64c40c729f505e7cded88c8f51c02245c8a3bc7c
[jackhill/guix/guix.git] / gnu / packages / bioinformatics.scm
1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016 Raoul Bonnal <ilpuccio.febo@gmail.com>
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)
29 #:use-module (guix utils)
30 #:use-module (guix download)
31 #:use-module (guix git-download)
32 #:use-module (guix hg-download)
33 #:use-module (guix build-system ant)
34 #:use-module (guix build-system gnu)
35 #:use-module (guix build-system cmake)
36 #:use-module (guix build-system perl)
37 #:use-module (guix build-system python)
38 #:use-module (guix build-system r)
39 #:use-module (guix build-system ruby)
40 #:use-module (guix build-system trivial)
41 #:use-module (gnu packages)
42 #:use-module (gnu packages autotools)
43 #:use-module (gnu packages algebra)
44 #:use-module (gnu packages base)
45 #:use-module (gnu packages bash)
46 #:use-module (gnu packages bison)
47 #:use-module (gnu packages boost)
48 #:use-module (gnu packages compression)
49 #:use-module (gnu packages cpio)
50 #:use-module (gnu packages curl)
51 #:use-module (gnu packages documentation)
52 #:use-module (gnu packages datastructures)
53 #:use-module (gnu packages file)
54 #:use-module (gnu packages flex)
55 #:use-module (gnu packages gawk)
56 #:use-module (gnu packages gcc)
57 #:use-module (gnu packages gd)
58 #:use-module (gnu packages gtk)
59 #:use-module (gnu packages glib)
60 #:use-module (gnu packages groff)
61 #:use-module (gnu packages guile)
62 #:use-module (gnu packages haskell)
63 #:use-module (gnu packages image)
64 #:use-module (gnu packages imagemagick)
65 #:use-module (gnu packages java)
66 #:use-module (gnu packages linux)
67 #:use-module (gnu packages logging)
68 #:use-module (gnu packages machine-learning)
69 #:use-module (gnu packages man)
70 #:use-module (gnu packages maths)
71 #:use-module (gnu packages mpi)
72 #:use-module (gnu packages ncurses)
73 #:use-module (gnu packages pcre)
74 #:use-module (gnu packages parallel)
75 #:use-module (gnu packages pdf)
76 #:use-module (gnu packages perl)
77 #:use-module (gnu packages pkg-config)
78 #:use-module (gnu packages popt)
79 #:use-module (gnu packages protobuf)
80 #:use-module (gnu packages python)
81 #:use-module (gnu packages readline)
82 #:use-module (gnu packages ruby)
83 #:use-module (gnu packages serialization)
84 #:use-module (gnu packages statistics)
85 #:use-module (gnu packages tbb)
86 #:use-module (gnu packages tex)
87 #:use-module (gnu packages texinfo)
88 #:use-module (gnu packages textutils)
89 #:use-module (gnu packages time)
90 #:use-module (gnu packages tls)
91 #:use-module (gnu packages vim)
92 #:use-module (gnu packages web)
93 #:use-module (gnu packages xml)
94 #:use-module (gnu packages xorg)
95 #:use-module (gnu packages zip)
96 #:use-module (srfi srfi-1))
97
98 (define-public aragorn
99 (package
100 (name "aragorn")
101 (version "1.2.38")
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
109 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
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
141 transfer-messenger RNA from nucleotide sequences, based on homology to known
142 tRNA consensus sequences and RNA structure. It also outputs the secondary
143 structure of the predicted RNA.")
144 (license license:gpl2)))
145
146 (define-public bamm
147 (package
148 (name "bamm")
149 (version "1.7.3")
150 (source (origin
151 (method url-fetch)
152 ;; BamM is not available on pypi.
153 (uri (string-append
154 "https://github.com/Ecogenomics/BamM/archive/"
155 version ".tar.gz"))
156 (file-name (string-append name "-" version ".tar.gz"))
157 (sha256
158 (base32
159 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
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)
220 ("python-pysam" ,python2-pysam)))
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
234 parse BAM files, specifically for the analysis of metagenomic data. For
235 instance, it implements several methods to assess contig-wise read coverage.")
236 (license license:lgpl3+)))
237
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)
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")))))))
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
268 BAM files.")
269 (license license:expat)))
270
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
324 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
325 transparently 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
329 (define-public bedops
330 (package
331 (name "bedops")
332 (version "2.4.14")
333 (source (origin
334 (method url-fetch)
335 (uri (string-append "https://github.com/bedops/bedops/archive/v"
336 version ".tar.gz"))
337 (file-name (string-append name "-" version ".tar.gz"))
338 (sha256
339 (base32
340 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
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
376 studies---mostly with regard to overlap and proximity relationships between
377 data sets. It aims to be scalable and flexible, facilitating the efficient
378 and accurate analysis and management of large-scale genomic data.
379
380 BEDOPS provides tools that perform highly efficient and scalable Boolean and
381 other set operations, statistical calculations, archiving, conversion and
382 other management of genomic data of arbitrary scale. Tasks can be easily
383 split by chromosome for distributing whole-genome analyses across a
384 computational cluster.")
385 (license license:gpl2+)))
386
387 (define-public bedtools
388 (package
389 (name "bedtools")
390 (version "2.26.0")
391 (source (origin
392 (method url-fetch)
393 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
394 version ".tar.gz"))
395 (file-name (string-append name "-" version ".tar.gz"))
396 (sha256
397 (base32
398 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
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
406 (modify-phases %standard-phases
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)))))
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
419 a wide-range of genomics analysis tasks. The most widely-used tools enable
420 genome arithmetic: that is, set theory on the genome. For example, bedtools
421 allows one to intersect, merge, count, complement, and shuffle genomic
422 intervals from multiple files in widely-used genomic file formats such as BAM,
423 BED, GFF/GTF, VCF.")
424 (license license:gpl2)))
425
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
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
467 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
468 provides the Ribotaper pipeline.")
469 (license license:gpl3+)))
470
471 (define-public ribodiff
472 (package
473 (name "ribodiff")
474 (version "0.2.2")
475 (source
476 (origin
477 (method url-fetch)
478 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
479 "archive/v" version ".tar.gz"))
480 (file-name (string-append name "-" version ".tar.gz"))
481 (sha256
482 (base32
483 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
484 (build-system python-build-system)
485 (arguments
486 `(#:python ,python-2
487 #:phases
488 (modify-phases %standard-phases
489 ;; Generate an installable executable script wrapper.
490 (add-after 'unpack 'patch-setup.py
491 (lambda _
492 (substitute* "setup.py"
493 (("^(.*)packages=.*" line prefix)
494 (string-append line "\n"
495 prefix "scripts=['scripts/TE.py'],\n")))
496 #t)))))
497 (inputs
498 `(("python-numpy" ,python2-numpy)
499 ("python-matplotlib" ,python2-matplotlib)
500 ("python-scipy" ,python2-scipy)
501 ("python-statsmodels" ,python2-statsmodels)))
502 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
503 (synopsis "Detect translation efficiency changes from ribosome footprints")
504 (description "RiboDiff is a statistical tool that detects the protein
505 translational efficiency change from Ribo-Seq (ribosome footprinting) and
506 RNA-Seq data. It uses a generalized linear model to detect genes showing
507 difference in translational profile taking mRNA abundance into account. It
508 facilitates us to decipher the translational regulation that behave
509 independently with transcriptional regulation.")
510 (license license:gpl3+)))
511
512 (define-public bioawk
513 (package
514 (name "bioawk")
515 (version "1.0")
516 (source (origin
517 (method url-fetch)
518 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
519 version ".tar.gz"))
520 (file-name (string-append name "-" version ".tar.gz"))
521 (sha256
522 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
523 (build-system gnu-build-system)
524 (inputs
525 `(("zlib" ,zlib)))
526 (native-inputs
527 `(("bison" ,bison)))
528 (arguments
529 `(#:tests? #f ; There are no tests to run.
530 ;; Bison must generate files, before other targets can build.
531 #:parallel-build? #f
532 #:phases
533 (modify-phases %standard-phases
534 (delete 'configure) ; There is no configure phase.
535 (replace 'install
536 (lambda* (#:key outputs #:allow-other-keys)
537 (let* ((out (assoc-ref outputs "out"))
538 (bin (string-append out "/bin"))
539 (man (string-append out "/share/man/man1")))
540 (mkdir-p man)
541 (copy-file "awk.1" (string-append man "/bioawk.1"))
542 (install-file "bioawk" bin)))))))
543 (home-page "https://github.com/lh3/bioawk")
544 (synopsis "AWK with bioinformatics extensions")
545 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
546 support of several common biological data formats, including optionally gzip'ed
547 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
548 also adds a few built-in functions and a command line option to use TAB as the
549 input/output delimiter. When the new functionality is not used, bioawk is
550 intended to behave exactly the same as the original BWK awk.")
551 (license license:x11)))
552
553 (define-public python2-pybedtools
554 (package
555 (name "python2-pybedtools")
556 (version "0.6.9")
557 (source (origin
558 (method url-fetch)
559 (uri (string-append
560 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
561 version ".tar.gz"))
562 (sha256
563 (base32
564 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
565 (build-system python-build-system)
566 (arguments `(#:python ,python-2)) ; no Python 3 support
567 (inputs
568 `(("python-matplotlib" ,python2-matplotlib)))
569 (propagated-inputs
570 `(("bedtools" ,bedtools)
571 ("samtools" ,samtools)))
572 (native-inputs
573 `(("python-cython" ,python2-cython)
574 ("python-pyyaml" ,python2-pyyaml)
575 ("python-nose" ,python2-nose)))
576 (home-page "https://pythonhosted.org/pybedtools/")
577 (synopsis "Python wrapper for BEDtools programs")
578 (description
579 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
580 which are widely used for genomic interval manipulation or \"genome algebra\".
581 pybedtools extends BEDTools by offering feature-level manipulations from with
582 Python.")
583 (license license:gpl2+)))
584
585 (define-public python-biom-format
586 (package
587 (name "python-biom-format")
588 (version "2.1.5")
589 (source
590 (origin
591 (method url-fetch)
592 ;; Use GitHub as source because PyPI distribution does not contain
593 ;; test data: https://github.com/biocore/biom-format/issues/693
594 (uri (string-append "https://github.com/biocore/biom-format/archive/"
595 version ".tar.gz"))
596 (file-name (string-append name "-" version ".tar.gz"))
597 (sha256
598 (base32
599 "1n25w3p1rixbpac8iysmzcja6m4ip5r6sz19l8y6wlwi49hxn278"))))
600 (build-system python-build-system)
601 (propagated-inputs
602 `(("python-numpy" ,python-numpy)
603 ("python-scipy" ,python-scipy)
604 ("python-future" ,python-future)
605 ("python-click" ,python-click)
606 ("python-h5py" ,python-h5py)))
607 (home-page "http://www.biom-format.org")
608 (synopsis "Biological Observation Matrix (BIOM) format utilities")
609 (description
610 "The BIOM file format is designed to be a general-use format for
611 representing counts of observations e.g. operational taxonomic units, KEGG
612 orthology groups or lipid types, in one or more biological samples
613 e.g. microbiome samples, genomes, metagenomes.")
614 (license license:bsd-3)
615 (properties `((python2-variant . ,(delay python2-biom-format))))))
616
617 (define-public python2-biom-format
618 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
619 (package
620 (inherit base)
621 (arguments
622 `(#:phases
623 (modify-phases %standard-phases
624 ;; Do not require the unmaintained pyqi library.
625 (add-after 'unpack 'remove-pyqi
626 (lambda _
627 (substitute* "setup.py"
628 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
629 #t)))
630 ,@(package-arguments base))))))
631
632 (define-public bioperl-minimal
633 (let* ((inputs `(("perl-module-build" ,perl-module-build)
634 ("perl-data-stag" ,perl-data-stag)
635 ("perl-libwww" ,perl-libwww)
636 ("perl-uri" ,perl-uri)))
637 (transitive-inputs
638 (map (compose package-name cadr)
639 (delete-duplicates
640 (concatenate
641 (map (compose package-transitive-target-inputs cadr) inputs))))))
642 (package
643 (name "bioperl-minimal")
644 (version "1.7.0")
645 (source
646 (origin
647 (method url-fetch)
648 (uri (string-append "https://github.com/bioperl/bioperl-live/"
649 "archive/release-"
650 (string-map (lambda (c)
651 (if (char=? c #\.)
652 #\- c)) version)
653 ".tar.gz"))
654 (sha256
655 (base32
656 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
657 (build-system perl-build-system)
658 (arguments
659 `(#:phases
660 (modify-phases %standard-phases
661 (add-after
662 'install 'wrap-programs
663 (lambda* (#:key outputs #:allow-other-keys)
664 ;; Make sure all executables in "bin" find the required Perl
665 ;; modules at runtime. As the PERL5LIB variable contains also
666 ;; the paths of native inputs, we pick the transitive target
667 ;; inputs from %build-inputs.
668 (let* ((out (assoc-ref outputs "out"))
669 (bin (string-append out "/bin/"))
670 (path (string-join
671 (cons (string-append out "/lib/perl5/site_perl")
672 (map (lambda (name)
673 (assoc-ref %build-inputs name))
674 ',transitive-inputs))
675 ":")))
676 (for-each (lambda (file)
677 (wrap-program file
678 `("PERL5LIB" ":" prefix (,path))))
679 (find-files bin "\\.pl$"))
680 #t))))))
681 (inputs inputs)
682 (native-inputs
683 `(("perl-test-most" ,perl-test-most)))
684 (home-page "http://search.cpan.org/dist/BioPerl")
685 (synopsis "Bioinformatics toolkit")
686 (description
687 "BioPerl is the product of a community effort to produce Perl code which
688 is useful in biology. Examples include Sequence objects, Alignment objects
689 and database searching objects. These objects not only do what they are
690 advertised to do in the documentation, but they also interact - Alignment
691 objects are made from the Sequence objects, Sequence objects have access to
692 Annotation and SeqFeature objects and databases, Blast objects can be
693 converted to Alignment objects, and so on. This means that the objects
694 provide a coordinated and extensible framework to do computational biology.")
695 (license (package-license perl)))))
696
697 (define-public python-biopython
698 (package
699 (name "python-biopython")
700 (version "1.68")
701 (source (origin
702 (method url-fetch)
703 ;; use PyPi rather than biopython.org to ease updating
704 (uri (pypi-uri "biopython" version))
705 (sha256
706 (base32
707 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
708 (build-system python-build-system)
709 (arguments
710 `(#:phases
711 (modify-phases %standard-phases
712 (add-before 'check 'set-home
713 ;; Some tests require a home directory to be set.
714 (lambda _ (setenv "HOME" "/tmp") #t)))))
715 (propagated-inputs
716 `(("python-numpy" ,python-numpy)))
717 (home-page "http://biopython.org/")
718 (synopsis "Tools for biological computation in Python")
719 (description
720 "Biopython is a set of tools for biological computation including parsers
721 for bioinformatics files into Python data structures; interfaces to common
722 bioinformatics programs; a standard sequence class and tools for performing
723 common operations on them; code to perform data classification; code for
724 dealing with alignments; code making it easy to split up parallelizable tasks
725 into separate processes; and more.")
726 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
727
728 (define-public python2-biopython
729 (package-with-python2 python-biopython))
730
731 ;; An outdated version of biopython is required for seqmagick, see
732 ;; https://github.com/fhcrc/seqmagick/issues/59
733 ;; When that issue has been resolved this package should be removed.
734 (define python2-biopython-1.66
735 (package
736 (inherit python2-biopython)
737 (version "1.66")
738 (source (origin
739 (method url-fetch)
740 (uri (pypi-uri "biopython" version))
741 (sha256
742 (base32
743 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
744
745 (define-public bpp-core
746 ;; The last release was in 2014 and the recommended way to install from source
747 ;; is to clone the git repository, so we do this.
748 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
749 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
750 (package
751 (name "bpp-core")
752 (version (string-append "2.2.0-1." (string-take commit 7)))
753 (source (origin
754 (method git-fetch)
755 (uri (git-reference
756 (url "http://biopp.univ-montp2.fr/git/bpp-core")
757 (commit commit)))
758 (file-name (string-append name "-" version "-checkout"))
759 (sha256
760 (base32
761 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
762 (build-system cmake-build-system)
763 (arguments
764 `(#:parallel-build? #f))
765 (inputs
766 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
767 ; compile all of the bpp packages with GCC 5.
768 (home-page "http://biopp.univ-montp2.fr")
769 (synopsis "C++ libraries for Bioinformatics")
770 (description
771 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
772 analysis, phylogenetics, molecular evolution and population genetics. It is
773 Object Oriented and is designed to be both easy to use and computer efficient.
774 Bio++ intends to help programmers to write computer expensive programs, by
775 providing them a set of re-usable tools.")
776 (license license:cecill-c))))
777
778 (define-public bpp-phyl
779 ;; The last release was in 2014 and the recommended way to install from source
780 ;; is to clone the git repository, so we do this.
781 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
782 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
783 (package
784 (name "bpp-phyl")
785 (version (string-append "2.2.0-1." (string-take commit 7)))
786 (source (origin
787 (method git-fetch)
788 (uri (git-reference
789 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
790 (commit commit)))
791 (file-name (string-append name "-" version "-checkout"))
792 (sha256
793 (base32
794 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
795 (build-system cmake-build-system)
796 (arguments
797 `(#:parallel-build? #f
798 ;; If out-of-source, test data is not copied into the build directory
799 ;; so the tests fail.
800 #:out-of-source? #f))
801 (inputs
802 `(("bpp-core" ,bpp-core)
803 ("bpp-seq" ,bpp-seq)
804 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
805 ;; modern GCC.
806 ("gcc" ,gcc-5)))
807 (home-page "http://biopp.univ-montp2.fr")
808 (synopsis "Bio++ phylogenetic Library")
809 (description
810 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
811 analysis, phylogenetics, molecular evolution and population genetics. This
812 library provides phylogenetics-related modules.")
813 (license license:cecill-c))))
814
815 (define-public bpp-popgen
816 ;; The last release was in 2014 and the recommended way to install from source
817 ;; is to clone the git repository, so we do this.
818 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
819 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
820 (package
821 (name "bpp-popgen")
822 (version (string-append "2.2.0-1." (string-take commit 7)))
823 (source (origin
824 (method git-fetch)
825 (uri (git-reference
826 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
827 (commit commit)))
828 (file-name (string-append name "-" version "-checkout"))
829 (sha256
830 (base32
831 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
832 (build-system cmake-build-system)
833 (arguments
834 `(#:parallel-build? #f
835 #:tests? #f)) ; There are no tests.
836 (inputs
837 `(("bpp-core" ,bpp-core)
838 ("bpp-seq" ,bpp-seq)
839 ("gcc" ,gcc-5)))
840 (home-page "http://biopp.univ-montp2.fr")
841 (synopsis "Bio++ population genetics library")
842 (description
843 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
844 analysis, phylogenetics, molecular evolution and population genetics. This
845 library provides population genetics-related modules.")
846 (license license:cecill-c))))
847
848 (define-public bpp-seq
849 ;; The last release was in 2014 and the recommended way to install from source
850 ;; is to clone the git repository, so we do this.
851 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
852 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
853 (package
854 (name "bpp-seq")
855 (version (string-append "2.2.0-1." (string-take commit 7)))
856 (source (origin
857 (method git-fetch)
858 (uri (git-reference
859 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
860 (commit commit)))
861 (file-name (string-append name "-" version "-checkout"))
862 (sha256
863 (base32
864 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
865 (build-system cmake-build-system)
866 (arguments
867 `(#:parallel-build? #f
868 ;; If out-of-source, test data is not copied into the build directory
869 ;; so the tests fail.
870 #:out-of-source? #f))
871 (inputs
872 `(("bpp-core" ,bpp-core)
873 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
874 (home-page "http://biopp.univ-montp2.fr")
875 (synopsis "Bio++ sequence library")
876 (description
877 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
878 analysis, phylogenetics, molecular evolution and population genetics. This
879 library provides sequence-related modules.")
880 (license license:cecill-c))))
881
882 (define-public bppsuite
883 ;; The last release was in 2014 and the recommended way to install from source
884 ;; is to clone the git repository, so we do this.
885 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
886 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
887 (package
888 (name "bppsuite")
889 (version (string-append "2.2.0-1." (string-take commit 7)))
890 (source (origin
891 (method git-fetch)
892 (uri (git-reference
893 (url "http://biopp.univ-montp2.fr/git/bppsuite")
894 (commit commit)))
895 (file-name (string-append name "-" version "-checkout"))
896 (sha256
897 (base32
898 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
899 (build-system cmake-build-system)
900 (arguments
901 `(#:parallel-build? #f
902 #:tests? #f)) ; There are no tests.
903 (native-inputs
904 `(("groff" ,groff)
905 ("man-db" ,man-db)
906 ("texinfo" ,texinfo)))
907 (inputs
908 `(("bpp-core" ,bpp-core)
909 ("bpp-seq" ,bpp-seq)
910 ("bpp-phyl" ,bpp-phyl)
911 ("bpp-phyl" ,bpp-popgen)
912 ("gcc" ,gcc-5)))
913 (home-page "http://biopp.univ-montp2.fr")
914 (synopsis "Bioinformatics tools written with the Bio++ libraries")
915 (description
916 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
917 analysis, phylogenetics, molecular evolution and population genetics. This
918 package provides command line tools using the Bio++ library.")
919 (license license:cecill-c))))
920
921 (define-public blast+
922 (package
923 (name "blast+")
924 (version "2.4.0")
925 (source (origin
926 (method url-fetch)
927 (uri (string-append
928 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
929 version "/ncbi-blast-" version "+-src.tar.gz"))
930 (sha256
931 (base32
932 "14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
933 (modules '((guix build utils)))
934 (snippet
935 '(begin
936 ;; Remove bundled bzip2 and zlib
937 (delete-file-recursively "c++/src/util/compress/bzip2")
938 (delete-file-recursively "c++/src/util/compress/zlib")
939 (substitute* "c++/src/util/compress/Makefile.in"
940 (("bzip2 zlib api") "api"))
941 ;; Remove useless msbuild directory
942 (delete-file-recursively
943 "c++/src/build-system/project_tree_builder/msbuild")
944 #t))))
945 (build-system gnu-build-system)
946 (arguments
947 `(;; There are three(!) tests for this massive library, and all fail with
948 ;; "unparsable timing stats".
949 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
950 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
951 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
952 #:tests? #f
953 #:out-of-source? #t
954 #:parallel-build? #f ; not supported
955 #:phases
956 (modify-phases %standard-phases
957 (add-before
958 'configure 'set-HOME
959 ;; $HOME needs to be set at some point during the configure phase
960 (lambda _ (setenv "HOME" "/tmp") #t))
961 (add-after
962 'unpack 'enter-dir
963 (lambda _ (chdir "c++") #t))
964 (add-after
965 'enter-dir 'fix-build-system
966 (lambda _
967 (define (which* cmd)
968 (cond ((string=? cmd "date")
969 ;; make call to "date" deterministic
970 "date -d @0")
971 ((which cmd)
972 => identity)
973 (else
974 (format (current-error-port)
975 "WARNING: Unable to find absolute path for ~s~%"
976 cmd)
977 #f)))
978
979 ;; Rewrite hardcoded paths to various tools
980 (substitute* (append '("src/build-system/configure.ac"
981 "src/build-system/configure"
982 "scripts/common/impl/if_diff.sh"
983 "scripts/common/impl/run_with_lock.sh"
984 "src/build-system/Makefile.configurables.real"
985 "src/build-system/Makefile.in.top"
986 "src/build-system/Makefile.meta.gmake=no"
987 "src/build-system/Makefile.meta.in"
988 "src/build-system/Makefile.meta_l"
989 "src/build-system/Makefile.meta_p"
990 "src/build-system/Makefile.meta_r"
991 "src/build-system/Makefile.mk.in"
992 "src/build-system/Makefile.requirements"
993 "src/build-system/Makefile.rules_with_autodep.in")
994 (find-files "scripts/common/check" "\\.sh$"))
995 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
996 (or (which* cmd) all)))
997
998 (substitute* (find-files "src/build-system" "^config.*")
999 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1000 (("^PATH=.*") ""))
1001
1002 ;; rewrite "/var/tmp" in check script
1003 (substitute* "scripts/common/check/check_make_unix.sh"
1004 (("/var/tmp") "/tmp"))
1005
1006 ;; do not reset PATH
1007 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1008 (("^ *PATH=.*") "")
1009 (("action=/bin/") "action=")
1010 (("export PATH") ":"))
1011 #t))
1012 (replace
1013 'configure
1014 (lambda* (#:key inputs outputs #:allow-other-keys)
1015 (let ((out (assoc-ref outputs "out"))
1016 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1017 (include (string-append (assoc-ref outputs "include")
1018 "/include/ncbi-tools++")))
1019 ;; The 'configure' script doesn't recognize things like
1020 ;; '--enable-fast-install'.
1021 (zero? (system* "./configure.orig"
1022 (string-append "--with-build-root=" (getcwd) "/build")
1023 (string-append "--prefix=" out)
1024 (string-append "--libdir=" lib)
1025 (string-append "--includedir=" include)
1026 (string-append "--with-bz2="
1027 (assoc-ref inputs "bzip2"))
1028 (string-append "--with-z="
1029 (assoc-ref inputs "zlib"))
1030 ;; Each library is built twice by default, once
1031 ;; with "-static" in its name, and again
1032 ;; without.
1033 "--without-static"
1034 "--with-dll"))))))))
1035 (outputs '("out" ; 19 MB
1036 "lib" ; 203 MB
1037 "include")) ; 32 MB
1038 (inputs
1039 `(("bzip2" ,bzip2)
1040 ("zlib" ,zlib)))
1041 (native-inputs
1042 `(("cpio" ,cpio)))
1043 (home-page "http://blast.ncbi.nlm.nih.gov")
1044 (synopsis "Basic local alignment search tool")
1045 (description
1046 "BLAST is a popular method of performing a DNA or protein sequence
1047 similarity search, using heuristics to produce results quickly. It also
1048 calculates an “expect value” that estimates how many matches would have
1049 occurred at a given score by chance, which can aid a user in judging how much
1050 confidence to have in an alignment.")
1051 ;; Most of the sources are in the public domain, with the following
1052 ;; exceptions:
1053 ;; * Expat:
1054 ;; * ./c++/include/util/bitset/
1055 ;; * ./c++/src/html/ncbi_menu*.js
1056 ;; * Boost license:
1057 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1058 ;; * LGPL 2+:
1059 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1060 ;; * ASL 2.0:
1061 ;; * ./c++/src/corelib/teamcity_*
1062 (license (list license:public-domain
1063 license:expat
1064 license:boost1.0
1065 license:lgpl2.0+
1066 license:asl2.0))))
1067
1068 (define-public bless
1069 (package
1070 (name "bless")
1071 (version "1p02")
1072 (source (origin
1073 (method url-fetch)
1074 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1075 version ".tgz"))
1076 (sha256
1077 (base32
1078 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1079 (modules '((guix build utils)))
1080 (snippet
1081 `(begin
1082 ;; Remove bundled boost, pigz, zlib, and .git directory
1083 ;; FIXME: also remove bundled sources for murmurhash3 and
1084 ;; kmc once packaged.
1085 (delete-file-recursively "boost")
1086 (delete-file-recursively "pigz")
1087 (delete-file-recursively "google-sparsehash")
1088 (delete-file-recursively "zlib")
1089 (delete-file-recursively ".git")
1090 #t))))
1091 (build-system gnu-build-system)
1092 (arguments
1093 '(#:tests? #f ;no "check" target
1094 #:make-flags
1095 (list (string-append "ZLIB="
1096 (assoc-ref %build-inputs "zlib")
1097 "/lib/libz.a")
1098 (string-append "LDFLAGS="
1099 (string-join '("-lboost_filesystem"
1100 "-lboost_system"
1101 "-lboost_iostreams"
1102 "-lz"
1103 "-fopenmp"
1104 "-std=c++11"))))
1105 #:phases
1106 (modify-phases %standard-phases
1107 (add-after 'unpack 'do-not-build-bundled-pigz
1108 (lambda* (#:key inputs outputs #:allow-other-keys)
1109 (substitute* "Makefile"
1110 (("cd pigz/pigz-2.3.3; make") ""))
1111 #t))
1112 (add-after 'unpack 'patch-paths-to-executables
1113 (lambda* (#:key inputs outputs #:allow-other-keys)
1114 (substitute* "parse_args.cpp"
1115 (("kmc_binary = .*")
1116 (string-append "kmc_binary = \""
1117 (assoc-ref outputs "out")
1118 "/bin/kmc\";"))
1119 (("pigz_binary = .*")
1120 (string-append "pigz_binary = \""
1121 (assoc-ref inputs "pigz")
1122 "/bin/pigz\";")))
1123 #t))
1124 (replace 'install
1125 (lambda* (#:key outputs #:allow-other-keys)
1126 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1127 (for-each (lambda (file)
1128 (install-file file bin))
1129 '("bless" "kmc/bin/kmc"))
1130 #t)))
1131 (delete 'configure))))
1132 (native-inputs
1133 `(("perl" ,perl)))
1134 (inputs
1135 `(("openmpi" ,openmpi)
1136 ("boost" ,boost)
1137 ("sparsehash" ,sparsehash)
1138 ("pigz" ,pigz)
1139 ("zlib" ,zlib)))
1140 (supported-systems '("x86_64-linux"))
1141 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1142 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1143 (description
1144 "@dfn{Bloom-filter-based error correction solution for high-throughput
1145 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1146 correction tool for genomic reads produced by @dfn{Next-generation
1147 sequencing} (NGS). BLESS produces accurate correction results with much less
1148 memory compared with previous solutions and is also able to tolerate a higher
1149 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1150 errors at the end of reads.")
1151 (license license:gpl3+)))
1152
1153 (define-public bowtie
1154 (package
1155 (name "bowtie")
1156 (version "2.2.9")
1157 (source (origin
1158 (method url-fetch)
1159 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1160 version ".tar.gz"))
1161 (file-name (string-append name "-" version ".tar.gz"))
1162 (sha256
1163 (base32
1164 "1vp5db8i7is57iwjybcdg18f5ivyzlj5g1ix1nlvxainzivhz55g"))
1165 (modules '((guix build utils)))
1166 (snippet
1167 '(substitute* "Makefile"
1168 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1169 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1170 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1171 (build-system gnu-build-system)
1172 (inputs `(("perl" ,perl)
1173 ("perl-clone" ,perl-clone)
1174 ("perl-test-deep" ,perl-test-deep)
1175 ("perl-test-simple" ,perl-test-simple)
1176 ("python" ,python-2)
1177 ("tbb" ,tbb)))
1178 (arguments
1179 '(#:make-flags
1180 (list "allall"
1181 "WITH_TBB=1"
1182 (string-append "prefix=" (assoc-ref %outputs "out")))
1183 #:phases
1184 (alist-delete
1185 'configure
1186 (alist-replace
1187 'check
1188 (lambda* (#:key outputs #:allow-other-keys)
1189 (system* "perl"
1190 "scripts/test/simple_tests.pl"
1191 "--bowtie2=./bowtie2"
1192 "--bowtie2-build=./bowtie2-build"))
1193 %standard-phases))))
1194 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1195 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1196 (description
1197 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1198 reads to long reference sequences. It is particularly good at aligning reads
1199 of about 50 up to 100s or 1,000s of characters, and particularly good at
1200 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1201 genome with an FM Index to keep its memory footprint small: for the human
1202 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1203 gapped, local, and paired-end alignment modes.")
1204 (supported-systems '("x86_64-linux"))
1205 (license license:gpl3+)))
1206
1207 (define-public tophat
1208 (package
1209 (name "tophat")
1210 (version "2.1.0")
1211 (source (origin
1212 (method url-fetch)
1213 (uri (string-append
1214 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1215 version ".tar.gz"))
1216 (sha256
1217 (base32
1218 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1219 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1220 (modules '((guix build utils)))
1221 (snippet
1222 '(begin
1223 ;; Remove bundled SeqAn and samtools
1224 (delete-file-recursively "src/SeqAn-1.3")
1225 (delete-file-recursively "src/samtools-0.1.18")
1226 #t))))
1227 (build-system gnu-build-system)
1228 (arguments
1229 '(#:parallel-build? #f ; not supported
1230 #:phases
1231 (modify-phases %standard-phases
1232 (add-after 'unpack 'use-system-samtools
1233 (lambda* (#:key inputs #:allow-other-keys)
1234 (substitute* "src/Makefile.in"
1235 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1236 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1237 (("SAMPROG = samtools_0\\.1\\.18") "")
1238 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1239 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1240 (substitute* '("src/common.cpp"
1241 "src/tophat.py")
1242 (("samtools_0.1.18") (which "samtools")))
1243 (substitute* '("src/common.h"
1244 "src/bam2fastx.cpp")
1245 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1246 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1247 (substitute* '("src/bwt_map.h"
1248 "src/map2gtf.h"
1249 "src/align_status.h")
1250 (("#include <bam.h>") "#include <samtools/bam.h>")
1251 (("#include <sam.h>") "#include <samtools/sam.h>"))
1252 #t)))))
1253 (inputs
1254 `(("boost" ,boost)
1255 ("bowtie" ,bowtie)
1256 ("samtools" ,samtools-0.1)
1257 ("ncurses" ,ncurses)
1258 ("python" ,python-2)
1259 ("perl" ,perl)
1260 ("zlib" ,zlib)
1261 ("seqan" ,seqan)))
1262 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1263 (synopsis "Spliced read mapper for RNA-Seq data")
1264 (description
1265 "TopHat is a fast splice junction mapper for nucleotide sequence
1266 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1267 mammalian-sized genomes using the ultra high-throughput short read
1268 aligner Bowtie, and then analyzes the mapping results to identify
1269 splice junctions between exons.")
1270 ;; TopHat is released under the Boost Software License, Version 1.0
1271 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1272 (license license:boost1.0)))
1273
1274 (define-public bwa
1275 (package
1276 (name "bwa")
1277 (version "0.7.12")
1278 (source (origin
1279 (method url-fetch)
1280 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1281 version ".tar.bz2"))
1282 (sha256
1283 (base32
1284 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
1285 (build-system gnu-build-system)
1286 (arguments
1287 '(#:tests? #f ;no "check" target
1288 #:phases
1289 (alist-replace
1290 'install
1291 (lambda* (#:key outputs #:allow-other-keys)
1292 (let ((bin (string-append
1293 (assoc-ref outputs "out") "/bin"))
1294 (doc (string-append
1295 (assoc-ref outputs "out") "/share/doc/bwa"))
1296 (man (string-append
1297 (assoc-ref outputs "out") "/share/man/man1")))
1298 (install-file "bwa" bin)
1299 (install-file "README.md" doc)
1300 (install-file "bwa.1" man)))
1301 ;; no "configure" script
1302 (alist-delete 'configure %standard-phases))))
1303 (inputs `(("zlib" ,zlib)))
1304 ;; Non-portable SSE instructions are used so building fails on platforms
1305 ;; other than x86_64.
1306 (supported-systems '("x86_64-linux"))
1307 (home-page "http://bio-bwa.sourceforge.net/")
1308 (synopsis "Burrows-Wheeler sequence aligner")
1309 (description
1310 "BWA is a software package for mapping low-divergent sequences against a
1311 large reference genome, such as the human genome. It consists of three
1312 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1313 designed for Illumina sequence reads up to 100bp, while the rest two for
1314 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1315 features such as long-read support and split alignment, but BWA-MEM, which is
1316 the latest, is generally recommended for high-quality queries as it is faster
1317 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1318 70-100bp Illumina reads.")
1319 (license license:gpl3+)))
1320
1321 (define-public bwa-pssm
1322 (package (inherit bwa)
1323 (name "bwa-pssm")
1324 (version "0.5.11")
1325 (source (origin
1326 (method url-fetch)
1327 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1328 "archive/" version ".tar.gz"))
1329 (file-name (string-append name "-" version ".tar.gz"))
1330 (sha256
1331 (base32
1332 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1333 (build-system gnu-build-system)
1334 (inputs
1335 `(("gdsl" ,gdsl)
1336 ("zlib" ,zlib)
1337 ("perl" ,perl)))
1338 (home-page "http://bwa-pssm.binf.ku.dk/")
1339 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1340 (description
1341 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1342 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1343 existing aligners it is fast and sensitive. Unlike most other aligners,
1344 however, it is also adaptible in the sense that one can direct the alignment
1345 based on known biases within the data set. It is coded as a modification of
1346 the original BWA alignment program and shares the genome index structure as
1347 well as many of the command line options.")
1348 (license license:gpl3+)))
1349
1350 (define-public python2-bx-python
1351 (package
1352 (name "python2-bx-python")
1353 (version "0.7.2")
1354 (source (origin
1355 (method url-fetch)
1356 (uri (string-append
1357 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
1358 version ".tar.gz"))
1359 (sha256
1360 (base32
1361 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
1362 (modules '((guix build utils)))
1363 (snippet
1364 '(substitute* "setup.py"
1365 ;; remove dependency on outdated "distribute" module
1366 (("^from distribute_setup import use_setuptools") "")
1367 (("^use_setuptools\\(\\)") "")))))
1368 (build-system python-build-system)
1369 (arguments
1370 `(#:tests? #f ;tests fail because test data are not included
1371 #:python ,python-2))
1372 (inputs
1373 `(("python-numpy" ,python2-numpy)
1374 ("zlib" ,zlib)))
1375 (native-inputs
1376 `(("python-nose" ,python2-nose)))
1377 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1378 (synopsis "Tools for manipulating biological data")
1379 (description
1380 "bx-python provides tools for manipulating biological data, particularly
1381 multiple sequence alignments.")
1382 (license license:expat)))
1383
1384 (define-public python-pysam
1385 (package
1386 (name "python-pysam")
1387 (version "0.9.1.4")
1388 (source (origin
1389 (method url-fetch)
1390 ;; Test data is missing on PyPi.
1391 (uri (string-append
1392 "https://github.com/pysam-developers/pysam/archive/v"
1393 version ".tar.gz"))
1394 (file-name (string-append name "-" version ".tar.gz"))
1395 (sha256
1396 (base32
1397 "0y41ssbg6nvn2jgcbnrvkzblpjcwszaiv1rgyd8dwzjkrbfsgsmc"))
1398 (modules '((guix build utils)))
1399 (snippet
1400 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1401 '(delete-file-recursively "htslib"))))
1402 (build-system python-build-system)
1403 (arguments
1404 `(#:phases
1405 (modify-phases %standard-phases
1406 (add-before 'build 'set-flags
1407 (lambda* (#:key inputs #:allow-other-keys)
1408 (setenv "HTSLIB_MODE" "external")
1409 (setenv "HTSLIB_LIBRARY_DIR"
1410 (string-append (assoc-ref inputs "htslib") "/lib"))
1411 (setenv "HTSLIB_INCLUDE_DIR"
1412 (string-append (assoc-ref inputs "htslib") "/include"))
1413 (setenv "LDFLAGS" "-lncurses")
1414 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1415 #t))
1416 (delete 'check)
1417 (add-after 'install 'check
1418 (lambda* (#:key inputs outputs #:allow-other-keys)
1419 (setenv "PYTHONPATH"
1420 (string-append
1421 (getenv "PYTHONPATH")
1422 ":" (assoc-ref outputs "out")
1423 "/lib/python"
1424 (string-take (string-take-right
1425 (assoc-ref inputs "python") 5) 3)
1426 "/site-packages"))
1427 ;; Step out of source dir so python does not import from CWD.
1428 (chdir "tests")
1429 (setenv "HOME" "/tmp")
1430 (and (zero? (system* "make" "-C" "pysam_data"))
1431 (zero? (system* "make" "-C" "cbcf_data"))
1432 (zero? (system* "nosetests" "-v"))))))))
1433 (propagated-inputs
1434 `(("htslib" ,htslib))) ; Included from installed header files.
1435 (inputs
1436 `(("ncurses" ,ncurses)
1437 ("zlib" ,zlib)))
1438 (native-inputs
1439 `(("python-cython" ,python-cython)
1440 ;; Dependencies below are are for tests only.
1441 ("samtools" ,samtools)
1442 ("bcftools" ,bcftools)
1443 ("python-nose" ,python-nose)))
1444 (home-page "https://github.com/pysam-developers/pysam")
1445 (synopsis "Python bindings to the SAMtools C API")
1446 (description
1447 "Pysam is a Python module for reading and manipulating files in the
1448 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1449 also includes an interface for tabix.")
1450 (license license:expat)))
1451
1452 (define-public python2-pysam
1453 (package-with-python2 python-pysam))
1454
1455 (define-public python-twobitreader
1456 (package
1457 (name "python-twobitreader")
1458 (version "3.1.4")
1459 (source (origin
1460 (method url-fetch)
1461 (uri (pypi-uri "twobitreader" version))
1462 (sha256
1463 (base32
1464 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1465 (build-system python-build-system)
1466 (arguments
1467 '(;; Tests are not distributed in the PyPi release.
1468 ;; TODO Try building from the Git repo or asking the upstream maintainer
1469 ;; to distribute the tests on PyPi.
1470 #:tests? #f))
1471 (native-inputs
1472 `(("python-sphinx" ,python-sphinx)))
1473 (home-page "https://github.com/benjschiller/twobitreader")
1474 (synopsis "Python library for reading .2bit files")
1475 (description
1476 "twobitreader is a Python library for reading .2bit files as used by the
1477 UCSC genome browser.")
1478 (license license:artistic2.0)))
1479
1480 (define-public python2-twobitreader
1481 (package-with-python2 python-twobitreader))
1482
1483 (define-public python-plastid
1484 (package
1485 (name "python-plastid")
1486 (version "0.4.6")
1487 (source (origin
1488 (method url-fetch)
1489 (uri (pypi-uri "plastid" version))
1490 (sha256
1491 (base32
1492 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
1493 (build-system python-build-system)
1494 (arguments
1495 ;; Some test files are not included.
1496 `(#:tests? #f))
1497 (propagated-inputs
1498 `(("python-numpy" ,python-numpy)
1499 ("python-scipy" ,python-scipy)
1500 ("python-pandas" ,python-pandas)
1501 ("python-pysam" ,python-pysam)
1502 ("python-matplotlib" ,python-matplotlib)
1503 ("python-biopython" ,python-biopython)
1504 ("python-twobitreader" ,python-twobitreader)
1505 ("python-termcolor" ,python-termcolor)))
1506 (native-inputs
1507 `(("python-cython" ,python-cython)
1508 ("python-nose" ,python-nose)))
1509 (home-page "https://github.com/joshuagryphon/plastid")
1510 (synopsis "Python library for genomic analysis")
1511 (description
1512 "plastid is a Python library for genomic analysis – in particular,
1513 high-throughput sequencing data – with an emphasis on simplicity.")
1514 (license license:bsd-3)))
1515
1516 (define-public python2-plastid
1517 (package-with-python2 python-plastid))
1518
1519 (define-public cd-hit
1520 (package
1521 (name "cd-hit")
1522 (version "4.6.6")
1523 (source (origin
1524 (method url-fetch)
1525 (uri (string-append "https://github.com/weizhongli/cdhit"
1526 "/releases/download/V" version
1527 "/cd-hit-v" version "-2016-0711.tar.gz"))
1528 (sha256
1529 (base32
1530 "1w8hd4fszgg29nqiz569fldwy012la77nljcmlhglgicws56z54p"))))
1531 (build-system gnu-build-system)
1532 (arguments
1533 `(#:tests? #f ; there are no tests
1534 #:make-flags
1535 ;; Executables are copied directly to the PREFIX.
1536 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1537 #:phases
1538 (modify-phases %standard-phases
1539 ;; No "configure" script
1540 (delete 'configure)
1541 ;; Remove sources of non-determinism
1542 (add-after 'unpack 'be-timeless
1543 (lambda _
1544 (substitute* "cdhit-utility.c++"
1545 ((" \\(built on \" __DATE__ \"\\)") ""))
1546 (substitute* "cdhit-common.c++"
1547 (("__DATE__") "\"0\"")
1548 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1549 #t))
1550 ;; The "install" target does not create the target directory
1551 (add-before 'install 'create-target-dir
1552 (lambda* (#:key outputs #:allow-other-keys)
1553 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1554 #t)))))
1555 (inputs
1556 `(("perl" ,perl)))
1557 (home-page "http://weizhongli-lab.org/cd-hit/")
1558 (synopsis "Cluster and compare protein or nucleotide sequences")
1559 (description
1560 "CD-HIT is a program for clustering and comparing protein or nucleotide
1561 sequences. CD-HIT is designed to be fast and handle extremely large
1562 databases.")
1563 ;; The manual says: "It can be copied under the GNU General Public License
1564 ;; version 2 (GPLv2)."
1565 (license license:gpl2)))
1566
1567 (define-public clipper
1568 (package
1569 (name "clipper")
1570 (version "1.1")
1571 (source (origin
1572 (method url-fetch)
1573 (uri (string-append
1574 "https://github.com/YeoLab/clipper/archive/"
1575 version ".tar.gz"))
1576 (file-name (string-append name "-" version ".tar.gz"))
1577 (sha256
1578 (base32
1579 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1580 (modules '((guix build utils)))
1581 (snippet
1582 '(begin
1583 ;; remove unnecessary setup dependency
1584 (substitute* "setup.py"
1585 (("setup_requires = .*") ""))
1586 (for-each delete-file
1587 '("clipper/src/peaks.so"
1588 "clipper/src/readsToWiggle.so"))
1589 (delete-file-recursively "dist/")
1590 #t))))
1591 (build-system python-build-system)
1592 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1593 (inputs
1594 `(("htseq" ,htseq)
1595 ("python-pybedtools" ,python2-pybedtools)
1596 ("python-cython" ,python2-cython)
1597 ("python-scikit-learn" ,python2-scikit-learn)
1598 ("python-matplotlib" ,python2-matplotlib)
1599 ("python-pandas" ,python2-pandas)
1600 ("python-pysam" ,python2-pysam)
1601 ("python-numpy" ,python2-numpy)
1602 ("python-scipy" ,python2-scipy)))
1603 (native-inputs
1604 `(("python-mock" ,python2-mock) ; for tests
1605 ("python-pytz" ,python2-pytz))) ; for tests
1606 (home-page "https://github.com/YeoLab/clipper")
1607 (synopsis "CLIP peak enrichment recognition")
1608 (description
1609 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1610 (license license:gpl2)))
1611
1612 (define-public codingquarry
1613 (package
1614 (name "codingquarry")
1615 (version "2.0")
1616 (source (origin
1617 (method url-fetch)
1618 (uri (string-append
1619 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1620 version ".tar.gz"))
1621 (sha256
1622 (base32
1623 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1624 (build-system gnu-build-system)
1625 (arguments
1626 '(#:tests? #f ; no "check" target
1627 #:phases
1628 (modify-phases %standard-phases
1629 (delete 'configure)
1630 (replace 'install
1631 (lambda* (#:key outputs #:allow-other-keys)
1632 (let* ((out (assoc-ref outputs "out"))
1633 (bin (string-append out "/bin"))
1634 (doc (string-append out "/share/doc/codingquarry")))
1635 (install-file "INSTRUCTIONS.pdf" doc)
1636 (copy-recursively "QuarryFiles"
1637 (string-append out "/QuarryFiles"))
1638 (install-file "CodingQuarry" bin)
1639 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1640 (inputs `(("openmpi" ,openmpi)))
1641 (native-search-paths
1642 (list (search-path-specification
1643 (variable "QUARRY_PATH")
1644 (files '("QuarryFiles")))))
1645 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1646 (synopsis "Fungal gene predictor")
1647 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1648 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1649 (home-page "https://sourceforge.net/projects/codingquarry/")
1650 (license license:gpl3+)))
1651
1652 (define-public couger
1653 (package
1654 (name "couger")
1655 (version "1.8.2")
1656 (source (origin
1657 (method url-fetch)
1658 (uri (string-append
1659 "http://couger.oit.duke.edu/static/assets/COUGER"
1660 version ".zip"))
1661 (sha256
1662 (base32
1663 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1664 (build-system gnu-build-system)
1665 (arguments
1666 `(#:tests? #f
1667 #:phases
1668 (modify-phases %standard-phases
1669 (delete 'configure)
1670 (delete 'build)
1671 (replace
1672 'install
1673 (lambda* (#:key outputs #:allow-other-keys)
1674 (let ((out (assoc-ref outputs "out")))
1675 (copy-recursively "src" (string-append out "/src"))
1676 (mkdir (string-append out "/bin"))
1677 ;; Add "src" directory to module lookup path.
1678 (substitute* "couger"
1679 (("from argparse")
1680 (string-append "import sys\nsys.path.append(\""
1681 out "\")\nfrom argparse")))
1682 (copy-file "couger" (string-append out "/bin/couger")))
1683 #t))
1684 (add-after
1685 'install 'wrap-program
1686 (lambda* (#:key inputs outputs #:allow-other-keys)
1687 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1688 (let* ((out (assoc-ref outputs "out"))
1689 (path (getenv "PYTHONPATH")))
1690 (wrap-program (string-append out "/bin/couger")
1691 `("PYTHONPATH" ":" prefix (,path))))
1692 #t)))))
1693 (inputs
1694 `(("python" ,python-2)
1695 ("python2-pillow" ,python2-pillow)
1696 ("python2-numpy" ,python2-numpy)
1697 ("python2-scipy" ,python2-scipy)
1698 ("python2-matplotlib" ,python2-matplotlib)))
1699 (propagated-inputs
1700 `(("r" ,r)
1701 ("libsvm" ,libsvm)
1702 ("randomjungle" ,randomjungle)))
1703 (native-inputs
1704 `(("unzip" ,unzip)))
1705 (home-page "http://couger.oit.duke.edu")
1706 (synopsis "Identify co-factors in sets of genomic regions")
1707 (description
1708 "COUGER can be applied to any two sets of genomic regions bound by
1709 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1710 putative co-factors that provide specificity to each TF. The framework
1711 determines the genomic targets uniquely-bound by each TF, and identifies a
1712 small set of co-factors that best explain the in vivo binding differences
1713 between the two TFs.
1714
1715 COUGER uses classification algorithms (support vector machines and random
1716 forests) with features that reflect the DNA binding specificities of putative
1717 co-factors. The features are generated either from high-throughput TF-DNA
1718 binding data (from protein binding microarray experiments), or from large
1719 collections of DNA motifs.")
1720 (license license:gpl3+)))
1721
1722 (define-public clustal-omega
1723 (package
1724 (name "clustal-omega")
1725 (version "1.2.1")
1726 (source (origin
1727 (method url-fetch)
1728 (uri (string-append
1729 "http://www.clustal.org/omega/clustal-omega-"
1730 version ".tar.gz"))
1731 (sha256
1732 (base32
1733 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1734 (build-system gnu-build-system)
1735 (inputs
1736 `(("argtable" ,argtable)))
1737 (home-page "http://www.clustal.org/omega/")
1738 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1739 (description
1740 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1741 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1742 of handling data-sets of hundreds of thousands of sequences in reasonable
1743 time.")
1744 (license license:gpl2+)))
1745
1746 (define-public crossmap
1747 (package
1748 (name "crossmap")
1749 (version "0.2.1")
1750 (source (origin
1751 (method url-fetch)
1752 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1753 version ".tar.gz"))
1754 (sha256
1755 (base32
1756 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1757 ;; This patch has been sent upstream already and is available
1758 ;; for download from Sourceforge, but it has not been merged.
1759 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1760 (modules '((guix build utils)))
1761 ;; remove bundled copy of pysam
1762 (snippet
1763 '(delete-file-recursively "lib/pysam"))))
1764 (build-system python-build-system)
1765 (arguments
1766 `(#:python ,python-2
1767 #:phases
1768 (alist-cons-after
1769 'unpack 'set-env
1770 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1771 %standard-phases)))
1772 (inputs
1773 `(("python-numpy" ,python2-numpy)
1774 ("python-pysam" ,python2-pysam)
1775 ("zlib" ,zlib)))
1776 (native-inputs
1777 `(("python-cython" ,python2-cython)
1778 ("python-nose" ,python2-nose)))
1779 (home-page "http://crossmap.sourceforge.net/")
1780 (synopsis "Convert genome coordinates between assemblies")
1781 (description
1782 "CrossMap is a program for conversion of genome coordinates or annotation
1783 files between different genome assemblies. It supports most commonly used
1784 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1785 (license license:gpl2+)))
1786
1787 (define-public cufflinks
1788 (package
1789 (name "cufflinks")
1790 (version "2.2.1")
1791 (source (origin
1792 (method url-fetch)
1793 (uri (string-append "http://cole-trapnell-lab.github.io/"
1794 "cufflinks/assets/downloads/cufflinks-"
1795 version ".tar.gz"))
1796 (sha256
1797 (base32
1798 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1799 (build-system gnu-build-system)
1800 (arguments
1801 `(#:make-flags
1802 (list
1803 ;; The includes for "eigen" are located in a subdirectory.
1804 (string-append "EIGEN_CPPFLAGS="
1805 "-I" (assoc-ref %build-inputs "eigen")
1806 "/include/eigen3/")
1807 ;; Cufflinks must be linked with various boost libraries.
1808 (string-append "LDFLAGS="
1809 (string-join '("-lboost_system"
1810 "-lboost_serialization"
1811 "-lboost_thread"))))
1812 #:phases
1813 (modify-phases %standard-phases
1814 (add-after 'unpack 'fix-search-for-bam
1815 (lambda _
1816 (substitute* '("ax_bam.m4"
1817 "configure"
1818 "src/hits.h")
1819 (("<bam/sam\\.h>") "<samtools/sam.h>")
1820 (("<bam/bam\\.h>") "<samtools/bam.h>")
1821 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1822 #t)))
1823 #:configure-flags
1824 (list (string-append "--with-bam="
1825 (assoc-ref %build-inputs "samtools")))))
1826 (inputs
1827 `(("eigen" ,eigen)
1828 ("samtools" ,samtools-0.1)
1829 ("htslib" ,htslib)
1830 ("boost" ,boost)
1831 ("python" ,python-2)
1832 ("zlib" ,zlib)))
1833 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1834 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1835 (description
1836 "Cufflinks assembles RNA transcripts, estimates their abundances,
1837 and tests for differential expression and regulation in RNA-Seq
1838 samples. It accepts aligned RNA-Seq reads and assembles the
1839 alignments into a parsimonious set of transcripts. Cufflinks then
1840 estimates the relative abundances of these transcripts based on how
1841 many reads support each one, taking into account biases in library
1842 preparation protocols.")
1843 (license license:boost1.0)))
1844
1845 (define-public cutadapt
1846 (package
1847 (name "cutadapt")
1848 (version "1.12")
1849 (source (origin
1850 (method url-fetch)
1851 (uri (string-append
1852 "https://github.com/marcelm/cutadapt/archive/v"
1853 version ".tar.gz"))
1854 (file-name (string-append name "-" version ".tar.gz"))
1855 (sha256
1856 (base32
1857 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1858 (build-system python-build-system)
1859 (arguments
1860 `(#:phases
1861 (modify-phases %standard-phases
1862 ;; The tests must be run after installation.
1863 (delete 'check)
1864 (add-after 'install 'check
1865 (lambda* (#:key inputs outputs #:allow-other-keys)
1866 (setenv "PYTHONPATH"
1867 (string-append
1868 (getenv "PYTHONPATH")
1869 ":" (assoc-ref outputs "out")
1870 "/lib/python"
1871 (string-take (string-take-right
1872 (assoc-ref inputs "python") 5) 3)
1873 "/site-packages"))
1874 (zero? (system* "nosetests" "-P" "tests")))))))
1875 (inputs
1876 `(("python-xopen" ,python-xopen)))
1877 (native-inputs
1878 `(("python-cython" ,python-cython)
1879 ("python-nose" ,python-nose)))
1880 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1881 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1882 (description
1883 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1884 other types of unwanted sequence from high-throughput sequencing reads.")
1885 (license license:expat)))
1886
1887 (define-public libbigwig
1888 (package
1889 (name "libbigwig")
1890 (version "0.1.4")
1891 (source (origin
1892 (method url-fetch)
1893 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1894 "archive/" version ".tar.gz"))
1895 (file-name (string-append name "-" version ".tar.gz"))
1896 (sha256
1897 (base32
1898 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1899 (build-system gnu-build-system)
1900 (arguments
1901 `(#:test-target "test"
1902 #:make-flags
1903 (list "CC=gcc"
1904 (string-append "prefix=" (assoc-ref %outputs "out")))
1905 #:phases
1906 (modify-phases %standard-phases
1907 (delete 'configure)
1908 (add-before 'check 'disable-curl-test
1909 (lambda _
1910 (substitute* "Makefile"
1911 (("./test/testRemote.*") ""))
1912 #t))
1913 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1914 ;; there has not yet been a release containing this change.
1915 (add-before 'install 'create-target-dirs
1916 (lambda* (#:key outputs #:allow-other-keys)
1917 (let ((out (assoc-ref outputs "out")))
1918 (mkdir-p (string-append out "/lib"))
1919 (mkdir-p (string-append out "/include"))
1920 #t))))))
1921 (inputs
1922 `(("zlib" ,zlib)
1923 ("curl" ,curl)))
1924 (native-inputs
1925 `(("doxygen" ,doxygen)))
1926 (home-page "https://github.com/dpryan79/libBigWig")
1927 (synopsis "C library for handling bigWig files")
1928 (description
1929 "This package provides a C library for parsing local and remote BigWig
1930 files.")
1931 (license license:expat)))
1932
1933 (define-public python-pybigwig
1934 (package
1935 (name "python-pybigwig")
1936 (version "0.2.5")
1937 (source (origin
1938 (method url-fetch)
1939 (uri (pypi-uri "pyBigWig" version))
1940 (sha256
1941 (base32
1942 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1943 (modules '((guix build utils)))
1944 (snippet
1945 '(begin
1946 ;; Delete bundled libBigWig sources
1947 (delete-file-recursively "libBigWig")))))
1948 (build-system python-build-system)
1949 (arguments
1950 `(#:phases
1951 (modify-phases %standard-phases
1952 (add-after 'unpack 'link-with-libBigWig
1953 (lambda* (#:key inputs #:allow-other-keys)
1954 (substitute* "setup.py"
1955 (("libs=\\[") "libs=[\"BigWig\", "))
1956 #t)))))
1957 (inputs
1958 `(("libbigwig" ,libbigwig)
1959 ("zlib" ,zlib)
1960 ("curl" ,curl)))
1961 (home-page "https://github.com/dpryan79/pyBigWig")
1962 (synopsis "Access bigWig files in Python using libBigWig")
1963 (description
1964 "This package provides Python bindings to the libBigWig library for
1965 accessing bigWig files.")
1966 (license license:expat)))
1967
1968 (define-public python2-pybigwig
1969 (package-with-python2 python-pybigwig))
1970
1971 (define-public python-dendropy
1972 (package
1973 (name "python-dendropy")
1974 (version "4.2.0")
1975 (source
1976 (origin
1977 (method url-fetch)
1978 (uri (pypi-uri "DendroPy" version))
1979 (sha256
1980 (base32
1981 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))))
1982 (build-system python-build-system)
1983 (home-page "http://packages.python.org/DendroPy/")
1984 (synopsis "Library for phylogenetics and phylogenetic computing")
1985 (description
1986 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1987 writing, simulation, processing and manipulation of phylogenetic
1988 trees (phylogenies) and characters.")
1989 (license license:bsd-3)
1990 (properties `((python2-variant . ,(delay python2-dendropy))))))
1991
1992 (define-public python2-dendropy
1993 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1994 (package
1995 (inherit base)
1996 (arguments
1997 `(#:python ,python-2
1998 #:phases
1999 (modify-phases %standard-phases
2000 (replace 'check
2001 ;; There is currently a test failure that only happens on some
2002 ;; systems, and only using "setup.py test"
2003 (lambda _ (zero? (system* "nosetests")))))))
2004 (native-inputs `(("python2-nose" ,python2-nose)
2005 ,@(package-native-inputs base))))))
2006
2007
2008 (define-public deeptools
2009 (package
2010 (name "deeptools")
2011 (version "2.1.1")
2012 (source (origin
2013 (method url-fetch)
2014 (uri (string-append "https://github.com/fidelram/deepTools/"
2015 "archive/" version ".tar.gz"))
2016 (file-name (string-append name "-" version ".tar.gz"))
2017 (sha256
2018 (base32
2019 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
2020 (build-system python-build-system)
2021 (arguments
2022 `(#:python ,python-2))
2023 (inputs
2024 `(("python-scipy" ,python2-scipy)
2025 ("python-numpy" ,python2-numpy)
2026 ("python-numpydoc" ,python2-numpydoc)
2027 ("python-matplotlib" ,python2-matplotlib)
2028 ("python-bx-python" ,python2-bx-python)
2029 ("python-pysam" ,python2-pysam)
2030 ("python-pybigwig" ,python2-pybigwig)))
2031 (native-inputs
2032 `(("python-mock" ,python2-mock) ;for tests
2033 ("python-pytz" ,python2-pytz))) ;for tests
2034 (home-page "https://github.com/fidelram/deepTools")
2035 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2036 (description
2037 "DeepTools addresses the challenge of handling the large amounts of data
2038 that are now routinely generated from DNA sequencing centers. To do so,
2039 deepTools contains useful modules to process the mapped reads data to create
2040 coverage files in standard bedGraph and bigWig file formats. By doing so,
2041 deepTools allows the creation of normalized coverage files or the comparison
2042 between two files (for example, treatment and control). Finally, using such
2043 normalized and standardized files, multiple visualizations can be created to
2044 identify enrichments with functional annotations of the genome.")
2045 (license license:gpl3+)))
2046
2047 (define-public diamond
2048 (package
2049 (name "diamond")
2050 (version "0.8.31")
2051 (source (origin
2052 (method url-fetch)
2053 (uri (string-append
2054 "https://github.com/bbuchfink/diamond/archive/v"
2055 version ".tar.gz"))
2056 (file-name (string-append name "-" version ".tar.gz"))
2057 (sha256
2058 (base32
2059 "0nh79f4rpgq8vmlga743r7vd0z0ik6spy34f7vfq0v9lcmvfr7xq"))))
2060 (build-system cmake-build-system)
2061 (arguments
2062 '(#:tests? #f ; no "check" target
2063 #:phases
2064 (modify-phases %standard-phases
2065 (add-after 'unpack 'remove-native-compilation
2066 (lambda _
2067 (substitute* "CMakeLists.txt" (("-march=native") ""))
2068 #t)))))
2069 (inputs
2070 `(("zlib" ,zlib)))
2071 (home-page "https://github.com/bbuchfink/diamond")
2072 (synopsis "Accelerated BLAST compatible local sequence aligner")
2073 (description
2074 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2075 translated DNA query sequences against a protein reference database (BLASTP
2076 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2077 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2078 data and settings.")
2079 ;; diamond fails to build on other platforms
2080 ;; https://github.com/bbuchfink/diamond/issues/18
2081 (supported-systems '("x86_64-linux"))
2082 (license (license:non-copyleft "file://src/COPYING"
2083 "See src/COPYING in the distribution."))))
2084
2085 (define-public discrover
2086 (package
2087 (name "discrover")
2088 (version "1.6.0")
2089 (source
2090 (origin
2091 (method url-fetch)
2092 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2093 version ".tar.gz"))
2094 (file-name (string-append name "-" version ".tar.gz"))
2095 (sha256
2096 (base32
2097 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2098 (build-system cmake-build-system)
2099 (arguments `(#:tests? #f)) ; there are no tests
2100 (inputs
2101 `(("boost" ,boost)
2102 ("cairo" ,cairo)))
2103 (native-inputs
2104 `(("texlive" ,texlive)
2105 ("imagemagick" ,imagemagick)))
2106 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2107 (synopsis "Discover discriminative nucleotide sequence motifs")
2108 (description "Discrover is a motif discovery method to find binding sites
2109 of nucleic acid binding proteins.")
2110 (license license:gpl3+)))
2111
2112 (define-public eigensoft
2113 (let ((revision "1")
2114 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2115 (package
2116 (name "eigensoft")
2117 (version (string-append "6.1.2-"
2118 revision "."
2119 (string-take commit 9)))
2120 (source
2121 (origin
2122 (method git-fetch)
2123 (uri (git-reference
2124 (url "https://github.com/DReichLab/EIG.git")
2125 (commit commit)))
2126 (file-name (string-append "eigensoft-" commit "-checkout"))
2127 (sha256
2128 (base32
2129 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2130 (modules '((guix build utils)))
2131 ;; Remove pre-built binaries.
2132 (snippet '(begin
2133 (delete-file-recursively "bin")
2134 (mkdir "bin")
2135 #t))))
2136 (build-system gnu-build-system)
2137 (arguments
2138 `(#:tests? #f ; There are no tests.
2139 #:make-flags '("CC=gcc")
2140 #:phases
2141 (modify-phases %standard-phases
2142 ;; There is no configure phase, but the Makefile is in a
2143 ;; sub-directory.
2144 (replace 'configure
2145 (lambda _
2146 (chdir "src")
2147 ;; The link flags are incomplete.
2148 (substitute* "Makefile"
2149 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2150 #t))
2151 ;; The provided install target only copies executables to
2152 ;; the "bin" directory in the build root.
2153 (add-after 'install 'actually-install
2154 (lambda* (#:key outputs #:allow-other-keys)
2155 (let* ((out (assoc-ref outputs "out"))
2156 (bin (string-append out "/bin")))
2157 (for-each (lambda (file)
2158 (install-file file bin))
2159 (find-files "../bin" ".*"))
2160 #t))))))
2161 (inputs
2162 `(("gsl" ,gsl)
2163 ("lapack" ,lapack)
2164 ("openblas" ,openblas)
2165 ("perl" ,perl)
2166 ("gfortran" ,gfortran "lib")))
2167 (home-page "https://github.com/DReichLab/EIG")
2168 (synopsis "Tools for population genetics")
2169 (description "The EIGENSOFT package provides tools for population
2170 genetics and stratification correction. EIGENSOFT implements methods commonly
2171 used in population genetics analyses such as PCA, computation of Tracy-Widom
2172 statistics, and finding related individuals in structured populations. It
2173 comes with a built-in plotting script and supports multiple file formats and
2174 quantitative phenotypes.")
2175 ;; The license of the eigensoft tools is Expat, but since it's
2176 ;; linking with the GNU Scientific Library (GSL) the effective
2177 ;; license is the GPL.
2178 (license license:gpl3+))))
2179
2180 (define-public edirect
2181 (package
2182 (name "edirect")
2183 (version "4.10")
2184 (source (origin
2185 (method url-fetch)
2186 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2187 "versions/2016-05-03/edirect.tar.gz"))
2188 (sha256
2189 (base32
2190 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2191 (build-system perl-build-system)
2192 (arguments
2193 `(#:tests? #f ;no "check" target
2194 #:phases
2195 (modify-phases %standard-phases
2196 (delete 'configure)
2197 (delete 'build)
2198 (replace 'install
2199 (lambda* (#:key outputs #:allow-other-keys)
2200 (let ((target (string-append (assoc-ref outputs "out")
2201 "/bin")))
2202 (mkdir-p target)
2203 (copy-file "edirect.pl"
2204 (string-append target "/edirect.pl"))
2205 #t)))
2206 (add-after
2207 'install 'wrap-program
2208 (lambda* (#:key inputs outputs #:allow-other-keys)
2209 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2210 (let* ((out (assoc-ref outputs "out"))
2211 (path (getenv "PERL5LIB")))
2212 (wrap-program (string-append out "/bin/edirect.pl")
2213 `("PERL5LIB" ":" prefix (,path)))))))))
2214 (inputs
2215 `(("perl-html-parser" ,perl-html-parser)
2216 ("perl-encode-locale" ,perl-encode-locale)
2217 ("perl-file-listing" ,perl-file-listing)
2218 ("perl-html-tagset" ,perl-html-tagset)
2219 ("perl-html-tree" ,perl-html-tree)
2220 ("perl-http-cookies" ,perl-http-cookies)
2221 ("perl-http-date" ,perl-http-date)
2222 ("perl-http-message" ,perl-http-message)
2223 ("perl-http-negotiate" ,perl-http-negotiate)
2224 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2225 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2226 ("perl-net-http" ,perl-net-http)
2227 ("perl-uri" ,perl-uri)
2228 ("perl-www-robotrules" ,perl-www-robotrules)
2229 ("perl" ,perl)))
2230 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2231 (synopsis "Tools for accessing the NCBI's set of databases")
2232 (description
2233 "Entrez Direct (EDirect) is a method for accessing the National Center
2234 for Biotechnology Information's (NCBI) set of interconnected
2235 databases (publication, sequence, structure, gene, variation, expression,
2236 etc.) from a terminal. Functions take search terms from command-line
2237 arguments. Individual operations are combined to build multi-step queries.
2238 Record retrieval and formatting normally complete the process.
2239
2240 EDirect also provides an argument-driven function that simplifies the
2241 extraction of data from document summaries or other results that are returned
2242 in structured XML format. This can eliminate the need for writing custom
2243 software to answer ad hoc questions.")
2244 (license license:public-domain)))
2245
2246 (define-public exonerate
2247 (package
2248 (name "exonerate")
2249 (version "2.4.0")
2250 (source
2251 (origin
2252 (method url-fetch)
2253 (uri
2254 (string-append
2255 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2256 "exonerate-" version ".tar.gz"))
2257 (sha256
2258 (base32
2259 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2260 (build-system gnu-build-system)
2261 (arguments
2262 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2263 (native-inputs
2264 `(("pkg-config" ,pkg-config)))
2265 (inputs
2266 `(("glib" ,glib)))
2267 (home-page
2268 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2269 (synopsis "Generic tool for biological sequence alignment")
2270 (description
2271 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2272 the alignment of sequences using a many alignment models, either exhaustive
2273 dynamic programming or a variety of heuristics.")
2274 (license license:gpl3)))
2275
2276 (define-public express
2277 (package
2278 (name "express")
2279 (version "1.5.1")
2280 (source (origin
2281 (method url-fetch)
2282 (uri
2283 (string-append
2284 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2285 version "/express-" version "-src.tgz"))
2286 (sha256
2287 (base32
2288 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2289 (build-system cmake-build-system)
2290 (arguments
2291 `(#:tests? #f ;no "check" target
2292 #:phases
2293 (alist-cons-after
2294 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2295 (lambda* (#:key inputs #:allow-other-keys)
2296 (substitute* "CMakeLists.txt"
2297 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2298 "set(Boost_USE_STATIC_LIBS OFF)")
2299 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2300 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2301 (substitute* "src/CMakeLists.txt"
2302 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2303 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2304 #t)
2305 %standard-phases)))
2306 (inputs
2307 `(("boost" ,boost)
2308 ("bamtools" ,bamtools)
2309 ("protobuf" ,protobuf)
2310 ("zlib" ,zlib)))
2311 (home-page "http://bio.math.berkeley.edu/eXpress")
2312 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2313 (description
2314 "eXpress is a streaming tool for quantifying the abundances of a set of
2315 target sequences from sampled subsequences. Example applications include
2316 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2317 analysis (from RNA-Seq), transcription factor binding quantification in
2318 ChIP-Seq, and analysis of metagenomic data.")
2319 (license license:artistic2.0)))
2320
2321 (define-public express-beta-diversity
2322 (package
2323 (name "express-beta-diversity")
2324 (version "1.0.7")
2325 (source (origin
2326 (method url-fetch)
2327 (uri
2328 (string-append
2329 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2330 version ".tar.gz"))
2331 (file-name (string-append name "-" version ".tar.gz"))
2332 (sha256
2333 (base32
2334 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2335 (build-system gnu-build-system)
2336 (arguments
2337 `(#:phases
2338 (modify-phases %standard-phases
2339 (delete 'configure)
2340 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2341 (replace 'check
2342 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2343 "-u"))))
2344 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2345 (replace 'install
2346 (lambda* (#:key outputs #:allow-other-keys)
2347 (let ((bin (string-append (assoc-ref outputs "out")
2348 "/bin")))
2349 (mkdir-p bin)
2350 (copy-file "scripts/convertToEBD.py"
2351 (string-append bin "/convertToEBD.py"))
2352 (copy-file "bin/ExpressBetaDiversity"
2353 (string-append bin "/ExpressBetaDiversity"))
2354 #t))))))
2355 (inputs
2356 `(("python" ,python-2)))
2357 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2358 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2359 (description
2360 "Express Beta Diversity (EBD) calculates ecological beta diversity
2361 (dissimilarity) measures between biological communities. EBD implements a
2362 variety of diversity measures including those that make use of phylogenetic
2363 similarity of community members.")
2364 (license license:gpl3+)))
2365
2366 (define-public fasttree
2367 (package
2368 (name "fasttree")
2369 (version "2.1.9")
2370 (source (origin
2371 (method url-fetch)
2372 (uri (string-append
2373 "http://www.microbesonline.org/fasttree/FastTree-"
2374 version ".c"))
2375 (sha256
2376 (base32
2377 "0ljvvw8i1als1wbfzvrf15c3ii2vw9db20a259g6pzg34xyyb97k"))))
2378 (build-system gnu-build-system)
2379 (arguments
2380 `(#:tests? #f ; no "check" target
2381 #:phases
2382 (modify-phases %standard-phases
2383 (delete 'unpack)
2384 (delete 'configure)
2385 (replace 'build
2386 (lambda* (#:key source #:allow-other-keys)
2387 (and (zero? (system* "gcc"
2388 "-O3"
2389 "-finline-functions"
2390 "-funroll-loops"
2391 "-Wall"
2392 "-o"
2393 "FastTree"
2394 source
2395 "-lm"))
2396 (zero? (system* "gcc"
2397 "-DOPENMP"
2398 "-fopenmp"
2399 "-O3"
2400 "-finline-functions"
2401 "-funroll-loops"
2402 "-Wall"
2403 "-o"
2404 "FastTreeMP"
2405 source
2406 "-lm")))))
2407 (replace 'install
2408 (lambda* (#:key outputs #:allow-other-keys)
2409 (let ((bin (string-append (assoc-ref outputs "out")
2410 "/bin")))
2411 (mkdir-p bin)
2412 (copy-file "FastTree"
2413 (string-append bin "/FastTree"))
2414 (copy-file "FastTreeMP"
2415 (string-append bin "/FastTreeMP"))
2416 #t))))))
2417 (home-page "http://www.microbesonline.org/fasttree")
2418 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2419 (description
2420 "FastTree can handle alignments with up to a million of sequences in a
2421 reasonable amount of time and memory. For large alignments, FastTree is
2422 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2423 (license license:gpl2+)))
2424
2425 (define-public fastx-toolkit
2426 (package
2427 (name "fastx-toolkit")
2428 (version "0.0.14")
2429 (source (origin
2430 (method url-fetch)
2431 (uri
2432 (string-append
2433 "https://github.com/agordon/fastx_toolkit/releases/download/"
2434 version "/fastx_toolkit-" version ".tar.bz2"))
2435 (sha256
2436 (base32
2437 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2438 (build-system gnu-build-system)
2439 (inputs
2440 `(("libgtextutils" ,libgtextutils)))
2441 (native-inputs
2442 `(("pkg-config" ,pkg-config)))
2443 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2444 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2445 (description
2446 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2447 FASTA/FASTQ files preprocessing.
2448
2449 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2450 containing multiple short-reads sequences. The main processing of such
2451 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2452 is sometimes more productive to preprocess the files before mapping the
2453 sequences to the genome---manipulating the sequences to produce better mapping
2454 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2455 (license license:agpl3+)))
2456
2457 (define-public flexbar
2458 (package
2459 (name "flexbar")
2460 (version "2.5")
2461 (source (origin
2462 (method url-fetch)
2463 (uri
2464 (string-append "mirror://sourceforge/flexbar/"
2465 version "/flexbar_v" version "_src.tgz"))
2466 (sha256
2467 (base32
2468 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2469 (build-system cmake-build-system)
2470 (arguments
2471 `(#:configure-flags (list
2472 (string-append "-DFLEXBAR_BINARY_DIR="
2473 (assoc-ref %outputs "out")
2474 "/bin/"))
2475 #:phases
2476 (alist-replace
2477 'check
2478 (lambda* (#:key outputs #:allow-other-keys)
2479 (setenv "PATH" (string-append
2480 (assoc-ref outputs "out") "/bin:"
2481 (getenv "PATH")))
2482 (chdir "../flexbar_v2.5_src/test")
2483 (zero? (system* "bash" "flexbar_validate.sh")))
2484 (alist-delete 'install %standard-phases))))
2485 (inputs
2486 `(("tbb" ,tbb)
2487 ("zlib" ,zlib)))
2488 (native-inputs
2489 `(("pkg-config" ,pkg-config)
2490 ("seqan" ,seqan)))
2491 (home-page "http://flexbar.sourceforge.net")
2492 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2493 (description
2494 "Flexbar preprocesses high-throughput nucleotide sequencing data
2495 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2496 Moreover, trimming and filtering features are provided. Flexbar increases
2497 read mapping rates and improves genome and transcriptome assemblies. It
2498 supports next-generation sequencing data in fasta/q and csfasta/q format from
2499 Illumina, Roche 454, and the SOLiD platform.")
2500 (license license:gpl3)))
2501
2502 (define-public fraggenescan
2503 (package
2504 (name "fraggenescan")
2505 (version "1.20")
2506 (source
2507 (origin
2508 (method url-fetch)
2509 (uri
2510 (string-append "mirror://sourceforge/fraggenescan/"
2511 "FragGeneScan" version ".tar.gz"))
2512 (sha256
2513 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
2514 (build-system gnu-build-system)
2515 (arguments
2516 `(#:phases
2517 (modify-phases %standard-phases
2518 (delete 'configure)
2519 (add-before 'build 'patch-paths
2520 (lambda* (#:key outputs #:allow-other-keys)
2521 (let* ((out (string-append (assoc-ref outputs "out")))
2522 (share (string-append out "/share/fraggenescan/")))
2523 (substitute* "run_FragGeneScan.pl"
2524 (("system\\(\"rm")
2525 (string-append "system(\"" (which "rm")))
2526 (("system\\(\"mv")
2527 (string-append "system(\"" (which "mv")))
2528 ;; This script and other programs expect the training files
2529 ;; to be in the non-standard location bin/train/XXX. Change
2530 ;; this to be share/fraggenescan/train/XXX instead.
2531 (("^\\$train.file = \\$dir.*")
2532 (string-append "$train_file = \""
2533 share
2534 "train/\".$FGS_train_file;")))
2535 (substitute* "run_hmm.c"
2536 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2537 (string-append " strcpy(train_dir, \"" share "/train/\");")))
2538 (substitute* "post_process.pl"
2539 (("^my \\$dir = substr.*")
2540 (string-append "my $dir = \"" share "\";"))))
2541 #t))
2542 (replace 'build
2543 (lambda _ (and (zero? (system* "make" "clean"))
2544 (zero? (system* "make" "fgs")))))
2545 (replace 'install
2546 (lambda* (#:key outputs #:allow-other-keys)
2547 (let* ((out (string-append (assoc-ref outputs "out")))
2548 (bin (string-append out "/bin/"))
2549 (share (string-append out "/share/fraggenescan/train")))
2550 (install-file "run_FragGeneScan.pl" bin)
2551 (install-file "FragGeneScan" bin)
2552 (install-file "FGS_gff.py" bin)
2553 (install-file "post_process.pl" bin)
2554 (copy-recursively "train" share))))
2555 (delete 'check)
2556 (add-after 'install 'post-install-check
2557 ;; In lieu of 'make check', run one of the examples and check the
2558 ;; output files gets created.
2559 (lambda* (#:key outputs #:allow-other-keys)
2560 (let* ((out (string-append (assoc-ref outputs "out")))
2561 (bin (string-append out "/bin/")))
2562 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
2563 "-genome=./example/NC_000913.fna"
2564 "-out=./test2"
2565 "-complete=1"
2566 "-train=complete"))
2567 (file-exists? "test2.faa")
2568 (file-exists? "test2.ffn")
2569 (file-exists? "test2.gff")
2570 (file-exists? "test2.out"))))))))
2571 (inputs
2572 `(("perl" ,perl)
2573 ("python" ,python-2))) ;not compatible with python 3.
2574 (home-page "https://sourceforge.net/projects/fraggenescan/")
2575 (synopsis "Finds potentially fragmented genes in short reads")
2576 (description
2577 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2578 short and error-prone DNA sequencing reads. It can also be applied to predict
2579 genes in incomplete assemblies or complete genomes.")
2580 ;; GPL3+ according to private correspondense with the authors.
2581 (license license:gpl3+)))
2582
2583 (define-public fxtract
2584 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2585 (package
2586 (name "fxtract")
2587 (version "2.3")
2588 (source
2589 (origin
2590 (method url-fetch)
2591 (uri (string-append
2592 "https://github.com/ctSkennerton/fxtract/archive/"
2593 version ".tar.gz"))
2594 (file-name (string-append "ctstennerton-util-"
2595 (string-take util-commit 7)
2596 "-checkout"))
2597 (sha256
2598 (base32
2599 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2600 (build-system gnu-build-system)
2601 (arguments
2602 `(#:make-flags (list
2603 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2604 "CC=gcc")
2605 #:test-target "fxtract_test"
2606 #:phases
2607 (modify-phases %standard-phases
2608 (delete 'configure)
2609 (add-before 'build 'copy-util
2610 (lambda* (#:key inputs #:allow-other-keys)
2611 (rmdir "util")
2612 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2613 #t))
2614 ;; Do not use make install as this requires additional dependencies.
2615 (replace 'install
2616 (lambda* (#:key outputs #:allow-other-keys)
2617 (let* ((out (assoc-ref outputs "out"))
2618 (bin (string-append out"/bin")))
2619 (install-file "fxtract" bin)
2620 #t))))))
2621 (inputs
2622 `(("pcre" ,pcre)
2623 ("zlib" ,zlib)))
2624 (native-inputs
2625 ;; ctskennerton-util is licensed under GPL2.
2626 `(("ctskennerton-util"
2627 ,(origin
2628 (method git-fetch)
2629 (uri (git-reference
2630 (url "https://github.com/ctSkennerton/util.git")
2631 (commit util-commit)))
2632 (file-name (string-append
2633 "ctstennerton-util-" util-commit "-checkout"))
2634 (sha256
2635 (base32
2636 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2637 (home-page "https://github.com/ctSkennerton/fxtract")
2638 (synopsis "Extract sequences from FASTA and FASTQ files")
2639 (description
2640 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2641 or FASTQ) file given a subsequence. It uses a simple substring search for
2642 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2643 lookups or multi-pattern searching as required. By default fxtract looks in
2644 the sequence of each record but can also be told to look in the header,
2645 comment or quality sections.")
2646 ;; 'util' requires SSE instructions.
2647 (supported-systems '("x86_64-linux"))
2648 (license license:expat))))
2649
2650 (define-public grit
2651 (package
2652 (name "grit")
2653 (version "2.0.2")
2654 (source (origin
2655 (method url-fetch)
2656 (uri (string-append
2657 "https://github.com/nboley/grit/archive/"
2658 version ".tar.gz"))
2659 (file-name (string-append name "-" version ".tar.gz"))
2660 (sha256
2661 (base32
2662 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2663 (build-system python-build-system)
2664 (arguments
2665 `(#:python ,python-2
2666 #:phases
2667 (alist-cons-after
2668 'unpack 'generate-from-cython-sources
2669 (lambda* (#:key inputs outputs #:allow-other-keys)
2670 ;; Delete these C files to force fresh generation from pyx sources.
2671 (delete-file "grit/sparsify_support_fns.c")
2672 (delete-file "grit/call_peaks_support_fns.c")
2673 (substitute* "setup.py"
2674 (("Cython.Setup") "Cython.Build")
2675 ;; Add numpy include path to fix compilation
2676 (("pyx\", \\]")
2677 (string-append "pyx\", ], include_dirs = ['"
2678 (assoc-ref inputs "python-numpy")
2679 "/lib/python2.7/site-packages/numpy/core/include/"
2680 "']"))) #t)
2681 %standard-phases)))
2682 (inputs
2683 `(("python-scipy" ,python2-scipy)
2684 ("python-numpy" ,python2-numpy)
2685 ("python-pysam" ,python2-pysam)
2686 ("python-networkx" ,python2-networkx)))
2687 (native-inputs
2688 `(("python-cython" ,python2-cython)))
2689 (home-page "http://grit-bio.org")
2690 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2691 (description
2692 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2693 full length transcript models. When none of these data sources are available,
2694 GRIT can be run by providing a candidate set of TES or TSS sites. In
2695 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2696 also be run in quantification mode, where it uses a provided GTF file and just
2697 estimates transcript expression.")
2698 (license license:gpl3+)))
2699
2700 (define-public hisat
2701 (package
2702 (name "hisat")
2703 (version "0.1.4")
2704 (source (origin
2705 (method url-fetch)
2706 (uri (string-append
2707 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2708 version "-beta-source.zip"))
2709 (sha256
2710 (base32
2711 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2712 (build-system gnu-build-system)
2713 (arguments
2714 `(#:tests? #f ;no check target
2715 #:make-flags '("allall"
2716 ;; Disable unsupported `popcnt' instructions on
2717 ;; architectures other than x86_64
2718 ,@(if (string-prefix? "x86_64"
2719 (or (%current-target-system)
2720 (%current-system)))
2721 '()
2722 '("POPCNT_CAPABILITY=0")))
2723 #:phases
2724 (alist-cons-after
2725 'unpack 'patch-sources
2726 (lambda _
2727 ;; XXX Cannot use snippet because zip files are not supported
2728 (substitute* "Makefile"
2729 (("^CC = .*$") "CC = gcc")
2730 (("^CPP = .*$") "CPP = g++")
2731 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2732 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2733 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2734 (substitute* '("hisat-build" "hisat-inspect")
2735 (("/usr/bin/env") (which "env"))))
2736 (alist-replace
2737 'install
2738 (lambda* (#:key outputs #:allow-other-keys)
2739 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2740 (for-each (lambda (file)
2741 (install-file file bin))
2742 (find-files
2743 "."
2744 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2745 (alist-delete 'configure %standard-phases)))))
2746 (native-inputs
2747 `(("unzip" ,unzip)))
2748 (inputs
2749 `(("perl" ,perl)
2750 ("python" ,python)
2751 ("zlib" ,zlib)))
2752 ;; Non-portable SSE instructions are used so building fails on platforms
2753 ;; other than x86_64.
2754 (supported-systems '("x86_64-linux"))
2755 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2756 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2757 (description
2758 "HISAT is a fast and sensitive spliced alignment program for mapping
2759 RNA-seq reads. In addition to one global FM index that represents a whole
2760 genome, HISAT uses a large set of small FM indexes that collectively cover the
2761 whole genome. These small indexes (called local indexes) combined with
2762 several alignment strategies enable effective alignment of RNA-seq reads, in
2763 particular, reads spanning multiple exons.")
2764 (license license:gpl3+)))
2765
2766 (define-public hisat2
2767 (package
2768 (name "hisat2")
2769 (version "2.0.5")
2770 (source
2771 (origin
2772 (method url-fetch)
2773 ;; FIXME: a better source URL is
2774 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2775 ;; "/downloads/hisat2-" version "-source.zip")
2776 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2777 ;; but it is currently unavailable.
2778 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2779 (file-name (string-append name "-" version ".tar.gz"))
2780 (sha256
2781 (base32
2782 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2783 (build-system gnu-build-system)
2784 (arguments
2785 `(#:tests? #f ; no check target
2786 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2787 #:modules ((guix build gnu-build-system)
2788 (guix build utils)
2789 (srfi srfi-26))
2790 #:phases
2791 (modify-phases %standard-phases
2792 (add-after 'unpack 'make-deterministic
2793 (lambda _
2794 (substitute* "Makefile"
2795 (("`date`") "0"))
2796 #t))
2797 (delete 'configure)
2798 (replace 'install
2799 (lambda* (#:key outputs #:allow-other-keys)
2800 (let* ((out (assoc-ref outputs "out"))
2801 (bin (string-append out "/bin/"))
2802 (doc (string-append out "/share/doc/hisat2/")))
2803 (for-each
2804 (cut install-file <> bin)
2805 (find-files "."
2806 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2807 (mkdir-p doc)
2808 (install-file "doc/manual.inc.html" doc))
2809 #t)))))
2810 (native-inputs
2811 `(("unzip" ,unzip) ; needed for archive from ftp
2812 ("perl" ,perl)
2813 ("pandoc" ,ghc-pandoc))) ; for documentation
2814 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2815 (synopsis "Graph-based alignment of genomic sequencing reads")
2816 (description "HISAT2 is a fast and sensitive alignment program for mapping
2817 next-generation sequencing reads (both DNA and RNA) to a population of human
2818 genomes (as well as to a single reference genome). In addition to using one
2819 global @dfn{graph FM} (GFM) index that represents a population of human
2820 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2821 the whole genome. These small indexes, combined with several alignment
2822 strategies, enable rapid and accurate alignment of sequencing reads. This new
2823 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2824 ;; HISAT2 contains files from Bowtie2, which is released under
2825 ;; GPLv2 or later. The HISAT2 source files are released under
2826 ;; GPLv3 or later.
2827 (license license:gpl3+)))
2828
2829 (define-public hmmer
2830 (package
2831 (name "hmmer")
2832 (version "3.1b2")
2833 (source (origin
2834 (method url-fetch)
2835 (uri (string-append
2836 "http://eddylab.org/software/hmmer"
2837 (version-prefix version 1) "/"
2838 version "/hmmer-" version ".tar.gz"))
2839 (sha256
2840 (base32
2841 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
2842 (build-system gnu-build-system)
2843 (native-inputs `(("perl" ,perl)))
2844 (home-page "http://hmmer.org/")
2845 (synopsis "Biosequence analysis using profile hidden Markov models")
2846 (description
2847 "HMMER is used for searching sequence databases for homologs of protein
2848 sequences, and for making protein sequence alignments. It implements methods
2849 using probabilistic models called profile hidden Markov models (profile
2850 HMMs).")
2851 (license (list license:gpl3+
2852 ;; The bundled library 'easel' is distributed
2853 ;; under The Janelia Farm Software License.
2854 (license:non-copyleft
2855 "file://easel/LICENSE"
2856 "See easel/LICENSE in the distribution.")))))
2857
2858 (define-public htseq
2859 (package
2860 (name "htseq")
2861 (version "0.6.1")
2862 (source (origin
2863 (method url-fetch)
2864 (uri (string-append
2865 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2866 version ".tar.gz"))
2867 (sha256
2868 (base32
2869 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2870 (build-system python-build-system)
2871 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2872 ;; Numpy needs to be propagated when htseq is used as a Python library.
2873 (propagated-inputs
2874 `(("python-numpy" ,python2-numpy)))
2875 (inputs
2876 `(("python-pysam" ,python2-pysam)))
2877 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2878 (synopsis "Analysing high-throughput sequencing data with Python")
2879 (description
2880 "HTSeq is a Python package that provides infrastructure to process data
2881 from high-throughput sequencing assays.")
2882 (license license:gpl3+)))
2883
2884 (define-public java-htsjdk
2885 (package
2886 (name "java-htsjdk")
2887 (version "1.129")
2888 (source (origin
2889 (method url-fetch)
2890 (uri (string-append
2891 "https://github.com/samtools/htsjdk/archive/"
2892 version ".tar.gz"))
2893 (file-name (string-append name "-" version ".tar.gz"))
2894 (sha256
2895 (base32
2896 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2897 (modules '((guix build utils)))
2898 ;; remove build dependency on git
2899 (snippet '(substitute* "build.xml"
2900 (("failifexecutionfails=\"true\"")
2901 "failifexecutionfails=\"false\"")))))
2902 (build-system ant-build-system)
2903 (arguments
2904 `(#:tests? #f ; test require Internet access
2905 #:make-flags
2906 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2907 "/share/java/htsjdk/"))
2908 #:build-target "all"
2909 #:phases
2910 (modify-phases %standard-phases
2911 ;; The build phase also installs the jars
2912 (delete 'install))))
2913 (home-page "http://samtools.github.io/htsjdk/")
2914 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2915 (description
2916 "HTSJDK is an implementation of a unified Java library for accessing
2917 common file formats, such as SAM and VCF, used for high-throughput
2918 sequencing (HTS) data. There are also an number of useful utilities for
2919 manipulating HTS data.")
2920 (license license:expat)))
2921
2922 (define-public htslib
2923 (package
2924 (name "htslib")
2925 (version "1.3.1")
2926 (source (origin
2927 (method url-fetch)
2928 (uri (string-append
2929 "https://github.com/samtools/htslib/releases/download/"
2930 version "/htslib-" version ".tar.bz2"))
2931 (sha256
2932 (base32
2933 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
2934 (build-system gnu-build-system)
2935 (arguments
2936 `(#:phases
2937 (modify-phases %standard-phases
2938 (add-after
2939 'unpack 'patch-tests
2940 (lambda _
2941 (substitute* "test/test.pl"
2942 (("/bin/bash") (which "bash")))
2943 #t)))))
2944 (inputs
2945 `(("zlib" ,zlib)))
2946 (native-inputs
2947 `(("perl" ,perl)))
2948 (home-page "http://www.htslib.org")
2949 (synopsis "C library for reading/writing high-throughput sequencing data")
2950 (description
2951 "HTSlib is a C library for reading/writing high-throughput sequencing
2952 data. It also provides the bgzip, htsfile, and tabix utilities.")
2953 ;; Files under cram/ are released under the modified BSD license;
2954 ;; the rest is released under the Expat license
2955 (license (list license:expat license:bsd-3))))
2956
2957 (define-public idr
2958 (package
2959 (name "idr")
2960 (version "2.0.0")
2961 (source (origin
2962 (method url-fetch)
2963 (uri (string-append
2964 "https://github.com/nboley/idr/archive/"
2965 version ".tar.gz"))
2966 (file-name (string-append name "-" version ".tar.gz"))
2967 (sha256
2968 (base32
2969 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
2970 (build-system python-build-system)
2971 (arguments
2972 `(#:phases
2973 (modify-phases %standard-phases
2974 (add-after
2975 'install 'wrap-program
2976 (lambda* (#:key inputs outputs #:allow-other-keys)
2977 (let* ((out (assoc-ref outputs "out"))
2978 (python-version (string-take (string-take-right
2979 (assoc-ref inputs "python") 5) 3))
2980 (path (string-join
2981 (map (lambda (name)
2982 (string-append (assoc-ref inputs name)
2983 "/lib/python" python-version
2984 "/site-packages"))
2985 '("python-scipy"
2986 "python-numpy"
2987 "python-matplotlib"))
2988 ":")))
2989 (wrap-program (string-append out "/bin/idr")
2990 `("PYTHONPATH" ":" prefix (,path))))
2991 #t)))))
2992 (inputs
2993 `(("python-scipy" ,python-scipy)
2994 ("python-numpy" ,python-numpy)
2995 ("python-matplotlib" ,python-matplotlib)))
2996 (native-inputs
2997 `(("python-cython" ,python-cython)))
2998 (home-page "https://github.com/nboley/idr")
2999 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3000 (description
3001 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3002 to measure the reproducibility of findings identified from replicate
3003 experiments and provide highly stable thresholds based on reproducibility.")
3004 (license license:gpl3+)))
3005
3006 (define-public jellyfish
3007 (package
3008 (name "jellyfish")
3009 (version "2.2.4")
3010 (source (origin
3011 (method url-fetch)
3012 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3013 "releases/download/v" version
3014 "/jellyfish-" version ".tar.gz"))
3015 (sha256
3016 (base32
3017 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3018 (build-system gnu-build-system)
3019 (outputs '("out" ;for library
3020 "ruby" ;for Ruby bindings
3021 "python")) ;for Python bindings
3022 (arguments
3023 `(#:configure-flags
3024 (list (string-append "--enable-ruby-binding="
3025 (assoc-ref %outputs "ruby"))
3026 (string-append "--enable-python-binding="
3027 (assoc-ref %outputs "python")))
3028 #:phases
3029 (modify-phases %standard-phases
3030 (add-before 'check 'set-SHELL-variable
3031 (lambda _
3032 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3033 ;; to run tests.
3034 (setenv "SHELL" (which "bash"))
3035 #t)))))
3036 (native-inputs
3037 `(("bc" ,bc)
3038 ("time" ,time)
3039 ("ruby" ,ruby)
3040 ("python" ,python-2)))
3041 (synopsis "Tool for fast counting of k-mers in DNA")
3042 (description
3043 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3044 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3045 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3046 is a command-line program that reads FASTA and multi-FASTA files containing
3047 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3048 translated into a human-readable text format using the @code{jellyfish dump}
3049 command, or queried for specific k-mers with @code{jellyfish query}.")
3050 (home-page "http://www.genome.umd.edu/jellyfish.html")
3051 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3052 (supported-systems '("x86_64-linux"))
3053 ;; The combined work is published under the GPLv3 or later. Individual
3054 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3055 (license (list license:gpl3+ license:expat))))
3056
3057 (define-public khmer
3058 (package
3059 (name "khmer")
3060 (version "2.0")
3061 (source
3062 (origin
3063 (method url-fetch)
3064 (uri (pypi-uri "khmer" version))
3065 (sha256
3066 (base32
3067 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3068 (patches (search-patches "khmer-use-libraries.patch"))))
3069 (build-system python-build-system)
3070 (arguments
3071 `(#:phases
3072 (modify-phases %standard-phases
3073 (add-after 'unpack 'set-paths
3074 (lambda* (#:key inputs outputs #:allow-other-keys)
3075 ;; Delete bundled libraries.
3076 (delete-file-recursively "third-party/zlib")
3077 (delete-file-recursively "third-party/bzip2")
3078 ;; Replace bundled seqan.
3079 (let* ((seqan-all "third-party/seqan")
3080 (seqan-include (string-append
3081 seqan-all "/core/include")))
3082 (delete-file-recursively seqan-all)
3083 (copy-recursively (string-append (assoc-ref inputs "seqan")
3084 "/include/seqan")
3085 (string-append seqan-include "/seqan")))
3086 ;; We do not replace the bundled MurmurHash as the canonical
3087 ;; repository for this code 'SMHasher' is unsuitable for
3088 ;; providing a library. See
3089 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3090 #t))
3091 (add-after 'unpack 'set-cc
3092 (lambda _
3093 (setenv "CC" "gcc")
3094 #t))
3095 ;; It is simpler to test after installation.
3096 (delete 'check)
3097 (add-after 'install 'post-install-check
3098 (lambda* (#:key inputs outputs #:allow-other-keys)
3099 (let ((out (assoc-ref outputs "out")))
3100 (setenv "PATH"
3101 (string-append
3102 (getenv "PATH")
3103 ":"
3104 (assoc-ref outputs "out")
3105 "/bin"))
3106 (setenv "PYTHONPATH"
3107 (string-append
3108 (getenv "PYTHONPATH")
3109 ":"
3110 out
3111 "/lib/python"
3112 (string-take (string-take-right
3113 (assoc-ref inputs "python") 5) 3)
3114 "/site-packages"))
3115 (with-directory-excursion "build"
3116 (zero? (system* "nosetests" "khmer" "--attr"
3117 "!known_failing")))))))))
3118 (native-inputs
3119 `(("seqan" ,seqan)
3120 ("python-nose" ,python-nose)))
3121 (inputs
3122 `(("zlib" ,zlib)
3123 ("bzip2" ,bzip2)
3124 ("python-screed" ,python-screed)
3125 ("python-bz2file" ,python-bz2file)))
3126 (home-page "https://khmer.readthedocs.org/")
3127 (synopsis "K-mer counting, filtering and graph traversal library")
3128 (description "The khmer software is a set of command-line tools for
3129 working with DNA shotgun sequencing data from genomes, transcriptomes,
3130 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3131 sometimes better. Khmer can also identify and fix problems with shotgun
3132 data.")
3133 ;; When building on i686, armhf and mips64el, we get the following error:
3134 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3135 (supported-systems '("x86_64-linux"))
3136 (license license:bsd-3)))
3137
3138 (define-public macs
3139 (package
3140 (name "macs")
3141 (version "2.1.0.20151222")
3142 (source (origin
3143 (method url-fetch)
3144 (uri (pypi-uri "MACS2" version))
3145 (sha256
3146 (base32
3147 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3148 (build-system python-build-system)
3149 (arguments
3150 `(#:python ,python-2 ; only compatible with Python 2.7
3151 #:tests? #f)) ; no test target
3152 (inputs
3153 `(("python-numpy" ,python2-numpy)))
3154 (home-page "http://github.com/taoliu/MACS/")
3155 (synopsis "Model based analysis for ChIP-Seq data")
3156 (description
3157 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3158 identifying transcript factor binding sites named Model-based Analysis of
3159 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3160 the significance of enriched ChIP regions and it improves the spatial
3161 resolution of binding sites through combining the information of both
3162 sequencing tag position and orientation.")
3163 (license license:bsd-3)))
3164
3165 (define-public mafft
3166 (package
3167 (name "mafft")
3168 (version "7.305")
3169 (source (origin
3170 (method url-fetch)
3171 (uri (string-append
3172 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3173 "-without-extensions-src.tgz"))
3174 (file-name (string-append name "-" version ".tgz"))
3175 (sha256
3176 (base32
3177 "0ziim7g58n3z8gppsa713f5fxprl60ldj3xck186z0n9dpp06i8r"))))
3178 (build-system gnu-build-system)
3179 (arguments
3180 `(#:tests? #f ; no automated tests, though there are tests in the read me
3181 #:make-flags (let ((out (assoc-ref %outputs "out")))
3182 (list (string-append "PREFIX=" out)
3183 (string-append "BINDIR="
3184 (string-append out "/bin"))))
3185 #:phases
3186 (modify-phases %standard-phases
3187 (add-after 'unpack 'enter-dir
3188 (lambda _ (chdir "core") #t))
3189 (add-after 'enter-dir 'patch-makefile
3190 (lambda _
3191 ;; on advice from the MAFFT authors, there is no need to
3192 ;; distribute mafft-profile, mafft-distance, or
3193 ;; mafft-homologs.rb as they are too "specialised".
3194 (substitute* "Makefile"
3195 ;; remove mafft-homologs.rb from SCRIPTS
3196 (("^SCRIPTS = mafft mafft-homologs.rb")
3197 "SCRIPTS = mafft")
3198 ;; remove mafft-homologs from MANPAGES
3199 (("^MANPAGES = mafft.1 mafft-homologs.1")
3200 "MANPAGES = mafft.1")
3201 ;; remove mafft-distance from PROGS
3202 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3203 "PROGS = dvtditr dndfast7 dndblast sextet5")
3204 ;; remove mafft-profile from PROGS
3205 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3206 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3207 (("^rm -f mafft-profile mafft-profile.exe") "#")
3208 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3209 ;; do not install MAN pages in libexec folder
3210 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3211 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3212 #t))
3213 (add-after 'enter-dir 'patch-paths
3214 (lambda* (#:key inputs #:allow-other-keys)
3215 (substitute* '("pairash.c"
3216 "mafft.tmpl")
3217 (("perl") (which "perl"))
3218 (("([\"`| ])awk" _ prefix)
3219 (string-append prefix (which "awk")))
3220 (("grep") (which "grep")))
3221 #t))
3222 (delete 'configure)
3223 (add-after 'install 'wrap-programs
3224 (lambda* (#:key outputs #:allow-other-keys)
3225 (let* ((out (assoc-ref outputs "out"))
3226 (bin (string-append out "/bin"))
3227 (path (string-append
3228 (assoc-ref %build-inputs "coreutils") "/bin:")))
3229 (for-each (lambda (file)
3230 (wrap-program file
3231 `("PATH" ":" prefix (,path))))
3232 (find-files bin)))
3233 #t)))))
3234 (inputs
3235 `(("perl" ,perl)
3236 ("ruby" ,ruby)
3237 ("gawk" ,gawk)
3238 ("grep" ,grep)
3239 ("coreutils" ,coreutils)))
3240 (home-page "http://mafft.cbrc.jp/alignment/software/")
3241 (synopsis "Multiple sequence alignment program")
3242 (description
3243 "MAFFT offers a range of multiple alignment methods for nucleotide and
3244 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3245 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3246 sequences).")
3247 (license (license:non-copyleft
3248 "http://mafft.cbrc.jp/alignment/software/license.txt"
3249 "BSD-3 with different formatting"))))
3250
3251 (define-public mash
3252 (package
3253 (name "mash")
3254 (version "1.1.1")
3255 (source (origin
3256 (method url-fetch)
3257 (uri (string-append
3258 "https://github.com/marbl/mash/archive/v"
3259 version ".tar.gz"))
3260 (file-name (string-append name "-" version ".tar.gz"))
3261 (sha256
3262 (base32
3263 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3264 (modules '((guix build utils)))
3265 (snippet
3266 ;; Delete bundled kseq.
3267 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3268 '(delete-file "src/mash/kseq.h"))))
3269 (build-system gnu-build-system)
3270 (arguments
3271 `(#:tests? #f ; No tests.
3272 #:configure-flags
3273 (list
3274 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3275 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3276 #:make-flags (list "CC=gcc")
3277 #:phases
3278 (modify-phases %standard-phases
3279 (add-after 'unpack 'fix-includes
3280 (lambda _
3281 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3282 (("^#include \"kseq\\.h\"")
3283 "#include \"htslib/kseq.h\""))
3284 #t))
3285 (add-before 'configure 'autoconf
3286 (lambda _ (zero? (system* "autoconf")))))))
3287 (native-inputs
3288 `(("autoconf" ,autoconf)
3289 ;; Capnproto and htslib are statically embedded in the final
3290 ;; application. Therefore we also list their licenses, below.
3291 ("capnproto" ,capnproto)
3292 ("htslib" ,htslib)))
3293 (inputs
3294 `(("gsl" ,gsl)
3295 ("zlib" ,zlib)))
3296 (supported-systems '("x86_64-linux"))
3297 (home-page "https://mash.readthedocs.io")
3298 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3299 (description "Mash is a fast sequence distance estimator that uses the
3300 MinHash algorithm and is designed to work with genomes and metagenomes in the
3301 form of assemblies or reads.")
3302 (license (list license:bsd-3 ; Mash
3303 license:expat ; HTSlib and capnproto
3304 license:public-domain ; MurmurHash 3
3305 license:cpl1.0)))) ; Open Bloom Filter
3306
3307 (define-public metabat
3308 ;; We package from a git commit because compilation of the released version
3309 ;; fails.
3310 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3311 (package
3312 (name "metabat")
3313 (version (string-append "0.32.4-1." (string-take commit 8)))
3314 (source
3315 (origin
3316 (method git-fetch)
3317 (uri (git-reference
3318 (url "https://bitbucket.org/berkeleylab/metabat.git")
3319 (commit commit)))
3320 (file-name (string-append name "-" version))
3321 (sha256
3322 (base32
3323 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3324 (patches (search-patches "metabat-remove-compilation-date.patch"))))
3325 (build-system gnu-build-system)
3326 (arguments
3327 `(#:phases
3328 (modify-phases %standard-phases
3329 (add-after 'unpack 'fix-includes
3330 (lambda _
3331 (substitute* "src/BamUtils.h"
3332 (("^#include \"bam/bam\\.h\"")
3333 "#include \"samtools/bam.h\"")
3334 (("^#include \"bam/sam\\.h\"")
3335 "#include \"samtools/sam.h\""))
3336 (substitute* "src/KseqReader.h"
3337 (("^#include \"bam/kseq\\.h\"")
3338 "#include \"htslib/kseq.h\""))
3339 #t))
3340 (add-after 'unpack 'fix-scons
3341 (lambda* (#:key inputs #:allow-other-keys)
3342 (substitute* "SConstruct"
3343 (("^htslib_dir = 'samtools'")
3344 (string-append "hitslib_dir = '"
3345 (assoc-ref inputs "htslib")
3346 "'"))
3347 (("^samtools_dir = 'samtools'")
3348 (string-append "samtools_dir = '"
3349 (assoc-ref inputs "htslib")
3350 "'"))
3351 (("^findStaticOrShared\\('bam', hts_lib")
3352 (string-append "findStaticOrShared('bam', '"
3353 (assoc-ref inputs "samtools")
3354 "/lib'"))
3355 ;; Do not distribute README.
3356 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3357 #t))
3358 (delete 'configure)
3359 (replace 'build
3360 (lambda* (#:key inputs outputs #:allow-other-keys)
3361 (mkdir (assoc-ref outputs "out"))
3362 (zero? (system* "scons"
3363 (string-append
3364 "PREFIX="
3365 (assoc-ref outputs "out"))
3366 (string-append
3367 "BOOST_ROOT="
3368 (assoc-ref inputs "boost"))
3369 "install"))))
3370 ;; Check and install are carried out during build phase.
3371 (delete 'check)
3372 (delete 'install))))
3373 (inputs
3374 `(("zlib" ,zlib)
3375 ("perl" ,perl)
3376 ("samtools" ,samtools)
3377 ("htslib" ,htslib)
3378 ("boost" ,boost)))
3379 (native-inputs
3380 `(("scons" ,scons)))
3381 (home-page "https://bitbucket.org/berkeleylab/metabat")
3382 (synopsis
3383 "Reconstruction of single genomes from complex microbial communities")
3384 (description
3385 "Grouping large genomic fragments assembled from shotgun metagenomic
3386 sequences to deconvolute complex microbial communities, or metagenome binning,
3387 enables the study of individual organisms and their interactions. MetaBAT is
3388 an automated metagenome binning software, which integrates empirical
3389 probabilistic distances of genome abundance and tetranucleotide frequency.")
3390 (license (license:non-copyleft "file://license.txt"
3391 "See license.txt in the distribution.")))))
3392
3393 (define-public minced
3394 (package
3395 (name "minced")
3396 (version "0.2.0")
3397 (source (origin
3398 (method url-fetch)
3399 (uri (string-append
3400 "https://github.com/ctSkennerton/minced/archive/"
3401 version ".tar.gz"))
3402 (file-name (string-append name "-" version ".tar.gz"))
3403 (sha256
3404 (base32
3405 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3406 (build-system gnu-build-system)
3407 (arguments
3408 `(#:test-target "test"
3409 #:phases
3410 (modify-phases %standard-phases
3411 (delete 'configure)
3412 (add-before 'check 'fix-test
3413 (lambda _
3414 ;; Fix test for latest version.
3415 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3416 (("minced:0.1.6") "minced:0.2.0"))
3417 #t))
3418 (replace 'install ; No install target.
3419 (lambda* (#:key inputs outputs #:allow-other-keys)
3420 (let* ((out (assoc-ref outputs "out"))
3421 (bin (string-append out "/bin"))
3422 (wrapper (string-append bin "/minced")))
3423 ;; Minced comes with a wrapper script that tries to figure out where
3424 ;; it is located before running the JAR. Since these paths are known
3425 ;; to us, we build our own wrapper to avoid coreutils dependency.
3426 (install-file "minced.jar" bin)
3427 (with-output-to-file wrapper
3428 (lambda _
3429 (display
3430 (string-append
3431 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3432 (assoc-ref inputs "jre") "/bin/java -jar "
3433 bin "/minced.jar \"$@\"\n"))))
3434 (chmod wrapper #o555)))))))
3435 (native-inputs
3436 `(("jdk" ,icedtea "jdk")))
3437 (inputs
3438 `(("bash" ,bash)
3439 ("jre" ,icedtea "out")))
3440 (home-page "https://github.com/ctSkennerton/minced")
3441 (synopsis "Mining CRISPRs in Environmental Datasets")
3442 (description
3443 "MinCED is a program to find Clustered Regularly Interspaced Short
3444 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3445 unassembled metagenomic reads, but is mainly designed for full genomes and
3446 assembled metagenomic sequence.")
3447 (license license:gpl3+)))
3448
3449 (define-public miso
3450 (package
3451 (name "miso")
3452 (version "0.5.3")
3453 (source (origin
3454 (method url-fetch)
3455 (uri (string-append
3456 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3457 version ".tar.gz"))
3458 (sha256
3459 (base32
3460 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3461 (modules '((guix build utils)))
3462 (snippet
3463 '(substitute* "setup.py"
3464 ;; Use setuptools, or else the executables are not
3465 ;; installed.
3466 (("distutils.core") "setuptools")
3467 ;; use "gcc" instead of "cc" for compilation
3468 (("^defines")
3469 "cc.set_executables(
3470 compiler='gcc',
3471 compiler_so='gcc',
3472 linker_exe='gcc',
3473 linker_so='gcc -shared'); defines")))))
3474 (build-system python-build-system)
3475 (arguments
3476 `(#:python ,python-2 ; only Python 2 is supported
3477 #:tests? #f)) ; no "test" target
3478 (inputs
3479 `(("samtools" ,samtools)
3480 ("python-numpy" ,python2-numpy)
3481 ("python-pysam" ,python2-pysam)
3482 ("python-scipy" ,python2-scipy)
3483 ("python-matplotlib" ,python2-matplotlib)))
3484 (native-inputs
3485 `(("python-mock" ,python2-mock) ;for tests
3486 ("python-pytz" ,python2-pytz))) ;for tests
3487 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3488 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3489 (description
3490 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3491 the expression level of alternatively spliced genes from RNA-Seq data, and
3492 identifies differentially regulated isoforms or exons across samples. By
3493 modeling the generative process by which reads are produced from isoforms in
3494 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3495 that a read originated from a particular isoform.")
3496 (license license:gpl2)))
3497
3498 (define-public muscle
3499 (package
3500 (name "muscle")
3501 (version "3.8.1551")
3502 (source (origin
3503 (method url-fetch/tarbomb)
3504 (file-name (string-append name "-" version))
3505 (uri (string-append
3506 "http://www.drive5.com/muscle/muscle_src_"
3507 version ".tar.gz"))
3508 (sha256
3509 (base32
3510 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3511 (build-system gnu-build-system)
3512 (arguments
3513 `(#:make-flags (list "LDLIBS = -lm")
3514 #:phases
3515 (modify-phases %standard-phases
3516 (delete 'configure)
3517 (replace 'check
3518 ;; There are no tests, so just test if it runs.
3519 (lambda _ (zero? (system* "./muscle" "-version"))))
3520 (replace 'install
3521 (lambda* (#:key outputs #:allow-other-keys)
3522 (let* ((out (assoc-ref outputs "out"))
3523 (bin (string-append out "/bin")))
3524 (install-file "muscle" bin)))))))
3525 (home-page "http://www.drive5.com/muscle")
3526 (synopsis "Multiple sequence alignment program")
3527 (description
3528 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3529 program for nucleotide and protein sequences.")
3530 ;; License information found in 'muscle -h' and usage.cpp.
3531 (license license:public-domain)))
3532
3533 (define-public newick-utils
3534 ;; There are no recent releases so we package from git.
3535 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3536 (package
3537 (name "newick-utils")
3538 (version (string-append "1.6-1." (string-take commit 8)))
3539 (source (origin
3540 (method git-fetch)
3541 (uri (git-reference
3542 (url "https://github.com/tjunier/newick_utils.git")
3543 (commit commit)))
3544 (file-name (string-append name "-" version "-checkout"))
3545 (sha256
3546 (base32
3547 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3548 (build-system gnu-build-system)
3549 (arguments
3550 `(#:phases
3551 (modify-phases %standard-phases
3552 (add-after 'unpack 'autoconf
3553 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3554 (inputs
3555 ;; XXX: TODO: Enable Lua and Guile bindings.
3556 ;; https://github.com/tjunier/newick_utils/issues/13
3557 `(("libxml2" ,libxml2)
3558 ("flex" ,flex)
3559 ("bison" ,bison)))
3560 (native-inputs
3561 `(("autoconf" ,autoconf)
3562 ("automake" ,automake)
3563 ("libtool" ,libtool)))
3564 (synopsis "Programs for working with newick format phylogenetic trees")
3565 (description
3566 "Newick-utils is a suite of utilities for processing phylogenetic trees
3567 in Newick format. Functions include re-rooting, extracting subtrees,
3568 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3569 (home-page "https://github.com/tjunier/newick_utils")
3570 (license license:bsd-3))))
3571
3572 (define-public orfm
3573 (package
3574 (name "orfm")
3575 (version "0.6.1")
3576 (source (origin
3577 (method url-fetch)
3578 (uri (string-append
3579 "https://github.com/wwood/OrfM/releases/download/v"
3580 version "/orfm-" version ".tar.gz"))
3581 (sha256
3582 (base32
3583 "19hwp13n82isdvk16710l9m35cmzf0q3fsrcn3r8c5r67biiz39s"))))
3584 (build-system gnu-build-system)
3585 (inputs `(("zlib" ,zlib)))
3586 (native-inputs
3587 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3588 ("ruby-rspec" ,ruby-rspec)
3589 ("ruby" ,ruby)))
3590 (synopsis "Simple and not slow open reading frame (ORF) caller")
3591 (description
3592 "An ORF caller finds stretches of DNA that, when translated, are not
3593 interrupted by stop codons. OrfM finds and prints these ORFs.")
3594 (home-page "https://github.com/wwood/OrfM")
3595 (license license:lgpl3+)))
3596
3597 (define-public python2-pbcore
3598 (package
3599 (name "python2-pbcore")
3600 (version "1.2.10")
3601 (source (origin
3602 (method url-fetch)
3603 (uri (pypi-uri "pbcore" version))
3604 (sha256
3605 (base32
3606 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3607 (build-system python-build-system)
3608 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3609 (propagated-inputs
3610 `(("python-cython" ,python2-cython)
3611 ("python-numpy" ,python2-numpy)
3612 ("python-pysam" ,python2-pysam)
3613 ("python-h5py" ,python2-h5py)))
3614 (native-inputs
3615 `(("python-nose" ,python2-nose)
3616 ("python-sphinx" ,python2-sphinx)
3617 ("python-pyxb" ,python2-pyxb)))
3618 (home-page "http://pacificbiosciences.github.io/pbcore/")
3619 (synopsis "Library for reading and writing PacBio data files")
3620 (description
3621 "The pbcore package provides Python APIs for interacting with PacBio data
3622 files and writing bioinformatics applications.")
3623 (license license:bsd-3)))
3624
3625 (define-public python2-warpedlmm
3626 (package
3627 (name "python2-warpedlmm")
3628 (version "0.21")
3629 (source
3630 (origin
3631 (method url-fetch)
3632 (uri (string-append
3633 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3634 version ".zip"))
3635 (sha256
3636 (base32
3637 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3638 (build-system python-build-system)
3639 (arguments
3640 `(#:python ,python-2)) ; requires Python 2.7
3641 (propagated-inputs
3642 `(("python-scipy" ,python2-scipy)
3643 ("python-numpy" ,python2-numpy)
3644 ("python-matplotlib" ,python2-matplotlib)
3645 ("python-fastlmm" ,python2-fastlmm)
3646 ("python-pandas" ,python2-pandas)
3647 ("python-pysnptools" ,python2-pysnptools)))
3648 (native-inputs
3649 `(("python-mock" ,python2-mock)
3650 ("python-nose" ,python2-nose)
3651 ("unzip" ,unzip)))
3652 (home-page "https://github.com/PMBio/warpedLMM")
3653 (synopsis "Implementation of warped linear mixed models")
3654 (description
3655 "WarpedLMM is a Python implementation of the warped linear mixed model,
3656 which automatically learns an optimal warping function (or transformation) for
3657 the phenotype as it models the data.")
3658 (license license:asl2.0)))
3659
3660 (define-public pbtranscript-tofu
3661 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3662 (package
3663 (name "pbtranscript-tofu")
3664 (version (string-append "2.2.3." (string-take commit 7)))
3665 (source (origin
3666 (method git-fetch)
3667 (uri (git-reference
3668 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3669 (commit commit)))
3670 (file-name (string-append name "-" version "-checkout"))
3671 (sha256
3672 (base32
3673 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3674 (modules '((guix build utils)))
3675 (snippet
3676 '(begin
3677 ;; remove bundled Cython sources
3678 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3679 #t))))
3680 (build-system python-build-system)
3681 (arguments
3682 `(#:python ,python-2
3683 #:phases
3684 (modify-phases %standard-phases
3685 (add-after 'unpack 'enter-directory
3686 (lambda _
3687 (chdir "pbtranscript-tofu/pbtranscript/")
3688 #t))
3689 ;; With setuptools version 18.0 and later this setup.py hack causes
3690 ;; a build error, so we disable it.
3691 (add-after 'enter-directory 'patch-setuppy
3692 (lambda _
3693 (substitute* "setup.py"
3694 (("if 'setuptools.extension' in sys.modules:")
3695 "if False:"))
3696 #t)))))
3697 (inputs
3698 `(("python-numpy" ,python2-numpy)
3699 ("python-bx-python" ,python2-bx-python)
3700 ("python-networkx" ,python2-networkx)
3701 ("python-scipy" ,python2-scipy)
3702 ("python-pbcore" ,python2-pbcore)
3703 ("python-h5py" ,python2-h5py)))
3704 (native-inputs
3705 `(("python-cython" ,python2-cython)
3706 ("python-nose" ,python2-nose)))
3707 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3708 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3709 (description
3710 "pbtranscript-tofu contains scripts to analyze transcriptome data
3711 generated using the PacBio Iso-Seq protocol.")
3712 (license license:bsd-3))))
3713
3714 (define-public prank
3715 (package
3716 (name "prank")
3717 (version "150803")
3718 (source (origin
3719 (method url-fetch)
3720 (uri (string-append
3721 "http://wasabiapp.org/download/prank/prank.source."
3722 version ".tgz"))
3723 (sha256
3724 (base32
3725 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3726 (build-system gnu-build-system)
3727 (arguments
3728 `(#:phases
3729 (modify-phases %standard-phases
3730 (add-after 'unpack 'enter-src-dir
3731 (lambda _
3732 (chdir "src")
3733 #t))
3734 (add-after 'unpack 'remove-m64-flag
3735 ;; Prank will build with the correct 'bit-ness' without this flag
3736 ;; and this allows building on 32-bit machines.
3737 (lambda _ (substitute* "src/Makefile"
3738 (("-m64") ""))
3739 #t))
3740 (delete 'configure)
3741 (replace 'install
3742 (lambda* (#:key outputs #:allow-other-keys)
3743 (let* ((out (assoc-ref outputs "out"))
3744 (bin (string-append out "/bin"))
3745 (man (string-append out "/share/man/man1"))
3746 (path (string-append
3747 (assoc-ref %build-inputs "mafft") "/bin:"
3748 (assoc-ref %build-inputs "exonerate") "/bin:"
3749 (assoc-ref %build-inputs "bppsuite") "/bin")))
3750 (install-file "prank" bin)
3751 (wrap-program (string-append bin "/prank")
3752 `("PATH" ":" prefix (,path)))
3753 (install-file "prank.1" man))
3754 #t)))))
3755 (inputs
3756 `(("mafft" ,mafft)
3757 ("exonerate" ,exonerate)
3758 ("bppsuite" ,bppsuite)))
3759 (home-page "http://wasabiapp.org/software/prank/")
3760 (synopsis "Probabilistic multiple sequence alignment program")
3761 (description
3762 "PRANK is a probabilistic multiple sequence alignment program for DNA,
3763 codon and amino-acid sequences. It is based on a novel algorithm that treats
3764 insertions correctly and avoids over-estimation of the number of deletion
3765 events. In addition, PRANK borrows ideas from maximum likelihood methods used
3766 in phylogenetics and correctly takes into account the evolutionary distances
3767 between sequences. Lastly, PRANK allows for defining a potential structure
3768 for sequences to be aligned and then, simultaneously with the alignment,
3769 predicts the locations of structural units in the sequences.")
3770 (license license:gpl2+)))
3771
3772 (define-public proteinortho
3773 (package
3774 (name "proteinortho")
3775 (version "5.15")
3776 (source
3777 (origin
3778 (method url-fetch)
3779 (uri
3780 (string-append
3781 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
3782 version "_src.tar.gz"))
3783 (sha256
3784 (base32
3785 "05wacnnbx56avpcwhzlcf6b7s77swcpv3qnwz5sh1z54i51gg2ki"))))
3786 (build-system gnu-build-system)
3787 (arguments
3788 `(#:test-target "test"
3789 #:phases
3790 (modify-phases %standard-phases
3791 (replace 'configure
3792 ;; There is no configure script, so we modify the Makefile directly.
3793 (lambda* (#:key outputs #:allow-other-keys)
3794 (substitute* "Makefile"
3795 (("INSTALLDIR=.*")
3796 (string-append
3797 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
3798 #t))
3799 (add-before 'install 'make-install-directory
3800 ;; The install directory is not created during 'make install'.
3801 (lambda* (#:key outputs #:allow-other-keys)
3802 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3803 #t))
3804 (add-after 'install 'wrap-programs
3805 (lambda* (#:key inputs outputs #:allow-other-keys)
3806 (let* ((path (getenv "PATH"))
3807 (out (assoc-ref outputs "out"))
3808 (binary (string-append out "/bin/proteinortho5.pl")))
3809 (wrap-program binary `("PATH" ":" prefix (,path))))
3810 #t)))))
3811 (inputs
3812 `(("perl" ,perl)
3813 ("python" ,python-2)
3814 ("blast+" ,blast+)))
3815 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
3816 (synopsis "Detect orthologous genes across species")
3817 (description
3818 "Proteinortho is a tool to detect orthologous genes across different
3819 species. For doing so, it compares similarities of given gene sequences and
3820 clusters them to find significant groups. The algorithm was designed to handle
3821 large-scale data and can be applied to hundreds of species at once.")
3822 (license license:gpl2+)))
3823
3824 (define-public pyicoteo
3825 (package
3826 (name "pyicoteo")
3827 (version "2.0.7")
3828 (source
3829 (origin
3830 (method url-fetch)
3831 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
3832 "pyicoteo/get/v" version ".tar.bz2"))
3833 (file-name (string-append name "-" version ".tar.bz2"))
3834 (sha256
3835 (base32
3836 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
3837 (build-system python-build-system)
3838 (arguments
3839 `(#:python ,python-2 ; does not work with Python 3
3840 #:tests? #f)) ; there are no tests
3841 (inputs
3842 `(("python2-matplotlib" ,python2-matplotlib)))
3843 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
3844 (synopsis "Analyze high-throughput genetic sequencing data")
3845 (description
3846 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
3847 sequencing data. It works with genomic coordinates. There are currently six
3848 different command-line tools:
3849
3850 @enumerate
3851 @item pyicoregion: for generating exploratory regions automatically;
3852 @item pyicoenrich: for differential enrichment between two conditions;
3853 @item pyicoclip: for calling CLIP-Seq peaks without a control;
3854 @item pyicos: for genomic coordinates manipulation;
3855 @item pyicoller: for peak calling on punctuated ChIP-Seq;
3856 @item pyicount: to count how many reads from N experiment files overlap in a
3857 region file;
3858 @item pyicotrocol: to combine operations from pyicoteo.
3859 @end enumerate\n")
3860 (license license:gpl3+)))
3861
3862 (define-public prodigal
3863 (package
3864 (name "prodigal")
3865 (version "2.6.3")
3866 (source (origin
3867 (method url-fetch)
3868 (uri (string-append
3869 "https://github.com/hyattpd/Prodigal/archive/v"
3870 version ".tar.gz"))
3871 (file-name (string-append name "-" version ".tar.gz"))
3872 (sha256
3873 (base32
3874 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
3875 (build-system gnu-build-system)
3876 (arguments
3877 `(#:tests? #f ;no check target
3878 #:make-flags (list (string-append "INSTALLDIR="
3879 (assoc-ref %outputs "out")
3880 "/bin"))
3881 #:phases
3882 (modify-phases %standard-phases
3883 (delete 'configure))))
3884 (home-page "http://prodigal.ornl.gov")
3885 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
3886 (description
3887 "Prodigal runs smoothly on finished genomes, draft genomes, and
3888 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
3889 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
3890 partial genes, and identifies translation initiation sites.")
3891 (license license:gpl3+)))
3892
3893 (define-public roary
3894 (package
3895 (name "roary")
3896 (version "3.7.0")
3897 (source
3898 (origin
3899 (method url-fetch)
3900 (uri (string-append
3901 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
3902 version ".tar.gz"))
3903 (sha256
3904 (base32
3905 "0x2hpb3nfsc6x2nq1788w0fhqfzc7cn2dp4xwyva9m3k6xlz0m43"))))
3906 (build-system perl-build-system)
3907 (arguments
3908 `(#:phases
3909 (modify-phases %standard-phases
3910 (delete 'configure)
3911 (delete 'build)
3912 (replace 'check
3913 (lambda _
3914 ;; The tests are not run by default, so we run each test file
3915 ;; directly.
3916 (setenv "PATH" (string-append (getcwd) "/bin" ":"
3917 (getenv "PATH")))
3918 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
3919 (getenv "PERL5LIB")))
3920 (zero? (length (filter (lambda (file)
3921 (display file)(display "\n")
3922 (not (zero? (system* "perl" file))))
3923 (find-files "t" ".*\\.t$"))))))
3924 (replace 'install
3925 ;; There is no 'install' target in the Makefile.
3926 (lambda* (#:key outputs #:allow-other-keys)
3927 (let* ((out (assoc-ref outputs "out"))
3928 (bin (string-append out "/bin"))
3929 (perl (string-append out "/lib/perl5/site_perl"))
3930 (roary-plots "contrib/roary_plots"))
3931 (mkdir-p bin)
3932 (mkdir-p perl)
3933 (copy-recursively "bin" bin)
3934 (copy-recursively "lib" perl)
3935 #t)))
3936 (add-after 'install 'wrap-programs
3937 (lambda* (#:key inputs outputs #:allow-other-keys)
3938 (let* ((out (assoc-ref outputs "out"))
3939 (perl5lib (getenv "PERL5LIB"))
3940 (path (getenv "PATH")))
3941 (for-each (lambda (prog)
3942 (let ((binary (string-append out "/" prog)))
3943 (wrap-program binary
3944 `("PERL5LIB" ":" prefix
3945 (,(string-append perl5lib ":" out
3946 "/lib/perl5/site_perl"))))
3947 (wrap-program binary
3948 `("PATH" ":" prefix
3949 (,(string-append path ":" out "/bin"))))))
3950 (find-files "bin" ".*[^R]$"))
3951 (let ((file
3952 (string-append out "/bin/roary-create_pan_genome_plots.R"))
3953 (r-site-lib (getenv "R_LIBS_SITE"))
3954 (coreutils-path
3955 (string-append (assoc-ref inputs "coreutils") "/bin")))
3956 (wrap-program file
3957 `("R_LIBS_SITE" ":" prefix
3958 (,(string-append r-site-lib ":" out "/site-library/"))))
3959 (wrap-program file
3960 `("PATH" ":" prefix
3961 (,(string-append coreutils-path ":" out "/bin"))))))
3962 #t)))))
3963 (native-inputs
3964 `(("perl-env-path" ,perl-env-path)
3965 ("perl-test-files" ,perl-test-files)
3966 ("perl-test-most" ,perl-test-most)
3967 ("perl-test-output" ,perl-test-output)))
3968 (inputs
3969 `(("perl-array-utils" ,perl-array-utils)
3970 ("bioperl" ,bioperl-minimal)
3971 ("perl-exception-class" ,perl-exception-class)
3972 ("perl-file-find-rule" ,perl-file-find-rule)
3973 ("perl-file-grep" ,perl-file-grep)
3974 ("perl-file-slurper" ,perl-file-slurper)
3975 ("perl-file-which" ,perl-file-which)
3976 ("perl-graph" ,perl-graph)
3977 ("perl-graph-readwrite" ,perl-graph-readwrite)
3978 ("perl-log-log4perl" ,perl-log-log4perl)
3979 ("perl-moose" ,perl-moose)
3980 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
3981 ("perl-text-csv" ,perl-text-csv)
3982 ("bedtools" ,bedtools)
3983 ("cd-hit" ,cd-hit)
3984 ("blast+" ,blast+)
3985 ("mcl" ,mcl)
3986 ("parallel" ,parallel)
3987 ("prank" ,prank)
3988 ("mafft" ,mafft)
3989 ("fasttree" ,fasttree)
3990 ("grep" ,grep)
3991 ("sed" ,sed)
3992 ("gawk" ,gawk)
3993 ("r" ,r)
3994 ("r-ggplot2" ,r-ggplot2)
3995 ("coreutils" ,coreutils)))
3996 (home-page "http://sanger-pathogens.github.io/Roary")
3997 (synopsis "High speed stand-alone pan genome pipeline")
3998 (description
3999 "Roary is a high speed stand alone pan genome pipeline, which takes
4000 annotated assemblies in GFF3 format (produced by the Prokka program) and
4001 calculates the pan genome. Using a standard desktop PC, it can analyse
4002 datasets with thousands of samples, without compromising the quality of the
4003 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4004 single processor. Roary is not intended for metagenomics or for comparing
4005 extremely diverse sets of genomes.")
4006 (license license:gpl3)))
4007
4008 (define-public raxml
4009 (package
4010 (name "raxml")
4011 (version "8.2.9")
4012 (source
4013 (origin
4014 (method url-fetch)
4015 (uri
4016 (string-append
4017 "https://github.com/stamatak/standard-RAxML/archive/v"
4018 version ".tar.gz"))
4019 (file-name (string-append name "-" version ".tar.gz"))
4020 (sha256
4021 (base32
4022 "1pv8p2fy67y21a9y4cm7xpvxqjwz2v4201flfjshdq1p8j52rqf7"))))
4023 (build-system gnu-build-system)
4024 (arguments
4025 `(#:tests? #f ; There are no tests.
4026 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4027 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4028 #:phases
4029 (modify-phases %standard-phases
4030 (delete 'configure)
4031 (replace 'install
4032 (lambda* (#:key outputs #:allow-other-keys)
4033 (let* ((out (assoc-ref outputs "out"))
4034 (bin (string-append out "/bin"))
4035 (executable "raxmlHPC-HYBRID"))
4036 (install-file executable bin)
4037 (symlink (string-append bin "/" executable) "raxml"))
4038 #t)))))
4039 (inputs
4040 `(("openmpi" ,openmpi)))
4041 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4042 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4043 (description
4044 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4045 phylogenies.")
4046 (license license:gpl2+)))
4047
4048 (define-public rsem
4049 (package
4050 (name "rsem")
4051 (version "1.2.20")
4052 (source
4053 (origin
4054 (method url-fetch)
4055 (uri
4056 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4057 version ".tar.gz"))
4058 (sha256
4059 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4060 (patches (search-patches "rsem-makefile.patch"))
4061 (modules '((guix build utils)))
4062 (snippet
4063 '(begin
4064 ;; remove bundled copy of boost
4065 (delete-file-recursively "boost")
4066 #t))))
4067 (build-system gnu-build-system)
4068 (arguments
4069 `(#:tests? #f ;no "check" target
4070 #:phases
4071 (modify-phases %standard-phases
4072 ;; No "configure" script.
4073 ;; Do not build bundled samtools library.
4074 (replace 'configure
4075 (lambda _
4076 (substitute* "Makefile"
4077 (("^all : sam/libbam.a") "all : "))
4078 #t))
4079 (replace 'install
4080 (lambda* (#:key outputs #:allow-other-keys)
4081 (let* ((out (string-append (assoc-ref outputs "out")))
4082 (bin (string-append out "/bin/"))
4083 (perl (string-append out "/lib/perl5/site_perl")))
4084 (mkdir-p bin)
4085 (mkdir-p perl)
4086 (for-each (lambda (file)
4087 (copy-file file
4088 (string-append bin (basename file))))
4089 (find-files "." "rsem-.*"))
4090 (copy-file "rsem_perl_utils.pm"
4091 (string-append perl "/rsem_perl_utils.pm")))
4092 #t))
4093 (add-after
4094 'install 'wrap-program
4095 (lambda* (#:key outputs #:allow-other-keys)
4096 (let ((out (assoc-ref outputs "out")))
4097 (for-each (lambda (prog)
4098 (wrap-program (string-append out "/bin/" prog)
4099 `("PERL5LIB" ":" prefix
4100 (,(string-append out "/lib/perl5/site_perl")))))
4101 '("rsem-plot-transcript-wiggles"
4102 "rsem-calculate-expression"
4103 "rsem-generate-ngvector"
4104 "rsem-run-ebseq"
4105 "rsem-prepare-reference")))
4106 #t)))))
4107 (inputs
4108 `(("boost" ,boost)
4109 ("ncurses" ,ncurses)
4110 ("r" ,r)
4111 ("perl" ,perl)
4112 ("samtools" ,samtools-0.1)
4113 ("zlib" ,zlib)))
4114 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4115 (synopsis "Estimate gene expression levels from RNA-Seq data")
4116 (description
4117 "RSEM is a software package for estimating gene and isoform expression
4118 levels from RNA-Seq data. The RSEM package provides a user-friendly
4119 interface, supports threads for parallel computation of the EM algorithm,
4120 single-end and paired-end read data, quality scores, variable-length reads and
4121 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4122 interval estimates for expression levels. For visualization, it can generate
4123 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4124 (license license:gpl3+)))
4125
4126 (define-public rseqc
4127 (package
4128 (name "rseqc")
4129 (version "2.6.1")
4130 (source
4131 (origin
4132 (method url-fetch)
4133 (uri
4134 (string-append "mirror://sourceforge/rseqc/"
4135 "RSeQC-" version ".tar.gz"))
4136 (sha256
4137 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4138 (modules '((guix build utils)))
4139 (snippet
4140 '(begin
4141 ;; remove bundled copy of pysam
4142 (delete-file-recursively "lib/pysam")
4143 (substitute* "setup.py"
4144 ;; remove dependency on outdated "distribute" module
4145 (("^from distribute_setup import use_setuptools") "")
4146 (("^use_setuptools\\(\\)") "")
4147 ;; do not use bundled copy of pysam
4148 (("^have_pysam = False") "have_pysam = True"))))))
4149 (build-system python-build-system)
4150 (arguments `(#:python ,python-2))
4151 (inputs
4152 `(("python-cython" ,python2-cython)
4153 ("python-pysam" ,python2-pysam)
4154 ("python-numpy" ,python2-numpy)
4155 ("zlib" ,zlib)))
4156 (native-inputs
4157 `(("python-nose" ,python2-nose)))
4158 (home-page "http://rseqc.sourceforge.net/")
4159 (synopsis "RNA-seq quality control package")
4160 (description
4161 "RSeQC provides a number of modules that can comprehensively evaluate
4162 high throughput sequence data, especially RNA-seq data. Some basic modules
4163 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4164 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4165 distribution, coverage uniformity, strand specificity, etc.")
4166 (license license:gpl3+)))
4167
4168 (define-public seek
4169 ;; There are no release tarballs. According to the installation
4170 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4171 ;; stable release is identified by this changeset ID.
4172 (let ((changeset "2329130")
4173 (revision "1"))
4174 (package
4175 (name "seek")
4176 (version (string-append "0-" revision "." changeset))
4177 (source (origin
4178 (method hg-fetch)
4179 (uri (hg-reference
4180 (url "https://bitbucket.org/libsleipnir/sleipnir")
4181 (changeset changeset)))
4182 (sha256
4183 (base32
4184 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4185 (build-system gnu-build-system)
4186 (arguments
4187 `(#:modules ((srfi srfi-1)
4188 (guix build gnu-build-system)
4189 (guix build utils))
4190 #:phases
4191 (let ((dirs '("SeekMiner"
4192 "SeekEvaluator"
4193 "SeekPrep"
4194 "Distancer"
4195 "Data2DB"
4196 "PCL2Bin")))
4197 (modify-phases %standard-phases
4198 (add-before 'configure 'bootstrap
4199 (lambda _
4200 (zero? (system* "bash" "gen_auto"))))
4201 (add-after 'build 'build-additional-tools
4202 (lambda* (#:key make-flags #:allow-other-keys)
4203 (every (lambda (dir)
4204 (with-directory-excursion (string-append "tools/" dir)
4205 (zero? (apply system* "make" make-flags))))
4206 dirs)))
4207 (add-after 'install 'install-additional-tools
4208 (lambda* (#:key make-flags #:allow-other-keys)
4209 (fold (lambda (dir result)
4210 (with-directory-excursion (string-append "tools/" dir)
4211 (and result
4212 (zero? (apply system*
4213 `("make" ,@make-flags "install"))))))
4214 #t dirs)))))))
4215 (inputs
4216 `(("gsl" ,gsl)
4217 ("boost" ,boost)
4218 ("libsvm" ,libsvm)
4219 ("readline" ,readline)
4220 ("gengetopt" ,gengetopt)
4221 ("log4cpp" ,log4cpp)))
4222 (native-inputs
4223 `(("autoconf" ,autoconf)
4224 ("automake" ,automake)
4225 ("perl" ,perl)))
4226 (home-page "http://seek.princeton.edu")
4227 (synopsis "Gene co-expression search engine")
4228 (description
4229 "SEEK is a computational gene co-expression search engine. SEEK provides
4230 biologists with a way to navigate the massive human expression compendium that
4231 now contains thousands of expression datasets. SEEK returns a robust ranking
4232 of co-expressed genes in the biological area of interest defined by the user's
4233 query genes. It also prioritizes thousands of expression datasets according
4234 to the user's query of interest.")
4235 (license license:cc-by3.0))))
4236
4237 (define-public samtools
4238 (package
4239 (name "samtools")
4240 (version "1.3.1")
4241 (source
4242 (origin
4243 (method url-fetch)
4244 (uri
4245 (string-append "mirror://sourceforge/samtools/samtools/"
4246 version "/samtools-" version ".tar.bz2"))
4247 (sha256
4248 (base32
4249 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4250 (build-system gnu-build-system)
4251 (arguments
4252 `(#:modules ((ice-9 ftw)
4253 (ice-9 regex)
4254 (guix build gnu-build-system)
4255 (guix build utils))
4256 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4257 #:configure-flags (list "--with-ncurses")
4258 #:phases
4259 (alist-cons-after
4260 'unpack 'patch-tests
4261 (lambda _
4262 (substitute* "test/test.pl"
4263 ;; The test script calls out to /bin/bash
4264 (("/bin/bash") (which "bash")))
4265 #t)
4266 (alist-cons-after
4267 'install 'install-library
4268 (lambda* (#:key outputs #:allow-other-keys)
4269 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4270 (install-file "libbam.a" lib)))
4271 (alist-cons-after
4272 'install 'install-headers
4273 (lambda* (#:key outputs #:allow-other-keys)
4274 (let ((include (string-append (assoc-ref outputs "out")
4275 "/include/samtools/")))
4276 (for-each (lambda (file)
4277 (install-file file include))
4278 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4279 #t))
4280 %standard-phases)))))
4281 (native-inputs `(("pkg-config" ,pkg-config)))
4282 (inputs `(("ncurses" ,ncurses)
4283 ("perl" ,perl)
4284 ("python" ,python)
4285 ("zlib" ,zlib)))
4286 (home-page "http://samtools.sourceforge.net")
4287 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4288 (description
4289 "Samtools implements various utilities for post-processing nucleotide
4290 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4291 variant calling (in conjunction with bcftools), and a simple alignment
4292 viewer.")
4293 (license license:expat)))
4294
4295 (define-public samtools-0.1
4296 ;; This is the most recent version of the 0.1 line of samtools. The input
4297 ;; and output formats differ greatly from that used and produced by samtools
4298 ;; 1.x and is still used in many bioinformatics pipelines.
4299 (package (inherit samtools)
4300 (version "0.1.19")
4301 (source
4302 (origin
4303 (method url-fetch)
4304 (uri
4305 (string-append "mirror://sourceforge/samtools/samtools/"
4306 version "/samtools-" version ".tar.bz2"))
4307 (sha256
4308 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4309 (arguments
4310 `(#:tests? #f ;no "check" target
4311 ,@(substitute-keyword-arguments (package-arguments samtools)
4312 ((#:make-flags flags)
4313 `(cons "LIBCURSES=-lncurses" ,flags))
4314 ((#:phases phases)
4315 `(modify-phases ,phases
4316 (replace 'install
4317 (lambda* (#:key outputs #:allow-other-keys)
4318 (let ((bin (string-append
4319 (assoc-ref outputs "out") "/bin")))
4320 (mkdir-p bin)
4321 (copy-file "samtools"
4322 (string-append bin "/samtools")))))
4323 (delete 'patch-tests)
4324 (delete 'configure))))))))
4325
4326 (define-public mosaik
4327 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4328 (package
4329 (name "mosaik")
4330 (version "2.2.30")
4331 (source (origin
4332 ;; There are no release tarballs nor tags.
4333 (method git-fetch)
4334 (uri (git-reference
4335 (url "https://github.com/wanpinglee/MOSAIK.git")
4336 (commit commit)))
4337 (file-name (string-append name "-" version))
4338 (sha256
4339 (base32
4340 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4341 (build-system gnu-build-system)
4342 (arguments
4343 `(#:tests? #f ; no tests
4344 #:make-flags (list "CC=gcc")
4345 #:phases
4346 (modify-phases %standard-phases
4347 (replace 'configure
4348 (lambda _ (chdir "src") #t))
4349 (replace 'install
4350 (lambda* (#:key outputs #:allow-other-keys)
4351 (let ((bin (string-append (assoc-ref outputs "out")
4352 "/bin")))
4353 (mkdir-p bin)
4354 (copy-recursively "../bin" bin)
4355 #t))))))
4356 (inputs
4357 `(("perl" ,perl)
4358 ("zlib" ,zlib)))
4359 (supported-systems '("x86_64-linux"))
4360 (home-page "https://github.com/wanpinglee/MOSAIK")
4361 (synopsis "Map nucleotide sequence reads to reference genomes")
4362 (description
4363 "MOSAIK is a program for mapping second and third-generation sequencing
4364 reads to a reference genome. MOSAIK can align reads generated by all the
4365 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4366 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4367 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4368 ;; code released into the public domain:
4369 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4370 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4371 (license (list license:gpl2+ license:public-domain)))))
4372
4373 (define-public ngs-sdk
4374 (package
4375 (name "ngs-sdk")
4376 (version "1.2.5")
4377 (source
4378 (origin
4379 (method url-fetch)
4380 (uri
4381 (string-append "https://github.com/ncbi/ngs/archive/"
4382 version ".tar.gz"))
4383 (file-name (string-append name "-" version ".tar.gz"))
4384 (sha256
4385 (base32
4386 "04y1fsmdnb5y86m3gg6f5g9wcscr6r25n7m8mdlcxy0i2q6w6cia"))))
4387 (build-system gnu-build-system)
4388 (arguments
4389 `(#:parallel-build? #f ; not supported
4390 #:tests? #f ; no "check" target
4391 #:phases
4392 (alist-replace
4393 'configure
4394 (lambda* (#:key outputs #:allow-other-keys)
4395 (let ((out (assoc-ref outputs "out")))
4396 ;; The 'configure' script doesn't recognize things like
4397 ;; '--enable-fast-install'.
4398 (zero? (system* "./configure"
4399 (string-append "--build-prefix=" (getcwd) "/build")
4400 (string-append "--prefix=" out)))))
4401 (alist-cons-after
4402 'unpack 'enter-dir
4403 (lambda _ (chdir "ngs-sdk") #t)
4404 %standard-phases))))
4405 (native-inputs `(("perl" ,perl)))
4406 ;; According to the test
4407 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4408 ;; in ngs-sdk/setup/konfigure.perl
4409 (supported-systems '("i686-linux" "x86_64-linux"))
4410 (home-page "https://github.com/ncbi/ngs")
4411 (synopsis "API for accessing Next Generation Sequencing data")
4412 (description
4413 "NGS is a domain-specific API for accessing reads, alignments and pileups
4414 produced from Next Generation Sequencing. The API itself is independent from
4415 any particular back-end implementation, and supports use of multiple back-ends
4416 simultaneously.")
4417 (license license:public-domain)))
4418
4419 (define-public java-ngs
4420 (package (inherit ngs-sdk)
4421 (name "java-ngs")
4422 (arguments
4423 `(,@(substitute-keyword-arguments
4424 `(#:modules ((guix build gnu-build-system)
4425 (guix build utils)
4426 (srfi srfi-1)
4427 (srfi srfi-26))
4428 ,@(package-arguments ngs-sdk))
4429 ((#:phases phases)
4430 `(modify-phases ,phases
4431 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4432 (inputs
4433 `(("jdk" ,icedtea "jdk")
4434 ("ngs-sdk" ,ngs-sdk)))
4435 (synopsis "Java bindings for NGS SDK")))
4436
4437 (define-public ncbi-vdb
4438 (package
4439 (name "ncbi-vdb")
4440 (version "2.7.0")
4441 (source
4442 (origin
4443 (method url-fetch)
4444 (uri
4445 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4446 version ".tar.gz"))
4447 (file-name (string-append name "-" version ".tar.gz"))
4448 (sha256
4449 (base32
4450 "0x1cg1x8vy0yjlkp0snc1533zcjhxqzqsaiwqk598n7vvw37n8lf"))))
4451 (build-system gnu-build-system)
4452 (arguments
4453 `(#:parallel-build? #f ; not supported
4454 #:tests? #f ; no "check" target
4455 #:phases
4456 (alist-replace
4457 'configure
4458 (lambda* (#:key inputs outputs #:allow-other-keys)
4459 (let ((out (assoc-ref outputs "out")))
4460 ;; Override include path for libmagic
4461 (substitute* "setup/package.prl"
4462 (("name => 'magic', Include => '/usr/include'")
4463 (string-append "name=> 'magic', Include => '"
4464 (assoc-ref inputs "libmagic")
4465 "/include" "'")))
4466
4467 ;; Install kdf5 library (needed by sra-tools)
4468 (substitute* "build/Makefile.install"
4469 (("LIBRARIES_TO_INSTALL =")
4470 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4471
4472 (substitute* "build/Makefile.env"
4473 (("CFLAGS =" prefix)
4474 (string-append prefix "-msse2 ")))
4475
4476 ;; The 'configure' script doesn't recognize things like
4477 ;; '--enable-fast-install'.
4478 (zero? (system*
4479 "./configure"
4480 (string-append "--build-prefix=" (getcwd) "/build")
4481 (string-append "--prefix=" (assoc-ref outputs "out"))
4482 (string-append "--debug")
4483 (string-append "--with-xml2-prefix="
4484 (assoc-ref inputs "libxml2"))
4485 (string-append "--with-ngs-sdk-prefix="
4486 (assoc-ref inputs "ngs-sdk"))
4487 (string-append "--with-ngs-java-prefix="
4488 (assoc-ref inputs "java-ngs"))
4489 (string-append "--with-hdf5-prefix="
4490 (assoc-ref inputs "hdf5"))))))
4491 (alist-cons-after
4492 'install 'install-interfaces
4493 (lambda* (#:key outputs #:allow-other-keys)
4494 ;; Install interface libraries. On i686 the interface libraries
4495 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4496 ;; architecture name ("i386") instead of the target system prefix
4497 ;; ("i686").
4498 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4499 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4500 ,(system->linux-architecture
4501 (or (%current-target-system)
4502 (%current-system)))
4503 "/rel/ilib")
4504 (string-append (assoc-ref outputs "out")
4505 "/ilib"))
4506 ;; Install interface headers
4507 (copy-recursively "interfaces"
4508 (string-append (assoc-ref outputs "out")
4509 "/include")))
4510 %standard-phases))))
4511 (inputs
4512 `(("libxml2" ,libxml2)
4513 ("ngs-sdk" ,ngs-sdk)
4514 ("java-ngs" ,java-ngs)
4515 ("libmagic" ,file)
4516 ("hdf5" ,hdf5)))
4517 (native-inputs `(("perl" ,perl)))
4518 ;; NCBI-VDB requires SSE capability.
4519 (supported-systems '("i686-linux" "x86_64-linux"))
4520 (home-page "https://github.com/ncbi/ncbi-vdb")
4521 (synopsis "Database engine for genetic information")
4522 (description
4523 "The NCBI-VDB library implements a highly compressed columnar data
4524 warehousing engine that is most often used to store genetic information.
4525 Databases are stored in a portable image within the file system, and can be
4526 accessed/downloaded on demand across HTTP.")
4527 (license license:public-domain)))
4528
4529 (define-public plink
4530 (package
4531 (name "plink")
4532 (version "1.07")
4533 (source
4534 (origin
4535 (method url-fetch)
4536 (uri (string-append
4537 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4538 version "-src.zip"))
4539 (sha256
4540 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4541 (patches (search-patches "plink-1.07-unclobber-i.patch"
4542 "plink-endian-detection.patch"))))
4543 (build-system gnu-build-system)
4544 (arguments
4545 '(#:tests? #f ;no "check" target
4546 #:make-flags (list (string-append "LIB_LAPACK="
4547 (assoc-ref %build-inputs "lapack")
4548 "/lib/liblapack.so")
4549 "WITH_LAPACK=1"
4550 "FORCE_DYNAMIC=1"
4551 ;; disable phoning home
4552 "WITH_WEBCHECK=")
4553 #:phases
4554 (modify-phases %standard-phases
4555 ;; no "configure" script
4556 (delete 'configure)
4557 (replace 'install
4558 (lambda* (#:key outputs #:allow-other-keys)
4559 (let ((bin (string-append (assoc-ref outputs "out")
4560 "/bin/")))
4561 (install-file "plink" bin)
4562 #t))))))
4563 (inputs
4564 `(("zlib" ,zlib)
4565 ("lapack" ,lapack)))
4566 (native-inputs
4567 `(("unzip" ,unzip)))
4568 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4569 (synopsis "Whole genome association analysis toolset")
4570 (description
4571 "PLINK is a whole genome association analysis toolset, designed to
4572 perform a range of basic, large-scale analyses in a computationally efficient
4573 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4574 so there is no support for steps prior to this (e.g. study design and
4575 planning, generating genotype or CNV calls from raw data). Through
4576 integration with gPLINK and Haploview, there is some support for the
4577 subsequent visualization, annotation and storage of results.")
4578 ;; Code is released under GPLv2, except for fisher.h, which is under
4579 ;; LGPLv2.1+
4580 (license (list license:gpl2 license:lgpl2.1+))))
4581
4582 (define-public smithlab-cpp
4583 (let ((revision "1")
4584 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4585 (package
4586 (name "smithlab-cpp")
4587 (version (string-append "0." revision "." (string-take commit 7)))
4588 (source (origin
4589 (method git-fetch)
4590 (uri (git-reference
4591 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4592 (commit commit)))
4593 (file-name (string-append name "-" version "-checkout"))
4594 (sha256
4595 (base32
4596 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4597 (build-system gnu-build-system)
4598 (arguments
4599 `(#:modules ((guix build gnu-build-system)
4600 (guix build utils)
4601 (srfi srfi-26))
4602 #:tests? #f ;no "check" target
4603 #:phases
4604 (modify-phases %standard-phases
4605 (add-after 'unpack 'use-samtools-headers
4606 (lambda _
4607 (substitute* '("SAM.cpp"
4608 "SAM.hpp")
4609 (("sam.h") "samtools/sam.h"))
4610 #t))
4611 (replace 'install
4612 (lambda* (#:key outputs #:allow-other-keys)
4613 (let* ((out (assoc-ref outputs "out"))
4614 (lib (string-append out "/lib"))
4615 (include (string-append out "/include/smithlab-cpp")))
4616 (mkdir-p lib)
4617 (mkdir-p include)
4618 (for-each (cut install-file <> lib)
4619 (find-files "." "\\.o$"))
4620 (for-each (cut install-file <> include)
4621 (find-files "." "\\.hpp$")))
4622 #t))
4623 (delete 'configure))))
4624 (inputs
4625 `(("samtools" ,samtools-0.1)
4626 ("zlib" ,zlib)))
4627 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4628 (synopsis "C++ helper library for functions used in Smith lab projects")
4629 (description
4630 "Smithlab CPP is a C++ library that includes functions used in many of
4631 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4632 structures, classes for genomic regions, mapped sequencing reads, etc.")
4633 (license license:gpl3+))))
4634
4635 (define-public preseq
4636 (package
4637 (name "preseq")
4638 (version "2.0")
4639 (source (origin
4640 (method url-fetch)
4641 (uri (string-append "https://github.com/smithlabcode/"
4642 "preseq/archive/v" version ".tar.gz"))
4643 (file-name (string-append name "-" version ".tar.gz"))
4644 (sha256
4645 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4646 (modules '((guix build utils)))
4647 (snippet
4648 ;; Remove bundled samtools.
4649 '(delete-file-recursively "samtools"))))
4650 (build-system gnu-build-system)
4651 (arguments
4652 `(#:tests? #f ;no "check" target
4653 #:phases
4654 (modify-phases %standard-phases
4655 (delete 'configure))
4656 #:make-flags
4657 (list (string-append "PREFIX="
4658 (assoc-ref %outputs "out"))
4659 (string-append "LIBBAM="
4660 (assoc-ref %build-inputs "samtools")
4661 "/lib/libbam.a")
4662 (string-append "SMITHLAB_CPP="
4663 (assoc-ref %build-inputs "smithlab-cpp")
4664 "/lib")
4665 "PROGS=preseq"
4666 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4667 (inputs
4668 `(("gsl" ,gsl)
4669 ("samtools" ,samtools-0.1)
4670 ("smithlab-cpp" ,smithlab-cpp)
4671 ("zlib" ,zlib)))
4672 (home-page "http://smithlabresearch.org/software/preseq/")
4673 (synopsis "Program for analyzing library complexity")
4674 (description
4675 "The preseq package is aimed at predicting and estimating the complexity
4676 of a genomic sequencing library, equivalent to predicting and estimating the
4677 number of redundant reads from a given sequencing depth and how many will be
4678 expected from additional sequencing using an initial sequencing experiment.
4679 The estimates can then be used to examine the utility of further sequencing,
4680 optimize the sequencing depth, or to screen multiple libraries to avoid low
4681 complexity samples.")
4682 (license license:gpl3+)))
4683
4684 (define-public python-screed
4685 (package
4686 (name "python-screed")
4687 (version "0.9")
4688 (source
4689 (origin
4690 (method url-fetch)
4691 (uri (pypi-uri "screed" version))
4692 (sha256
4693 (base32
4694 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4695 (build-system python-build-system)
4696 (arguments
4697 `(#:phases
4698 (modify-phases %standard-phases
4699 (replace 'check
4700 (lambda _
4701 (setenv "PYTHONPATH"
4702 (string-append (getenv "PYTHONPATH") ":."))
4703 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4704 (native-inputs
4705 `(("python-nose" ,python-nose)))
4706 (inputs
4707 `(("python-bz2file" ,python-bz2file)))
4708 (home-page "http://github.com/dib-lab/screed/")
4709 (synopsis "Short read sequence database utilities")
4710 (description "Screed parses FASTA and FASTQ files and generates databases.
4711 Values such as sequence name, sequence description, sequence quality and the
4712 sequence itself can be retrieved from these databases.")
4713 (license license:bsd-3)))
4714
4715 (define-public python2-screed
4716 (package-with-python2 python-screed))
4717
4718 (define-public sra-tools
4719 (package
4720 (name "sra-tools")
4721 (version "2.7.0")
4722 (source
4723 (origin
4724 (method url-fetch)
4725 (uri
4726 (string-append "https://github.com/ncbi/sra-tools/archive/"
4727 version ".tar.gz"))
4728 (file-name (string-append name "-" version ".tar.gz"))
4729 (sha256
4730 (base32
4731 "13paw7bq6y47d2pl0ac5gpgcqp1xsy1g7v1fwysm3hr8lb2dck17"))))
4732 (build-system gnu-build-system)
4733 (arguments
4734 `(#:parallel-build? #f ; not supported
4735 #:tests? #f ; no "check" target
4736 #:make-flags
4737 (list (string-append "VDB_LIBDIR="
4738 (assoc-ref %build-inputs "ncbi-vdb")
4739 ,(if (string-prefix? "x86_64"
4740 (or (%current-target-system)
4741 (%current-system)))
4742 "/lib64"
4743 "/lib32")))
4744 #:phases
4745 (alist-replace
4746 'configure
4747 (lambda* (#:key inputs outputs #:allow-other-keys)
4748 ;; The build system expects a directory containing the sources and
4749 ;; raw build output of ncbi-vdb, including files that are not
4750 ;; installed. Since we are building against an installed version of
4751 ;; ncbi-vdb, the following modifications are needed.
4752 (substitute* "setup/konfigure.perl"
4753 ;; Make the configure script look for the "ilib" directory of
4754 ;; "ncbi-vdb" without first checking for the existence of a
4755 ;; matching library in its "lib" directory.
4756 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
4757 "my $f = File::Spec->catdir($ilibdir, $ilib);")
4758 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
4759 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
4760 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
4761
4762 ;; Dynamic linking
4763 (substitute* "tools/copycat/Makefile"
4764 (("smagic-static") "lmagic"))
4765
4766 ;; The 'configure' script doesn't recognize things like
4767 ;; '--enable-fast-install'.
4768 (zero? (system*
4769 "./configure"
4770 (string-append "--build-prefix=" (getcwd) "/build")
4771 (string-append "--prefix=" (assoc-ref outputs "out"))
4772 (string-append "--debug")
4773 (string-append "--with-fuse-prefix="
4774 (assoc-ref inputs "fuse"))
4775 (string-append "--with-magic-prefix="
4776 (assoc-ref inputs "libmagic"))
4777 ;; TODO: building with libxml2 fails with linker errors
4778 ;; (string-append "--with-xml2-prefix="
4779 ;; (assoc-ref inputs "libxml2"))
4780 (string-append "--with-ncbi-vdb-sources="
4781 (assoc-ref inputs "ncbi-vdb"))
4782 (string-append "--with-ncbi-vdb-build="
4783 (assoc-ref inputs "ncbi-vdb"))
4784 (string-append "--with-ngs-sdk-prefix="
4785 (assoc-ref inputs "ngs-sdk"))
4786 (string-append "--with-hdf5-prefix="
4787 (assoc-ref inputs "hdf5")))))
4788 %standard-phases)))
4789 (native-inputs `(("perl" ,perl)))
4790 (inputs
4791 `(("ngs-sdk" ,ngs-sdk)
4792 ("ncbi-vdb" ,ncbi-vdb)
4793 ("libmagic" ,file)
4794 ("fuse" ,fuse)
4795 ("hdf5" ,hdf5)
4796 ("zlib" ,zlib)))
4797 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
4798 (synopsis "Tools and libraries for reading and writing sequencing data")
4799 (description
4800 "The SRA Toolkit from NCBI is a collection of tools and libraries for
4801 reading of sequencing files from the Sequence Read Archive (SRA) database and
4802 writing files into the .sra format.")
4803 (license license:public-domain)))
4804
4805 (define-public seqan
4806 (package
4807 (name "seqan")
4808 (version "1.4.2")
4809 (source (origin
4810 (method url-fetch)
4811 (uri (string-append "http://packages.seqan.de/seqan-library/"
4812 "seqan-library-" version ".tar.bz2"))
4813 (sha256
4814 (base32
4815 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
4816 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
4817 ;; makes sense to split the outputs.
4818 (outputs '("out" "doc"))
4819 (build-system trivial-build-system)
4820 (arguments
4821 `(#:modules ((guix build utils))
4822 #:builder
4823 (begin
4824 (use-modules (guix build utils))
4825 (let ((tar (assoc-ref %build-inputs "tar"))
4826 (bzip (assoc-ref %build-inputs "bzip2"))
4827 (out (assoc-ref %outputs "out"))
4828 (doc (assoc-ref %outputs "doc")))
4829 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
4830 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
4831 (chdir (string-append "seqan-library-" ,version))
4832 (copy-recursively "include" (string-append out "/include"))
4833 (copy-recursively "share" (string-append doc "/share"))))))
4834 (native-inputs
4835 `(("source" ,source)
4836 ("tar" ,tar)
4837 ("bzip2" ,bzip2)))
4838 (home-page "http://www.seqan.de")
4839 (synopsis "Library for nucleotide sequence analysis")
4840 (description
4841 "SeqAn is a C++ library of efficient algorithms and data structures for
4842 the analysis of sequences with the focus on biological data. It contains
4843 algorithms and data structures for string representation and their
4844 manipulation, online and indexed string search, efficient I/O of
4845 bioinformatics file formats, sequence alignment, and more.")
4846 (license license:bsd-3)))
4847
4848 (define-public seqmagick
4849 (package
4850 (name "seqmagick")
4851 (version "0.6.1")
4852 (source
4853 (origin
4854 (method url-fetch)
4855 (uri (string-append
4856 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
4857 version ".tar.gz"))
4858 (sha256
4859 (base32
4860 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
4861 (build-system python-build-system)
4862 (arguments
4863 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
4864 `(#:python ,python-2
4865 #:phases
4866 (modify-phases %standard-phases
4867 ;; Current test in setup.py does not work as of 0.6.1,
4868 ;; so use nose to run tests instead for now. See
4869 ;; https://github.com/fhcrc/seqmagick/issues/55
4870 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
4871 (inputs
4872 ;; biopython-1.66 is required due to
4873 ;; https://github.com/fhcrc/seqmagick/issues/59
4874 ;; When that issue is resolved the 'python2-biopython-1.66' package
4875 ;; should be removed.
4876 `(("python-biopython" ,python2-biopython-1.66)))
4877 (native-inputs
4878 `(("python-nose" ,python2-nose)))
4879 (home-page "http://github.com/fhcrc/seqmagick")
4880 (synopsis "Tools for converting and modifying sequence files")
4881 (description
4882 "Bioinformaticians often have to convert sequence files between formats
4883 and do little manipulations on them, and it's not worth writing scripts for
4884 that. Seqmagick is a utility to expose the file format conversion in
4885 BioPython in a convenient way. Instead of having a big mess of scripts, there
4886 is one that takes arguments.")
4887 (license license:gpl3)))
4888
4889 (define-public seqtk
4890 (package
4891 (name "seqtk")
4892 (version "1.2")
4893 (source (origin
4894 (method url-fetch)
4895 (uri (string-append
4896 "https://github.com/lh3/seqtk/archive/v"
4897 version ".tar.gz"))
4898 (file-name (string-append name "-" version ".tar.gz"))
4899 (sha256
4900 (base32
4901 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
4902 (modules '((guix build utils)))
4903 (snippet
4904 '(begin
4905 ;; Remove extraneous header files, as is done in the seqtk
4906 ;; master branch.
4907 (for-each (lambda (file) (delete-file file))
4908 (list "ksort.h" "kstring.h" "kvec.h"))
4909 #t))))
4910 (build-system gnu-build-system)
4911 (arguments
4912 `(#:phases
4913 (modify-phases %standard-phases
4914 (delete 'configure)
4915 (replace 'check
4916 ;; There are no tests, so we just run a sanity check.
4917 (lambda _ (zero? (system* "./seqtk" "seq"))))
4918 (replace 'install
4919 (lambda* (#:key outputs #:allow-other-keys)
4920 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4921 (install-file "seqtk" bin)))))))
4922 (inputs
4923 `(("zlib" ,zlib)))
4924 (home-page "https://github.com/lh3/seqtk")
4925 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
4926 (description
4927 "Seqtk is a fast and lightweight tool for processing sequences in the
4928 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
4929 optionally compressed by gzip.")
4930 (license license:expat)))
4931
4932 (define-public snap-aligner
4933 (package
4934 (name "snap-aligner")
4935 (version "1.0beta.18")
4936 (source (origin
4937 (method url-fetch)
4938 (uri (string-append
4939 "https://github.com/amplab/snap/archive/v"
4940 version ".tar.gz"))
4941 (file-name (string-append name "-" version ".tar.gz"))
4942 (sha256
4943 (base32
4944 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
4945 (build-system gnu-build-system)
4946 (arguments
4947 '(#:phases
4948 (modify-phases %standard-phases
4949 (delete 'configure)
4950 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
4951 (replace 'install
4952 (lambda* (#:key outputs #:allow-other-keys)
4953 (let* ((out (assoc-ref outputs "out"))
4954 (bin (string-append out "/bin")))
4955 (install-file "snap-aligner" bin)
4956 (install-file "SNAPCommand" bin)
4957 #t))))))
4958 (native-inputs
4959 `(("zlib" ,zlib)))
4960 (home-page "http://snap.cs.berkeley.edu/")
4961 (synopsis "Short read DNA sequence aligner")
4962 (description
4963 "SNAP is a fast and accurate aligner for short DNA reads. It is
4964 optimized for modern read lengths of 100 bases or higher, and takes advantage
4965 of these reads to align data quickly through a hash-based indexing scheme.")
4966 ;; 32-bit systems are not supported by the unpatched code.
4967 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
4968 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
4969 ;; systems without a lot of memory cannot make good use of this program.
4970 (supported-systems '("x86_64-linux"))
4971 (license license:asl2.0)))
4972
4973 (define-public sortmerna
4974 (package
4975 (name "sortmerna")
4976 (version "2.1b")
4977 (source
4978 (origin
4979 (method url-fetch)
4980 (uri (string-append
4981 "https://github.com/biocore/sortmerna/archive/"
4982 version ".tar.gz"))
4983 (file-name (string-append name "-" version ".tar.gz"))
4984 (sha256
4985 (base32
4986 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
4987 (build-system gnu-build-system)
4988 (outputs '("out" ;for binaries
4989 "db")) ;for sequence databases
4990 (arguments
4991 `(#:phases
4992 (modify-phases %standard-phases
4993 (replace 'install
4994 (lambda* (#:key outputs #:allow-other-keys)
4995 (let* ((out (assoc-ref outputs "out"))
4996 (bin (string-append out "/bin"))
4997 (db (assoc-ref outputs "db"))
4998 (share
4999 (string-append db "/share/sortmerna/rRNA_databases")))
5000 (install-file "sortmerna" bin)
5001 (install-file "indexdb_rna" bin)
5002 (for-each (lambda (file)
5003 (install-file file share))
5004 (find-files "rRNA_databases" ".*fasta"))
5005 #t))))))
5006 (inputs
5007 `(("zlib" ,zlib)))
5008 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5009 (synopsis "Biological sequence analysis tool for NGS reads")
5010 (description
5011 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5012 and operational taxonomic unit (OTU) picking of next generation
5013 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5014 allows for fast and sensitive analyses of nucleotide sequences. The main
5015 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5016 (license license:lgpl3)))
5017
5018 (define-public star
5019 (package
5020 (name "star")
5021 (version "2.5.2b")
5022 (source (origin
5023 (method url-fetch)
5024 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5025 version ".tar.gz"))
5026 (file-name (string-append name "-" version ".tar.gz"))
5027 (sha256
5028 (base32
5029 "1na6np880r1zaamiy00hy8bid5anpy0kgf63587v2yl080krk2zq"))
5030 (modules '((guix build utils)))
5031 (snippet
5032 '(begin
5033 (substitute* "source/Makefile"
5034 (("/bin/rm") "rm"))
5035 ;; Remove pre-built binaries and bundled htslib sources.
5036 (delete-file-recursively "bin/MacOSX_x86_64")
5037 (delete-file-recursively "bin/Linux_x86_64")
5038 (delete-file-recursively "bin/Linux_x86_64_static")
5039 (delete-file-recursively "source/htslib")
5040 #t))))
5041 (build-system gnu-build-system)
5042 (arguments
5043 '(#:tests? #f ;no check target
5044 #:make-flags '("STAR")
5045 #:phases
5046 (modify-phases %standard-phases
5047 (add-after 'unpack 'enter-source-dir
5048 (lambda _ (chdir "source") #t))
5049 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5050 (lambda _
5051 (substitute* "Makefile"
5052 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5053 _ prefix) prefix))
5054 (substitute* '("BAMfunctions.cpp"
5055 "signalFromBAM.h"
5056 "bam_cat.h"
5057 "bam_cat.c"
5058 "STAR.cpp"
5059 "bamRemoveDuplicates.cpp")
5060 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5061 (string-append "#include <" header ">")))
5062 (substitute* "IncludeDefine.h"
5063 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5064 (string-append "<" header ">")))
5065 #t))
5066 (replace 'install
5067 (lambda* (#:key outputs #:allow-other-keys)
5068 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5069 (install-file "STAR" bin))
5070 #t))
5071 (delete 'configure))))
5072 (native-inputs
5073 `(("vim" ,vim))) ; for xxd
5074 (inputs
5075 `(("htslib" ,htslib)
5076 ("zlib" ,zlib)))
5077 (home-page "https://github.com/alexdobin/STAR")
5078 (synopsis "Universal RNA-seq aligner")
5079 (description
5080 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5081 based on a previously undescribed RNA-seq alignment algorithm that uses
5082 sequential maximum mappable seed search in uncompressed suffix arrays followed
5083 by seed clustering and stitching procedure. In addition to unbiased de novo
5084 detection of canonical junctions, STAR can discover non-canonical splices and
5085 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5086 sequences.")
5087 ;; Only 64-bit systems are supported according to the README.
5088 (supported-systems '("x86_64-linux" "mips64el-linux"))
5089 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5090 (license license:gpl3+)))
5091
5092 (define-public subread
5093 (package
5094 (name "subread")
5095 (version "1.5.1")
5096 (source (origin
5097 (method url-fetch)
5098 (uri (string-append "mirror://sourceforge/subread/subread-"
5099 version "/subread-" version "-source.tar.gz"))
5100 (sha256
5101 (base32
5102 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5103 (build-system gnu-build-system)
5104 (arguments
5105 `(#:tests? #f ;no "check" target
5106 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5107 ;; optimizations by default, so we override these flags such that x86_64
5108 ;; flags are only added when the build target is an x86_64 system.
5109 #:make-flags
5110 (list (let ((system ,(or (%current-target-system)
5111 (%current-system)))
5112 (flags '("-ggdb" "-fomit-frame-pointer"
5113 "-ffast-math" "-funroll-loops"
5114 "-fmessage-length=0"
5115 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5116 "-DMAKE_STANDALONE"
5117 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5118 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5119 (if (string-prefix? "x86_64" system)
5120 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5121 (string-append "CCFLAGS=" (string-join flags))))
5122 "-f" "Makefile.Linux"
5123 "CC=gcc ${CCFLAGS}")
5124 #:phases
5125 (alist-cons-after
5126 'unpack 'enter-dir
5127 (lambda _ (chdir "src") #t)
5128 (alist-replace
5129 'install
5130 (lambda* (#:key outputs #:allow-other-keys)
5131 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5132 (mkdir-p bin)
5133 (copy-recursively "../bin" bin)))
5134 ;; no "configure" script
5135 (alist-delete 'configure %standard-phases)))))
5136 (inputs `(("zlib" ,zlib)))
5137 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5138 (synopsis "Tool kit for processing next-gen sequencing data")
5139 (description
5140 "The subread package contains the following tools: subread aligner, a
5141 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5142 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5143 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5144 against local background noises.")
5145 (license license:gpl3+)))
5146
5147 (define-public stringtie
5148 (package
5149 (name "stringtie")
5150 (version "1.2.1")
5151 (source (origin
5152 (method url-fetch)
5153 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5154 "stringtie-" version ".tar.gz"))
5155 (sha256
5156 (base32
5157 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5158 (modules '((guix build utils)))
5159 (snippet
5160 '(begin
5161 (delete-file-recursively "samtools-0.1.18")
5162 #t))))
5163 (build-system gnu-build-system)
5164 (arguments
5165 `(#:tests? #f ;no test suite
5166 #:phases
5167 (modify-phases %standard-phases
5168 ;; no configure script
5169 (delete 'configure)
5170 (add-before 'build 'use-system-samtools
5171 (lambda _
5172 (substitute* "Makefile"
5173 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5174 "stringtie: "))
5175 (substitute* '("gclib/GBam.h"
5176 "gclib/GBam.cpp")
5177 (("#include \"(bam|sam|kstring).h\"" _ header)
5178 (string-append "#include <samtools/" header ".h>")))
5179 #t))
5180 (replace 'install
5181 (lambda* (#:key outputs #:allow-other-keys)
5182 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5183 (install-file "stringtie" bin)
5184 #t))))))
5185 (inputs
5186 `(("samtools" ,samtools-0.1)
5187 ("zlib" ,zlib)))
5188 (home-page "http://ccb.jhu.edu/software/stringtie/")
5189 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5190 (description
5191 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5192 alignments into potential transcripts. It uses a novel network flow algorithm
5193 as well as an optional de novo assembly step to assemble and quantitate
5194 full-length transcripts representing multiple splice variants for each gene
5195 locus. Its input can include not only the alignments of raw reads used by
5196 other transcript assemblers, but also alignments of longer sequences that have
5197 been assembled from those reads. To identify differentially expressed genes
5198 between experiments, StringTie's output can be processed either by the
5199 Cuffdiff or Ballgown programs.")
5200 (license license:artistic2.0)))
5201
5202 (define-public vcftools
5203 (package
5204 (name "vcftools")
5205 (version "0.1.14")
5206 (source (origin
5207 (method url-fetch)
5208 (uri (string-append
5209 "https://github.com/vcftools/vcftools/releases/download/v"
5210 version "/vcftools-" version ".tar.gz"))
5211 (sha256
5212 (base32
5213 "10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
5214 (build-system gnu-build-system)
5215 (arguments
5216 `(#:tests? #f ; no "check" target
5217 #:make-flags (list
5218 "CFLAGS=-O2" ; override "-m64" flag
5219 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5220 (string-append "MANDIR=" (assoc-ref %outputs "out")
5221 "/share/man/man1"))))
5222 (native-inputs
5223 `(("pkg-config" ,pkg-config)))
5224 (inputs
5225 `(("perl" ,perl)
5226 ("zlib" ,zlib)))
5227 (home-page "https://vcftools.github.io/")
5228 (synopsis "Tools for working with VCF files")
5229 (description
5230 "VCFtools is a program package designed for working with VCF files, such
5231 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5232 provide easily accessible methods for working with complex genetic variation
5233 data in the form of VCF files.")
5234 ;; The license is declared as LGPLv3 in the README and
5235 ;; at https://vcftools.github.io/license.html
5236 (license license:lgpl3)))
5237
5238 (define-public infernal
5239 (package
5240 (name "infernal")
5241 (version "1.1.2")
5242 (source (origin
5243 (method url-fetch)
5244 (uri (string-append "http://eddylab.org/software/infernal/"
5245 "infernal-" version ".tar.gz"))
5246 (sha256
5247 (base32
5248 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5249 (build-system gnu-build-system)
5250 (native-inputs
5251 `(("perl" ,perl))) ; for tests
5252 (home-page "http://eddylab.org/infernal/")
5253 (synopsis "Inference of RNA alignments")
5254 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5255 searching DNA sequence databases for RNA structure and sequence similarities.
5256 It is an implementation of a special case of profile stochastic context-free
5257 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5258 profile, but it scores a combination of sequence consensus and RNA secondary
5259 structure consensus, so in many cases, it is more capable of identifying RNA
5260 homologs that conserve their secondary structure more than their primary
5261 sequence.")
5262 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5263 (supported-systems '("i686-linux" "x86_64-linux"))
5264 (license license:bsd-3)))
5265
5266 (define-public r-centipede
5267 (package
5268 (name "r-centipede")
5269 (version "1.2")
5270 (source (origin
5271 (method url-fetch)
5272 (uri (string-append "http://download.r-forge.r-project.org/"
5273 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5274 (sha256
5275 (base32
5276 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5277 (build-system r-build-system)
5278 (home-page "http://centipede.uchicago.edu/")
5279 (synopsis "Predict transcription factor binding sites")
5280 (description
5281 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5282 of the genome that are bound by particular transcription factors. It starts
5283 by identifying a set of candidate binding sites, and then aims to classify the
5284 sites according to whether each site is bound or not bound by a transcription
5285 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5286 between two different types of motif instances using as much relevant
5287 information as possible.")
5288 (license (list license:gpl2+ license:gpl3+))))
5289
5290 (define-public r-vegan
5291 (package
5292 (name "r-vegan")
5293 (version "2.4-1")
5294 (source
5295 (origin
5296 (method url-fetch)
5297 (uri (cran-uri "vegan" version))
5298 (sha256
5299 (base32
5300 "0i0c7rc0nzgbysd1nlxzxd2rvy75qcnw3yc7nggzqjzzj5d7yzsd"))))
5301 (build-system r-build-system)
5302 (arguments
5303 `(#:phases
5304 (modify-phases %standard-phases
5305 (add-after 'unpack 'revert-test-deletion
5306 ;; The distributed sources do not include tests with the CRAN
5307 ;; package. Here we revert the commit
5308 ;; `591d0e8ba1deaaf82445474ec6619c0b43db4e63' which deletes these
5309 ;; tests. There are plans to not delete tests in future as
5310 ;; documented at https://github.com/vegandevs/vegan/issues/181.
5311 (lambda* (#:key inputs #:allow-other-keys)
5312 (zero?
5313 (system* "patch" "-R" "-p1" "-i"
5314 (assoc-ref inputs "r-vegan-delete-tests-patch"))))))))
5315 (native-inputs
5316 `(("gfortran" ,gfortran)
5317 ("r-knitr" ,r-knitr)
5318 ("r-vegan-delete-tests-patch"
5319 ,(origin
5320 (method url-fetch)
5321 (uri (string-append
5322 "https://github.com/vegandevs/vegan/commit/"
5323 "591d0e8ba1deaaf82445474ec6619c0b43db4e63.patch"))
5324 (sha256
5325 (base32
5326 "0b1bi7y4jjdl3ph721vm9apm51dr2z9piwvhy4355sf2b4kyyj5a"))))))
5327 (propagated-inputs
5328 `(("r-cluster" ,r-cluster)
5329 ("r-lattice" ,r-lattice)
5330 ("r-mgcv" ,r-mgcv)
5331 ("r-permute" ,r-permute)))
5332 (home-page "https://cran.r-project.org/web/packages/vegan")
5333 (synopsis "Functions for community ecology")
5334 (description
5335 "The vegan package provides tools for descriptive community ecology. It
5336 has most basic functions of diversity analysis, community ordination and
5337 dissimilarity analysis. Most of its multivariate tools can be used for other
5338 data types as well.")
5339 (license license:gpl2+)))
5340
5341 (define-public r-annotate
5342 (package
5343 (name "r-annotate")
5344 (version "1.52.1")
5345 (source
5346 (origin
5347 (method url-fetch)
5348 (uri (bioconductor-uri "annotate" version))
5349 (sha256
5350 (base32
5351 "0yymz8qxgnbybvfhqrgkd1hh9dhwxdii1yxkhr1zicjgb35xixxb"))))
5352 (build-system r-build-system)
5353 (propagated-inputs
5354 `(("r-annotationdbi" ,r-annotationdbi)
5355 ("r-biobase" ,r-biobase)
5356 ("r-biocgenerics" ,r-biocgenerics)
5357 ("r-dbi" ,r-dbi)
5358 ("r-rcurl" ,r-rcurl)
5359 ("r-xml" ,r-xml)
5360 ("r-xtable" ,r-xtable)))
5361 (home-page
5362 "http://bioconductor.org/packages/annotate")
5363 (synopsis "Annotation for microarrays")
5364 (description "This package provides R enviroments for the annotation of
5365 microarrays.")
5366 (license license:artistic2.0)))
5367
5368 (define-public r-geneplotter
5369 (package
5370 (name "r-geneplotter")
5371 (version "1.52.0")
5372 (source
5373 (origin
5374 (method url-fetch)
5375 (uri (bioconductor-uri "geneplotter" version))
5376 (sha256
5377 (base32
5378 "1p6yvxi243irhjxwm97hp73abhwampj0myyf8z00ij166674pc7h"))))
5379 (build-system r-build-system)
5380 (propagated-inputs
5381 `(("r-annotate" ,r-annotate)
5382 ("r-annotationdbi" ,r-annotationdbi)
5383 ("r-biobase" ,r-biobase)
5384 ("r-biocgenerics" ,r-biocgenerics)
5385 ("r-lattice" ,r-lattice)
5386 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5387 (home-page "http://bioconductor.org/packages/geneplotter")
5388 (synopsis "Graphics functions for genomic data")
5389 (description
5390 "This package provides functions for plotting genomic data.")
5391 (license license:artistic2.0)))
5392
5393 (define-public r-genefilter
5394 (package
5395 (name "r-genefilter")
5396 (version "1.56.0")
5397 (source
5398 (origin
5399 (method url-fetch)
5400 (uri (bioconductor-uri "genefilter" version))
5401 (sha256
5402 (base32
5403 "1vzgciqd09csqcw9qync8blsv51ylrd86a65iadgyy6j26g01fwd"))))
5404 (build-system r-build-system)
5405 (native-inputs
5406 `(("gfortran" ,gfortran)))
5407 (propagated-inputs
5408 `(("r-annotate" ,r-annotate)
5409 ("r-annotationdbi" ,r-annotationdbi)
5410 ("r-biobase" ,r-biobase)
5411 ("r-s4vectors" ,r-s4vectors)))
5412 (home-page "http://bioconductor.org/packages/genefilter")
5413 (synopsis "Filter genes from high-throughput experiments")
5414 (description
5415 "This package provides basic functions for filtering genes from
5416 high-throughput sequencing experiments.")
5417 (license license:artistic2.0)))
5418
5419 (define-public r-deseq2
5420 (package
5421 (name "r-deseq2")
5422 (version "1.14.1")
5423 (source
5424 (origin
5425 (method url-fetch)
5426 (uri (bioconductor-uri "DESeq2" version))
5427 (sha256
5428 (base32
5429 "1walwkqryn1gnwz7zryr5764a0p6ia7ag4w6w9n8fskg8dkg0fqs"))))
5430 (properties `((upstream-name . "DESeq2")))
5431 (build-system r-build-system)
5432 (arguments
5433 `(#:phases
5434 (modify-phases %standard-phases
5435 (add-after 'unpack 'link-against-armadillo
5436 (lambda _
5437 (substitute* "src/Makevars"
5438 (("PKG_LIBS =" prefix)
5439 (string-append prefix "-larmadillo"))))))))
5440 (propagated-inputs
5441 `(("r-biobase" ,r-biobase)
5442 ("r-biocgenerics" ,r-biocgenerics)
5443 ("r-biocparallel" ,r-biocparallel)
5444 ("r-genefilter" ,r-genefilter)
5445 ("r-geneplotter" ,r-geneplotter)
5446 ("r-genomicranges" ,r-genomicranges)
5447 ("r-ggplot2" ,r-ggplot2)
5448 ("r-hmisc" ,r-hmisc)
5449 ("r-iranges" ,r-iranges)
5450 ("r-locfit" ,r-locfit)
5451 ("r-rcpp" ,r-rcpp)
5452 ("r-rcpparmadillo" ,r-rcpparmadillo)
5453 ("r-s4vectors" ,r-s4vectors)
5454 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5455 (home-page "http://bioconductor.org/packages/DESeq2")
5456 (synopsis "Differential gene expression analysis")
5457 (description
5458 "This package provides functions to estimate variance-mean dependence in
5459 count data from high-throughput nucleotide sequencing assays and test for
5460 differential expression based on a model using the negative binomial
5461 distribution.")
5462 (license license:lgpl3+)))
5463
5464 (define-public r-annotationforge
5465 (package
5466 (name "r-annotationforge")
5467 (version "1.16.0")
5468 (source
5469 (origin
5470 (method url-fetch)
5471 (uri (bioconductor-uri "AnnotationForge" version))
5472 (sha256
5473 (base32
5474 "02msyb9p3hywrryx00zpjkjl126mrv827i1ah1092s0cplm6xxvf"))))
5475 (properties
5476 `((upstream-name . "AnnotationForge")))
5477 (build-system r-build-system)
5478 (propagated-inputs
5479 `(("r-annotationdbi" ,r-annotationdbi)
5480 ("r-biobase" ,r-biobase)
5481 ("r-biocgenerics" ,r-biocgenerics)
5482 ("r-dbi" ,r-dbi)
5483 ("r-rcurl" ,r-rcurl)
5484 ("r-rsqlite" ,r-rsqlite)
5485 ("r-s4vectors" ,r-s4vectors)
5486 ("r-xml" ,r-xml)))
5487 (home-page "http://bioconductor.org/packages/AnnotationForge")
5488 (synopsis "Code for building annotation database packages")
5489 (description
5490 "This package provides code for generating Annotation packages and their
5491 databases. Packages produced are intended to be used with AnnotationDbi.")
5492 (license license:artistic2.0)))
5493
5494 (define-public r-rbgl
5495 (package
5496 (name "r-rbgl")
5497 (version "1.50.0")
5498 (source
5499 (origin
5500 (method url-fetch)
5501 (uri (bioconductor-uri "RBGL" version))
5502 (sha256
5503 (base32
5504 "1q14m8w6ih56v680kf3d9wh1qbgp7af33kz3cxafdf1vvzx9km08"))))
5505 (properties `((upstream-name . "RBGL")))
5506 (build-system r-build-system)
5507 (propagated-inputs `(("r-graph" ,r-graph)))
5508 (home-page "http://www.bioconductor.org/packages/RBGL")
5509 (synopsis "Interface to the Boost graph library")
5510 (description
5511 "This package provides a fairly extensive and comprehensive interface to
5512 the graph algorithms contained in the Boost library.")
5513 (license license:artistic2.0)))
5514
5515 (define-public r-gseabase
5516 (package
5517 (name "r-gseabase")
5518 (version "1.36.0")
5519 (source
5520 (origin
5521 (method url-fetch)
5522 (uri (bioconductor-uri "GSEABase" version))
5523 (sha256
5524 (base32
5525 "0l2x7yj7lfb0m2dmsav5ib026dikpgl4crdckrnj776yy08lgxpj"))))
5526 (properties `((upstream-name . "GSEABase")))
5527 (build-system r-build-system)
5528 (propagated-inputs
5529 `(("r-annotate" ,r-annotate)
5530 ("r-annotationdbi" ,r-annotationdbi)
5531 ("r-biobase" ,r-biobase)
5532 ("r-biocgenerics" ,r-biocgenerics)
5533 ("r-graph" ,r-graph)
5534 ("r-xml" ,r-xml)))
5535 (home-page "http://bioconductor.org/packages/GSEABase")
5536 (synopsis "Gene set enrichment data structures and methods")
5537 (description
5538 "This package provides classes and methods to support @dfn{Gene Set
5539 Enrichment Analysis} (GSEA).")
5540 (license license:artistic2.0)))
5541
5542 (define-public r-category
5543 (package
5544 (name "r-category")
5545 (version "2.40.0")
5546 (source
5547 (origin
5548 (method url-fetch)
5549 (uri (bioconductor-uri "Category" version))
5550 (sha256
5551 (base32
5552 "16ncwz7b4y48k0p3fvbrbmvf7nfz63li9ysgcl8kp9kl4hg7llng"))))
5553 (properties `((upstream-name . "Category")))
5554 (build-system r-build-system)
5555 (propagated-inputs
5556 `(("r-annotate" ,r-annotate)
5557 ("r-annotationdbi" ,r-annotationdbi)
5558 ("r-biobase" ,r-biobase)
5559 ("r-biocgenerics" ,r-biocgenerics)
5560 ("r-genefilter" ,r-genefilter)
5561 ("r-graph" ,r-graph)
5562 ("r-gseabase" ,r-gseabase)
5563 ("r-matrix" ,r-matrix)
5564 ("r-rbgl" ,r-rbgl)
5565 ("r-rsqlite" ,r-rsqlite)))
5566 (home-page "http://bioconductor.org/packages/Category")
5567 (synopsis "Category analysis")
5568 (description
5569 "This package provides a collection of tools for performing category
5570 analysis.")
5571 (license license:artistic2.0)))
5572
5573 (define-public r-gostats
5574 (package
5575 (name "r-gostats")
5576 (version "2.40.0")
5577 (source
5578 (origin
5579 (method url-fetch)
5580 (uri (bioconductor-uri "GOstats" version))
5581 (sha256
5582 (base32
5583 "0g2czm94zhzx92z7y2r4mjfxhwml7bhab2db6820ks8nkw1zvr9n"))))
5584 (properties `((upstream-name . "GOstats")))
5585 (build-system r-build-system)
5586 (propagated-inputs
5587 `(("r-annotate" ,r-annotate)
5588 ("r-annotationdbi" ,r-annotationdbi)
5589 ("r-annotationforge" ,r-annotationforge)
5590 ("r-biobase" ,r-biobase)
5591 ("r-category" ,r-category)
5592 ("r-go-db" ,r-go-db)
5593 ("r-graph" ,r-graph)
5594 ("r-rbgl" ,r-rbgl)))
5595 (home-page "http://bioconductor.org/packages/GOstats")
5596 (synopsis "Tools for manipulating GO and microarrays")
5597 (description
5598 "This package provides a set of tools for interacting with GO and
5599 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5600 testing and other simple calculations.")
5601 (license license:artistic2.0)))
5602
5603 (define-public r-shortread
5604 (package
5605 (name "r-shortread")
5606 (version "1.32.0")
5607 (source
5608 (origin
5609 (method url-fetch)
5610 (uri (bioconductor-uri "ShortRead" version))
5611 (sha256
5612 (base32
5613 "0mjdlg92x5qw4x2djc4dv5lxwl7ai6ix56nnf86zr07jk8vc7yls"))))
5614 (properties `((upstream-name . "ShortRead")))
5615 (build-system r-build-system)
5616 (inputs
5617 `(("zlib" ,zlib)))
5618 (propagated-inputs
5619 `(("r-biobase" ,r-biobase)
5620 ("r-biocgenerics" ,r-biocgenerics)
5621 ("r-biocparallel" ,r-biocparallel)
5622 ("r-biostrings" ,r-biostrings)
5623 ("r-genomeinfodb" ,r-genomeinfodb)
5624 ("r-genomicalignments" ,r-genomicalignments)
5625 ("r-genomicranges" ,r-genomicranges)
5626 ("r-hwriter" ,r-hwriter)
5627 ("r-iranges" ,r-iranges)
5628 ("r-lattice" ,r-lattice)
5629 ("r-latticeextra" ,r-latticeextra)
5630 ("r-rsamtools" ,r-rsamtools)
5631 ("r-s4vectors" ,r-s4vectors)
5632 ("r-xvector" ,r-xvector)
5633 ("r-zlibbioc" ,r-zlibbioc)))
5634 (home-page "http://bioconductor.org/packages/ShortRead")
5635 (synopsis "FASTQ input and manipulation tools")
5636 (description
5637 "This package implements sampling, iteration, and input of FASTQ files.
5638 It includes functions for filtering and trimming reads, and for generating a
5639 quality assessment report. Data are represented as
5640 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5641 purposes. The package also contains legacy support for early single-end,
5642 ungapped alignment formats.")
5643 (license license:artistic2.0)))
5644
5645 (define-public r-systempiper
5646 (package
5647 (name "r-systempiper")
5648 (version "1.8.1")
5649 (source
5650 (origin
5651 (method url-fetch)
5652 (uri (bioconductor-uri "systemPipeR" version))
5653 (sha256
5654 (base32
5655 "0hyi841w8fm2yzpm6lwqi3jz5kc8ny8dy5p29dxynzaw5bpjw56d"))))
5656 (properties `((upstream-name . "systemPipeR")))
5657 (build-system r-build-system)
5658 (propagated-inputs
5659 `(("r-annotate" ,r-annotate)
5660 ("r-batchjobs" ,r-batchjobs)
5661 ("r-biocgenerics" ,r-biocgenerics)
5662 ("r-biostrings" ,r-biostrings)
5663 ("r-deseq2" ,r-deseq2)
5664 ("r-edger" ,r-edger)
5665 ("r-genomicfeatures" ,r-genomicfeatures)
5666 ("r-genomicranges" ,r-genomicranges)
5667 ("r-ggplot2" ,r-ggplot2)
5668 ("r-go-db" ,r-go-db)
5669 ("r-gostats" ,r-gostats)
5670 ("r-limma" ,r-limma)
5671 ("r-pheatmap" ,r-pheatmap)
5672 ("r-rjson" ,r-rjson)
5673 ("r-rsamtools" ,r-rsamtools)
5674 ("r-shortread" ,r-shortread)
5675 ("r-summarizedexperiment" ,r-summarizedexperiment)
5676 ("r-variantannotation" ,r-variantannotation)))
5677 (home-page "https://github.com/tgirke/systemPipeR")
5678 (synopsis "Next generation sequencing workflow and reporting environment")
5679 (description
5680 "This R package provides tools for building and running automated
5681 end-to-end analysis workflows for a wide range of @dfn{next generation
5682 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5683 Important features include a uniform workflow interface across different NGS
5684 applications, automated report generation, and support for running both R and
5685 command-line software, such as NGS aligners or peak/variant callers, on local
5686 computers or compute clusters. Efficient handling of complex sample sets and
5687 experimental designs is facilitated by a consistently implemented sample
5688 annotation infrastructure.")
5689 (license license:artistic2.0)))
5690
5691 (define-public r-grohmm
5692 (package
5693 (name "r-grohmm")
5694 (version "1.8.0")
5695 (source
5696 (origin
5697 (method url-fetch)
5698 (uri (bioconductor-uri "groHMM" version))
5699 (sha256
5700 (base32
5701 "0d91nyhqbi5hv3mgmr2z0g29wg2md26g0hyv5mgapmz20cd9zi4y"))))
5702 (properties `((upstream-name . "groHMM")))
5703 (build-system r-build-system)
5704 (propagated-inputs
5705 `(("r-genomeinfodb" ,r-genomeinfodb)
5706 ("r-genomicalignments" ,r-genomicalignments)
5707 ("r-genomicranges" ,r-genomicranges)
5708 ("r-iranges" ,r-iranges)
5709 ("r-rtracklayer" ,r-rtracklayer)
5710 ("r-s4vectors" ,r-s4vectors)))
5711 (home-page "https://github.com/Kraus-Lab/groHMM")
5712 (synopsis "GRO-seq analysis pipeline")
5713 (description
5714 "This package provides a pipeline for the analysis of GRO-seq data.")
5715 (license license:gpl3+)))
5716
5717 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
5718 (package
5719 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
5720 (version "3.2.2")
5721 (source (origin
5722 (method url-fetch)
5723 ;; We cannot use bioconductor-uri here because this tarball is
5724 ;; located under "data/annotation/" instead of "bioc/".
5725 (uri (string-append "http://bioconductor.org/packages/"
5726 "release/data/annotation/src/contrib"
5727 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
5728 version ".tar.gz"))
5729 (sha256
5730 (base32
5731 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
5732 (properties
5733 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
5734 (build-system r-build-system)
5735 ;; As this package provides little more than a very large data file it
5736 ;; doesn't make sense to build substitutes.
5737 (arguments `(#:substitutable? #f))
5738 (propagated-inputs
5739 `(("r-genomicfeatures" ,r-genomicfeatures)))
5740 (home-page
5741 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
5742 (synopsis "Annotation package for human genome in TxDb format")
5743 (description
5744 "This package provides an annotation database of Homo sapiens genome
5745 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
5746 track. The database is exposed as a @code{TxDb} object.")
5747 (license license:artistic2.0)))
5748
5749 (define-public vsearch
5750 (package
5751 (name "vsearch")
5752 (version "2.3.4")
5753 (source
5754 (origin
5755 (method url-fetch)
5756 (uri (string-append
5757 "https://github.com/torognes/vsearch/archive/v"
5758 version ".tar.gz"))
5759 (file-name (string-append name "-" version ".tar.gz"))
5760 (sha256
5761 (base32
5762 "1xyraxmhyx62mxx8z7c8waygvcijwkh48ms1ar60w2cv2y2sn4al"))
5763 (modules '((guix build utils)))
5764 (snippet
5765 '(begin
5766 ;; Remove bundled cityhash and '-mtune=native'.
5767 (substitute* "src/Makefile.am"
5768 (("^AM_CXXFLAGS=-I\\$\\{srcdir\\}/cityhash \
5769 -O3 -mtune=native -Wall -Wsign-compare")
5770 (string-append "AM_CXXFLAGS=-lcityhash"
5771 " -O3 -Wall -Wsign-compare"))
5772 (("^__top_builddir__bin_vsearch_SOURCES = city.h \\\\")
5773 "__top_builddir__bin_vsearch_SOURCES = \\")
5774 (("^city.h \\\\") "\\")
5775 (("^citycrc.h \\\\") "\\")
5776 (("^libcityhash_a.*") "")
5777 (("noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a \
5778 libcityhash.a")
5779 "noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a")
5780 (("__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
5781 libcpu_sse2.a libcityhash.a")
5782 "__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
5783 libcpu_sse2.a -lcityhash"))
5784 (substitute* "src/vsearch.h"
5785 (("^\\#include \"city.h\"") "#include <city.h>")
5786 (("^\\#include \"citycrc.h\"") "#include <citycrc.h>"))
5787 (delete-file "src/city.h")
5788 (delete-file "src/citycrc.h")
5789 (delete-file "src/city.cc")
5790 #t))))
5791 (build-system gnu-build-system)
5792 (arguments
5793 `(#:phases
5794 (modify-phases %standard-phases
5795 (add-before 'configure 'autogen
5796 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
5797 (inputs
5798 `(("zlib" ,zlib)
5799 ("bzip2" ,bzip2)
5800 ("cityhash" ,cityhash)))
5801 (native-inputs
5802 `(("autoconf" ,autoconf)
5803 ("automake" ,automake)))
5804 (synopsis "Sequence search tools for metagenomics")
5805 (description
5806 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
5807 dereplication, pairwise alignment, shuffling, subsampling, sorting and
5808 masking. The tool takes advantage of parallelism in the form of SIMD
5809 vectorization as well as multiple threads to perform accurate alignments at
5810 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
5811 Needleman-Wunsch).")
5812 (home-page "https://github.com/torognes/vsearch")
5813 ;; vsearch uses non-portable SSE intrinsics so building fails on other
5814 ;; platforms.
5815 (supported-systems '("x86_64-linux"))
5816 ;; Dual licensed; also includes public domain source.
5817 (license (list license:gpl3 license:bsd-2))))
5818
5819 (define-public pardre
5820 (package
5821 (name "pardre")
5822 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
5823 (version "1.1.5-1")
5824 (source
5825 (origin
5826 (method url-fetch)
5827 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
5828 "1.1.5" ".tar.gz"))
5829 (sha256
5830 (base32
5831 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
5832 (build-system gnu-build-system)
5833 (arguments
5834 `(#:tests? #f ; no tests included
5835 #:phases
5836 (modify-phases %standard-phases
5837 (delete 'configure)
5838 (replace 'install
5839 (lambda* (#:key outputs #:allow-other-keys)
5840 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
5841 (install-file "ParDRe" bin)
5842 #t))))))
5843 (inputs
5844 `(("openmpi" ,openmpi)
5845 ("zlib" ,zlib)))
5846 (synopsis "Parallel tool to remove duplicate DNA reads")
5847 (description
5848 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
5849 Duplicate reads can be seen as identical or nearly identical sequences with
5850 some mismatches. This tool lets users avoid the analysis of unnecessary
5851 reads, reducing the time of subsequent procedures with the
5852 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
5853 in order to exploit the parallel capabilities of multicore clusters. It is
5854 faster than multithreaded counterparts (end of 2015) for the same number of
5855 cores and, thanks to the message-passing technology, it can be executed on
5856 clusters.")
5857 (home-page "https://sourceforge.net/projects/pardre/")
5858 (license license:gpl3+)))
5859
5860 (define-public ruby-bio-kseq
5861 (package
5862 (name "ruby-bio-kseq")
5863 (version "0.0.2")
5864 (source
5865 (origin
5866 (method url-fetch)
5867 (uri (rubygems-uri "bio-kseq" version))
5868 (sha256
5869 (base32
5870 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
5871 (build-system ruby-build-system)
5872 (arguments
5873 `(#:test-target "spec"))
5874 (native-inputs
5875 `(("bundler" ,bundler)
5876 ("ruby-rspec" ,ruby-rspec)
5877 ("ruby-rake-compiler" ,ruby-rake-compiler)))
5878 (inputs
5879 `(("zlib" ,zlib)))
5880 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
5881 (description
5882 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
5883 FASTQ parsing code. It provides a fast iterator over sequences and their
5884 quality scores.")
5885 (home-page "https://github.com/gusevfe/bio-kseq")
5886 (license license:expat)))
5887
5888 (define-public bio-locus
5889 (package
5890 (name "bio-locus")
5891 (version "0.0.7")
5892 (source
5893 (origin
5894 (method url-fetch)
5895 (uri (rubygems-uri "bio-locus" version))
5896 (sha256
5897 (base32
5898 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
5899 (build-system ruby-build-system)
5900 (native-inputs
5901 `(("ruby-rspec" ,ruby-rspec)))
5902 (synopsis "Tool for fast querying of genome locations")
5903 (description
5904 "Bio-locus is a tabix-like tool for fast querying of genome
5905 locations. Many file formats in bioinformatics contain records that
5906 start with a chromosome name and a position for a SNP, or a start-end
5907 position for indels. Bio-locus allows users to store this chr+pos or
5908 chr+pos+alt information in a database.")
5909 (home-page "https://github.com/pjotrp/bio-locus")
5910 (license license:expat)))
5911
5912 (define-public bio-blastxmlparser
5913 (package
5914 (name "bio-blastxmlparser")
5915 (version "2.0.4")
5916 (source (origin
5917 (method url-fetch)
5918 (uri (rubygems-uri "bio-blastxmlparser" version))
5919 (sha256
5920 (base32
5921 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
5922 (build-system ruby-build-system)
5923 (propagated-inputs
5924 `(("ruby-bio-logger" ,ruby-bio-logger)
5925 ("ruby-nokogiri" ,ruby-nokogiri)))
5926 (inputs
5927 `(("ruby-rspec" ,ruby-rspec)))
5928 (synopsis "Fast big data BLAST XML parser and library")
5929 (description
5930 "Very fast parallel big-data BLAST XML file parser which can be used as
5931 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
5932 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
5933 (home-page "http://github.com/pjotrp/blastxmlparser")
5934 (license license:expat)))
5935
5936 (define-public bioruby
5937 (package
5938 (name "bioruby")
5939 (version "1.5.1")
5940 (source
5941 (origin
5942 (method url-fetch)
5943 (uri (rubygems-uri "bio" version))
5944 (sha256
5945 (base32
5946 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
5947 (build-system ruby-build-system)
5948 (propagated-inputs
5949 `(("ruby-libxml" ,ruby-libxml)))
5950 (native-inputs
5951 `(("which" ,which))) ; required for test phase
5952 (arguments
5953 `(#:phases
5954 (modify-phases %standard-phases
5955 (add-before 'build 'patch-test-command
5956 (lambda _
5957 (substitute* '("test/functional/bio/test_command.rb")
5958 (("/bin/sh") (which "sh")))
5959 (substitute* '("test/functional/bio/test_command.rb")
5960 (("/bin/ls") (which "ls")))
5961 (substitute* '("test/functional/bio/test_command.rb")
5962 (("which") (which "which")))
5963 (substitute* '("test/functional/bio/test_command.rb",
5964 "test/data/command/echoarg2.sh")
5965 (("/bin/echo") (which "echo")))
5966 #t)))))
5967 (synopsis "Ruby library, shell and utilities for bioinformatics")
5968 (description "BioRuby comes with a comprehensive set of Ruby development
5969 tools and libraries for bioinformatics and molecular biology. BioRuby has
5970 components for sequence analysis, pathway analysis, protein modelling and
5971 phylogenetic analysis; it supports many widely used data formats and provides
5972 easy access to databases, external programs and public web services, including
5973 BLAST, KEGG, GenBank, MEDLINE and GO.")
5974 (home-page "http://bioruby.org/")
5975 ;; Code is released under Ruby license, except for setup
5976 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
5977 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
5978
5979 (define-public r-acsnminer
5980 (package
5981 (name "r-acsnminer")
5982 (version "0.16.8.25")
5983 (source (origin
5984 (method url-fetch)
5985 (uri (cran-uri "ACSNMineR" version))
5986 (sha256
5987 (base32
5988 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
5989 (properties `((upstream-name . "ACSNMineR")))
5990 (build-system r-build-system)
5991 (propagated-inputs
5992 `(("r-ggplot2" ,r-ggplot2)
5993 ("r-gridextra" ,r-gridextra)))
5994 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
5995 (synopsis "Gene enrichment analysis")
5996 (description
5997 "This package provides tools to compute and represent gene set enrichment
5998 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
5999 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6000 enrichment can be run with hypergeometric test or Fisher exact test, and can
6001 use multiple corrections. Visualization of data can be done either by
6002 barplots or heatmaps.")
6003 (license license:gpl2+)))
6004
6005 (define-public r-biocgenerics
6006 (package
6007 (name "r-biocgenerics")
6008 (version "0.20.0")
6009 (source (origin
6010 (method url-fetch)
6011 (uri (bioconductor-uri "BiocGenerics" version))
6012 (sha256
6013 (base32
6014 "06szdz7dfs1iyv5zdl4fjzad18nnf1zf3wvglc6c6yd9mrqlf7vk"))))
6015 (properties
6016 `((upstream-name . "BiocGenerics")))
6017 (build-system r-build-system)
6018 (home-page "http://bioconductor.org/packages/BiocGenerics")
6019 (synopsis "S4 generic functions for Bioconductor")
6020 (description
6021 "This package provides S4 generic functions needed by many Bioconductor
6022 packages.")
6023 (license license:artistic2.0)))
6024
6025 (define-public r-biocinstaller
6026 (package
6027 (name "r-biocinstaller")
6028 (version "1.24.0")
6029 (source (origin
6030 (method url-fetch)
6031 (uri (bioconductor-uri "BiocInstaller" version))
6032 (sha256
6033 (base32
6034 "0y1y5wmy6lzjqx3hdg15n91d417ccjj8dbvdkhmp99bs5aijwcpn"))))
6035 (properties
6036 `((upstream-name . "BiocInstaller")))
6037 (build-system r-build-system)
6038 (home-page "http://bioconductor.org/packages/BiocInstaller")
6039 (synopsis "Install Bioconductor packages")
6040 (description "This package is used to install and update R packages from
6041 Bioconductor, CRAN, and Github.")
6042 (license license:artistic2.0)))
6043
6044 (define-public r-biocviews
6045 (package
6046 (name "r-biocviews")
6047 (version "1.42.0")
6048 (source (origin
6049 (method url-fetch)
6050 (uri (bioconductor-uri "biocViews" version))
6051 (sha256
6052 (base32
6053 "07rjk10b91pkriyq297w86199r2d3sfji3ggs9mq2gyalsa8y4b6"))))
6054 (properties
6055 `((upstream-name . "biocViews")))
6056 (build-system r-build-system)
6057 (propagated-inputs
6058 `(("r-biobase" ,r-biobase)
6059 ("r-graph" ,r-graph)
6060 ("r-rbgl" ,r-rbgl)
6061 ("r-rcurl" ,r-rcurl)
6062 ("r-xml" ,r-xml)
6063 ("r-knitr" ,r-knitr)
6064 ("r-runit" ,r-runit)))
6065 (home-page "http://bioconductor.org/packages/biocViews")
6066 (synopsis "Bioconductor package categorization helper")
6067 (description "The purpose of biocViews is to create HTML pages that
6068 categorize packages in a Bioconductor package repository according to keywords,
6069 also known as views, in a controlled vocabulary.")
6070 (license license:artistic2.0)))
6071
6072 (define-public r-biocstyle
6073 (package
6074 (name "r-biocstyle")
6075 (version "2.2.1")
6076 (source (origin
6077 (method url-fetch)
6078 (uri (bioconductor-uri "BiocStyle" version))
6079 (sha256
6080 (base32
6081 "0sl99xw940ixrm6v24lgaw3ljh56g59a6rdz7g160hx84z9f8n2n"))))
6082 (properties
6083 `((upstream-name . "BiocStyle")))
6084 (build-system r-build-system)
6085 (home-page "http://bioconductor.org/packages/BiocStyle")
6086 (synopsis "Bioconductor formatting styles")
6087 (description "This package provides standard formatting styles for
6088 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6089 functionality.")
6090 (license license:artistic2.0)))
6091
6092 (define-public r-bioccheck
6093 (package
6094 (name "r-bioccheck")
6095 (version "1.10.0")
6096 (source (origin
6097 (method url-fetch)
6098 (uri (bioconductor-uri "BiocCheck" version))
6099 (sha256
6100 (base32
6101 "1rfy37xg1nc2cmgbclvzsi7sgmdcdjiahsx9crgx3yaw7kxgiack"))))
6102 (properties
6103 `((upstream-name . "BiocCheck")))
6104 (build-system r-build-system)
6105 (arguments
6106 '(#:phases
6107 (modify-phases %standard-phases
6108 ;; This package can be used by calling BiocCheck(<package>) from
6109 ;; within R, or by running R CMD BiocCheck <package>. This phase
6110 ;; makes sure the latter works. For this to work, the BiocCheck
6111 ;; script must be somewhere on the PATH (not the R bin directory).
6112 (add-after 'install 'install-bioccheck-subcommand
6113 (lambda* (#:key outputs #:allow-other-keys)
6114 (let* ((out (assoc-ref outputs "out"))
6115 (dest-dir (string-append out "/bin"))
6116 (script-dir
6117 (string-append out "/site-library/BiocCheck/script/")))
6118 (mkdir-p dest-dir)
6119 (symlink (string-append script-dir "/checkBadDeps.R")
6120 (string-append dest-dir "/checkBadDeps.R"))
6121 (symlink (string-append script-dir "/BiocCheck")
6122 (string-append dest-dir "/BiocCheck")))
6123 #t)))))
6124 (native-inputs
6125 `(("which" ,which)))
6126 (propagated-inputs
6127 `(("r-graph" ,r-graph)
6128 ("r-knitr" ,r-knitr)
6129 ("r-httr" ,r-httr)
6130 ("r-optparse" ,r-optparse)
6131 ("r-devtools" ,r-devtools)
6132 ("r-biocinstaller" ,r-biocinstaller)
6133 ("r-biocviews" ,r-biocviews)))
6134 (home-page "http://bioconductor.org/packages/BiocCheck")
6135 (synopsis "Executes Bioconductor-specific package checks")
6136 (description "This package contains tools to perform additional quality
6137 checks on R packages that are to be submitted to the Bioconductor repository.")
6138 (license license:artistic2.0)))
6139
6140 (define-public r-getopt
6141 (package
6142 (name "r-getopt")
6143 (version "1.20.0")
6144 (source
6145 (origin
6146 (method url-fetch)
6147 (uri (cran-uri "getopt" version))
6148 (sha256
6149 (base32
6150 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6151 (build-system r-build-system)
6152 (home-page "https://github.com/trevorld/getopt")
6153 (synopsis "Command-line option processor for R")
6154 (description
6155 "This package is designed to be used with Rscript to write shebang
6156 scripts that accept short and long options. Many users will prefer to
6157 use the packages @code{optparse} or @code{argparse} which add extra
6158 features like automatically generated help options and usage texts,
6159 support for default values, positional argument support, etc.")
6160 (license license:gpl2+)))
6161
6162 (define-public r-optparse
6163 (package
6164 (name "r-optparse")
6165 (version "1.3.2")
6166 (source
6167 (origin
6168 (method url-fetch)
6169 (uri (cran-uri "optparse" version))
6170 (sha256
6171 (base32
6172 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6173 (build-system r-build-system)
6174 (propagated-inputs
6175 `(("r-getopt" ,r-getopt)))
6176 (home-page
6177 "https://github.com/trevorld/optparse")
6178 (synopsis "Command line option parser")
6179 (description
6180 "This package provides a command line parser inspired by Python's
6181 @code{optparse} library to be used with Rscript to write shebang scripts
6182 that accept short and long options.")
6183 (license license:gpl2+)))
6184
6185 (define-public r-dnacopy
6186 (package
6187 (name "r-dnacopy")
6188 (version "1.48.0")
6189 (source (origin
6190 (method url-fetch)
6191 (uri (bioconductor-uri "DNAcopy" version))
6192 (sha256
6193 (base32
6194 "1idyvfvy7xx8k9vk00y4k3819qmip8iqm809j3vpxabmsn7r9zyh"))))
6195 (properties
6196 `((upstream-name . "DNAcopy")))
6197 (build-system r-build-system)
6198 (inputs
6199 `(("gfortran" ,gfortran)))
6200 (home-page "https://bioconductor.org/packages/DNAcopy")
6201 (synopsis "Implementation of a circular binary segmentation algorithm")
6202 (description "This package implements the circular binary segmentation (CBS)
6203 algorithm to segment DNA copy number data and identify genomic regions with
6204 abnormal copy number.")
6205 (license license:gpl2+)))
6206
6207 (define-public r-s4vectors
6208 (package
6209 (name "r-s4vectors")
6210 (version "0.12.1")
6211 (source (origin
6212 (method url-fetch)
6213 (uri (bioconductor-uri "S4Vectors" version))
6214 (sha256
6215 (base32
6216 "0i36y3w36h3d8rmazxcrip4gvn54rd9av1wz4lygsprrjmylfhcc"))))
6217 (properties
6218 `((upstream-name . "S4Vectors")))
6219 (build-system r-build-system)
6220 (propagated-inputs
6221 `(("r-biocgenerics" ,r-biocgenerics)))
6222 (home-page "http://bioconductor.org/packages/S4Vectors")
6223 (synopsis "S4 implementation of vectors and lists")
6224 (description
6225 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6226 classes and a set of generic functions that extend the semantic of ordinary
6227 vectors and lists in R. Package developers can easily implement vector-like
6228 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6229 In addition, a few low-level concrete subclasses of general interest (e.g.
6230 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6231 S4Vectors package itself.")
6232 (license license:artistic2.0)))
6233
6234 (define-public r-seqinr
6235 (package
6236 (name "r-seqinr")
6237 (version "3.3-3")
6238 (source
6239 (origin
6240 (method url-fetch)
6241 (uri (cran-uri "seqinr" version))
6242 (sha256
6243 (base32
6244 "0rk4yba8km26c0rh1f4h474zsb5n6kjmqsi55bnzr6p8pymp18hj"))))
6245 (build-system r-build-system)
6246 (propagated-inputs
6247 `(("r-ade4" ,r-ade4)
6248 ("r-segmented" ,r-segmented)))
6249 (inputs
6250 `(("zlib" ,zlib)))
6251 (home-page "http://seqinr.r-forge.r-project.org/")
6252 (synopsis "Biological sequences retrieval and analysis")
6253 (description
6254 "This package provides tools for exploratory data analysis and data
6255 visualization of biological sequence (DNA and protein) data. It also includes
6256 utilities for sequence data management under the ACNUC system.")
6257 (license license:gpl2+)))
6258
6259 (define-public r-iranges
6260 (package
6261 (name "r-iranges")
6262 (version "2.8.1")
6263 (source (origin
6264 (method url-fetch)
6265 (uri (bioconductor-uri "IRanges" version))
6266 (sha256
6267 (base32
6268 "0cryqnpqb3p6l9jjw27hyqd550sxlljls3ka7b9rb38hkji7b5hw"))))
6269 (properties
6270 `((upstream-name . "IRanges")))
6271 (build-system r-build-system)
6272 (propagated-inputs
6273 `(("r-biocgenerics" ,r-biocgenerics)
6274 ("r-s4vectors" ,r-s4vectors)))
6275 (home-page "http://bioconductor.org/packages/IRanges")
6276 (synopsis "Infrastructure for manipulating intervals on sequences")
6277 (description
6278 "This package provides efficient low-level and highly reusable S4 classes
6279 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6280 generally, data that can be organized sequentially (formally defined as
6281 @code{Vector} objects), as well as views on these @code{Vector} objects.
6282 Efficient list-like classes are also provided for storing big collections of
6283 instances of the basic classes. All classes in the package use consistent
6284 naming and share the same rich and consistent \"Vector API\" as much as
6285 possible.")
6286 (license license:artistic2.0)))
6287
6288 (define-public r-genomeinfodb
6289 (package
6290 (name "r-genomeinfodb")
6291 (version "1.10.2")
6292 (source (origin
6293 (method url-fetch)
6294 (uri (bioconductor-uri "GenomeInfoDb" version))
6295 (sha256
6296 (base32
6297 "0zh894qd1sgpjbn0wfvq6hs2dzn7y1pyicvzk2aa48y3zbidanv7"))))
6298 (properties
6299 `((upstream-name . "GenomeInfoDb")))
6300 (build-system r-build-system)
6301 (propagated-inputs
6302 `(("r-biocgenerics" ,r-biocgenerics)
6303 ("r-iranges" ,r-iranges)
6304 ("r-s4vectors" ,r-s4vectors)))
6305 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6306 (synopsis "Utilities for manipulating chromosome identifiers")
6307 (description
6308 "This package contains data and functions that define and allow
6309 translation between different chromosome sequence naming conventions (e.g.,
6310 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6311 names in their natural, rather than lexicographic, order.")
6312 (license license:artistic2.0)))
6313
6314 (define-public r-edger
6315 (package
6316 (name "r-edger")
6317 (version "3.16.5")
6318 (source (origin
6319 (method url-fetch)
6320 (uri (bioconductor-uri "edgeR" version))
6321 (sha256
6322 (base32
6323 "04vpa0a6dkkjyvvfbkmfjyaxf2ldkagi66g028qpaszd8jsk8yiv"))))
6324 (properties `((upstream-name . "edgeR")))
6325 (build-system r-build-system)
6326 (propagated-inputs
6327 `(("r-limma" ,r-limma)
6328 ("r-locfit" ,r-locfit)))
6329 (home-page "http://bioinf.wehi.edu.au/edgeR")
6330 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6331 (description "This package can do differential expression analysis of
6332 RNA-seq expression profiles with biological replication. It implements a range
6333 of statistical methodology based on the negative binomial distributions,
6334 including empirical Bayes estimation, exact tests, generalized linear models
6335 and quasi-likelihood tests. It be applied to differential signal analysis of
6336 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6337 CAGE.")
6338 (license license:gpl2+)))
6339
6340 (define-public r-variantannotation
6341 (package
6342 (name "r-variantannotation")
6343 (version "1.20.2")
6344 (source (origin
6345 (method url-fetch)
6346 (uri (bioconductor-uri "VariantAnnotation" version))
6347 (sha256
6348 (base32
6349 "165wda1d2jagd907pnra4m3sla66icyqxvd60xpv09jl5agd5mn9"))))
6350 (properties
6351 `((upstream-name . "VariantAnnotation")))
6352 (inputs
6353 `(("zlib" ,zlib)))
6354 (propagated-inputs
6355 `(("r-annotationdbi" ,r-annotationdbi)
6356 ("r-biobase" ,r-biobase)
6357 ("r-biocgenerics" ,r-biocgenerics)
6358 ("r-biostrings" ,r-biostrings)
6359 ("r-bsgenome" ,r-bsgenome)
6360 ("r-dbi" ,r-dbi)
6361 ("r-genomeinfodb" ,r-genomeinfodb)
6362 ("r-genomicfeatures" ,r-genomicfeatures)
6363 ("r-genomicranges" ,r-genomicranges)
6364 ("r-iranges" ,r-iranges)
6365 ("r-summarizedexperiment" ,r-summarizedexperiment)
6366 ("r-rsamtools" ,r-rsamtools)
6367 ("r-rtracklayer" ,r-rtracklayer)
6368 ("r-s4vectors" ,r-s4vectors)
6369 ("r-xvector" ,r-xvector)
6370 ("r-zlibbioc" ,r-zlibbioc)))
6371 (build-system r-build-system)
6372 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6373 (synopsis "Package for annotation of genetic variants")
6374 (description "This R package can annotate variants, compute amino acid
6375 coding changes and predict coding outcomes.")
6376 (license license:artistic2.0)))
6377
6378 (define-public r-limma
6379 (package
6380 (name "r-limma")
6381 (version "3.30.7")
6382 (source (origin
6383 (method url-fetch)
6384 (uri (bioconductor-uri "limma" version))
6385 (sha256
6386 (base32
6387 "1xg9w4lmn9n4hwyflxiwi6g969lcy569cg4z1x47crwwg7z7qdka"))))
6388 (build-system r-build-system)
6389 (home-page "http://bioinf.wehi.edu.au/limma")
6390 (synopsis "Package for linear models for microarray and RNA-seq data")
6391 (description "This package can be used for the analysis of gene expression
6392 studies, especially the use of linear models for analysing designed experiments
6393 and the assessment of differential expression. The analysis methods apply to
6394 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6395 (license license:gpl2+)))
6396
6397 (define-public r-xvector
6398 (package
6399 (name "r-xvector")
6400 (version "0.14.0")
6401 (source (origin
6402 (method url-fetch)
6403 (uri (bioconductor-uri "XVector" version))
6404 (sha256
6405 (base32
6406 "09lbqxpqr80g0kw77mpz0p1a8cq706j33kz8194wp71il67cdzi7"))))
6407 (properties
6408 `((upstream-name . "XVector")))
6409 (build-system r-build-system)
6410 (arguments
6411 `(#:phases
6412 (modify-phases %standard-phases
6413 (add-after 'unpack 'use-system-zlib
6414 (lambda _
6415 (substitute* "DESCRIPTION"
6416 (("zlibbioc, ") ""))
6417 (substitute* "NAMESPACE"
6418 (("import\\(zlibbioc\\)") ""))
6419 #t)))))
6420 (inputs
6421 `(("zlib" ,zlib)))
6422 (propagated-inputs
6423 `(("r-biocgenerics" ,r-biocgenerics)
6424 ("r-iranges" ,r-iranges)
6425 ("r-s4vectors" ,r-s4vectors)))
6426 (home-page "http://bioconductor.org/packages/XVector")
6427 (synopsis "Representation and manpulation of external sequences")
6428 (description
6429 "This package provides memory efficient S4 classes for storing sequences
6430 \"externally\" (behind an R external pointer, or on disk).")
6431 (license license:artistic2.0)))
6432
6433 (define-public r-genomicranges
6434 (package
6435 (name "r-genomicranges")
6436 (version "1.26.2")
6437 (source (origin
6438 (method url-fetch)
6439 (uri (bioconductor-uri "GenomicRanges" version))
6440 (sha256
6441 (base32
6442 "0if5dswkp77lyqppd0z2iyvnwag9h1gsr03707s8npcx13mzpsia"))))
6443 (properties
6444 `((upstream-name . "GenomicRanges")))
6445 (build-system r-build-system)
6446 (propagated-inputs
6447 `(("r-biocgenerics" ,r-biocgenerics)
6448 ("r-genomeinfodb" ,r-genomeinfodb)
6449 ("r-iranges" ,r-iranges)
6450 ("r-s4vectors" ,r-s4vectors)
6451 ("r-xvector" ,r-xvector)))
6452 (home-page "http://bioconductor.org/packages/GenomicRanges")
6453 (synopsis "Representation and manipulation of genomic intervals")
6454 (description
6455 "This package provides tools to efficiently represent and manipulate
6456 genomic annotations and alignments is playing a central role when it comes to
6457 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6458 GenomicRanges package defines general purpose containers for storing and
6459 manipulating genomic intervals and variables defined along a genome.")
6460 (license license:artistic2.0)))
6461
6462 (define-public r-biobase
6463 (package
6464 (name "r-biobase")
6465 (version "2.34.0")
6466 (source (origin
6467 (method url-fetch)
6468 (uri (bioconductor-uri "Biobase" version))
6469 (sha256
6470 (base32
6471 "0js9j9wqls8f571ifl9ylllbb9a9hwf7b7drf2grwb1fl31ldazl"))))
6472 (properties
6473 `((upstream-name . "Biobase")))
6474 (build-system r-build-system)
6475 (propagated-inputs
6476 `(("r-biocgenerics" ,r-biocgenerics)))
6477 (home-page "http://bioconductor.org/packages/Biobase")
6478 (synopsis "Base functions for Bioconductor")
6479 (description
6480 "This package provides functions that are needed by many other packages
6481 on Bioconductor or which replace R functions.")
6482 (license license:artistic2.0)))
6483
6484 (define-public r-annotationdbi
6485 (package
6486 (name "r-annotationdbi")
6487 (version "1.36.0")
6488 (source (origin
6489 (method url-fetch)
6490 (uri (bioconductor-uri "AnnotationDbi" version))
6491 (sha256
6492 (base32
6493 "0ydrqw1k1j5p6w76bwc753cx545c055x88q87wzya93858synj6r"))))
6494 (properties
6495 `((upstream-name . "AnnotationDbi")))
6496 (build-system r-build-system)
6497 (propagated-inputs
6498 `(("r-biobase" ,r-biobase)
6499 ("r-biocgenerics" ,r-biocgenerics)
6500 ("r-dbi" ,r-dbi)
6501 ("r-iranges" ,r-iranges)
6502 ("r-rsqlite" ,r-rsqlite)
6503 ("r-s4vectors" ,r-s4vectors)))
6504 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6505 (synopsis "Annotation database interface")
6506 (description
6507 "This package provides user interface and database connection code for
6508 annotation data packages using SQLite data storage.")
6509 (license license:artistic2.0)))
6510
6511 (define-public r-biomart
6512 (package
6513 (name "r-biomart")
6514 (version "2.30.0")
6515 (source (origin
6516 (method url-fetch)
6517 (uri (bioconductor-uri "biomaRt" version))
6518 (sha256
6519 (base32
6520 "1x0flcghq71784q2l02j0g4f9jkmyb14f6i307n6c59d6ji7h7x6"))))
6521 (properties
6522 `((upstream-name . "biomaRt")))
6523 (build-system r-build-system)
6524 (propagated-inputs
6525 `(("r-annotationdbi" ,r-annotationdbi)
6526 ("r-rcurl" ,r-rcurl)
6527 ("r-xml" ,r-xml)))
6528 (home-page "http://bioconductor.org/packages/biomaRt")
6529 (synopsis "Interface to BioMart databases")
6530 (description
6531 "biomaRt provides an interface to a growing collection of databases
6532 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6533 package enables retrieval of large amounts of data in a uniform way without
6534 the need to know the underlying database schemas or write complex SQL queries.
6535 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6536 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6537 users direct access to a diverse set of data and enable a wide range of
6538 powerful online queries from gene annotation to database mining.")
6539 (license license:artistic2.0)))
6540
6541 (define-public r-biocparallel
6542 (package
6543 (name "r-biocparallel")
6544 (version "1.8.1")
6545 (source (origin
6546 (method url-fetch)
6547 (uri (bioconductor-uri "BiocParallel" version))
6548 (sha256
6549 (base32
6550 "123i928rwi4h4sy4fpysv6pinw5nns0sm3myxi2ghqhm34ws8gyl"))))
6551 (properties
6552 `((upstream-name . "BiocParallel")))
6553 (build-system r-build-system)
6554 (propagated-inputs
6555 `(("r-futile-logger" ,r-futile-logger)
6556 ("r-snow" ,r-snow)))
6557 (home-page "http://bioconductor.org/packages/BiocParallel")
6558 (synopsis "Bioconductor facilities for parallel evaluation")
6559 (description
6560 "This package provides modified versions and novel implementation of
6561 functions for parallel evaluation, tailored to use with Bioconductor
6562 objects.")
6563 (license (list license:gpl2+ license:gpl3+))))
6564
6565 (define-public r-biostrings
6566 (package
6567 (name "r-biostrings")
6568 (version "2.42.1")
6569 (source (origin
6570 (method url-fetch)
6571 (uri (bioconductor-uri "Biostrings" version))
6572 (sha256
6573 (base32
6574 "0vqgd9i6y3wj4zviqwgvwgd4qj6033fg01rmx1cw9bw5i8ans42d"))))
6575 (properties
6576 `((upstream-name . "Biostrings")))
6577 (build-system r-build-system)
6578 (propagated-inputs
6579 `(("r-biocgenerics" ,r-biocgenerics)
6580 ("r-iranges" ,r-iranges)
6581 ("r-s4vectors" ,r-s4vectors)
6582 ("r-xvector" ,r-xvector)))
6583 (home-page "http://bioconductor.org/packages/Biostrings")
6584 (synopsis "String objects and algorithms for biological sequences")
6585 (description
6586 "This package provides memory efficient string containers, string
6587 matching algorithms, and other utilities, for fast manipulation of large
6588 biological sequences or sets of sequences.")
6589 (license license:artistic2.0)))
6590
6591 (define-public r-rsamtools
6592 (package
6593 (name "r-rsamtools")
6594 (version "1.26.1")
6595 (source (origin
6596 (method url-fetch)
6597 (uri (bioconductor-uri "Rsamtools" version))
6598 (sha256
6599 (base32
6600 "0pf4f6brf4bl5zgjrah0f38qslazrs49ayqgyh0xfqgrh63yx4ck"))))
6601 (properties
6602 `((upstream-name . "Rsamtools")))
6603 (build-system r-build-system)
6604 (arguments
6605 `(#:phases
6606 (modify-phases %standard-phases
6607 (add-after 'unpack 'use-system-zlib
6608 (lambda _
6609 (substitute* "DESCRIPTION"
6610 (("zlibbioc, ") ""))
6611 (substitute* "NAMESPACE"
6612 (("import\\(zlibbioc\\)") ""))
6613 #t)))))
6614 (inputs
6615 `(("zlib" ,zlib)))
6616 (propagated-inputs
6617 `(("r-biocgenerics" ,r-biocgenerics)
6618 ("r-biocparallel" ,r-biocparallel)
6619 ("r-biostrings" ,r-biostrings)
6620 ("r-bitops" ,r-bitops)
6621 ("r-genomeinfodb" ,r-genomeinfodb)
6622 ("r-genomicranges" ,r-genomicranges)
6623 ("r-iranges" ,r-iranges)
6624 ("r-s4vectors" ,r-s4vectors)
6625 ("r-xvector" ,r-xvector)))
6626 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6627 (synopsis "Interface to samtools, bcftools, and tabix")
6628 (description
6629 "This package provides an interface to the 'samtools', 'bcftools', and
6630 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6631 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6632 files.")
6633 (license license:expat)))
6634
6635 (define-public r-summarizedexperiment
6636 (package
6637 (name "r-summarizedexperiment")
6638 (version "1.4.0")
6639 (source (origin
6640 (method url-fetch)
6641 (uri (bioconductor-uri "SummarizedExperiment" version))
6642 (sha256
6643 (base32
6644 "1kbj8sg2ik9f8d6g95wz0py62jldg01qy5rsdpg1cxw95nf7dzi3"))))
6645 (properties
6646 `((upstream-name . "SummarizedExperiment")))
6647 (build-system r-build-system)
6648 (propagated-inputs
6649 `(("r-biobase" ,r-biobase)
6650 ("r-biocgenerics" ,r-biocgenerics)
6651 ("r-genomeinfodb" ,r-genomeinfodb)
6652 ("r-genomicranges" ,r-genomicranges)
6653 ("r-iranges" ,r-iranges)
6654 ("r-s4vectors" ,r-s4vectors)))
6655 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
6656 (synopsis "Container for representing genomic ranges by sample")
6657 (description
6658 "The SummarizedExperiment container contains one or more assays, each
6659 represented by a matrix-like object of numeric or other mode. The rows
6660 typically represent genomic ranges of interest and the columns represent
6661 samples.")
6662 (license license:artistic2.0)))
6663
6664 (define-public r-genomicalignments
6665 (package
6666 (name "r-genomicalignments")
6667 (version "1.10.0")
6668 (source (origin
6669 (method url-fetch)
6670 (uri (bioconductor-uri "GenomicAlignments" version))
6671 (sha256
6672 (base32
6673 "11vb0a0zd36i4yhg4mfijv787v0nihn6pkjj6q7rfy19gwy61xlc"))))
6674 (properties
6675 `((upstream-name . "GenomicAlignments")))
6676 (build-system r-build-system)
6677 (propagated-inputs
6678 `(("r-biocgenerics" ,r-biocgenerics)
6679 ("r-biocparallel" ,r-biocparallel)
6680 ("r-biostrings" ,r-biostrings)
6681 ("r-genomeinfodb" ,r-genomeinfodb)
6682 ("r-genomicranges" ,r-genomicranges)
6683 ("r-iranges" ,r-iranges)
6684 ("r-rsamtools" ,r-rsamtools)
6685 ("r-s4vectors" ,r-s4vectors)
6686 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6687 (home-page "http://bioconductor.org/packages/GenomicAlignments")
6688 (synopsis "Representation and manipulation of short genomic alignments")
6689 (description
6690 "This package provides efficient containers for storing and manipulating
6691 short genomic alignments (typically obtained by aligning short reads to a
6692 reference genome). This includes read counting, computing the coverage,
6693 junction detection, and working with the nucleotide content of the
6694 alignments.")
6695 (license license:artistic2.0)))
6696
6697 (define-public r-rtracklayer
6698 (package
6699 (name "r-rtracklayer")
6700 (version "1.34.1")
6701 (source (origin
6702 (method url-fetch)
6703 (uri (bioconductor-uri "rtracklayer" version))
6704 (sha256
6705 (base32
6706 "0x59k2fd0iaqi93gy6bm58p2j2z90z1b7a6w5b4c098y98n096rc"))))
6707 (build-system r-build-system)
6708 (arguments
6709 `(#:phases
6710 (modify-phases %standard-phases
6711 (add-after 'unpack 'use-system-zlib
6712 (lambda _
6713 (substitute* "DESCRIPTION"
6714 (("zlibbioc, ") ""))
6715 (substitute* "NAMESPACE"
6716 (("import\\(zlibbioc\\)") ""))
6717 #t)))))
6718 (inputs
6719 `(("zlib" ,zlib)))
6720 (propagated-inputs
6721 `(("r-biocgenerics" ,r-biocgenerics)
6722 ("r-biostrings" ,r-biostrings)
6723 ("r-genomeinfodb" ,r-genomeinfodb)
6724 ("r-genomicalignments" ,r-genomicalignments)
6725 ("r-genomicranges" ,r-genomicranges)
6726 ("r-iranges" ,r-iranges)
6727 ("r-rcurl" ,r-rcurl)
6728 ("r-rsamtools" ,r-rsamtools)
6729 ("r-s4vectors" ,r-s4vectors)
6730 ("r-xml" ,r-xml)
6731 ("r-xvector" ,r-xvector)))
6732 (home-page "http://bioconductor.org/packages/rtracklayer")
6733 (synopsis "R interface to genome browsers and their annotation tracks")
6734 (description
6735 "rtracklayer is an extensible framework for interacting with multiple
6736 genome browsers (currently UCSC built-in) and manipulating annotation tracks
6737 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
6738 built-in). The user may export/import tracks to/from the supported browsers,
6739 as well as query and modify the browser state, such as the current viewport.")
6740 (license license:artistic2.0)))
6741
6742 (define-public r-genomicfeatures
6743 (package
6744 (name "r-genomicfeatures")
6745 (version "1.26.2")
6746 (source (origin
6747 (method url-fetch)
6748 (uri (bioconductor-uri "GenomicFeatures" version))
6749 (sha256
6750 (base32
6751 "1ybi6r3bax07wlv2qcd34y5qjdvcqcfayfvlrjc39ifrkk65wv4f"))))
6752 (properties
6753 `((upstream-name . "GenomicFeatures")))
6754 (build-system r-build-system)
6755 (propagated-inputs
6756 `(("r-annotationdbi" ,r-annotationdbi)
6757 ("r-biobase" ,r-biobase)
6758 ("r-biocgenerics" ,r-biocgenerics)
6759 ("r-biomart" ,r-biomart)
6760 ("r-biostrings" ,r-biostrings)
6761 ("r-dbi" ,r-dbi)
6762 ("r-genomeinfodb" ,r-genomeinfodb)
6763 ("r-genomicranges" ,r-genomicranges)
6764 ("r-iranges" ,r-iranges)
6765 ("r-rcurl" ,r-rcurl)
6766 ("r-rsqlite" ,r-rsqlite)
6767 ("r-rtracklayer" ,r-rtracklayer)
6768 ("r-s4vectors" ,r-s4vectors)
6769 ("r-xvector" ,r-xvector)))
6770 (home-page "http://bioconductor.org/packages/GenomicFeatures")
6771 (synopsis "Tools for working with transcript centric annotations")
6772 (description
6773 "This package provides a set of tools and methods for making and
6774 manipulating transcript centric annotations. With these tools the user can
6775 easily download the genomic locations of the transcripts, exons and cds of a
6776 given organism, from either the UCSC Genome Browser or a BioMart
6777 database (more sources will be supported in the future). This information is
6778 then stored in a local database that keeps track of the relationship between
6779 transcripts, exons, cds and genes. Flexible methods are provided for
6780 extracting the desired features in a convenient format.")
6781 (license license:artistic2.0)))
6782
6783 (define-public r-go-db
6784 (package
6785 (name "r-go-db")
6786 (version "3.4.0")
6787 (source (origin
6788 (method url-fetch)
6789 (uri (string-append "http://www.bioconductor.org/packages/"
6790 "release/data/annotation/src/contrib/GO.db_"
6791 version ".tar.gz"))
6792 (sha256
6793 (base32
6794 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
6795 (properties
6796 `((upstream-name . "GO.db")))
6797 (build-system r-build-system)
6798 (propagated-inputs
6799 `(("r-annotationdbi" ,r-annotationdbi)))
6800 (home-page "http://bioconductor.org/packages/GO.db")
6801 (synopsis "Annotation maps describing the entire Gene Ontology")
6802 (description
6803 "The purpose of this GO.db annotation package is to provide detailed
6804 information about the latest version of the Gene Ontologies.")
6805 (license license:artistic2.0)))
6806
6807 (define-public r-graph
6808 (package
6809 (name "r-graph")
6810 (version "1.52.0")
6811 (source (origin
6812 (method url-fetch)
6813 (uri (bioconductor-uri "graph" version))
6814 (sha256
6815 (base32
6816 "0g3dk5vsdp489fmyg8mifczmzgqrjlakkkr8i96dj15gghp3l135"))))
6817 (build-system r-build-system)
6818 (propagated-inputs
6819 `(("r-biocgenerics" ,r-biocgenerics)))
6820 (home-page "http://bioconductor.org/packages/graph")
6821 (synopsis "Handle graph data structures in R")
6822 (description
6823 "This package implements some simple graph handling capabilities for R.")
6824 (license license:artistic2.0)))
6825
6826 (define-public r-topgo
6827 (package
6828 (name "r-topgo")
6829 (version "2.26.0")
6830 (source (origin
6831 (method url-fetch)
6832 (uri (bioconductor-uri "topGO" version))
6833 (sha256
6834 (base32
6835 "0j6sgvam4lk9348ag6pypcbkv93x4fk0di8ivhr23mz2s2yqzwrx"))))
6836 (properties
6837 `((upstream-name . "topGO")))
6838 (build-system r-build-system)
6839 (propagated-inputs
6840 `(("r-annotationdbi" ,r-annotationdbi)
6841 ("r-dbi" ,r-dbi)
6842 ("r-biobase" ,r-biobase)
6843 ("r-biocgenerics" ,r-biocgenerics)
6844 ("r-go-db" ,r-go-db)
6845 ("r-matrixstats" ,r-matrixstats)
6846 ("r-graph" ,r-graph)
6847 ("r-sparsem" ,r-sparsem)))
6848 (home-page "http://bioconductor.org/packages/topGO")
6849 (synopsis "Enrichment analysis for gene ontology")
6850 (description
6851 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
6852 terms while accounting for the topology of the GO graph. Different test
6853 statistics and different methods for eliminating local similarities and
6854 dependencies between GO terms can be implemented and applied.")
6855 ;; Any version of the LGPL applies.
6856 (license license:lgpl2.1+)))
6857
6858 (define-public r-bsgenome
6859 (package
6860 (name "r-bsgenome")
6861 (version "1.42.0")
6862 (source (origin
6863 (method url-fetch)
6864 (uri (bioconductor-uri "BSgenome" version))
6865 (sha256
6866 (base32
6867 "0hxwc02h5mzhkrk60d1jmlsfjf0ai9jxdc0128kj1sg4r2k1q94y"))))
6868 (properties
6869 `((upstream-name . "BSgenome")))
6870 (build-system r-build-system)
6871 (propagated-inputs
6872 `(("r-biocgenerics" ,r-biocgenerics)
6873 ("r-biostrings" ,r-biostrings)
6874 ("r-genomeinfodb" ,r-genomeinfodb)
6875 ("r-genomicranges" ,r-genomicranges)
6876 ("r-iranges" ,r-iranges)
6877 ("r-rsamtools" ,r-rsamtools)
6878 ("r-rtracklayer" ,r-rtracklayer)
6879 ("r-s4vectors" ,r-s4vectors)
6880 ("r-xvector" ,r-xvector)))
6881 (home-page "http://bioconductor.org/packages/BSgenome")
6882 (synopsis "Infrastructure for Biostrings-based genome data packages")
6883 (description
6884 "This package provides infrastructure shared by all Biostrings-based
6885 genome data packages and support for efficient SNP representation.")
6886 (license license:artistic2.0)))
6887
6888 (define-public r-impute
6889 (package
6890 (name "r-impute")
6891 (version "1.48.0")
6892 (source (origin
6893 (method url-fetch)
6894 (uri (bioconductor-uri "impute" version))
6895 (sha256
6896 (base32
6897 "1164zvnikbjd0ybdn9xwn520rlmdjd824vmhnl83zgv3v9lzp9bm"))))
6898 (inputs
6899 `(("gfortran" ,gfortran)))
6900 (build-system r-build-system)
6901 (home-page "http://bioconductor.org/packages/impute")
6902 (synopsis "Imputation for microarray data")
6903 (description
6904 "This package provides a function to impute missing gene expression
6905 microarray data, using nearest neighbor averaging.")
6906 (license license:gpl2+)))
6907
6908 (define-public r-seqpattern
6909 (package
6910 (name "r-seqpattern")
6911 (version "1.6.0")
6912 (source (origin
6913 (method url-fetch)
6914 (uri (bioconductor-uri "seqPattern" version))
6915 (sha256
6916 (base32
6917 "0lsa5pz36xapi3yiv78k3z286a5md5sm5g21pgfyg8zmhmkxr7y8"))))
6918 (properties
6919 `((upstream-name . "seqPattern")))
6920 (build-system r-build-system)
6921 (propagated-inputs
6922 `(("r-biostrings" ,r-biostrings)
6923 ("r-genomicranges" ,r-genomicranges)
6924 ("r-iranges" ,r-iranges)
6925 ("r-kernsmooth" ,r-kernsmooth)
6926 ("r-plotrix" ,r-plotrix)))
6927 (home-page "http://bioconductor.org/packages/seqPattern")
6928 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
6929 (description
6930 "This package provides tools to visualize oligonucleotide patterns and
6931 sequence motif occurrences across a large set of sequences centred at a common
6932 reference point and sorted by a user defined feature.")
6933 (license license:gpl3+)))
6934
6935 (define-public r-genomation
6936 (package
6937 (name "r-genomation")
6938 (version "1.6.0")
6939 (source (origin
6940 (method url-fetch)
6941 (uri (bioconductor-uri "genomation" version))
6942 (sha256
6943 (base32
6944 "1m4mz7wihj8yqivwkzw68div8ybk4rjsai3ffki7xp7sh21ax03y"))))
6945 (build-system r-build-system)
6946 (propagated-inputs
6947 `(("r-biostrings" ,r-biostrings)
6948 ("r-bsgenome" ,r-bsgenome)
6949 ("r-data-table" ,r-data-table)
6950 ("r-genomeinfodb" ,r-genomeinfodb)
6951 ("r-genomicalignments" ,r-genomicalignments)
6952 ("r-genomicranges" ,r-genomicranges)
6953 ("r-ggplot2" ,r-ggplot2)
6954 ("r-gridbase" ,r-gridbase)
6955 ("r-impute" ,r-impute)
6956 ("r-iranges" ,r-iranges)
6957 ("r-matrixstats" ,r-matrixstats)
6958 ("r-plotrix" ,r-plotrix)
6959 ("r-plyr" ,r-plyr)
6960 ("r-rcpp" ,r-rcpp)
6961 ("r-readr" ,r-readr)
6962 ("r-reshape2" ,r-reshape2)
6963 ("r-rhtslib" ,r-rhtslib)
6964 ("r-rsamtools" ,r-rsamtools)
6965 ("r-rtracklayer" ,r-rtracklayer)
6966 ("r-runit" ,r-runit)
6967 ("r-s4vectors" ,r-s4vectors)
6968 ("r-seqpattern" ,r-seqpattern)))
6969 (inputs
6970 `(("zlib" ,zlib)))
6971 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
6972 (synopsis "Summary, annotation and visualization of genomic data")
6973 (description
6974 "This package provides a package for summary and annotation of genomic
6975 intervals. Users can visualize and quantify genomic intervals over
6976 pre-defined functional regions, such as promoters, exons, introns, etc. The
6977 genomic intervals represent regions with a defined chromosome position, which
6978 may be associated with a score, such as aligned reads from HT-seq experiments,
6979 TF binding sites, methylation scores, etc. The package can use any tabular
6980 genomic feature data as long as it has minimal information on the locations of
6981 genomic intervals. In addition, it can use BAM or BigWig files as input.")
6982 (license license:artistic2.0)))
6983
6984 (define-public r-genomationdata
6985 (package
6986 (name "r-genomationdata")
6987 (version "1.6.0")
6988 (source (origin
6989 (method url-fetch)
6990 ;; We cannot use bioconductor-uri here because this tarball is
6991 ;; located under "data/annotation/" instead of "bioc/".
6992 (uri (string-append "https://bioconductor.org/packages/"
6993 "release/data/experiment/src/contrib/"
6994 "genomationData_" version ".tar.gz"))
6995 (sha256
6996 (base32
6997 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
6998 (build-system r-build-system)
6999 ;; As this package provides little more than large data files, it doesn't
7000 ;; make sense to build substitutes.
7001 (arguments `(#:substitutable? #f))
7002 (native-inputs
7003 `(("r-knitr" ,r-knitr)))
7004 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7005 (synopsis "Experimental data for use with the genomation package")
7006 (description
7007 "This package contains experimental genetic data for use with the
7008 genomation package. Included are Chip Seq, Methylation and Cage data,
7009 downloaded from Encode.")
7010 (license license:gpl3+)))
7011
7012 (define-public r-org-hs-eg-db
7013 (package
7014 (name "r-org-hs-eg-db")
7015 (version "3.4.0")
7016 (source (origin
7017 (method url-fetch)
7018 ;; We cannot use bioconductor-uri here because this tarball is
7019 ;; located under "data/annotation/" instead of "bioc/".
7020 (uri (string-append "http://www.bioconductor.org/packages/"
7021 "release/data/annotation/src/contrib/"
7022 "org.Hs.eg.db_" version ".tar.gz"))
7023 (sha256
7024 (base32
7025 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7026 (properties
7027 `((upstream-name . "org.Hs.eg.db")))
7028 (build-system r-build-system)
7029 (propagated-inputs
7030 `(("r-annotationdbi" ,r-annotationdbi)))
7031 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
7032 (synopsis "Genome wide annotation for Human")
7033 (description
7034 "This package provides mappings from Entrez gene identifiers to various
7035 annotations for the human genome.")
7036 (license license:artistic2.0)))
7037
7038 (define-public r-org-ce-eg-db
7039 (package
7040 (name "r-org-ce-eg-db")
7041 (version "3.4.0")
7042 (source (origin
7043 (method url-fetch)
7044 ;; We cannot use bioconductor-uri here because this tarball is
7045 ;; located under "data/annotation/" instead of "bioc/".
7046 (uri (string-append "http://www.bioconductor.org/packages/"
7047 "release/data/annotation/src/contrib/"
7048 "org.Ce.eg.db_" version ".tar.gz"))
7049 (sha256
7050 (base32
7051 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7052 (properties
7053 `((upstream-name . "org.Ce.eg.db")))
7054 (build-system r-build-system)
7055 (propagated-inputs
7056 `(("r-annotationdbi" ,r-annotationdbi)))
7057 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
7058 (synopsis "Genome wide annotation for Worm")
7059 (description
7060 "This package provides mappings from Entrez gene identifiers to various
7061 annotations for the genome of the model worm Caenorhabditis elegans.")
7062 (license license:artistic2.0)))
7063
7064 (define-public r-org-dm-eg-db
7065 (package
7066 (name "r-org-dm-eg-db")
7067 (version "3.4.0")
7068 (source (origin
7069 (method url-fetch)
7070 ;; We cannot use bioconductor-uri here because this tarball is
7071 ;; located under "data/annotation/" instead of "bioc/".
7072 (uri (string-append "http://www.bioconductor.org/packages/"
7073 "release/data/annotation/src/contrib/"
7074 "org.Dm.eg.db_" version ".tar.gz"))
7075 (sha256
7076 (base32
7077 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7078 (properties
7079 `((upstream-name . "org.Dm.eg.db")))
7080 (build-system r-build-system)
7081 (propagated-inputs
7082 `(("r-annotationdbi" ,r-annotationdbi)))
7083 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
7084 (synopsis "Genome wide annotation for Fly")
7085 (description
7086 "This package provides mappings from Entrez gene identifiers to various
7087 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7088 (license license:artistic2.0)))
7089
7090 (define-public r-org-mm-eg-db
7091 (package
7092 (name "r-org-mm-eg-db")
7093 (version "3.4.0")
7094 (source (origin
7095 (method url-fetch)
7096 ;; We cannot use bioconductor-uri here because this tarball is
7097 ;; located under "data/annotation/" instead of "bioc/".
7098 (uri (string-append "http://www.bioconductor.org/packages/"
7099 "release/data/annotation/src/contrib/"
7100 "org.Mm.eg.db_" version ".tar.gz"))
7101 (sha256
7102 (base32
7103 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7104 (properties
7105 `((upstream-name . "org.Mm.eg.db")))
7106 (build-system r-build-system)
7107 (propagated-inputs
7108 `(("r-annotationdbi" ,r-annotationdbi)))
7109 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
7110 (synopsis "Genome wide annotation for Mouse")
7111 (description
7112 "This package provides mappings from Entrez gene identifiers to various
7113 annotations for the genome of the model mouse Mus musculus.")
7114 (license license:artistic2.0)))
7115
7116 (define-public r-seqlogo
7117 (package
7118 (name "r-seqlogo")
7119 (version "1.40.0")
7120 (source
7121 (origin
7122 (method url-fetch)
7123 (uri (bioconductor-uri "seqLogo" version))
7124 (sha256
7125 (base32
7126 "18bajdl75h3039559d81rgllqqvnq8ygsfxfx081xphxs0v6xggy"))))
7127 (properties `((upstream-name . "seqLogo")))
7128 (build-system r-build-system)
7129 (home-page "http://bioconductor.org/packages/seqLogo")
7130 (synopsis "Sequence logos for DNA sequence alignments")
7131 (description
7132 "seqLogo takes the position weight matrix of a DNA sequence motif and
7133 plots the corresponding sequence logo as introduced by Schneider and
7134 Stephens (1990).")
7135 (license license:lgpl2.0+)))
7136
7137 (define-public r-bsgenome-hsapiens-ucsc-hg19
7138 (package
7139 (name "r-bsgenome-hsapiens-ucsc-hg19")
7140 (version "1.4.0")
7141 (source (origin
7142 (method url-fetch)
7143 ;; We cannot use bioconductor-uri here because this tarball is
7144 ;; located under "data/annotation/" instead of "bioc/".
7145 (uri (string-append "http://www.bioconductor.org/packages/"
7146 "release/data/annotation/src/contrib/"
7147 "BSgenome.Hsapiens.UCSC.hg19_"
7148 version ".tar.gz"))
7149 (sha256
7150 (base32
7151 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7152 (properties
7153 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7154 (build-system r-build-system)
7155 ;; As this package provides little more than a very large data file it
7156 ;; doesn't make sense to build substitutes.
7157 (arguments `(#:substitutable? #f))
7158 (propagated-inputs
7159 `(("r-bsgenome" ,r-bsgenome)))
7160 (home-page
7161 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7162 (synopsis "Full genome sequences for Homo sapiens")
7163 (description
7164 "This package provides full genome sequences for Homo sapiens as provided
7165 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7166 (license license:artistic2.0)))
7167
7168 (define-public r-bsgenome-mmusculus-ucsc-mm9
7169 (package
7170 (name "r-bsgenome-mmusculus-ucsc-mm9")
7171 (version "1.4.0")
7172 (source (origin
7173 (method url-fetch)
7174 ;; We cannot use bioconductor-uri here because this tarball is
7175 ;; located under "data/annotation/" instead of "bioc/".
7176 (uri (string-append "http://www.bioconductor.org/packages/"
7177 "release/data/annotation/src/contrib/"
7178 "BSgenome.Mmusculus.UCSC.mm9_"
7179 version ".tar.gz"))
7180 (sha256
7181 (base32
7182 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7183 (properties
7184 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7185 (build-system r-build-system)
7186 ;; As this package provides little more than a very large data file it
7187 ;; doesn't make sense to build substitutes.
7188 (arguments `(#:substitutable? #f))
7189 (propagated-inputs
7190 `(("r-bsgenome" ,r-bsgenome)))
7191 (home-page
7192 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7193 (synopsis "Full genome sequences for Mouse")
7194 (description
7195 "This package provides full genome sequences for Mus musculus (Mouse) as
7196 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7197 (license license:artistic2.0)))
7198
7199 (define-public r-bsgenome-mmusculus-ucsc-mm10
7200 (package
7201 (name "r-bsgenome-mmusculus-ucsc-mm10")
7202 (version "1.4.0")
7203 (source (origin
7204 (method url-fetch)
7205 ;; We cannot use bioconductor-uri here because this tarball is
7206 ;; located under "data/annotation/" instead of "bioc/".
7207 (uri (string-append "http://www.bioconductor.org/packages/"
7208 "release/data/annotation/src/contrib/"
7209 "BSgenome.Mmusculus.UCSC.mm10_"
7210 version ".tar.gz"))
7211 (sha256
7212 (base32
7213 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7214 (properties
7215 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7216 (build-system r-build-system)
7217 ;; As this package provides little more than a very large data file it
7218 ;; doesn't make sense to build substitutes.
7219 (arguments `(#:substitutable? #f))
7220 (propagated-inputs
7221 `(("r-bsgenome" ,r-bsgenome)))
7222 (home-page
7223 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7224 (synopsis "Full genome sequences for Mouse")
7225 (description
7226 "This package provides full genome sequences for Mus
7227 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7228 in Biostrings objects.")
7229 (license license:artistic2.0)))
7230
7231 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7232 (package
7233 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7234 (version "3.4.0")
7235 (source (origin
7236 (method url-fetch)
7237 ;; We cannot use bioconductor-uri here because this tarball is
7238 ;; located under "data/annotation/" instead of "bioc/".
7239 (uri (string-append "http://www.bioconductor.org/packages/"
7240 "release/data/annotation/src/contrib/"
7241 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7242 version ".tar.gz"))
7243 (sha256
7244 (base32
7245 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7246 (properties
7247 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7248 (build-system r-build-system)
7249 ;; As this package provides little more than a very large data file it
7250 ;; doesn't make sense to build substitutes.
7251 (arguments `(#:substitutable? #f))
7252 (propagated-inputs
7253 `(("r-bsgenome" ,r-bsgenome)
7254 ("r-genomicfeatures" ,r-genomicfeatures)
7255 ("r-annotationdbi" ,r-annotationdbi)))
7256 (home-page
7257 "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7258 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7259 (description
7260 "This package loads a TxDb object, which is an R interface to
7261 prefabricated databases contained in this package. This package provides
7262 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7263 based on the knownGene track.")
7264 (license license:artistic2.0)))
7265
7266 (define-public r-bsgenome-celegans-ucsc-ce6
7267 (package
7268 (name "r-bsgenome-celegans-ucsc-ce6")
7269 (version "1.4.0")
7270 (source (origin
7271 (method url-fetch)
7272 ;; We cannot use bioconductor-uri here because this tarball is
7273 ;; located under "data/annotation/" instead of "bioc/".
7274 (uri (string-append "http://www.bioconductor.org/packages/"
7275 "release/data/annotation/src/contrib/"
7276 "BSgenome.Celegans.UCSC.ce6_"
7277 version ".tar.gz"))
7278 (sha256
7279 (base32
7280 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7281 (properties
7282 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7283 (build-system r-build-system)
7284 ;; As this package provides little more than a very large data file it
7285 ;; doesn't make sense to build substitutes.
7286 (arguments `(#:substitutable? #f))
7287 (propagated-inputs
7288 `(("r-bsgenome" ,r-bsgenome)))
7289 (home-page
7290 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7291 (synopsis "Full genome sequences for Worm")
7292 (description
7293 "This package provides full genome sequences for Caenorhabditis
7294 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7295 objects.")
7296 (license license:artistic2.0)))
7297
7298 (define-public r-bsgenome-celegans-ucsc-ce10
7299 (package
7300 (name "r-bsgenome-celegans-ucsc-ce10")
7301 (version "1.4.0")
7302 (source (origin
7303 (method url-fetch)
7304 ;; We cannot use bioconductor-uri here because this tarball is
7305 ;; located under "data/annotation/" instead of "bioc/".
7306 (uri (string-append "http://www.bioconductor.org/packages/"
7307 "release/data/annotation/src/contrib/"
7308 "BSgenome.Celegans.UCSC.ce10_"
7309 version ".tar.gz"))
7310 (sha256
7311 (base32
7312 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7313 (properties
7314 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7315 (build-system r-build-system)
7316 ;; As this package provides little more than a very large data file it
7317 ;; doesn't make sense to build substitutes.
7318 (arguments `(#:substitutable? #f))
7319 (propagated-inputs
7320 `(("r-bsgenome" ,r-bsgenome)))
7321 (home-page
7322 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7323 (synopsis "Full genome sequences for Worm")
7324 (description
7325 "This package provides full genome sequences for Caenorhabditis
7326 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7327 objects.")
7328 (license license:artistic2.0)))
7329
7330 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7331 (package
7332 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7333 (version "1.4.0")
7334 (source (origin
7335 (method url-fetch)
7336 ;; We cannot use bioconductor-uri here because this tarball is
7337 ;; located under "data/annotation/" instead of "bioc/".
7338 (uri (string-append "http://www.bioconductor.org/packages/"
7339 "release/data/annotation/src/contrib/"
7340 "BSgenome.Dmelanogaster.UCSC.dm3_"
7341 version ".tar.gz"))
7342 (sha256
7343 (base32
7344 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7345 (properties
7346 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7347 (build-system r-build-system)
7348 ;; As this package provides little more than a very large data file it
7349 ;; doesn't make sense to build substitutes.
7350 (arguments `(#:substitutable? #f))
7351 (propagated-inputs
7352 `(("r-bsgenome" ,r-bsgenome)))
7353 (home-page
7354 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7355 (synopsis "Full genome sequences for Fly")
7356 (description
7357 "This package provides full genome sequences for Drosophila
7358 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7359 Biostrings objects.")
7360 (license license:artistic2.0)))
7361
7362 (define-public r-motifrg
7363 (package
7364 (name "r-motifrg")
7365 (version "1.18.0")
7366 (source
7367 (origin
7368 (method url-fetch)
7369 (uri (bioconductor-uri "motifRG" version))
7370 (sha256
7371 (base32
7372 "1pa97aj6c5f3gx4bgriw110764dj3m9h104ddi8rv2bpy41yd98d"))))
7373 (properties `((upstream-name . "motifRG")))
7374 (build-system r-build-system)
7375 (propagated-inputs
7376 `(("r-biostrings" ,r-biostrings)
7377 ("r-bsgenome" ,r-bsgenome)
7378 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7379 ("r-iranges" ,r-iranges)
7380 ("r-seqlogo" ,r-seqlogo)
7381 ("r-xvector" ,r-xvector)))
7382 (home-page "http://bioconductor.org/packages/motifRG")
7383 (synopsis "Discover motifs in high throughput sequencing data")
7384 (description
7385 "This package provides tools for discriminative motif discovery in high
7386 throughput genetic sequencing data sets using regression methods.")
7387 (license license:artistic2.0)))
7388
7389 (define-public r-qtl
7390 (package
7391 (name "r-qtl")
7392 (version "1.40-8")
7393 (source
7394 (origin
7395 (method url-fetch)
7396 (uri (string-append "mirror://cran/src/contrib/qtl_"
7397 version ".tar.gz"))
7398 (sha256
7399 (base32
7400 "05bj1x2ry0i7yqiydlswb3d2h4pxg70z8w1072az1mrv1m54k8sp"))))
7401 (build-system r-build-system)
7402 (home-page "http://rqtl.org/")
7403 (synopsis "R package for analyzing QTL experiments in genetics")
7404 (description "R/qtl is an extension library for the R statistics
7405 system. It is used to analyze experimental crosses for identifying
7406 genes contributing to variation in quantitative traits (so-called
7407 quantitative trait loci, QTLs).
7408
7409 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7410 identify genotyping errors, and to perform single-QTL and two-QTL,
7411 two-dimensional genome scans.")
7412 (license license:gpl3)))
7413
7414 (define-public r-zlibbioc
7415 (package
7416 (name "r-zlibbioc")
7417 (version "1.20.0")
7418 (source (origin
7419 (method url-fetch)
7420 (uri (bioconductor-uri "zlibbioc" version))
7421 (sha256
7422 (base32
7423 "0hbk90q5hl0fycfvy5nxxa4hxgglag9lzp7i0fg849bqygg5nbyq"))))
7424 (properties
7425 `((upstream-name . "zlibbioc")))
7426 (build-system r-build-system)
7427 (home-page "https://bioconductor.org/packages/zlibbioc")
7428 (synopsis "Provider for zlib-1.2.5 to R packages")
7429 (description "This package uses the source code of zlib-1.2.5 to create
7430 libraries for systems that do not have these available via other means.")
7431 (license license:artistic2.0)))
7432
7433 (define-public r-r4rna
7434 (package
7435 (name "r-r4rna")
7436 (version "0.1.4")
7437 (source
7438 (origin
7439 (method url-fetch)
7440 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7441 version ".tar.gz"))
7442 (sha256
7443 (base32
7444 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7445 (build-system r-build-system)
7446 (propagated-inputs
7447 `(("r-optparse" ,r-optparse)
7448 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7449 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7450 (synopsis "Analysis framework for RNA secondary structure")
7451 (description
7452 "The R4RNA package aims to be a general framework for the analysis of RNA
7453 secondary structure and comparative analysis in R.")
7454 (license license:gpl3+)))
7455
7456 (define-public r-rhtslib
7457 (package
7458 (name "r-rhtslib")
7459 (version "1.6.0")
7460 (source
7461 (origin
7462 (method url-fetch)
7463 (uri (bioconductor-uri "Rhtslib" version))
7464 (sha256
7465 (base32
7466 "1vk3ng61dhi3pbia1lp3gl3mlr3i1vb2lkq83qb53i9dzz128wh9"))))
7467 (properties `((upstream-name . "Rhtslib")))
7468 (build-system r-build-system)
7469 (propagated-inputs
7470 `(("r-zlibbioc" ,r-zlibbioc)))
7471 (inputs
7472 `(("zlib" ,zlib)))
7473 (native-inputs
7474 `(("autoconf" ,autoconf)))
7475 (home-page "https://github.com/nhayden/Rhtslib")
7476 (synopsis "High-throughput sequencing library as an R package")
7477 (description
7478 "This package provides the HTSlib C library for high-throughput
7479 nucleotide sequence analysis. The package is primarily useful to developers
7480 of other R packages who wish to make use of HTSlib.")
7481 (license license:lgpl2.0+)))
7482
7483 (define-public r-bamsignals
7484 (package
7485 (name "r-bamsignals")
7486 (version "1.6.0")
7487 (source
7488 (origin
7489 (method url-fetch)
7490 (uri (bioconductor-uri "bamsignals" version))
7491 (sha256
7492 (base32
7493 "1k42gvk5mgq4la1fp0in3an2zfdz69h6522jsqhmk0f6i75kg4mb"))))
7494 (build-system r-build-system)
7495 (propagated-inputs
7496 `(("r-biocgenerics" ,r-biocgenerics)
7497 ("r-genomicranges" ,r-genomicranges)
7498 ("r-iranges" ,r-iranges)
7499 ("r-rcpp" ,r-rcpp)
7500 ("r-rhtslib" ,r-rhtslib)
7501 ("r-zlibbioc" ,r-zlibbioc)))
7502 (inputs
7503 `(("zlib" ,zlib)))
7504 (home-page "http://bioconductor.org/packages/bamsignals")
7505 (synopsis "Extract read count signals from bam files")
7506 (description
7507 "This package allows to efficiently obtain count vectors from indexed bam
7508 files. It counts the number of nucleotide sequence reads in given genomic
7509 ranges and it computes reads profiles and coverage profiles. It also handles
7510 paired-end data.")
7511 (license license:gpl2+)))
7512
7513 (define-public r-rcas
7514 (package
7515 (name "r-rcas")
7516 (version "1.1.1")
7517 (source (origin
7518 (method url-fetch)
7519 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7520 version ".tar.gz"))
7521 (file-name (string-append name "-" version ".tar.gz"))
7522 (sha256
7523 (base32
7524 "1hd0r66556bxbdd82ksjklq7nfli36l4k6y88ic7kkg9873wa1nw"))))
7525 (build-system r-build-system)
7526 (native-inputs
7527 `(("r-knitr" ,r-knitr)
7528 ("r-testthat" ,r-testthat)
7529 ;; During vignette building knitr checks that "pandoc-citeproc"
7530 ;; is in the PATH.
7531 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7532 (propagated-inputs
7533 `(("r-data-table" ,r-data-table)
7534 ("r-biomart" ,r-biomart)
7535 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7536 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7537 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7538 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7539 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7540 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7541 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7542 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7543 ("r-topgo" ,r-topgo)
7544 ("r-dt" ,r-dt)
7545 ("r-plotly" ,r-plotly)
7546 ("r-plotrix" ,r-plotrix)
7547 ("r-motifrg" ,r-motifrg)
7548 ("r-genomation" ,r-genomation)
7549 ("r-genomicfeatures" ,r-genomicfeatures)
7550 ("r-rtracklayer" ,r-rtracklayer)
7551 ("r-rmarkdown" ,r-rmarkdown)))
7552 (synopsis "RNA-centric annotation system")
7553 (description
7554 "RCAS aims to be a standalone RNA-centric annotation system that provides
7555 intuitive reports and publication-ready graphics. This package provides the R
7556 library implementing most of the pipeline's features.")
7557 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7558 (license license:expat)))
7559
7560 (define-public rcas-web
7561 (package
7562 (name "rcas-web")
7563 (version "0.0.3")
7564 (source
7565 (origin
7566 (method url-fetch)
7567 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7568 "releases/download/v" version
7569 "/rcas-web-" version ".tar.gz"))
7570 (sha256
7571 (base32
7572 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7573 (build-system gnu-build-system)
7574 (arguments
7575 `(#:phases
7576 (modify-phases %standard-phases
7577 (add-after 'install 'wrap-executable
7578 (lambda* (#:key inputs outputs #:allow-other-keys)
7579 (let* ((out (assoc-ref outputs "out"))
7580 (json (assoc-ref inputs "guile-json"))
7581 (redis (assoc-ref inputs "guile-redis"))
7582 (path (string-append
7583 json "/share/guile/site/2.2:"
7584 redis "/share/guile/site/2.2")))
7585 (wrap-program (string-append out "/bin/rcas-web")
7586 `("GUILE_LOAD_PATH" ":" = (,path))
7587 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
7588 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
7589 #t)))))
7590 (inputs
7591 `(("r" ,r)
7592 ("r-rcas" ,r-rcas)
7593 ("guile-next" ,guile-next)
7594 ("guile-json" ,guile2.2-json)
7595 ("guile-redis" ,guile2.2-redis)))
7596 (native-inputs
7597 `(("pkg-config" ,pkg-config)))
7598 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
7599 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
7600 (description "This package provides a simple web interface for the
7601 @dfn{RNA-centric annotation system} (RCAS).")
7602 (license license:agpl3+)))
7603
7604 (define-public r-mutationalpatterns
7605 (package
7606 (name "r-mutationalpatterns")
7607 (version "1.0.0")
7608 (source
7609 (origin
7610 (method url-fetch)
7611 (uri (bioconductor-uri "MutationalPatterns" version))
7612 (sha256
7613 (base32
7614 "1a3c2bm0xx0q4gf98jiw74msmdf2fr8rbsdysd5ww9kqlzmsbr17"))))
7615 (build-system r-build-system)
7616 (propagated-inputs
7617 `(("r-biocgenerics" ,r-biocgenerics)
7618 ("r-biostrings" ,r-biostrings)
7619 ("r-genomicranges" ,r-genomicranges)
7620 ("r-genomeinfodb" ,r-genomeinfodb)
7621 ("r-ggplot2" ,r-ggplot2)
7622 ("r-gridextra" ,r-gridextra)
7623 ("r-iranges" ,r-iranges)
7624 ("r-nmf" ,r-nmf)
7625 ("r-plyr" ,r-plyr)
7626 ("r-pracma" ,r-pracma)
7627 ("r-reshape2" ,r-reshape2)
7628 ("r-summarizedexperiment" ,r-summarizedexperiment)
7629 ("r-variantannotation" ,r-variantannotation)))
7630 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
7631 (synopsis "Extract and visualize mutational patterns in genomic data")
7632 (description "This package provides an extensive toolset for the
7633 characterization and visualization of a wide range of mutational patterns
7634 in SNV base substitution data.")
7635 (license license:expat)))
7636
7637 (define-public r-wgcna
7638 (package
7639 (name "r-wgcna")
7640 (version "1.51")
7641 (source
7642 (origin
7643 (method url-fetch)
7644 (uri (cran-uri "WGCNA" version))
7645 (sha256
7646 (base32
7647 "0hzvnhw76vwg8bl8x368f0c5szpwb8323bmrb3bir93i5bmfjsxx"))))
7648 (properties `((upstream-name . "WGCNA")))
7649 (build-system r-build-system)
7650 (propagated-inputs
7651 `(("r-annotationdbi" ,r-annotationdbi)
7652 ("r-doparallel" ,r-doparallel)
7653 ("r-dynamictreecut" ,r-dynamictreecut)
7654 ("r-fastcluster" ,r-fastcluster)
7655 ("r-foreach" ,r-foreach)
7656 ("r-go-db" ,r-go-db)
7657 ("r-hmisc" ,r-hmisc)
7658 ("r-impute" ,r-impute)
7659 ("r-matrixstats" ,r-matrixstats)
7660 ("r-preprocesscore" ,r-preprocesscore)))
7661 (home-page
7662 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
7663 (synopsis "Weighted correlation network analysis")
7664 (description
7665 "This package provides functions necessary to perform Weighted
7666 Correlation Network Analysis on high-dimensional data. It includes functions
7667 for rudimentary data cleaning, construction and summarization of correlation
7668 networks, module identification and functions for relating both variables and
7669 modules to sample traits. It also includes a number of utility functions for
7670 data manipulation and visualization.")
7671 (license license:gpl2+)))
7672
7673 (define-public r-chipkernels
7674 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
7675 (revision "1"))
7676 (package
7677 (name "r-chipkernels")
7678 (version (string-append "1.1-" revision "." (string-take commit 9)))
7679 (source
7680 (origin
7681 (method git-fetch)
7682 (uri (git-reference
7683 (url "https://github.com/ManuSetty/ChIPKernels.git")
7684 (commit commit)))
7685 (file-name (string-append name "-" version))
7686 (sha256
7687 (base32
7688 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
7689 (build-system r-build-system)
7690 (propagated-inputs
7691 `(("r-iranges" ,r-iranges)
7692 ("r-xvector" ,r-xvector)
7693 ("r-biostrings" ,r-biostrings)
7694 ("r-bsgenome" ,r-bsgenome)
7695 ("r-gtools" ,r-gtools)
7696 ("r-genomicranges" ,r-genomicranges)
7697 ("r-sfsmisc" ,r-sfsmisc)
7698 ("r-kernlab" ,r-kernlab)
7699 ("r-s4vectors" ,r-s4vectors)
7700 ("r-biocgenerics" ,r-biocgenerics)))
7701 (home-page "https://github.com/ManuSetty/ChIPKernels")
7702 (synopsis "Build string kernels for DNA Sequence analysis")
7703 (description "ChIPKernels is an R package for building different string
7704 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
7705 must be built and this dictionary can be used for determining kernels for DNA
7706 Sequences.")
7707 (license license:gpl2+))))
7708
7709 (define-public r-seqgl
7710 (package
7711 (name "r-seqgl")
7712 (version "1.1.4")
7713 (source
7714 (origin
7715 (method url-fetch)
7716 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
7717 "archive/" version ".tar.gz"))
7718 (file-name (string-append name "-" version ".tar.gz"))
7719 (sha256
7720 (base32
7721 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
7722 (build-system r-build-system)
7723 (propagated-inputs
7724 `(("r-biostrings" ,r-biostrings)
7725 ("r-chipkernels" ,r-chipkernels)
7726 ("r-genomicranges" ,r-genomicranges)
7727 ("r-spams" ,r-spams)
7728 ("r-wgcna" ,r-wgcna)
7729 ("r-fastcluster" ,r-fastcluster)))
7730 (home-page "https://github.com/ManuSetty/SeqGL")
7731 (synopsis "Group lasso for Dnase/ChIP-seq data")
7732 (description "SeqGL is a group lasso based algorithm to extract
7733 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
7734 This package presents a method which uses group lasso to discriminate between
7735 bound and non bound genomic regions to accurately identify transcription
7736 factors bound at the specific regions.")
7737 (license license:gpl2+)))
7738
7739 (define-public r-gkmsvm
7740 (package
7741 (name "r-gkmsvm")
7742 (version "0.71.0")
7743 (source
7744 (origin
7745 (method url-fetch)
7746 (uri (cran-uri "gkmSVM" version))
7747 (sha256
7748 (base32
7749 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
7750 (properties `((upstream-name . "gkmSVM")))
7751 (build-system r-build-system)
7752 (propagated-inputs
7753 `(("r-biocgenerics" ,r-biocgenerics)
7754 ("r-biostrings" ,r-biostrings)
7755 ("r-genomeinfodb" ,r-genomeinfodb)
7756 ("r-genomicranges" ,r-genomicranges)
7757 ("r-iranges" ,r-iranges)
7758 ("r-kernlab" ,r-kernlab)
7759 ("r-rcpp" ,r-rcpp)
7760 ("r-rocr" ,r-rocr)
7761 ("r-rtracklayer" ,r-rtracklayer)
7762 ("r-s4vectors" ,r-s4vectors)
7763 ("r-seqinr" ,r-seqinr)))
7764 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
7765 (synopsis "Gapped-kmer support vector machine")
7766 (description
7767 "This R package provides tools for training gapped-kmer SVM classifiers
7768 for DNA and protein sequences. This package supports several sequence
7769 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
7770 (license license:gpl2+)))
7771
7772 (define-public emboss
7773 (package
7774 (name "emboss")
7775 (version "6.5.7")
7776 (source (origin
7777 (method url-fetch)
7778 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
7779 (version-major+minor version) ".0/"
7780 "EMBOSS-" version ".tar.gz"))
7781 (sha256
7782 (base32
7783 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
7784 (build-system gnu-build-system)
7785 (arguments
7786 `(#:configure-flags
7787 (list (string-append "--with-hpdf="
7788 (assoc-ref %build-inputs "libharu")))
7789 #:phases
7790 (modify-phases %standard-phases
7791 (add-after 'unpack 'fix-checks
7792 (lambda _
7793 ;; The PNGDRIVER tests check for the presence of libgd, libpng
7794 ;; and zlib, but assume that they are all found at the same
7795 ;; prefix.
7796 (substitute* "configure.in"
7797 (("CHECK_PNGDRIVER")
7798 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
7799 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
7800 AM_CONDITIONAL(AMPNG, true)"))
7801 #t))
7802 (add-after 'unpack 'disable-update-check
7803 (lambda _
7804 ;; At build time there is no connection to the Internet, so
7805 ;; looking for updates will not work.
7806 (substitute* "Makefile.am"
7807 (("\\$\\(bindir\\)/embossupdate") ""))
7808 #t))
7809 (add-before 'configure 'autogen
7810 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
7811 (inputs
7812 `(("perl" ,perl)
7813 ("libpng" ,libpng)
7814 ("gd" ,gd)
7815 ("libx11" ,libx11)
7816 ("libharu" ,libharu)
7817 ("zlib" ,zlib)))
7818 (native-inputs
7819 `(("autoconf" ,autoconf)
7820 ("automake" ,automake)
7821 ("libtool" ,libtool)
7822 ("pkg-config" ,pkg-config)))
7823 (home-page "http://emboss.sourceforge.net")
7824 (synopsis "Molecular biology analysis suite")
7825 (description "EMBOSS is the \"European Molecular Biology Open Software
7826 Suite\". EMBOSS is an analysis package specially developed for the needs of
7827 the molecular biology (e.g. EMBnet) user community. The software
7828 automatically copes with data in a variety of formats and even allows
7829 transparent retrieval of sequence data from the web. It also provides a
7830 number of libraries for the development of software in the field of molecular
7831 biology. EMBOSS also integrates a range of currently available packages and
7832 tools for sequence analysis into a seamless whole.")
7833 (license license:gpl2+)))
7834
7835 (define-public bits
7836 (let ((revision "1")
7837 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
7838 (package
7839 (name "bits")
7840 ;; The version is 2.13.0 even though no release archives have been
7841 ;; published as yet.
7842 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
7843 (source (origin
7844 (method git-fetch)
7845 (uri (git-reference
7846 (url "https://github.com/arq5x/bits.git")
7847 (commit commit)))
7848 (file-name (string-append name "-" version "-checkout"))
7849 (sha256
7850 (base32
7851 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
7852 (build-system gnu-build-system)
7853 (arguments
7854 `(#:tests? #f ;no tests included
7855 #:phases
7856 (modify-phases %standard-phases
7857 (delete 'configure)
7858 (add-after 'unpack 'remove-cuda
7859 (lambda _
7860 (substitute* "Makefile"
7861 ((".*_cuda") "")
7862 (("(bits_test_intersections) \\\\" _ match) match))
7863 #t))
7864 (replace 'install
7865 (lambda* (#:key outputs #:allow-other-keys)
7866 (copy-recursively
7867 "bin" (string-append (assoc-ref outputs "out") "/bin"))
7868 #t)))))
7869 (inputs
7870 `(("gsl" ,gsl)
7871 ("zlib" ,zlib)))
7872 (home-page "https://github.com/arq5x/bits")
7873 (synopsis "Implementation of binary interval search algorithm")
7874 (description "This package provides an implementation of the
7875 BITS (Binary Interval Search) algorithm, an approach to interval set
7876 intersection. It is especially suited for the comparison of diverse genomic
7877 datasets and the exploration of large datasets of genome
7878 intervals (e.g. genes, sequence alignments).")
7879 (license license:gpl2))))
7880
7881 (define-public piranha
7882 ;; There is no release tarball for the latest version. The latest commit is
7883 ;; older than one year at the time of this writing.
7884 (let ((revision "1")
7885 (commit "0466d364b71117d01e4471b74c514436cc281233"))
7886 (package
7887 (name "piranha")
7888 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
7889 (source (origin
7890 (method git-fetch)
7891 (uri (git-reference
7892 (url "https://github.com/smithlabcode/piranha.git")
7893 (commit commit)))
7894 (sha256
7895 (base32
7896 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
7897 (build-system gnu-build-system)
7898 (arguments
7899 `(#:test-target "test"
7900 #:phases
7901 (modify-phases %standard-phases
7902 (add-after 'unpack 'copy-smithlab-cpp
7903 (lambda* (#:key inputs #:allow-other-keys)
7904 (for-each (lambda (file)
7905 (install-file file "./src/smithlab_cpp/"))
7906 (find-files (assoc-ref inputs "smithlab-cpp")))
7907 #t))
7908 (add-after 'install 'install-to-store
7909 (lambda* (#:key outputs #:allow-other-keys)
7910 (let* ((out (assoc-ref outputs "out"))
7911 (bin (string-append out "/bin")))
7912 (for-each (lambda (file)
7913 (install-file file bin))
7914 (find-files "bin" ".*")))
7915 #t)))
7916 #:configure-flags
7917 (list (string-append "--with-bam_tools_headers="
7918 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
7919 (string-append "--with-bam_tools_library="
7920 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
7921 (inputs
7922 `(("bamtools" ,bamtools)
7923 ("samtools" ,samtools-0.1)
7924 ("gsl" ,gsl)
7925 ("smithlab-cpp"
7926 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
7927 (origin
7928 (method git-fetch)
7929 (uri (git-reference
7930 (url "https://github.com/smithlabcode/smithlab_cpp.git")
7931 (commit commit)))
7932 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
7933 (sha256
7934 (base32
7935 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
7936 (native-inputs
7937 `(("python" ,python-2)))
7938 (home-page "https://github.com/smithlabcode/piranha")
7939 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
7940 (description
7941 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
7942 RIP-seq experiments. It takes input in BED or BAM format and identifies
7943 regions of statistically significant read enrichment. Additional covariates
7944 may optionally be provided to further inform the peak-calling process.")
7945 (license license:gpl3+))))
7946
7947 (define-public pepr
7948 (package
7949 (name "pepr")
7950 (version "1.0.9")
7951 (source (origin
7952 (method url-fetch)
7953 (uri (string-append "https://pypi.python.org/packages/source/P"
7954 "/PePr/PePr-" version ".tar.gz"))
7955 (sha256
7956 (base32
7957 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
7958 (build-system python-build-system)
7959 (arguments
7960 `(#:python ,python-2 ; python2 only
7961 #:tests? #f)) ; no tests included
7962 (propagated-inputs
7963 `(("python2-numpy" ,python2-numpy)
7964 ("python2-scipy" ,python2-scipy)
7965 ("python2-pysam" ,python2-pysam)))
7966 (home-page "https://github.com/shawnzhangyx/PePr")
7967 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
7968 (description
7969 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
7970 that is primarily designed for data with biological replicates. It uses a
7971 negative binomial distribution to model the read counts among the samples in
7972 the same group, and look for consistent differences between ChIP and control
7973 group or two ChIP groups run under different conditions.")
7974 (license license:gpl3+)))
7975
7976 (define-public filevercmp
7977 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
7978 (package
7979 (name "filevercmp")
7980 (version (string-append "0-1." (string-take commit 7)))
7981 (source (origin
7982 (method url-fetch)
7983 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
7984 commit ".tar.gz"))
7985 (file-name (string-append name "-" version ".tar.gz"))
7986 (sha256
7987 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
7988 (build-system gnu-build-system)
7989 (arguments
7990 `(#:tests? #f ; There are no tests to run.
7991 #:phases
7992 (modify-phases %standard-phases
7993 (delete 'configure) ; There is no configure phase.
7994 (replace 'install
7995 (lambda* (#:key outputs #:allow-other-keys)
7996 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7997 (install-file "filevercmp" bin)))))))
7998 (home-page "https://github.com/ekg/filevercmp")
7999 (synopsis "This program compares version strings")
8000 (description "This program compares version strings. It intends to be a
8001 replacement for strverscmp.")
8002 (license license:gpl3+))))
8003
8004 (define-public multiqc
8005 (package
8006 (name "multiqc")
8007 (version "0.9")
8008 (source
8009 (origin
8010 (method url-fetch)
8011 (uri (pypi-uri "multiqc" version))
8012 (sha256
8013 (base32
8014 "12gs1jw2jrxrij529rnl5kaqxfcqn15yzcsggxkfhdx634ml0cny"))
8015 (patches (search-patches "multiqc-fix-git-subprocess-error.patch"))))
8016 (build-system python-build-system)
8017 (arguments
8018 ;; Tests are to be introduced in the next version, see
8019 ;; https://github.com/ewels/MultiQC/issues/376
8020 `(#:tests? #f))
8021 (propagated-inputs
8022 `(("python-jinja2" ,python-jinja2)
8023 ("python-simplejson" ,python-simplejson)
8024 ("python-pyyaml" ,python-pyyaml)
8025 ("python-click" ,python-click)
8026 ("python-matplotlib" ,python-matplotlib)
8027 ("python-numpy" ,python-numpy)
8028 ;; MultQC checks for the presence of nose at runtime.
8029 ("python-nose" ,python-nose)))
8030 (home-page "http://multiqc.info")
8031 (synopsis "Aggregate bioinformatics analysis reports")
8032 (description
8033 "MultiQC is a tool to aggregate bioinformatics results across many
8034 samples into a single report. It contains modules for a large number of
8035 common bioinformatics tools.")
8036 (license license:gpl3)))
8037
8038 (define-public r-chipseq
8039 (package
8040 (name "r-chipseq")
8041 (version "1.24.0")
8042 (source
8043 (origin
8044 (method url-fetch)
8045 (uri (bioconductor-uri "chipseq" version))
8046 (sha256
8047 (base32
8048 "115ayp82rs99iaswrx45skw1i5iacgwzz5k8rzijbp5qic0554n0"))))
8049 (build-system r-build-system)
8050 (propagated-inputs
8051 `(("r-biocgenerics" ,r-biocgenerics)
8052 ("r-genomicranges" ,r-genomicranges)
8053 ("r-iranges" ,r-iranges)
8054 ("r-s4vectors" ,r-s4vectors)
8055 ("r-shortread" ,r-shortread)))
8056 (home-page "http://bioconductor.org/packages/chipseq")
8057 (synopsis "Package for analyzing ChIPseq data")
8058 (description
8059 "This package provides tools for processing short read data from ChIPseq
8060 experiments.")
8061 (license license:artistic2.0)))
8062
8063 (define-public r-copyhelper
8064 (package
8065 (name "r-copyhelper")
8066 (version "1.6.0")
8067 (source
8068 (origin
8069 (method url-fetch)
8070 (uri (string-append "http://bioconductor.org/packages/release/"
8071 "data/experiment/src/contrib/CopyhelpeR_"
8072 version ".tar.gz"))
8073 (sha256
8074 (base32
8075 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8076 (properties `((upstream-name . "CopyhelpeR")))
8077 (build-system r-build-system)
8078 (home-page "http://bioconductor.org/packages/CopyhelpeR/")
8079 (synopsis "Helper files for CopywriteR")
8080 (description
8081 "This package contains the helper files that are required to run the
8082 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8083 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8084 mm10. In addition, it contains a blacklist filter to remove regions that
8085 display copy number variation. Files are stored as GRanges objects from the
8086 GenomicRanges Bioconductor package.")
8087 (license license:gpl2)))
8088
8089 (define-public r-copywriter
8090 (package
8091 (name "r-copywriter")
8092 (version "2.6.0")
8093 (source
8094 (origin
8095 (method url-fetch)
8096 (uri (bioconductor-uri "CopywriteR" version))
8097 (sha256
8098 (base32
8099 "1bwwnsyk7cpgwkagsnn5mv6fv233b0rkhjvbadrh70h8m4anawfj"))))
8100 (properties `((upstream-name . "CopywriteR")))
8101 (build-system r-build-system)
8102 (propagated-inputs
8103 `(("r-biocparallel" ,r-biocparallel)
8104 ("r-chipseq" ,r-chipseq)
8105 ("r-copyhelper" ,r-copyhelper)
8106 ("r-data-table" ,r-data-table)
8107 ("r-dnacopy" ,r-dnacopy)
8108 ("r-futile-logger" ,r-futile-logger)
8109 ("r-genomeinfodb" ,r-genomeinfodb)
8110 ("r-genomicalignments" ,r-genomicalignments)
8111 ("r-genomicranges" ,r-genomicranges)
8112 ("r-gtools" ,r-gtools)
8113 ("r-iranges" ,r-iranges)
8114 ("r-matrixstats" ,r-matrixstats)
8115 ("r-rsamtools" ,r-rsamtools)
8116 ("r-s4vectors" ,r-s4vectors)))
8117 (home-page "https://github.com/PeeperLab/CopywriteR")
8118 (synopsis "Copy number information from targeted sequencing")
8119 (description
8120 "CopywriteR extracts DNA copy number information from targeted sequencing
8121 by utilizing off-target reads. It allows for extracting uniformly distributed
8122 copy number information, can be used without reference, and can be applied to
8123 sequencing data obtained from various techniques including chromatin
8124 immunoprecipitation and target enrichment on small gene panels. Thereby,
8125 CopywriteR constitutes a widely applicable alternative to available copy
8126 number detection tools.")
8127 (license license:gpl2)))
8128
8129 (define-public r-sva
8130 (package
8131 (name "r-sva")
8132 (version "3.22.0")
8133 (source
8134 (origin
8135 (method url-fetch)
8136 (uri (bioconductor-uri "sva" version))
8137 (sha256
8138 (base32
8139 "1wc1fjm6dzlsqqagm43y57w8jh8nsh0r0m8z1p6ximcb5gxqh7hn"))))
8140 (build-system r-build-system)
8141 (propagated-inputs
8142 `(("r-genefilter" ,r-genefilter)))
8143 (home-page "http://bioconductor.org/packages/sva")
8144 (synopsis "Surrogate variable analysis")
8145 (description
8146 "This package contains functions for removing batch effects and other
8147 unwanted variation in high-throughput experiment. It also contains functions
8148 for identifying and building surrogate variables for high-dimensional data
8149 sets. Surrogate variables are covariates constructed directly from
8150 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8151 imaging data that can be used in subsequent analyses to adjust for unknown,
8152 unmodeled, or latent sources of noise.")
8153 (license license:artistic2.0)))
8154
8155 (define-public r-seqminer
8156 (package
8157 (name "r-seqminer")
8158 (version "5.3")
8159 (source
8160 (origin
8161 (method url-fetch)
8162 (uri (cran-uri "seqminer" version))
8163 (sha256
8164 (base32
8165 "0y0gc5lws3hdxasjb84m532ics6imb7qg9sl1zy62h503jh4j9gw"))))
8166 (build-system r-build-system)
8167 (inputs
8168 `(("zlib" ,zlib)))
8169 (home-page "http://seqminer.genomic.codes")
8170 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8171 (description
8172 "This package provides tools to integrate nucleotide sequencing
8173 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8174 ;; Any version of the GPL is acceptable
8175 (license (list license:gpl2+ license:gpl3+))))
8176
8177 (define-public r-raremetals2
8178 (package
8179 (name "r-raremetals2")
8180 (version "0.1")
8181 (source
8182 (origin
8183 (method url-fetch)
8184 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8185 "b/b7/RareMETALS2_" version ".tar.gz"))
8186 (sha256
8187 (base32
8188 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8189 (properties `((upstream-name . "RareMETALS2")))
8190 (build-system r-build-system)
8191 (propagated-inputs
8192 `(("r-seqminer" ,r-seqminer)
8193 ("r-mvtnorm" ,r-mvtnorm)
8194 ("r-compquadform" ,r-compquadform)
8195 ("r-getopt" ,r-getopt)))
8196 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8197 (synopsis "Analyze gene-level association tests for binary trait")
8198 (description
8199 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8200 It was designed to meta-analyze gene-level association tests for binary trait.
8201 While rareMETALS offers a near-complete solution for meta-analysis of
8202 gene-level tests for quantitative trait, it does not offer the optimal
8203 solution for binary trait. The package rareMETALS2 offers improved features
8204 for analyzing gene-level association tests in meta-analyses for binary
8205 trait.")
8206 (license license:gpl3)))
8207
8208 (define-public r-maldiquant
8209 (package
8210 (name "r-maldiquant")
8211 (version "1.16")
8212 (source
8213 (origin
8214 (method url-fetch)
8215 (uri (cran-uri "MALDIquant" version))
8216 (sha256
8217 (base32
8218 "067xbmy10mpsvmv77g62chd7wwhdhcfn5hmp5fisbnz2h5rq0q60"))))
8219 (properties `((upstream-name . "MALDIquant")))
8220 (build-system r-build-system)
8221 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8222 (synopsis "Quantitative analysis of mass spectrometry data")
8223 (description
8224 "This package provides a complete analysis pipeline for matrix-assisted
8225 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8226 two-dimensional mass spectrometry data. In addition to commonly used plotting
8227 and processing methods it includes distinctive features, namely baseline
8228 subtraction methods such as morphological filters (TopHat) or the
8229 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8230 alignment using warping functions, handling of replicated measurements as well
8231 as allowing spectra with different resolutions.")
8232 (license license:gpl3+)))
8233
8234 (define-public r-protgenerics
8235 (package
8236 (name "r-protgenerics")
8237 (version "1.6.0")
8238 (source
8239 (origin
8240 (method url-fetch)
8241 (uri (bioconductor-uri "ProtGenerics" version))
8242 (sha256
8243 (base32
8244 "0hb3vrrvfx6lcfalmjxm8dmigfmi5nba0pzjfgsrzd35c8mbfc6f"))))
8245 (properties `((upstream-name . "ProtGenerics")))
8246 (build-system r-build-system)
8247 (home-page "https://github.com/lgatto/ProtGenerics")
8248 (synopsis "S4 generic functions for proteomics infrastructure")
8249 (description
8250 "This package provides S4 generic functions needed by Bioconductor
8251 proteomics packages.")
8252 (license license:artistic2.0)))
8253
8254 (define-public r-mzr
8255 (package
8256 (name "r-mzr")
8257 (version "2.8.1")
8258 (source
8259 (origin
8260 (method url-fetch)
8261 (uri (bioconductor-uri "mzR" version))
8262 (sha256
8263 (base32
8264 "0ipmhg6l3pf648rdx5g2ha7l5ppd3cja6afxhdw76x8ga3633x0r"))))
8265 (properties `((upstream-name . "mzR")))
8266 (build-system r-build-system)
8267 (inputs
8268 `(("netcdf" ,netcdf)))
8269 (propagated-inputs
8270 `(("r-biobase" ,r-biobase)
8271 ("r-biocgenerics" ,r-biocgenerics)
8272 ("r-protgenerics" ,r-protgenerics)
8273 ("r-rcpp" ,r-rcpp)
8274 ("r-zlibbioc" ,r-zlibbioc)))
8275 (home-page "https://github.com/sneumann/mzR/")
8276 (synopsis "Parser for mass spectrometry data files")
8277 (description
8278 "The mzR package provides a unified API to the common file formats and
8279 parsers available for mass spectrometry data. It comes with a wrapper for the
8280 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8281 The package contains the original code written by the ISB, and a subset of the
8282 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8283 previously been used in XCMS.")
8284 (license license:artistic2.0)))
8285
8286 (define-public r-affyio
8287 (package
8288 (name "r-affyio")
8289 (version "1.44.0")
8290 (source
8291 (origin
8292 (method url-fetch)
8293 (uri (bioconductor-uri "affyio" version))
8294 (sha256
8295 (base32
8296 "1svsl4mpk06xm505pap913x69ywks99262krag8y4ygpllj7dfyy"))))
8297 (build-system r-build-system)
8298 (propagated-inputs
8299 `(("r-zlibbioc" ,r-zlibbioc)))
8300 (inputs
8301 `(("zlib" ,zlib)))
8302 (home-page "https://github.com/bmbolstad/affyio")
8303 (synopsis "Tools for parsing Affymetrix data files")
8304 (description
8305 "This package provides routines for parsing Affymetrix data files based
8306 upon file format information. The primary focus is on accessing the CEL and
8307 CDF file formats.")
8308 (license license:lgpl2.0+)))
8309
8310 (define-public r-affy
8311 (package
8312 (name "r-affy")
8313 (version "1.52.0")
8314 (source
8315 (origin
8316 (method url-fetch)
8317 (uri (bioconductor-uri "affy" version))
8318 (sha256
8319 (base32
8320 "1snq71ligf0wvaxa6zfrl13ydw0zfhspmhdyfk8q3ba3np4cz344"))))
8321 (build-system r-build-system)
8322 (propagated-inputs
8323 `(("r-affyio" ,r-affyio)
8324 ("r-biobase" ,r-biobase)
8325 ("r-biocgenerics" ,r-biocgenerics)
8326 ("r-biocinstaller" ,r-biocinstaller)
8327 ("r-preprocesscore" ,r-preprocesscore)
8328 ("r-zlibbioc" ,r-zlibbioc)))
8329 (home-page "http://bioconductor.org/packages/affy")
8330 (synopsis "Methods for affymetrix oligonucleotide arrays")
8331 (description
8332 "This package contains functions for exploratory oligonucleotide array
8333 analysis.")
8334 (license license:lgpl2.0+)))
8335
8336 (define-public r-vsn
8337 (package
8338 (name "r-vsn")
8339 (version "3.42.3")
8340 (source
8341 (origin
8342 (method url-fetch)
8343 (uri (bioconductor-uri "vsn" version))
8344 (sha256
8345 (base32
8346 "0mgl0azys2g90simf8wx6jdwd7gyg3m4pf12n6w6507jixm2cg97"))))
8347 (build-system r-build-system)
8348 (propagated-inputs
8349 `(("r-affy" ,r-affy)
8350 ("r-biobase" ,r-biobase)
8351 ("r-ggplot2" ,r-ggplot2)
8352 ("r-limma" ,r-limma)))
8353 (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
8354 (synopsis "Variance stabilization and calibration for microarray data")
8355 (description
8356 "The package implements a method for normalising microarray intensities,
8357 and works for single- and multiple-color arrays. It can also be used for data
8358 from other technologies, as long as they have similar format. The method uses
8359 a robust variant of the maximum-likelihood estimator for an
8360 additive-multiplicative error model and affine calibration. The model
8361 incorporates data calibration step (a.k.a. normalization), a model for the
8362 dependence of the variance on the mean intensity and a variance stabilizing
8363 data transformation. Differences between transformed intensities are
8364 analogous to \"normalized log-ratios\". However, in contrast to the latter,
8365 their variance is independent of the mean, and they are usually more sensitive
8366 and specific in detecting differential transcription.")
8367 (license license:artistic2.0)))
8368
8369 (define-public r-mzid
8370 (package
8371 (name "r-mzid")
8372 (version "1.12.0")
8373 (source
8374 (origin
8375 (method url-fetch)
8376 (uri (bioconductor-uri "mzID" version))
8377 (sha256
8378 (base32
8379 "1zn896cpfvqp1qmq5c4vcj933hb8rxwb6gkck1wqvr7393rpqy1q"))))
8380 (properties `((upstream-name . "mzID")))
8381 (build-system r-build-system)
8382 (propagated-inputs
8383 `(("r-doparallel" ,r-doparallel)
8384 ("r-foreach" ,r-foreach)
8385 ("r-iterators" ,r-iterators)
8386 ("r-plyr" ,r-plyr)
8387 ("r-protgenerics" ,r-protgenerics)
8388 ("r-rcpp" ,r-rcpp)
8389 ("r-xml" ,r-xml)))
8390 (home-page "http://bioconductor.org/packages/mzID")
8391 (synopsis "Parser for mzIdentML files")
8392 (description
8393 "This package provides a parser for mzIdentML files implemented using the
8394 XML package. The parser tries to be general and able to handle all types of
8395 mzIdentML files with the drawback of having less pretty output than a vendor
8396 specific parser.")
8397 (license license:gpl2+)))
8398
8399 (define-public r-pcamethods
8400 (package
8401 (name "r-pcamethods")
8402 (version "1.66.0")
8403 (source
8404 (origin
8405 (method url-fetch)
8406 (uri (bioconductor-uri "pcaMethods" version))
8407 (sha256
8408 (base32
8409 "18mawhxw57pgpn87qha4mwki24gqja7wpqha8q496476vyap11xw"))))
8410 (properties `((upstream-name . "pcaMethods")))
8411 (build-system r-build-system)
8412 (propagated-inputs
8413 `(("r-biobase" ,r-biobase)
8414 ("r-biocgenerics" ,r-biocgenerics)
8415 ("r-rcpp" ,r-rcpp)))
8416 (home-page "https://github.com/hredestig/pcamethods")
8417 (synopsis "Collection of PCA methods")
8418 (description
8419 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
8420 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
8421 for missing value estimation is included for comparison. BPCA, PPCA and
8422 NipalsPCA may be used to perform PCA on incomplete data as well as for
8423 accurate missing value estimation. A set of methods for printing and plotting
8424 the results is also provided. All PCA methods make use of the same data
8425 structure (pcaRes) to provide a common interface to the PCA results.")
8426 (license license:gpl3+)))
8427
8428 (define-public r-msnbase
8429 (package
8430 (name "r-msnbase")
8431 (version "2.0.2")
8432 (source
8433 (origin
8434 (method url-fetch)
8435 (uri (bioconductor-uri "MSnbase" version))
8436 (sha256
8437 (base32
8438 "0jjjs29dcwsjaxzfqxy98ycpg3rwxzzchkj77my3cjgdc00sm66n"))))
8439 (properties `((upstream-name . "MSnbase")))
8440 (build-system r-build-system)
8441 (propagated-inputs
8442 `(("r-affy" ,r-affy)
8443 ("r-biobase" ,r-biobase)
8444 ("r-biocgenerics" ,r-biocgenerics)
8445 ("r-biocparallel" ,r-biocparallel)
8446 ("r-digest" ,r-digest)
8447 ("r-ggplot2" ,r-ggplot2)
8448 ("r-impute" ,r-impute)
8449 ("r-iranges" ,r-iranges)
8450 ("r-maldiquant" ,r-maldiquant)
8451 ("r-mzid" ,r-mzid)
8452 ("r-mzr" ,r-mzr)
8453 ("r-pcamethods" ,r-pcamethods)
8454 ("r-plyr" ,r-plyr)
8455 ("r-preprocesscore" ,r-preprocesscore)
8456 ("r-protgenerics" ,r-protgenerics)
8457 ("r-rcpp" ,r-rcpp)
8458 ("r-reshape2" ,r-reshape2)
8459 ("r-s4vectors" ,r-s4vectors)
8460 ("r-vsn" ,r-vsn)
8461 ("r-xml" ,r-xml)))
8462 (home-page "https://github.com/lgatto/MSnbase")
8463 (synopsis "Base functions and classes for MS-based proteomics")
8464 (description
8465 "This package provides basic plotting, data manipulation and processing
8466 of mass spectrometry based proteomics data.")
8467 (license license:artistic2.0)))
8468
8469 (define-public r-msnid
8470 (package
8471 (name "r-msnid")
8472 (version "1.8.0")
8473 (source
8474 (origin
8475 (method url-fetch)
8476 (uri (bioconductor-uri "MSnID" version))
8477 (sha256
8478 (base32
8479 "0fkk3za39cxi0jyxmagmycjdslr2xf6vg3ylz14jyffqi0blw9d5"))))
8480 (properties `((upstream-name . "MSnID")))
8481 (build-system r-build-system)
8482 (propagated-inputs
8483 `(("r-biobase" ,r-biobase)
8484 ("r-data-table" ,r-data-table)
8485 ("r-doparallel" ,r-doparallel)
8486 ("r-dplyr" ,r-dplyr)
8487 ("r-foreach" ,r-foreach)
8488 ("r-iterators" ,r-iterators)
8489 ("r-msnbase" ,r-msnbase)
8490 ("r-mzid" ,r-mzid)
8491 ("r-mzr" ,r-mzr)
8492 ("r-protgenerics" ,r-protgenerics)
8493 ("r-r-cache" ,r-r-cache)
8494 ("r-rcpp" ,r-rcpp)
8495 ("r-reshape2" ,r-reshape2)))
8496 (home-page "http://bioconductor.org/packages/MSnID")
8497 (synopsis "Utilities for LC-MSn proteomics identifications")
8498 (description
8499 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
8500 from mzIdentML (leveraging the mzID package) or text files. After collating
8501 the search results from multiple datasets it assesses their identification
8502 quality and optimize filtering criteria to achieve the maximum number of
8503 identifications while not exceeding a specified false discovery rate. It also
8504 contains a number of utilities to explore the MS/MS results and assess missed
8505 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
8506 (license license:artistic2.0)))