy" ,python2-scipy)))
1562 (native-inputs
f3b98f4f
HG		 1563 `(("python-mock" ,python2-mock) ; for tests
1564 ("python-pytz" ,python2-pytz))) ; for tests
810cff85
RW		 1565 (home-page "https://github.com/YeoLab/clipper")
1566 (synopsis "CLIP peak enrichment recognition")
1567 (description
1568 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1569 (license license:gpl2)))
1570
6a35566d
RS		 1571(define-public codingquarry
1572 (package
1573 (name "codingquarry")
1574 (version "2.0")
1575 (source (origin
1576 (method url-fetch)
1577 (uri (string-append
1578 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1579 version ".tar.gz"))
1580 (sha256
1581 (base32
1582 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1583 (build-system gnu-build-system)
1584 (arguments
1585 '(#:tests? #f ; no "check" target
1586 #:phases
1587 (modify-phases %standard-phases
1588 (delete 'configure)
1589 (replace 'install
1590 (lambda* (#:key outputs #:allow-other-keys)
1591 (let* ((out (assoc-ref outputs "out"))
1592 (bin (string-append out "/bin"))
1593 (doc (string-append out "/share/doc/codingquarry")))
1594 (install-file "INSTRUCTIONS.pdf" doc)
1595 (copy-recursively "QuarryFiles"
1596 (string-append out "/QuarryFiles"))
1597 (install-file "CodingQuarry" bin)
1598 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1599 (inputs `(("openmpi" ,openmpi)))
1600 (native-search-paths
1601 (list (search-path-specification
1602 (variable "QUARRY_PATH")
1603 (files '("QuarryFiles")))))
1604 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1605 (synopsis "Fungal gene predictor")
1606 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1607gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1608 (home-page "https://sourceforge.net/projects/codingquarry/")
1609 (license license:gpl3+)))
1610
36742f43
RW		 1611(define-public couger
1612 (package
1613 (name "couger")
1614 (version "1.8.2")
1615 (source (origin
1616 (method url-fetch)
1617 (uri (string-append
1618 "http://couger.oit.duke.edu/static/assets/COUGER"
1619 version ".zip"))
1620 (sha256
1621 (base32
1622 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1623 (build-system gnu-build-system)
1624 (arguments
1625 `(#:tests? #f
1626 #:phases
1627 (modify-phases %standard-phases
1628 (delete 'configure)
1629 (delete 'build)
1630 (replace
1631 'install
1632 (lambda* (#:key outputs #:allow-other-keys)
1633 (let ((out (assoc-ref outputs "out")))
1634 (copy-recursively "src" (string-append out "/src"))
1635 (mkdir (string-append out "/bin"))
1636 ;; Add "src" directory to module lookup path.
1637 (substitute* "couger"
1638 (("from argparse")
1639 (string-append "import sys\nsys.path.append(\""
1640 out "\")\nfrom argparse")))
1641 (copy-file "couger" (string-append out "/bin/couger")))
1642 #t))
1643 (add-after
1644 'install 'wrap-program
1645 (lambda* (#:key inputs outputs #:allow-other-keys)
1646 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1647 (let* ((out (assoc-ref outputs "out"))
1648 (path (getenv "PYTHONPATH")))
1649 (wrap-program (string-append out "/bin/couger")
1650 `("PYTHONPATH" ":" prefix (,path))))
1651 #t)))))
1652 (inputs
1653 `(("python" ,python-2)
1654 ("python2-pillow" ,python2-pillow)
1655 ("python2-numpy" ,python2-numpy)
1656 ("python2-scipy" ,python2-scipy)
1657 ("python2-matplotlib" ,python2-matplotlib)))
1658 (propagated-inputs
1659 `(("r" ,r)
1660 ("libsvm" ,libsvm)
1661 ("randomjungle" ,randomjungle)))
1662 (native-inputs
1663 `(("unzip" ,unzip)))
1664 (home-page "http://couger.oit.duke.edu")
1665 (synopsis "Identify co-factors in sets of genomic regions")
1666 (description
1667 "COUGER can be applied to any two sets of genomic regions bound by
1668paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1669putative co-factors that provide specificity to each TF. The framework
1670determines the genomic targets uniquely-bound by each TF, and identifies a
1671small set of co-factors that best explain the in vivo binding differences
1672between the two TFs.
1673
1674COUGER uses classification algorithms (support vector machines and random
1675forests) with features that reflect the DNA binding specificities of putative
1676co-factors. The features are generated either from high-throughput TF-DNA
1677binding data (from protein binding microarray experiments), or from large
1678collections of DNA motifs.")
1679 (license license:gpl3+)))
1680
bfe3c685
RW		 1681(define-public clustal-omega
1682 (package
1683 (name "clustal-omega")
1684 (version "1.2.1")
1685 (source (origin
1686 (method url-fetch)
1687 (uri (string-append
1688 "http://www.clustal.org/omega/clustal-omega-"
1689 version ".tar.gz"))
1690 (sha256
1691 (base32
1692 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1693 (build-system gnu-build-system)
1694 (inputs
1695 `(("argtable" ,argtable)))
1696 (home-page "http://www.clustal.org/omega/")
1697 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1698 (description
1699 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1700program for protein and DNA/RNA. It produces high quality MSAs and is capable
1701of handling data-sets of hundreds of thousands of sequences in reasonable
1702time.")
1703 (license license:gpl2+)))
1704
191c7101
RW		 1705(define-public crossmap
1706 (package
1707 (name "crossmap")
61d5fd03 1708 (version "0.2.1")
191c7101
RW		 1709 (source (origin
1710 (method url-fetch)
1711 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1712 version ".tar.gz"))
1713 (sha256
1714 (base32
61d5fd03
RW		 1715 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1716 ;; This patch has been sent upstream already and is available
1717 ;; for download from Sourceforge, but it has not been merged.
fc1adab1 1718 (patches (search-patches "crossmap-allow-system-pysam.patch"))
191c7101
RW		 1719 (modules '((guix build utils)))
1720 ;; remove bundled copy of pysam
1721 (snippet
1722 '(delete-file-recursively "lib/pysam"))))
1723 (build-system python-build-system)
1724 (arguments
1725 `(#:python ,python-2
1726 #:phases
1727 (alist-cons-after
1728 'unpack 'set-env
1729 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1730 %standard-phases)))
1731 (inputs
1732 `(("python-numpy" ,python2-numpy)
1733 ("python-pysam" ,python2-pysam)
1734 ("zlib" ,zlib)))
1735 (native-inputs
1736 `(("python-cython" ,python2-cython)
f3b98f4f 1737 ("python-nose" ,python2-nose)))
191c7101
RW		 1738 (home-page "http://crossmap.sourceforge.net/")
1739 (synopsis "Convert genome coordinates between assemblies")
1740 (description
1741 "CrossMap is a program for conversion of genome coordinates or annotation
1742files between different genome assemblies. It supports most commonly used
1743file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1744 (license license:gpl2+)))
1745
3a40a92c
RW		 1746(define-public cufflinks
1747 (package
1748 (name "cufflinks")
1749 (version "2.2.1")
1750 (source (origin
1751 (method url-fetch)
1752 (uri (string-append "http://cole-trapnell-lab.github.io/"
1753 "cufflinks/assets/downloads/cufflinks-"
1754 version ".tar.gz"))
1755 (sha256
1756 (base32
1757 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1758 (build-system gnu-build-system)
1759 (arguments
1760 `(#:make-flags
1761 (list
1762 ;; The includes for "eigen" are located in a subdirectory.
1763 (string-append "EIGEN_CPPFLAGS="
1764 "-I" (assoc-ref %build-inputs "eigen")
1765 "/include/eigen3/")
1766 ;; Cufflinks must be linked with various boost libraries.
1767 (string-append "LDFLAGS="
1768 (string-join '("-lboost_system"
1769 "-lboost_serialization"
1770 "-lboost_thread"))))
1771 #:phases
1772 (modify-phases %standard-phases
1773 (add-after 'unpack 'fix-search-for-bam
1774 (lambda _
1775 (substitute* '("ax_bam.m4"
1776 "configure"
1777 "src/hits.h")
1778 (("<bam/sam\\.h>") "<samtools/sam.h>")
1779 (("<bam/bam\\.h>") "<samtools/bam.h>")
1780 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1781 #t)))
1782 #:configure-flags
1783 (list (string-append "--with-bam="
1784 (assoc-ref %build-inputs "samtools")))))
1785 (inputs
1786 `(("eigen" ,eigen)
1787 ("samtools" ,samtools-0.1)
1788 ("htslib" ,htslib)
1789 ("boost" ,boost)
1790 ("python" ,python-2)
1791 ("zlib" ,zlib)))
1792 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1793 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1794 (description
1795 "Cufflinks assembles RNA transcripts, estimates their abundances,
1796and tests for differential expression and regulation in RNA-Seq
1797samples. It accepts aligned RNA-Seq reads and assembles the
1798alignments into a parsimonious set of transcripts. Cufflinks then
1799estimates the relative abundances of these transcripts based on how
1800many reads support each one, taking into account biases in library
1801preparation protocols.")
1802 (license license:boost1.0)))
1803
8e913213
RW		 1804(define-public cutadapt
1805 (package
1806 (name "cutadapt")
1f94bff2 1807 (version "1.12")
8e913213
RW		 1808 (source (origin
1809 (method url-fetch)
1810 (uri (string-append
1811 "https://github.com/marcelm/cutadapt/archive/v"
1812 version ".tar.gz"))
1813 (file-name (string-append name "-" version ".tar.gz"))
1814 (sha256
1815 (base32
1f94bff2 1816 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
8e913213
RW		 1817 (build-system python-build-system)
1818 (arguments
33d5b246
TGR		 1819 `(#:phases
1820 (modify-phases %standard-phases
1821 ;; The tests must be run after installation.
1822 (delete 'check)
1823 (add-after 'install 'check
1824 (lambda* (#:key inputs outputs #:allow-other-keys)
1825 (setenv "PYTHONPATH"
1826 (string-append
1827 (getenv "PYTHONPATH")
1828 ":" (assoc-ref outputs "out")
1829 "/lib/python"
1830 (string-take (string-take-right
1831 (assoc-ref inputs "python") 5) 3)
1832 "/site-packages"))
1833 (zero? (system* "nosetests" "-P" "tests")))))))
1f94bff2
TGR		 1834 (inputs
1835 `(("python-xopen" ,python-xopen)))
8e913213
RW		 1836 (native-inputs
1837 `(("python-cython" ,python-cython)
f3b98f4f 1838 ("python-nose" ,python-nose)))
0c6c9c00 1839 (home-page "https://cutadapt.readthedocs.io/en/stable/")
8e913213
RW		 1840 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1841 (description
1842 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1843other types of unwanted sequence from high-throughput sequencing reads.")
1844 (license license:expat)))
1845
1baee943
RW		 1846(define-public libbigwig
1847 (package
1848 (name "libbigwig")
1849 (version "0.1.4")
1850 (source (origin
1851 (method url-fetch)
1852 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1853 "archive/" version ".tar.gz"))
1854 (file-name (string-append name "-" version ".tar.gz"))
1855 (sha256
1856 (base32
1857 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1858 (build-system gnu-build-system)
1859 (arguments
1860 `(#:test-target "test"
1861 #:make-flags
1862 (list "CC=gcc"
1863 (string-append "prefix=" (assoc-ref %outputs "out")))
1864 #:phases
1865 (modify-phases %standard-phases
1866 (delete 'configure)
1867 (add-before 'check 'disable-curl-test
1868 (lambda _
1869 (substitute* "Makefile"
1870 (("./test/testRemote.*") ""))
1871 #t))
1872 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1873 ;; there has not yet been a release containing this change.
1874 (add-before 'install 'create-target-dirs
1875 (lambda* (#:key outputs #:allow-other-keys)
1876 (let ((out (assoc-ref outputs "out")))
1877 (mkdir-p (string-append out "/lib"))
1878 (mkdir-p (string-append out "/include"))
1879 #t))))))
1880 (inputs
1881 `(("zlib" ,zlib)
1882 ("curl" ,curl)))
1883 (native-inputs
1884 `(("doxygen" ,doxygen)))
1885 (home-page "https://github.com/dpryan79/libBigWig")
1886 (synopsis "C library for handling bigWig files")
1887 (description
1888 "This package provides a C library for parsing local and remote BigWig
1889files.")
1890 (license license:expat)))
1891
69e0e03c
RW		 1892(define-public python-pybigwig
1893 (package
1894 (name "python-pybigwig")
1895 (version "0.2.5")
1896 (source (origin
1897 (method url-fetch)
1898 (uri (pypi-uri "pyBigWig" version))
1899 (sha256
1900 (base32
1901 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1902 (modules '((guix build utils)))
1903 (snippet
1904 '(begin
1905 ;; Delete bundled libBigWig sources
1906 (delete-file-recursively "libBigWig")))))
1907 (build-system python-build-system)
1908 (arguments
1909 `(#:phases
1910 (modify-phases %standard-phases
1911 (add-after 'unpack 'link-with-libBigWig
1912 (lambda* (#:key inputs #:allow-other-keys)
1913 (substitute* "setup.py"
1914 (("libs=\\[") "libs=[\"BigWig\", "))
1915 #t)))))
1916 (inputs
1917 `(("libbigwig" ,libbigwig)
1918 ("zlib" ,zlib)
1919 ("curl" ,curl)))
1920 (home-page "https://github.com/dpryan79/pyBigWig")
1921 (synopsis "Access bigWig files in Python using libBigWig")
1922 (description
1923 "This package provides Python bindings to the libBigWig library for
1924accessing bigWig files.")
1925 (license license:expat)))
1926
1927(define-public python2-pybigwig
5c31f4aa 1928 (package-with-python2 python-pybigwig))
69e0e03c 1929
ec2a67de
BW		 1930(define-public python-dendropy
1931 (package
1932 (name "python-dendropy")
1933 (version "4.1.0")
1934 (source
1935 (origin
1936 (method url-fetch)
1937 (uri (pypi-uri "DendroPy" version))
1938 (sha256
1939 (base32
1940 "1jfz7gp18wph311w1yygbvjanb3n5mdqal439bb6myw41dwb5m63"))
1941 ;; There are two known test failures that will be fixed in the next
1942 ;; release after 4.1.0.
1943 ;; https://github.com/jeetsukumaran/DendroPy/issues/48
1944 (patches (search-patches
1945 "python-dendropy-exclude-failing-tests.patch"))))
1946 (build-system python-build-system)
1947 (home-page "http://packages.python.org/DendroPy/")
1948 (synopsis "Library for phylogenetics and phylogenetic computing")
1949 (description
1950 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1951writing, simulation, processing and manipulation of phylogenetic
1952trees (phylogenies) and characters.")
1953 (license license:bsd-3)
1954 (properties `((python2-variant . ,(delay python2-dendropy))))))
1955
1956(define-public python2-dendropy
1957 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1958 (package
1959 (inherit base)
9602e3cc
BW		 1960 ;; Do not use same source as 'python-dendropy' because the patched
1961 ;; failing tests do not occur on Python 2.
1962 (source
1963 (origin
1964 (method url-fetch)
1965 (uri (pypi-uri "DendroPy" (package-version base)))
1966 (sha256
1967 (base32
1968 "1jfz7gp18wph311w1yygbvjanb3n5mdqal439bb6myw41dwb5m63"))))
1969 (arguments
1970 `(#:python ,python-2
1971 #:phases
1972 (modify-phases %standard-phases
1973 (replace 'check
1974 ;; There is currently a test failure that only happens on some
1975 ;; systems, and only using "setup.py test"
1976 (lambda _ (zero? (system* "nosetests")))))))
f3b98f4f 1977 (native-inputs `(("python2-nose" ,python2-nose)
ec2a67de
BW		 1978 ,@(package-native-inputs base))))))
1979
1980
1921b1de
RW		 1981(define-public deeptools
1982 (package
1983 (name "deeptools")
3acb8c85 1984 (version "2.1.1")
1921b1de
RW		 1985 (source (origin
1986 (method url-fetch)
3acb8c85
RW		 1987 (uri (string-append "https://github.com/fidelram/deepTools/"
1988 "archive/" version ".tar.gz"))
1921b1de
RW		 1989 (file-name (string-append name "-" version ".tar.gz"))
1990 (sha256
1991 (base32
3acb8c85 1992 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
1921b1de
RW		 1993 (build-system python-build-system)
1994 (arguments
1995 `(#:python ,python-2))
14bda1ff 1996 (inputs
1921b1de
RW		 1997 `(("python-scipy" ,python2-scipy)
1998 ("python-numpy" ,python2-numpy)
3acb8c85 1999 ("python-numpydoc" ,python2-numpydoc)
1921b1de
RW		 2000 ("python-matplotlib" ,python2-matplotlib)
2001 ("python-bx-python" ,python2-bx-python)
3acb8c85
RW		 2002 ("python-pysam" ,python2-pysam)
2003 ("python-pybigwig" ,python2-pybigwig)))
1921b1de 2004 (native-inputs
f3b98f4f
HG		 2005 `(("python-mock" ,python2-mock) ;for tests
2006 ("python-pytz" ,python2-pytz))) ;for tests
1921b1de
RW		 2007 (home-page "https://github.com/fidelram/deepTools")
2008 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2009 (description
2010 "DeepTools addresses the challenge of handling the large amounts of data
2011that are now routinely generated from DNA sequencing centers. To do so,
2012deepTools contains useful modules to process the mapped reads data to create
2013coverage files in standard bedGraph and bigWig file formats. By doing so,
2014deepTools allows the creation of normalized coverage files or the comparison
2015between two files (for example, treatment and control). Finally, using such
2016normalized and standardized files, multiple visualizations can be created to
2017identify enrichments with functional annotations of the genome.")
2018 (license license:gpl3+)))
2019
684bf7c7
BW		 2020(define-public diamond
2021 (package
2022 (name "diamond")
9916ef8b 2023 (version "0.8.30")
684bf7c7
BW		 2024 (source (origin
2025 (method url-fetch)
2026 (uri (string-append
2027 "https://github.com/bbuchfink/diamond/archive/v"
2028 version ".tar.gz"))
2029 (file-name (string-append name "-" version ".tar.gz"))
2030 (sha256
2031 (base32
9916ef8b 2032 "1fqzbrh5kxxbw805nwanddfa8lic65s58y37x5n2swf28518w4zf"))))
122395f9 2033 (build-system cmake-build-system)
684bf7c7 2034 (arguments
7c544991
BW		 2035 '(#:tests? #f ; no "check" target
2036 #:phases
2037 (modify-phases %standard-phases
2038 (add-after 'unpack 'remove-native-compilation
2039 (lambda _
2040 (substitute* "CMakeLists.txt" (("-march=native") ""))
2041 #t)))))
684bf7c7 2042 (inputs
122395f9 2043 `(("zlib" ,zlib)))
684bf7c7
BW		 2044 (home-page "https://github.com/bbuchfink/diamond")
2045 (synopsis "Accelerated BLAST compatible local sequence aligner")
2046 (description
2047 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2048translated DNA query sequences against a protein reference database (BLASTP
2049and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2050reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2051data and settings.")
d9c44e9c
BW		 2052 ;; diamond fails to build on other platforms
2053 ;; https://github.com/bbuchfink/diamond/issues/18
2054 (supported-systems '("x86_64-linux"))
684bf7c7
BW		 2055 (license (license:non-copyleft "file://src/COPYING"
2056 "See src/COPYING in the distribution."))))
2057
97b9da68
RW		 2058(define-public discrover
2059 (package
2060 (name "discrover")
2061 (version "1.6.0")
2062 (source
2063 (origin
2064 (method url-fetch)
2065 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2066 version ".tar.gz"))
2067 (file-name (string-append name "-" version ".tar.gz"))
2068 (sha256
2069 (base32
2070 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2071 (build-system cmake-build-system)
2072 (arguments `(#:tests? #f)) ; there are no tests
2073 (inputs
2074 `(("boost" ,boost)
2075 ("cairo" ,cairo)))
2076 (native-inputs
2077 `(("texlive" ,texlive)
2078 ("imagemagick" ,imagemagick)))
2079 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2080 (synopsis "Discover discriminative nucleotide sequence motifs")
2081 (description "Discrover is a motif discovery method to find binding sites
2082of nucleic acid binding proteins.")
2083 (license license:gpl3+)))
2084
6619f9c7
RW		 2085(define-public eigensoft
2086 (let ((revision "1")
2087 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2088 (package
2089 (name "eigensoft")
2090 (version (string-append "6.1.2-"
2091 revision "."
2092 (string-take commit 9)))
2093 (source
2094 (origin
2095 (method git-fetch)
2096 (uri (git-reference
2097 (url "https://github.com/DReichLab/EIG.git")
2098 (commit commit)))
2099 (file-name (string-append "eigensoft-" commit "-checkout"))
2100 (sha256
2101 (base32
2102 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2103 (modules '((guix build utils)))
2104 ;; Remove pre-built binaries.
2105 (snippet '(begin
2106 (delete-file-recursively "bin")
2107 (mkdir "bin")
2108 #t))))
2109 (build-system gnu-build-system)
2110 (arguments
2111 `(#:tests? #f ; There are no tests.
2112 #:make-flags '("CC=gcc")
2113 #:phases
2114 (modify-phases %standard-phases
2115 ;; There is no configure phase, but the Makefile is in a
2116 ;; sub-directory.
2117 (replace 'configure
2118 (lambda _
2119 (chdir "src")
2120 ;; The link flags are incomplete.
2121 (substitute* "Makefile"
2122 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2123 #t))
2124 ;; The provided install target only copies executables to
2125 ;; the "bin" directory in the build root.
2126 (add-after 'install 'actually-install
2127 (lambda* (#:key outputs #:allow-other-keys)
2128 (let* ((out (assoc-ref outputs "out"))
2129 (bin (string-append out "/bin")))
6619f9c7
RW		 2130 (for-each (lambda (file)
2131 (install-file file bin))
2132 (find-files "../bin" ".*"))
2133 #t))))))
2134 (inputs
2135 `(("gsl" ,gsl)
2136 ("lapack" ,lapack)
6619f9c7
RW		 2137 ("openblas" ,openblas)
2138 ("perl" ,perl)
2139 ("gfortran" ,gfortran "lib")))
2140 (home-page "https://github.com/DReichLab/EIG")
2141 (synopsis "Tools for population genetics")
2142 (description "The EIGENSOFT package provides tools for population
2143genetics and stratification correction. EIGENSOFT implements methods commonly
2144used in population genetics analyses such as PCA, computation of Tracy-Widom
2145statistics, and finding related individuals in structured populations. It
2146comes with a built-in plotting script and supports multiple file formats and
2147quantitative phenotypes.")
2148 ;; The license of the eigensoft tools is Expat, but since it's
2149 ;; linking with the GNU Scientific Library (GSL) the effective
2150 ;; license is the GPL.
2151 (license license:gpl3+))))
2152
365c8153
RW		 2153(define-public edirect
2154 (package
2155 (name "edirect")
83b84fa8 2156 (version "4.10")
365c8153
RW		 2157 (source (origin
2158 (method url-fetch)
83b84fa8
RW		 2159 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2160 "versions/2016-05-03/edirect.tar.gz"))
365c8153
RW		 2161 (sha256
2162 (base32
83b84fa8 2163 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
365c8153
RW		 2164 (build-system perl-build-system)
2165 (arguments
2166 `(#:tests? #f ;no "check" target
2167 #:phases
2168 (modify-phases %standard-phases
2169 (delete 'configure)
2170 (delete 'build)
2171 (replace 'install
2172 (lambda* (#:key outputs #:allow-other-keys)
2173 (let ((target (string-append (assoc-ref outputs "out")
2174 "/bin")))
2175 (mkdir-p target)
2176 (copy-file "edirect.pl"
2177 (string-append target "/edirect.pl"))
2178 #t)))
2179 (add-after
2180 'install 'wrap-program
2181 (lambda* (#:key inputs outputs #:allow-other-keys)
2182 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2183 (let* ((out (assoc-ref outputs "out"))
2184 (path (getenv "PERL5LIB")))
2185 (wrap-program (string-append out "/bin/edirect.pl")
2186 `("PERL5LIB" ":" prefix (,path)))))))))
2187 (inputs
2188 `(("perl-html-parser" ,perl-html-parser)
2189 ("perl-encode-locale" ,perl-encode-locale)
2190 ("perl-file-listing" ,perl-file-listing)
2191 ("perl-html-tagset" ,perl-html-tagset)
2192 ("perl-html-tree" ,perl-html-tree)
2193 ("perl-http-cookies" ,perl-http-cookies)
2194 ("perl-http-date" ,perl-http-date)
2195 ("perl-http-message" ,perl-http-message)
2196 ("perl-http-negotiate" ,perl-http-negotiate)
2197 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2198 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2199 ("perl-net-http" ,perl-net-http)
2200 ("perl-uri" ,perl-uri)
2201 ("perl-www-robotrules" ,perl-www-robotrules)
2202 ("perl" ,perl)))
3d51ec91 2203 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
365c8153
RW		 2204 (synopsis "Tools for accessing the NCBI's set of databases")
2205 (description
2206 "Entrez Direct (EDirect) is a method for accessing the National Center
2207for Biotechnology Information's (NCBI) set of interconnected
2208databases (publication, sequence, structure, gene, variation, expression,
2209etc.) from a terminal. Functions take search terms from command-line
2210arguments. Individual operations are combined to build multi-step queries.
2211Record retrieval and formatting normally complete the process.
2212
2213EDirect also provides an argument-driven function that simplifies the
2214extraction of data from document summaries or other results that are returned
2215in structured XML format. This can eliminate the need for writing custom
2216software to answer ad hoc questions.")
2217 (license license:public-domain)))
2218
b16728b0
BW		 2219(define-public exonerate
2220 (package
2221 (name "exonerate")
2222 (version "2.4.0")
2223 (source
2224 (origin
2225 (method url-fetch)
2226 (uri
2227 (string-append
2228 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2229 "exonerate-" version ".tar.gz"))
2230 (sha256
2231 (base32
2232 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2233 (build-system gnu-build-system)
2234 (arguments
2235 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2236 (native-inputs
2237 `(("pkg-config" ,pkg-config)))
2238 (inputs
2239 `(("glib" ,glib)))
2240 (home-page
2241 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2242 (synopsis "Generic tool for biological sequence alignment")
2243 (description
2244 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2245the alignment of sequences using a many alignment models, either exhaustive
2246dynamic programming or a variety of heuristics.")
2247 (license license:gpl3)))
2248
e4e5a4d8
RW		 2249(define-public express
2250 (package
2251 (name "express")
2252 (version "1.5.1")
2253 (source (origin
2254 (method url-fetch)
2255 (uri
2256 (string-append
2257 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2258 version "/express-" version "-src.tgz"))
2259 (sha256
2260 (base32
2261 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2262 (build-system cmake-build-system)
2263 (arguments
2264 `(#:tests? #f ;no "check" target
2265 #:phases
2266 (alist-cons-after
2267 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2268 (lambda* (#:key inputs #:allow-other-keys)
2269 (substitute* "CMakeLists.txt"
2270 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2271 "set(Boost_USE_STATIC_LIBS OFF)")
2272 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2273 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2274 (substitute* "src/CMakeLists.txt"
2275 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2276 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2277 #t)
2278 %standard-phases)))
2279 (inputs
2280 `(("boost" ,boost)
2281 ("bamtools" ,bamtools)
2282 ("protobuf" ,protobuf)
2283 ("zlib" ,zlib)))
2284 (home-page "http://bio.math.berkeley.edu/eXpress")
2285 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2286 (description
2287 "eXpress is a streaming tool for quantifying the abundances of a set of
2288target sequences from sampled subsequences. Example applications include
2289transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2290analysis (from RNA-Seq), transcription factor binding quantification in
2291ChIP-Seq, and analysis of metagenomic data.")
2292 (license license:artistic2.0)))
2293
f3674b1c
BW		 2294(define-public express-beta-diversity
2295 (package
2296 (name "express-beta-diversity")
2297 (version "1.0.7")
2298 (source (origin
2299 (method url-fetch)
2300 (uri
2301 (string-append
2302 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2303 version ".tar.gz"))
2304 (file-name (string-append name "-" version ".tar.gz"))
2305 (sha256
2306 (base32
2307 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2308 (build-system gnu-build-system)
2309 (arguments
2310 `(#:phases
2311 (modify-phases %standard-phases
2312 (delete 'configure)
2313 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2314 (replace 'check
2315 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2316 "-u"))))
2317 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2318 (replace 'install
2319 (lambda* (#:key outputs #:allow-other-keys)
2320 (let ((bin (string-append (assoc-ref outputs "out")
2321 "/bin")))
2322 (mkdir-p bin)
2323 (copy-file "scripts/convertToEBD.py"
2324 (string-append bin "/convertToEBD.py"))
2325 (copy-file "bin/ExpressBetaDiversity"
2326 (string-append bin "/ExpressBetaDiversity"))
2327 #t))))))
2328 (inputs
2329 `(("python" ,python-2)))
2330 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2331 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2332 (description
2333 "Express Beta Diversity (EBD) calculates ecological beta diversity
2334(dissimilarity) measures between biological communities. EBD implements a
2335variety of diversity measures including those that make use of phylogenetic
2336similarity of community members.")
2337 (license license:gpl3+)))
2338
12b04cbe
BW		 2339(define-public fasttree
2340 (package
2341 (name "fasttree")
e03a5153 2342 (version "2.1.9")
12b04cbe
BW		 2343 (source (origin
2344 (method url-fetch)
2345 (uri (string-append
2346 "http://www.microbesonline.org/fasttree/FastTree-"
2347 version ".c"))
2348 (sha256
2349 (base32
e03a5153 2350 "0ljvvw8i1als1wbfzvrf15c3ii2vw9db20a259g6pzg34xyyb97k"))))
12b04cbe
BW		 2351 (build-system gnu-build-system)
2352 (arguments
2353 `(#:tests? #f ; no "check" target
2354 #:phases
2355 (modify-phases %standard-phases
2356 (delete 'unpack)
2357 (delete 'configure)
2358 (replace 'build
e03a5153
BW		 2359 (lambda* (#:key source #:allow-other-keys)
2360 (and (zero? (system* "gcc"
2361 "-O3"
2362 "-finline-functions"
2363 "-funroll-loops"
2364 "-Wall"
2365 "-o"
2366 "FastTree"
2367 source
2368 "-lm"))
2369 (zero? (system* "gcc"
2370 "-DOPENMP"
2371 "-fopenmp"
2372 "-O3"
2373 "-finline-functions"
2374 "-funroll-loops"
2375 "-Wall"
2376 "-o"
2377 "FastTreeMP"
2378 source
2379 "-lm")))))
12b04cbe 2380 (replace 'install
e03a5153
BW		 2381 (lambda* (#:key outputs #:allow-other-keys)
2382 (let ((bin (string-append (assoc-ref outputs "out")
2383 "/bin")))
2384 (mkdir-p bin)
2385 (copy-file "FastTree"
2386 (string-append bin "/FastTree"))
2387 (copy-file "FastTreeMP"
2388 (string-append bin "/FastTreeMP"))
2389 #t))))))
12b04cbe
BW		 2390 (home-page "http://www.microbesonline.org/fasttree")
2391 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2392 (description
2393 "FastTree can handle alignments with up to a million of sequences in a
2394reasonable amount of time and memory. For large alignments, FastTree is
2395100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2396 (license license:gpl2+)))
2397
2127cedb
RW		 2398(define-public fastx-toolkit
2399 (package
2400 (name "fastx-toolkit")
2401 (version "0.0.14")
2402 (source (origin
2403 (method url-fetch)
2404 (uri
2405 (string-append
2406 "https://github.com/agordon/fastx_toolkit/releases/download/"
2407 version "/fastx_toolkit-" version ".tar.bz2"))
2408 (sha256
2409 (base32
2410 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2411 (build-system gnu-build-system)
2412 (inputs
2413 `(("libgtextutils" ,libgtextutils)))
2414 (native-inputs
2415 `(("pkg-config" ,pkg-config)))
2416 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2417 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2418 (description
2419 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2420FASTA/FASTQ files preprocessing.
2421
2422Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2423containing multiple short-reads sequences. The main processing of such
2424FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2425is sometimes more productive to preprocess the files before mapping the
2426sequences to the genome---manipulating the sequences to produce better mapping
2427results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2428 (license license:agpl3+)))
2429
d7678942
RW		 2430(define-public flexbar
2431 (package
2432 (name "flexbar")
2433 (version "2.5")
2434 (source (origin
2435 (method url-fetch)
2436 (uri
2437 (string-append "mirror://sourceforge/flexbar/"
2438 version "/flexbar_v" version "_src.tgz"))
2439 (sha256
2440 (base32
2441 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2442 (build-system cmake-build-system)
2443 (arguments
4ca009c0 2444 `(#:configure-flags (list
d7678942
RW		 2445 (string-append "-DFLEXBAR_BINARY_DIR="
2446 (assoc-ref %outputs "out")
2447 "/bin/"))
2448 #:phases
4ca009c0
RW		 2449 (alist-replace
2450 'check
2451 (lambda* (#:key outputs #:allow-other-keys)
2452 (setenv "PATH" (string-append
2453 (assoc-ref outputs "out") "/bin:"
2454 (getenv "PATH")))
2455 (chdir "../flexbar_v2.5_src/test")
2456 (zero? (system* "bash" "flexbar_validate.sh")))
2457 (alist-delete 'install %standard-phases))))
d7678942
RW		 2458 (inputs
2459 `(("tbb" ,tbb)
2460 ("zlib" ,zlib)))
2461 (native-inputs
2462 `(("pkg-config" ,pkg-config)
2463 ("seqan" ,seqan)))
2464 (home-page "http://flexbar.sourceforge.net")
2465 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2466 (description
2467 "Flexbar preprocesses high-throughput nucleotide sequencing data
2468efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2469Moreover, trimming and filtering features are provided. Flexbar increases
2470read mapping rates and improves genome and transcriptome assemblies. It
2471supports next-generation sequencing data in fasta/q and csfasta/q format from
2472Illumina, Roche 454, and the SOLiD platform.")
2473 (license license:gpl3)))
2474
19f4554c
BW		 2475(define-public fraggenescan
2476 (package
2477 (name "fraggenescan")
2478 (version "1.20")
2479 (source
2480 (origin
2481 (method url-fetch)
2482 (uri
2483 (string-append "mirror://sourceforge/fraggenescan/"
2484 "FragGeneScan" version ".tar.gz"))
2485 (sha256
2486 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
2487 (build-system gnu-build-system)
2488 (arguments
2489 `(#:phases
2490 (modify-phases %standard-phases
2491 (delete 'configure)
2492 (add-before 'build 'patch-paths
2493 (lambda* (#:key outputs #:allow-other-keys)
2494 (let* ((out (string-append (assoc-ref outputs "out")))
2495 (share (string-append out "/share/fraggenescan/")))
2496 (substitute* "run_FragGeneScan.pl"
2497 (("system\\(\"rm")
2498 (string-append "system(\"" (which "rm")))
2499 (("system\\(\"mv")
2500 (string-append "system(\"" (which "mv")))
2501 ;; This script and other programs expect the training files
2502 ;; to be in the non-standard location bin/train/XXX. Change
2503 ;; this to be share/fraggenescan/train/XXX instead.
2504 (("^\\$train.file = \\$dir.*")
2505 (string-append "$train_file = \""
2506 share
2507 "train/\".$FGS_train_file;")))
2508 (substitute* "run_hmm.c"
2509 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2510 (string-append " strcpy(train_dir, \"" share "/train/\");")))
2511 (substitute* "post_process.pl"
2512 (("^my \\$dir = substr.*")
2513 (string-append "my $dir = \"" share "\";"))))
2514 #t))
2515 (replace 'build
2516 (lambda _ (and (zero? (system* "make" "clean"))
2517 (zero? (system* "make" "fgs")))))
2518 (replace 'install
2519 (lambda* (#:key outputs #:allow-other-keys)
2520 (let* ((out (string-append (assoc-ref outputs "out")))
2521 (bin (string-append out "/bin/"))
2522 (share (string-append out "/share/fraggenescan/train")))
2523 (install-file "run_FragGeneScan.pl" bin)
2524 (install-file "FragGeneScan" bin)
2525 (install-file "FGS_gff.py" bin)
2526 (install-file "post_process.pl" bin)
2527 (copy-recursively "train" share))))
2528 (delete 'check)
2529 (add-after 'install 'post-install-check
2530 ;; In lieu of 'make check', run one of the examples and check the
2531 ;; output files gets created.
2532 (lambda* (#:key outputs #:allow-other-keys)
2533 (let* ((out (string-append (assoc-ref outputs "out")))
2534 (bin (string-append out "/bin/")))
2535 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
2536 "-genome=./example/NC_000913.fna"
2537 "-out=./test2"
2538 "-complete=1"
2539 "-train=complete"))
2540 (file-exists? "test2.faa")
2541 (file-exists? "test2.ffn")
2542 (file-exists? "test2.gff")
2543 (file-exists? "test2.out"))))))))
2544 (inputs
2545 `(("perl" ,perl)
2546 ("python" ,python-2))) ;not compatible with python 3.
2547 (home-page "https://sourceforge.net/projects/fraggenescan/")
2548 (synopsis "Finds potentially fragmented genes in short reads")
2549 (description
2550 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2551short and error-prone DNA sequencing reads. It can also be applied to predict
2552genes in incomplete assemblies or complete genomes.")
2553 ;; GPL3+ according to private correspondense with the authors.
2554 (license license:gpl3+)))
2555
81f3e0c1
BW		 2556(define-public fxtract
2557 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2558 (package
2559 (name "fxtract")
2560 (version "2.3")
2561 (source
2562 (origin
2563 (method url-fetch)
2564 (uri (string-append
2565 "https://github.com/ctSkennerton/fxtract/archive/"
2566 version ".tar.gz"))
2567 (file-name (string-append "ctstennerton-util-"
2568 (string-take util-commit 7)
2569 "-checkout"))
2570 (sha256
2571 (base32
2572 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2573 (build-system gnu-build-system)
2574 (arguments
2575 `(#:make-flags (list
2576 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2577 "CC=gcc")
2578 #:test-target "fxtract_test"
2579 #:phases
2580 (modify-phases %standard-phases
2581 (delete 'configure)
2582 (add-before 'build 'copy-util
2583 (lambda* (#:key inputs #:allow-other-keys)
2584 (rmdir "util")
2585 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2586 #t))
2587 ;; Do not use make install as this requires additional dependencies.
2588 (replace 'install
2589 (lambda* (#:key outputs #:allow-other-keys)
2590 (let* ((out (assoc-ref outputs "out"))
2591 (bin (string-append out"/bin")))
2592 (install-file "fxtract" bin)
2593 #t))))))
2594 (inputs
2595 `(("pcre" ,pcre)
2596 ("zlib" ,zlib)))
2597 (native-inputs
2598 ;; ctskennerton-util is licensed under GPL2.
2599 `(("ctskennerton-util"
2600 ,(origin
2601 (method git-fetch)
2602 (uri (git-reference
2603 (url "https://github.com/ctSkennerton/util.git")
2604 (commit util-commit)))
2605 (file-name (string-append
2606 "ctstennerton-util-" util-commit "-checkout"))
2607 (sha256
2608 (base32
2609 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2610 (home-page "https://github.com/ctSkennerton/fxtract")
2611 (synopsis "Extract sequences from FASTA and FASTQ files")
2612 (description
2613 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2614or FASTQ) file given a subsequence. It uses a simple substring search for
2615basic tasks but can change to using POSIX regular expressions, PCRE, hash
2616lookups or multi-pattern searching as required. By default fxtract looks in
2617the sequence of each record but can also be told to look in the header,
2618comment or quality sections.")
afde1a26
BW		 2619 ;; 'util' requires SSE instructions.
2620 (supported-systems '("x86_64-linux"))
81f3e0c1
BW		 2621 (license license:expat))))
2622
5854f685
RW		 2623(define-public grit
2624 (package
2625 (name "grit")
2626 (version "2.0.2")
2627 (source (origin
2628 (method url-fetch)
2629 (uri (string-append
2630 "https://github.com/nboley/grit/archive/"
2631 version ".tar.gz"))
2632 (file-name (string-append name "-" version ".tar.gz"))
2633 (sha256
2634 (base32
2635 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2636 (build-system python-build-system)
2637 (arguments
2638 `(#:python ,python-2
2639 #:phases
2640 (alist-cons-after
2641 'unpack 'generate-from-cython-sources
2642 (lambda* (#:key inputs outputs #:allow-other-keys)
2643 ;; Delete these C files to force fresh generation from pyx sources.
2644 (delete-file "grit/sparsify_support_fns.c")
2645 (delete-file "grit/call_peaks_support_fns.c")
2646 (substitute* "setup.py"
2647 (("Cython.Setup") "Cython.Build")
2648 ;; Add numpy include path to fix compilation
2649 (("pyx\", \\]")
2650 (string-append "pyx\", ], include_dirs = ['"
2651 (assoc-ref inputs "python-numpy")
2652 "/lib/python2.7/site-packages/numpy/core/include/"
2653 "']"))) #t)
2654 %standard-phases)))
2655 (inputs
2656 `(("python-scipy" ,python2-scipy)
2657 ("python-numpy" ,python2-numpy)
2658 ("python-pysam" ,python2-pysam)
2659 ("python-networkx" ,python2-networkx)))
2660 (native-inputs
f3b98f4f 2661 `(("python-cython" ,python2-cython)))
5854f685
RW		 2662 (home-page "http://grit-bio.org")
2663 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2664 (description
2665 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2666full length transcript models. When none of these data sources are available,
2667GRIT can be run by providing a candidate set of TES or TSS sites. In
2668addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2669also be run in quantification mode, where it uses a provided GTF file and just
2670estimates transcript expression.")
2671 (license license:gpl3+)))
2672
346a829a
RW		 2673(define-public hisat
2674 (package
2675 (name "hisat")
2676 (version "0.1.4")
2677 (source (origin
2678 (method url-fetch)
2679 (uri (string-append
2680 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2681 version "-beta-source.zip"))
2682 (sha256
2683 (base32
2684 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2685 (build-system gnu-build-system)
2686 (arguments
e58d01fa
RW		 2687 `(#:tests? #f ;no check target
2688 #:make-flags '("allall"
2689 ;; Disable unsupported `popcnt' instructions on
2690 ;; architectures other than x86_64
2691 ,@(if (string-prefix? "x86_64"
2692 (or (%current-target-system)
2693 (%current-system)))
2694 '()
2695 '("POPCNT_CAPABILITY=0")))
346a829a 2696 #:phases
da6dd842
LC		 2697 (alist-cons-after
2698 'unpack 'patch-sources
2699 (lambda _
2700 ;; XXX Cannot use snippet because zip files are not supported
2701 (substitute* "Makefile"
2702 (("^CC = .*$") "CC = gcc")
2703 (("^CPP = .*$") "CPP = g++")
2704 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2705 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2706 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2707 (substitute* '("hisat-build" "hisat-inspect")
2708 (("/usr/bin/env") (which "env"))))
2709 (alist-replace
2710 'install
2711 (lambda* (#:key outputs #:allow-other-keys)
84590149 2712 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
96c46210
LC		 2713 (for-each (lambda (file)
2714 (install-file file bin))
2715 (find-files
2716 "."
2717 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
da6dd842 2718 (alist-delete 'configure %standard-phases)))))
346a829a
RW		 2719 (native-inputs
2720 `(("unzip" ,unzip)))
2721 (inputs
2722 `(("perl" ,perl)
2723 ("python" ,python)
2724 ("zlib" ,zlib)))
60af3d82
RW		 2725 ;; Non-portable SSE instructions are used so building fails on platforms
2726 ;; other than x86_64.
2727 (supported-systems '("x86_64-linux"))
346a829a
RW		 2728 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2729 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2730 (description
2731 "HISAT is a fast and sensitive spliced alignment program for mapping
2732RNA-seq reads. In addition to one global FM index that represents a whole
2733genome, HISAT uses a large set of small FM indexes that collectively cover the
2734whole genome. These small indexes (called local indexes) combined with
2735several alignment strategies enable effective alignment of RNA-seq reads, in
2736particular, reads spanning multiple exons.")
2737 (license license:gpl3+)))
2738
c684629f
BW		 2739(define-public hmmer
2740 (package
2741 (name "hmmer")
2742 (version "3.1b2")
2743 (source (origin
2744 (method url-fetch)
2745 (uri (string-append
a83e6046 2746 "http://eddylab.org/software/hmmer"
c684629f
BW		 2747 (version-prefix version 1) "/"
2748 version "/hmmer-" version ".tar.gz"))
2749 (sha256
2750 (base32
2751 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
2752 (build-system gnu-build-system)
b3546174 2753 (native-inputs `(("perl" ,perl)))
a83e6046 2754 (home-page "http://hmmer.org/")
c684629f
BW		 2755 (synopsis "Biosequence analysis using profile hidden Markov models")
2756 (description
2757 "HMMER is used for searching sequence databases for homologs of protein
2758sequences, and for making protein sequence alignments. It implements methods
2759using probabilistic models called profile hidden Markov models (profile
2760HMMs).")
2761 (license (list license:gpl3+
2762 ;; The bundled library 'easel' is distributed
2763 ;; under The Janelia Farm Software License.
2764 (license:non-copyleft
2765 "file://easel/LICENSE"
2766 "See easel/LICENSE in the distribution.")))))
2767
85652f59
RW		 2768(define-public htseq
2769 (package
2770 (name "htseq")
2771 (version "0.6.1")
2772 (source (origin
2773 (method url-fetch)
2774 (uri (string-append
2775 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2776 version ".tar.gz"))
2777 (sha256
2778 (base32
2779 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2780 (build-system python-build-system)
2781 (arguments `(#:python ,python-2)) ; only Python 2 is supported
0536727e
RW		 2782 ;; Numpy needs to be propagated when htseq is used as a Python library.
2783 (propagated-inputs
2784 `(("python-numpy" ,python2-numpy)))
578b05d9
RW		 2785 (inputs
2786 `(("python-pysam" ,python2-pysam)))
85652f59
RW		 2787 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2788 (synopsis "Analysing high-throughput sequencing data with Python")
2789 (description
2790 "HTSeq is a Python package that provides infrastructure to process data
2791from high-throughput sequencing assays.")
2792 (license license:gpl3+)))
2793
1ad15c16 2794(define-public java-htsjdk
15a3c3d4 2795 (package
1ad15c16 2796 (name "java-htsjdk")
15a3c3d4
RW		 2797 (version "1.129")
2798 (source (origin
2799 (method url-fetch)
2800 (uri (string-append
2801 "https://github.com/samtools/htsjdk/archive/"
2802 version ".tar.gz"))
2803 (file-name (string-append name "-" version ".tar.gz"))
2804 (sha256
2805 (base32
2806 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2807 (modules '((guix build utils)))
2808 ;; remove build dependency on git
2809 (snippet '(substitute* "build.xml"
2810 (("failifexecutionfails=\"true\"")
2811 "failifexecutionfails=\"false\"")))))
10b4a969 2812 (build-system ant-build-system)
15a3c3d4 2813 (arguments
10b4a969
RW		 2814 `(#:tests? #f ; test require Internet access
2815 #:make-flags
2816 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2817 "/share/java/htsjdk/"))
2818 #:build-target "all"
2819 #:phases
2820 (modify-phases %standard-phases
2821 ;; The build phase also installs the jars
2822 (delete 'install))))
15a3c3d4
RW		 2823 (home-page "http://samtools.github.io/htsjdk/")
2824 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2825 (description
2826 "HTSJDK is an implementation of a unified Java library for accessing
2827common file formats, such as SAM and VCF, used for high-throughput
2828sequencing (HTS) data. There are also an number of useful utilities for
2829manipulating HTS data.")
2830 (license license:expat)))
2831
e7c09730
RW		 2832(define-public htslib
2833 (package
2834 (name "htslib")
6c737963 2835 (version "1.3.1")
e7c09730
RW		 2836 (source (origin
2837 (method url-fetch)
2838 (uri (string-append
2839 "https://github.com/samtools/htslib/releases/download/"
2840 version "/htslib-" version ".tar.bz2"))
2841 (sha256
2842 (base32
6c737963 2843 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
e7c09730
RW		 2844 (build-system gnu-build-system)
2845 (arguments
2846 `(#:phases
2847 (modify-phases %standard-phases
2848 (add-after
2849 'unpack 'patch-tests
2850 (lambda _
2851 (substitute* "test/test.pl"
2852 (("/bin/bash") (which "bash")))
2853 #t)))))
2854 (inputs
2855 `(("zlib" ,zlib)))
2856 (native-inputs
2857 `(("perl" ,perl)))
2858 (home-page "http://www.htslib.org")
2859 (synopsis "C library for reading/writing high-throughput sequencing data")
2860 (description
2861 "HTSlib is a C library for reading/writing high-throughput sequencing
2862data. It also provides the bgzip, htsfile, and tabix utilities.")
2863 ;; Files under cram/ are released under the modified BSD license;
2864 ;; the rest is released under the Expat license
2865 (license (list license:expat license:bsd-3))))
2866
c4325f62
RW		 2867(define-public idr
2868 (package
2869 (name "idr")
2870 (version "2.0.0")
2871 (source (origin
2872 (method url-fetch)
2873 (uri (string-append
2874 "https://github.com/nboley/idr/archive/"
2875 version ".tar.gz"))
2876 (file-name (string-append name "-" version ".tar.gz"))
2877 (sha256
2878 (base32
2879 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
2880 (build-system python-build-system)
2881 (arguments
2882 `(#:phases
2883 (modify-phases %standard-phases
2884 (add-after
2885 'install 'wrap-program
2886 (lambda* (#:key inputs outputs #:allow-other-keys)
2887 (let* ((out (assoc-ref outputs "out"))
2888 (python-version (string-take (string-take-right
2889 (assoc-ref inputs "python") 5) 3))
2890 (path (string-join
2891 (map (lambda (name)
2892 (string-append (assoc-ref inputs name)
2893 "/lib/python" python-version
2894 "/site-packages"))
2895 '("python-scipy"
2896 "python-numpy"
2897 "python-matplotlib"))
2898 ":")))
2899 (wrap-program (string-append out "/bin/idr")
2900 `("PYTHONPATH" ":" prefix (,path))))
2901 #t)))))
2902 (inputs
2903 `(("python-scipy" ,python-scipy)
2904 ("python-numpy" ,python-numpy)
2905 ("python-matplotlib" ,python-matplotlib)))
2906 (native-inputs
f3b98f4f 2907 `(("python-cython" ,python-cython)))
c4325f62
RW		 2908 (home-page "https://github.com/nboley/idr")
2909 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
2910 (description
2911 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
2912to measure the reproducibility of findings identified from replicate
2913experiments and provide highly stable thresholds based on reproducibility.")
2914 (license license:gpl3+)))
2915
43c565d2
RW		 2916(define-public jellyfish
2917 (package
2918 (name "jellyfish")
2919 (version "2.2.4")
2920 (source (origin
2921 (method url-fetch)
2922 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
2923 "releases/download/v" version
2924 "/jellyfish-" version ".tar.gz"))
2925 (sha256
2926 (base32
2927 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
2928 (build-system gnu-build-system)
2929 (outputs '("out" ;for library
2930 "ruby" ;for Ruby bindings
2931 "python")) ;for Python bindings
2932 (arguments
2933 `(#:configure-flags
2934 (list (string-append "--enable-ruby-binding="
2935 (assoc-ref %outputs "ruby"))
2936 (string-append "--enable-python-binding="
2937 (assoc-ref %outputs "python")))
2938 #:phases
2939 (modify-phases %standard-phases
2940 (add-before 'check 'set-SHELL-variable
2941 (lambda _
2942 ;; generator_manager.hpp either uses /bin/sh or $SHELL
2943 ;; to run tests.
2944 (setenv "SHELL" (which "bash"))
2945 #t)))))
2946 (native-inputs
2947 `(("bc" ,bc)
2948 ("time" ,time)
2949 ("ruby" ,ruby)
2950 ("python" ,python-2)))
2951 (synopsis "Tool for fast counting of k-mers in DNA")
2952 (description
2953 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
2954DNA. A k-mer is a substring of length k, and counting the occurrences of all
2955such substrings is a central step in many analyses of DNA sequence. Jellyfish
2956is a command-line program that reads FASTA and multi-FASTA files containing
2957DNA sequences. It outputs its k-mer counts in a binary format, which can be
2958translated into a human-readable text format using the @code{jellyfish dump}
2959command, or queried for specific k-mers with @code{jellyfish query}.")
2960 (home-page "http://www.genome.umd.edu/jellyfish.html")
6e8faf77
EF		 2961 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
2962 (supported-systems '("x86_64-linux"))
43c565d2
RW		 2963 ;; The combined work is published under the GPLv3 or later. Individual
2964 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
2965 (license (list license:gpl3+ license:expat))))
2966
94ff3157
BW		 2967(define-public khmer
2968 (package
2969 (name "khmer")
2970 (version "2.0")
2971 (source
2972 (origin
2973 (method url-fetch)
2974 (uri (pypi-uri "khmer" version))
2975 (sha256
2976 (base32
2977 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
2978 (patches (search-patches "khmer-use-libraries.patch"))))
2979 (build-system python-build-system)
2980 (arguments
2981 `(#:phases
2982 (modify-phases %standard-phases
2983 (add-after 'unpack 'set-paths
2984 (lambda* (#:key inputs outputs #:allow-other-keys)
2985 ;; Delete bundled libraries.
2986 (delete-file-recursively "third-party/zlib")
2987 (delete-file-recursively "third-party/bzip2")
2988 ;; Replace bundled seqan.
2989 (let* ((seqan-all "third-party/seqan")
2990 (seqan-include (string-append
2991 seqan-all "/core/include")))
2992 (delete-file-recursively seqan-all)
2993 (copy-recursively (string-append (assoc-ref inputs "seqan")
2994 "/include/seqan")
2995 (string-append seqan-include "/seqan")))
2996 ;; We do not replace the bundled MurmurHash as the canonical
2997 ;; repository for this code 'SMHasher' is unsuitable for
2998 ;; providing a library. See
2999 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3000 #t))
3001 (add-after 'unpack 'set-cc
3002 (lambda _
3003 (setenv "CC" "gcc")
3004 #t))
3005 ;; It is simpler to test after installation.
3006 (delete 'check)
3007 (add-after 'install 'post-install-check
3008 (lambda* (#:key inputs outputs #:allow-other-keys)
3009 (let ((out (assoc-ref outputs "out")))
3010 (setenv "PATH"
3011 (string-append
3012 (getenv "PATH")
3013 ":"
3014 (assoc-ref outputs "out")
3015 "/bin"))
3016 (setenv "PYTHONPATH"
3017 (string-append
3018 (getenv "PYTHONPATH")
3019 ":"
3020 out
3021 "/lib/python"
3022 (string-take (string-take-right
3023 (assoc-ref inputs "python") 5) 3)
3024 "/site-packages"))
3025 (with-directory-excursion "build"
3026 (zero? (system* "nosetests" "khmer" "--attr"
3027 "!known_failing")))))))))
3028 (native-inputs
3029 `(("seqan" ,seqan)
3030 ("python-nose" ,python-nose)))
3031 (inputs
3032 `(("zlib" ,zlib)
3033 ("bzip2" ,bzip2)
3034 ("python-screed" ,python-screed)
3035 ("python-bz2file" ,python-bz2file)))
3036 (home-page "https://khmer.readthedocs.org/")
3037 (synopsis "K-mer counting, filtering and graph traversal library")
3038 (description "The khmer software is a set of command-line tools for
3039working with DNA shotgun sequencing data from genomes, transcriptomes,
3040metagenomes and single cells. Khmer can make de novo assemblies faster, and
3041sometimes better. Khmer can also identify and fix problems with shotgun
3042data.")
8157af2e
EF		 3043 ;; When building on i686, armhf and mips64el, we get the following error:
3044 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3045 (supported-systems '("x86_64-linux"))
94ff3157
BW		 3046 (license license:bsd-3)))
3047
d57e6d0f
RW		 3048(define-public macs
3049 (package
3050 (name "macs")
0d0bcaa0 3051 (version "2.1.0.20151222")
d57e6d0f
RW		 3052 (source (origin
3053 (method url-fetch)
43ec07f1 3054 (uri (pypi-uri "MACS2" version))
d57e6d0f
RW		 3055 (sha256
3056 (base32
0d0bcaa0 3057 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
d57e6d0f
RW		 3058 (build-system python-build-system)
3059 (arguments
3060 `(#:python ,python-2 ; only compatible with Python 2.7
3061 #:tests? #f)) ; no test target
3062 (inputs
3063 `(("python-numpy" ,python2-numpy)))
d57e6d0f
RW		 3064 (home-page "http://github.com/taoliu/MACS/")
3065 (synopsis "Model based analysis for ChIP-Seq data")
3066 (description
3067 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3068identifying transcript factor binding sites named Model-based Analysis of
3069ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3070the significance of enriched ChIP regions and it improves the spatial
3071resolution of binding sites through combining the information of both
3072sequencing tag position and orientation.")
3073 (license license:bsd-3)))
3074
41ddebdd
BW		 3075(define-public mafft
3076 (package
3077 (name "mafft")
71461f88 3078 (version "7.305")
41ddebdd
BW		 3079 (source (origin
3080 (method url-fetch)
3081 (uri (string-append
3082 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3083 "-without-extensions-src.tgz"))
3084 (file-name (string-append name "-" version ".tgz"))
3085 (sha256
3086 (base32
71461f88 3087 "0ziim7g58n3z8gppsa713f5fxprl60ldj3xck186z0n9dpp06i8r"))))
41ddebdd
BW		 3088 (build-system gnu-build-system)
3089 (arguments
3090 `(#:tests? #f ; no automated tests, though there are tests in the read me
3091 #:make-flags (let ((out (assoc-ref %outputs "out")))
3092 (list (string-append "PREFIX=" out)
3093 (string-append "BINDIR="
3094 (string-append out "/bin"))))
3095 #:phases
3096 (modify-phases %standard-phases
3097 (add-after 'unpack 'enter-dir
101e8f71 3098 (lambda _ (chdir "core") #t))
41ddebdd 3099 (add-after 'enter-dir 'patch-makefile
101e8f71
BW		 3100 (lambda _
3101 ;; on advice from the MAFFT authors, there is no need to
3102 ;; distribute mafft-profile, mafft-distance, or
3103 ;; mafft-homologs.rb as they are too "specialised".
3104 (substitute* "Makefile"
3105 ;; remove mafft-homologs.rb from SCRIPTS
3106 (("^SCRIPTS = mafft mafft-homologs.rb")
3107 "SCRIPTS = mafft")
3108 ;; remove mafft-homologs from MANPAGES
3109 (("^MANPAGES = mafft.1 mafft-homologs.1")
3110 "MANPAGES = mafft.1")
3111 ;; remove mafft-distance from PROGS
3112 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3113 "PROGS = dvtditr dndfast7 dndblast sextet5")
3114 ;; remove mafft-profile from PROGS
3115 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3116 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3117 (("^rm -f mafft-profile mafft-profile.exe") "#")
3118 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3119 ;; do not install MAN pages in libexec folder
3120 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
41ddebdd 3121\\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
101e8f71 3122 #t))
02f35bb5
BW		 3123 (add-after 'enter-dir 'patch-paths
3124 (lambda* (#:key inputs #:allow-other-keys)
3125 (substitute* '("pairash.c"
3126 "mafft.tmpl")
3127 (("perl") (which "perl"))
3128 (("([\"`| ])awk" _ prefix)
3129 (string-append prefix (which "awk")))
3130 (("grep") (which "grep")))
3131 #t))
101e8f71
BW		 3132 (delete 'configure)
3133 (add-after 'install 'wrap-programs
3134 (lambda* (#:key outputs #:allow-other-keys)
3135 (let* ((out (assoc-ref outputs "out"))
3136 (bin (string-append out "/bin"))
3137 (path (string-append
3138 (assoc-ref %build-inputs "coreutils") "/bin:")))
3139 (for-each (lambda (file)
3140 (wrap-program file
3141 `("PATH" ":" prefix (,path))))
3142 (find-files bin)))
3143 #t)))))
41ddebdd 3144 (inputs
02f35bb5 3145 `(("perl" ,perl)
71461f88 3146 ("ruby" ,ruby)
02f35bb5 3147 ("gawk" ,gawk)
101e8f71
BW		 3148 ("grep" ,grep)
3149 ("coreutils" ,coreutils)))
41ddebdd
BW		 3150 (home-page "http://mafft.cbrc.jp/alignment/software/")
3151 (synopsis "Multiple sequence alignment program")
3152 (description
3153 "MAFFT offers a range of multiple alignment methods for nucleotide and
3154protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3155of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3156sequences).")
3157 (license (license:non-copyleft
3158 "http://mafft.cbrc.jp/alignment/software/license.txt"
3159 "BSD-3 with different formatting"))))
8fd790eb 3160
84be3b99
MB		 3161(define-public mash
3162 (package
3163 (name "mash")
3164 (version "1.1.1")
3165 (source (origin
3166 (method url-fetch)
3167 (uri (string-append
3168 "https://github.com/marbl/mash/archive/v"
3169 version ".tar.gz"))
3170 (file-name (string-append name "-" version ".tar.gz"))
3171 (sha256
3172 (base32
3173 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3174 (modules '((guix build utils)))
3175 (snippet
3176 ;; Delete bundled kseq.
3177 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3178 '(delete-file "src/mash/kseq.h"))))
3179 (build-system gnu-build-system)
3180 (arguments
3181 `(#:tests? #f ; No tests.
3182 #:configure-flags
3183 (list
3184 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3185 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3186 #:make-flags (list "CC=gcc")
3187 #:phases
3188 (modify-phases %standard-phases
3189 (add-after 'unpack 'fix-includes
3190 (lambda _
3191 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3192 (("^#include \"kseq\\.h\"")
3193 "#include \"htslib/kseq.h\""))
3194 #t))
3195 (add-before 'configure 'autoconf
3196 (lambda _ (zero? (system* "autoconf")))))))
3197 (native-inputs
3198 `(("autoconf" ,autoconf)
3199 ;; Capnproto and htslib are statically embedded in the final
3200 ;; application. Therefore we also list their licenses, below.
3201 ("capnproto" ,capnproto)
3202 ("htslib" ,htslib)))
3203 (inputs
3204 `(("gsl" ,gsl)
3205 ("zlib" ,zlib)))
3206 (supported-systems '("x86_64-linux"))
3207 (home-page "https://mash.readthedocs.io")
3208 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3209 (description "Mash is a fast sequence distance estimator that uses the
3210MinHash algorithm and is designed to work with genomes and metagenomes in the
3211form of assemblies or reads.")
3212 (license (list license:bsd-3 ; Mash
3213 license:expat ; HTSlib and capnproto
3214 license:public-domain ; MurmurHash 3
3215 license:cpl1.0)))) ; Open Bloom Filter
3216
8fd790eb 3217(define-public metabat
2c3eb4b8
BW		 3218 ;; We package from a git commit because compilation of the released version
3219 ;; fails.
3220 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3221 (package
3222 (name "metabat")
3223 (version (string-append "0.32.4-1." (string-take commit 8)))
3224 (source
3225 (origin
3226 (method git-fetch)
3227 (uri (git-reference
3228 (url "https://bitbucket.org/berkeleylab/metabat.git")
3229 (commit commit)))
3230 (file-name (string-append name "-" version))
3231 (sha256
3232 (base32
3233 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3234 (patches (search-patches "metabat-remove-compilation-date.patch"))))
8fd790eb
BW		 3235 (build-system gnu-build-system)
3236 (arguments
3237 `(#:phases
3238 (modify-phases %standard-phases
3239 (add-after 'unpack 'fix-includes
45469ebe
BW		 3240 (lambda _
3241 (substitute* "src/BamUtils.h"
3242 (("^#include \"bam/bam\\.h\"")
3243 "#include \"samtools/bam.h\"")
3244 (("^#include \"bam/sam\\.h\"")
3245 "#include \"samtools/sam.h\""))
3246 (substitute* "src/KseqReader.h"
3247 (("^#include \"bam/kseq\\.h\"")
3248 "#include \"htslib/kseq.h\""))
3249 #t))
8fd790eb 3250 (add-after 'unpack 'fix-scons
45469ebe
BW		 3251 (lambda* (#:key inputs #:allow-other-keys)
3252 (substitute* "SConstruct"
3253 (("^htslib_dir = 'samtools'")
3254 (string-append "hitslib_dir = '"
3255 (assoc-ref inputs "htslib")
3256 "'"))
3257 (("^samtools_dir = 'samtools'")
3258 (string-append "samtools_dir = '"
3259 (assoc-ref inputs "htslib")
3260 "'"))
3261 (("^findStaticOrShared\\('bam', hts_lib")
3262 (string-append "findStaticOrShared('bam', '"
3263 (assoc-ref inputs "samtools")
3264 "/lib'"))
3265 ;; Do not distribute README.
3266 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3267 #t))
8fd790eb
BW		 3268 (delete 'configure)
3269 (replace 'build
3270 (lambda* (#:key inputs outputs #:allow-other-keys)
3271 (mkdir (assoc-ref outputs "out"))
3272 (zero? (system* "scons"
3273 (string-append
3274 "PREFIX="
3275 (assoc-ref outputs "out"))
8fd790eb
BW		 3276 (string-append
3277 "BOOST_ROOT="
3278 (assoc-ref inputs "boost"))
3279 "install"))))
45469ebe 3280 ;; Check and install are carried out during build phase.
8fd790eb
BW		 3281 (delete 'check)
3282 (delete 'install))))
3283 (inputs
3284 `(("zlib" ,zlib)
3285 ("perl" ,perl)
3286 ("samtools" ,samtools)
3287 ("htslib" ,htslib)
3288 ("boost" ,boost)))
3289 (native-inputs
3290 `(("scons" ,scons)))
3291 (home-page "https://bitbucket.org/berkeleylab/metabat")
3292 (synopsis
3293 "Reconstruction of single genomes from complex microbial communities")
3294 (description
3295 "Grouping large genomic fragments assembled from shotgun metagenomic
3296sequences to deconvolute complex microbial communities, or metagenome binning,
3297enables the study of individual organisms and their interactions. MetaBAT is
3298an automated metagenome binning software, which integrates empirical
3299probabilistic distances of genome abundance and tetranucleotide frequency.")
3300 (license (license:non-copyleft "file://license.txt"
2c3eb4b8 3301 "See license.txt in the distribution.")))))
8fd790eb 3302
318c0aee
MB		 3303(define-public minced
3304 (package
3305 (name "minced")
3306 (version "0.2.0")
3307 (source (origin
3308 (method url-fetch)
3309 (uri (string-append
3310 "https://github.com/ctSkennerton/minced/archive/"
3311 version ".tar.gz"))
3312 (file-name (string-append name "-" version ".tar.gz"))
3313 (sha256
3314 (base32
3315 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3316 (build-system gnu-build-system)
3317 (arguments
3318 `(#:test-target "test"
3319 #:phases
3320 (modify-phases %standard-phases
3321 (delete 'configure)
3322 (add-before 'check 'fix-test
3323 (lambda _
3324 ;; Fix test for latest version.
3325 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3326 (("minced:0.1.6") "minced:0.2.0"))
3327 #t))
3328 (replace 'install ; No install target.
3329 (lambda* (#:key inputs outputs #:allow-other-keys)
3330 (let* ((out (assoc-ref outputs "out"))
3331 (bin (string-append out "/bin"))
3332 (wrapper (string-append bin "/minced")))
3333 ;; Minced comes with a wrapper script that tries to figure out where
3334 ;; it is located before running the JAR. Since these paths are known
3335 ;; to us, we build our own wrapper to avoid coreutils dependency.
3336 (install-file "minced.jar" bin)
3337 (with-output-to-file wrapper
3338 (lambda _
3339 (display
3340 (string-append
3341 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3342 (assoc-ref inputs "jre") "/bin/java -jar "
3343 bin "/minced.jar \"$@\"\n"))))
3344 (chmod wrapper #o555)))))))
3345 (native-inputs
3346 `(("jdk" ,icedtea "jdk")))
3347 (inputs
3348 `(("bash" ,bash)
3349 ("jre" ,icedtea "out")))
3350 (home-page "https://github.com/ctSkennerton/minced")
3351 (synopsis "Mining CRISPRs in Environmental Datasets")
3352 (description
3353 "MinCED is a program to find Clustered Regularly Interspaced Short
3354Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3355unassembled metagenomic reads, but is mainly designed for full genomes and
3356assembled metagenomic sequence.")
3357 (license license:gpl3+)))
3358
ddd82e0e
RW		 3359(define-public miso
3360 (package
3361 (name "miso")
3362 (version "0.5.3")
3363 (source (origin
3364 (method url-fetch)
3365 (uri (string-append
86517de6 3366 "https://pypi.python.org/packages/source/m/misopy/misopy-"
ddd82e0e
RW		 3367 version ".tar.gz"))
3368 (sha256
3369 (base32
3370 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3371 (modules '((guix build utils)))
ddd82e0e
RW		 3372 (snippet
3373 '(substitute* "setup.py"
0ec8b206
RW		 3374 ;; Use setuptools, or else the executables are not
3375 ;; installed.
3376 (("distutils.core") "setuptools")
3377 ;; use "gcc" instead of "cc" for compilation
ddd82e0e
RW		 3378 (("^defines")
3379 "cc.set_executables(
3380compiler='gcc',
3381compiler_so='gcc',
3382linker_exe='gcc',
3383linker_so='gcc -shared'); defines")))))
3384 (build-system python-build-system)
3385 (arguments
3386 `(#:python ,python-2 ; only Python 2 is supported
3387 #:tests? #f)) ; no "test" target
3388 (inputs
3389 `(("samtools" ,samtools)
3390 ("python-numpy" ,python2-numpy)
3391 ("python-pysam" ,python2-pysam)
3392 ("python-scipy" ,python2-scipy)
3393 ("python-matplotlib" ,python2-matplotlib)))
3394 (native-inputs
f3b98f4f
HG		 3395 `(("python-mock" ,python2-mock) ;for tests
3396 ("python-pytz" ,python2-pytz))) ;for tests
ddd82e0e
RW		 3397 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3398 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3399 (description
3400 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3401the expression level of alternatively spliced genes from RNA-Seq data, and
3402identifies differentially regulated isoforms or exons across samples. By
3403modeling the generative process by which reads are produced from isoforms in
3404RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3405that a read originated from a particular isoform.")
3406 (license license:gpl2)))
3407
324efb88
BW		 3408(define-public muscle
3409 (package
3410 (name "muscle")
3411 (version "3.8.1551")
3412 (source (origin
3413 (method url-fetch/tarbomb)
3414 (file-name (string-append name "-" version))
3415 (uri (string-append
3416 "http://www.drive5.com/muscle/muscle_src_"
3417 version ".tar.gz"))
3418 (sha256
3419 (base32
3420 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3421 (build-system gnu-build-system)
3422 (arguments
3423 `(#:make-flags (list "LDLIBS = -lm")
3424 #:phases
3425 (modify-phases %standard-phases
3426 (delete 'configure)
3427 (replace 'check
3428 ;; There are no tests, so just test if it runs.
3429 (lambda _ (zero? (system* "./muscle" "-version"))))
3430 (replace 'install
3431 (lambda* (#:key outputs #:allow-other-keys)
3432 (let* ((out (assoc-ref outputs "out"))
3433 (bin (string-append out "/bin")))
3434 (install-file "muscle" bin)))))))
3435 (home-page "http://www.drive5.com/muscle")
3436 (synopsis "Multiple sequence alignment program")
3437 (description
3438 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3439program for nucleotide and protein sequences.")
3440 ;; License information found in 'muscle -h' and usage.cpp.
3441 (license license:public-domain)))
3442
99268755
BW		 3443(define-public newick-utils
3444 ;; There are no recent releases so we package from git.
3445 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3446 (package
3447 (name "newick-utils")
3448 (version (string-append "1.6-1." (string-take commit 8)))
3449 (source (origin
3450 (method git-fetch)
3451 (uri (git-reference
3452 (url "https://github.com/tjunier/newick_utils.git")
3453 (commit commit)))
3454 (file-name (string-append name "-" version "-checkout"))
3455 (sha256
3456 (base32
3457 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3458 (build-system gnu-build-system)
3459 (arguments
3460 `(#:phases
3461 (modify-phases %standard-phases
3462 (add-after 'unpack 'autoconf
3463 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3464 (inputs
3465 ;; XXX: TODO: Enable Lua and Guile bindings.
3466 ;; https://github.com/tjunier/newick_utils/issues/13
3467 `(("libxml2" ,libxml2)
3468 ("flex" ,flex)
3469 ("bison" ,bison)))
3470 (native-inputs
3471 `(("autoconf" ,autoconf)
3472 ("automake" ,automake)
3473 ("libtool" ,libtool)))
3474 (synopsis "Programs for working with newick format phylogenetic trees")
3475 (description
3476 "Newick-utils is a suite of utilities for processing phylogenetic trees
3477in Newick format. Functions include re-rooting, extracting subtrees,
3478trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3479 (home-page "https://github.com/tjunier/newick_utils")
3480 (license license:bsd-3))))
3481
1e44cf8b
BW		 3482(define-public orfm
3483 (package
3484 (name "orfm")
ced1c496 3485 (version "0.6.1")
1e44cf8b
BW		 3486 (source (origin
3487 (method url-fetch)
3488 (uri (string-append
3489 "https://github.com/wwood/OrfM/releases/download/v"
3490 version "/orfm-" version ".tar.gz"))
3491 (sha256
3492 (base32
ced1c496 3493 "19hwp13n82isdvk16710l9m35cmzf0q3fsrcn3r8c5r67biiz39s"))))
1e44cf8b
BW		 3494 (build-system gnu-build-system)
3495 (inputs `(("zlib" ,zlib)))
6b6f7d6a
BW		 3496 (native-inputs
3497 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3498 ("ruby-rspec" ,ruby-rspec)
3499 ("ruby" ,ruby)))
1e44cf8b
BW		 3500 (synopsis "Simple and not slow open reading frame (ORF) caller")
3501 (description
6b6f7d6a 3502 "An ORF caller finds stretches of DNA that, when translated, are not
1e44cf8b
BW		 3503interrupted by stop codons. OrfM finds and prints these ORFs.")
3504 (home-page "https://github.com/wwood/OrfM")
3505 (license license:lgpl3+)))
3506
19ee9201
RW		 3507(define-public python2-pbcore
3508 (package
3509 (name "python2-pbcore")
e301bfc8 3510 (version "1.2.10")
19ee9201
RW		 3511 (source (origin
3512 (method url-fetch)
ddb83129 3513 (uri (pypi-uri "pbcore" version))
19ee9201
RW		 3514 (sha256
3515 (base32
e301bfc8 3516 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
19ee9201
RW		 3517 (build-system python-build-system)
3518 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
de5bc890 3519 (propagated-inputs
19ee9201
RW		 3520 `(("python-cython" ,python2-cython)
3521 ("python-numpy" ,python2-numpy)
3522 ("python-pysam" ,python2-pysam)
3523 ("python-h5py" ,python2-h5py)))
3524 (native-inputs
de5bc890
HG		 3525 `(("python-nose" ,python2-nose)
3526 ("python-sphinx" ,python2-sphinx)
3527 ("python-pyxb" ,python2-pyxb)))
19ee9201
RW		 3528 (home-page "http://pacificbiosciences.github.io/pbcore/")
3529 (synopsis "Library for reading and writing PacBio data files")
3530 (description
3531 "The pbcore package provides Python APIs for interacting with PacBio data
3532files and writing bioinformatics applications.")
3533 (license license:bsd-3)))
3534
c61fe02c
RW		 3535(define-public python2-warpedlmm
3536 (package
3537 (name "python2-warpedlmm")
3538 (version "0.21")
3539 (source
3540 (origin
3541 (method url-fetch)
3542 (uri (string-append
3543 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3544 version ".zip"))
3545 (sha256
3546 (base32
3547 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3548 (build-system python-build-system)
3549 (arguments
54c85e12 3550 `(#:python ,python-2)) ; requires Python 2.7
c61fe02c
RW		 3551 (propagated-inputs
3552 `(("python-scipy" ,python2-scipy)
3553 ("python-numpy" ,python2-numpy)
3554 ("python-matplotlib" ,python2-matplotlib)
3555 ("python-fastlmm" ,python2-fastlmm)
3556 ("python-pandas" ,python2-pandas)
3557 ("python-pysnptools" ,python2-pysnptools)))
3558 (native-inputs
f3b98f4f 3559 `(("python-mock" ,python2-mock)
c61fe02c
RW		 3560 ("python-nose" ,python2-nose)
3561 ("unzip" ,unzip)))
3562 (home-page "https://github.com/PMBio/warpedLMM")
3563 (synopsis "Implementation of warped linear mixed models")
3564 (description
3565 "WarpedLMM is a Python implementation of the warped linear mixed model,
3566which automatically learns an optimal warping function (or transformation) for
3567the phenotype as it models the data.")
3568 (license license:asl2.0)))
3569
2c16316e 3570(define-public pbtranscript-tofu
698bd297 3571 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
2c16316e
RW		 3572 (package
3573 (name "pbtranscript-tofu")
698bd297 3574 (version (string-append "2.2.3." (string-take commit 7)))
2c16316e
RW		 3575 (source (origin
3576 (method git-fetch)
3577 (uri (git-reference
3578 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3579 (commit commit)))
9a067efd 3580 (file-name (string-append name "-" version "-checkout"))
2c16316e
RW		 3581 (sha256
3582 (base32
9a067efd
RW		 3583 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3584 (modules '((guix build utils)))
3585 (snippet
3586 '(begin
3587 ;; remove bundled Cython sources
3588 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3589 #t))))
2c16316e
RW		 3590 (build-system python-build-system)
3591 (arguments
3592 `(#:python ,python-2
2c16316e 3593 #:phases
9a067efd
RW		 3594 (modify-phases %standard-phases
3595 (add-after 'unpack 'enter-directory
3596 (lambda _
3597 (chdir "pbtranscript-tofu/pbtranscript/")
3598 #t))
3599 ;; With setuptools version 18.0 and later this setup.py hack causes
3600 ;; a build error, so we disable it.
3601 (add-after 'enter-directory 'patch-setuppy
3602 (lambda _
3603 (substitute* "setup.py"
3604 (("if 'setuptools.extension' in sys.modules:")
3605 "if False:"))
3606 #t)))))
2c16316e 3607 (inputs
9a067efd 3608 `(("python-numpy" ,python2-numpy)
2c16316e 3609 ("python-bx-python" ,python2-bx-python)
c5372108
RW		 3610 ("python-networkx" ,python2-networkx)
3611 ("python-scipy" ,python2-scipy)
9a067efd
RW		 3612 ("python-pbcore" ,python2-pbcore)
3613 ("python-h5py" ,python2-h5py)))
2c16316e 3614 (native-inputs
9a067efd 3615 `(("python-cython" ,python2-cython)
f3b98f4f 3616 ("python-nose" ,python2-nose)))
2c16316e
RW		 3617 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3618 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3619 (description
3620 "pbtranscript-tofu contains scripts to analyze transcriptome data
3621generated using the PacBio Iso-Seq protocol.")
3622 (license license:bsd-3))))
3623
024130d2
BW		 3624(define-public prank
3625 (package
3626 (name "prank")
3627 (version "150803")
3628 (source (origin
3629 (method url-fetch)
3630 (uri (string-append
3631 "http://wasabiapp.org/download/prank/prank.source."
3632 version ".tgz"))
3633 (sha256
3634 (base32
3635 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3636 (build-system gnu-build-system)
3637 (arguments
3638 `(#:phases
3639 (modify-phases %standard-phases
3640 (add-after 'unpack 'enter-src-dir
3641 (lambda _
3642 (chdir "src")
3643 #t))
62d00095
EF		 3644 (add-after 'unpack 'remove-m64-flag
3645 ;; Prank will build with the correct 'bit-ness' without this flag
3646 ;; and this allows building on 32-bit machines.
3647 (lambda _ (substitute* "src/Makefile"
3648 (("-m64") ""))
3649 #t))
024130d2
BW		 3650 (delete 'configure)
3651 (replace 'install
3652 (lambda* (#:key outputs #:allow-other-keys)
3653 (let* ((out (assoc-ref outputs "out"))
3654 (bin (string-append out "/bin"))
3655 (man (string-append out "/share/man/man1"))
3656 (path (string-append
3657 (assoc-ref %build-inputs "mafft") "/bin:"
3658 (assoc-ref %build-inputs "exonerate") "/bin:"
3659 (assoc-ref %build-inputs "bppsuite") "/bin")))
3660 (install-file "prank" bin)
3661 (wrap-program (string-append bin "/prank")
3662 `("PATH" ":" prefix (,path)))
3663 (install-file "prank.1" man))
3664 #t)))))
3665 (inputs
3666 `(("mafft" ,mafft)
3667 ("exonerate" ,exonerate)
3668 ("bppsuite" ,bppsuite)))
3669 (home-page "http://wasabiapp.org/software/prank/")
3670 (synopsis "Probabilistic multiple sequence alignment program")
3671 (description
3672 "PRANK is a probabilistic multiple sequence alignment program for DNA,
3673codon and amino-acid sequences. It is based on a novel algorithm that treats
3674insertions correctly and avoids over-estimation of the number of deletion
3675events. In addition, PRANK borrows ideas from maximum likelihood methods used
3676in phylogenetics and correctly takes into account the evolutionary distances
3677between sequences. Lastly, PRANK allows for defining a potential structure
3678for sequences to be aligned and then, simultaneously with the alignment,
3679predicts the locations of structural units in the sequences.")
3680 (license license:gpl2+)))
3681
31a9d653
BW		 3682(define-public proteinortho
3683 (package
3684 (name "proteinortho")
3685 (version "5.15")
3686 (source
3687 (origin
3688 (method url-fetch)
3689 (uri
3690 (string-append
3691 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
3692 version "_src.tar.gz"))
3693 (sha256
3694 (base32
3695 "05wacnnbx56avpcwhzlcf6b7s77swcpv3qnwz5sh1z54i51gg2ki"))))
3696 (build-system gnu-build-system)
3697 (arguments
3698 `(#:test-target "test"
3699 #:phases
3700 (modify-phases %standard-phases
3701 (replace 'configure
3702 ;; There is no configure script, so we modify the Makefile directly.
3703 (lambda* (#:key outputs #:allow-other-keys)
3704 (substitute* "Makefile"
3705 (("INSTALLDIR=.*")
3706 (string-append
3707 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
3708 #t))
3709 (add-before 'install 'make-install-directory
3710 ;; The install directory is not created during 'make install'.
3711 (lambda* (#:key outputs #:allow-other-keys)
3712 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3713 #t))
3714 (add-after 'install 'wrap-programs
3715 (lambda* (#:key inputs outputs #:allow-other-keys)
3716 (let* ((path (getenv "PATH"))
3717 (out (assoc-ref outputs "out"))
3718 (binary (string-append out "/bin/proteinortho5.pl")))
3719 (wrap-program binary `("PATH" ":" prefix (,path))))
3720 #t)))))
3721 (inputs
3722 `(("perl" ,perl)
3723 ("python" ,python-2)
3724 ("blast+" ,blast+)))
3725 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
3726 (synopsis "Detect orthologous genes across species")
3727 (description
3728 "Proteinortho is a tool to detect orthologous genes across different
3729species. For doing so, it compares similarities of given gene sequences and
3730clusters them to find significant groups. The algorithm was designed to handle
3731large-scale data and can be applied to hundreds of species at once.")
3732 (license license:gpl2+)))
3733
846e3409
RW		 3734(define-public pyicoteo
3735 (package
3736 (name "pyicoteo")
3737 (version "2.0.7")
3738 (source
3739 (origin
3740 (method url-fetch)
3741 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
3742 "pyicoteo/get/v" version ".tar.bz2"))
3743 (file-name (string-append name "-" version ".tar.bz2"))
3744 (sha256
3745 (base32
3746 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
3747 (build-system python-build-system)
3748 (arguments
3749 `(#:python ,python-2 ; does not work with Python 3
3750 #:tests? #f)) ; there are no tests
3751 (inputs
3752 `(("python2-matplotlib" ,python2-matplotlib)))
3753 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
3754 (synopsis "Analyze high-throughput genetic sequencing data")
3755 (description
3756 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
3757sequencing data. It works with genomic coordinates. There are currently six
3758different command-line tools:
3759
3760@enumerate
3761@item pyicoregion: for generating exploratory regions automatically;
3762@item pyicoenrich: for differential enrichment between two conditions;
3763@item pyicoclip: for calling CLIP-Seq peaks without a control;
3764@item pyicos: for genomic coordinates manipulation;
3765@item pyicoller: for peak calling on punctuated ChIP-Seq;
3766@item pyicount: to count how many reads from N experiment files overlap in a
3767 region file;
3768@item pyicotrocol: to combine operations from pyicoteo.
3769@end enumerate\n")
3770 (license license:gpl3+)))
3771
af860475
BW		 3772(define-public prodigal
3773 (package
3774 (name "prodigal")
e70f7a23 3775 (version "2.6.3")
af860475
BW		 3776 (source (origin
3777 (method url-fetch)
3778 (uri (string-append
3779 "https://github.com/hyattpd/Prodigal/archive/v"
3780 version ".tar.gz"))
3781 (file-name (string-append name "-" version ".tar.gz"))
3782 (sha256
3783 (base32
e70f7a23 3784 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
af860475
BW		 3785 (build-system gnu-build-system)
3786 (arguments
3787 `(#:tests? #f ;no check target
3788 #:make-flags (list (string-append "INSTALLDIR="
3789 (assoc-ref %outputs "out")
3790 "/bin"))
3791 #:phases
3792 (modify-phases %standard-phases
3793 (delete 'configure))))
3794 (home-page "http://prodigal.ornl.gov")
3795 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
3796 (description
3797 "Prodigal runs smoothly on finished genomes, draft genomes, and
3798metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
3799format. It runs quickly, in an unsupervised fashion, handles gaps, handles
3800partial genes, and identifies translation initiation sites.")
3801 (license license:gpl3+)))
608dd932 3802
ceb62d54
BW		 3803(define-public roary
3804 (package
3805 (name "roary")
5e0a0f42 3806 (version "3.7.0")
ceb62d54
BW		 3807 (source
3808 (origin
3809 (method url-fetch)
3810 (uri (string-append
3811 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
3812 version ".tar.gz"))
3813 (sha256
3814 (base32
5e0a0f42 3815 "0x2hpb3nfsc6x2nq1788w0fhqfzc7cn2dp4xwyva9m3k6xlz0m43"))))
ceb62d54
BW		 3816 (build-system perl-build-system)
3817 (arguments
3818 `(#:phases
3819 (modify-phases %standard-phases
3820 (delete 'configure)
3821 (delete 'build)
3822 (replace 'check
3823 (lambda _
3824 ;; The tests are not run by default, so we run each test file
3825 ;; directly.
3826 (setenv "PATH" (string-append (getcwd) "/bin" ":"
3827 (getenv "PATH")))
3828 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
3829 (getenv "PERL5LIB")))
3830 (zero? (length (filter (lambda (file)
3831 (display file)(display "\n")
3832 (not (zero? (system* "perl" file))))
3833 (find-files "t" ".*\\.t$"))))))
3834 (replace 'install
3835 ;; There is no 'install' target in the Makefile.
3836 (lambda* (#:key outputs #:allow-other-keys)
3837 (let* ((out (assoc-ref outputs "out"))
3838 (bin (string-append out "/bin"))
3839 (perl (string-append out "/lib/perl5/site_perl"))
3840 (roary-plots "contrib/roary_plots"))
3841 (mkdir-p bin)
3842 (mkdir-p perl)
3843 (copy-recursively "bin" bin)
3844 (copy-recursively "lib" perl)
3845 #t)))
3846 (add-after 'install 'wrap-programs
3847 (lambda* (#:key inputs outputs #:allow-other-keys)
3848 (let* ((out (assoc-ref outputs "out"))
3849 (perl5lib (getenv "PERL5LIB"))
3850 (path (getenv "PATH")))
3851 (for-each (lambda (prog)
3852 (let ((binary (string-append out "/" prog)))
3853 (wrap-program binary
3854 `("PERL5LIB" ":" prefix
3855 (,(string-append perl5lib ":" out
3856 "/lib/perl5/site_perl"))))
3857 (wrap-program binary
3858 `("PATH" ":" prefix
3859 (,(string-append path ":" out "/bin"))))))
3860 (find-files "bin" ".*[^R]$"))
3861 (let ((file
3862 (string-append out "/bin/roary-create_pan_genome_plots.R"))
3863 (r-site-lib (getenv "R_LIBS_SITE"))
3864 (coreutils-path
3865 (string-append (assoc-ref inputs "coreutils") "/bin")))
3866 (wrap-program file
3867 `("R_LIBS_SITE" ":" prefix
3868 (,(string-append r-site-lib ":" out "/site-library/"))))
3869 (wrap-program file
3870 `("PATH" ":" prefix
3871 (,(string-append coreutils-path ":" out "/bin"))))))
3872 #t)))))
3873 (native-inputs
3874 `(("perl-env-path" ,perl-env-path)
3875 ("perl-test-files" ,perl-test-files)
3876 ("perl-test-most" ,perl-test-most)
3877 ("perl-test-output" ,perl-test-output)))
3878 (inputs
3879 `(("perl-array-utils" ,perl-array-utils)
3880 ("bioperl" ,bioperl-minimal)
3881 ("perl-exception-class" ,perl-exception-class)
3882 ("perl-file-find-rule" ,perl-file-find-rule)
3883 ("perl-file-grep" ,perl-file-grep)
3884 ("perl-file-slurper" ,perl-file-slurper)
3885 ("perl-file-which" ,perl-file-which)
3886 ("perl-graph" ,perl-graph)
3887 ("perl-graph-readwrite" ,perl-graph-readwrite)
3888 ("perl-log-log4perl" ,perl-log-log4perl)
3889 ("perl-moose" ,perl-moose)
3890 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
3891 ("perl-text-csv" ,perl-text-csv)
3892 ("bedtools" ,bedtools)
3893 ("cd-hit" ,cd-hit)
3894 ("blast+" ,blast+)
3895 ("mcl" ,mcl)
3896 ("parallel" ,parallel)
3897 ("prank" ,prank)
3898 ("mafft" ,mafft)
3899 ("fasttree" ,fasttree)
3900 ("grep" ,grep)
3901 ("sed" ,sed)
3902 ("gawk" ,gawk)
3903 ("r" ,r)
3904 ("r-ggplot2" ,r-ggplot2)
3905 ("coreutils" ,coreutils)))
3906 (home-page "http://sanger-pathogens.github.io/Roary")
3907 (synopsis "High speed stand-alone pan genome pipeline")
3908 (description
3909 "Roary is a high speed stand alone pan genome pipeline, which takes
3910annotated assemblies in GFF3 format (produced by the Prokka program) and
3911calculates the pan genome. Using a standard desktop PC, it can analyse
3912datasets with thousands of samples, without compromising the quality of the
3913results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
3914single processor. Roary is not intended for metagenomics or for comparing
3915extremely diverse sets of genomes.")
3916 (license license:gpl3)))
3917
608dd932
BW		 3918(define-public raxml
3919 (package
3920 (name "raxml")
3921 (version "8.2.9")
3922 (source
3923 (origin
3924 (method url-fetch)
3925 (uri
3926 (string-append
3927 "https://github.com/stamatak/standard-RAxML/archive/v"
3928 version ".tar.gz"))
3929 (file-name (string-append name "-" version ".tar.gz"))
3930 (sha256
3931 (base32
3932 "1pv8p2fy67y21a9y4cm7xpvxqjwz2v4201flfjshdq1p8j52rqf7"))))
3933 (build-system gnu-build-system)
3934 (arguments
3935 `(#:tests? #f ; There are no tests.
3936 ;; Use 'standard' Makefile rather than SSE or AVX ones.
3937 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
3938 #:phases
3939 (modify-phases %standard-phases
3940 (delete 'configure)
3941 (replace 'install
3942 (lambda* (#:key outputs #:allow-other-keys)
3943 (let* ((out (assoc-ref outputs "out"))
3944 (bin (string-append out "/bin"))
3945 (executable "raxmlHPC-HYBRID"))
3946 (install-file executable bin)
3947 (symlink (string-append bin "/" executable) "raxml"))
3948 #t)))))
3949 (inputs
3950 `(("openmpi" ,openmpi)))
3951 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
3952 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
3953 (description
3954 "RAxML is a tool for phylogenetic analysis and post-analysis of large
3955phylogenies.")
3956 (license license:gpl2+)))
af860475 3957
66e3eff1
RW		 3958(define-public rsem
3959 (package
3960 (name "rsem")
3961 (version "1.2.20")
3962 (source
3963 (origin
3964 (method url-fetch)
3965 (uri
3966 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
3967 version ".tar.gz"))
3968 (sha256
3969 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
fc1adab1 3970 (patches (search-patches "rsem-makefile.patch"))
66e3eff1
RW		 3971 (modules '((guix build utils)))
3972 (snippet
3973 '(begin
3974 ;; remove bundled copy of boost
3975 (delete-file-recursively "boost")
3976 #t))))
3977 (build-system gnu-build-system)
3978 (arguments
3979 `(#:tests? #f ;no "check" target
3980 #:phases
3981 (modify-phases %standard-phases
3982 ;; No "configure" script.
3983 ;; Do not build bundled samtools library.
3984 (replace 'configure
3985 (lambda _
3986 (substitute* "Makefile"
3987 (("^all : sam/libbam.a") "all : "))
3988 #t))
3989 (replace 'install
3990 (lambda* (#:key outputs #:allow-other-keys)
3991 (let* ((out (string-append (assoc-ref outputs "out")))
3992 (bin (string-append out "/bin/"))
3993 (perl (string-append out "/lib/perl5/site_perl")))
3994 (mkdir-p bin)
3995 (mkdir-p perl)
3996 (for-each (lambda (file)
3997 (copy-file file
3998 (string-append bin (basename file))))
3999 (find-files "." "rsem-.*"))
4000 (copy-file "rsem_perl_utils.pm"
4001 (string-append perl "/rsem_perl_utils.pm")))
4002 #t))
4003 (add-after
4004 'install 'wrap-program
4005 (lambda* (#:key outputs #:allow-other-keys)
4006 (let ((out (assoc-ref outputs "out")))
4007 (for-each (lambda (prog)
4008 (wrap-program (string-append out "/bin/" prog)
4009 `("PERL5LIB" ":" prefix
4010 (,(string-append out "/lib/perl5/site_perl")))))
4011 '("rsem-plot-transcript-wiggles"
4012 "rsem-calculate-expression"
4013 "rsem-generate-ngvector"
4014 "rsem-run-ebseq"
4015 "rsem-prepare-reference")))
4016 #t)))))
4017 (inputs
4018 `(("boost" ,boost)
4019 ("ncurses" ,ncurses)
4020 ("r" ,r)
4021 ("perl" ,perl)
4022 ("samtools" ,samtools-0.1)
4023 ("zlib" ,zlib)))
4024 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4025 (synopsis "Estimate gene expression levels from RNA-Seq data")
4026 (description
4027 "RSEM is a software package for estimating gene and isoform expression
4028levels from RNA-Seq data. The RSEM package provides a user-friendly
4029interface, supports threads for parallel computation of the EM algorithm,
4030single-end and paired-end read data, quality scores, variable-length reads and
4031RSPD estimation. In addition, it provides posterior mean and 95% credibility
4032interval estimates for expression levels. For visualization, it can generate
4033BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4034 (license license:gpl3+)))
4035
8622a072
RW		 4036(define-public rseqc
4037 (package
4038 (name "rseqc")
4039 (version "2.6.1")
4040 (source
4041 (origin
4042 (method url-fetch)
4043 (uri
4044 (string-append "mirror://sourceforge/rseqc/"
de67e922 4045 "RSeQC-" version ".tar.gz"))
8622a072 4046 (sha256
8214b7fb 4047 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
8622a072
RW		 4048 (modules '((guix build utils)))
4049 (snippet
4050 '(begin
4051 ;; remove bundled copy of pysam
4052 (delete-file-recursively "lib/pysam")
4053 (substitute* "setup.py"
4054 ;; remove dependency on outdated "distribute" module
4055 (("^from distribute_setup import use_setuptools") "")
4056 (("^use_setuptools\\(\\)") "")
4057 ;; do not use bundled copy of pysam
4058 (("^have_pysam = False") "have_pysam = True"))))))
4059 (build-system python-build-system)
4060 (arguments `(#:python ,python-2))
4061 (inputs
4062 `(("python-cython" ,python2-cython)
4063 ("python-pysam" ,python2-pysam)
4064 ("python-numpy" ,python2-numpy)
8622a072
RW		 4065 ("zlib" ,zlib)))
4066 (native-inputs
4067 `(("python-nose" ,python2-nose)))
4068 (home-page "http://rseqc.sourceforge.net/")
4069 (synopsis "RNA-seq quality control package")
4070 (description
4071 "RSeQC provides a number of modules that can comprehensively evaluate
4072high throughput sequence data, especially RNA-seq data. Some basic modules
4073inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4074while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4075distribution, coverage uniformity, strand specificity, etc.")
4076 (license license:gpl3+)))
4077
ec946638
RW		 4078(define-public seek
4079 ;; There are no release tarballs. According to the installation
4080 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4081 ;; stable release is identified by this changeset ID.
4082 (let ((changeset "2329130")
4083 (revision "1"))
4084 (package
4085 (name "seek")
4086 (version (string-append "0-" revision "." changeset))
4087 (source (origin
4088 (method hg-fetch)
4089 (uri (hg-reference
4090 (url "https://bitbucket.org/libsleipnir/sleipnir")
4091 (changeset changeset)))
4092 (sha256
4093 (base32
4094 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4095 (build-system gnu-build-system)
4096 (arguments
4097 `(#:modules ((srfi srfi-1)
4098 (guix build gnu-build-system)
4099 (guix build utils))
4100 #:phases
4101 (let ((dirs '("SeekMiner"
4102 "SeekEvaluator"
4103 "SeekPrep"
4104 "Distancer"
4105 "Data2DB"
4106 "PCL2Bin")))
4107 (modify-phases %standard-phases
4108 (add-before 'configure 'bootstrap
4109 (lambda _
4110 (zero? (system* "bash" "gen_auto"))))
4111 (add-after 'build 'build-additional-tools
4112 (lambda* (#:key make-flags #:allow-other-keys)
4113 (every (lambda (dir)
4114 (with-directory-excursion (string-append "tools/" dir)
4115 (zero? (apply system* "make" make-flags))))
4116 dirs)))
4117 (add-after 'install 'install-additional-tools
4118 (lambda* (#:key make-flags #:allow-other-keys)
4119 (fold (lambda (dir result)
4120 (with-directory-excursion (string-append "tools/" dir)
4121 (and result
4122 (zero? (apply system*
4123 `("make" ,@make-flags "install"))))))
4124 #t dirs)))))))
4125 (inputs
4126 `(("gsl" ,gsl)
4127 ("boost" ,boost)
4128 ("libsvm" ,libsvm)
4129 ("readline" ,readline)
4130 ("gengetopt" ,gengetopt)
4131 ("log4cpp" ,log4cpp)))
4132 (native-inputs
4133 `(("autoconf" ,autoconf)
4134 ("automake" ,automake)
4135 ("perl" ,perl)))
4136 (home-page "http://seek.princeton.edu")
4137 (synopsis "Gene co-expression search engine")
4138 (description
4139 "SEEK is a computational gene co-expression search engine. SEEK provides
4140biologists with a way to navigate the massive human expression compendium that
4141now contains thousands of expression datasets. SEEK returns a robust ranking
4142of co-expressed genes in the biological area of interest defined by the user's
4143query genes. It also prioritizes thousands of expression datasets according
4144to the user's query of interest.")
4145 (license license:cc-by3.0))))
4146
4e10a221
RW		 4147(define-public samtools
4148 (package
4149 (name "samtools")
79b555ed 4150 (version "1.3.1")
4e10a221
RW		 4151 (source
4152 (origin
4153 (method url-fetch)
4154 (uri
de67e922 4155 (string-append "mirror://sourceforge/samtools/samtools/"
4e10a221
RW		 4156 version "/samtools-" version ".tar.bz2"))
4157 (sha256
4158 (base32
79b555ed 4159 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4e10a221
RW		 4160 (build-system gnu-build-system)
4161 (arguments
c4473411 4162 `(#:modules ((ice-9 ftw)
5bdda30b
RW		 4163 (ice-9 regex)
4164 (guix build gnu-build-system)
4165 (guix build utils))
c4473411
RW		 4166 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4167 #:configure-flags (list "--with-ncurses")
4e10a221
RW		 4168 #:phases
4169 (alist-cons-after
c4473411
RW		 4170 'unpack 'patch-tests
4171 (lambda _
4172 (substitute* "test/test.pl"
4173 ;; The test script calls out to /bin/bash
4174 (("/bin/bash") (which "bash")))
4175 #t)
41dd7126
RW		 4176 (alist-cons-after
4177 'install 'install-library
4178 (lambda* (#:key outputs #:allow-other-keys)
4179 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
96c46210 4180 (install-file "libbam.a" lib)))
5bdda30b
RW		 4181 (alist-cons-after
4182 'install 'install-headers
4183 (lambda* (#:key outputs #:allow-other-keys)
4184 (let ((include (string-append (assoc-ref outputs "out")
4185 "/include/samtools/")))
5bdda30b 4186 (for-each (lambda (file)
96c46210 4187 (install-file file include))
5bdda30b
RW		 4188 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4189 #t))
c4473411 4190 %standard-phases)))))
4e10a221
RW		 4191 (native-inputs `(("pkg-config" ,pkg-config)))
4192 (inputs `(("ncurses" ,ncurses)
4193 ("perl" ,perl)
4194 ("python" ,python)
4195 ("zlib" ,zlib)))
4196 (home-page "http://samtools.sourceforge.net")
4197 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4198 (description
4199 "Samtools implements various utilities for post-processing nucleotide
4200sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4201variant calling (in conjunction with bcftools), and a simple alignment
4202viewer.")
4203 (license license:expat)))
d3517eda 4204
0b84a0aa
RW		 4205(define-public samtools-0.1
4206 ;; This is the most recent version of the 0.1 line of samtools. The input
4207 ;; and output formats differ greatly from that used and produced by samtools
4208 ;; 1.x and is still used in many bioinformatics pipelines.
4209 (package (inherit samtools)
4210 (version "0.1.19")
4211 (source
4212 (origin
4213 (method url-fetch)
4214 (uri
de67e922 4215 (string-append "mirror://sourceforge/samtools/samtools/"
0b84a0aa
RW		 4216 version "/samtools-" version ".tar.bz2"))
4217 (sha256
4218 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4219 (arguments
2309ed68
RW		 4220 `(#:tests? #f ;no "check" target
4221 ,@(substitute-keyword-arguments (package-arguments samtools)
4222 ((#:make-flags flags)
4223 `(cons "LIBCURSES=-lncurses" ,flags))
4224 ((#:phases phases)
4225 `(modify-phases ,phases
4226 (replace 'install
4227 (lambda* (#:key outputs #:allow-other-keys)
4228 (let ((bin (string-append
4229 (assoc-ref outputs "out") "/bin")))
4230 (mkdir-p bin)
4231 (copy-file "samtools"
4232 (string-append bin "/samtools")))))
4233 (delete 'patch-tests)
4234 (delete 'configure))))))))
0b84a0aa 4235
fe4c37c2 4236(define-public mosaik
698bd297 4237 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
fe4c37c2
RW		 4238 (package
4239 (name "mosaik")
4240 (version "2.2.30")
4241 (source (origin
4242 ;; There are no release tarballs nor tags.
4243 (method git-fetch)
4244 (uri (git-reference
4245 (url "https://github.com/wanpinglee/MOSAIK.git")
4246 (commit commit)))
4247 (file-name (string-append name "-" version))
4248 (sha256
4249 (base32
4250 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4251 (build-system gnu-build-system)
4252 (arguments
4253 `(#:tests? #f ; no tests
4254 #:make-flags (list "CC=gcc")
4255 #:phases
4256 (modify-phases %standard-phases
4257 (replace 'configure
4258 (lambda _ (chdir "src") #t))
4259 (replace 'install
4260 (lambda* (#:key outputs #:allow-other-keys)
4261 (let ((bin (string-append (assoc-ref outputs "out")
4262 "/bin")))
4263 (mkdir-p bin)
4264 (copy-recursively "../bin" bin)
4265 #t))))))
4266 (inputs
4267 `(("perl" ,perl)
4268 ("zlib" ,zlib)))
029d9f77 4269 (supported-systems '("x86_64-linux"))
0c6c9c00 4270 (home-page "https://github.com/wanpinglee/MOSAIK")
fe4c37c2
RW		 4271 (synopsis "Map nucleotide sequence reads to reference genomes")
4272 (description
4273 "MOSAIK is a program for mapping second and third-generation sequencing
4274reads to a reference genome. MOSAIK can align reads generated by all the
4275major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4276Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4277 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4278 ;; code released into the public domain:
4279 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4280 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4281 (license (list license:gpl2+ license:public-domain)))))
4282
282c5087
RW		 4283(define-public ngs-sdk
4284 (package
4285 (name "ngs-sdk")
48b419eb 4286 (version "1.2.5")
282c5087
RW		 4287 (source
4288 (origin
4289 (method url-fetch)
4290 (uri
4291 (string-append "https://github.com/ncbi/ngs/archive/"
4292 version ".tar.gz"))
4293 (file-name (string-append name "-" version ".tar.gz"))
4294 (sha256
4295 (base32
48b419eb 4296 "04y1fsmdnb5y86m3gg6f5g9wcscr6r25n7m8mdlcxy0i2q6w6cia"))))
282c5087
RW		 4297 (build-system gnu-build-system)
4298 (arguments
4299 `(#:parallel-build? #f ; not supported
4300 #:tests? #f ; no "check" target
4301 #:phases
4302 (alist-replace
4303 'configure
4304 (lambda* (#:key outputs #:allow-other-keys)
4305 (let ((out (assoc-ref outputs "out")))
282c5087
RW		 4306 ;; The 'configure' script doesn't recognize things like
4307 ;; '--enable-fast-install'.
4308 (zero? (system* "./configure"
4309 (string-append "--build-prefix=" (getcwd) "/build")
4310 (string-append "--prefix=" out)))))
4311 (alist-cons-after
4312 'unpack 'enter-dir
4313 (lambda _ (chdir "ngs-sdk") #t)
4314 %standard-phases))))
4315 (native-inputs `(("perl" ,perl)))
a0dadf0c
AE		 4316 ;; According to the test
4317 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4318 ;; in ngs-sdk/setup/konfigure.perl
ab29be81 4319 (supported-systems '("i686-linux" "x86_64-linux"))
282c5087
RW		 4320 (home-page "https://github.com/ncbi/ngs")
4321 (synopsis "API for accessing Next Generation Sequencing data")
4322 (description
4323 "NGS is a domain-specific API for accessing reads, alignments and pileups
4324produced from Next Generation Sequencing. The API itself is independent from
4325any particular back-end implementation, and supports use of multiple back-ends
4326simultaneously.")
4327 (license license:public-domain)))
4328
1ad15c16 4329(define-public java-ngs
2651a5e6 4330 (package (inherit ngs-sdk)
1ad15c16 4331 (name "java-ngs")
2651a5e6
RW		 4332 (arguments
4333 `(,@(substitute-keyword-arguments
4334 `(#:modules ((guix build gnu-build-system)
4335 (guix build utils)
4336 (srfi srfi-1)
4337 (srfi srfi-26))
4338 ,@(package-arguments ngs-sdk))
4339 ((#:phases phases)
614a8977
RW		 4340 `(modify-phases ,phases
4341 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
2651a5e6 4342 (inputs
d2540f80 4343 `(("jdk" ,icedtea "jdk")
2651a5e6
RW		 4344 ("ngs-sdk" ,ngs-sdk)))
4345 (synopsis "Java bindings for NGS SDK")))
4346
75dd2424
RW		 4347(define-public ncbi-vdb
4348 (package
4349 (name "ncbi-vdb")
40974c93 4350 (version "2.7.0")
75dd2424
RW		 4351 (source
4352 (origin
4353 (method url-fetch)
4354 (uri
4355 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4356 version ".tar.gz"))
4357 (file-name (string-append name "-" version ".tar.gz"))
4358 (sha256
4359 (base32
40974c93 4360 "0x1cg1x8vy0yjlkp0snc1533zcjhxqzqsaiwqk598n7vvw37n8lf"))))
75dd2424
RW		 4361 (build-system gnu-build-system)
4362 (arguments
4363 `(#:parallel-build? #f ; not supported
4364 #:tests? #f ; no "check" target
4365 #:phases
4366 (alist-replace
4367 'configure
4368 (lambda* (#:key inputs outputs #:allow-other-keys)
4369 (let ((out (assoc-ref outputs "out")))
75dd2424
RW		 4370 ;; Override include path for libmagic
4371 (substitute* "setup/package.prl"
4372 (("name => 'magic', Include => '/usr/include'")
4373 (string-append "name=> 'magic', Include => '"
4374 (assoc-ref inputs "libmagic")
4375 "/include" "'")))
4376
4377 ;; Install kdf5 library (needed by sra-tools)
4378 (substitute* "build/Makefile.install"
4379 (("LIBRARIES_TO_INSTALL =")
4380 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4381
675d7ae2
RW		 4382 (substitute* "build/Makefile.env"
4383 (("CFLAGS =" prefix)
4384 (string-append prefix "-msse2 ")))
4385
75dd2424
RW		 4386 ;; The 'configure' script doesn't recognize things like
4387 ;; '--enable-fast-install'.
4388 (zero? (system*
4389 "./configure"
4390 (string-append "--build-prefix=" (getcwd) "/build")
4391 (string-append "--prefix=" (assoc-ref outputs "out"))
4392 (string-append "--debug")
4393 (string-append "--with-xml2-prefix="
4394 (assoc-ref inputs "libxml2"))
4395 (string-append "--with-ngs-sdk-prefix="
4396 (assoc-ref inputs "ngs-sdk"))
4397 (string-append "--with-ngs-java-prefix="
1ad15c16 4398 (assoc-ref inputs "java-ngs"))
75dd2424
RW		 4399 (string-append "--with-hdf5-prefix="
4400 (assoc-ref inputs "hdf5"))))))
4401 (alist-cons-after
4402 'install 'install-interfaces
132b4c8c
RW		 4403 (lambda* (#:key outputs #:allow-other-keys)
4404 ;; Install interface libraries. On i686 the interface libraries
4405 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4406 ;; architecture name ("i386") instead of the target system prefix
4407 ;; ("i686").
75dd2424
RW		 4408 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4409 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
132b4c8c
RW		 4410 ,(system->linux-architecture
4411 (or (%current-target-system)
4412 (%current-system)))
75dd2424
RW		 4413 "/rel/ilib")
4414 (string-append (assoc-ref outputs "out")
4415 "/ilib"))
4416 ;; Install interface headers
4417 (copy-recursively "interfaces"
4418 (string-append (assoc-ref outputs "out")
4419 "/include")))
4420 %standard-phases))))
4421 (inputs
4422 `(("libxml2" ,libxml2)
4423 ("ngs-sdk" ,ngs-sdk)
1ad15c16 4424 ("java-ngs" ,java-ngs)
75dd2424
RW		 4425 ("libmagic" ,file)
4426 ("hdf5" ,hdf5)))
4427 (native-inputs `(("perl" ,perl)))
675d7ae2
RW		 4428 ;; NCBI-VDB requires SSE capability.
4429 (supported-systems '("i686-linux" "x86_64-linux"))
75dd2424
RW		 4430 (home-page "https://github.com/ncbi/ncbi-vdb")
4431 (synopsis "Database engine for genetic information")
4432 (description
4433 "The NCBI-VDB library implements a highly compressed columnar data
4434warehousing engine that is most often used to store genetic information.
4435Databases are stored in a portable image within the file system, and can be
4436accessed/downloaded on demand across HTTP.")
4437 (license license:public-domain)))
4438
cc6ed477
RW		 4439(define-public plink
4440 (package
4441 (name "plink")
4442 (version "1.07")
4443 (source
4444 (origin
4445 (method url-fetch)
4446 (uri (string-append
4447 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4448 version "-src.zip"))
4449 (sha256
4450 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
0dbb7ac2
EF		 4451 (patches (search-patches "plink-1.07-unclobber-i.patch"
4452 "plink-endian-detection.patch"))))
cc6ed477
RW		 4453 (build-system gnu-build-system)
4454 (arguments
4455 '(#:tests? #f ;no "check" target
4456 #:make-flags (list (string-append "LIB_LAPACK="
4457 (assoc-ref %build-inputs "lapack")
4458 "/lib/liblapack.so")
4459 "WITH_LAPACK=1"
4460 "FORCE_DYNAMIC=1"
4461 ;; disable phoning home
4462 "WITH_WEBCHECK=")
4463 #:phases
4464 (modify-phases %standard-phases
4465 ;; no "configure" script
4466 (delete 'configure)
4467 (replace 'install
4468 (lambda* (#:key outputs #:allow-other-keys)
4469 (let ((bin (string-append (assoc-ref outputs "out")
4470 "/bin/")))
96c46210 4471 (install-file "plink" bin)
cc6ed477
RW		 4472 #t))))))
4473 (inputs
4474 `(("zlib" ,zlib)
4475 ("lapack" ,lapack)))
4476 (native-inputs
4477 `(("unzip" ,unzip)))
4478 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4479 (synopsis "Whole genome association analysis toolset")
4480 (description
4481 "PLINK is a whole genome association analysis toolset, designed to
4482perform a range of basic, large-scale analyses in a computationally efficient
4483manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4484so there is no support for steps prior to this (e.g. study design and
4485planning, generating genotype or CNV calls from raw data). Through
4486integration with gPLINK and Haploview, there is some support for the
4487subsequent visualization, annotation and storage of results.")
4488 ;; Code is released under GPLv2, except for fisher.h, which is under
4489 ;; LGPLv2.1+
4490 (license (list license:gpl2 license:lgpl2.1+))))
4491
c6a24d6e
RW		 4492(define-public smithlab-cpp
4493 (let ((revision "1")
698bd297 4494 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
c6a24d6e
RW		 4495 (package
4496 (name "smithlab-cpp")
698bd297 4497 (version (string-append "0." revision "." (string-take commit 7)))
c6a24d6e
RW		 4498 (source (origin
4499 (method git-fetch)
4500 (uri (git-reference
4501 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4502 (commit commit)))
4503 (file-name (string-append name "-" version "-checkout"))
4504 (sha256
4505 (base32
4506 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4507 (build-system gnu-build-system)
4508 (arguments
4509 `(#:modules ((guix build gnu-build-system)
4510 (guix build utils)
4511 (srfi srfi-26))
4512 #:tests? #f ;no "check" target
4513 #:phases
4514 (modify-phases %standard-phases
4515 (add-after 'unpack 'use-samtools-headers
4516 (lambda _
4517 (substitute* '("SAM.cpp"
4518 "SAM.hpp")
4519 (("sam.h") "samtools/sam.h"))
4520 #t))
4521 (replace 'install
4522 (lambda* (#:key outputs #:allow-other-keys)
4523 (let* ((out (assoc-ref outputs "out"))
4524 (lib (string-append out "/lib"))
4525 (include (string-append out "/include/smithlab-cpp")))
4526 (mkdir-p lib)
4527 (mkdir-p include)
4528 (for-each (cut install-file <> lib)
4529 (find-files "." "\\.o$"))
4530 (for-each (cut install-file <> include)
4531 (find-files "." "\\.hpp$")))
4532 #t))
4533 (delete 'configure))))
4534 (inputs
4535 `(("samtools" ,samtools-0.1)
4536 ("zlib" ,zlib)))
4537 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4538 (synopsis "C++ helper library for functions used in Smith lab projects")
4539 (description
4540 "Smithlab CPP is a C++ library that includes functions used in many of
4541the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4542structures, classes for genomic regions, mapped sequencing reads, etc.")
4543 (license license:gpl3+))))
4544
56e373ef
RW		 4545(define-public preseq
4546 (package
4547 (name "preseq")
b49c5a58 4548 (version "2.0")
56e373ef
RW		 4549 (source (origin
4550 (method url-fetch)
b49c5a58
RW		 4551 (uri (string-append "https://github.com/smithlabcode/"
4552 "preseq/archive/v" version ".tar.gz"))
4553 (file-name (string-append name "-" version ".tar.gz"))
56e373ef 4554 (sha256
b49c5a58 4555 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
56e373ef
RW		 4556 (modules '((guix build utils)))
4557 (snippet
4558 ;; Remove bundled samtools.
b49c5a58 4559 '(delete-file-recursively "samtools"))))
56e373ef
RW		 4560 (build-system gnu-build-system)
4561 (arguments
4562 `(#:tests? #f ;no "check" target
4563 #:phases
4564 (modify-phases %standard-phases
56e373ef 4565 (delete 'configure))
b49c5a58
RW		 4566 #:make-flags
4567 (list (string-append "PREFIX="
4568 (assoc-ref %outputs "out"))
4569 (string-append "LIBBAM="
4570 (assoc-ref %build-inputs "samtools")
4571 "/lib/libbam.a")
4572 (string-append "SMITHLAB_CPP="
4573 (assoc-ref %build-inputs "smithlab-cpp")
4574 "/lib")
4575 "PROGS=preseq"
4576 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
56e373ef
RW		 4577 (inputs
4578 `(("gsl" ,gsl)
4579 ("samtools" ,samtools-0.1)
b49c5a58 4580 ("smithlab-cpp" ,smithlab-cpp)
56e373ef
RW		 4581 ("zlib" ,zlib)))
4582 (home-page "http://smithlabresearch.org/software/preseq/")
4583 (synopsis "Program for analyzing library complexity")
4584 (description
4585 "The preseq package is aimed at predicting and estimating the complexity
4586of a genomic sequencing library, equivalent to predicting and estimating the
4587number of redundant reads from a given sequencing depth and how many will be
4588expected from additional sequencing using an initial sequencing experiment.
4589The estimates can then be used to examine the utility of further sequencing,
4590optimize the sequencing depth, or to screen multiple libraries to avoid low
4591complexity samples.")
4592 (license license:gpl3+)))
4593
9ded1457
BW		 4594(define-public python-screed
4595 (package
4596 (name "python-screed")
4597 (version "0.9")
4598 (source
4599 (origin
4600 (method url-fetch)
4601 (uri (pypi-uri "screed" version))
4602 (sha256
4603 (base32
4604 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4605 (build-system python-build-system)
4606 (arguments
4607 `(#:phases
4608 (modify-phases %standard-phases
4609 (replace 'check
4610 (lambda _
4611 (setenv "PYTHONPATH"
4612 (string-append (getenv "PYTHONPATH") ":."))
4613 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4614 (native-inputs
4615 `(("python-nose" ,python-nose)))
4616 (inputs
4617 `(("python-bz2file" ,python-bz2file)))
4618 (home-page "http://github.com/dib-lab/screed/")
4619 (synopsis "Short read sequence database utilities")
4620 (description "Screed parses FASTA and FASTQ files and generates databases.
4621Values such as sequence name, sequence description, sequence quality and the
4622sequence itself can be retrieved from these databases.")
4623 (license license:bsd-3)))
4624
4625(define-public python2-screed
5c31f4aa 4626 (package-with-python2 python-screed))
9ded1457 4627
51c64999
RW		 4628(define-public sra-tools
4629 (package
4630 (name "sra-tools")
646a8433 4631 (version "2.7.0")
51c64999
RW		 4632 (source
4633 (origin
4634 (method url-fetch)
4635 (uri
4636 (string-append "https://github.com/ncbi/sra-tools/archive/"
4637 version ".tar.gz"))
4638 (file-name (string-append name "-" version ".tar.gz"))
4639 (sha256
4640 (base32
646a8433 4641 "13paw7bq6y47d2pl0ac5gpgcqp1xsy1g7v1fwysm3hr8lb2dck17"))))
51c64999
RW		 4642 (build-system gnu-build-system)
4643 (arguments
4644 `(#:parallel-build? #f ; not supported
4645 #:tests? #f ; no "check" target
2320e76b
RW		 4646 #:make-flags
4647 (list (string-append "VDB_LIBDIR="
4648 (assoc-ref %build-inputs "ncbi-vdb")
4649 ,(if (string-prefix? "x86_64"
4650 (or (%current-target-system)
4651 (%current-system)))
4652 "/lib64"
4653 "/lib32")))
51c64999
RW		 4654 #:phases
4655 (alist-replace
4656 'configure
4657 (lambda* (#:key inputs outputs #:allow-other-keys)
4658 ;; The build system expects a directory containing the sources and
4659 ;; raw build output of ncbi-vdb, including files that are not
4660 ;; installed. Since we are building against an installed version of
4661 ;; ncbi-vdb, the following modifications are needed.
4662 (substitute* "setup/konfigure.perl"
4663 ;; Make the configure script look for the "ilib" directory of
4664 ;; "ncbi-vdb" without first checking for the existence of a
4665 ;; matching library in its "lib" directory.
4666 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
4667 "my $f = File::Spec->catdir($ilibdir, $ilib);")
4668 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
4669 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
4670 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
4671
2320e76b
RW		 4672 ;; Dynamic linking
4673 (substitute* "tools/copycat/Makefile"
4674 (("smagic-static") "lmagic"))
4675
51c64999
RW		 4676 ;; The 'configure' script doesn't recognize things like
4677 ;; '--enable-fast-install'.
4678 (zero? (system*
4679 "./configure"
4680 (string-append "--build-prefix=" (getcwd) "/build")
4681 (string-append "--prefix=" (assoc-ref outputs "out"))
4682 (string-append "--debug")
4683 (string-append "--with-fuse-prefix="
4684 (assoc-ref inputs "fuse"))
4685 (string-append "--with-magic-prefix="
4686 (assoc-ref inputs "libmagic"))
4687 ;; TODO: building with libxml2 fails with linker errors
4688 ;; (string-append "--with-xml2-prefix="
4689 ;; (assoc-ref inputs "libxml2"))
4690 (string-append "--with-ncbi-vdb-sources="
4691 (assoc-ref inputs "ncbi-vdb"))
4692 (string-append "--with-ncbi-vdb-build="
4693 (assoc-ref inputs "ncbi-vdb"))
4694 (string-append "--with-ngs-sdk-prefix="
4695 (assoc-ref inputs "ngs-sdk"))
4696 (string-append "--with-hdf5-prefix="
4697 (assoc-ref inputs "hdf5")))))
4698 %standard-phases)))
4699 (native-inputs `(("perl" ,perl)))
4700 (inputs
4701 `(("ngs-sdk" ,ngs-sdk)
4702 ("ncbi-vdb" ,ncbi-vdb)
4703 ("libmagic" ,file)
4704 ("fuse" ,fuse)
4705 ("hdf5" ,hdf5)
4706 ("zlib" ,zlib)))
4707 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
4708 (synopsis "Tools and libraries for reading and writing sequencing data")
4709 (description
4710 "The SRA Toolkit from NCBI is a collection of tools and libraries for
4711reading of sequencing files from the Sequence Read Archive (SRA) database and
4712writing files into the .sra format.")
4713 (license license:public-domain)))
4714
d3517eda
RW		 4715(define-public seqan
4716 (package
4717 (name "seqan")
4718 (version "1.4.2")
4719 (source (origin
4720 (method url-fetch)
4721 (uri (string-append "http://packages.seqan.de/seqan-library/"
4722 "seqan-library-" version ".tar.bz2"))
4723 (sha256
4724 (base32
4725 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
4726 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
4727 ;; makes sense to split the outputs.
4728 (outputs '("out" "doc"))
4729 (build-system trivial-build-system)
4730 (arguments
4731 `(#:modules ((guix build utils))
4732 #:builder
4733 (begin
4734 (use-modules (guix build utils))
4735 (let ((tar (assoc-ref %build-inputs "tar"))
4736 (bzip (assoc-ref %build-inputs "bzip2"))
4737 (out (assoc-ref %outputs "out"))
4738 (doc (assoc-ref %outputs "doc")))
4739 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
4740 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
4741 (chdir (string-append "seqan-library-" ,version))
4742 (copy-recursively "include" (string-append out "/include"))
4743 (copy-recursively "share" (string-append doc "/share"))))))
4744 (native-inputs
4745 `(("source" ,source)
4746 ("tar" ,tar)
4747 ("bzip2" ,bzip2)))
4748 (home-page "http://www.seqan.de")
4749 (synopsis "Library for nucleotide sequence analysis")
4750 (description
4751 "SeqAn is a C++ library of efficient algorithms and data structures for
4752the analysis of sequences with the focus on biological data. It contains
4753algorithms and data structures for string representation and their
4754manipulation, online and indexed string search, efficient I/O of
4755bioinformatics file formats, sequence alignment, and more.")
4756 (license license:bsd-3)))
ce7155d5 4757
d708b7a9
BW		 4758(define-public seqmagick
4759 (package
4760 (name "seqmagick")
4761 (version "0.6.1")
4762 (source
4763 (origin
4764 (method url-fetch)
4765 (uri (string-append
4766 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
4767 version ".tar.gz"))
4768 (sha256
4769 (base32
4770 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
4771 (build-system python-build-system)
4772 (arguments
4773 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
4774 `(#:python ,python-2
4775 #:phases
4776 (modify-phases %standard-phases
4777 ;; Current test in setup.py does not work as of 0.6.1,
4778 ;; so use nose to run tests instead for now. See
4779 ;; https://github.com/fhcrc/seqmagick/issues/55
4780 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
4781 (inputs
7bba95b7
BW		 4782 ;; biopython-1.66 is required due to
4783 ;; https://github.com/fhcrc/seqmagick/issues/59
4784 ;; When that issue is resolved the 'python2-biopython-1.66' package
4785 ;; should be removed.
4786 `(("python-biopython" ,python2-biopython-1.66)))
d708b7a9 4787 (native-inputs
f3b98f4f 4788 `(("python-nose" ,python2-nose)))
d708b7a9
BW		 4789 (home-page "http://github.com/fhcrc/seqmagick")
4790 (synopsis "Tools for converting and modifying sequence files")
4791 (description
4792 "Bioinformaticians often have to convert sequence files between formats
4793and do little manipulations on them, and it's not worth writing scripts for
4794that. Seqmagick is a utility to expose the file format conversion in
4795BioPython in a convenient way. Instead of having a big mess of scripts, there
4796is one that takes arguments.")
4797 (license license:gpl3)))
4798
66daf78c
BW		 4799(define-public seqtk
4800 (package
4801 (name "seqtk")
4802 (version "1.2")
4803 (source (origin
4804 (method url-fetch)
4805 (uri (string-append
4806 "https://github.com/lh3/seqtk/archive/v"
4807 version ".tar.gz"))
4808 (file-name (string-append name "-" version ".tar.gz"))
4809 (sha256
4810 (base32
4811 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
4812 (modules '((guix build utils)))
4813 (snippet
4814 '(begin
4815 ;; Remove extraneous header files, as is done in the seqtk
4816 ;; master branch.
4817 (for-each (lambda (file) (delete-file file))
4818 (list "ksort.h" "kstring.h" "kvec.h"))
4819 #t))))
4820 (build-system gnu-build-system)
4821 (arguments
4822 `(#:phases
4823 (modify-phases %standard-phases
4824 (delete 'configure)
4825 (replace 'check
4826 ;; There are no tests, so we just run a sanity check.
4827 (lambda _ (zero? (system* "./seqtk" "seq"))))
4828 (replace 'install
4829 (lambda* (#:key outputs #:allow-other-keys)
4830 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4831 (install-file "seqtk" bin)))))))
4832 (inputs
4833 `(("zlib" ,zlib)))
4834 (home-page "https://github.com/lh3/seqtk")
4835 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
4836 (description
4837 "Seqtk is a fast and lightweight tool for processing sequences in the
4838FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
4839optionally compressed by gzip.")
4840 (license license:expat)))
4841
5f7e17be
BW		 4842(define-public snap-aligner
4843 (package
4844 (name "snap-aligner")
4845 (version "1.0beta.18")
4846 (source (origin
4847 (method url-fetch)
4848 (uri (string-append
4849 "https://github.com/amplab/snap/archive/v"
4850 version ".tar.gz"))
4851 (file-name (string-append name "-" version ".tar.gz"))
4852 (sha256
4853 (base32
4854 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
4855 (build-system gnu-build-system)
4856 (arguments
4857 '(#:phases
4858 (modify-phases %standard-phases
4859 (delete 'configure)
4860 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
4861 (replace 'install
4862 (lambda* (#:key outputs #:allow-other-keys)
4863 (let* ((out (assoc-ref outputs "out"))
4864 (bin (string-append out "/bin")))
5f7e17be
BW		 4865 (install-file "snap-aligner" bin)
4866 (install-file "SNAPCommand" bin)
4867 #t))))))
4868 (native-inputs
4869 `(("zlib" ,zlib)))
4870 (home-page "http://snap.cs.berkeley.edu/")
4871 (synopsis "Short read DNA sequence aligner")
4872 (description
4873 "SNAP is a fast and accurate aligner for short DNA reads. It is
4874optimized for modern read lengths of 100 bases or higher, and takes advantage
4875of these reads to align data quickly through a hash-based indexing scheme.")
3e6fdd5f
EF		 4876 ;; 32-bit systems are not supported by the unpatched code.
4877 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
4878 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
4879 ;; systems without a lot of memory cannot make good use of this program.
4880 (supported-systems '("x86_64-linux"))
5f7e17be
BW		 4881 (license license:asl2.0)))
4882
bcadaf00
BW		 4883(define-public sortmerna
4884 (package
4885 (name "sortmerna")
849485f5 4886 (version "2.1b")
bcadaf00
BW		 4887 (source
4888 (origin
4889 (method url-fetch)
4890 (uri (string-append
4891 "https://github.com/biocore/sortmerna/archive/"
4892 version ".tar.gz"))
4893 (file-name (string-append name "-" version ".tar.gz"))
4894 (sha256
4895 (base32
849485f5 4896 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
bcadaf00
BW		 4897 (build-system gnu-build-system)
4898 (outputs '("out" ;for binaries
4899 "db")) ;for sequence databases
4900 (arguments
4901 `(#:phases
4902 (modify-phases %standard-phases
4903 (replace 'install
4904 (lambda* (#:key outputs #:allow-other-keys)
4905 (let* ((out (assoc-ref outputs "out"))
4906 (bin (string-append out "/bin"))
4907 (db (assoc-ref outputs "db"))
4908 (share
4909 (string-append db "/share/sortmerna/rRNA_databases")))
4910 (install-file "sortmerna" bin)
4911 (install-file "indexdb_rna" bin)
4912 (for-each (lambda (file)
4913 (install-file file share))
4914 (find-files "rRNA_databases" ".*fasta"))
4915 #t))))))
849485f5
BW		 4916 (inputs
4917 `(("zlib" ,zlib)))
bcadaf00
BW		 4918 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
4919 (synopsis "Biological sequence analysis tool for NGS reads")
4920 (description
4921 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
4922and operational taxonomic unit (OTU) picking of next generation
4923sequencing (NGS) reads. The core algorithm is based on approximate seeds and
4924allows for fast and sensitive analyses of nucleotide sequences. The main
4925application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
4926 (license license:lgpl3)))
4927
ce7155d5
RW		 4928(define-public star
4929 (package
4930 (name "star")
c9e9154e 4931 (version "2.5.2b")
ce7155d5
RW		 4932 (source (origin
4933 (method url-fetch)
3062d750
RW		 4934 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
4935 version ".tar.gz"))
4936 (file-name (string-append name "-" version ".tar.gz"))
ce7155d5
RW		 4937 (sha256
4938 (base32
c9e9154e 4939 "1na6np880r1zaamiy00hy8bid5anpy0kgf63587v2yl080krk2zq"))
ce7155d5
RW		 4940 (modules '((guix build utils)))
4941 (snippet
3062d750
RW		 4942 '(begin
4943 (substitute* "source/Makefile"
4944 (("/bin/rm") "rm"))
4945 ;; Remove pre-built binaries and bundled htslib sources.
4946 (delete-file-recursively "bin/MacOSX_x86_64")
4947 (delete-file-recursively "bin/Linux_x86_64")
c9e9154e 4948 (delete-file-recursively "bin/Linux_x86_64_static")
3062d750
RW		 4949 (delete-file-recursively "source/htslib")
4950 #t))))
ce7155d5
RW		 4951 (build-system gnu-build-system)
4952 (arguments
4953 '(#:tests? #f ;no check target
4954 #:make-flags '("STAR")
4955 #:phases
c0266e8d
RW		 4956 (modify-phases %standard-phases
4957 (add-after 'unpack 'enter-source-dir
4958 (lambda _ (chdir "source") #t))
3062d750
RW		 4959 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
4960 (lambda _
4961 (substitute* "Makefile"
4962 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
4963 _ prefix) prefix))
4964 (substitute* '("BAMfunctions.cpp"
4965 "signalFromBAM.h"
4966 "bam_cat.h"
4967 "bam_cat.c"
4968 "STAR.cpp"
4969 "bamRemoveDuplicates.cpp")
4970 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
4971 (string-append "#include <" header ">")))
4972 (substitute* "IncludeDefine.h"
4973 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
4974 (string-append "<" header ">")))
4975 #t))
c0266e8d
RW		 4976 (replace 'install
4977 (lambda* (#:key outputs #:allow-other-keys)
4978 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4979 (install-file "STAR" bin))
4980 #t))
4981 (delete 'configure))))
ce7155d5
RW		 4982 (native-inputs
4983 `(("vim" ,vim))) ; for xxd
4984 (inputs
3062d750
RW		 4985 `(("htslib" ,htslib)
4986 ("zlib" ,zlib)))
ce7155d5
RW		 4987 (home-page "https://github.com/alexdobin/STAR")
4988 (synopsis "Universal RNA-seq aligner")
4989 (description
4990 "The Spliced Transcripts Alignment to a Reference (STAR) software is
4991based on a previously undescribed RNA-seq alignment algorithm that uses
4992sequential maximum mappable seed search in uncompressed suffix arrays followed
4993by seed clustering and stitching procedure. In addition to unbiased de novo
4994detection of canonical junctions, STAR can discover non-canonical splices and
4995chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
4996sequences.")
c11f79a4
BW		 4997 ;; Only 64-bit systems are supported according to the README.
4998 (supported-systems '("x86_64-linux" "mips64el-linux"))
ce7155d5
RW		 4999 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5000 (license license:gpl3+)))
de07c0db 5001
dbf4ed7c
RW		 5002(define-public subread
5003 (package
5004 (name "subread")
c180533b 5005 (version "1.5.1")
dbf4ed7c
RW		 5006 (source (origin
5007 (method url-fetch)
de67e922
LF		 5008 (uri (string-append "mirror://sourceforge/subread/subread-"
5009 version "/subread-" version "-source.tar.gz"))
dbf4ed7c
RW		 5010 (sha256
5011 (base32
c180533b 5012 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
dbf4ed7c
RW		 5013 (build-system gnu-build-system)
5014 (arguments
5015 `(#:tests? #f ;no "check" target
104c1986
RW		 5016 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5017 ;; optimizations by default, so we override these flags such that x86_64
5018 ;; flags are only added when the build target is an x86_64 system.
5019 #:make-flags
5020 (list (let ((system ,(or (%current-target-system)
5021 (%current-system)))
5022 (flags '("-ggdb" "-fomit-frame-pointer"
5023 "-ffast-math" "-funroll-loops"
5024 "-fmessage-length=0"
5025 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5026 "-DMAKE_STANDALONE"
5027 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5028 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5029 (if (string-prefix? "x86_64" system)
5030 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5031 (string-append "CCFLAGS=" (string-join flags))))
5032 "-f" "Makefile.Linux"
5033 "CC=gcc ${CCFLAGS}")
dbf4ed7c
RW		 5034 #:phases
5035 (alist-cons-after
5036 'unpack 'enter-dir
5037 (lambda _ (chdir "src") #t)
5038 (alist-replace
5039 'install
5040 (lambda* (#:key outputs #:allow-other-keys)
5041 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5042 (mkdir-p bin)
5043 (copy-recursively "../bin" bin)))
5044 ;; no "configure" script
5045 (alist-delete 'configure %standard-phases)))))
5046 (inputs `(("zlib" ,zlib)))
5047 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5048 (synopsis "Tool kit for processing next-gen sequencing data")
5049 (description
5050 "The subread package contains the following tools: subread aligner, a
5051general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5052and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5053features; exactSNP: a SNP caller that discovers SNPs by testing signals
5054against local background noises.")
5055 (license license:gpl3+)))
5056
d15d981e
RW		 5057(define-public stringtie
5058 (package
5059 (name "stringtie")
5060 (version "1.2.1")
5061 (source (origin
5062 (method url-fetch)
5063 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5064 "stringtie-" version ".tar.gz"))
5065 (sha256
5066 (base32
5067 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5068 (modules '((guix build utils)))
5069 (snippet
5070 '(begin
5071 (delete-file-recursively "samtools-0.1.18")
5072 #t))))
5073 (build-system gnu-build-system)
5074 (arguments
5075 `(#:tests? #f ;no test suite
5076 #:phases
5077 (modify-phases %standard-phases
5078 ;; no configure script
5079 (delete 'configure)
5080 (add-before 'build 'use-system-samtools
5081 (lambda _
5082 (substitute* "Makefile"
5083 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5084 "stringtie: "))
5085 (substitute* '("gclib/GBam.h"
5086 "gclib/GBam.cpp")
5087 (("#include \"(bam|sam|kstring).h\"" _ header)
5088 (string-append "#include <samtools/" header ".h>")))
5089 #t))
5090 (replace 'install
5091 (lambda* (#:key outputs #:allow-other-keys)
5092 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5093 (install-file "stringtie" bin)
5094 #t))))))
5095 (inputs
5096 `(("samtools" ,samtools-0.1)
5097 ("zlib" ,zlib)))
5098 (home-page "http://ccb.jhu.edu/software/stringtie/")
5099 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5100 (description
5101 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5102alignments into potential transcripts. It uses a novel network flow algorithm
5103as well as an optional de novo assembly step to assemble and quantitate
5104full-length transcripts representing multiple splice variants for each gene
5105locus. Its input can include not only the alignments of raw reads used by
5106other transcript assemblers, but also alignments of longer sequences that have
5107been assembled from those reads. To identify differentially expressed genes
5108between experiments, StringTie's output can be processed either by the
5109Cuffdiff or Ballgown programs.")
5110 (license license:artistic2.0)))
5111
de07c0db
RW		 5112(define-public vcftools
5113 (package
5114 (name "vcftools")
9b36e256 5115 (version "0.1.14")
de07c0db
RW		 5116 (source (origin
5117 (method url-fetch)
5118 (uri (string-append
9b36e256
RJ		 5119 "https://github.com/vcftools/vcftools/releases/download/v"
5120 version "/vcftools-" version ".tar.gz"))
de07c0db
RW		 5121 (sha256
5122 (base32
9b36e256 5123 "10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
de07c0db
RW		 5124 (build-system gnu-build-system)
5125 (arguments
5126 `(#:tests? #f ; no "check" target
5127 #:make-flags (list
7c3958e1 5128 "CFLAGS=-O2" ; override "-m64" flag
de07c0db
RW		 5129 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5130 (string-append "MANDIR=" (assoc-ref %outputs "out")
9b36e256
RJ		 5131 "/share/man/man1"))))
5132 (native-inputs
5133 `(("pkg-config" ,pkg-config)))
de07c0db
RW		 5134 (inputs
5135 `(("perl" ,perl)
5136 ("zlib" ,zlib)))
9b36e256 5137 (home-page "https://vcftools.github.io/")
de07c0db
RW		 5138 (synopsis "Tools for working with VCF files")
5139 (description
5140 "VCFtools is a program package designed for working with VCF files, such
5141as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5142provide easily accessible methods for working with complex genetic variation
5143data in the form of VCF files.")
5144 ;; The license is declared as LGPLv3 in the README and
9b36e256 5145 ;; at https://vcftools.github.io/license.html
de07c0db 5146 (license license:lgpl3)))
9c38b540 5147
35aa90a1
RW		 5148(define-public infernal
5149 (package
5150 (name "infernal")
5151 (version "1.1.2")
5152 (source (origin
5153 (method url-fetch)
5154 (uri (string-append "http://eddylab.org/software/infernal/"
5155 "infernal-" version ".tar.gz"))
5156 (sha256
5157 (base32
5158 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5159 (build-system gnu-build-system)
5160 (native-inputs
5161 `(("perl" ,perl))) ; for tests
5162 (home-page "http://eddylab.org/infernal/")
5163 (synopsis "Inference of RNA alignments")
5164 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5165searching DNA sequence databases for RNA structure and sequence similarities.
5166It is an implementation of a special case of profile stochastic context-free
5167grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5168profile, but it scores a combination of sequence consensus and RNA secondary
5169structure consensus, so in many cases, it is more capable of identifying RNA
5170homologs that conserve their secondary structure more than their primary
5171sequence.")
48409ef2
EF		 5172 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5173 (supported-systems '("i686-linux" "x86_64-linux"))
35aa90a1
RW		 5174 (license license:bsd-3)))
5175
7b3df1e5
BW		 5176(define-public r-vegan
5177 (package
5178 (name "r-vegan")
2c575bb9 5179 (version "2.4-1")
7b3df1e5
BW		 5180 (source
5181 (origin
5182 (method url-fetch)
5183 (uri (cran-uri "vegan" version))
5184 (sha256
5185 (base32
2c575bb9 5186 "0i0c7rc0nzgbysd1nlxzxd2rvy75qcnw3yc7nggzqjzzj5d7yzsd"))))
7b3df1e5
BW		 5187 (build-system r-build-system)
5188 (arguments
5189 `(#:phases
5190 (modify-phases %standard-phases
5191 (add-after 'unpack 'revert-test-deletion
5192 ;; The distributed sources do not include tests with the CRAN
5193 ;; package. Here we revert the commit
5194 ;; `591d0e8ba1deaaf82445474ec6619c0b43db4e63' which deletes these
5195 ;; tests. There are plans to not delete tests in future as
5196 ;; documented at https://github.com/vegandevs/vegan/issues/181.
5197 (lambda* (#:key inputs #:allow-other-keys)
5198 (zero?
5199 (system* "patch" "-R" "-p1" "-i"
5200 (assoc-ref inputs "r-vegan-delete-tests-patch"))))))))
5201 (native-inputs
5202 `(("gfortran" ,gfortran)
5203 ("r-knitr" ,r-knitr)
5204 ("r-vegan-delete-tests-patch"
5205 ,(origin
5206 (method url-fetch)
5207 (uri (string-append
5208 "https://github.com/vegandevs/vegan/commit/"
5209 "591d0e8ba1deaaf82445474ec6619c0b43db4e63.patch"))
5210 (sha256
5211 (base32
5212 "0b1bi7y4jjdl3ph721vm9apm51dr2z9piwvhy4355sf2b4kyyj5a"))))))
5213 (propagated-inputs
5214 `(("r-cluster" ,r-cluster)
5215 ("r-lattice" ,r-lattice)
5216 ("r-mgcv" ,r-mgcv)
5217 ("r-permute" ,r-permute)))
5218 (home-page "https://cran.r-project.org/web/packages/vegan")
5219 (synopsis "Functions for community ecology")
5220 (description
5221 "The vegan package provides tools for descriptive community ecology. It
5222has most basic functions of diversity analysis, community ordination and
5223dissimilarity analysis. Most of its multivariate tools can be used for other
5224data types as well.")
5225 (license license:gpl2+)))
5226
8c6de588
RW		 5227(define-public r-annotate
5228 (package
5229 (name "r-annotate")
d0f0579e 5230 (version "1.52.1")
8c6de588
RW		 5231 (source
5232 (origin
5233 (method url-fetch)
5234 (uri (bioconductor-uri "annotate" version))
5235 (sha256
5236 (base32
d0f0579e 5237 "0yymz8qxgnbybvfhqrgkd1hh9dhwxdii1yxkhr1zicjgb35xixxb"))))
8c6de588
RW		 5238 (build-system r-build-system)
5239 (propagated-inputs
5240 `(("r-annotationdbi" ,r-annotationdbi)
5241 ("r-biobase" ,r-biobase)
5242 ("r-biocgenerics" ,r-biocgenerics)
5243 ("r-dbi" ,r-dbi)
d0f0579e 5244 ("r-rcurl" ,r-rcurl)
8c6de588
RW		 5245 ("r-xml" ,r-xml)
5246 ("r-xtable" ,r-xtable)))
5247 (home-page
5248 "http://bioconductor.org/packages/annotate")
5249 (synopsis "Annotation for microarrays")
5250 (description "This package provides R enviroments for the annotation of
5251microarrays.")
5252 (license license:artistic2.0)))
5253
07a664cd
RW		 5254(define-public r-geneplotter
5255 (package
5256 (name "r-geneplotter")
6faa2a48 5257 (version "1.52.0")
07a664cd
RW		 5258 (source
5259 (origin
5260 (method url-fetch)
5261 (uri (bioconductor-uri "geneplotter" version))
5262 (sha256
5263 (base32
6faa2a48 5264 "1p6yvxi243irhjxwm97hp73abhwampj0myyf8z00ij166674pc7h"))))
07a664cd
RW		 5265 (build-system r-build-system)
5266 (propagated-inputs
5267 `(("r-annotate" ,r-annotate)
5268 ("r-annotationdbi" ,r-annotationdbi)
5269 ("r-biobase" ,r-biobase)
5270 ("r-biocgenerics" ,r-biocgenerics)
5271 ("r-lattice" ,r-lattice)
5272 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5273 (home-page "http://bioconductor.org/packages/geneplotter")
5274 (synopsis "Graphics functions for genomic data")
5275 (description
5276 "This package provides functions for plotting genomic data.")
5277 (license license:artistic2.0)))
5278
2301fd3e
RW		 5279(define-public r-genefilter
5280 (package
5281 (name "r-genefilter")
1e66e719 5282 (version "1.56.0")
2301fd3e
RW		 5283 (source
5284 (origin
5285 (method url-fetch)
5286 (uri (bioconductor-uri "genefilter" version))
5287 (sha256
5288 (base32
1e66e719 5289 "1vzgciqd09csqcw9qync8blsv51ylrd86a65iadgyy6j26g01fwd"))))
2301fd3e
RW		 5290 (build-system r-build-system)
5291 (native-inputs
5292 `(("gfortran" ,gfortran)))
5293 (propagated-inputs
5294 `(("r-annotate" ,r-annotate)
5295 ("r-annotationdbi" ,r-annotationdbi)
5296 ("r-biobase" ,r-biobase)
5297 ("r-s4vectors" ,r-s4vectors)))
5298 (home-page "http://bioconductor.org/packages/genefilter")
5299 (synopsis "Filter genes from high-throughput experiments")
5300 (description
5301 "This package provides basic functions for filtering genes from
5302high-throughput sequencing experiments.")
5303 (license license:artistic2.0)))
5304
ad34f0ac
RW		 5305(define-public r-deseq2
5306 (package
5307 (name "r-deseq2")
007ee802 5308 (version "1.14.1")
ad34f0ac
RW		 5309 (source
5310 (origin
5311 (method url-fetch)
5312 (uri (bioconductor-uri "DESeq2" version))
5313 (sha256
5314 (base32
007ee802 5315 "1walwkqryn1gnwz7zryr5764a0p6ia7ag4w6w9n8fskg8dkg0fqs"))))
ad34f0ac
RW		 5316 (properties `((upstream-name . "DESeq2")))
5317 (build-system r-build-system)
5318 (arguments
5319 `(#:phases
5320 (modify-phases %standard-phases
5321 (add-after 'unpack 'link-against-armadillo
5322 (lambda _
5323 (substitute* "src/Makevars"
5324 (("PKG_LIBS =" prefix)
5325 (string-append prefix "-larmadillo"))))))))
5326 (propagated-inputs
5327 `(("r-biobase" ,r-biobase)
5328 ("r-biocgenerics" ,r-biocgenerics)
5329 ("r-biocparallel" ,r-biocparallel)
5330 ("r-genefilter" ,r-genefilter)
5331 ("r-geneplotter" ,r-geneplotter)
5332 ("r-genomicranges" ,r-genomicranges)
5333 ("r-ggplot2" ,r-ggplot2)
5334 ("r-hmisc" ,r-hmisc)
5335 ("r-iranges" ,r-iranges)
5336 ("r-locfit" ,r-locfit)
5337 ("r-rcpp" ,r-rcpp)
5338 ("r-rcpparmadillo" ,r-rcpparmadillo)
5339 ("r-s4vectors" ,r-s4vectors)
5340 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5341 (home-page "http://bioconductor.org/packages/DESeq2")
5342 (synopsis "Differential gene expression analysis")
5343 (description
5344 "This package provides functions to estimate variance-mean dependence in
5345count data from high-throughput nucleotide sequencing assays and test for
5346differential expression based on a model using the negative binomial
5347distribution.")
5348 (license license:lgpl3+)))
5349
e8163773
RW		 5350(define-public r-annotationforge
5351 (package
5352 (name "r-annotationforge")
55cd914c 5353 (version "1.16.0")
e8163773
RW		 5354 (source
5355 (origin
5356 (method url-fetch)
5357 (uri (bioconductor-uri "AnnotationForge" version))
5358 (sha256
5359 (base32
55cd914c 5360 "02msyb9p3hywrryx00zpjkjl126mrv827i1ah1092s0cplm6xxvf"))))
e8163773
RW		 5361 (properties
5362 `((upstream-name . "AnnotationForge")))
5363 (build-system r-build-system)
5364 (propagated-inputs
5365 `(("r-annotationdbi" ,r-annotationdbi)
5366 ("r-biobase" ,r-biobase)
5367 ("r-biocgenerics" ,r-biocgenerics)
5368 ("r-dbi" ,r-dbi)
55cd914c 5369 ("r-rcurl" ,r-rcurl)
e8163773
RW		 5370 ("r-rsqlite" ,r-rsqlite)
5371 ("r-s4vectors" ,r-s4vectors)
5372 ("r-xml" ,r-xml)))
5373 (home-page "http://bioconductor.org/packages/AnnotationForge")
5374 (synopsis "Code for building annotation database packages")
5375 (description
5376 "This package provides code for generating Annotation packages and their
5377databases. Packages produced are intended to be used with AnnotationDbi.")
5378 (license license:artistic2.0)))
5379
cd9e7dc7
RW		 5380(define-public r-rbgl
5381 (package
5382 (name "r-rbgl")
700c780d 5383 (version "1.50.0")
cd9e7dc7
RW		 5384 (source
5385 (origin
5386 (method url-fetch)
5387 (uri (bioconductor-uri "RBGL" version))
5388 (sha256
5389 (base32
700c780d 5390 "1q14m8w6ih56v680kf3d9wh1qbgp7af33kz3cxafdf1vvzx9km08"))))
cd9e7dc7
RW		 5391 (properties `((upstream-name . "RBGL")))
5392 (build-system r-build-system)
5393 (propagated-inputs `(("r-graph" ,r-graph)))
5394 (home-page "http://www.bioconductor.org/packages/RBGL")
5395 (synopsis "Interface to the Boost graph library")
5396 (description
5397 "This package provides a fairly extensive and comprehensive interface to
5398the graph algorithms contained in the Boost library.")
5399 (license license:artistic2.0)))
5400
ad740ff8
RW		 5401(define-public r-gseabase
5402 (package
5403 (name "r-gseabase")
558d02c3 5404 (version "1.36.0")
ad740ff8
RW		 5405 (source
5406 (origin
5407 (method url-fetch)
5408 (uri (bioconductor-uri "GSEABase" version))
5409 (sha256
5410 (base32
558d02c3 5411 "0l2x7yj7lfb0m2dmsav5ib026dikpgl4crdckrnj776yy08lgxpj"))))
ad740ff8
RW		 5412 (properties `((upstream-name . "GSEABase")))
5413 (build-system r-build-system)
5414 (propagated-inputs
5415 `(("r-annotate" ,r-annotate)
5416 ("r-annotationdbi" ,r-annotationdbi)
5417 ("r-biobase" ,r-biobase)
5418 ("r-biocgenerics" ,r-biocgenerics)
5419 ("r-graph" ,r-graph)
5420 ("r-xml" ,r-xml)))
5421 (home-page "http://bioconductor.org/packages/GSEABase")
5422 (synopsis "Gene set enrichment data structures and methods")
5423 (description
5424 "This package provides classes and methods to support @dfn{Gene Set
5425Enrichment Analysis} (GSEA).")
5426 (license license:artistic2.0)))
5427
1a1931f7
RW		 5428(define-public r-category
5429 (package
5430 (name "r-category")
816599c1 5431 (version "2.40.0")
1a1931f7
RW		 5432 (source
5433 (origin
5434 (method url-fetch)
5435 (uri (bioconductor-uri "Category" version))
5436 (sha256
5437 (base32
816599c1 5438 "16ncwz7b4y48k0p3fvbrbmvf7nfz63li9ysgcl8kp9kl4hg7llng"))))
1a1931f7
RW		 5439 (properties `((upstream-name . "Category")))
5440 (build-system r-build-system)
5441 (propagated-inputs
5442 `(("r-annotate" ,r-annotate)
5443 ("r-annotationdbi" ,r-annotationdbi)
5444 ("r-biobase" ,r-biobase)
5445 ("r-biocgenerics" ,r-biocgenerics)
5446 ("r-genefilter" ,r-genefilter)
5447 ("r-graph" ,r-graph)
5448 ("r-gseabase" ,r-gseabase)
5449 ("r-matrix" ,r-matrix)
5450 ("r-rbgl" ,r-rbgl)
5451 ("r-rsqlite" ,r-rsqlite)))
5452 (home-page "http://bioconductor.org/packages/Category")
5453 (synopsis "Category analysis")
5454 (description
5455 "This package provides a collection of tools for performing category
5456analysis.")
5457 (license license:artistic2.0)))
5458
89f40c5e
RW		 5459(define-public r-gostats
5460 (package
5461 (name "r-gostats")
ae6899b6 5462 (version "2.40.0")
89f40c5e
RW		 5463 (source
5464 (origin
5465 (method url-fetch)
5466 (uri (bioconductor-uri "GOstats" version))
5467 (sha256
5468 (base32
ae6899b6 5469 "0g2czm94zhzx92z7y2r4mjfxhwml7bhab2db6820ks8nkw1zvr9n"))))
89f40c5e
RW		 5470 (properties `((upstream-name . "GOstats")))
5471 (build-system r-build-system)
5472 (propagated-inputs
5473 `(("r-annotate" ,r-annotate)
5474 ("r-annotationdbi" ,r-annotationdbi)
5475 ("r-annotationforge" ,r-annotationforge)
5476 ("r-biobase" ,r-biobase)
5477 ("r-category" ,r-category)
5478 ("r-go-db" ,r-go-db)
5479 ("r-graph" ,r-graph)
5480 ("r-rbgl" ,r-rbgl)))
5481 (home-page "http://bioconductor.org/packages/GOstats")
5482 (synopsis "Tools for manipulating GO and microarrays")
5483 (description
5484 "This package provides a set of tools for interacting with GO and
5485microarray data. A variety of basic manipulation tools for graphs, hypothesis
5486testing and other simple calculations.")
5487 (license license:artistic2.0)))
5488
cb99d457
RW		 5489(define-public r-shortread
5490 (package
5491 (name "r-shortread")
b87b41a7 5492 (version "1.32.0")
cb99d457
RW		 5493 (source
5494 (origin
5495 (method url-fetch)
5496 (uri (bioconductor-uri "ShortRead" version))
5497 (sha256
5498 (base32
b87b41a7 5499 "0mjdlg92x5qw4x2djc4dv5lxwl7ai6ix56nnf86zr07jk8vc7yls"))))
cb99d457
RW		 5500 (properties `((upstream-name . "ShortRead")))
5501 (build-system r-build-system)
5502 (inputs
5503 `(("zlib" ,zlib)))
5504 (propagated-inputs
5505 `(("r-biobase" ,r-biobase)
5506 ("r-biocgenerics" ,r-biocgenerics)
5507 ("r-biocparallel" ,r-biocparallel)
5508 ("r-biostrings" ,r-biostrings)
5509 ("r-genomeinfodb" ,r-genomeinfodb)
5510 ("r-genomicalignments" ,r-genomicalignments)
5511 ("r-genomicranges" ,r-genomicranges)
5512 ("r-hwriter" ,r-hwriter)
5513 ("r-iranges" ,r-iranges)
5514 ("r-lattice" ,r-lattice)
5515 ("r-latticeextra" ,r-latticeextra)
5516 ("r-rsamtools" ,r-rsamtools)
5517 ("r-s4vectors" ,r-s4vectors)
5518 ("r-xvector" ,r-xvector)
5519 ("r-zlibbioc" ,r-zlibbioc)))
5520 (home-page "http://bioconductor.org/packages/ShortRead")
5521 (synopsis "FASTQ input and manipulation tools")
5522 (description
5523 "This package implements sampling, iteration, and input of FASTQ files.
5524It includes functions for filtering and trimming reads, and for generating a
5525quality assessment report. Data are represented as
5526@code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5527purposes. The package also contains legacy support for early single-end,
5528ungapped alignment formats.")
5529 (license license:artistic2.0)))
5530
7f903d73
RW		 5531(define-public r-systempiper
5532 (package
5533 (name "r-systempiper")
1265d387 5534 (version "1.8.1")
7f903d73
RW		 5535 (source
5536 (origin
5537 (method url-fetch)
5538 (uri (bioconductor-uri "systemPipeR" version))
5539 (sha256
5540 (base32
1265d387 5541 "0hyi841w8fm2yzpm6lwqi3jz5kc8ny8dy5p29dxynzaw5bpjw56d"))))
7f903d73
RW		 5542 (properties `((upstream-name . "systemPipeR")))
5543 (build-system r-build-system)
5544 (propagated-inputs
5545 `(("r-annotate" ,r-annotate)
5546 ("r-batchjobs" ,r-batchjobs)
5547 ("r-biocgenerics" ,r-biocgenerics)
5548 ("r-biostrings" ,r-biostrings)
5549 ("r-deseq2" ,r-deseq2)
5550 ("r-edger" ,r-edger)
5551 ("r-genomicfeatures" ,r-genomicfeatures)
5552 ("r-genomicranges" ,r-genomicranges)
5553 ("r-ggplot2" ,r-ggplot2)
5554 ("r-go-db" ,r-go-db)
5555 ("r-gostats" ,r-gostats)
5556 ("r-limma" ,r-limma)
5557 ("r-pheatmap" ,r-pheatmap)
5558 ("r-rjson" ,r-rjson)
5559 ("r-rsamtools" ,r-rsamtools)
5560 ("r-shortread" ,r-shortread)
5561 ("r-summarizedexperiment" ,r-summarizedexperiment)
5562 ("r-variantannotation" ,r-variantannotation)))
5563 (home-page "https://github.com/tgirke/systemPipeR")
5564 (synopsis "Next generation sequencing workflow and reporting environment")
5565 (description
5566 "This R package provides tools for building and running automated
5567end-to-end analysis workflows for a wide range of @dfn{next generation
5568sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5569Important features include a uniform workflow interface across different NGS
5570applications, automated report generation, and support for running both R and
5571command-line software, such as NGS aligners or peak/variant callers, on local
5572computers or compute clusters. Efficient handling of complex sample sets and
5573experimental designs is facilitated by a consistently implemented sample
5574annotation infrastructure.")
5575 (license license:artistic2.0)))
5576
684f29bd
RW		 5577(define-public r-grohmm
5578 (package
5579 (name "r-grohmm")
c9b5046a 5580 (version "1.8.0")
684f29bd
RW		 5581 (source
5582 (origin
5583 (method url-fetch)
5584 (uri (bioconductor-uri "groHMM" version))
5585 (sha256
5586 (base32
c9b5046a 5587 "0d91nyhqbi5hv3mgmr2z0g29wg2md26g0hyv5mgapmz20cd9zi4y"))))
684f29bd
RW		 5588 (properties `((upstream-name . "groHMM")))
5589 (build-system r-build-system)
5590 (propagated-inputs
5591 `(("r-genomeinfodb" ,r-genomeinfodb)
5592 ("r-genomicalignments" ,r-genomicalignments)
5593 ("r-genomicranges" ,r-genomicranges)
5594 ("r-iranges" ,r-iranges)
5595 ("r-rtracklayer" ,r-rtracklayer)
5596 ("r-s4vectors" ,r-s4vectors)))
5597 (home-page "https://github.com/Kraus-Lab/groHMM")
5598 (synopsis "GRO-seq analysis pipeline")
5599 (description
5600 "This package provides a pipeline for the analysis of GRO-seq data.")
5601 (license license:gpl3+)))
5602
f3cfe451
RW		 5603(define-public r-txdb-hsapiens-ucsc-hg19-knowngene
5604 (package
5605 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
5606 (version "3.2.2")
5607 (source (origin
5608 (method url-fetch)
5609 ;; We cannot use bioconductor-uri here because this tarball is
5610 ;; located under "data/annotation/" instead of "bioc/".
5611 (uri (string-append "http://bioconductor.org/packages/"
5612 "release/data/annotation/src/contrib"
5613 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
5614 version ".tar.gz"))
5615 (sha256
5616 (base32
5617 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
5618 (properties
5619 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
5620 (build-system r-build-system)
5621 ;; As this package provides little more than a very large data file it
5622 ;; doesn't make sense to build substitutes.
5623 (arguments `(#:substitutable? #f))
5624 (propagated-inputs
5625 `(("r-genomicfeatures" ,r-genomicfeatures)))
5626 (home-page
5627 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
5628 (synopsis "Annotation package for human genome in TxDb format")
5629 (description
5630 "This package provides an annotation database of Homo sapiens genome
5631data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
5632track. The database is exposed as a @code{TxDb} object.")
5633 (license license:artistic2.0)))
5634
a2950fa4
BW		 5635(define-public vsearch
5636 (package
5637 (name "vsearch")
a225db52 5638 (version "2.3.4")
a2950fa4
BW		 5639 (source
5640 (origin
5641 (method url-fetch)
5642 (uri (string-append
5643 "https://github.com/torognes/vsearch/archive/v"
5644 version ".tar.gz"))
5645 (file-name (string-append name "-" version ".tar.gz"))
5646 (sha256
5647 (base32
a225db52 5648 "1xyraxmhyx62mxx8z7c8waygvcijwkh48ms1ar60w2cv2y2sn4al"))
a2950fa4
BW		 5649 (modules '((guix build utils)))
5650 (snippet
5651 '(begin
5652 ;; Remove bundled cityhash and '-mtune=native'.
5653 (substitute* "src/Makefile.am"
5654 (("^AM_CXXFLAGS=-I\\$\\{srcdir\\}/cityhash \
5655-O3 -mtune=native -Wall -Wsign-compare")
5656 (string-append "AM_CXXFLAGS=-lcityhash"
5657 " -O3 -Wall -Wsign-compare"))
cf6edaba 5658 (("^__top_builddir__bin_vsearch_SOURCES = city.h \\\\")
a2950fa4 5659 "__top_builddir__bin_vsearch_SOURCES = \\")
cf6edaba
BW		 5660 (("^city.h \\\\") "\\")
5661 (("^citycrc.h \\\\") "\\")
5662 (("^libcityhash_a.*") "")
5663 (("noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a \
5664libcityhash.a")
5665 "noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a")
5666 (("__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
5667libcpu_sse2.a libcityhash.a")
5668 "__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
5669libcpu_sse2.a -lcityhash"))
a2950fa4 5670 (substitute* "src/vsearch.h"
cf6edaba
BW		 5671 (("^\\#include \"city.h\"") "#include <city.h>")
5672 (("^\\#include \"citycrc.h\"") "#include <citycrc.h>"))
5673 (delete-file "src/city.h")
5674 (delete-file "src/citycrc.h")
5675 (delete-file "src/city.cc")
a2950fa4
BW		 5676 #t))))
5677 (build-system gnu-build-system)
5678 (arguments
5679 `(#:phases
5680 (modify-phases %standard-phases
5681 (add-before 'configure 'autogen
5682 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
5683 (inputs
5684 `(("zlib" ,zlib)
5685 ("bzip2" ,bzip2)
5686 ("cityhash" ,cityhash)))
5687 (native-inputs
5688 `(("autoconf" ,autoconf)
5689 ("automake" ,automake)))
5690 (synopsis "Sequence search tools for metagenomics")
5691 (description
5692 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
5693dereplication, pairwise alignment, shuffling, subsampling, sorting and
5694masking. The tool takes advantage of parallelism in the form of SIMD
5695vectorization as well as multiple threads to perform accurate alignments at
5696high speed. VSEARCH uses an optimal global aligner (full dynamic programming
5697Needleman-Wunsch).")
5698 (home-page "https://github.com/torognes/vsearch")
6f04e515
BW		 5699 ;; vsearch uses non-portable SSE intrinsics so building fails on other
5700 ;; platforms.
5701 (supported-systems '("x86_64-linux"))
a2950fa4
BW		 5702 ;; Dual licensed; also includes public domain source.
5703 (license (list license:gpl3 license:bsd-2))))
5704
07837874
RW		 5705(define-public pardre
5706 (package
5707 (name "pardre")
7922ab8f
BW		 5708 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
5709 (version "1.1.5-1")
07837874
RW		 5710 (source
5711 (origin
5712 (method url-fetch)
5713 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7922ab8f 5714 "1.1.5" ".tar.gz"))
07837874
RW		 5715 (sha256
5716 (base32
7922ab8f 5717 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
07837874
RW		 5718 (build-system gnu-build-system)
5719 (arguments
5720 `(#:tests? #f ; no tests included
5721 #:phases
5722 (modify-phases %standard-phases
5723 (delete 'configure)
5724 (replace 'install
5725 (lambda* (#:key outputs #:allow-other-keys)
5726 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
07837874
RW		 5727 (install-file "ParDRe" bin)
5728 #t))))))
5729 (inputs
5730 `(("openmpi" ,openmpi)
5731 ("zlib" ,zlib)))
5732 (synopsis "Parallel tool to remove duplicate DNA reads")
5733 (description
5734 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
5735Duplicate reads can be seen as identical or nearly identical sequences with
5736some mismatches. This tool lets users avoid the analysis of unnecessary
5737reads, reducing the time of subsequent procedures with the
5738dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
5739in order to exploit the parallel capabilities of multicore clusters. It is
5740faster than multithreaded counterparts (end of 2015) for the same number of
5741cores and, thanks to the message-passing technology, it can be executed on
5742clusters.")
5743 (home-page "https://sourceforge.net/projects/pardre/")
5744 (license license:gpl3+)))
5745
e4a44a6a
BW		 5746(define-public ruby-bio-kseq
5747 (package
5748 (name "ruby-bio-kseq")
5749 (version "0.0.2")
5750 (source
5751 (origin
5752 (method url-fetch)
5753 (uri (rubygems-uri "bio-kseq" version))
5754 (sha256
5755 (base32
5756 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
5757 (build-system ruby-build-system)
5758 (arguments
5759 `(#:test-target "spec"))
5760 (native-inputs
5761 `(("bundler" ,bundler)
5762 ("ruby-rspec" ,ruby-rspec)
5763 ("ruby-rake-compiler" ,ruby-rake-compiler)))
5764 (inputs
5765 `(("zlib" ,zlib)))
5766 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
5767 (description
5768 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
5769FASTQ parsing code. It provides a fast iterator over sequences and their
5770quality scores.")
5771 (home-page "https://github.com/gusevfe/bio-kseq")
5772 (license license:expat)))
5773
9c38b540
PP		 5774(define-public bio-locus
5775 (package
5776 (name "bio-locus")
5777 (version "0.0.7")
5778 (source
5779 (origin
5780 (method url-fetch)
5781 (uri (rubygems-uri "bio-locus" version))
5782 (sha256
5783 (base32
5784 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
5785 (build-system ruby-build-system)
5786 (native-inputs
5787 `(("ruby-rspec" ,ruby-rspec)))
5788 (synopsis "Tool for fast querying of genome locations")
5789 (description
5790 "Bio-locus is a tabix-like tool for fast querying of genome
5791locations. Many file formats in bioinformatics contain records that
5792start with a chromosome name and a position for a SNP, or a start-end
5793position for indels. Bio-locus allows users to store this chr+pos or
5794chr+pos+alt information in a database.")
5795 (home-page "https://github.com/pjotrp/bio-locus")
5796 (license license:expat)))
edb15985 5797
b2bddb07
PP		 5798(define-public bio-blastxmlparser
5799 (package
5800 (name "bio-blastxmlparser")
5801 (version "2.0.4")
5802 (source (origin
5803 (method url-fetch)
5804 (uri (rubygems-uri "bio-blastxmlparser" version))
5805 (sha256
5806 (base32
5807 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
5808 (build-system ruby-build-system)
5809 (propagated-inputs
5810 `(("ruby-bio-logger" ,ruby-bio-logger)
5811 ("ruby-nokogiri" ,ruby-nokogiri)))
5812 (inputs
5813 `(("ruby-rspec" ,ruby-rspec)))
5814 (synopsis "Fast big data BLAST XML parser and library")
5815 (description
5816 "Very fast parallel big-data BLAST XML file parser which can be used as
5817command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
5818generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
5819 (home-page "http://github.com/pjotrp/blastxmlparser")
5820 (license license:expat)))
5821
edb15985
PP		 5822(define-public bioruby
5823 (package
5824 (name "bioruby")
5825 (version "1.5.0")
5826 (source
5827 (origin
5828 (method url-fetch)
5829 (uri (rubygems-uri "bio" version))
5830 (sha256
5831 (base32
5832 "01k2fyjl5fpx4zn8g6gqiqvsg2j1fgixrs9p03vzxckynxdq3wmc"))))
5833 (build-system ruby-build-system)
5834 (propagated-inputs
5835 `(("ruby-libxml" ,ruby-libxml)))
5836 (native-inputs
5837 `(("which" ,which))) ; required for test phase
5838 (arguments
5839 `(#:phases
5840 (modify-phases %standard-phases
5841 (add-before 'build 'patch-test-command
5842 (lambda _
5843 (substitute* '("test/functional/bio/test_command.rb")
5844 (("/bin/sh") (which "sh")))
5845 (substitute* '("test/functional/bio/test_command.rb")
5846 (("/bin/ls") (which "ls")))
5847 (substitute* '("test/functional/bio/test_command.rb")
5848 (("which") (which "which")))
5849 (substitute* '("test/functional/bio/test_command.rb",
5850 "test/data/command/echoarg2.sh")
5851 (("/bin/echo") (which "echo")))
5852 #t)))))
5853 (synopsis "Ruby library, shell and utilities for bioinformatics")
5854 (description "BioRuby comes with a comprehensive set of Ruby development
5855tools and libraries for bioinformatics and molecular biology. BioRuby has
5856components for sequence analysis, pathway analysis, protein modelling and
5857phylogenetic analysis; it supports many widely used data formats and provides
5858easy access to databases, external programs and public web services, including
5859BLAST, KEGG, GenBank, MEDLINE and GO.")
5860 (home-page "http://bioruby.org/")
5861 ;; Code is released under Ruby license, except for setup
5862 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
5863 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
a5002ae7 5864
9fba89e8
RW		 5865(define-public r-acsnminer
5866 (package
5867 (name "r-acsnminer")
0b54b4c9 5868 (version "0.16.8.25")
9fba89e8
RW		 5869 (source (origin
5870 (method url-fetch)
5871 (uri (cran-uri "ACSNMineR" version))
5872 (sha256
5873 (base32
0b54b4c9 5874 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
9fba89e8
RW		 5875 (properties `((upstream-name . "ACSNMineR")))
5876 (build-system r-build-system)
5877 (propagated-inputs
5878 `(("r-ggplot2" ,r-ggplot2)
5879 ("r-gridextra" ,r-gridextra)))
5880 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
5881 (synopsis "Gene enrichment analysis")
5882 (description
5883 "This package provides tools to compute and represent gene set enrichment
5884or depletion from your data based on pre-saved maps from the @dfn{Atlas of
5885Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
5886enrichment can be run with hypergeometric test or Fisher exact test, and can
5887use multiple corrections. Visualization of data can be done either by
5888barplots or heatmaps.")
5889 (license license:gpl2+)))
5890
d29b25c4
RW		 5891(define-public r-biocgenerics
5892 (package
5893 (name "r-biocgenerics")
f0b297e1 5894 (version "0.20.0")
d29b25c4
RW		 5895 (source (origin
5896 (method url-fetch)
5897 (uri (bioconductor-uri "BiocGenerics" version))
5898 (sha256
5899 (base32
f0b297e1 5900 "06szdz7dfs1iyv5zdl4fjzad18nnf1zf3wvglc6c6yd9mrqlf7vk"))))
d29b25c4 5901 (properties
1d216b6e 5902 `((upstream-name . "BiocGenerics")))
d29b25c4
RW		 5903 (build-system r-build-system)
5904 (home-page "http://bioconductor.org/packages/BiocGenerics")
5905 (synopsis "S4 generic functions for Bioconductor")
5906 (description
5907 "This package provides S4 generic functions needed by many Bioconductor
5908packages.")
5909 (license license:artistic2.0)))
5910
eb24341f
RJ		 5911(define-public r-biocinstaller
5912 (package
5913 (name "r-biocinstaller")
5c7b04e0 5914 (version "1.24.0")
eb24341f
RJ		 5915 (source (origin
5916 (method url-fetch)
5917 (uri (bioconductor-uri "BiocInstaller" version))
5918 (sha256
5919 (base32
5c7b04e0 5920 "0y1y5wmy6lzjqx3hdg15n91d417ccjj8dbvdkhmp99bs5aijwcpn"))))
eb24341f
RJ		 5921 (properties
5922 `((upstream-name . "BiocInstaller")))
5923 (build-system r-build-system)
5924 (home-page "http://bioconductor.org/packages/BiocInstaller")
5925 (synopsis "Install Bioconductor packages")
5926 (description "This package is used to install and update R packages from
5927Bioconductor, CRAN, and Github.")
5928 (license license:artistic2.0)))
5929
207ce8fb
RJ		 5930(define-public r-biocviews
5931 (package
5932 (name "r-biocviews")
5933 (version "1.42.0")
5934 (source (origin
5935 (method url-fetch)
5936 (uri (bioconductor-uri "biocViews" version))
5937 (sha256
5938 (base32
5939 "07rjk10b91pkriyq297w86199r2d3sfji3ggs9mq2gyalsa8y4b6"))))
5940 (properties
5941 `((upstream-name . "biocViews")))
5942 (build-system r-build-system)
5943 (propagated-inputs
5944 `(("r-biobase" ,r-biobase)
5945 ("r-graph" ,r-graph)
5946 ("r-rbgl" ,r-rbgl)
5947 ("r-rcurl" ,r-rcurl)
5948 ("r-xml" ,r-xml)
5949 ("r-knitr" ,r-knitr)
5950 ("r-runit" ,r-runit)))
5951 (home-page "http://bioconductor.org/packages/biocViews")
5952 (synopsis "Bioconductor package categorization helper")
5953 (description "The purpose of biocViews is to create HTML pages that
5954categorize packages in a Bioconductor package repository according to keywords,
5955also known as views, in a controlled vocabulary.")
5956 (license license:artistic2.0)))
5957
99df12cd
RJ		 5958(define-public r-biocstyle
5959 (package
5960 (name "r-biocstyle")
c8ad8b69 5961 (version "2.2.1")
99df12cd
RJ		 5962 (source (origin
5963 (method url-fetch)
5964 (uri (bioconductor-uri "BiocStyle" version))
5965 (sha256
5966 (base32
c8ad8b69 5967 "0sl99xw940ixrm6v24lgaw3ljh56g59a6rdz7g160hx84z9f8n2n"))))
99df12cd
RJ		 5968 (properties
5969 `((upstream-name . "BiocStyle")))
5970 (build-system r-build-system)
5971 (home-page "http://bioconductor.org/packages/BiocStyle")
5972 (synopsis "Bioconductor formatting styles")
5973 (description "This package provides standard formatting styles for
5974Bioconductor PDF and HTML documents. Package vignettes illustrate use and
5975functionality.")
5976 (license license:artistic2.0)))
5977
4644644a
RJ		 5978(define-public r-bioccheck
5979 (package
5980 (name "r-bioccheck")
5981 (version "1.10.0")
5982 (source (origin
5983 (method url-fetch)
5984 (uri (bioconductor-uri "BiocCheck" version))
5985 (sha256
5986 (base32
5987 "1rfy37xg1nc2cmgbclvzsi7sgmdcdjiahsx9crgx3yaw7kxgiack"))))
5988 (properties
5989 `((upstream-name . "BiocCheck")))
5990 (build-system r-build-system)
5991 (arguments
5992 '(#:phases
5993 (modify-phases %standard-phases
5994 ;; This package can be used by calling BiocCheck(<package>) from
5995 ;; within R, or by running R CMD BiocCheck <package>. This phase
5996 ;; makes sure the latter works. For this to work, the BiocCheck
5997 ;; script must be somewhere on the PATH (not the R bin directory).
5998 (add-after 'install 'install-bioccheck-subcommand
5999 (lambda* (#:key outputs #:allow-other-keys)
6000 (let* ((out (assoc-ref outputs "out"))
6001 (dest-dir (string-append out "/bin"))
6002 (script-dir
6003 (string-append out "/site-library/BiocCheck/script/")))
6004 (mkdir-p dest-dir)
6005 (symlink (string-append script-dir "/checkBadDeps.R")
6006 (string-append dest-dir "/checkBadDeps.R"))
6007 (symlink (string-append script-dir "/BiocCheck")
6008 (string-append dest-dir "/BiocCheck")))
6009 #t)))))
6010 (native-inputs
6011 `(("which" ,which)))
6012 (propagated-inputs
6013 `(("r-graph" ,r-graph)
6014 ("r-knitr" ,r-knitr)
6015 ("r-httr" ,r-httr)
6016 ("r-optparse" ,r-optparse)
6017 ("r-devtools" ,r-devtools)
6018 ("r-biocinstaller" ,r-biocinstaller)
6019 ("r-biocviews" ,r-biocviews)))
6020 (home-page "http://bioconductor.org/packages/BiocCheck")
6021 (synopsis "Executes Bioconductor-specific package checks")
6022 (description "This package contains tools to perform additional quality
6023checks on R packages that are to be submitted to the Bioconductor repository.")
6024 (license license:artistic2.0)))
6025
2acaaee5
RJ		 6026(define-public r-getopt
6027 (package
6028 (name "r-getopt")
6029 (version "1.20.0")
6030 (source
6031 (origin
6032 (method url-fetch)
6033 (uri (cran-uri "getopt" version))
6034 (sha256
6035 (base32
6036 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6037 (build-system r-build-system)
6038 (home-page "https://github.com/trevorld/getopt")
6039 (synopsis "Command-line option processor for R")
6040 (description
6041 "This package is designed to be used with Rscript to write shebang
6042scripts that accept short and long options. Many users will prefer to
6043use the packages @code{optparse} or @code{argparse} which add extra
6044features like automatically generated help options and usage texts,
6045support for default values, positional argument support, etc.")
6046 (license license:gpl2+)))
6047
c79ad57a
RJ		 6048(define-public r-optparse
6049 (package
6050 (name "r-optparse")
6051 (version "1.3.2")
6052 (source
6053 (origin
6054 (method url-fetch)
6055 (uri (cran-uri "optparse" version))
6056 (sha256
6057 (base32
6058 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6059 (build-system r-build-system)
6060 (propagated-inputs
6061 `(("r-getopt" ,r-getopt)))
6062 (home-page
6063 "https://github.com/trevorld/optparse")
6064 (synopsis "Command line option parser")
6065 (description
6066 "This package provides a command line parser inspired by Python's
6067@code{optparse} library to be used with Rscript to write shebang scripts
6068that accept short and long options.")
6069 (license license:gpl2+)))
6070
247d498a
RJ		 6071(define-public r-dnacopy
6072 (package
6073 (name "r-dnacopy")
22c5d736 6074 (version "1.48.0")
247d498a
RJ		 6075 (source (origin
6076 (method url-fetch)
6077 (uri (bioconductor-uri "DNAcopy" version))
6078 (sha256
6079 (base32
22c5d736 6080 "1idyvfvy7xx8k9vk00y4k3819qmip8iqm809j3vpxabmsn7r9zyh"))))
247d498a
RJ		 6081 (properties
6082 `((upstream-name . "DNAcopy")))
6083 (build-system r-build-system)
6084 (inputs
6085 `(("gfortran" ,gfortran)))
5697fdc3 6086 (home-page "https://bioconductor.org/packages/DNAcopy")
247d498a
RJ		 6087 (synopsis "Implementation of a circular binary segmentation algorithm")
6088 (description "This package implements the circular binary segmentation (CBS)
6089algorithm to segment DNA copy number data and identify genomic regions with
6090abnormal copy number.")
6091 (license license:gpl2+)))
6092
7485129e
RW		 6093(define-public r-s4vectors
6094 (package
6095 (name "r-s4vectors")
86fc9c4a 6096 (version "0.12.1")
7485129e
RW		 6097 (source (origin
6098 (method url-fetch)
6099 (uri (bioconductor-uri "S4Vectors" version))
6100 (sha256
6101 (base32
86fc9c4a 6102 "0i36y3w36h3d8rmazxcrip4gvn54rd9av1wz4lygsprrjmylfhcc"))))
7485129e 6103 (properties
1d216b6e 6104 `((upstream-name . "S4Vectors")))
7485129e
RW		 6105 (build-system r-build-system)
6106 (propagated-inputs
6107 `(("r-biocgenerics" ,r-biocgenerics)))
6108 (home-page "http://bioconductor.org/packages/S4Vectors")
6109 (synopsis "S4 implementation of vectors and lists")
6110 (description
6111 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6112classes and a set of generic functions that extend the semantic of ordinary
6113vectors and lists in R. Package developers can easily implement vector-like
6114or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6115In addition, a few low-level concrete subclasses of general interest (e.g.
6116@code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6117S4Vectors package itself.")
6118 (license license:artistic2.0)))
6119
274da826
RW		 6120(define-public r-seqinr
6121 (package
6122 (name "r-seqinr")
a46cc723 6123 (version "3.3-3")
274da826
RW		 6124 (source
6125 (origin
6126 (method url-fetch)
6127 (uri (cran-uri "seqinr" version))
6128 (sha256
6129 (base32
a46cc723 6130 "0rk4yba8km26c0rh1f4h474zsb5n6kjmqsi55bnzr6p8pymp18hj"))))
274da826
RW		 6131 (build-system r-build-system)
6132 (propagated-inputs
3b851cd4
RW		 6133 `(("r-ade4" ,r-ade4)
6134 ("r-segmented" ,r-segmented)))
274da826
RW		 6135 (inputs
6136 `(("zlib" ,zlib)))
6137 (home-page "http://seqinr.r-forge.r-project.org/")
6138 (synopsis "Biological sequences retrieval and analysis")
6139 (description
6140 "This package provides tools for exploratory data analysis and data
6141visualization of biological sequence (DNA and protein) data. It also includes
6142utilities for sequence data management under the ACNUC system.")
6143 (license license:gpl2+)))
6144
78addcb0
RW		 6145(define-public r-iranges
6146 (package
6147 (name "r-iranges")
54d9b568 6148 (version "2.8.1")
78addcb0
RW		 6149 (source (origin
6150 (method url-fetch)
6151 (uri (bioconductor-uri "IRanges" version))
6152 (sha256
6153 (base32
54d9b568 6154 "0cryqnpqb3p6l9jjw27hyqd550sxlljls3ka7b9rb38hkji7b5hw"))))
78addcb0 6155 (properties
1d216b6e 6156 `((upstream-name . "IRanges")))
78addcb0
RW		 6157 (build-system r-build-system)
6158 (propagated-inputs
6159 `(("r-biocgenerics" ,r-biocgenerics)
6160 ("r-s4vectors" ,r-s4vectors)))
6161 (home-page "http://bioconductor.org/packages/IRanges")
6162 (synopsis "Infrastructure for manipulating intervals on sequences")
6163 (description
6164 "This package provides efficient low-level and highly reusable S4 classes
6165for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6166generally, data that can be organized sequentially (formally defined as
6167@code{Vector} objects), as well as views on these @code{Vector} objects.
6168Efficient list-like classes are also provided for storing big collections of
6169instances of the basic classes. All classes in the package use consistent
6170naming and share the same rich and consistent \"Vector API\" as much as
6171possible.")
6172 (license license:artistic2.0)))
6173
bf7764b7
RW		 6174(define-public r-genomeinfodb
6175 (package
6176 (name "r-genomeinfodb")
81a17b61 6177 (version "1.10.1")
bf7764b7
RW		 6178 (source (origin
6179 (method url-fetch)
6180 (uri (bioconductor-uri "GenomeInfoDb" version))
6181 (sha256
6182 (base32
81a17b61 6183 "1d3wwlzx0dk08wps35ilr4mg3f29f0fa72hcnzzsp5npaaxi1zrk"))))
bf7764b7 6184 (properties
1d216b6e 6185 `((upstream-name . "GenomeInfoDb")))
bf7764b7
RW		 6186 (build-system r-build-system)
6187 (propagated-inputs
6188 `(("r-biocgenerics" ,r-biocgenerics)
6189 ("r-iranges" ,r-iranges)
6190 ("r-s4vectors" ,r-s4vectors)))
6191 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6192 (synopsis "Utilities for manipulating chromosome identifiers")
6193 (description
6194 "This package contains data and functions that define and allow
6195translation between different chromosome sequence naming conventions (e.g.,
6196\"chr1\" versus \"1\"), including a function that attempts to place sequence
6197names in their natural, rather than lexicographic, order.")
6198 (license license:artistic2.0)))
6199
744004a3
RJ		 6200(define-public r-edger
6201 (package
6202 (name "r-edger")
5d3acc0b 6203 (version "3.16.5")
744004a3
RJ		 6204 (source (origin
6205 (method url-fetch)
6206 (uri (bioconductor-uri "edgeR" version))
6207 (sha256
6208 (base32
5d3acc0b 6209 "04vpa0a6dkkjyvvfbkmfjyaxf2ldkagi66g028qpaszd8jsk8yiv"))))
744004a3
RJ		 6210 (properties `((upstream-name . "edgeR")))
6211 (build-system r-build-system)
6212 (propagated-inputs
5e48005f
RW		 6213 `(("r-limma" ,r-limma)
6214 ("r-locfit" ,r-locfit)))
744004a3
RJ		 6215 (home-page "http://bioinf.wehi.edu.au/edgeR")
6216 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6217 (description "This package can do differential expression analysis of
6218RNA-seq expression profiles with biological replication. It implements a range
6219of statistical methodology based on the negative binomial distributions,
6220including empirical Bayes estimation, exact tests, generalized linear models
6221and quasi-likelihood tests. It be applied to differential signal analysis of
6222other types of genomic data that produce counts, including ChIP-seq, SAGE and
6223CAGE.")
6224 (license license:gpl2+)))
6225
b669d9c4
RJ		 6226(define-public r-variantannotation
6227 (package
6228 (name "r-variantannotation")
37d96f1d 6229 (version "1.20.0")
b669d9c4
RJ		 6230 (source (origin
6231 (method url-fetch)
6232 (uri (bioconductor-uri "VariantAnnotation" version))
6233 (sha256
6234 (base32
37d96f1d 6235 "1lwzfgahz8ipwli73kcfqb18y6adi129hap1gnycnj3980m54i8q"))))
b669d9c4
RJ		 6236 (properties
6237 `((upstream-name . "VariantAnnotation")))
6238 (inputs
6239 `(("zlib" ,zlib)))
6240 (propagated-inputs
6241 `(("r-annotationdbi" ,r-annotationdbi)
37d96f1d 6242 ("r-biobase" ,r-biobase)
b669d9c4 6243 ("r-biocgenerics" ,r-biocgenerics)
37d96f1d 6244 ("r-biostrings" ,r-biostrings)
b669d9c4
RJ		 6245 ("r-bsgenome" ,r-bsgenome)
6246 ("r-dbi" ,r-dbi)
6247 ("r-genomeinfodb" ,r-genomeinfodb)
6248 ("r-genomicfeatures" ,r-genomicfeatures)
6249 ("r-genomicranges" ,r-genomicranges)
37d96f1d 6250 ("r-iranges" ,r-iranges)
b669d9c4
RJ		 6251 ("r-summarizedexperiment" ,r-summarizedexperiment)
6252 ("r-rsamtools" ,r-rsamtools)
37d96f1d
RW		 6253 ("r-rtracklayer" ,r-rtracklayer)
6254 ("r-s4vectors" ,r-s4vectors)
6255 ("r-xvector" ,r-xvector)
b669d9c4
RJ		 6256 ("r-zlibbioc" ,r-zlibbioc)))
6257 (build-system r-build-system)
6258 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6259 (synopsis "Package for annotation of genetic variants")
6260 (description "This R package can annotate variants, compute amino acid
6261coding changes and predict coding outcomes.")
6262 (license license:artistic2.0)))
6263
7d4224d7
RJ		 6264(define-public r-limma
6265 (package
6266 (name "r-limma")
5b3b2d2f 6267 (version "3.30.2")
7d4224d7
RJ		 6268 (source (origin
6269 (method url-fetch)
6270 (uri (bioconductor-uri "limma" version))
6271 (sha256
6272 (base32
5b3b2d2f 6273 "04jris7wk2lxksrrvrjsysznsdb2k04lfgrnp18ic49sazva0hfy"))))
7d4224d7
RJ		 6274 (build-system r-build-system)
6275 (home-page "http://bioinf.wehi.edu.au/limma")
6276 (synopsis "Package for linear models for microarray and RNA-seq data")
6277 (description "This package can be used for the analysis of gene expression
6278studies, especially the use of linear models for analysing designed experiments
6279and the assessment of differential expression. The analysis methods apply to
6280different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6281 (license license:gpl2+)))
6282
0e7d5560
RW		 6283(define-public r-xvector
6284 (package
6285 (name "r-xvector")
1d048589 6286 (version "0.14.0")
0e7d5560
RW		 6287 (source (origin
6288 (method url-fetch)
6289 (uri (bioconductor-uri "XVector" version))
6290 (sha256
6291 (base32
1d048589 6292 "09lbqxpqr80g0kw77mpz0p1a8cq706j33kz8194wp71il67cdzi7"))))
0e7d5560 6293 (properties
1d216b6e 6294 `((upstream-name . "XVector")))
0e7d5560
RW		 6295 (build-system r-build-system)
6296 (arguments
6297 `(#:phases
6298 (modify-phases %standard-phases
6299 (add-after 'unpack 'use-system-zlib
6300 (lambda _
6301 (substitute* "DESCRIPTION"
6302 (("zlibbioc, ") ""))
6303 (substitute* "NAMESPACE"
6304 (("import\\(zlibbioc\\)") ""))
6305 #t)))))
6306 (inputs
6307 `(("zlib" ,zlib)))
6308 (propagated-inputs
6309 `(("r-biocgenerics" ,r-biocgenerics)
6310 ("r-iranges" ,r-iranges)
6311 ("r-s4vectors" ,r-s4vectors)))
6312 (home-page "http://bioconductor.org/packages/XVector")
6313 (synopsis "Representation and manpulation of external sequences")
6314 (description
6315 "This package provides memory efficient S4 classes for storing sequences
6316\"externally\" (behind an R external pointer, or on disk).")
6317 (license license:artistic2.0)))
6318
e2cd1d0f
RW		 6319(define-public r-genomicranges
6320 (package
6321 (name "r-genomicranges")
92a740af 6322 (version "1.26.1")
e2cd1d0f
RW		 6323 (source (origin
6324 (method url-fetch)
6325 (uri (bioconductor-uri "GenomicRanges" version))
6326 (sha256
6327 (base32
92a740af 6328 "039nxccg9i2an8q2wni79x8dr9p1fcfcqvih9hg9w243pczg2g3c"))))
e2cd1d0f 6329 (properties
1d216b6e 6330 `((upstream-name . "GenomicRanges")))
e2cd1d0f
RW		 6331 (build-system r-build-system)
6332 (propagated-inputs
6333 `(("r-biocgenerics" ,r-biocgenerics)
6334 ("r-genomeinfodb" ,r-genomeinfodb)
92a740af
RW		 6335 ("r-iranges" ,r-iranges)
6336 ("r-s4vectors" ,r-s4vectors)
e2cd1d0f
RW		 6337 ("r-xvector" ,r-xvector)))
6338 (home-page "http://bioconductor.org/packages/GenomicRanges")
6339 (synopsis "Representation and manipulation of genomic intervals")
6340 (description
6341 "This package provides tools to efficiently represent and manipulate
6342genomic annotations and alignments is playing a central role when it comes to
6343analyzing high-throughput sequencing data (a.k.a. NGS data). The
6344GenomicRanges package defines general purpose containers for storing and
6345manipulating genomic intervals and variables defined along a genome.")
6346 (license license:artistic2.0)))
6347
555e3399
RW		 6348(define-public r-biobase
6349 (package
6350 (name "r-biobase")
464870ca 6351 (version "2.34.0")
555e3399
RW		 6352 (source (origin
6353 (method url-fetch)
6354 (uri (bioconductor-uri "Biobase" version))
6355 (sha256
6356 (base32
464870ca 6357 "0js9j9wqls8f571ifl9ylllbb9a9hwf7b7drf2grwb1fl31ldazl"))))
555e3399
RW		 6358 (properties
6359 `((upstream-name . "Biobase")))
6360 (build-system r-build-system)
6361 (propagated-inputs
6362 `(("r-biocgenerics" ,r-biocgenerics)))
6363 (home-page "http://bioconductor.org/packages/Biobase")
6364 (synopsis "Base functions for Bioconductor")
6365 (description
6366 "This package provides functions that are needed by many other packages
6367on Bioconductor or which replace R functions.")
6368 (license license:artistic2.0)))
6369
8b7bce74
RW		 6370(define-public r-annotationdbi
6371 (package
6372 (name "r-annotationdbi")
e45dc057 6373 (version "1.36.0")
8b7bce74
RW		 6374 (source (origin
6375 (method url-fetch)
6376 (uri (bioconductor-uri "AnnotationDbi" version))
6377 (sha256
6378 (base32
e45dc057 6379 "0ydrqw1k1j5p6w76bwc753cx545c055x88q87wzya93858synj6r"))))
8b7bce74
RW		 6380 (properties
6381 `((upstream-name . "AnnotationDbi")))
6382 (build-system r-build-system)
6383 (propagated-inputs
6384 `(("r-biobase" ,r-biobase)
6385 ("r-biocgenerics" ,r-biocgenerics)
6386 ("r-dbi" ,r-dbi)
6387 ("r-iranges" ,r-iranges)
6388 ("r-rsqlite" ,r-rsqlite)
6389 ("r-s4vectors" ,r-s4vectors)))
6390 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6391 (synopsis "Annotation database interface")
6392 (description
6393 "This package provides user interface and database connection code for
6394annotation data packages using SQLite data storage.")
6395 (license license:artistic2.0)))
6396
c465fa72
RW		 6397(define-public r-biomart
6398 (package
6399 (name "r-biomart")
94053331 6400 (version "2.30.0")
c465fa72
RW		 6401 (source (origin
6402 (method url-fetch)
6403 (uri (bioconductor-uri "biomaRt" version))
6404 (sha256
6405 (base32
94053331 6406 "1x0flcghq71784q2l02j0g4f9jkmyb14f6i307n6c59d6ji7h7x6"))))
c465fa72
RW		 6407 (properties
6408 `((upstream-name . "biomaRt")))
6409 (build-system r-build-system)
6410 (propagated-inputs
6411 `(("r-annotationdbi" ,r-annotationdbi)
6412 ("r-rcurl" ,r-rcurl)
6413 ("r-xml" ,r-xml)))
6414 (home-page "http://bioconductor.org/packages/biomaRt")
6415 (synopsis "Interface to BioMart databases")
6416 (description
6417 "biomaRt provides an interface to a growing collection of databases
6418implementing the @url{BioMart software suite, http://www.biomart.org}. The
6419package enables retrieval of large amounts of data in a uniform way without
6420the need to know the underlying database schemas or write complex SQL queries.
6421Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6422Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6423users direct access to a diverse set of data and enable a wide range of
6424powerful online queries from gene annotation to database mining.")
6425 (license license:artistic2.0)))
6426
e91d362e
RW		 6427(define-public r-biocparallel
6428 (package
6429 (name "r-biocparallel")
c15ae9b0 6430 (version "1.8.1")
e91d362e
RW		 6431 (source (origin
6432 (method url-fetch)
6433 (uri (bioconductor-uri "BiocParallel" version))
6434 (sha256
6435 (base32
c15ae9b0 6436 "123i928rwi4h4sy4fpysv6pinw5nns0sm3myxi2ghqhm34ws8gyl"))))
e91d362e
RW		 6437 (properties
6438 `((upstream-name . "BiocParallel")))
6439 (build-system r-build-system)
6440 (propagated-inputs
6441 `(("r-futile-logger" ,r-futile-logger)
6442 ("r-snow" ,r-snow)))
6443 (home-page "http://bioconductor.org/packages/BiocParallel")
6444 (synopsis "Bioconductor facilities for parallel evaluation")
6445 (description
6446 "This package provides modified versions and novel implementation of
6447functions for parallel evaluation, tailored to use with Bioconductor
6448objects.")
6449 (license (list license:gpl2+ license:gpl3+))))
6450
bf159353
RW		 6451(define-public r-biostrings
6452 (package
6453 (name "r-biostrings")
47d39b6e 6454 (version "2.42.0")
bf159353
RW		 6455 (source (origin
6456 (method url-fetch)
6457 (uri (bioconductor-uri "Biostrings" version))
6458 (sha256
6459 (base32
47d39b6e 6460 "08z8lkz3axa94wkf144a931ry6vf6cc25avi1ywr84ln2k5czz9f"))))
bf159353
RW		 6461 (properties
6462 `((upstream-name . "Biostrings")))
6463 (build-system r-build-system)
6464 (propagated-inputs
6465 `(("r-biocgenerics" ,r-biocgenerics)
6466 ("r-iranges" ,r-iranges)
6467 ("r-s4vectors" ,r-s4vectors)
6468 ("r-xvector" ,r-xvector)))
6469 (home-page "http://bioconductor.org/packages/Biostrings")
6470 (synopsis "String objects and algorithms for biological sequences")
6471 (description
6472 "This package provides memory efficient string containers, string
6473matching algorithms, and other utilities, for fast manipulation of large
6474biological sequences or sets of sequences.")
6475 (license license:artistic2.0)))
6476
f8d74f70
RW		 6477(define-public r-rsamtools
6478 (package
6479 (name "r-rsamtools")
c0ccef41 6480 (version "1.26.1")
f8d74f70
RW		 6481 (source (origin
6482 (method url-fetch)
6483 (uri (bioconductor-uri "Rsamtools" version))
6484 (sha256
6485 (base32
c0ccef41 6486 "0pf4f6brf4bl5zgjrah0f38qslazrs49ayqgyh0xfqgrh63yx4ck"))))
f8d74f70
RW		 6487 (properties
6488 `((upstream-name . "Rsamtools")))
6489 (build-system r-build-system)
6490 (arguments
6491 `(#:phases
6492 (modify-phases %standard-phases
6493 (add-after 'unpack 'use-system-zlib
6494 (lambda _
6495 (substitute* "DESCRIPTION"
6496 (("zlibbioc, ") ""))
6497 (substitute* "NAMESPACE"
6498 (("import\\(zlibbioc\\)") ""))
6499 #t)))))
6500 (inputs
6501 `(("zlib" ,zlib)))
6502 (propagated-inputs
6503 `(("r-biocgenerics" ,r-biocgenerics)
6504 ("r-biocparallel" ,r-biocparallel)
6505 ("r-biostrings" ,r-biostrings)
6506 ("r-bitops" ,r-bitops)
6507 ("r-genomeinfodb" ,r-genomeinfodb)
6508 ("r-genomicranges" ,r-genomicranges)
6509 ("r-iranges" ,r-iranges)
6510 ("r-s4vectors" ,r-s4vectors)
6511 ("r-xvector" ,r-xvector)))
6512 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6513 (synopsis "Interface to samtools, bcftools, and tabix")
6514 (description
6515 "This package provides an interface to the 'samtools', 'bcftools', and
6516'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6517binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6518files.")
6519 (license license:expat)))
6520
6e76dda2
RW		 6521(define-public r-summarizedexperiment
6522 (package
6523 (name "r-summarizedexperiment")
08da08d2 6524 (version "1.4.0")
6e76dda2
RW		 6525 (source (origin
6526 (method url-fetch)
6527 (uri (bioconductor-uri "SummarizedExperiment" version))
6528 (sha256
6529 (base32
08da08d2 6530 "1kbj8sg2ik9f8d6g95wz0py62jldg01qy5rsdpg1cxw95nf7dzi3"))))
6e76dda2
RW		 6531 (properties
6532 `((upstream-name . "SummarizedExperiment")))
6533 (build-system r-build-system)
6534 (propagated-inputs
6535 `(("r-biobase" ,r-biobase)
6536 ("r-biocgenerics" ,r-biocgenerics)
6537 ("r-genomeinfodb" ,r-genomeinfodb)
6538 ("r-genomicranges" ,r-genomicranges)
6539 ("r-iranges" ,r-iranges)
6540 ("r-s4vectors" ,r-s4vectors)))
6541 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
6542 (synopsis "Container for representing genomic ranges by sample")
6543 (description
6544 "The SummarizedExperiment container contains one or more assays, each
6545represented by a matrix-like object of numeric or other mode. The rows
6546typically represent genomic ranges of interest and the columns represent
6547samples.")
6548 (license license:artistic2.0)))
6549
d8a828af
RW		 6550(define-public r-genomicalignments
6551 (package
6552 (name "r-genomicalignments")
4ab32f0c 6553 (version "1.10.0")
d8a828af
RW		 6554 (source (origin
6555 (method url-fetch)
6556 (uri (bioconductor-uri "GenomicAlignments" version))
6557 (sha256
6558 (base32
4ab32f0c 6559 "11vb0a0zd36i4yhg4mfijv787v0nihn6pkjj6q7rfy19gwy61xlc"))))
d8a828af
RW		 6560 (properties
6561 `((upstream-name . "GenomicAlignments")))
6562 (build-system r-build-system)
6563 (propagated-inputs
6564 `(("r-biocgenerics" ,r-biocgenerics)
6565 ("r-biocparallel" ,r-biocparallel)
6566 ("r-biostrings" ,r-biostrings)
6567 ("r-genomeinfodb" ,r-genomeinfodb)
6568 ("r-genomicranges" ,r-genomicranges)
6569 ("r-iranges" ,r-iranges)
6570 ("r-rsamtools" ,r-rsamtools)
6571 ("r-s4vectors" ,r-s4vectors)
6572 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6573 (home-page "http://bioconductor.org/packages/GenomicAlignments")
6574 (synopsis "Representation and manipulation of short genomic alignments")
6575 (description
6576 "This package provides efficient containers for storing and manipulating
6577short genomic alignments (typically obtained by aligning short reads to a
6578reference genome). This includes read counting, computing the coverage,
6579junction detection, and working with the nucleotide content of the
6580alignments.")
6581 (license license:artistic2.0)))
6582
317755ff
RW		 6583(define-public r-rtracklayer
6584 (package
6585 (name "r-rtracklayer")
16a8bd31 6586 (version "1.34.1")
317755ff
RW		 6587 (source (origin
6588 (method url-fetch)
6589 (uri (bioconductor-uri "rtracklayer" version))
6590 (sha256
6591 (base32
16a8bd31 6592 "0x59k2fd0iaqi93gy6bm58p2j2z90z1b7a6w5b4c098y98n096rc"))))
317755ff
RW		 6593 (build-system r-build-system)
6594 (arguments
6595 `(#:phases
6596 (modify-phases %standard-phases
6597 (add-after 'unpack 'use-system-zlib
6598 (lambda _
6599 (substitute* "DESCRIPTION"
6600 (("zlibbioc, ") ""))
6601 (substitute* "NAMESPACE"
6602 (("import\\(zlibbioc\\)") ""))
6603 #t)))))
6604 (inputs
6605 `(("zlib" ,zlib)))
6606 (propagated-inputs
6607 `(("r-biocgenerics" ,r-biocgenerics)
6608 ("r-biostrings" ,r-biostrings)
6609 ("r-genomeinfodb" ,r-genomeinfodb)
6610 ("r-genomicalignments" ,r-genomicalignments)
6611 ("r-genomicranges" ,r-genomicranges)
6612 ("r-iranges" ,r-iranges)
6613 ("r-rcurl" ,r-rcurl)
6614 ("r-rsamtools" ,r-rsamtools)
6615 ("r-s4vectors" ,r-s4vectors)
6616 ("r-xml" ,r-xml)
6617 ("r-xvector" ,r-xvector)))
6618 (home-page "http://bioconductor.org/packages/rtracklayer")
6619 (synopsis "R interface to genome browsers and their annotation tracks")
6620 (description
6621 "rtracklayer is an extensible framework for interacting with multiple
6622genome browsers (currently UCSC built-in) and manipulating annotation tracks
6623in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
6624built-in). The user may export/import tracks to/from the supported browsers,
6625as well as query and modify the browser state, such as the current viewport.")
6626 (license license:artistic2.0)))
6627
2fd7c049
RW		 6628(define-public r-genomicfeatures
6629 (package
6630 (name "r-genomicfeatures")
b17aac08 6631 (version "1.26.0")
2fd7c049
RW		 6632 (source (origin
6633 (method url-fetch)
6634 (uri (bioconductor-uri "GenomicFeatures" version))
6635 (sha256
6636 (base32
b17aac08 6637 "0z8spi2knwzwi10c38vr7xlvi3ah9faj7m1lka880mmxkl9cai4k"))))
2fd7c049
RW		 6638 (properties
6639 `((upstream-name . "GenomicFeatures")))
6640 (build-system r-build-system)
6641 (propagated-inputs
6642 `(("r-annotationdbi" ,r-annotationdbi)
6643 ("r-biobase" ,r-biobase)
6644 ("r-biocgenerics" ,r-biocgenerics)
6645 ("r-biomart" ,r-biomart)
6646 ("r-biostrings" ,r-biostrings)
6647 ("r-dbi" ,r-dbi)
6648 ("r-genomeinfodb" ,r-genomeinfodb)
6649 ("r-genomicranges" ,r-genomicranges)
6650 ("r-iranges" ,r-iranges)
6651 ("r-rcurl" ,r-rcurl)
6652 ("r-rsqlite" ,r-rsqlite)
6653 ("r-rtracklayer" ,r-rtracklayer)
6654 ("r-s4vectors" ,r-s4vectors)
6655 ("r-xvector" ,r-xvector)))
6656 (home-page "http://bioconductor.org/packages/GenomicFeatures")
6657 (synopsis "Tools for working with transcript centric annotations")
6658 (description
6659 "This package provides a set of tools and methods for making and
6660manipulating transcript centric annotations. With these tools the user can
6661easily download the genomic locations of the transcripts, exons and cds of a
6662given organism, from either the UCSC Genome Browser or a BioMart
6663database (more sources will be supported in the future). This information is
6664then stored in a local database that keeps track of the relationship between
6665transcripts, exons, cds and genes. Flexible methods are provided for
6666extracting the desired features in a convenient format.")
6667 (license license:artistic2.0)))
6668
fb25d880
RW		 6669(define-public r-go-db
6670 (package
6671 (name "r-go-db")
d1b1587c 6672 (version "3.4.0")
fb25d880
RW		 6673 (source (origin
6674 (method url-fetch)
f82c8c3c
PP		 6675 (uri (string-append "http://www.bioconductor.org/packages/"
6676 "release/data/annotation/src/contrib/GO.db_"
6677 version ".tar.gz"))
fb25d880
RW		 6678 (sha256
6679 (base32
d1b1587c 6680 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
fb25d880
RW		 6681 (properties
6682 `((upstream-name . "GO.db")))
6683 (build-system r-build-system)
3141b83d
RW		 6684 (propagated-inputs
6685 `(("r-annotationdbi" ,r-annotationdbi)))
fb25d880
RW		 6686 (home-page "http://bioconductor.org/packages/GO.db")
6687 (synopsis "Annotation maps describing the entire Gene Ontology")
6688 (description
6689 "The purpose of this GO.db annotation package is to provide detailed
6690information about the latest version of the Gene Ontologies.")
6691 (license license:artistic2.0)))
6692
d1dbde6a
RW		 6693(define-public r-graph
6694 (package
6695 (name "r-graph")
3587b464 6696 (version "1.52.0")
d1dbde6a
RW		 6697 (source (origin
6698 (method url-fetch)
6699 (uri (bioconductor-uri "graph" version))
6700 (sha256
6701 (base32
3587b464 6702 "0g3dk5vsdp489fmyg8mifczmzgqrjlakkkr8i96dj15gghp3l135"))))
d1dbde6a
RW		 6703 (build-system r-build-system)
6704 (propagated-inputs
6705 `(("r-biocgenerics" ,r-biocgenerics)))
6706 (home-page "http://bioconductor.org/packages/graph")
6707 (synopsis "Handle graph data structures in R")
6708 (description
6709 "This package implements some simple graph handling capabilities for R.")
6710 (license license:artistic2.0)))
6711
d547ce5e
RW		 6712(define-public r-topgo
6713 (package
6714 (name "r-topgo")
30ec4de7 6715 (version "2.26.0")
d547ce5e
RW		 6716 (source (origin
6717 (method url-fetch)
6718 (uri (bioconductor-uri "topGO" version))
6719 (sha256
6720 (base32
30ec4de7 6721 "0j6sgvam4lk9348ag6pypcbkv93x4fk0di8ivhr23mz2s2yqzwrx"))))
d547ce5e
RW		 6722 (properties
6723 `((upstream-name . "topGO")))
6724 (build-system r-build-system)
6725 (propagated-inputs
6726 `(("r-annotationdbi" ,r-annotationdbi)
30ec4de7 6727 ("r-dbi" ,r-dbi)
d547ce5e
RW		 6728 ("r-biobase" ,r-biobase)
6729 ("r-biocgenerics" ,r-biocgenerics)
6730 ("r-go-db" ,r-go-db)
e48e88c2 6731 ("r-matrixstats" ,r-matrixstats)
6d415db2 6732 ("r-graph" ,r-graph)
d547ce5e
RW		 6733 ("r-sparsem" ,r-sparsem)))
6734 (home-page "http://bioconductor.org/packages/topGO")
6735 (synopsis "Enrichment analysis for gene ontology")
6736 (description
6737 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
6738terms while accounting for the topology of the GO graph. Different test
6739statistics and different methods for eliminating local similarities and
6740dependencies between GO terms can be implemented and applied.")
6741 ;; Any version of the LGPL applies.
6742 (license license:lgpl2.1+)))
6743
c63cef66
RW		 6744(define-public r-bsgenome
6745 (package
6746 (name "r-bsgenome")
3d74c044 6747 (version "1.42.0")
c63cef66
RW		 6748 (source (origin
6749 (method url-fetch)
6750 (uri (bioconductor-uri "BSgenome" version))
6751 (sha256
6752 (base32
3d74c044 6753 "0hxwc02h5mzhkrk60d1jmlsfjf0ai9jxdc0128kj1sg4r2k1q94y"))))
c63cef66
RW		 6754 (properties
6755 `((upstream-name . "BSgenome")))
6756 (build-system r-build-system)
6757 (propagated-inputs
6758 `(("r-biocgenerics" ,r-biocgenerics)
6759 ("r-biostrings" ,r-biostrings)
6760 ("r-genomeinfodb" ,r-genomeinfodb)
6761 ("r-genomicranges" ,r-genomicranges)
6762 ("r-iranges" ,r-iranges)
6763 ("r-rsamtools" ,r-rsamtools)
6764 ("r-rtracklayer" ,r-rtracklayer)
6765 ("r-s4vectors" ,r-s4vectors)
6766 ("r-xvector" ,r-xvector)))
6767 (home-page "http://bioconductor.org/packages/BSgenome")
6768 (synopsis "Infrastructure for Biostrings-based genome data packages")
6769 (description
6770 "This package provides infrastructure shared by all Biostrings-based
6771genome data packages and support for efficient SNP representation.")
6772 (license license:artistic2.0)))
6773
c43a011d
RW		 6774(define-public r-impute
6775 (package
6776 (name "r-impute")
acf6f7e0 6777 (version "1.48.0")
c43a011d
RW		 6778 (source (origin
6779 (method url-fetch)
6780 (uri (bioconductor-uri "impute" version))
6781 (sha256
6782 (base32
acf6f7e0 6783 "1164zvnikbjd0ybdn9xwn520rlmdjd824vmhnl83zgv3v9lzp9bm"))))
c43a011d
RW		 6784 (inputs
6785 `(("gfortran" ,gfortran)))
6786 (build-system r-build-system)
6787 (home-page "http://bioconductor.org/packages/impute")
6788 (synopsis "Imputation for microarray data")
6789 (description
6790 "This package provides a function to impute missing gene expression
6791microarray data, using nearest neighbor averaging.")
6792 (license license:gpl2+)))
6793
03ea5a35
RW		 6794(define-public r-seqpattern
6795 (package
6796 (name "r-seqpattern")
e92dd6f5 6797 (version "1.6.0")
03ea5a35
RW		 6798 (source (origin
6799 (method url-fetch)
6800 (uri (bioconductor-uri "seqPattern" version))
6801 (sha256
6802 (base32
e92dd6f5 6803 "0lsa5pz36xapi3yiv78k3z286a5md5sm5g21pgfyg8zmhmkxr7y8"))))
03ea5a35
RW		 6804 (properties
6805 `((upstream-name . "seqPattern")))
6806 (build-system r-build-system)
6807 (propagated-inputs
6808 `(("r-biostrings" ,r-biostrings)
6809 ("r-genomicranges" ,r-genomicranges)
6810 ("r-iranges" ,r-iranges)
e92dd6f5 6811 ("r-kernsmooth" ,r-kernsmooth)
03ea5a35
RW		 6812 ("r-plotrix" ,r-plotrix)))
6813 (home-page "http://bioconductor.org/packages/seqPattern")
6814 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
6815 (description
6816 "This package provides tools to visualize oligonucleotide patterns and
6817sequence motif occurrences across a large set of sequences centred at a common
6818reference point and sorted by a user defined feature.")
6819 (license license:gpl3+)))
6820
cb933df6
RW		 6821(define-public r-genomation
6822 (package
6823 (name "r-genomation")
51c3c490 6824 (version "1.6.0")
cb933df6
RW		 6825 (source (origin
6826 (method url-fetch)
6827 (uri (bioconductor-uri "genomation" version))
6828 (sha256
6829 (base32
51c3c490 6830 "1m4mz7wihj8yqivwkzw68div8ybk4rjsai3ffki7xp7sh21ax03y"))))
cb933df6
RW		 6831 (build-system r-build-system)
6832 (propagated-inputs
6833 `(("r-biostrings" ,r-biostrings)
6834 ("r-bsgenome" ,r-bsgenome)
6835 ("r-data-table" ,r-data-table)
6836 ("r-genomeinfodb" ,r-genomeinfodb)
6837 ("r-genomicalignments" ,r-genomicalignments)
6838 ("r-genomicranges" ,r-genomicranges)
6839 ("r-ggplot2" ,r-ggplot2)
6840 ("r-gridbase" ,r-gridbase)
6841 ("r-impute" ,r-impute)
6842 ("r-iranges" ,r-iranges)
6843 ("r-matrixstats" ,r-matrixstats)
6844 ("r-plotrix" ,r-plotrix)
6845 ("r-plyr" ,r-plyr)
51c3c490 6846 ("r-rcpp" ,r-rcpp)
cb933df6
RW		 6847 ("r-readr" ,r-readr)
6848 ("r-reshape2" ,r-reshape2)
51c3c490 6849 ("r-rhtslib" ,r-rhtslib)
cb933df6
RW		 6850 ("r-rsamtools" ,r-rsamtools)
6851 ("r-rtracklayer" ,r-rtracklayer)
51c3c490
RW		 6852 ("r-runit" ,r-runit)
6853 ("r-s4vectors" ,r-s4vectors)
cb933df6 6854 ("r-seqpattern" ,r-seqpattern)))
51c3c490
RW		 6855 (inputs
6856 `(("zlib" ,zlib)))
cb933df6
RW		 6857 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
6858 (synopsis "Summary, annotation and visualization of genomic data")
6859 (description
6860 "This package provides a package for summary and annotation of genomic
6861intervals. Users can visualize and quantify genomic intervals over
6862pre-defined functional regions, such as promoters, exons, introns, etc. The
6863genomic intervals represent regions with a defined chromosome position, which
6864may be associated with a score, such as aligned reads from HT-seq experiments,
6865TF binding sites, methylation scores, etc. The package can use any tabular
6866genomic feature data as long as it has minimal information on the locations of
6867genomic intervals. In addition, it can use BAM or BigWig files as input.")
6868 (license license:artistic2.0)))
6869
64efa307
RW		 6870(define-public r-genomationdata
6871 (package
6872 (name "r-genomationdata")
59198f8f 6873 (version "1.6.0")
64efa307
RW		 6874 (source (origin
6875 (method url-fetch)
6876 ;; We cannot use bioconductor-uri here because this tarball is
6877 ;; located under "data/annotation/" instead of "bioc/".
6878 (uri (string-append "https://bioconductor.org/packages/"
6879 "release/data/experiment/src/contrib/"
6880 "genomationData_" version ".tar.gz"))
6881 (sha256
6882 (base32
59198f8f 6883 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
64efa307
RW		 6884 (build-system r-build-system)
6885 ;; As this package provides little more than large data files, it doesn't
6886 ;; make sense to build substitutes.
6887 (arguments `(#:substitutable? #f))
6888 (native-inputs
6889 `(("r-knitr" ,r-knitr)))
6890 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
6891 (synopsis "Experimental data for use with the genomation package")
6892 (description
6893 "This package contains experimental genetic data for use with the
6894genomation package. Included are Chip Seq, Methylation and Cage data,
6895downloaded from Encode.")
6896 (license license:gpl3+)))
6897
486da491
RW		 6898(define-public r-org-hs-eg-db
6899 (package
6900 (name "r-org-hs-eg-db")
83f9a6fb 6901 (version "3.4.0")
486da491
RW		 6902 (source (origin
6903 (method url-fetch)
6904 ;; We cannot use bioconductor-uri here because this tarball is
6905 ;; located under "data/annotation/" instead of "bioc/".
6906 (uri (string-append "http://www.bioconductor.org/packages/"
6907 "release/data/annotation/src/contrib/"
6908 "org.Hs.eg.db_" version ".tar.gz"))
6909 (sha256
6910 (base32
83f9a6fb 6911 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
486da491
RW		 6912 (properties
6913 `((upstream-name . "org.Hs.eg.db")))
6914 (build-system r-build-system)
6915 (propagated-inputs
6916 `(("r-annotationdbi" ,r-annotationdbi)))
6917 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
6918 (synopsis "Genome wide annotation for Human")
6919 (description
6920 "This package provides mappings from Entrez gene identifiers to various
6921annotations for the human genome.")
6922 (license license:artistic2.0)))
6923
fefedf98
RW		 6924(define-public r-org-ce-eg-db
6925 (package
6926 (name "r-org-ce-eg-db")
f04a3eff 6927 (version "3.4.0")
fefedf98
RW		 6928 (source (origin
6929 (method url-fetch)
6930 ;; We cannot use bioconductor-uri here because this tarball is
6931 ;; located under "data/annotation/" instead of "bioc/".
6932 (uri (string-append "http://www.bioconductor.org/packages/"
6933 "release/data/annotation/src/contrib/"
6934 "org.Ce.eg.db_" version ".tar.gz"))
6935 (sha256
6936 (base32
f04a3eff 6937 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
fefedf98
RW		 6938 (properties
6939 `((upstream-name . "org.Ce.eg.db")))
6940 (build-system r-build-system)
6941 (propagated-inputs
6942 `(("r-annotationdbi" ,r-annotationdbi)))
6943 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
6944 (synopsis "Genome wide annotation for Worm")
6945 (description
6946 "This package provides mappings from Entrez gene identifiers to various
6947annotations for the genome of the model worm Caenorhabditis elegans.")
6948 (license license:artistic2.0)))
6949
16c53a1e
RW		 6950(define-public r-org-dm-eg-db
6951 (package
6952 (name "r-org-dm-eg-db")
0cfac6f2 6953 (version "3.4.0")
16c53a1e
RW		 6954 (source (origin
6955 (method url-fetch)
6956 ;; We cannot use bioconductor-uri here because this tarball is
6957 ;; located under "data/annotation/" instead of "bioc/".
6958 (uri (string-append "http://www.bioconductor.org/packages/"
6959 "release/data/annotation/src/contrib/"
6960 "org.Dm.eg.db_" version ".tar.gz"))
6961 (sha256
6962 (base32
0cfac6f2 6963 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
16c53a1e
RW		 6964 (properties
6965 `((upstream-name . "org.Dm.eg.db")))
6966 (build-system r-build-system)
6967 (propagated-inputs
6968 `(("r-annotationdbi" ,r-annotationdbi)))
6969 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
6970 (synopsis "Genome wide annotation for Fly")
6971 (description
6972 "This package provides mappings from Entrez gene identifiers to various
6973annotations for the genome of the model fruit fly Drosophila melanogaster.")
6974 (license license:artistic2.0)))
6975
e761beb9
RW		 6976(define-public r-org-mm-eg-db
6977 (package
6978 (name "r-org-mm-eg-db")
7c45670b 6979 (version "3.4.0")
e761beb9
RW		 6980 (source (origin
6981 (method url-fetch)
6982 ;; We cannot use bioconductor-uri here because this tarball is
6983 ;; located under "data/annotation/" instead of "bioc/".
6984 (uri (string-append "http://www.bioconductor.org/packages/"
6985 "release/data/annotation/src/contrib/"
6986 "org.Mm.eg.db_" version ".tar.gz"))
6987 (sha256
6988 (base32
7c45670b 6989 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
e761beb9
RW		 6990 (properties
6991 `((upstream-name . "org.Mm.eg.db")))
6992 (build-system r-build-system)
6993 (propagated-inputs
6994 `(("r-annotationdbi" ,r-annotationdbi)))
6995 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
6996 (synopsis "Genome wide annotation for Mouse")
6997 (description
6998 "This package provides mappings from Entrez gene identifiers to various
6999annotations for the genome of the model mouse Mus musculus.")
7000 (license license:artistic2.0)))
7001
936e7d67
RW		 7002(define-public r-seqlogo
7003 (package
7004 (name "r-seqlogo")
21d6c7a3 7005 (version "1.40.0")
936e7d67
RW		 7006 (source
7007 (origin
7008 (method url-fetch)
7009 (uri (bioconductor-uri "seqLogo" version))
7010 (sha256
7011 (base32
21d6c7a3 7012 "18bajdl75h3039559d81rgllqqvnq8ygsfxfx081xphxs0v6xggy"))))
936e7d67
RW		 7013 (properties `((upstream-name . "seqLogo")))
7014 (build-system r-build-system)
7015 (home-page "http://bioconductor.org/packages/seqLogo")
7016 (synopsis "Sequence logos for DNA sequence alignments")
7017 (description
7018 "seqLogo takes the position weight matrix of a DNA sequence motif and
7019plots the corresponding sequence logo as introduced by Schneider and
7020Stephens (1990).")
7021 (license license:lgpl2.0+)))
7022
c90a4baf
RW		 7023(define-public r-bsgenome-hsapiens-ucsc-hg19
7024 (package
7025 (name "r-bsgenome-hsapiens-ucsc-hg19")
7026 (version "1.4.0")
7027 (source (origin
7028 (method url-fetch)
7029 ;; We cannot use bioconductor-uri here because this tarball is
7030 ;; located under "data/annotation/" instead of "bioc/".
7031 (uri (string-append "http://www.bioconductor.org/packages/"
7032 "release/data/annotation/src/contrib/"
7033 "BSgenome.Hsapiens.UCSC.hg19_"
7034 version ".tar.gz"))
7035 (sha256
7036 (base32
7037 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7038 (properties
7039 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7040 (build-system r-build-system)
7041 ;; As this package provides little more than a very large data file it
7042 ;; doesn't make sense to build substitutes.
7043 (arguments `(#:substitutable? #f))
7044 (propagated-inputs
7045 `(("r-bsgenome" ,r-bsgenome)))
7046 (home-page
7047 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7048 (synopsis "Full genome sequences for Homo sapiens")
7049 (description
7050 "This package provides full genome sequences for Homo sapiens as provided
7051by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7052 (license license:artistic2.0)))
7053
a3e90287
RW		 7054(define-public r-bsgenome-mmusculus-ucsc-mm9
7055 (package
7056 (name "r-bsgenome-mmusculus-ucsc-mm9")
7057 (version "1.4.0")
7058 (source (origin
7059 (method url-fetch)
7060 ;; We cannot use bioconductor-uri here because this tarball is
7061 ;; located under "data/annotation/" instead of "bioc/".
7062 (uri (string-append "http://www.bioconductor.org/packages/"
7063 "release/data/annotation/src/contrib/"
7064 "BSgenome.Mmusculus.UCSC.mm9_"
7065 version ".tar.gz"))
7066 (sha256
7067 (base32
7068 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7069 (properties
7070 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7071 (build-system r-build-system)
7072 ;; As this package provides little more than a very large data file it
7073 ;; doesn't make sense to build substitutes.
7074 (arguments `(#:substitutable? #f))
7075 (propagated-inputs
7076 `(("r-bsgenome" ,r-bsgenome)))
7077 (home-page
7078 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7079 (synopsis "Full genome sequences for Mouse")
7080 (description
7081 "This package provides full genome sequences for Mus musculus (Mouse) as
7082provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7083 (license license:artistic2.0)))
7084
4714d521
RW		 7085(define-public r-bsgenome-mmusculus-ucsc-mm10
7086 (package
7087 (name "r-bsgenome-mmusculus-ucsc-mm10")
7088 (version "1.4.0")
7089 (source (origin
7090 (method url-fetch)
7091 ;; We cannot use bioconductor-uri here because this tarball is
7092 ;; located under "data/annotation/" instead of "bioc/".
7093 (uri (string-append "http://www.bioconductor.org/packages/"
7094 "release/data/annotation/src/contrib/"
7095 "BSgenome.Mmusculus.UCSC.mm10_"
7096 version ".tar.gz"))
7097 (sha256
7098 (base32
7099 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7100 (properties
7101 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7102 (build-system r-build-system)
7103 ;; As this package provides little more than a very large data file it
7104 ;; doesn't make sense to build substitutes.
7105 (arguments `(#:substitutable? #f))
7106 (propagated-inputs
7107 `(("r-bsgenome" ,r-bsgenome)))
7108 (home-page
7109 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7110 (synopsis "Full genome sequences for Mouse")
7111 (description
7112 "This package provides full genome sequences for Mus
7113musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7114in Biostrings objects.")
7115 (license license:artistic2.0)))
7116
943bd627
RW		 7117(define-public r-bsgenome-celegans-ucsc-ce6
7118 (package
7119 (name "r-bsgenome-celegans-ucsc-ce6")
7120 (version "1.4.0")
7121 (source (origin
7122 (method url-fetch)
7123 ;; We cannot use bioconductor-uri here because this tarball is
7124 ;; located under "data/annotation/" instead of "bioc/".
7125 (uri (string-append "http://www.bioconductor.org/packages/"
7126 "release/data/annotation/src/contrib/"
7127 "BSgenome.Celegans.UCSC.ce6_"
7128 version ".tar.gz"))
7129 (sha256
7130 (base32
7131 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7132 (properties
7133 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7134 (build-system r-build-system)
7135 ;; As this package provides little more than a very large data file it
7136 ;; doesn't make sense to build substitutes.
7137 (arguments `(#:substitutable? #f))
7138 (propagated-inputs
7139 `(("r-bsgenome" ,r-bsgenome)))
7140 (home-page
7141 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7142 (synopsis "Full genome sequences for Worm")
7143 (description
7144 "This package provides full genome sequences for Caenorhabditis
7145elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7146objects.")
7147 (license license:artistic2.0)))
7148
fc47c7d6
RW		 7149(define-public r-bsgenome-celegans-ucsc-ce10
7150 (package
7151 (name "r-bsgenome-celegans-ucsc-ce10")
7152 (version "1.4.0")
7153 (source (origin
7154 (method url-fetch)
7155 ;; We cannot use bioconductor-uri here because this tarball is
7156 ;; located under "data/annotation/" instead of "bioc/".
7157 (uri (string-append "http://www.bioconductor.org/packages/"
7158 "release/data/annotation/src/contrib/"
7159 "BSgenome.Celegans.UCSC.ce10_"
7160 version ".tar.gz"))
7161 (sha256
7162 (base32
7163 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7164 (properties
7165 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7166 (build-system r-build-system)
7167 ;; As this package provides little more than a very large data file it
7168 ;; doesn't make sense to build substitutes.
7169 (arguments `(#:substitutable? #f))
7170 (propagated-inputs
7171 `(("r-bsgenome" ,r-bsgenome)))
7172 (home-page
7173 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7174 (synopsis "Full genome sequences for Worm")
7175 (description
7176 "This package provides full genome sequences for Caenorhabditis
7177elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7178objects.")
7179 (license license:artistic2.0)))
7180
6dc60998
RW		 7181(define-public r-bsgenome-dmelanogaster-ucsc-dm3
7182 (package
7183 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7184 (version "1.4.0")
7185 (source (origin
7186 (method url-fetch)
7187 ;; We cannot use bioconductor-uri here because this tarball is
7188 ;; located under "data/annotation/" instead of "bioc/".
7189 (uri (string-append "http://www.bioconductor.org/packages/"
7190 "release/data/annotation/src/contrib/"
7191 "BSgenome.Dmelanogaster.UCSC.dm3_"
7192 version ".tar.gz"))
7193 (sha256
7194 (base32
7195 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7196 (properties
7197 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7198 (build-system r-build-system)
7199 ;; As this package provides little more than a very large data file it
7200 ;; doesn't make sense to build substitutes.
7201 (arguments `(#:substitutable? #f))
7202 (propagated-inputs
7203 `(("r-bsgenome" ,r-bsgenome)))
7204 (home-page
7205 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7206 (synopsis "Full genome sequences for Fly")
7207 (description
7208 "This package provides full genome sequences for Drosophila
7209melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7210Biostrings objects.")
7211 (license license:artistic2.0)))
7212
ae2462f7
RW		 7213(define-public r-motifrg
7214 (package
7215 (name "r-motifrg")
809251e1 7216 (version "1.18.0")
ae2462f7
RW		 7217 (source
7218 (origin
7219 (method url-fetch)
7220 (uri (bioconductor-uri "motifRG" version))
7221 (sha256
7222 (base32
809251e1 7223 "1pa97aj6c5f3gx4bgriw110764dj3m9h104ddi8rv2bpy41yd98d"))))
ae2462f7
RW		 7224 (properties `((upstream-name . "motifRG")))
7225 (build-system r-build-system)
7226 (propagated-inputs
7227 `(("r-biostrings" ,r-biostrings)
7228 ("r-bsgenome" ,r-bsgenome)
7229 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7230 ("r-iranges" ,r-iranges)
7231 ("r-seqlogo" ,r-seqlogo)
7232 ("r-xvector" ,r-xvector)))
7233 (home-page "http://bioconductor.org/packages/motifRG")
7234 (synopsis "Discover motifs in high throughput sequencing data")
7235 (description
7236 "This package provides tools for discriminative motif discovery in high
7237throughput genetic sequencing data sets using regression methods.")
7238 (license license:artistic2.0)))
7239
a5002ae7
AE		 7240(define-public r-qtl
7241 (package
7242 (name "r-qtl")
421f7772 7243 (version "1.40-8")
a5002ae7
AE		 7244 (source
7245 (origin
7246 (method url-fetch)
7247 (uri (string-append "mirror://cran/src/contrib/qtl_"
7248 version ".tar.gz"))
7249 (sha256
7250 (base32
421f7772 7251 "05bj1x2ry0i7yqiydlswb3d2h4pxg70z8w1072az1mrv1m54k8sp"))))
a5002ae7
AE		 7252 (build-system r-build-system)
7253 (home-page "http://rqtl.org/")
7254 (synopsis "R package for analyzing QTL experiments in genetics")
7255 (description "R/qtl is an extension library for the R statistics
7256system. It is used to analyze experimental crosses for identifying
7257genes contributing to variation in quantitative traits (so-called
7258quantitative trait loci, QTLs).
7259
7260Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7261identify genotyping errors, and to perform single-QTL and two-QTL,
7262two-dimensional genome scans.")
7263 (license license:gpl3)))
d1e32822 7264
9e3ba31c
RJ		 7265(define-public r-zlibbioc
7266 (package
7267 (name "r-zlibbioc")
da22da86 7268 (version "1.20.0")
9e3ba31c
RJ		 7269 (source (origin
7270 (method url-fetch)
7271 (uri (bioconductor-uri "zlibbioc" version))
7272 (sha256
7273 (base32
da22da86 7274 "0hbk90q5hl0fycfvy5nxxa4hxgglag9lzp7i0fg849bqygg5nbyq"))))
9e3ba31c
RJ		 7275 (properties
7276 `((upstream-name . "zlibbioc")))
7277 (build-system r-build-system)
7278 (home-page "https://bioconductor.org/packages/zlibbioc")
7279 (synopsis "Provider for zlib-1.2.5 to R packages")
7280 (description "This package uses the source code of zlib-1.2.5 to create
7281libraries for systems that do not have these available via other means.")
7282 (license license:artistic2.0)))
7283
e619a5c2
RW		 7284(define-public r-r4rna
7285 (package
7286 (name "r-r4rna")
7287 (version "0.1.4")
7288 (source
7289 (origin
7290 (method url-fetch)
7291 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7292 version ".tar.gz"))
7293 (sha256
7294 (base32
7295 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7296 (build-system r-build-system)
7297 (propagated-inputs
7298 `(("r-optparse" ,r-optparse)
7299 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7300 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7301 (synopsis "Analysis framework for RNA secondary structure")
7302 (description
7303 "The R4RNA package aims to be a general framework for the analysis of RNA
7304secondary structure and comparative analysis in R.")
7305 (license license:gpl3+)))
7306
52765a63
RW		 7307(define-public r-rhtslib
7308 (package
7309 (name "r-rhtslib")
53ca52f0 7310 (version "1.6.0")
52765a63
RW		 7311 (source
7312 (origin
7313 (method url-fetch)
7314 (uri (bioconductor-uri "Rhtslib" version))
7315 (sha256
7316 (base32
53ca52f0 7317 "1vk3ng61dhi3pbia1lp3gl3mlr3i1vb2lkq83qb53i9dzz128wh9"))))
52765a63
RW		 7318 (properties `((upstream-name . "Rhtslib")))
7319 (build-system r-build-system)
7320 (propagated-inputs
7321 `(("r-zlibbioc" ,r-zlibbioc)))
7322 (inputs
7323 `(("zlib" ,zlib)))
53ca52f0
RW		 7324 (native-inputs
7325 `(("autoconf" ,autoconf)))
52765a63
RW		 7326 (home-page "https://github.com/nhayden/Rhtslib")
7327 (synopsis "High-throughput sequencing library as an R package")
7328 (description
7329 "This package provides the HTSlib C library for high-throughput
7330nucleotide sequence analysis. The package is primarily useful to developers
7331of other R packages who wish to make use of HTSlib.")
7332 (license license:lgpl2.0+)))
7333
fe02c4c9
RW		 7334(define-public r-bamsignals
7335 (package
7336 (name "r-bamsignals")
e357bec8 7337 (version "1.6.0")
fe02c4c9
RW		 7338 (source
7339 (origin
7340 (method url-fetch)
7341 (uri (bioconductor-uri "bamsignals" version))
7342 (sha256
7343 (base32
e357bec8 7344 "1k42gvk5mgq4la1fp0in3an2zfdz69h6522jsqhmk0f6i75kg4mb"))))
fe02c4c9
RW		 7345 (build-system r-build-system)
7346 (propagated-inputs
7347 `(("r-biocgenerics" ,r-biocgenerics)
7348 ("r-genomicranges" ,r-genomicranges)
7349 ("r-iranges" ,r-iranges)
7350 ("r-rcpp" ,r-rcpp)
7351 ("r-rhtslib" ,r-rhtslib)
7352 ("r-zlibbioc" ,r-zlibbioc)))
7353 (inputs
7354 `(("zlib" ,zlib)))
7355 (home-page "http://bioconductor.org/packages/bamsignals")
7356 (synopsis "Extract read count signals from bam files")
7357 (description
7358 "This package allows to efficiently obtain count vectors from indexed bam
7359files. It counts the number of nucleotide sequence reads in given genomic
7360ranges and it computes reads profiles and coverage profiles. It also handles
7361paired-end data.")
7362 (license license:gpl2+)))
7363
89984be4
RW		 7364(define-public r-rcas
7365 (package
7366 (name "r-rcas")
2c8d6c0b 7367 (version "1.1.1")
89984be4
RW		 7368 (source (origin
7369 (method url-fetch)
7370 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7371 version ".tar.gz"))
7372 (file-name (string-append name "-" version ".tar.gz"))
7373 (sha256
7374 (base32
2c8d6c0b 7375 "1hd0r66556bxbdd82ksjklq7nfli36l4k6y88ic7kkg9873wa1nw"))))
89984be4
RW		 7376 (build-system r-build-system)
7377 (native-inputs
7378 `(("r-knitr" ,r-knitr)
7379 ("r-testthat" ,r-testthat)
7380 ;; During vignette building knitr checks that "pandoc-citeproc"
7381 ;; is in the PATH.
7382 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7383 (propagated-inputs
7384 `(("r-data-table" ,r-data-table)
7385 ("r-biomart" ,r-biomart)
7386 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7387 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7388 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7389 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7390 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7391 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7392 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7393 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7394 ("r-topgo" ,r-topgo)
7395 ("r-dt" ,r-dt)
7396 ("r-plotly" ,r-plotly)
2c8d6c0b 7397 ("r-plotrix" ,r-plotrix)
89984be4
RW		 7398 ("r-motifrg" ,r-motifrg)
7399 ("r-genomation" ,r-genomation)
7400 ("r-genomicfeatures" ,r-genomicfeatures)
7401 ("r-rtracklayer" ,r-rtracklayer)
7402 ("r-rmarkdown" ,r-rmarkdown)))
7403 (synopsis "RNA-centric annotation system")
7404 (description
7405 "RCAS aims to be a standalone RNA-centric annotation system that provides
7406intuitive reports and publication-ready graphics. This package provides the R
7407library implementing most of the pipeline's features.")
7408 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7409 (license license:expat)))
7410
50937297
RW		 7411(define-public rcas-web
7412 (package
7413 (name "rcas-web")
7414 (version "0.0.3")
7415 (source
7416 (origin
7417 (method url-fetch)
7418 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7419 "releases/download/v" version
7420 "/rcas-web-" version ".tar.gz"))
7421 (sha256
7422 (base32
7423 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7424 (build-system gnu-build-system)
7425 (arguments
7426 `(#:phases
7427 (modify-phases %standard-phases
7428 (add-after 'install 'wrap-executable
7429 (lambda* (#:key inputs outputs #:allow-other-keys)
7430 (let* ((out (assoc-ref outputs "out"))
7431 (json (assoc-ref inputs "guile-json"))
7432 (redis (assoc-ref inputs "guile-redis"))
7433 (path (string-append
7434 json "/share/guile/site/2.2:"
7435 redis "/share/guile/site/2.2")))
7436 (wrap-program (string-append out "/bin/rcas-web")
7437 `("GUILE_LOAD_PATH" ":" = (,path))
7438 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
7439 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
7440 #t)))))
7441 (inputs
7442 `(("r" ,r)
7443 ("r-rcas" ,r-rcas)
7444 ("guile-next" ,guile-next)
7445 ("guile-json" ,guile2.2-json)
7446 ("guile-redis" ,guile2.2-redis)))
7447 (native-inputs
7448 `(("pkg-config" ,pkg-config)))
7449 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
7450 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
7451 (description "This package provides a simple web interface for the
7452@dfn{RNA-centric annotation system} (RCAS).")
7453 (license license:agpl3+)))
7454
7500e42b
RJ		 7455(define-public r-mutationalpatterns
7456 (package
7457 (name "r-mutationalpatterns")
7458 (version "1.0.0")
7459 (source
7460 (origin
7461 (method url-fetch)
7462 (uri (bioconductor-uri "MutationalPatterns" version))
7463 (sha256
7464 (base32
7465 "1a3c2bm0xx0q4gf98jiw74msmdf2fr8rbsdysd5ww9kqlzmsbr17"))))
7466 (build-system r-build-system)
7467 (propagated-inputs
7468 `(("r-biocgenerics" ,r-biocgenerics)
7469 ("r-biostrings" ,r-biostrings)
7470 ("r-genomicranges" ,r-genomicranges)
7471 ("r-genomeinfodb" ,r-genomeinfodb)
7472 ("r-ggplot2" ,r-ggplot2)
7473 ("r-gridextra" ,r-gridextra)
7474 ("r-iranges" ,r-iranges)
7475 ("r-nmf" ,r-nmf)
7476 ("r-plyr" ,r-plyr)
7477 ("r-pracma" ,r-pracma)
7478 ("r-reshape2" ,r-reshape2)
7479 ("r-summarizedexperiment" ,r-summarizedexperiment)
7480 ("r-variantannotation" ,r-variantannotation)))
7481 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
7482 (synopsis "Extract and visualize mutational patterns in genomic data")
7483 (description "This package provides an extensive toolset for the
7484characterization and visualization of a wide range of mutational patterns
7485in SNV base substitution data.")
7486 (license license:expat)))
7487
d7160529
RW		 7488(define-public r-wgcna
7489 (package
7490 (name "r-wgcna")
7491 (version "1.51")
7492 (source
7493 (origin
7494 (method url-fetch)
7495 (uri (cran-uri "WGCNA" version))
7496 (sha256
7497 (base32
7498 "0hzvnhw76vwg8bl8x368f0c5szpwb8323bmrb3bir93i5bmfjsxx"))))
7499 (properties `((upstream-name . "WGCNA")))
7500 (build-system r-build-system)
7501 (propagated-inputs
7502 `(("r-annotationdbi" ,r-annotationdbi)
7503 ("r-doparallel" ,r-doparallel)
7504 ("r-dynamictreecut" ,r-dynamictreecut)
7505 ("r-fastcluster" ,r-fastcluster)
7506 ("r-foreach" ,r-foreach)
7507 ("r-go-db" ,r-go-db)
7508 ("r-hmisc" ,r-hmisc)
7509 ("r-impute" ,r-impute)
7510 ("r-matrixstats" ,r-matrixstats)
7511 ("r-preprocesscore" ,r-preprocesscore)))
7512 (home-page
7513 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
7514 (synopsis "Weighted correlation network analysis")
7515 (description
7516 "This package provides functions necessary to perform Weighted
7517Correlation Network Analysis on high-dimensional data. It includes functions
7518for rudimentary data cleaning, construction and summarization of correlation
7519networks, module identification and functions for relating both variables and
7520modules to sample traits. It also includes a number of utility functions for
7521data manipulation and visualization.")
7522 (license license:gpl2+)))
7523
c827f202
RW		 7524(define-public r-chipkernels
7525 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
7526 (revision "1"))
7527 (package
7528 (name "r-chipkernels")
7529 (version (string-append "1.1-" revision "." (string-take commit 9)))
7530 (source
7531 (origin
7532 (method git-fetch)
7533 (uri (git-reference
7534 (url "https://github.com/ManuSetty/ChIPKernels.git")
7535 (commit commit)))
7536 (file-name (string-append name "-" version))
7537 (sha256
7538 (base32
7539 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
7540 (build-system r-build-system)
7541 (propagated-inputs
7542 `(("r-iranges" ,r-iranges)
7543 ("r-xvector" ,r-xvector)
7544 ("r-biostrings" ,r-biostrings)
7545 ("r-bsgenome" ,r-bsgenome)
7546 ("r-gtools" ,r-gtools)
7547 ("r-genomicranges" ,r-genomicranges)
7548 ("r-sfsmisc" ,r-sfsmisc)
7549 ("r-kernlab" ,r-kernlab)
7550 ("r-s4vectors" ,r-s4vectors)
7551 ("r-biocgenerics" ,r-biocgenerics)))
7552 (home-page "https://github.com/ManuSetty/ChIPKernels")
7553 (synopsis "Build string kernels for DNA Sequence analysis")
7554 (description "ChIPKernels is an R package for building different string
7555kernels used for DNA Sequence analysis. A dictionary of the desired kernel
7556must be built and this dictionary can be used for determining kernels for DNA
7557Sequences.")
7558 (license license:gpl2+))))
7559
2d9fb170
RW		 7560(define-public r-seqgl
7561 (package
7562 (name "r-seqgl")
7563 (version "1.1.4")
7564 (source
7565 (origin
7566 (method url-fetch)
7567 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
7568 "archive/" version ".tar.gz"))
7569 (file-name (string-append name "-" version ".tar.gz"))
7570 (sha256
7571 (base32
7572 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
7573 (build-system r-build-system)
7574 (propagated-inputs
7575 `(("r-biostrings" ,r-biostrings)
7576 ("r-chipkernels" ,r-chipkernels)
7577 ("r-genomicranges" ,r-genomicranges)
7578 ("r-spams" ,r-spams)
7579 ("r-wgcna" ,r-wgcna)
7580 ("r-fastcluster" ,r-fastcluster)))
7581 (home-page "https://github.com/ManuSetty/SeqGL")
7582 (synopsis "Group lasso for Dnase/ChIP-seq data")
7583 (description "SeqGL is a group lasso based algorithm to extract
7584transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
7585This package presents a method which uses group lasso to discriminate between
7586bound and non bound genomic regions to accurately identify transcription
7587factors bound at the specific regions.")
7588 (license license:gpl2+)))
7589
bd3be46e
RW		 7590(define-public r-gkmsvm
7591 (package
7592 (name "r-gkmsvm")
7593 (version "0.71.0")
7594 (source
7595 (origin
7596 (method url-fetch)
7597 (uri (cran-uri "gkmSVM" version))
7598 (sha256
7599 (base32
7600 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
7601 (properties `((upstream-name . "gkmSVM")))
7602 (build-system r-build-system)
7603 (propagated-inputs
7604 `(("r-biocgenerics" ,r-biocgenerics)
7605 ("r-biostrings" ,r-biostrings)
7606 ("r-genomeinfodb" ,r-genomeinfodb)
7607 ("r-genomicranges" ,r-genomicranges)
7608 ("r-iranges" ,r-iranges)
7609 ("r-kernlab" ,r-kernlab)
7610 ("r-rcpp" ,r-rcpp)
7611 ("r-rocr" ,r-rocr)
7612 ("r-rtracklayer" ,r-rtracklayer)
7613 ("r-s4vectors" ,r-s4vectors)
7614 ("r-seqinr" ,r-seqinr)))
7615 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
7616 (synopsis "Gapped-kmer support vector machine")
7617 (description
7618 "This R package provides tools for training gapped-kmer SVM classifiers
7619for DNA and protein sequences. This package supports several sequence
7620kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
7621 (license license:gpl2+)))
7622
66e40e00
RW		 7623(define-public emboss
7624 (package
7625 (name "emboss")
7626 (version "6.5.7")
7627 (source (origin
7628 (method url-fetch)
7629 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
7630 (version-major+minor version) ".0/"
7631 "EMBOSS-" version ".tar.gz"))
7632 (sha256
7633 (base32
7634 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
7635 (build-system gnu-build-system)
7636 (arguments
7637 `(#:configure-flags
7638 (list (string-append "--with-hpdf="
7639 (assoc-ref %build-inputs "libharu")))
7640 #:phases
7641 (modify-phases %standard-phases
7642 (add-after 'unpack 'fix-checks
7643 (lambda _
7644 ;; The PNGDRIVER tests check for the presence of libgd, libpng
7645 ;; and zlib, but assume that they are all found at the same
7646 ;; prefix.
7647 (substitute* "configure.in"
7648 (("CHECK_PNGDRIVER")
7649 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
7650AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
7651AM_CONDITIONAL(AMPNG, true)"))
7652 #t))
7653 (add-after 'unpack 'disable-update-check
7654 (lambda _
7655 ;; At build time there is no connection to the Internet, so
7656 ;; looking for updates will not work.
7657 (substitute* "Makefile.am"
7658 (("\\$\\(bindir\\)/embossupdate") ""))
7659 #t))
7660 (add-before 'configure 'autogen
7661 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
7662 (inputs
7663 `(("perl" ,perl)
7664 ("libpng" ,libpng)
7665 ("gd" ,gd)
7666 ("libx11" ,libx11)
7667 ("libharu" ,libharu)
7668 ("zlib" ,zlib)))
7669 (native-inputs
7670 `(("autoconf" ,autoconf)
7671 ("automake" ,automake)
7672 ("libtool" ,libtool)
7673 ("pkg-config" ,pkg-config)))
7674 (home-page "http://emboss.sourceforge.net")
7675 (synopsis "Molecular biology analysis suite")
7676 (description "EMBOSS is the \"European Molecular Biology Open Software
7677Suite\". EMBOSS is an analysis package specially developed for the needs of
7678the molecular biology (e.g. EMBnet) user community. The software
7679automatically copes with data in a variety of formats and even allows
7680transparent retrieval of sequence data from the web. It also provides a
7681number of libraries for the development of software in the field of molecular
7682biology. EMBOSS also integrates a range of currently available packages and
7683tools for sequence analysis into a seamless whole.")
7684 (license license:gpl2+)))
7685
1f1b20b8
RW		 7686(define-public bits
7687 (let ((revision "1")
7688 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
7689 (package
7690 (name "bits")
7691 ;; The version is 2.13.0 even though no release archives have been
7692 ;; published as yet.
7693 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
7694 (source (origin
7695 (method git-fetch)
7696 (uri (git-reference
7697 (url "https://github.com/arq5x/bits.git")
7698 (commit commit)))
7699 (file-name (string-append name "-" version "-checkout"))
7700 (sha256
7701 (base32
7702 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
7703 (build-system gnu-build-system)
7704 (arguments
7705 `(#:tests? #f ;no tests included
7706 #:phases
7707 (modify-phases %standard-phases
7708 (delete 'configure)
7709 (add-after 'unpack 'remove-cuda
7710 (lambda _
7711 (substitute* "Makefile"
7712 ((".*_cuda") "")
7713 (("(bits_test_intersections) \\\\" _ match) match))
7714 #t))
7715 (replace 'install
7716 (lambda* (#:key outputs #:allow-other-keys)
7717 (copy-recursively
7718 "bin" (string-append (assoc-ref outputs "out") "/bin"))
7719 #t)))))
7720 (inputs
7721 `(("gsl" ,gsl)
7722 ("zlib" ,zlib)))
7723 (home-page "https://github.com/arq5x/bits")
7724 (synopsis "Implementation of binary interval search algorithm")
7725 (description "This package provides an implementation of the
7726BITS (Binary Interval Search) algorithm, an approach to interval set
7727intersection. It is especially suited for the comparison of diverse genomic
7728datasets and the exploration of large datasets of genome
7729intervals (e.g. genes, sequence alignments).")
7730 (license license:gpl2))))
7731
e62ffce5 7732(define-public piranha
883302da
RW		 7733 ;; There is no release tarball for the latest version. The latest commit is
7734 ;; older than one year at the time of this writing.
7735 (let ((revision "1")
7736 (commit "0466d364b71117d01e4471b74c514436cc281233"))
7737 (package
7738 (name "piranha")
7739 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
7740 (source (origin
7741 (method git-fetch)
7742 (uri (git-reference
7743 (url "https://github.com/smithlabcode/piranha.git")
7744 (commit commit)))
7745 (sha256
7746 (base32
7747 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
7748 (build-system gnu-build-system)
7749 (arguments
7750 `(#:test-target "test"
7751 #:phases
7752 (modify-phases %standard-phases
7753 (add-after 'unpack 'copy-smithlab-cpp
7754 (lambda* (#:key inputs #:allow-other-keys)
e62ffce5 7755 (for-each (lambda (file)
883302da
RW		 7756 (install-file file "./src/smithlab_cpp/"))
7757 (find-files (assoc-ref inputs "smithlab-cpp")))
7758 #t))
7759 (add-after 'install 'install-to-store
7760 (lambda* (#:key outputs #:allow-other-keys)
7761 (let* ((out (assoc-ref outputs "out"))
7762 (bin (string-append out "/bin")))
883302da
RW		 7763 (for-each (lambda (file)
7764 (install-file file bin))
7765 (find-files "bin" ".*")))
7766 #t)))
7767 #:configure-flags
7768 (list (string-append "--with-bam_tools_headers="
7769 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
7770 (string-append "--with-bam_tools_library="
7771 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
7772 (inputs
7773 `(("bamtools" ,bamtools)
7774 ("samtools" ,samtools-0.1)
7775 ("gsl" ,gsl)
7776 ("smithlab-cpp"
7777 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
7778 (origin
7779 (method git-fetch)
7780 (uri (git-reference
7781 (url "https://github.com/smithlabcode/smithlab_cpp.git")
7782 (commit commit)))
7783 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
7784 (sha256
7785 (base32
7786 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
7787 (native-inputs
7788 `(("python" ,python-2)))
7789 (home-page "https://github.com/smithlabcode/piranha")
7790 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
7791 (description
7792 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
e62ffce5
RW		 7793RIP-seq experiments. It takes input in BED or BAM format and identifies
7794regions of statistically significant read enrichment. Additional covariates
7795may optionally be provided to further inform the peak-calling process.")
883302da 7796 (license license:gpl3+))))
e62ffce5 7797
d1e32822
RW		 7798(define-public pepr
7799 (package
7800 (name "pepr")
7801 (version "1.0.9")
7802 (source (origin
7803 (method url-fetch)
7804 (uri (string-append "https://pypi.python.org/packages/source/P"
7805 "/PePr/PePr-" version ".tar.gz"))
7806 (sha256
7807 (base32
7808 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
7809 (build-system python-build-system)
7810 (arguments
7811 `(#:python ,python-2 ; python2 only
b41a05ce 7812 #:tests? #f)) ; no tests included
d1e32822
RW		 7813 (propagated-inputs
7814 `(("python2-numpy" ,python2-numpy)
7815 ("python2-scipy" ,python2-scipy)
7816 ("python2-pysam" ,python2-pysam)))
0c6c9c00 7817 (home-page "https://github.com/shawnzhangyx/PePr")
d1e32822
RW		 7818 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
7819 (description
7820 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
7821that is primarily designed for data with biological replicates. It uses a
7822negative binomial distribution to model the read counts among the samples in
7823the same group, and look for consistent differences between ChIP and control
7824group or two ChIP groups run under different conditions.")
7825 (license license:gpl3+)))
6b49a37e
RJ		 7826
7827(define-public filevercmp
7828 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
7829 (package
7830 (name "filevercmp")
7831 (version (string-append "0-1." (string-take commit 7)))
7832 (source (origin
7833 (method url-fetch)
7834 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
7835 commit ".tar.gz"))
7836 (file-name (string-append name "-" version ".tar.gz"))
7837 (sha256
7838 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
7839 (build-system gnu-build-system)
7840 (arguments
7841 `(#:tests? #f ; There are no tests to run.
7842 #:phases
7843 (modify-phases %standard-phases
7844 (delete 'configure) ; There is no configure phase.
7845 (replace 'install
7846 (lambda* (#:key outputs #:allow-other-keys)
7847 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7848 (install-file "filevercmp" bin)))))))
7849 (home-page "https://github.com/ekg/filevercmp")
7850 (synopsis "This program compares version strings")
7851 (description "This program compares version strings. It intends to be a
7852replacement for strverscmp.")
7853 (license license:gpl3+))))
5fb5dffb
RW		 7854
7855(define-public multiqc
7856 (package
7857 (name "multiqc")
7858 (version "0.6")
7859 (source
7860 (origin
7861 (method url-fetch)
7862 (uri (pypi-uri "multiqc" version))
7863 (sha256
7864 (base32
7865 "0avw11h63ldpxy5pizc3wl1wa01ha7q10wb240nggsjz3jaqvyiy"))))
7866 (build-system python-build-system)
7867 (propagated-inputs
7868 `(("python-jinja2" ,python-jinja2)
7869 ("python-simplejson" ,python-simplejson)
7870 ("python-pyyaml" ,python-pyyaml)
7871 ("python-click" ,python-click)
7872 ("python-matplotlib" ,python-matplotlib)
7873 ("python-numpy" ,python-numpy)))
5fb5dffb
RW		 7874 (home-page "http://multiqc.info")
7875 (synopsis "Aggregate bioinformatics analysis reports")
7876 (description
7877 "MultiQC is a tool to aggregate bioinformatics results across many
7878samples into a single report. It contains modules for a large number of
7879common bioinformatics tools.")
7880 (license license:gpl3)))
jackhill's copy of GNU Guix: https://guix.gnu.org/