gnu: Add imp.
[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, 2017 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 ocaml)
37 #:use-module (guix build-system perl)
38 #:use-module (guix build-system python)
39 #:use-module (guix build-system r)
40 #:use-module (guix build-system ruby)
41 #:use-module (guix build-system trivial)
42 #:use-module (gnu packages)
43 #:use-module (gnu packages autotools)
44 #:use-module (gnu packages algebra)
45 #:use-module (gnu packages base)
46 #:use-module (gnu packages bash)
47 #:use-module (gnu packages bison)
48 #:use-module (gnu packages boost)
49 #:use-module (gnu packages compression)
50 #:use-module (gnu packages cpio)
51 #:use-module (gnu packages curl)
52 #:use-module (gnu packages documentation)
53 #:use-module (gnu packages datastructures)
54 #:use-module (gnu packages file)
55 #:use-module (gnu packages flex)
56 #:use-module (gnu packages gawk)
57 #:use-module (gnu packages gcc)
58 #:use-module (gnu packages gd)
59 #:use-module (gnu packages gtk)
60 #:use-module (gnu packages glib)
61 #:use-module (gnu packages groff)
62 #:use-module (gnu packages guile)
63 #:use-module (gnu packages haskell)
64 #:use-module (gnu packages image)
65 #:use-module (gnu packages imagemagick)
66 #:use-module (gnu packages java)
67 #:use-module (gnu packages ldc)
68 #:use-module (gnu packages linux)
69 #:use-module (gnu packages logging)
70 #:use-module (gnu packages machine-learning)
71 #:use-module (gnu packages man)
72 #:use-module (gnu packages maths)
73 #:use-module (gnu packages mpi)
74 #:use-module (gnu packages ncurses)
75 #:use-module (gnu packages ocaml)
76 #:use-module (gnu packages pcre)
77 #:use-module (gnu packages parallel)
78 #:use-module (gnu packages pdf)
79 #:use-module (gnu packages perl)
80 #:use-module (gnu packages pkg-config)
81 #:use-module (gnu packages popt)
82 #:use-module (gnu packages protobuf)
83 #:use-module (gnu packages python)
84 #:use-module (gnu packages readline)
85 #:use-module (gnu packages ruby)
86 #:use-module (gnu packages serialization)
87 #:use-module (gnu packages statistics)
88 #:use-module (gnu packages swig)
89 #:use-module (gnu packages tbb)
90 #:use-module (gnu packages tex)
91 #:use-module (gnu packages texinfo)
92 #:use-module (gnu packages textutils)
93 #:use-module (gnu packages time)
94 #:use-module (gnu packages tls)
95 #:use-module (gnu packages vim)
96 #:use-module (gnu packages web)
97 #:use-module (gnu packages xml)
98 #:use-module (gnu packages xorg)
99 #:use-module (gnu packages zip)
100 #:use-module (srfi srfi-1))
101
102 (define-public r-ape
103 (package
104 (name "r-ape")
105 (version "4.1")
106 (source
107 (origin
108 (method url-fetch)
109 (uri (cran-uri "ape" version))
110 (sha256
111 (base32
112 "0959fiiy11rzfzrzaknmgrx64bhszj02l0ycz79k5a6bmpfzanlk"))))
113 (build-system r-build-system)
114 (propagated-inputs
115 `(("r-lattice" ,r-lattice)
116 ("r-nlme" ,r-nlme)))
117 (home-page "http://ape-package.ird.fr/")
118 (synopsis "Analyses of phylogenetics and evolution")
119 (description
120 "This package provides functions for reading, writing, plotting, and
121 manipulating phylogenetic trees, analyses of comparative data in a
122 phylogenetic framework, ancestral character analyses, analyses of
123 diversification and macroevolution, computing distances from DNA sequences,
124 and several other tools.")
125 (license license:gpl2+)))
126
127 (define-public aragorn
128 (package
129 (name "aragorn")
130 (version "1.2.38")
131 (source (origin
132 (method url-fetch)
133 (uri (string-append
134 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
135 version ".tgz"))
136 (sha256
137 (base32
138 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
139 (build-system gnu-build-system)
140 (arguments
141 `(#:tests? #f ; there are no tests
142 #:phases
143 (modify-phases %standard-phases
144 (delete 'configure)
145 (replace 'build
146 (lambda _
147 (zero? (system* "gcc"
148 "-O3"
149 "-ffast-math"
150 "-finline-functions"
151 "-o"
152 "aragorn"
153 (string-append "aragorn" ,version ".c")))))
154 (replace 'install
155 (lambda* (#:key outputs #:allow-other-keys)
156 (let* ((out (assoc-ref outputs "out"))
157 (bin (string-append out "/bin"))
158 (man (string-append out "/share/man/man1")))
159 (mkdir-p bin)
160 (install-file "aragorn" bin)
161 (mkdir-p man)
162 (install-file "aragorn.1" man))
163 #t)))))
164 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
165 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
166 (description
167 "Aragorn identifies transfer RNA, mitochondrial RNA and
168 transfer-messenger RNA from nucleotide sequences, based on homology to known
169 tRNA consensus sequences and RNA structure. It also outputs the secondary
170 structure of the predicted RNA.")
171 (license license:gpl2)))
172
173 (define-public bamm
174 (package
175 (name "bamm")
176 (version "1.7.3")
177 (source (origin
178 (method url-fetch)
179 ;; BamM is not available on pypi.
180 (uri (string-append
181 "https://github.com/Ecogenomics/BamM/archive/"
182 version ".tar.gz"))
183 (file-name (string-append name "-" version ".tar.gz"))
184 (sha256
185 (base32
186 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
187 (modules '((guix build utils)))
188 (snippet
189 `(begin
190 ;; Delete bundled htslib.
191 (delete-file-recursively "c/htslib-1.3.1")
192 #t))))
193 (build-system python-build-system)
194 (arguments
195 `(#:python ,python-2 ; BamM is Python 2 only.
196 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
197 ;; been modified from its original form.
198 #:configure-flags
199 (let ((htslib (assoc-ref %build-inputs "htslib")))
200 (list "--with-libhts-lib" (string-append htslib "/lib")
201 "--with-libhts-inc" (string-append htslib "/include/htslib")))
202 #:phases
203 (modify-phases %standard-phases
204 (add-after 'unpack 'autogen
205 (lambda _
206 (with-directory-excursion "c"
207 (let ((sh (which "sh")))
208 ;; Use autogen so that 'configure' works.
209 (substitute* "autogen.sh" (("/bin/sh") sh))
210 (setenv "CONFIG_SHELL" sh)
211 (substitute* "configure" (("/bin/sh") sh))
212 (zero? (system* "./autogen.sh"))))))
213 (delete 'build)
214 ;; Run tests after installation so compilation only happens once.
215 (delete 'check)
216 (add-after 'install 'wrap-executable
217 (lambda* (#:key outputs #:allow-other-keys)
218 (let* ((out (assoc-ref outputs "out"))
219 (path (getenv "PATH")))
220 (wrap-program (string-append out "/bin/bamm")
221 `("PATH" ":" prefix (,path))))
222 #t))
223 (add-after 'wrap-executable 'post-install-check
224 (lambda* (#:key inputs outputs #:allow-other-keys)
225 (setenv "PATH"
226 (string-append (assoc-ref outputs "out")
227 "/bin:"
228 (getenv "PATH")))
229 (setenv "PYTHONPATH"
230 (string-append
231 (assoc-ref outputs "out")
232 "/lib/python"
233 (string-take (string-take-right
234 (assoc-ref inputs "python") 5) 3)
235 "/site-packages:"
236 (getenv "PYTHONPATH")))
237 ;; There are 2 errors printed, but they are safe to ignore:
238 ;; 1) [E::hts_open_format] fail to open file ...
239 ;; 2) samtools view: failed to open ...
240 (zero? (system* "nosetests")))))))
241 (native-inputs
242 `(("autoconf" ,autoconf)
243 ("automake" ,automake)
244 ("libtool" ,libtool)
245 ("zlib" ,zlib)
246 ("python-nose" ,python2-nose)
247 ("python-pysam" ,python2-pysam)))
248 (inputs
249 `(("htslib" ,htslib)
250 ("samtools" ,samtools)
251 ("bwa" ,bwa)
252 ("grep" ,grep)
253 ("sed" ,sed)
254 ("coreutils" ,coreutils)))
255 (propagated-inputs
256 `(("python-numpy" ,python2-numpy)))
257 (home-page "http://ecogenomics.github.io/BamM/")
258 (synopsis "Metagenomics-focused BAM file manipulator")
259 (description
260 "BamM is a C library, wrapped in python, to efficiently generate and
261 parse BAM files, specifically for the analysis of metagenomic data. For
262 instance, it implements several methods to assess contig-wise read coverage.")
263 (license license:lgpl3+)))
264
265 (define-public bamtools
266 (package
267 (name "bamtools")
268 (version "2.4.1")
269 (source (origin
270 (method url-fetch)
271 (uri (string-append
272 "https://github.com/pezmaster31/bamtools/archive/v"
273 version ".tar.gz"))
274 (file-name (string-append name "-" version ".tar.gz"))
275 (sha256
276 (base32
277 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
278 (build-system cmake-build-system)
279 (arguments
280 `(#:tests? #f ;no "check" target
281 #:phases
282 (modify-phases %standard-phases
283 (add-before
284 'configure 'set-ldflags
285 (lambda* (#:key outputs #:allow-other-keys)
286 (setenv "LDFLAGS"
287 (string-append
288 "-Wl,-rpath="
289 (assoc-ref outputs "out") "/lib/bamtools")))))))
290 (inputs `(("zlib" ,zlib)))
291 (home-page "https://github.com/pezmaster31/bamtools")
292 (synopsis "C++ API and command-line toolkit for working with BAM data")
293 (description
294 "BamTools provides both a C++ API and a command-line toolkit for handling
295 BAM files.")
296 (license license:expat)))
297
298 (define-public bcftools
299 (package
300 (name "bcftools")
301 (version "1.3.1")
302 (source (origin
303 (method url-fetch)
304 (uri (string-append
305 "https://github.com/samtools/bcftools/releases/download/"
306 version "/bcftools-" version ".tar.bz2"))
307 (sha256
308 (base32
309 "095ry68vmz9q5s1scjsa698dhgyvgw5aicz24c19iwfbai07mhqj"))
310 (modules '((guix build utils)))
311 (snippet
312 ;; Delete bundled htslib.
313 '(delete-file-recursively "htslib-1.3.1"))))
314 (build-system gnu-build-system)
315 (arguments
316 `(#:test-target "test"
317 #:make-flags
318 (list
319 "USE_GPL=1"
320 (string-append "prefix=" (assoc-ref %outputs "out"))
321 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
322 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.a")
323 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
324 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix"))
325 #:phases
326 (modify-phases %standard-phases
327 (add-after 'unpack 'patch-Makefile
328 (lambda _
329 (substitute* "Makefile"
330 ;; Do not attempt to build htslib.
331 (("^include \\$\\(HTSDIR\\)/htslib\\.mk") "")
332 ;; Link against GSL cblas.
333 (("-lcblas") "-lgslcblas"))
334 #t))
335 (delete 'configure)
336 (add-before 'check 'patch-tests
337 (lambda _
338 (substitute* "test/test.pl"
339 (("/bin/bash") (which "bash")))
340 #t)))))
341 (native-inputs
342 `(("htslib" ,htslib)
343 ("perl" ,perl)))
344 (inputs
345 `(("gsl" ,gsl)
346 ("zlib" ,zlib)))
347 (home-page "https://samtools.github.io/bcftools/")
348 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
349 (description
350 "BCFtools is a set of utilities that manipulate variant calls in the
351 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
352 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
353 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
354 (license (list license:gpl3+ license:expat))))
355
356 (define-public bedops
357 (package
358 (name "bedops")
359 (version "2.4.14")
360 (source (origin
361 (method url-fetch)
362 (uri (string-append "https://github.com/bedops/bedops/archive/v"
363 version ".tar.gz"))
364 (file-name (string-append name "-" version ".tar.gz"))
365 (sha256
366 (base32
367 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
368 (build-system gnu-build-system)
369 (arguments
370 '(#:tests? #f
371 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
372 #:phases
373 (alist-cons-after
374 'unpack 'unpack-tarballs
375 (lambda _
376 ;; FIXME: Bedops includes tarballs of minimally patched upstream
377 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
378 ;; libraries because at least one of the libraries (zlib) is
379 ;; patched to add a C++ function definition (deflateInit2cpp).
380 ;; Until the Bedops developers offer a way to link against system
381 ;; libraries we have to build the in-tree copies of these three
382 ;; libraries.
383
384 ;; See upstream discussion:
385 ;; https://github.com/bedops/bedops/issues/124
386
387 ;; Unpack the tarballs to benefit from shebang patching.
388 (with-directory-excursion "third-party"
389 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
390 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
391 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
392 ;; Disable unpacking of tarballs in Makefile.
393 (substitute* "system.mk/Makefile.linux"
394 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
395 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
396 (substitute* "third-party/zlib-1.2.7/Makefile.in"
397 (("^SHELL=.*$") "SHELL=bash\n")))
398 (alist-delete 'configure %standard-phases))))
399 (home-page "https://github.com/bedops/bedops")
400 (synopsis "Tools for high-performance genomic feature operations")
401 (description
402 "BEDOPS is a suite of tools to address common questions raised in genomic
403 studies---mostly with regard to overlap and proximity relationships between
404 data sets. It aims to be scalable and flexible, facilitating the efficient
405 and accurate analysis and management of large-scale genomic data.
406
407 BEDOPS provides tools that perform highly efficient and scalable Boolean and
408 other set operations, statistical calculations, archiving, conversion and
409 other management of genomic data of arbitrary scale. Tasks can be easily
410 split by chromosome for distributing whole-genome analyses across a
411 computational cluster.")
412 (license license:gpl2+)))
413
414 (define-public bedtools
415 (package
416 (name "bedtools")
417 (version "2.26.0")
418 (source (origin
419 (method url-fetch)
420 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
421 version ".tar.gz"))
422 (file-name (string-append name "-" version ".tar.gz"))
423 (sha256
424 (base32
425 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
426 (build-system gnu-build-system)
427 (native-inputs `(("python" ,python-2)))
428 (inputs `(("samtools" ,samtools)
429 ("zlib" ,zlib)))
430 (arguments
431 '(#:test-target "test"
432 #:phases
433 (modify-phases %standard-phases
434 (delete 'configure)
435 (replace 'install
436 (lambda* (#:key outputs #:allow-other-keys)
437 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
438 (for-each (lambda (file)
439 (install-file file bin))
440 (find-files "bin" ".*")))
441 #t)))))
442 (home-page "https://github.com/arq5x/bedtools2")
443 (synopsis "Tools for genome analysis and arithmetic")
444 (description
445 "Collectively, the bedtools utilities are a swiss-army knife of tools for
446 a wide-range of genomics analysis tasks. The most widely-used tools enable
447 genome arithmetic: that is, set theory on the genome. For example, bedtools
448 allows one to intersect, merge, count, complement, and shuffle genomic
449 intervals from multiple files in widely-used genomic file formats such as BAM,
450 BED, GFF/GTF, VCF.")
451 (license license:gpl2)))
452
453 ;; Later releases of bedtools produce files with more columns than
454 ;; what Ribotaper expects.
455 (define-public bedtools-2.18
456 (package (inherit bedtools)
457 (name "bedtools")
458 (version "2.18.0")
459 (source (origin
460 (method url-fetch)
461 (uri (string-append "https://github.com/arq5x/bedtools2/"
462 "archive/v" version ".tar.gz"))
463 (file-name (string-append name "-" version ".tar.gz"))
464 (sha256
465 (base32
466 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
467
468 (define-public ribotaper
469 (package
470 (name "ribotaper")
471 (version "1.3.1")
472 (source (origin
473 (method url-fetch)
474 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
475 "files/RiboTaper/RiboTaper_Version_"
476 version ".tar.gz"))
477 (sha256
478 (base32
479 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
480 (build-system gnu-build-system)
481 (inputs
482 `(("bedtools" ,bedtools-2.18)
483 ("samtools" ,samtools-0.1)
484 ("r-minimal" ,r-minimal)
485 ("r-foreach" ,r-foreach)
486 ("r-xnomial" ,r-xnomial)
487 ("r-domc" ,r-domc)
488 ("r-multitaper" ,r-multitaper)
489 ("r-seqinr" ,r-seqinr)))
490 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
491 (synopsis "Define translated ORFs using ribosome profiling data")
492 (description
493 "Ribotaper is a method for defining translated @dfn{open reading
494 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
495 provides the Ribotaper pipeline.")
496 (license license:gpl3+)))
497
498 (define-public ribodiff
499 (package
500 (name "ribodiff")
501 (version "0.2.2")
502 (source
503 (origin
504 (method url-fetch)
505 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
506 "archive/v" version ".tar.gz"))
507 (file-name (string-append name "-" version ".tar.gz"))
508 (sha256
509 (base32
510 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
511 (build-system python-build-system)
512 (arguments
513 `(#:python ,python-2
514 #:phases
515 (modify-phases %standard-phases
516 ;; Generate an installable executable script wrapper.
517 (add-after 'unpack 'patch-setup.py
518 (lambda _
519 (substitute* "setup.py"
520 (("^(.*)packages=.*" line prefix)
521 (string-append line "\n"
522 prefix "scripts=['scripts/TE.py'],\n")))
523 #t)))))
524 (inputs
525 `(("python-numpy" ,python2-numpy)
526 ("python-matplotlib" ,python2-matplotlib)
527 ("python-scipy" ,python2-scipy)
528 ("python-statsmodels" ,python2-statsmodels)))
529 (native-inputs
530 `(("python-mock" ,python2-mock)
531 ("python-nose" ,python2-nose)))
532 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
533 (synopsis "Detect translation efficiency changes from ribosome footprints")
534 (description "RiboDiff is a statistical tool that detects the protein
535 translational efficiency change from Ribo-Seq (ribosome footprinting) and
536 RNA-Seq data. It uses a generalized linear model to detect genes showing
537 difference in translational profile taking mRNA abundance into account. It
538 facilitates us to decipher the translational regulation that behave
539 independently with transcriptional regulation.")
540 (license license:gpl3+)))
541
542 (define-public bioawk
543 (package
544 (name "bioawk")
545 (version "1.0")
546 (source (origin
547 (method url-fetch)
548 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
549 version ".tar.gz"))
550 (file-name (string-append name "-" version ".tar.gz"))
551 (sha256
552 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
553 (build-system gnu-build-system)
554 (inputs
555 `(("zlib" ,zlib)))
556 (native-inputs
557 `(("bison" ,bison)))
558 (arguments
559 `(#:tests? #f ; There are no tests to run.
560 ;; Bison must generate files, before other targets can build.
561 #:parallel-build? #f
562 #:phases
563 (modify-phases %standard-phases
564 (delete 'configure) ; There is no configure phase.
565 (replace 'install
566 (lambda* (#:key outputs #:allow-other-keys)
567 (let* ((out (assoc-ref outputs "out"))
568 (bin (string-append out "/bin"))
569 (man (string-append out "/share/man/man1")))
570 (mkdir-p man)
571 (copy-file "awk.1" (string-append man "/bioawk.1"))
572 (install-file "bioawk" bin)))))))
573 (home-page "https://github.com/lh3/bioawk")
574 (synopsis "AWK with bioinformatics extensions")
575 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
576 support of several common biological data formats, including optionally gzip'ed
577 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
578 also adds a few built-in functions and a command line option to use TAB as the
579 input/output delimiter. When the new functionality is not used, bioawk is
580 intended to behave exactly the same as the original BWK awk.")
581 (license license:x11)))
582
583 (define-public python2-pybedtools
584 (package
585 (name "python2-pybedtools")
586 (version "0.6.9")
587 (source (origin
588 (method url-fetch)
589 (uri (string-append
590 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
591 version ".tar.gz"))
592 (sha256
593 (base32
594 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
595 (build-system python-build-system)
596 (arguments `(#:python ,python-2)) ; no Python 3 support
597 (inputs
598 `(("python-matplotlib" ,python2-matplotlib)))
599 (propagated-inputs
600 `(("bedtools" ,bedtools)
601 ("samtools" ,samtools)))
602 (native-inputs
603 `(("python-cython" ,python2-cython)
604 ("python-pyyaml" ,python2-pyyaml)
605 ("python-nose" ,python2-nose)))
606 (home-page "https://pythonhosted.org/pybedtools/")
607 (synopsis "Python wrapper for BEDtools programs")
608 (description
609 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
610 which are widely used for genomic interval manipulation or \"genome algebra\".
611 pybedtools extends BEDTools by offering feature-level manipulations from with
612 Python.")
613 (license license:gpl2+)))
614
615 (define-public python-biom-format
616 (package
617 (name "python-biom-format")
618 (version "2.1.6")
619 (source
620 (origin
621 (method url-fetch)
622 ;; Use GitHub as source because PyPI distribution does not contain
623 ;; test data: https://github.com/biocore/biom-format/issues/693
624 (uri (string-append "https://github.com/biocore/biom-format/archive/"
625 version ".tar.gz"))
626 (file-name (string-append name "-" version ".tar.gz"))
627 (sha256
628 (base32
629 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
630 (build-system python-build-system)
631 (propagated-inputs
632 `(("python-numpy" ,python-numpy)
633 ("python-scipy" ,python-scipy)
634 ("python-future" ,python-future)
635 ("python-click" ,python-click)
636 ("python-h5py" ,python-h5py)
637 ("python-pandas" ,python-pandas)))
638 (native-inputs
639 `(("python-nose" ,python-nose)))
640 (home-page "http://www.biom-format.org")
641 (synopsis "Biological Observation Matrix (BIOM) format utilities")
642 (description
643 "The BIOM file format is designed to be a general-use format for
644 representing counts of observations e.g. operational taxonomic units, KEGG
645 orthology groups or lipid types, in one or more biological samples
646 e.g. microbiome samples, genomes, metagenomes.")
647 (license license:bsd-3)
648 (properties `((python2-variant . ,(delay python2-biom-format))))))
649
650 (define-public python2-biom-format
651 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
652 (package
653 (inherit base)
654 (arguments
655 `(#:phases
656 (modify-phases %standard-phases
657 ;; Do not require the unmaintained pyqi library.
658 (add-after 'unpack 'remove-pyqi
659 (lambda _
660 (substitute* "setup.py"
661 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
662 #t)))
663 ,@(package-arguments base))))))
664
665 (define-public bioperl-minimal
666 (let* ((inputs `(("perl-module-build" ,perl-module-build)
667 ("perl-data-stag" ,perl-data-stag)
668 ("perl-libwww" ,perl-libwww)
669 ("perl-uri" ,perl-uri)))
670 (transitive-inputs
671 (map (compose package-name cadr)
672 (delete-duplicates
673 (concatenate
674 (map (compose package-transitive-target-inputs cadr) inputs))))))
675 (package
676 (name "bioperl-minimal")
677 (version "1.7.0")
678 (source
679 (origin
680 (method url-fetch)
681 (uri (string-append "https://github.com/bioperl/bioperl-live/"
682 "archive/release-"
683 (string-map (lambda (c)
684 (if (char=? c #\.)
685 #\- c)) version)
686 ".tar.gz"))
687 (sha256
688 (base32
689 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
690 (build-system perl-build-system)
691 (arguments
692 `(#:phases
693 (modify-phases %standard-phases
694 (add-after
695 'install 'wrap-programs
696 (lambda* (#:key outputs #:allow-other-keys)
697 ;; Make sure all executables in "bin" find the required Perl
698 ;; modules at runtime. As the PERL5LIB variable contains also
699 ;; the paths of native inputs, we pick the transitive target
700 ;; inputs from %build-inputs.
701 (let* ((out (assoc-ref outputs "out"))
702 (bin (string-append out "/bin/"))
703 (path (string-join
704 (cons (string-append out "/lib/perl5/site_perl")
705 (map (lambda (name)
706 (assoc-ref %build-inputs name))
707 ',transitive-inputs))
708 ":")))
709 (for-each (lambda (file)
710 (wrap-program file
711 `("PERL5LIB" ":" prefix (,path))))
712 (find-files bin "\\.pl$"))
713 #t))))))
714 (inputs inputs)
715 (native-inputs
716 `(("perl-test-most" ,perl-test-most)))
717 (home-page "http://search.cpan.org/dist/BioPerl")
718 (synopsis "Bioinformatics toolkit")
719 (description
720 "BioPerl is the product of a community effort to produce Perl code which
721 is useful in biology. Examples include Sequence objects, Alignment objects
722 and database searching objects. These objects not only do what they are
723 advertised to do in the documentation, but they also interact - Alignment
724 objects are made from the Sequence objects, Sequence objects have access to
725 Annotation and SeqFeature objects and databases, Blast objects can be
726 converted to Alignment objects, and so on. This means that the objects
727 provide a coordinated and extensible framework to do computational biology.")
728 (license license:perl-license))))
729
730 (define-public python-biopython
731 (package
732 (name "python-biopython")
733 (version "1.68")
734 (source (origin
735 (method url-fetch)
736 ;; use PyPi rather than biopython.org to ease updating
737 (uri (pypi-uri "biopython" version))
738 (sha256
739 (base32
740 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
741 (build-system python-build-system)
742 (arguments
743 `(#:phases
744 (modify-phases %standard-phases
745 (add-before 'check 'set-home
746 ;; Some tests require a home directory to be set.
747 (lambda _ (setenv "HOME" "/tmp") #t)))))
748 (propagated-inputs
749 `(("python-numpy" ,python-numpy)))
750 (home-page "http://biopython.org/")
751 (synopsis "Tools for biological computation in Python")
752 (description
753 "Biopython is a set of tools for biological computation including parsers
754 for bioinformatics files into Python data structures; interfaces to common
755 bioinformatics programs; a standard sequence class and tools for performing
756 common operations on them; code to perform data classification; code for
757 dealing with alignments; code making it easy to split up parallelizable tasks
758 into separate processes; and more.")
759 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
760
761 (define-public python2-biopython
762 (package-with-python2 python-biopython))
763
764 ;; An outdated version of biopython is required for seqmagick, see
765 ;; https://github.com/fhcrc/seqmagick/issues/59
766 ;; When that issue has been resolved this package should be removed.
767 (define python2-biopython-1.66
768 (package
769 (inherit python2-biopython)
770 (version "1.66")
771 (source (origin
772 (method url-fetch)
773 (uri (pypi-uri "biopython" version))
774 (sha256
775 (base32
776 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
777
778 (define-public bpp-core
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 "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
783 (package
784 (name "bpp-core")
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-core")
790 (commit commit)))
791 (file-name (string-append name "-" version "-checkout"))
792 (sha256
793 (base32
794 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
795 (build-system cmake-build-system)
796 (arguments
797 `(#:parallel-build? #f))
798 (inputs
799 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
800 ; compile all of the bpp packages with GCC 5.
801 (home-page "http://biopp.univ-montp2.fr")
802 (synopsis "C++ libraries for Bioinformatics")
803 (description
804 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
805 analysis, phylogenetics, molecular evolution and population genetics. It is
806 Object Oriented and is designed to be both easy to use and computer efficient.
807 Bio++ intends to help programmers to write computer expensive programs, by
808 providing them a set of re-usable tools.")
809 (license license:cecill-c))))
810
811 (define-public bpp-phyl
812 ;; The last release was in 2014 and the recommended way to install from source
813 ;; is to clone the git repository, so we do this.
814 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
815 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
816 (package
817 (name "bpp-phyl")
818 (version (string-append "2.2.0-1." (string-take commit 7)))
819 (source (origin
820 (method git-fetch)
821 (uri (git-reference
822 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
823 (commit commit)))
824 (file-name (string-append name "-" version "-checkout"))
825 (sha256
826 (base32
827 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
828 (build-system cmake-build-system)
829 (arguments
830 `(#:parallel-build? #f
831 ;; If out-of-source, test data is not copied into the build directory
832 ;; so the tests fail.
833 #:out-of-source? #f))
834 (inputs
835 `(("bpp-core" ,bpp-core)
836 ("bpp-seq" ,bpp-seq)
837 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
838 ;; modern GCC.
839 ("gcc" ,gcc-5)))
840 (home-page "http://biopp.univ-montp2.fr")
841 (synopsis "Bio++ phylogenetic 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 phylogenetics-related modules.")
846 (license license:cecill-c))))
847
848 (define-public bpp-popgen
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 "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
853 (package
854 (name "bpp-popgen")
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-popgen")
860 (commit commit)))
861 (file-name (string-append name "-" version "-checkout"))
862 (sha256
863 (base32
864 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
865 (build-system cmake-build-system)
866 (arguments
867 `(#:parallel-build? #f
868 #:tests? #f)) ; There are no tests.
869 (inputs
870 `(("bpp-core" ,bpp-core)
871 ("bpp-seq" ,bpp-seq)
872 ("gcc" ,gcc-5)))
873 (home-page "http://biopp.univ-montp2.fr")
874 (synopsis "Bio++ population genetics library")
875 (description
876 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
877 analysis, phylogenetics, molecular evolution and population genetics. This
878 library provides population genetics-related modules.")
879 (license license:cecill-c))))
880
881 (define-public bpp-seq
882 ;; The last release was in 2014 and the recommended way to install from source
883 ;; is to clone the git repository, so we do this.
884 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
885 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
886 (package
887 (name "bpp-seq")
888 (version (string-append "2.2.0-1." (string-take commit 7)))
889 (source (origin
890 (method git-fetch)
891 (uri (git-reference
892 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
893 (commit commit)))
894 (file-name (string-append name "-" version "-checkout"))
895 (sha256
896 (base32
897 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
898 (build-system cmake-build-system)
899 (arguments
900 `(#:parallel-build? #f
901 ;; If out-of-source, test data is not copied into the build directory
902 ;; so the tests fail.
903 #:out-of-source? #f))
904 (inputs
905 `(("bpp-core" ,bpp-core)
906 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
907 (home-page "http://biopp.univ-montp2.fr")
908 (synopsis "Bio++ sequence library")
909 (description
910 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
911 analysis, phylogenetics, molecular evolution and population genetics. This
912 library provides sequence-related modules.")
913 (license license:cecill-c))))
914
915 (define-public bppsuite
916 ;; The last release was in 2014 and the recommended way to install from source
917 ;; is to clone the git repository, so we do this.
918 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
919 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
920 (package
921 (name "bppsuite")
922 (version (string-append "2.2.0-1." (string-take commit 7)))
923 (source (origin
924 (method git-fetch)
925 (uri (git-reference
926 (url "http://biopp.univ-montp2.fr/git/bppsuite")
927 (commit commit)))
928 (file-name (string-append name "-" version "-checkout"))
929 (sha256
930 (base32
931 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
932 (build-system cmake-build-system)
933 (arguments
934 `(#:parallel-build? #f
935 #:tests? #f)) ; There are no tests.
936 (native-inputs
937 `(("groff" ,groff)
938 ("man-db" ,man-db)
939 ("texinfo" ,texinfo)))
940 (inputs
941 `(("bpp-core" ,bpp-core)
942 ("bpp-seq" ,bpp-seq)
943 ("bpp-phyl" ,bpp-phyl)
944 ("bpp-phyl" ,bpp-popgen)
945 ("gcc" ,gcc-5)))
946 (home-page "http://biopp.univ-montp2.fr")
947 (synopsis "Bioinformatics tools written with the Bio++ libraries")
948 (description
949 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
950 analysis, phylogenetics, molecular evolution and population genetics. This
951 package provides command line tools using the Bio++ library.")
952 (license license:cecill-c))))
953
954 (define-public blast+
955 (package
956 (name "blast+")
957 (version "2.4.0")
958 (source (origin
959 (method url-fetch)
960 (uri (string-append
961 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
962 version "/ncbi-blast-" version "+-src.tar.gz"))
963 (sha256
964 (base32
965 "14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
966 (modules '((guix build utils)))
967 (snippet
968 '(begin
969 ;; Remove bundled bzip2 and zlib
970 (delete-file-recursively "c++/src/util/compress/bzip2")
971 (delete-file-recursively "c++/src/util/compress/zlib")
972 (substitute* "c++/src/util/compress/Makefile.in"
973 (("bzip2 zlib api") "api"))
974 ;; Remove useless msbuild directory
975 (delete-file-recursively
976 "c++/src/build-system/project_tree_builder/msbuild")
977 #t))))
978 (build-system gnu-build-system)
979 (arguments
980 `(;; There are three(!) tests for this massive library, and all fail with
981 ;; "unparsable timing stats".
982 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
983 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
984 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
985 #:tests? #f
986 #:out-of-source? #t
987 #:parallel-build? #f ; not supported
988 #:phases
989 (modify-phases %standard-phases
990 (add-before
991 'configure 'set-HOME
992 ;; $HOME needs to be set at some point during the configure phase
993 (lambda _ (setenv "HOME" "/tmp") #t))
994 (add-after
995 'unpack 'enter-dir
996 (lambda _ (chdir "c++") #t))
997 (add-after
998 'enter-dir 'fix-build-system
999 (lambda _
1000 (define (which* cmd)
1001 (cond ((string=? cmd "date")
1002 ;; make call to "date" deterministic
1003 "date -d @0")
1004 ((which cmd)
1005 => identity)
1006 (else
1007 (format (current-error-port)
1008 "WARNING: Unable to find absolute path for ~s~%"
1009 cmd)
1010 #f)))
1011
1012 ;; Rewrite hardcoded paths to various tools
1013 (substitute* (append '("src/build-system/configure.ac"
1014 "src/build-system/configure"
1015 "scripts/common/impl/if_diff.sh"
1016 "scripts/common/impl/run_with_lock.sh"
1017 "src/build-system/Makefile.configurables.real"
1018 "src/build-system/Makefile.in.top"
1019 "src/build-system/Makefile.meta.gmake=no"
1020 "src/build-system/Makefile.meta.in"
1021 "src/build-system/Makefile.meta_l"
1022 "src/build-system/Makefile.meta_p"
1023 "src/build-system/Makefile.meta_r"
1024 "src/build-system/Makefile.mk.in"
1025 "src/build-system/Makefile.requirements"
1026 "src/build-system/Makefile.rules_with_autodep.in")
1027 (find-files "scripts/common/check" "\\.sh$"))
1028 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1029 (or (which* cmd) all)))
1030
1031 (substitute* (find-files "src/build-system" "^config.*")
1032 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1033 (("^PATH=.*") ""))
1034
1035 ;; rewrite "/var/tmp" in check script
1036 (substitute* "scripts/common/check/check_make_unix.sh"
1037 (("/var/tmp") "/tmp"))
1038
1039 ;; do not reset PATH
1040 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1041 (("^ *PATH=.*") "")
1042 (("action=/bin/") "action=")
1043 (("export PATH") ":"))
1044 #t))
1045 (replace
1046 'configure
1047 (lambda* (#:key inputs outputs #:allow-other-keys)
1048 (let ((out (assoc-ref outputs "out"))
1049 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1050 (include (string-append (assoc-ref outputs "include")
1051 "/include/ncbi-tools++")))
1052 ;; The 'configure' script doesn't recognize things like
1053 ;; '--enable-fast-install'.
1054 (zero? (system* "./configure.orig"
1055 (string-append "--with-build-root=" (getcwd) "/build")
1056 (string-append "--prefix=" out)
1057 (string-append "--libdir=" lib)
1058 (string-append "--includedir=" include)
1059 (string-append "--with-bz2="
1060 (assoc-ref inputs "bzip2"))
1061 (string-append "--with-z="
1062 (assoc-ref inputs "zlib"))
1063 ;; Each library is built twice by default, once
1064 ;; with "-static" in its name, and again
1065 ;; without.
1066 "--without-static"
1067 "--with-dll"))))))))
1068 (outputs '("out" ; 19 MB
1069 "lib" ; 203 MB
1070 "include")) ; 32 MB
1071 (inputs
1072 `(("bzip2" ,bzip2)
1073 ("zlib" ,zlib)))
1074 (native-inputs
1075 `(("cpio" ,cpio)))
1076 (home-page "http://blast.ncbi.nlm.nih.gov")
1077 (synopsis "Basic local alignment search tool")
1078 (description
1079 "BLAST is a popular method of performing a DNA or protein sequence
1080 similarity search, using heuristics to produce results quickly. It also
1081 calculates an “expect value” that estimates how many matches would have
1082 occurred at a given score by chance, which can aid a user in judging how much
1083 confidence to have in an alignment.")
1084 ;; Most of the sources are in the public domain, with the following
1085 ;; exceptions:
1086 ;; * Expat:
1087 ;; * ./c++/include/util/bitset/
1088 ;; * ./c++/src/html/ncbi_menu*.js
1089 ;; * Boost license:
1090 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1091 ;; * LGPL 2+:
1092 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1093 ;; * ASL 2.0:
1094 ;; * ./c++/src/corelib/teamcity_*
1095 (license (list license:public-domain
1096 license:expat
1097 license:boost1.0
1098 license:lgpl2.0+
1099 license:asl2.0))))
1100
1101 (define-public bless
1102 (package
1103 (name "bless")
1104 (version "1p02")
1105 (source (origin
1106 (method url-fetch)
1107 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1108 version ".tgz"))
1109 (sha256
1110 (base32
1111 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1112 (modules '((guix build utils)))
1113 (snippet
1114 `(begin
1115 ;; Remove bundled boost, pigz, zlib, and .git directory
1116 ;; FIXME: also remove bundled sources for murmurhash3 and
1117 ;; kmc once packaged.
1118 (delete-file-recursively "boost")
1119 (delete-file-recursively "pigz")
1120 (delete-file-recursively "google-sparsehash")
1121 (delete-file-recursively "zlib")
1122 (delete-file-recursively ".git")
1123 #t))))
1124 (build-system gnu-build-system)
1125 (arguments
1126 '(#:tests? #f ;no "check" target
1127 #:make-flags
1128 (list (string-append "ZLIB="
1129 (assoc-ref %build-inputs "zlib")
1130 "/lib/libz.a")
1131 (string-append "LDFLAGS="
1132 (string-join '("-lboost_filesystem"
1133 "-lboost_system"
1134 "-lboost_iostreams"
1135 "-lz"
1136 "-fopenmp"
1137 "-std=c++11"))))
1138 #:phases
1139 (modify-phases %standard-phases
1140 (add-after 'unpack 'do-not-build-bundled-pigz
1141 (lambda* (#:key inputs outputs #:allow-other-keys)
1142 (substitute* "Makefile"
1143 (("cd pigz/pigz-2.3.3; make") ""))
1144 #t))
1145 (add-after 'unpack 'patch-paths-to-executables
1146 (lambda* (#:key inputs outputs #:allow-other-keys)
1147 (substitute* "parse_args.cpp"
1148 (("kmc_binary = .*")
1149 (string-append "kmc_binary = \""
1150 (assoc-ref outputs "out")
1151 "/bin/kmc\";"))
1152 (("pigz_binary = .*")
1153 (string-append "pigz_binary = \""
1154 (assoc-ref inputs "pigz")
1155 "/bin/pigz\";")))
1156 #t))
1157 (replace 'install
1158 (lambda* (#:key outputs #:allow-other-keys)
1159 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1160 (for-each (lambda (file)
1161 (install-file file bin))
1162 '("bless" "kmc/bin/kmc"))
1163 #t)))
1164 (delete 'configure))))
1165 (native-inputs
1166 `(("perl" ,perl)))
1167 (inputs
1168 `(("openmpi" ,openmpi)
1169 ("boost" ,boost)
1170 ("sparsehash" ,sparsehash)
1171 ("pigz" ,pigz)
1172 ("zlib" ,zlib)))
1173 (supported-systems '("x86_64-linux"))
1174 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1175 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1176 (description
1177 "@dfn{Bloom-filter-based error correction solution for high-throughput
1178 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1179 correction tool for genomic reads produced by @dfn{Next-generation
1180 sequencing} (NGS). BLESS produces accurate correction results with much less
1181 memory compared with previous solutions and is also able to tolerate a higher
1182 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1183 errors at the end of reads.")
1184 (license license:gpl3+)))
1185
1186 (define-public bowtie
1187 (package
1188 (name "bowtie")
1189 (version "2.2.9")
1190 (source (origin
1191 (method url-fetch)
1192 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1193 version ".tar.gz"))
1194 (file-name (string-append name "-" version ".tar.gz"))
1195 (sha256
1196 (base32
1197 "1vp5db8i7is57iwjybcdg18f5ivyzlj5g1ix1nlvxainzivhz55g"))
1198 (modules '((guix build utils)))
1199 (snippet
1200 '(substitute* "Makefile"
1201 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1202 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1203 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1204 (build-system gnu-build-system)
1205 (inputs `(("perl" ,perl)
1206 ("perl-clone" ,perl-clone)
1207 ("perl-test-deep" ,perl-test-deep)
1208 ("perl-test-simple" ,perl-test-simple)
1209 ("python" ,python-2)
1210 ("tbb" ,tbb)))
1211 (arguments
1212 '(#:make-flags
1213 (list "allall"
1214 "WITH_TBB=1"
1215 (string-append "prefix=" (assoc-ref %outputs "out")))
1216 #:phases
1217 (alist-delete
1218 'configure
1219 (alist-replace
1220 'check
1221 (lambda* (#:key outputs #:allow-other-keys)
1222 (system* "perl"
1223 "scripts/test/simple_tests.pl"
1224 "--bowtie2=./bowtie2"
1225 "--bowtie2-build=./bowtie2-build"))
1226 %standard-phases))))
1227 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1228 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1229 (description
1230 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1231 reads to long reference sequences. It is particularly good at aligning reads
1232 of about 50 up to 100s or 1,000s of characters, and particularly good at
1233 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1234 genome with an FM Index to keep its memory footprint small: for the human
1235 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1236 gapped, local, and paired-end alignment modes.")
1237 (supported-systems '("x86_64-linux"))
1238 (license license:gpl3+)))
1239
1240 (define-public tophat
1241 (package
1242 (name "tophat")
1243 (version "2.1.0")
1244 (source (origin
1245 (method url-fetch)
1246 (uri (string-append
1247 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1248 version ".tar.gz"))
1249 (sha256
1250 (base32
1251 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1252 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1253 (modules '((guix build utils)))
1254 (snippet
1255 '(begin
1256 ;; Remove bundled SeqAn and samtools
1257 (delete-file-recursively "src/SeqAn-1.3")
1258 (delete-file-recursively "src/samtools-0.1.18")
1259 #t))))
1260 (build-system gnu-build-system)
1261 (arguments
1262 '(#:parallel-build? #f ; not supported
1263 #:phases
1264 (modify-phases %standard-phases
1265 (add-after 'unpack 'use-system-samtools
1266 (lambda* (#:key inputs #:allow-other-keys)
1267 (substitute* "src/Makefile.in"
1268 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1269 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1270 (("SAMPROG = samtools_0\\.1\\.18") "")
1271 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1272 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1273 (substitute* '("src/common.cpp"
1274 "src/tophat.py")
1275 (("samtools_0.1.18") (which "samtools")))
1276 (substitute* '("src/common.h"
1277 "src/bam2fastx.cpp")
1278 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1279 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1280 (substitute* '("src/bwt_map.h"
1281 "src/map2gtf.h"
1282 "src/align_status.h")
1283 (("#include <bam.h>") "#include <samtools/bam.h>")
1284 (("#include <sam.h>") "#include <samtools/sam.h>"))
1285 #t)))))
1286 (inputs
1287 `(("boost" ,boost)
1288 ("bowtie" ,bowtie)
1289 ("samtools" ,samtools-0.1)
1290 ("ncurses" ,ncurses)
1291 ("python" ,python-2)
1292 ("perl" ,perl)
1293 ("zlib" ,zlib)
1294 ("seqan" ,seqan)))
1295 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1296 (synopsis "Spliced read mapper for RNA-Seq data")
1297 (description
1298 "TopHat is a fast splice junction mapper for nucleotide sequence
1299 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1300 mammalian-sized genomes using the ultra high-throughput short read
1301 aligner Bowtie, and then analyzes the mapping results to identify
1302 splice junctions between exons.")
1303 ;; TopHat is released under the Boost Software License, Version 1.0
1304 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1305 (license license:boost1.0)))
1306
1307 (define-public bwa
1308 (package
1309 (name "bwa")
1310 (version "0.7.12")
1311 (source (origin
1312 (method url-fetch)
1313 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1314 version ".tar.bz2"))
1315 (sha256
1316 (base32
1317 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
1318 (build-system gnu-build-system)
1319 (arguments
1320 '(#:tests? #f ;no "check" target
1321 #:phases
1322 (alist-replace
1323 'install
1324 (lambda* (#:key outputs #:allow-other-keys)
1325 (let ((bin (string-append
1326 (assoc-ref outputs "out") "/bin"))
1327 (doc (string-append
1328 (assoc-ref outputs "out") "/share/doc/bwa"))
1329 (man (string-append
1330 (assoc-ref outputs "out") "/share/man/man1")))
1331 (install-file "bwa" bin)
1332 (install-file "README.md" doc)
1333 (install-file "bwa.1" man)))
1334 ;; no "configure" script
1335 (alist-delete 'configure %standard-phases))))
1336 (inputs `(("zlib" ,zlib)))
1337 ;; Non-portable SSE instructions are used so building fails on platforms
1338 ;; other than x86_64.
1339 (supported-systems '("x86_64-linux"))
1340 (home-page "http://bio-bwa.sourceforge.net/")
1341 (synopsis "Burrows-Wheeler sequence aligner")
1342 (description
1343 "BWA is a software package for mapping low-divergent sequences against a
1344 large reference genome, such as the human genome. It consists of three
1345 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1346 designed for Illumina sequence reads up to 100bp, while the rest two for
1347 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1348 features such as long-read support and split alignment, but BWA-MEM, which is
1349 the latest, is generally recommended for high-quality queries as it is faster
1350 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1351 70-100bp Illumina reads.")
1352 (license license:gpl3+)))
1353
1354 (define-public bwa-pssm
1355 (package (inherit bwa)
1356 (name "bwa-pssm")
1357 (version "0.5.11")
1358 (source (origin
1359 (method url-fetch)
1360 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1361 "archive/" version ".tar.gz"))
1362 (file-name (string-append name "-" version ".tar.gz"))
1363 (sha256
1364 (base32
1365 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1366 (build-system gnu-build-system)
1367 (inputs
1368 `(("gdsl" ,gdsl)
1369 ("zlib" ,zlib)
1370 ("perl" ,perl)))
1371 (home-page "http://bwa-pssm.binf.ku.dk/")
1372 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1373 (description
1374 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1375 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1376 existing aligners it is fast and sensitive. Unlike most other aligners,
1377 however, it is also adaptible in the sense that one can direct the alignment
1378 based on known biases within the data set. It is coded as a modification of
1379 the original BWA alignment program and shares the genome index structure as
1380 well as many of the command line options.")
1381 (license license:gpl3+)))
1382
1383 (define-public python2-bx-python
1384 (package
1385 (name "python2-bx-python")
1386 (version "0.7.2")
1387 (source (origin
1388 (method url-fetch)
1389 (uri (string-append
1390 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
1391 version ".tar.gz"))
1392 (sha256
1393 (base32
1394 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
1395 (modules '((guix build utils)))
1396 (snippet
1397 '(substitute* "setup.py"
1398 ;; remove dependency on outdated "distribute" module
1399 (("^from distribute_setup import use_setuptools") "")
1400 (("^use_setuptools\\(\\)") "")))))
1401 (build-system python-build-system)
1402 (arguments
1403 `(#:tests? #f ;tests fail because test data are not included
1404 #:python ,python-2))
1405 (inputs
1406 `(("python-numpy" ,python2-numpy)
1407 ("zlib" ,zlib)))
1408 (native-inputs
1409 `(("python-nose" ,python2-nose)))
1410 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1411 (synopsis "Tools for manipulating biological data")
1412 (description
1413 "bx-python provides tools for manipulating biological data, particularly
1414 multiple sequence alignments.")
1415 (license license:expat)))
1416
1417 (define-public python-pysam
1418 (package
1419 (name "python-pysam")
1420 (version "0.10.0")
1421 (source (origin
1422 (method url-fetch)
1423 ;; Test data is missing on PyPi.
1424 (uri (string-append
1425 "https://github.com/pysam-developers/pysam/archive/v"
1426 version ".tar.gz"))
1427 (file-name (string-append name "-" version ".tar.gz"))
1428 (sha256
1429 (base32
1430 "1mmvn91agr238kwz7226xq0i7k84lg2nxywn9712mzj7gvgqhfy8"))
1431 (modules '((guix build utils)))
1432 (snippet
1433 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1434 '(delete-file-recursively "htslib"))))
1435 (build-system python-build-system)
1436 (arguments
1437 `(#:modules ((ice-9 ftw)
1438 (srfi srfi-26)
1439 (guix build python-build-system)
1440 (guix build utils))
1441 #:phases
1442 (modify-phases %standard-phases
1443 (add-before 'build 'set-flags
1444 (lambda* (#:key inputs #:allow-other-keys)
1445 (setenv "HTSLIB_MODE" "external")
1446 (setenv "HTSLIB_LIBRARY_DIR"
1447 (string-append (assoc-ref inputs "htslib") "/lib"))
1448 (setenv "HTSLIB_INCLUDE_DIR"
1449 (string-append (assoc-ref inputs "htslib") "/include"))
1450 (setenv "LDFLAGS" "-lncurses")
1451 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1452 #t))
1453 (replace 'check
1454 (lambda* (#:key inputs outputs #:allow-other-keys)
1455 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1456 (setenv "PYTHONPATH"
1457 (string-append
1458 (getenv "PYTHONPATH")
1459 ":" (getcwd) "/build/"
1460 (car (scandir "build"
1461 (negate (cut string-prefix? "." <>))))))
1462 ;; Step out of source dir so python does not import from CWD.
1463 (with-directory-excursion "tests"
1464 (setenv "HOME" "/tmp")
1465 (and (zero? (system* "make" "-C" "pysam_data"))
1466 (zero? (system* "make" "-C" "cbcf_data"))
1467 ;; Running nosetests without explicitly asking for a
1468 ;; single process leads to a crash. Running with multiple
1469 ;; processes fails because the tests are not designed to
1470 ;; run in parallel.
1471
1472 ;; FIXME: tests keep timing out on some systems.
1473 ;; (zero? (system* "nosetests" "-v"
1474 ;; "--processes" "1"))
1475 )))))))
1476 (propagated-inputs
1477 `(("htslib" ,htslib))) ; Included from installed header files.
1478 (inputs
1479 `(("ncurses" ,ncurses)
1480 ("zlib" ,zlib)))
1481 (native-inputs
1482 `(("python-cython" ,python-cython)
1483 ;; Dependencies below are are for tests only.
1484 ("samtools" ,samtools)
1485 ("bcftools" ,bcftools)
1486 ("python-nose" ,python-nose)))
1487 (home-page "https://github.com/pysam-developers/pysam")
1488 (synopsis "Python bindings to the SAMtools C API")
1489 (description
1490 "Pysam is a Python module for reading and manipulating files in the
1491 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1492 also includes an interface for tabix.")
1493 (license license:expat)))
1494
1495 (define-public python2-pysam
1496 (package-with-python2 python-pysam))
1497
1498 (define-public python-twobitreader
1499 (package
1500 (name "python-twobitreader")
1501 (version "3.1.4")
1502 (source (origin
1503 (method url-fetch)
1504 (uri (pypi-uri "twobitreader" version))
1505 (sha256
1506 (base32
1507 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1508 (build-system python-build-system)
1509 (arguments
1510 '(;; Tests are not distributed in the PyPi release.
1511 ;; TODO Try building from the Git repo or asking the upstream maintainer
1512 ;; to distribute the tests on PyPi.
1513 #:tests? #f))
1514 (native-inputs
1515 `(("python-sphinx" ,python-sphinx)))
1516 (home-page "https://github.com/benjschiller/twobitreader")
1517 (synopsis "Python library for reading .2bit files")
1518 (description
1519 "twobitreader is a Python library for reading .2bit files as used by the
1520 UCSC genome browser.")
1521 (license license:artistic2.0)))
1522
1523 (define-public python2-twobitreader
1524 (package-with-python2 python-twobitreader))
1525
1526 (define-public python-plastid
1527 (package
1528 (name "python-plastid")
1529 (version "0.4.6")
1530 (source (origin
1531 (method url-fetch)
1532 (uri (pypi-uri "plastid" version))
1533 (sha256
1534 (base32
1535 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
1536 (build-system python-build-system)
1537 (arguments
1538 ;; Some test files are not included.
1539 `(#:tests? #f))
1540 (propagated-inputs
1541 `(("python-numpy" ,python-numpy)
1542 ("python-scipy" ,python-scipy)
1543 ("python-pandas" ,python-pandas)
1544 ("python-pysam" ,python-pysam)
1545 ("python-matplotlib" ,python-matplotlib)
1546 ("python-biopython" ,python-biopython)
1547 ("python-twobitreader" ,python-twobitreader)
1548 ("python-termcolor" ,python-termcolor)))
1549 (native-inputs
1550 `(("python-cython" ,python-cython)
1551 ("python-nose" ,python-nose)))
1552 (home-page "https://github.com/joshuagryphon/plastid")
1553 (synopsis "Python library for genomic analysis")
1554 (description
1555 "plastid is a Python library for genomic analysis – in particular,
1556 high-throughput sequencing data – with an emphasis on simplicity.")
1557 (license license:bsd-3)))
1558
1559 (define-public python2-plastid
1560 (package-with-python2 python-plastid))
1561
1562 (define-public cd-hit
1563 (package
1564 (name "cd-hit")
1565 (version "4.6.6")
1566 (source (origin
1567 (method url-fetch)
1568 (uri (string-append "https://github.com/weizhongli/cdhit"
1569 "/releases/download/V" version
1570 "/cd-hit-v" version "-2016-0711.tar.gz"))
1571 (sha256
1572 (base32
1573 "1w8hd4fszgg29nqiz569fldwy012la77nljcmlhglgicws56z54p"))))
1574 (build-system gnu-build-system)
1575 (arguments
1576 `(#:tests? #f ; there are no tests
1577 #:make-flags
1578 ;; Executables are copied directly to the PREFIX.
1579 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1580 #:phases
1581 (modify-phases %standard-phases
1582 ;; No "configure" script
1583 (delete 'configure)
1584 ;; Remove sources of non-determinism
1585 (add-after 'unpack 'be-timeless
1586 (lambda _
1587 (substitute* "cdhit-utility.c++"
1588 ((" \\(built on \" __DATE__ \"\\)") ""))
1589 (substitute* "cdhit-common.c++"
1590 (("__DATE__") "\"0\"")
1591 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1592 #t))
1593 ;; The "install" target does not create the target directory
1594 (add-before 'install 'create-target-dir
1595 (lambda* (#:key outputs #:allow-other-keys)
1596 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1597 #t)))))
1598 (inputs
1599 `(("perl" ,perl)))
1600 (home-page "http://weizhongli-lab.org/cd-hit/")
1601 (synopsis "Cluster and compare protein or nucleotide sequences")
1602 (description
1603 "CD-HIT is a program for clustering and comparing protein or nucleotide
1604 sequences. CD-HIT is designed to be fast and handle extremely large
1605 databases.")
1606 ;; The manual says: "It can be copied under the GNU General Public License
1607 ;; version 2 (GPLv2)."
1608 (license license:gpl2)))
1609
1610 (define-public clipper
1611 (package
1612 (name "clipper")
1613 (version "1.1")
1614 (source (origin
1615 (method url-fetch)
1616 (uri (string-append
1617 "https://github.com/YeoLab/clipper/archive/"
1618 version ".tar.gz"))
1619 (file-name (string-append name "-" version ".tar.gz"))
1620 (sha256
1621 (base32
1622 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1623 (modules '((guix build utils)))
1624 (snippet
1625 '(begin
1626 ;; remove unnecessary setup dependency
1627 (substitute* "setup.py"
1628 (("setup_requires = .*") ""))
1629 (for-each delete-file
1630 '("clipper/src/peaks.so"
1631 "clipper/src/readsToWiggle.so"))
1632 (delete-file-recursively "dist/")
1633 #t))))
1634 (build-system python-build-system)
1635 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1636 (inputs
1637 `(("htseq" ,htseq)
1638 ("python-pybedtools" ,python2-pybedtools)
1639 ("python-cython" ,python2-cython)
1640 ("python-scikit-learn" ,python2-scikit-learn)
1641 ("python-matplotlib" ,python2-matplotlib)
1642 ("python-pandas" ,python2-pandas)
1643 ("python-pysam" ,python2-pysam)
1644 ("python-numpy" ,python2-numpy)
1645 ("python-scipy" ,python2-scipy)))
1646 (native-inputs
1647 `(("python-mock" ,python2-mock) ; for tests
1648 ("python-nose" ,python2-nose) ; for tests
1649 ("python-pytz" ,python2-pytz))) ; for tests
1650 (home-page "https://github.com/YeoLab/clipper")
1651 (synopsis "CLIP peak enrichment recognition")
1652 (description
1653 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1654 (license license:gpl2)))
1655
1656 (define-public codingquarry
1657 (package
1658 (name "codingquarry")
1659 (version "2.0")
1660 (source (origin
1661 (method url-fetch)
1662 (uri (string-append
1663 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1664 version ".tar.gz"))
1665 (sha256
1666 (base32
1667 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1668 (build-system gnu-build-system)
1669 (arguments
1670 '(#:tests? #f ; no "check" target
1671 #:phases
1672 (modify-phases %standard-phases
1673 (delete 'configure)
1674 (replace 'install
1675 (lambda* (#:key outputs #:allow-other-keys)
1676 (let* ((out (assoc-ref outputs "out"))
1677 (bin (string-append out "/bin"))
1678 (doc (string-append out "/share/doc/codingquarry")))
1679 (install-file "INSTRUCTIONS.pdf" doc)
1680 (copy-recursively "QuarryFiles"
1681 (string-append out "/QuarryFiles"))
1682 (install-file "CodingQuarry" bin)
1683 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1684 (inputs `(("openmpi" ,openmpi)))
1685 (native-search-paths
1686 (list (search-path-specification
1687 (variable "QUARRY_PATH")
1688 (files '("QuarryFiles")))))
1689 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1690 (synopsis "Fungal gene predictor")
1691 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1692 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1693 (home-page "https://sourceforge.net/projects/codingquarry/")
1694 (license license:gpl3+)))
1695
1696 (define-public couger
1697 (package
1698 (name "couger")
1699 (version "1.8.2")
1700 (source (origin
1701 (method url-fetch)
1702 (uri (string-append
1703 "http://couger.oit.duke.edu/static/assets/COUGER"
1704 version ".zip"))
1705 (sha256
1706 (base32
1707 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1708 (build-system gnu-build-system)
1709 (arguments
1710 `(#:tests? #f
1711 #:phases
1712 (modify-phases %standard-phases
1713 (delete 'configure)
1714 (delete 'build)
1715 (replace
1716 'install
1717 (lambda* (#:key outputs #:allow-other-keys)
1718 (let* ((out (assoc-ref outputs "out"))
1719 (bin (string-append out "/bin")))
1720 (copy-recursively "src" (string-append out "/src"))
1721 (mkdir bin)
1722 ;; Add "src" directory to module lookup path.
1723 (substitute* "couger"
1724 (("from argparse")
1725 (string-append "import sys\nsys.path.append(\""
1726 out "\")\nfrom argparse")))
1727 (install-file "couger" bin))
1728 #t))
1729 (add-after
1730 'install 'wrap-program
1731 (lambda* (#:key inputs outputs #:allow-other-keys)
1732 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1733 (let* ((out (assoc-ref outputs "out"))
1734 (path (getenv "PYTHONPATH")))
1735 (wrap-program (string-append out "/bin/couger")
1736 `("PYTHONPATH" ":" prefix (,path))))
1737 #t)))))
1738 (inputs
1739 `(("python" ,python-2)
1740 ("python2-pillow" ,python2-pillow)
1741 ("python2-numpy" ,python2-numpy)
1742 ("python2-scipy" ,python2-scipy)
1743 ("python2-matplotlib" ,python2-matplotlib)))
1744 (propagated-inputs
1745 `(("r-minimal" ,r-minimal)
1746 ("libsvm" ,libsvm)
1747 ("randomjungle" ,randomjungle)))
1748 (native-inputs
1749 `(("unzip" ,unzip)))
1750 (home-page "http://couger.oit.duke.edu")
1751 (synopsis "Identify co-factors in sets of genomic regions")
1752 (description
1753 "COUGER can be applied to any two sets of genomic regions bound by
1754 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1755 putative co-factors that provide specificity to each TF. The framework
1756 determines the genomic targets uniquely-bound by each TF, and identifies a
1757 small set of co-factors that best explain the in vivo binding differences
1758 between the two TFs.
1759
1760 COUGER uses classification algorithms (support vector machines and random
1761 forests) with features that reflect the DNA binding specificities of putative
1762 co-factors. The features are generated either from high-throughput TF-DNA
1763 binding data (from protein binding microarray experiments), or from large
1764 collections of DNA motifs.")
1765 (license license:gpl3+)))
1766
1767 (define-public clustal-omega
1768 (package
1769 (name "clustal-omega")
1770 (version "1.2.1")
1771 (source (origin
1772 (method url-fetch)
1773 (uri (string-append
1774 "http://www.clustal.org/omega/clustal-omega-"
1775 version ".tar.gz"))
1776 (sha256
1777 (base32
1778 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1779 (build-system gnu-build-system)
1780 (inputs
1781 `(("argtable" ,argtable)))
1782 (home-page "http://www.clustal.org/omega/")
1783 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1784 (description
1785 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1786 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1787 of handling data-sets of hundreds of thousands of sequences in reasonable
1788 time.")
1789 (license license:gpl2+)))
1790
1791 (define-public crossmap
1792 (package
1793 (name "crossmap")
1794 (version "0.2.1")
1795 (source (origin
1796 (method url-fetch)
1797 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1798 version ".tar.gz"))
1799 (sha256
1800 (base32
1801 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1802 ;; This patch has been sent upstream already and is available
1803 ;; for download from Sourceforge, but it has not been merged.
1804 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1805 (modules '((guix build utils)))
1806 ;; remove bundled copy of pysam
1807 (snippet
1808 '(delete-file-recursively "lib/pysam"))))
1809 (build-system python-build-system)
1810 (arguments
1811 `(#:python ,python-2
1812 #:phases
1813 (alist-cons-after
1814 'unpack 'set-env
1815 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1816 %standard-phases)))
1817 (inputs
1818 `(("python-numpy" ,python2-numpy)
1819 ("python-pysam" ,python2-pysam)
1820 ("zlib" ,zlib)))
1821 (native-inputs
1822 `(("python-cython" ,python2-cython)
1823 ("python-nose" ,python2-nose)))
1824 (home-page "http://crossmap.sourceforge.net/")
1825 (synopsis "Convert genome coordinates between assemblies")
1826 (description
1827 "CrossMap is a program for conversion of genome coordinates or annotation
1828 files between different genome assemblies. It supports most commonly used
1829 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1830 (license license:gpl2+)))
1831
1832 (define-public cufflinks
1833 (package
1834 (name "cufflinks")
1835 (version "2.2.1")
1836 (source (origin
1837 (method url-fetch)
1838 (uri (string-append "http://cole-trapnell-lab.github.io/"
1839 "cufflinks/assets/downloads/cufflinks-"
1840 version ".tar.gz"))
1841 (sha256
1842 (base32
1843 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1844 (build-system gnu-build-system)
1845 (arguments
1846 `(#:make-flags
1847 (list
1848 ;; The includes for "eigen" are located in a subdirectory.
1849 (string-append "EIGEN_CPPFLAGS="
1850 "-I" (assoc-ref %build-inputs "eigen")
1851 "/include/eigen3/")
1852 ;; Cufflinks must be linked with various boost libraries.
1853 (string-append "LDFLAGS="
1854 (string-join '("-lboost_system"
1855 "-lboost_serialization"
1856 "-lboost_thread"))))
1857 #:phases
1858 (modify-phases %standard-phases
1859 (add-after 'unpack 'fix-search-for-bam
1860 (lambda _
1861 (substitute* '("ax_bam.m4"
1862 "configure"
1863 "src/hits.h")
1864 (("<bam/sam\\.h>") "<samtools/sam.h>")
1865 (("<bam/bam\\.h>") "<samtools/bam.h>")
1866 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1867 #t)))
1868 #:configure-flags
1869 (list (string-append "--with-bam="
1870 (assoc-ref %build-inputs "samtools")))))
1871 (inputs
1872 `(("eigen" ,eigen)
1873 ("samtools" ,samtools-0.1)
1874 ("htslib" ,htslib)
1875 ("boost" ,boost)
1876 ("python" ,python-2)
1877 ("zlib" ,zlib)))
1878 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1879 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1880 (description
1881 "Cufflinks assembles RNA transcripts, estimates their abundances,
1882 and tests for differential expression and regulation in RNA-Seq
1883 samples. It accepts aligned RNA-Seq reads and assembles the
1884 alignments into a parsimonious set of transcripts. Cufflinks then
1885 estimates the relative abundances of these transcripts based on how
1886 many reads support each one, taking into account biases in library
1887 preparation protocols.")
1888 (license license:boost1.0)))
1889
1890 (define-public cutadapt
1891 (package
1892 (name "cutadapt")
1893 (version "1.12")
1894 (source (origin
1895 (method url-fetch)
1896 (uri (string-append
1897 "https://github.com/marcelm/cutadapt/archive/v"
1898 version ".tar.gz"))
1899 (file-name (string-append name "-" version ".tar.gz"))
1900 (sha256
1901 (base32
1902 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1903 (build-system python-build-system)
1904 (arguments
1905 `(#:phases
1906 (modify-phases %standard-phases
1907 ;; The tests must be run after installation.
1908 (delete 'check)
1909 (add-after 'install 'check
1910 (lambda* (#:key inputs outputs #:allow-other-keys)
1911 (setenv "PYTHONPATH"
1912 (string-append
1913 (getenv "PYTHONPATH")
1914 ":" (assoc-ref outputs "out")
1915 "/lib/python"
1916 (string-take (string-take-right
1917 (assoc-ref inputs "python") 5) 3)
1918 "/site-packages"))
1919 (zero? (system* "nosetests" "-P" "tests")))))))
1920 (inputs
1921 `(("python-xopen" ,python-xopen)))
1922 (native-inputs
1923 `(("python-cython" ,python-cython)
1924 ("python-nose" ,python-nose)))
1925 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1926 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1927 (description
1928 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1929 other types of unwanted sequence from high-throughput sequencing reads.")
1930 (license license:expat)))
1931
1932 (define-public libbigwig
1933 (package
1934 (name "libbigwig")
1935 (version "0.1.4")
1936 (source (origin
1937 (method url-fetch)
1938 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1939 "archive/" version ".tar.gz"))
1940 (file-name (string-append name "-" version ".tar.gz"))
1941 (sha256
1942 (base32
1943 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1944 (build-system gnu-build-system)
1945 (arguments
1946 `(#:test-target "test"
1947 #:make-flags
1948 (list "CC=gcc"
1949 (string-append "prefix=" (assoc-ref %outputs "out")))
1950 #:phases
1951 (modify-phases %standard-phases
1952 (delete 'configure)
1953 (add-before 'check 'disable-curl-test
1954 (lambda _
1955 (substitute* "Makefile"
1956 (("./test/testRemote.*") ""))
1957 #t))
1958 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1959 ;; there has not yet been a release containing this change.
1960 (add-before 'install 'create-target-dirs
1961 (lambda* (#:key outputs #:allow-other-keys)
1962 (let ((out (assoc-ref outputs "out")))
1963 (mkdir-p (string-append out "/lib"))
1964 (mkdir-p (string-append out "/include"))
1965 #t))))))
1966 (inputs
1967 `(("zlib" ,zlib)
1968 ("curl" ,curl)))
1969 (native-inputs
1970 `(("doxygen" ,doxygen)))
1971 (home-page "https://github.com/dpryan79/libBigWig")
1972 (synopsis "C library for handling bigWig files")
1973 (description
1974 "This package provides a C library for parsing local and remote BigWig
1975 files.")
1976 (license license:expat)))
1977
1978 (define-public python-pybigwig
1979 (package
1980 (name "python-pybigwig")
1981 (version "0.2.5")
1982 (source (origin
1983 (method url-fetch)
1984 (uri (pypi-uri "pyBigWig" version))
1985 (sha256
1986 (base32
1987 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1988 (modules '((guix build utils)))
1989 (snippet
1990 '(begin
1991 ;; Delete bundled libBigWig sources
1992 (delete-file-recursively "libBigWig")))))
1993 (build-system python-build-system)
1994 (arguments
1995 `(#:phases
1996 (modify-phases %standard-phases
1997 (add-after 'unpack 'link-with-libBigWig
1998 (lambda* (#:key inputs #:allow-other-keys)
1999 (substitute* "setup.py"
2000 (("libs=\\[") "libs=[\"BigWig\", "))
2001 #t)))))
2002 (inputs
2003 `(("libbigwig" ,libbigwig)
2004 ("zlib" ,zlib)
2005 ("curl" ,curl)))
2006 (home-page "https://github.com/dpryan79/pyBigWig")
2007 (synopsis "Access bigWig files in Python using libBigWig")
2008 (description
2009 "This package provides Python bindings to the libBigWig library for
2010 accessing bigWig files.")
2011 (license license:expat)))
2012
2013 (define-public python2-pybigwig
2014 (package-with-python2 python-pybigwig))
2015
2016 (define-public python-dendropy
2017 (package
2018 (name "python-dendropy")
2019 (version "4.2.0")
2020 (source
2021 (origin
2022 (method url-fetch)
2023 (uri (pypi-uri "DendroPy" version))
2024 (sha256
2025 (base32
2026 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
2027 (patches (search-patches "python-dendropy-fix-tests.patch"))))
2028 (build-system python-build-system)
2029 (home-page "http://packages.python.org/DendroPy/")
2030 (synopsis "Library for phylogenetics and phylogenetic computing")
2031 (description
2032 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2033 writing, simulation, processing and manipulation of phylogenetic
2034 trees (phylogenies) and characters.")
2035 (license license:bsd-3)
2036 (properties `((python2-variant . ,(delay python2-dendropy))))))
2037
2038 (define-public python2-dendropy
2039 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2040 (package
2041 (inherit base)
2042 (arguments
2043 `(#:python ,python-2
2044 #:phases
2045 (modify-phases %standard-phases
2046 (replace 'check
2047 ;; There is currently a test failure that only happens on some
2048 ;; systems, and only using "setup.py test"
2049 (lambda _ (zero? (system* "nosetests")))))))
2050 (native-inputs `(("python2-nose" ,python2-nose)
2051 ,@(package-native-inputs base))))))
2052
2053
2054 (define-public deeptools
2055 (package
2056 (name "deeptools")
2057 (version "2.1.1")
2058 (source (origin
2059 (method url-fetch)
2060 (uri (string-append "https://github.com/fidelram/deepTools/"
2061 "archive/" version ".tar.gz"))
2062 (file-name (string-append name "-" version ".tar.gz"))
2063 (sha256
2064 (base32
2065 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
2066 (build-system python-build-system)
2067 (arguments
2068 `(#:python ,python-2))
2069 (inputs
2070 `(("python-scipy" ,python2-scipy)
2071 ("python-numpy" ,python2-numpy)
2072 ("python-numpydoc" ,python2-numpydoc)
2073 ("python-matplotlib" ,python2-matplotlib)
2074 ("python-bx-python" ,python2-bx-python)
2075 ("python-pysam" ,python2-pysam)
2076 ("python-pybigwig" ,python2-pybigwig)))
2077 (native-inputs
2078 `(("python-mock" ,python2-mock) ;for tests
2079 ("python-nose" ,python2-nose) ;for tests
2080 ("python-pytz" ,python2-pytz))) ;for tests
2081 (home-page "https://github.com/fidelram/deepTools")
2082 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2083 (description
2084 "DeepTools addresses the challenge of handling the large amounts of data
2085 that are now routinely generated from DNA sequencing centers. To do so,
2086 deepTools contains useful modules to process the mapped reads data to create
2087 coverage files in standard bedGraph and bigWig file formats. By doing so,
2088 deepTools allows the creation of normalized coverage files or the comparison
2089 between two files (for example, treatment and control). Finally, using such
2090 normalized and standardized files, multiple visualizations can be created to
2091 identify enrichments with functional annotations of the genome.")
2092 (license license:gpl3+)))
2093
2094 (define-public diamond
2095 (package
2096 (name "diamond")
2097 (version "0.9.6")
2098 (source (origin
2099 (method url-fetch)
2100 (uri (string-append
2101 "https://github.com/bbuchfink/diamond/archive/v"
2102 version ".tar.gz"))
2103 (file-name (string-append name "-" version ".tar.gz"))
2104 (sha256
2105 (base32
2106 "1y8a10b695pvgn7kk2s87jdwbdf7iszpnr6139pw8ina1ajs4w8y"))))
2107 (build-system cmake-build-system)
2108 (arguments
2109 '(#:tests? #f ; no "check" target
2110 #:phases
2111 (modify-phases %standard-phases
2112 (add-after 'unpack 'remove-native-compilation
2113 (lambda _
2114 (substitute* "CMakeLists.txt" (("-march=native") ""))
2115 #t)))))
2116 (inputs
2117 `(("zlib" ,zlib)))
2118 (home-page "https://github.com/bbuchfink/diamond")
2119 (synopsis "Accelerated BLAST compatible local sequence aligner")
2120 (description
2121 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2122 translated DNA query sequences against a protein reference database (BLASTP
2123 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2124 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2125 data and settings.")
2126 (license license:agpl3+)))
2127
2128 (define-public discrover
2129 (package
2130 (name "discrover")
2131 (version "1.6.0")
2132 (source
2133 (origin
2134 (method url-fetch)
2135 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2136 version ".tar.gz"))
2137 (file-name (string-append name "-" version ".tar.gz"))
2138 (sha256
2139 (base32
2140 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2141 (build-system cmake-build-system)
2142 (arguments
2143 `(#:tests? #f ; there are no tests
2144 #:phases
2145 (modify-phases %standard-phases
2146 (add-after 'unpack 'add-missing-includes
2147 (lambda _
2148 (substitute* "src/executioninformation.hpp"
2149 (("#define EXECUTIONINFORMATION_HPP" line)
2150 (string-append line "\n#include <random>")))
2151 (substitute* "src/plasma/fasta.hpp"
2152 (("#define FASTA_HPP" line)
2153 (string-append line "\n#include <random>")))
2154 #t)))))
2155 (inputs
2156 `(("boost" ,boost)
2157 ("cairo" ,cairo)))
2158 (native-inputs
2159 `(("texlive" ,texlive)
2160 ("imagemagick" ,imagemagick)))
2161 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2162 (synopsis "Discover discriminative nucleotide sequence motifs")
2163 (description "Discrover is a motif discovery method to find binding sites
2164 of nucleic acid binding proteins.")
2165 (license license:gpl3+)))
2166
2167 (define-public eigensoft
2168 (let ((revision "1")
2169 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2170 (package
2171 (name "eigensoft")
2172 (version (string-append "6.1.2-"
2173 revision "."
2174 (string-take commit 9)))
2175 (source
2176 (origin
2177 (method git-fetch)
2178 (uri (git-reference
2179 (url "https://github.com/DReichLab/EIG.git")
2180 (commit commit)))
2181 (file-name (string-append "eigensoft-" commit "-checkout"))
2182 (sha256
2183 (base32
2184 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2185 (modules '((guix build utils)))
2186 ;; Remove pre-built binaries.
2187 (snippet '(begin
2188 (delete-file-recursively "bin")
2189 (mkdir "bin")
2190 #t))))
2191 (build-system gnu-build-system)
2192 (arguments
2193 `(#:tests? #f ; There are no tests.
2194 #:make-flags '("CC=gcc")
2195 #:phases
2196 (modify-phases %standard-phases
2197 ;; There is no configure phase, but the Makefile is in a
2198 ;; sub-directory.
2199 (replace 'configure
2200 (lambda _
2201 (chdir "src")
2202 ;; The link flags are incomplete.
2203 (substitute* "Makefile"
2204 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2205 #t))
2206 ;; The provided install target only copies executables to
2207 ;; the "bin" directory in the build root.
2208 (add-after 'install 'actually-install
2209 (lambda* (#:key outputs #:allow-other-keys)
2210 (let* ((out (assoc-ref outputs "out"))
2211 (bin (string-append out "/bin")))
2212 (for-each (lambda (file)
2213 (install-file file bin))
2214 (find-files "../bin" ".*"))
2215 #t))))))
2216 (inputs
2217 `(("gsl" ,gsl)
2218 ("lapack" ,lapack)
2219 ("openblas" ,openblas)
2220 ("perl" ,perl)
2221 ("gfortran" ,gfortran "lib")))
2222 (home-page "https://github.com/DReichLab/EIG")
2223 (synopsis "Tools for population genetics")
2224 (description "The EIGENSOFT package provides tools for population
2225 genetics and stratification correction. EIGENSOFT implements methods commonly
2226 used in population genetics analyses such as PCA, computation of Tracy-Widom
2227 statistics, and finding related individuals in structured populations. It
2228 comes with a built-in plotting script and supports multiple file formats and
2229 quantitative phenotypes.")
2230 ;; The license of the eigensoft tools is Expat, but since it's
2231 ;; linking with the GNU Scientific Library (GSL) the effective
2232 ;; license is the GPL.
2233 (license license:gpl3+))))
2234
2235 (define-public edirect
2236 (package
2237 (name "edirect")
2238 (version "4.10")
2239 (source (origin
2240 (method url-fetch)
2241 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2242 "versions/2016-05-03/edirect.tar.gz"))
2243 (sha256
2244 (base32
2245 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2246 (build-system perl-build-system)
2247 (arguments
2248 `(#:tests? #f ;no "check" target
2249 #:phases
2250 (modify-phases %standard-phases
2251 (delete 'configure)
2252 (delete 'build)
2253 (replace 'install
2254 (lambda* (#:key outputs #:allow-other-keys)
2255 (let ((target (string-append (assoc-ref outputs "out")
2256 "/bin")))
2257 (mkdir-p target)
2258 (install-file "edirect.pl" target)
2259 #t)))
2260 (add-after
2261 'install 'wrap-program
2262 (lambda* (#:key inputs outputs #:allow-other-keys)
2263 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2264 (let* ((out (assoc-ref outputs "out"))
2265 (path (getenv "PERL5LIB")))
2266 (wrap-program (string-append out "/bin/edirect.pl")
2267 `("PERL5LIB" ":" prefix (,path)))))))))
2268 (inputs
2269 `(("perl-html-parser" ,perl-html-parser)
2270 ("perl-encode-locale" ,perl-encode-locale)
2271 ("perl-file-listing" ,perl-file-listing)
2272 ("perl-html-tagset" ,perl-html-tagset)
2273 ("perl-html-tree" ,perl-html-tree)
2274 ("perl-http-cookies" ,perl-http-cookies)
2275 ("perl-http-date" ,perl-http-date)
2276 ("perl-http-message" ,perl-http-message)
2277 ("perl-http-negotiate" ,perl-http-negotiate)
2278 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2279 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2280 ("perl-net-http" ,perl-net-http)
2281 ("perl-uri" ,perl-uri)
2282 ("perl-www-robotrules" ,perl-www-robotrules)
2283 ("perl" ,perl)))
2284 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2285 (synopsis "Tools for accessing the NCBI's set of databases")
2286 (description
2287 "Entrez Direct (EDirect) is a method for accessing the National Center
2288 for Biotechnology Information's (NCBI) set of interconnected
2289 databases (publication, sequence, structure, gene, variation, expression,
2290 etc.) from a terminal. Functions take search terms from command-line
2291 arguments. Individual operations are combined to build multi-step queries.
2292 Record retrieval and formatting normally complete the process.
2293
2294 EDirect also provides an argument-driven function that simplifies the
2295 extraction of data from document summaries or other results that are returned
2296 in structured XML format. This can eliminate the need for writing custom
2297 software to answer ad hoc questions.")
2298 (license license:public-domain)))
2299
2300 (define-public exonerate
2301 (package
2302 (name "exonerate")
2303 (version "2.4.0")
2304 (source
2305 (origin
2306 (method url-fetch)
2307 (uri
2308 (string-append
2309 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2310 "exonerate-" version ".tar.gz"))
2311 (sha256
2312 (base32
2313 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2314 (build-system gnu-build-system)
2315 (arguments
2316 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2317 (native-inputs
2318 `(("pkg-config" ,pkg-config)))
2319 (inputs
2320 `(("glib" ,glib)))
2321 (home-page
2322 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2323 (synopsis "Generic tool for biological sequence alignment")
2324 (description
2325 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2326 the alignment of sequences using a many alignment models, either exhaustive
2327 dynamic programming or a variety of heuristics.")
2328 (license license:gpl3)))
2329
2330 (define-public express
2331 (package
2332 (name "express")
2333 (version "1.5.1")
2334 (source (origin
2335 (method url-fetch)
2336 (uri
2337 (string-append
2338 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2339 version "/express-" version "-src.tgz"))
2340 (sha256
2341 (base32
2342 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2343 (build-system cmake-build-system)
2344 (arguments
2345 `(#:tests? #f ;no "check" target
2346 #:phases
2347 (alist-cons-after
2348 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2349 (lambda* (#:key inputs #:allow-other-keys)
2350 (substitute* "CMakeLists.txt"
2351 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2352 "set(Boost_USE_STATIC_LIBS OFF)")
2353 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2354 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2355 (substitute* "src/CMakeLists.txt"
2356 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2357 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2358 #t)
2359 %standard-phases)))
2360 (inputs
2361 `(("boost" ,boost)
2362 ("bamtools" ,bamtools)
2363 ("protobuf" ,protobuf)
2364 ("zlib" ,zlib)))
2365 (home-page "http://bio.math.berkeley.edu/eXpress")
2366 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2367 (description
2368 "eXpress is a streaming tool for quantifying the abundances of a set of
2369 target sequences from sampled subsequences. Example applications include
2370 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2371 analysis (from RNA-Seq), transcription factor binding quantification in
2372 ChIP-Seq, and analysis of metagenomic data.")
2373 (license license:artistic2.0)))
2374
2375 (define-public express-beta-diversity
2376 (package
2377 (name "express-beta-diversity")
2378 (version "1.0.7")
2379 (source (origin
2380 (method url-fetch)
2381 (uri
2382 (string-append
2383 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2384 version ".tar.gz"))
2385 (file-name (string-append name "-" version ".tar.gz"))
2386 (sha256
2387 (base32
2388 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2389 (build-system gnu-build-system)
2390 (arguments
2391 `(#:phases
2392 (modify-phases %standard-phases
2393 (delete 'configure)
2394 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2395 (replace 'check
2396 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2397 "-u"))))
2398 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2399 (replace 'install
2400 (lambda* (#:key outputs #:allow-other-keys)
2401 (let ((bin (string-append (assoc-ref outputs "out")
2402 "/bin")))
2403 (mkdir-p bin)
2404 (install-file "scripts/convertToEBD.py" bin)
2405 (install-file "bin/ExpressBetaDiversity" bin)
2406 #t))))))
2407 (inputs
2408 `(("python" ,python-2)))
2409 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2410 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2411 (description
2412 "Express Beta Diversity (EBD) calculates ecological beta diversity
2413 (dissimilarity) measures between biological communities. EBD implements a
2414 variety of diversity measures including those that make use of phylogenetic
2415 similarity of community members.")
2416 (license license:gpl3+)))
2417
2418 (define-public fasttree
2419 (package
2420 (name "fasttree")
2421 (version "2.1.10")
2422 (source (origin
2423 (method url-fetch)
2424 (uri (string-append
2425 "http://www.microbesonline.org/fasttree/FastTree-"
2426 version ".c"))
2427 (sha256
2428 (base32
2429 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2430 (build-system gnu-build-system)
2431 (arguments
2432 `(#:tests? #f ; no "check" target
2433 #:phases
2434 (modify-phases %standard-phases
2435 (delete 'unpack)
2436 (delete 'configure)
2437 (replace 'build
2438 (lambda* (#:key source #:allow-other-keys)
2439 (and (zero? (system* "gcc"
2440 "-O3"
2441 "-finline-functions"
2442 "-funroll-loops"
2443 "-Wall"
2444 "-o"
2445 "FastTree"
2446 source
2447 "-lm"))
2448 (zero? (system* "gcc"
2449 "-DOPENMP"
2450 "-fopenmp"
2451 "-O3"
2452 "-finline-functions"
2453 "-funroll-loops"
2454 "-Wall"
2455 "-o"
2456 "FastTreeMP"
2457 source
2458 "-lm")))))
2459 (replace 'install
2460 (lambda* (#:key outputs #:allow-other-keys)
2461 (let ((bin (string-append (assoc-ref outputs "out")
2462 "/bin")))
2463 (mkdir-p bin)
2464 (install-file "FastTree" bin)
2465 (install-file "FastTreeMP" bin)
2466 #t))))))
2467 (home-page "http://www.microbesonline.org/fasttree")
2468 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2469 (description
2470 "FastTree can handle alignments with up to a million of sequences in a
2471 reasonable amount of time and memory. For large alignments, FastTree is
2472 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2473 (license license:gpl2+)))
2474
2475 (define-public fastx-toolkit
2476 (package
2477 (name "fastx-toolkit")
2478 (version "0.0.14")
2479 (source (origin
2480 (method url-fetch)
2481 (uri
2482 (string-append
2483 "https://github.com/agordon/fastx_toolkit/releases/download/"
2484 version "/fastx_toolkit-" version ".tar.bz2"))
2485 (sha256
2486 (base32
2487 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2488 (build-system gnu-build-system)
2489 (inputs
2490 `(("libgtextutils" ,libgtextutils)))
2491 (native-inputs
2492 `(("pkg-config" ,pkg-config)))
2493 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2494 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2495 (description
2496 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2497 FASTA/FASTQ files preprocessing.
2498
2499 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2500 containing multiple short-reads sequences. The main processing of such
2501 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2502 is sometimes more productive to preprocess the files before mapping the
2503 sequences to the genome---manipulating the sequences to produce better mapping
2504 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2505 (license license:agpl3+)))
2506
2507 (define-public flexbar
2508 (package
2509 (name "flexbar")
2510 (version "2.5")
2511 (source (origin
2512 (method url-fetch)
2513 (uri
2514 (string-append "mirror://sourceforge/flexbar/"
2515 version "/flexbar_v" version "_src.tgz"))
2516 (sha256
2517 (base32
2518 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2519 (build-system cmake-build-system)
2520 (arguments
2521 `(#:configure-flags (list
2522 (string-append "-DFLEXBAR_BINARY_DIR="
2523 (assoc-ref %outputs "out")
2524 "/bin/"))
2525 #:phases
2526 (alist-replace
2527 'check
2528 (lambda* (#:key outputs #:allow-other-keys)
2529 (setenv "PATH" (string-append
2530 (assoc-ref outputs "out") "/bin:"
2531 (getenv "PATH")))
2532 (chdir "../flexbar_v2.5_src/test")
2533 (zero? (system* "bash" "flexbar_validate.sh")))
2534 (alist-delete 'install %standard-phases))))
2535 (inputs
2536 `(("tbb" ,tbb)
2537 ("zlib" ,zlib)))
2538 (native-inputs
2539 `(("pkg-config" ,pkg-config)
2540 ("seqan" ,seqan)))
2541 (home-page "http://flexbar.sourceforge.net")
2542 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2543 (description
2544 "Flexbar preprocesses high-throughput nucleotide sequencing data
2545 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2546 Moreover, trimming and filtering features are provided. Flexbar increases
2547 read mapping rates and improves genome and transcriptome assemblies. It
2548 supports next-generation sequencing data in fasta/q and csfasta/q format from
2549 Illumina, Roche 454, and the SOLiD platform.")
2550 (license license:gpl3)))
2551
2552 (define-public fraggenescan
2553 (package
2554 (name "fraggenescan")
2555 (version "1.30")
2556 (source
2557 (origin
2558 (method url-fetch)
2559 (uri
2560 (string-append "mirror://sourceforge/fraggenescan/"
2561 "FragGeneScan" version ".tar.gz"))
2562 (sha256
2563 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2564 (build-system gnu-build-system)
2565 (arguments
2566 `(#:phases
2567 (modify-phases %standard-phases
2568 (delete 'configure)
2569 (add-before 'build 'patch-paths
2570 (lambda* (#:key outputs #:allow-other-keys)
2571 (let* ((out (string-append (assoc-ref outputs "out")))
2572 (share (string-append out "/share/fraggenescan/")))
2573 (substitute* "run_FragGeneScan.pl"
2574 (("system\\(\"rm")
2575 (string-append "system(\"" (which "rm")))
2576 (("system\\(\"mv")
2577 (string-append "system(\"" (which "mv")))
2578 (("\\\"awk") (string-append "\"" (which "awk")))
2579 ;; This script and other programs expect the training files
2580 ;; to be in the non-standard location bin/train/XXX. Change
2581 ;; this to be share/fraggenescan/train/XXX instead.
2582 (("^\\$train.file = \\$dir.*")
2583 (string-append "$train_file = \""
2584 share
2585 "train/\".$FGS_train_file;")))
2586 (substitute* "run_hmm.c"
2587 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2588 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2589 #t))
2590 (replace 'build
2591 (lambda _ (and (zero? (system* "make" "clean"))
2592 (zero? (system* "make" "fgs")))))
2593 (replace 'install
2594 (lambda* (#:key outputs #:allow-other-keys)
2595 (let* ((out (string-append (assoc-ref outputs "out")))
2596 (bin (string-append out "/bin/"))
2597 (share (string-append out "/share/fraggenescan/train")))
2598 (install-file "run_FragGeneScan.pl" bin)
2599 (install-file "FragGeneScan" bin)
2600 (copy-recursively "train" share))))
2601 (delete 'check)
2602 (add-after 'install 'post-install-check
2603 ;; In lieu of 'make check', run one of the examples and check the
2604 ;; output files gets created.
2605 (lambda* (#:key outputs #:allow-other-keys)
2606 (let* ((out (string-append (assoc-ref outputs "out")))
2607 (bin (string-append out "/bin/"))
2608 (frag (string-append bin "run_FragGeneScan.pl")))
2609 (and (zero? (system* frag ; Test complete genome.
2610 "-genome=./example/NC_000913.fna"
2611 "-out=./test2"
2612 "-complete=1"
2613 "-train=complete"))
2614 (file-exists? "test2.faa")
2615 (file-exists? "test2.ffn")
2616 (file-exists? "test2.gff")
2617 (file-exists? "test2.out")
2618 (zero? (system* ; Test incomplete sequences.
2619 frag
2620 "-genome=./example/NC_000913-fgs.ffn"
2621 "-out=out"
2622 "-complete=0"
2623 "-train=454_30")))))))))
2624 (inputs
2625 `(("perl" ,perl)
2626 ("python" ,python-2))) ;not compatible with python 3.
2627 (home-page "https://sourceforge.net/projects/fraggenescan/")
2628 (synopsis "Finds potentially fragmented genes in short reads")
2629 (description
2630 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2631 short and error-prone DNA sequencing reads. It can also be applied to predict
2632 genes in incomplete assemblies or complete genomes.")
2633 ;; GPL3+ according to private correspondense with the authors.
2634 (license license:gpl3+)))
2635
2636 (define-public fxtract
2637 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2638 (package
2639 (name "fxtract")
2640 (version "2.3")
2641 (source
2642 (origin
2643 (method url-fetch)
2644 (uri (string-append
2645 "https://github.com/ctSkennerton/fxtract/archive/"
2646 version ".tar.gz"))
2647 (file-name (string-append "ctstennerton-util-"
2648 (string-take util-commit 7)
2649 "-checkout"))
2650 (sha256
2651 (base32
2652 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2653 (build-system gnu-build-system)
2654 (arguments
2655 `(#:make-flags (list
2656 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2657 "CC=gcc")
2658 #:test-target "fxtract_test"
2659 #:phases
2660 (modify-phases %standard-phases
2661 (delete 'configure)
2662 (add-before 'build 'copy-util
2663 (lambda* (#:key inputs #:allow-other-keys)
2664 (rmdir "util")
2665 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2666 #t))
2667 ;; Do not use make install as this requires additional dependencies.
2668 (replace 'install
2669 (lambda* (#:key outputs #:allow-other-keys)
2670 (let* ((out (assoc-ref outputs "out"))
2671 (bin (string-append out"/bin")))
2672 (install-file "fxtract" bin)
2673 #t))))))
2674 (inputs
2675 `(("pcre" ,pcre)
2676 ("zlib" ,zlib)))
2677 (native-inputs
2678 ;; ctskennerton-util is licensed under GPL2.
2679 `(("ctskennerton-util"
2680 ,(origin
2681 (method git-fetch)
2682 (uri (git-reference
2683 (url "https://github.com/ctSkennerton/util.git")
2684 (commit util-commit)))
2685 (file-name (string-append
2686 "ctstennerton-util-" util-commit "-checkout"))
2687 (sha256
2688 (base32
2689 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2690 (home-page "https://github.com/ctSkennerton/fxtract")
2691 (synopsis "Extract sequences from FASTA and FASTQ files")
2692 (description
2693 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2694 or FASTQ) file given a subsequence. It uses a simple substring search for
2695 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2696 lookups or multi-pattern searching as required. By default fxtract looks in
2697 the sequence of each record but can also be told to look in the header,
2698 comment or quality sections.")
2699 ;; 'util' requires SSE instructions.
2700 (supported-systems '("x86_64-linux"))
2701 (license license:expat))))
2702
2703 (define-public gemma
2704 (package
2705 (name "gemma")
2706 (version "0.96")
2707 (source (origin
2708 (method url-fetch)
2709 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2710 version ".tar.gz"))
2711 (file-name (string-append name "-" version ".tar.gz"))
2712 (sha256
2713 (base32
2714 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))))
2715 (inputs
2716 `(("gsl" ,gsl)
2717 ("lapack" ,lapack)
2718 ("zlib" ,zlib)))
2719 (build-system gnu-build-system)
2720 (arguments
2721 `(#:make-flags '("FORCE_DYNAMIC=1") ; use shared libs
2722 #:phases
2723 (modify-phases %standard-phases
2724 (delete 'configure)
2725 (add-before 'build 'bin-mkdir
2726 (lambda _
2727 (mkdir-p "bin")))
2728 (replace 'install
2729 (lambda* (#:key outputs #:allow-other-keys)
2730 (let ((out (assoc-ref outputs "out")))
2731 (install-file "bin/gemma"
2732 (string-append
2733 out "/bin"))))))
2734 #:tests? #f)) ; no tests included yet
2735 (home-page "https://github.com/xiangzhou/GEMMA")
2736 (synopsis "Tool for genome-wide efficient mixed model association")
2737 (description
2738 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2739 standard linear mixed model resolver with application in genome-wide
2740 association studies (GWAS).")
2741 (license license:gpl3)))
2742
2743 (define-public grit
2744 (package
2745 (name "grit")
2746 (version "2.0.2")
2747 (source (origin
2748 (method url-fetch)
2749 (uri (string-append
2750 "https://github.com/nboley/grit/archive/"
2751 version ".tar.gz"))
2752 (file-name (string-append name "-" version ".tar.gz"))
2753 (sha256
2754 (base32
2755 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2756 (build-system python-build-system)
2757 (arguments
2758 `(#:python ,python-2
2759 #:phases
2760 (alist-cons-after
2761 'unpack 'generate-from-cython-sources
2762 (lambda* (#:key inputs outputs #:allow-other-keys)
2763 ;; Delete these C files to force fresh generation from pyx sources.
2764 (delete-file "grit/sparsify_support_fns.c")
2765 (delete-file "grit/call_peaks_support_fns.c")
2766 (substitute* "setup.py"
2767 (("Cython.Setup") "Cython.Build")
2768 ;; Add numpy include path to fix compilation
2769 (("pyx\", \\]")
2770 (string-append "pyx\", ], include_dirs = ['"
2771 (assoc-ref inputs "python-numpy")
2772 "/lib/python2.7/site-packages/numpy/core/include/"
2773 "']"))) #t)
2774 %standard-phases)))
2775 (inputs
2776 `(("python-scipy" ,python2-scipy)
2777 ("python-numpy" ,python2-numpy)
2778 ("python-pysam" ,python2-pysam)
2779 ("python-networkx" ,python2-networkx)))
2780 (native-inputs
2781 `(("python-cython" ,python2-cython)))
2782 (home-page "http://grit-bio.org")
2783 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2784 (description
2785 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2786 full length transcript models. When none of these data sources are available,
2787 GRIT can be run by providing a candidate set of TES or TSS sites. In
2788 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2789 also be run in quantification mode, where it uses a provided GTF file and just
2790 estimates transcript expression.")
2791 (license license:gpl3+)))
2792
2793 (define-public hisat
2794 (package
2795 (name "hisat")
2796 (version "0.1.4")
2797 (source (origin
2798 (method url-fetch)
2799 (uri (string-append
2800 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2801 version "-beta-source.zip"))
2802 (sha256
2803 (base32
2804 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2805 (build-system gnu-build-system)
2806 (arguments
2807 `(#:tests? #f ;no check target
2808 #:make-flags '("allall"
2809 ;; Disable unsupported `popcnt' instructions on
2810 ;; architectures other than x86_64
2811 ,@(if (string-prefix? "x86_64"
2812 (or (%current-target-system)
2813 (%current-system)))
2814 '()
2815 '("POPCNT_CAPABILITY=0")))
2816 #:phases
2817 (alist-cons-after
2818 'unpack 'patch-sources
2819 (lambda _
2820 ;; XXX Cannot use snippet because zip files are not supported
2821 (substitute* "Makefile"
2822 (("^CC = .*$") "CC = gcc")
2823 (("^CPP = .*$") "CPP = g++")
2824 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2825 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2826 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2827 (substitute* '("hisat-build" "hisat-inspect")
2828 (("/usr/bin/env") (which "env"))))
2829 (alist-replace
2830 'install
2831 (lambda* (#:key outputs #:allow-other-keys)
2832 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2833 (for-each (lambda (file)
2834 (install-file file bin))
2835 (find-files
2836 "."
2837 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2838 (alist-delete 'configure %standard-phases)))))
2839 (native-inputs
2840 `(("unzip" ,unzip)))
2841 (inputs
2842 `(("perl" ,perl)
2843 ("python" ,python)
2844 ("zlib" ,zlib)))
2845 ;; Non-portable SSE instructions are used so building fails on platforms
2846 ;; other than x86_64.
2847 (supported-systems '("x86_64-linux"))
2848 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2849 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2850 (description
2851 "HISAT is a fast and sensitive spliced alignment program for mapping
2852 RNA-seq reads. In addition to one global FM index that represents a whole
2853 genome, HISAT uses a large set of small FM indexes that collectively cover the
2854 whole genome. These small indexes (called local indexes) combined with
2855 several alignment strategies enable effective alignment of RNA-seq reads, in
2856 particular, reads spanning multiple exons.")
2857 (license license:gpl3+)))
2858
2859 (define-public hisat2
2860 (package
2861 (name "hisat2")
2862 (version "2.0.5")
2863 (source
2864 (origin
2865 (method url-fetch)
2866 ;; FIXME: a better source URL is
2867 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2868 ;; "/downloads/hisat2-" version "-source.zip")
2869 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2870 ;; but it is currently unavailable.
2871 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2872 (file-name (string-append name "-" version ".tar.gz"))
2873 (sha256
2874 (base32
2875 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2876 (build-system gnu-build-system)
2877 (arguments
2878 `(#:tests? #f ; no check target
2879 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2880 #:modules ((guix build gnu-build-system)
2881 (guix build utils)
2882 (srfi srfi-26))
2883 #:phases
2884 (modify-phases %standard-phases
2885 (add-after 'unpack 'make-deterministic
2886 (lambda _
2887 (substitute* "Makefile"
2888 (("`date`") "0"))
2889 #t))
2890 (delete 'configure)
2891 (replace 'install
2892 (lambda* (#:key outputs #:allow-other-keys)
2893 (let* ((out (assoc-ref outputs "out"))
2894 (bin (string-append out "/bin/"))
2895 (doc (string-append out "/share/doc/hisat2/")))
2896 (for-each
2897 (cut install-file <> bin)
2898 (find-files "."
2899 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2900 (mkdir-p doc)
2901 (install-file "doc/manual.inc.html" doc))
2902 #t)))))
2903 (native-inputs
2904 `(("unzip" ,unzip) ; needed for archive from ftp
2905 ("perl" ,perl)
2906 ("pandoc" ,ghc-pandoc))) ; for documentation
2907 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2908 (synopsis "Graph-based alignment of genomic sequencing reads")
2909 (description "HISAT2 is a fast and sensitive alignment program for mapping
2910 next-generation sequencing reads (both DNA and RNA) to a population of human
2911 genomes (as well as to a single reference genome). In addition to using one
2912 global @dfn{graph FM} (GFM) index that represents a population of human
2913 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2914 the whole genome. These small indexes, combined with several alignment
2915 strategies, enable rapid and accurate alignment of sequencing reads. This new
2916 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2917 ;; HISAT2 contains files from Bowtie2, which is released under
2918 ;; GPLv2 or later. The HISAT2 source files are released under
2919 ;; GPLv3 or later.
2920 (license license:gpl3+)))
2921
2922 (define-public hmmer
2923 (package
2924 (name "hmmer")
2925 (version "3.1b2")
2926 (source
2927 (origin
2928 (method url-fetch)
2929 (uri (string-append
2930 "http://eddylab.org/software/hmmer"
2931 (version-prefix version 1) "/"
2932 version "/hmmer-" version ".tar.gz"))
2933 (sha256
2934 (base32
2935 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2936 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2937 (build-system gnu-build-system)
2938 (native-inputs `(("perl" ,perl)))
2939 (home-page "http://hmmer.org/")
2940 (synopsis "Biosequence analysis using profile hidden Markov models")
2941 (description
2942 "HMMER is used for searching sequence databases for homologs of protein
2943 sequences, and for making protein sequence alignments. It implements methods
2944 using probabilistic models called profile hidden Markov models (profile
2945 HMMs).")
2946 (license (list license:gpl3+
2947 ;; The bundled library 'easel' is distributed
2948 ;; under The Janelia Farm Software License.
2949 (license:non-copyleft
2950 "file://easel/LICENSE"
2951 "See easel/LICENSE in the distribution.")))))
2952
2953 (define-public htseq
2954 (package
2955 (name "htseq")
2956 (version "0.6.1")
2957 (source (origin
2958 (method url-fetch)
2959 (uri (string-append
2960 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2961 version ".tar.gz"))
2962 (sha256
2963 (base32
2964 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2965 (build-system python-build-system)
2966 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2967 ;; Numpy needs to be propagated when htseq is used as a Python library.
2968 (propagated-inputs
2969 `(("python-numpy" ,python2-numpy)))
2970 (inputs
2971 `(("python-pysam" ,python2-pysam)))
2972 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2973 (synopsis "Analysing high-throughput sequencing data with Python")
2974 (description
2975 "HTSeq is a Python package that provides infrastructure to process data
2976 from high-throughput sequencing assays.")
2977 (license license:gpl3+)))
2978
2979 (define-public java-htsjdk
2980 (package
2981 (name "java-htsjdk")
2982 (version "1.129")
2983 (source (origin
2984 (method url-fetch)
2985 (uri (string-append
2986 "https://github.com/samtools/htsjdk/archive/"
2987 version ".tar.gz"))
2988 (file-name (string-append name "-" version ".tar.gz"))
2989 (sha256
2990 (base32
2991 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2992 (modules '((guix build utils)))
2993 ;; remove build dependency on git
2994 (snippet '(substitute* "build.xml"
2995 (("failifexecutionfails=\"true\"")
2996 "failifexecutionfails=\"false\"")))))
2997 (build-system ant-build-system)
2998 (arguments
2999 `(#:tests? #f ; test require Internet access
3000 #:make-flags
3001 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3002 "/share/java/htsjdk/"))
3003 #:build-target "all"
3004 #:phases
3005 (modify-phases %standard-phases
3006 ;; The build phase also installs the jars
3007 (delete 'install))))
3008 (home-page "http://samtools.github.io/htsjdk/")
3009 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3010 (description
3011 "HTSJDK is an implementation of a unified Java library for accessing
3012 common file formats, such as SAM and VCF, used for high-throughput
3013 sequencing (HTS) data. There are also an number of useful utilities for
3014 manipulating HTS data.")
3015 (license license:expat)))
3016
3017 (define-public htslib
3018 (package
3019 (name "htslib")
3020 (version "1.3.1")
3021 (source (origin
3022 (method url-fetch)
3023 (uri (string-append
3024 "https://github.com/samtools/htslib/releases/download/"
3025 version "/htslib-" version ".tar.bz2"))
3026 (sha256
3027 (base32
3028 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
3029 (build-system gnu-build-system)
3030 (arguments
3031 `(#:phases
3032 (modify-phases %standard-phases
3033 (add-after
3034 'unpack 'patch-tests
3035 (lambda _
3036 (substitute* "test/test.pl"
3037 (("/bin/bash") (which "bash")))
3038 #t)))))
3039 (inputs
3040 `(("zlib" ,zlib)))
3041 (native-inputs
3042 `(("perl" ,perl)))
3043 (home-page "http://www.htslib.org")
3044 (synopsis "C library for reading/writing high-throughput sequencing data")
3045 (description
3046 "HTSlib is a C library for reading/writing high-throughput sequencing
3047 data. It also provides the bgzip, htsfile, and tabix utilities.")
3048 ;; Files under cram/ are released under the modified BSD license;
3049 ;; the rest is released under the Expat license
3050 (license (list license:expat license:bsd-3))))
3051
3052 (define-public idr
3053 (package
3054 (name "idr")
3055 (version "2.0.0")
3056 (source (origin
3057 (method url-fetch)
3058 (uri (string-append
3059 "https://github.com/nboley/idr/archive/"
3060 version ".tar.gz"))
3061 (file-name (string-append name "-" version ".tar.gz"))
3062 (sha256
3063 (base32
3064 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3065 (build-system python-build-system)
3066 (arguments
3067 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3068 (propagated-inputs
3069 `(("python-scipy" ,python-scipy)
3070 ("python-sympy" ,python-sympy)
3071 ("python-numpy" ,python-numpy)
3072 ("python-matplotlib" ,python-matplotlib)))
3073 (native-inputs
3074 `(("python-cython" ,python-cython)))
3075 (home-page "https://github.com/nboley/idr")
3076 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3077 (description
3078 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3079 to measure the reproducibility of findings identified from replicate
3080 experiments and provide highly stable thresholds based on reproducibility.")
3081 (license license:gpl3+)))
3082
3083 (define-public jellyfish
3084 (package
3085 (name "jellyfish")
3086 (version "2.2.4")
3087 (source (origin
3088 (method url-fetch)
3089 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3090 "releases/download/v" version
3091 "/jellyfish-" version ".tar.gz"))
3092 (sha256
3093 (base32
3094 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3095 (build-system gnu-build-system)
3096 (outputs '("out" ;for library
3097 "ruby" ;for Ruby bindings
3098 "python")) ;for Python bindings
3099 (arguments
3100 `(#:configure-flags
3101 (list (string-append "--enable-ruby-binding="
3102 (assoc-ref %outputs "ruby"))
3103 (string-append "--enable-python-binding="
3104 (assoc-ref %outputs "python")))
3105 #:phases
3106 (modify-phases %standard-phases
3107 (add-before 'check 'set-SHELL-variable
3108 (lambda _
3109 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3110 ;; to run tests.
3111 (setenv "SHELL" (which "bash"))
3112 #t)))))
3113 (native-inputs
3114 `(("bc" ,bc)
3115 ("time" ,time)
3116 ("ruby" ,ruby)
3117 ("python" ,python-2)))
3118 (synopsis "Tool for fast counting of k-mers in DNA")
3119 (description
3120 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3121 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3122 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3123 is a command-line program that reads FASTA and multi-FASTA files containing
3124 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3125 translated into a human-readable text format using the @code{jellyfish dump}
3126 command, or queried for specific k-mers with @code{jellyfish query}.")
3127 (home-page "http://www.genome.umd.edu/jellyfish.html")
3128 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3129 (supported-systems '("x86_64-linux"))
3130 ;; The combined work is published under the GPLv3 or later. Individual
3131 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3132 (license (list license:gpl3+ license:expat))))
3133
3134 (define-public khmer
3135 (package
3136 (name "khmer")
3137 (version "2.0")
3138 (source
3139 (origin
3140 (method url-fetch)
3141 (uri (pypi-uri "khmer" version))
3142 (sha256
3143 (base32
3144 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3145 (patches (search-patches "khmer-use-libraries.patch"))))
3146 (build-system python-build-system)
3147 (arguments
3148 `(#:phases
3149 (modify-phases %standard-phases
3150 (add-after 'unpack 'set-paths
3151 (lambda* (#:key inputs outputs #:allow-other-keys)
3152 ;; Delete bundled libraries.
3153 (delete-file-recursively "third-party/zlib")
3154 (delete-file-recursively "third-party/bzip2")
3155 ;; Replace bundled seqan.
3156 (let* ((seqan-all "third-party/seqan")
3157 (seqan-include (string-append
3158 seqan-all "/core/include")))
3159 (delete-file-recursively seqan-all)
3160 (copy-recursively (string-append (assoc-ref inputs "seqan")
3161 "/include/seqan")
3162 (string-append seqan-include "/seqan")))
3163 ;; We do not replace the bundled MurmurHash as the canonical
3164 ;; repository for this code 'SMHasher' is unsuitable for
3165 ;; providing a library. See
3166 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3167 #t))
3168 (add-after 'unpack 'set-cc
3169 (lambda _
3170 (setenv "CC" "gcc")
3171 #t))
3172 ;; It is simpler to test after installation.
3173 (delete 'check)
3174 (add-after 'install 'post-install-check
3175 (lambda* (#:key inputs outputs #:allow-other-keys)
3176 (let ((out (assoc-ref outputs "out")))
3177 (setenv "PATH"
3178 (string-append
3179 (getenv "PATH")
3180 ":"
3181 (assoc-ref outputs "out")
3182 "/bin"))
3183 (setenv "PYTHONPATH"
3184 (string-append
3185 (getenv "PYTHONPATH")
3186 ":"
3187 out
3188 "/lib/python"
3189 (string-take (string-take-right
3190 (assoc-ref inputs "python") 5) 3)
3191 "/site-packages"))
3192 (with-directory-excursion "build"
3193 (zero? (system* "nosetests" "khmer" "--attr"
3194 "!known_failing")))))))))
3195 (native-inputs
3196 `(("seqan" ,seqan)
3197 ("python-nose" ,python-nose)))
3198 (inputs
3199 `(("zlib" ,zlib)
3200 ("bzip2" ,bzip2)
3201 ("python-screed" ,python-screed)
3202 ("python-bz2file" ,python-bz2file)
3203 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3204 ;; until the next version of khmer (likely 2.1) is released.
3205 ("gcc" ,gcc-4.9)))
3206 (home-page "https://khmer.readthedocs.org/")
3207 (synopsis "K-mer counting, filtering and graph traversal library")
3208 (description "The khmer software is a set of command-line tools for
3209 working with DNA shotgun sequencing data from genomes, transcriptomes,
3210 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3211 sometimes better. Khmer can also identify and fix problems with shotgun
3212 data.")
3213 ;; When building on i686, armhf and mips64el, we get the following error:
3214 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3215 (supported-systems '("x86_64-linux"))
3216 (license license:bsd-3)))
3217
3218 (define-public kaiju
3219 (package
3220 (name "kaiju")
3221 (version "1.5.0")
3222 (source (origin
3223 (method url-fetch)
3224 (uri (string-append
3225 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3226 version ".tar.gz"))
3227 (file-name (string-append name "-" version ".tar.gz"))
3228 (sha256
3229 (base32
3230 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3231 (build-system gnu-build-system)
3232 (arguments
3233 `(#:tests? #f ; There are no tests.
3234 #:phases
3235 (modify-phases %standard-phases
3236 (delete 'configure)
3237 (add-before 'build 'move-to-src-dir
3238 (lambda _ (chdir "src") #t))
3239 (replace 'install
3240 (lambda* (#:key inputs outputs #:allow-other-keys)
3241 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3242 (mkdir-p bin)
3243 (chdir "..")
3244 (copy-recursively "bin" bin)
3245 (copy-recursively "util" bin))
3246 #t)))))
3247 (inputs
3248 `(("perl" ,perl)))
3249 (home-page "http://kaiju.binf.ku.dk/")
3250 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3251 (description "Kaiju is a program for sensitive taxonomic classification
3252 of high-throughput sequencing reads from metagenomic whole genome sequencing
3253 experiments.")
3254 (license license:gpl3+)))
3255
3256 (define-public macs
3257 (package
3258 (name "macs")
3259 (version "2.1.0.20151222")
3260 (source (origin
3261 (method url-fetch)
3262 (uri (pypi-uri "MACS2" version))
3263 (sha256
3264 (base32
3265 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3266 (build-system python-build-system)
3267 (arguments
3268 `(#:python ,python-2 ; only compatible with Python 2.7
3269 #:tests? #f)) ; no test target
3270 (inputs
3271 `(("python-numpy" ,python2-numpy)))
3272 (home-page "https://github.com/taoliu/MACS/")
3273 (synopsis "Model based analysis for ChIP-Seq data")
3274 (description
3275 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3276 identifying transcript factor binding sites named Model-based Analysis of
3277 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3278 the significance of enriched ChIP regions and it improves the spatial
3279 resolution of binding sites through combining the information of both
3280 sequencing tag position and orientation.")
3281 (license license:bsd-3)))
3282
3283 (define-public mafft
3284 (package
3285 (name "mafft")
3286 (version "7.310")
3287 (source (origin
3288 (method url-fetch)
3289 (uri (string-append
3290 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3291 "-without-extensions-src.tgz"))
3292 (file-name (string-append name "-" version ".tgz"))
3293 (sha256
3294 (base32
3295 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3296 (build-system gnu-build-system)
3297 (arguments
3298 `(#:tests? #f ; no automated tests, though there are tests in the read me
3299 #:make-flags (let ((out (assoc-ref %outputs "out")))
3300 (list (string-append "PREFIX=" out)
3301 (string-append "BINDIR="
3302 (string-append out "/bin"))))
3303 #:phases
3304 (modify-phases %standard-phases
3305 (add-after 'unpack 'enter-dir
3306 (lambda _ (chdir "core") #t))
3307 (add-after 'enter-dir 'patch-makefile
3308 (lambda _
3309 ;; on advice from the MAFFT authors, there is no need to
3310 ;; distribute mafft-profile, mafft-distance, or
3311 ;; mafft-homologs.rb as they are too "specialised".
3312 (substitute* "Makefile"
3313 ;; remove mafft-homologs.rb from SCRIPTS
3314 (("^SCRIPTS = mafft mafft-homologs.rb")
3315 "SCRIPTS = mafft")
3316 ;; remove mafft-homologs from MANPAGES
3317 (("^MANPAGES = mafft.1 mafft-homologs.1")
3318 "MANPAGES = mafft.1")
3319 ;; remove mafft-distance from PROGS
3320 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3321 "PROGS = dvtditr dndfast7 dndblast sextet5")
3322 ;; remove mafft-profile from PROGS
3323 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3324 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3325 (("^rm -f mafft-profile mafft-profile.exe") "#")
3326 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3327 ;; do not install MAN pages in libexec folder
3328 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3329 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3330 #t))
3331 (add-after 'enter-dir 'patch-paths
3332 (lambda* (#:key inputs #:allow-other-keys)
3333 (substitute* '("pairash.c"
3334 "mafft.tmpl")
3335 (("perl") (which "perl"))
3336 (("([\"`| ])awk" _ prefix)
3337 (string-append prefix (which "awk")))
3338 (("grep") (which "grep")))
3339 #t))
3340 (delete 'configure)
3341 (add-after 'install 'wrap-programs
3342 (lambda* (#:key outputs #:allow-other-keys)
3343 (let* ((out (assoc-ref outputs "out"))
3344 (bin (string-append out "/bin"))
3345 (path (string-append
3346 (assoc-ref %build-inputs "coreutils") "/bin:")))
3347 (for-each (lambda (file)
3348 (wrap-program file
3349 `("PATH" ":" prefix (,path))))
3350 (find-files bin)))
3351 #t)))))
3352 (inputs
3353 `(("perl" ,perl)
3354 ("ruby" ,ruby)
3355 ("gawk" ,gawk)
3356 ("grep" ,grep)
3357 ("coreutils" ,coreutils)))
3358 (home-page "http://mafft.cbrc.jp/alignment/software/")
3359 (synopsis "Multiple sequence alignment program")
3360 (description
3361 "MAFFT offers a range of multiple alignment methods for nucleotide and
3362 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3363 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3364 sequences).")
3365 (license (license:non-copyleft
3366 "http://mafft.cbrc.jp/alignment/software/license.txt"
3367 "BSD-3 with different formatting"))))
3368
3369 (define-public mash
3370 (package
3371 (name "mash")
3372 (version "1.1.1")
3373 (source (origin
3374 (method url-fetch)
3375 (uri (string-append
3376 "https://github.com/marbl/mash/archive/v"
3377 version ".tar.gz"))
3378 (file-name (string-append name "-" version ".tar.gz"))
3379 (sha256
3380 (base32
3381 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3382 (modules '((guix build utils)))
3383 (snippet
3384 ;; Delete bundled kseq.
3385 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3386 '(delete-file "src/mash/kseq.h"))))
3387 (build-system gnu-build-system)
3388 (arguments
3389 `(#:tests? #f ; No tests.
3390 #:configure-flags
3391 (list
3392 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3393 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3394 #:make-flags (list "CC=gcc")
3395 #:phases
3396 (modify-phases %standard-phases
3397 (add-after 'unpack 'fix-includes
3398 (lambda _
3399 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3400 (("^#include \"kseq\\.h\"")
3401 "#include \"htslib/kseq.h\""))
3402 #t))
3403 (add-before 'configure 'autoconf
3404 (lambda _ (zero? (system* "autoconf")))))))
3405 (native-inputs
3406 `(("autoconf" ,autoconf)
3407 ;; Capnproto and htslib are statically embedded in the final
3408 ;; application. Therefore we also list their licenses, below.
3409 ("capnproto" ,capnproto)
3410 ("htslib" ,htslib)))
3411 (inputs
3412 `(("gsl" ,gsl)
3413 ("zlib" ,zlib)))
3414 (supported-systems '("x86_64-linux"))
3415 (home-page "https://mash.readthedocs.io")
3416 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3417 (description "Mash is a fast sequence distance estimator that uses the
3418 MinHash algorithm and is designed to work with genomes and metagenomes in the
3419 form of assemblies or reads.")
3420 (license (list license:bsd-3 ; Mash
3421 license:expat ; HTSlib and capnproto
3422 license:public-domain ; MurmurHash 3
3423 license:cpl1.0)))) ; Open Bloom Filter
3424
3425 (define-public metabat
3426 ;; We package from a git commit because compilation of the released version
3427 ;; fails.
3428 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3429 (package
3430 (name "metabat")
3431 (version (string-append "0.32.4-1." (string-take commit 8)))
3432 (source
3433 (origin
3434 (method git-fetch)
3435 (uri (git-reference
3436 (url "https://bitbucket.org/berkeleylab/metabat.git")
3437 (commit commit)))
3438 (file-name (string-append name "-" version))
3439 (sha256
3440 (base32
3441 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3442 (patches (search-patches "metabat-remove-compilation-date.patch"))))
3443 (build-system gnu-build-system)
3444 (arguments
3445 `(#:phases
3446 (modify-phases %standard-phases
3447 (add-after 'unpack 'fix-includes
3448 (lambda _
3449 (substitute* "src/BamUtils.h"
3450 (("^#include \"bam/bam\\.h\"")
3451 "#include \"samtools/bam.h\"")
3452 (("^#include \"bam/sam\\.h\"")
3453 "#include \"samtools/sam.h\""))
3454 (substitute* "src/KseqReader.h"
3455 (("^#include \"bam/kseq\\.h\"")
3456 "#include \"htslib/kseq.h\""))
3457 #t))
3458 (add-after 'unpack 'fix-scons
3459 (lambda* (#:key inputs #:allow-other-keys)
3460 (substitute* "SConstruct"
3461 (("^htslib_dir = 'samtools'")
3462 (string-append "hitslib_dir = '"
3463 (assoc-ref inputs "htslib")
3464 "'"))
3465 (("^samtools_dir = 'samtools'")
3466 (string-append "samtools_dir = '"
3467 (assoc-ref inputs "htslib")
3468 "'"))
3469 (("^findStaticOrShared\\('bam', hts_lib")
3470 (string-append "findStaticOrShared('bam', '"
3471 (assoc-ref inputs "samtools")
3472 "/lib'"))
3473 ;; Do not distribute README.
3474 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3475 #t))
3476 (delete 'configure)
3477 (replace 'build
3478 (lambda* (#:key inputs outputs #:allow-other-keys)
3479 (mkdir (assoc-ref outputs "out"))
3480 (zero? (system* "scons"
3481 (string-append
3482 "PREFIX="
3483 (assoc-ref outputs "out"))
3484 (string-append
3485 "BOOST_ROOT="
3486 (assoc-ref inputs "boost"))
3487 "install"))))
3488 ;; Check and install are carried out during build phase.
3489 (delete 'check)
3490 (delete 'install))))
3491 (inputs
3492 `(("zlib" ,zlib)
3493 ("perl" ,perl)
3494 ("samtools" ,samtools)
3495 ("htslib" ,htslib)
3496 ("boost" ,boost)))
3497 (native-inputs
3498 `(("scons" ,scons)))
3499 (home-page "https://bitbucket.org/berkeleylab/metabat")
3500 (synopsis
3501 "Reconstruction of single genomes from complex microbial communities")
3502 (description
3503 "Grouping large genomic fragments assembled from shotgun metagenomic
3504 sequences to deconvolute complex microbial communities, or metagenome binning,
3505 enables the study of individual organisms and their interactions. MetaBAT is
3506 an automated metagenome binning software, which integrates empirical
3507 probabilistic distances of genome abundance and tetranucleotide frequency.")
3508 (license (license:non-copyleft "file://license.txt"
3509 "See license.txt in the distribution.")))))
3510
3511 (define-public minced
3512 (package
3513 (name "minced")
3514 (version "0.2.0")
3515 (source (origin
3516 (method url-fetch)
3517 (uri (string-append
3518 "https://github.com/ctSkennerton/minced/archive/"
3519 version ".tar.gz"))
3520 (file-name (string-append name "-" version ".tar.gz"))
3521 (sha256
3522 (base32
3523 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3524 (build-system gnu-build-system)
3525 (arguments
3526 `(#:test-target "test"
3527 #:phases
3528 (modify-phases %standard-phases
3529 (delete 'configure)
3530 (add-before 'check 'fix-test
3531 (lambda _
3532 ;; Fix test for latest version.
3533 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3534 (("minced:0.1.6") "minced:0.2.0"))
3535 #t))
3536 (replace 'install ; No install target.
3537 (lambda* (#:key inputs outputs #:allow-other-keys)
3538 (let* ((out (assoc-ref outputs "out"))
3539 (bin (string-append out "/bin"))
3540 (wrapper (string-append bin "/minced")))
3541 ;; Minced comes with a wrapper script that tries to figure out where
3542 ;; it is located before running the JAR. Since these paths are known
3543 ;; to us, we build our own wrapper to avoid coreutils dependency.
3544 (install-file "minced.jar" bin)
3545 (with-output-to-file wrapper
3546 (lambda _
3547 (display
3548 (string-append
3549 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3550 (assoc-ref inputs "jre") "/bin/java -jar "
3551 bin "/minced.jar \"$@\"\n"))))
3552 (chmod wrapper #o555)))))))
3553 (native-inputs
3554 `(("jdk" ,icedtea "jdk")))
3555 (inputs
3556 `(("bash" ,bash)
3557 ("jre" ,icedtea "out")))
3558 (home-page "https://github.com/ctSkennerton/minced")
3559 (synopsis "Mining CRISPRs in Environmental Datasets")
3560 (description
3561 "MinCED is a program to find Clustered Regularly Interspaced Short
3562 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3563 unassembled metagenomic reads, but is mainly designed for full genomes and
3564 assembled metagenomic sequence.")
3565 (license license:gpl3+)))
3566
3567 (define-public miso
3568 (package
3569 (name "miso")
3570 (version "0.5.3")
3571 (source (origin
3572 (method url-fetch)
3573 (uri (string-append
3574 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3575 version ".tar.gz"))
3576 (sha256
3577 (base32
3578 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3579 (modules '((guix build utils)))
3580 (snippet
3581 '(substitute* "setup.py"
3582 ;; Use setuptools, or else the executables are not
3583 ;; installed.
3584 (("distutils.core") "setuptools")
3585 ;; use "gcc" instead of "cc" for compilation
3586 (("^defines")
3587 "cc.set_executables(
3588 compiler='gcc',
3589 compiler_so='gcc',
3590 linker_exe='gcc',
3591 linker_so='gcc -shared'); defines")))))
3592 (build-system python-build-system)
3593 (arguments
3594 `(#:python ,python-2 ; only Python 2 is supported
3595 #:tests? #f)) ; no "test" target
3596 (inputs
3597 `(("samtools" ,samtools)
3598 ("python-numpy" ,python2-numpy)
3599 ("python-pysam" ,python2-pysam)
3600 ("python-scipy" ,python2-scipy)
3601 ("python-matplotlib" ,python2-matplotlib)))
3602 (native-inputs
3603 `(("python-mock" ,python2-mock) ;for tests
3604 ("python-pytz" ,python2-pytz))) ;for tests
3605 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3606 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3607 (description
3608 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3609 the expression level of alternatively spliced genes from RNA-Seq data, and
3610 identifies differentially regulated isoforms or exons across samples. By
3611 modeling the generative process by which reads are produced from isoforms in
3612 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3613 that a read originated from a particular isoform.")
3614 (license license:gpl2)))
3615
3616 (define-public muscle
3617 (package
3618 (name "muscle")
3619 (version "3.8.1551")
3620 (source (origin
3621 (method url-fetch/tarbomb)
3622 (uri (string-append
3623 "http://www.drive5.com/muscle/muscle_src_"
3624 version ".tar.gz"))
3625 (sha256
3626 (base32
3627 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3628 (build-system gnu-build-system)
3629 (arguments
3630 `(#:make-flags (list "LDLIBS = -lm")
3631 #:phases
3632 (modify-phases %standard-phases
3633 (delete 'configure)
3634 (replace 'check
3635 ;; There are no tests, so just test if it runs.
3636 (lambda _ (zero? (system* "./muscle" "-version"))))
3637 (replace 'install
3638 (lambda* (#:key outputs #:allow-other-keys)
3639 (let* ((out (assoc-ref outputs "out"))
3640 (bin (string-append out "/bin")))
3641 (install-file "muscle" bin)))))))
3642 (home-page "http://www.drive5.com/muscle")
3643 (synopsis "Multiple sequence alignment program")
3644 (description
3645 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3646 program for nucleotide and protein sequences.")
3647 ;; License information found in 'muscle -h' and usage.cpp.
3648 (license license:public-domain)))
3649
3650 (define-public newick-utils
3651 ;; There are no recent releases so we package from git.
3652 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3653 (package
3654 (name "newick-utils")
3655 (version (string-append "1.6-1." (string-take commit 8)))
3656 (source (origin
3657 (method git-fetch)
3658 (uri (git-reference
3659 (url "https://github.com/tjunier/newick_utils.git")
3660 (commit commit)))
3661 (file-name (string-append name "-" version "-checkout"))
3662 (sha256
3663 (base32
3664 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3665 (build-system gnu-build-system)
3666 (arguments
3667 `(#:phases
3668 (modify-phases %standard-phases
3669 (add-after 'unpack 'autoconf
3670 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3671 (inputs
3672 ;; XXX: TODO: Enable Lua and Guile bindings.
3673 ;; https://github.com/tjunier/newick_utils/issues/13
3674 `(("libxml2" ,libxml2)
3675 ("flex" ,flex)
3676 ("bison" ,bison)))
3677 (native-inputs
3678 `(("autoconf" ,autoconf)
3679 ("automake" ,automake)
3680 ("libtool" ,libtool)))
3681 (synopsis "Programs for working with newick format phylogenetic trees")
3682 (description
3683 "Newick-utils is a suite of utilities for processing phylogenetic trees
3684 in Newick format. Functions include re-rooting, extracting subtrees,
3685 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3686 (home-page "https://github.com/tjunier/newick_utils")
3687 (license license:bsd-3))))
3688
3689 (define-public orfm
3690 (package
3691 (name "orfm")
3692 (version "0.6.1")
3693 (source (origin
3694 (method url-fetch)
3695 (uri (string-append
3696 "https://github.com/wwood/OrfM/releases/download/v"
3697 version "/orfm-" version ".tar.gz"))
3698 (sha256
3699 (base32
3700 "19hwp13n82isdvk16710l9m35cmzf0q3fsrcn3r8c5r67biiz39s"))))
3701 (build-system gnu-build-system)
3702 (inputs `(("zlib" ,zlib)))
3703 (native-inputs
3704 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3705 ("ruby-rspec" ,ruby-rspec)
3706 ("ruby" ,ruby)))
3707 (synopsis "Simple and not slow open reading frame (ORF) caller")
3708 (description
3709 "An ORF caller finds stretches of DNA that, when translated, are not
3710 interrupted by stop codons. OrfM finds and prints these ORFs.")
3711 (home-page "https://github.com/wwood/OrfM")
3712 (license license:lgpl3+)))
3713
3714 (define-public pplacer
3715 (let ((commit "g807f6f3"))
3716 (package
3717 (name "pplacer")
3718 ;; The commit should be updated with each version change.
3719 (version "1.1.alpha19")
3720 (source
3721 (origin
3722 (method url-fetch)
3723 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3724 version ".tar.gz"))
3725 (file-name (string-append name "-" version ".tar.gz"))
3726 (sha256
3727 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3728 (build-system ocaml-build-system)
3729 (arguments
3730 `(#:ocaml ,ocaml-4.01
3731 #:findlib ,ocaml4.01-findlib
3732 #:modules ((guix build ocaml-build-system)
3733 (guix build utils)
3734 (ice-9 ftw))
3735 #:phases
3736 (modify-phases %standard-phases
3737 (delete 'configure)
3738 (add-after 'unpack 'replace-bundled-cddlib
3739 (lambda* (#:key inputs #:allow-other-keys)
3740 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3741 (local-dir "cddlib_guix"))
3742 (mkdir local-dir)
3743 (with-directory-excursion local-dir
3744 (system* "tar" "xvf" cddlib-src))
3745 (let ((cddlib-src-folder
3746 (string-append local-dir "/"
3747 (list-ref (scandir local-dir) 2)
3748 "/lib-src")))
3749 (for-each
3750 (lambda (file)
3751 (copy-file file
3752 (string-append "cdd_src/" (basename file))))
3753 (find-files cddlib-src-folder ".*[ch]$")))
3754 #t)))
3755 (add-after 'unpack 'fix-makefile
3756 (lambda _
3757 ;; Remove system calls to 'git'.
3758 (substitute* "Makefile"
3759 (("^DESCRIPT:=pplacer-.*")
3760 (string-append
3761 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3762 (substitute* "myocamlbuild.ml"
3763 (("git describe --tags --long .*\\\" with")
3764 (string-append
3765 "echo -n v" ,version "-" ,commit "\" with")))
3766 #t))
3767 (replace 'install
3768 (lambda* (#:key outputs #:allow-other-keys)
3769 (let* ((out (assoc-ref outputs "out"))
3770 (bin (string-append out "/bin")))
3771 (copy-recursively "bin" bin))
3772 #t)))))
3773 (native-inputs
3774 `(("zlib" ,zlib)
3775 ("gsl" ,gsl)
3776 ("ocaml-ounit" ,ocaml4.01-ounit)
3777 ("ocaml-batteries" ,ocaml4.01-batteries)
3778 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3779 ("ocaml-csv" ,ocaml4.01-csv)
3780 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3781 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3782 ("ocaml-mcl" ,ocaml4.01-mcl)
3783 ("ocaml-gsl" ,ocaml4.01-gsl)
3784 ("cddlib-src" ,(package-source cddlib))))
3785 (propagated-inputs
3786 `(("pplacer-scripts" ,pplacer-scripts)))
3787 (synopsis "Phylogenetic placement of biological sequences")
3788 (description
3789 "Pplacer places query sequences on a fixed reference phylogenetic tree
3790 to maximize phylogenetic likelihood or posterior probability according to a
3791 reference alignment. Pplacer is designed to be fast, to give useful
3792 information about uncertainty, and to offer advanced visualization and
3793 downstream analysis.")
3794 (home-page "http://matsen.fhcrc.org/pplacer")
3795 (license license:gpl3))))
3796
3797 ;; This package is installed alongside 'pplacer'. It is a separate package so
3798 ;; that it can use the python-build-system for the scripts that are
3799 ;; distributed alongside the main OCaml binaries.
3800 (define pplacer-scripts
3801 (package
3802 (inherit pplacer)
3803 (name "pplacer-scripts")
3804 (build-system python-build-system)
3805 (arguments
3806 `(#:python ,python-2
3807 #:phases
3808 (modify-phases %standard-phases
3809 (add-after 'unpack 'enter-scripts-dir
3810 (lambda _ (chdir "scripts")))
3811 (replace 'check
3812 (lambda _
3813 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
3814 (add-after 'install 'wrap-executables
3815 (lambda* (#:key inputs outputs #:allow-other-keys)
3816 (let* ((out (assoc-ref outputs "out"))
3817 (bin (string-append out "/bin")))
3818 (let ((path (string-append
3819 (assoc-ref inputs "hmmer") "/bin:"
3820 (assoc-ref inputs "infernal") "/bin")))
3821 (display path)
3822 (wrap-program (string-append bin "/refpkg_align.py")
3823 `("PATH" ":" prefix (,path))))
3824 (let ((path (string-append
3825 (assoc-ref inputs "hmmer") "/bin")))
3826 (wrap-program (string-append bin "/hrefpkg_query.py")
3827 `("PATH" ":" prefix (,path)))))
3828 #t)))))
3829 (inputs
3830 `(("infernal" ,infernal)
3831 ("hmmer" ,hmmer)))
3832 (propagated-inputs
3833 `(("python-biopython" ,python2-biopython)
3834 ("taxtastic" ,taxtastic)))
3835 (synopsis "Pplacer Python scripts")))
3836
3837 (define-public python2-pbcore
3838 (package
3839 (name "python2-pbcore")
3840 (version "1.2.10")
3841 (source (origin
3842 (method url-fetch)
3843 (uri (pypi-uri "pbcore" version))
3844 (sha256
3845 (base32
3846 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3847 (build-system python-build-system)
3848 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3849 (propagated-inputs
3850 `(("python-cython" ,python2-cython)
3851 ("python-numpy" ,python2-numpy)
3852 ("python-pysam" ,python2-pysam)
3853 ("python-h5py" ,python2-h5py)))
3854 (native-inputs
3855 `(("python-nose" ,python2-nose)
3856 ("python-sphinx" ,python2-sphinx)
3857 ("python-pyxb" ,python2-pyxb)))
3858 (home-page "http://pacificbiosciences.github.io/pbcore/")
3859 (synopsis "Library for reading and writing PacBio data files")
3860 (description
3861 "The pbcore package provides Python APIs for interacting with PacBio data
3862 files and writing bioinformatics applications.")
3863 (license license:bsd-3)))
3864
3865 (define-public python2-warpedlmm
3866 (package
3867 (name "python2-warpedlmm")
3868 (version "0.21")
3869 (source
3870 (origin
3871 (method url-fetch)
3872 (uri (string-append
3873 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3874 version ".zip"))
3875 (sha256
3876 (base32
3877 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3878 (build-system python-build-system)
3879 (arguments
3880 `(#:python ,python-2)) ; requires Python 2.7
3881 (propagated-inputs
3882 `(("python-scipy" ,python2-scipy)
3883 ("python-numpy" ,python2-numpy)
3884 ("python-matplotlib" ,python2-matplotlib)
3885 ("python-fastlmm" ,python2-fastlmm)
3886 ("python-pandas" ,python2-pandas)
3887 ("python-pysnptools" ,python2-pysnptools)))
3888 (native-inputs
3889 `(("python-mock" ,python2-mock)
3890 ("python-nose" ,python2-nose)
3891 ("unzip" ,unzip)))
3892 (home-page "https://github.com/PMBio/warpedLMM")
3893 (synopsis "Implementation of warped linear mixed models")
3894 (description
3895 "WarpedLMM is a Python implementation of the warped linear mixed model,
3896 which automatically learns an optimal warping function (or transformation) for
3897 the phenotype as it models the data.")
3898 (license license:asl2.0)))
3899
3900 (define-public pbtranscript-tofu
3901 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3902 (package
3903 (name "pbtranscript-tofu")
3904 (version (string-append "2.2.3." (string-take commit 7)))
3905 (source (origin
3906 (method git-fetch)
3907 (uri (git-reference
3908 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3909 (commit commit)))
3910 (file-name (string-append name "-" version "-checkout"))
3911 (sha256
3912 (base32
3913 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3914 (modules '((guix build utils)))
3915 (snippet
3916 '(begin
3917 ;; remove bundled Cython sources
3918 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3919 #t))))
3920 (build-system python-build-system)
3921 (arguments
3922 `(#:python ,python-2
3923 ;; FIXME: Tests fail with "No such file or directory:
3924 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3925 #:tests? #f
3926 #:phases
3927 (modify-phases %standard-phases
3928 (add-after 'unpack 'enter-directory
3929 (lambda _
3930 (chdir "pbtranscript-tofu/pbtranscript/")
3931 #t))
3932 ;; With setuptools version 18.0 and later this setup.py hack causes
3933 ;; a build error, so we disable it.
3934 (add-after 'enter-directory 'patch-setuppy
3935 (lambda _
3936 (substitute* "setup.py"
3937 (("if 'setuptools.extension' in sys.modules:")
3938 "if False:"))
3939 #t)))))
3940 (inputs
3941 `(("python-numpy" ,python2-numpy)
3942 ("python-bx-python" ,python2-bx-python)
3943 ("python-networkx" ,python2-networkx)
3944 ("python-scipy" ,python2-scipy)
3945 ("python-pbcore" ,python2-pbcore)
3946 ("python-h5py" ,python2-h5py)))
3947 (native-inputs
3948 `(("python-cython" ,python2-cython)
3949 ("python-nose" ,python2-nose)))
3950 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3951 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3952 (description
3953 "pbtranscript-tofu contains scripts to analyze transcriptome data
3954 generated using the PacBio Iso-Seq protocol.")
3955 (license license:bsd-3))))
3956
3957 (define-public prank
3958 (package
3959 (name "prank")
3960 (version "150803")
3961 (source (origin
3962 (method url-fetch)
3963 (uri (string-append
3964 "http://wasabiapp.org/download/prank/prank.source."
3965 version ".tgz"))
3966 (sha256
3967 (base32
3968 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3969 (build-system gnu-build-system)
3970 (arguments
3971 `(#:phases
3972 (modify-phases %standard-phases
3973 (add-after 'unpack 'enter-src-dir
3974 (lambda _
3975 (chdir "src")
3976 #t))
3977 (add-after 'unpack 'remove-m64-flag
3978 ;; Prank will build with the correct 'bit-ness' without this flag
3979 ;; and this allows building on 32-bit machines.
3980 (lambda _ (substitute* "src/Makefile"
3981 (("-m64") ""))
3982 #t))
3983 (delete 'configure)
3984 (replace 'install
3985 (lambda* (#:key outputs #:allow-other-keys)
3986 (let* ((out (assoc-ref outputs "out"))
3987 (bin (string-append out "/bin"))
3988 (man (string-append out "/share/man/man1"))
3989 (path (string-append
3990 (assoc-ref %build-inputs "mafft") "/bin:"
3991 (assoc-ref %build-inputs "exonerate") "/bin:"
3992 (assoc-ref %build-inputs "bppsuite") "/bin")))
3993 (install-file "prank" bin)
3994 (wrap-program (string-append bin "/prank")
3995 `("PATH" ":" prefix (,path)))
3996 (install-file "prank.1" man))
3997 #t)))))
3998 (inputs
3999 `(("mafft" ,mafft)
4000 ("exonerate" ,exonerate)
4001 ("bppsuite" ,bppsuite)))
4002 (home-page "http://wasabiapp.org/software/prank/")
4003 (synopsis "Probabilistic multiple sequence alignment program")
4004 (description
4005 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4006 codon and amino-acid sequences. It is based on a novel algorithm that treats
4007 insertions correctly and avoids over-estimation of the number of deletion
4008 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4009 in phylogenetics and correctly takes into account the evolutionary distances
4010 between sequences. Lastly, PRANK allows for defining a potential structure
4011 for sequences to be aligned and then, simultaneously with the alignment,
4012 predicts the locations of structural units in the sequences.")
4013 (license license:gpl2+)))
4014
4015 (define-public proteinortho
4016 (package
4017 (name "proteinortho")
4018 (version "5.16")
4019 (source
4020 (origin
4021 (method url-fetch)
4022 (uri
4023 (string-append
4024 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4025 version "_src.tar.gz"))
4026 (sha256
4027 (base32
4028 "0z4f5cg0cs8ai62hfvp4q6w66q2phcc55nhs4xj5cyhxxivjv2ai"))))
4029 (build-system gnu-build-system)
4030 (arguments
4031 `(#:test-target "test"
4032 #:phases
4033 (modify-phases %standard-phases
4034 (replace 'configure
4035 ;; There is no configure script, so we modify the Makefile directly.
4036 (lambda* (#:key outputs #:allow-other-keys)
4037 (substitute* "Makefile"
4038 (("INSTALLDIR=.*")
4039 (string-append
4040 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4041 #t))
4042 (add-before 'install 'make-install-directory
4043 ;; The install directory is not created during 'make install'.
4044 (lambda* (#:key outputs #:allow-other-keys)
4045 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4046 #t))
4047 (add-after 'install 'wrap-programs
4048 (lambda* (#:key inputs outputs #:allow-other-keys)
4049 (let* ((path (getenv "PATH"))
4050 (out (assoc-ref outputs "out"))
4051 (binary (string-append out "/bin/proteinortho5.pl")))
4052 (wrap-program binary `("PATH" ":" prefix (,path))))
4053 #t)))))
4054 (inputs
4055 `(("perl" ,perl)
4056 ("python" ,python-2)
4057 ("blast+" ,blast+)))
4058 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4059 (synopsis "Detect orthologous genes across species")
4060 (description
4061 "Proteinortho is a tool to detect orthologous genes across different
4062 species. For doing so, it compares similarities of given gene sequences and
4063 clusters them to find significant groups. The algorithm was designed to handle
4064 large-scale data and can be applied to hundreds of species at once.")
4065 (license license:gpl2+)))
4066
4067 (define-public pyicoteo
4068 (package
4069 (name "pyicoteo")
4070 (version "2.0.7")
4071 (source
4072 (origin
4073 (method url-fetch)
4074 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4075 "pyicoteo/get/v" version ".tar.bz2"))
4076 (file-name (string-append name "-" version ".tar.bz2"))
4077 (sha256
4078 (base32
4079 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4080 (build-system python-build-system)
4081 (arguments
4082 `(#:python ,python-2 ; does not work with Python 3
4083 #:tests? #f)) ; there are no tests
4084 (inputs
4085 `(("python2-matplotlib" ,python2-matplotlib)))
4086 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4087 (synopsis "Analyze high-throughput genetic sequencing data")
4088 (description
4089 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4090 sequencing data. It works with genomic coordinates. There are currently six
4091 different command-line tools:
4092
4093 @enumerate
4094 @item pyicoregion: for generating exploratory regions automatically;
4095 @item pyicoenrich: for differential enrichment between two conditions;
4096 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4097 @item pyicos: for genomic coordinates manipulation;
4098 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4099 @item pyicount: to count how many reads from N experiment files overlap in a
4100 region file;
4101 @item pyicotrocol: to combine operations from pyicoteo.
4102 @end enumerate\n")
4103 (license license:gpl3+)))
4104
4105 (define-public prodigal
4106 (package
4107 (name "prodigal")
4108 (version "2.6.3")
4109 (source (origin
4110 (method url-fetch)
4111 (uri (string-append
4112 "https://github.com/hyattpd/Prodigal/archive/v"
4113 version ".tar.gz"))
4114 (file-name (string-append name "-" version ".tar.gz"))
4115 (sha256
4116 (base32
4117 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4118 (build-system gnu-build-system)
4119 (arguments
4120 `(#:tests? #f ;no check target
4121 #:make-flags (list (string-append "INSTALLDIR="
4122 (assoc-ref %outputs "out")
4123 "/bin"))
4124 #:phases
4125 (modify-phases %standard-phases
4126 (delete 'configure))))
4127 (home-page "http://prodigal.ornl.gov")
4128 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4129 (description
4130 "Prodigal runs smoothly on finished genomes, draft genomes, and
4131 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4132 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4133 partial genes, and identifies translation initiation sites.")
4134 (license license:gpl3+)))
4135
4136 (define-public roary
4137 (package
4138 (name "roary")
4139 (version "3.8.2")
4140 (source
4141 (origin
4142 (method url-fetch)
4143 (uri (string-append
4144 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4145 version ".tar.gz"))
4146 (sha256
4147 (base32
4148 "03dfr2cd5fp80bcr65923zpdzrasvcxl7c2vgh8373v25a1yfap7"))))
4149 (build-system perl-build-system)
4150 (arguments
4151 `(#:phases
4152 (modify-phases %standard-phases
4153 (delete 'configure)
4154 (delete 'build)
4155 (replace 'check
4156 (lambda _
4157 ;; The tests are not run by default, so we run each test file
4158 ;; directly.
4159 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4160 (getenv "PATH")))
4161 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4162 (getenv "PERL5LIB")))
4163 (zero? (length (filter (lambda (file)
4164 (display file)(display "\n")
4165 (not (zero? (system* "perl" file))))
4166 (find-files "t" ".*\\.t$"))))))
4167 (replace 'install
4168 ;; There is no 'install' target in the Makefile.
4169 (lambda* (#:key outputs #:allow-other-keys)
4170 (let* ((out (assoc-ref outputs "out"))
4171 (bin (string-append out "/bin"))
4172 (perl (string-append out "/lib/perl5/site_perl"))
4173 (roary-plots "contrib/roary_plots"))
4174 (mkdir-p bin)
4175 (mkdir-p perl)
4176 (copy-recursively "bin" bin)
4177 (copy-recursively "lib" perl)
4178 #t)))
4179 (add-after 'install 'wrap-programs
4180 (lambda* (#:key inputs outputs #:allow-other-keys)
4181 (let* ((out (assoc-ref outputs "out"))
4182 (perl5lib (getenv "PERL5LIB"))
4183 (path (getenv "PATH")))
4184 (for-each (lambda (prog)
4185 (let ((binary (string-append out "/" prog)))
4186 (wrap-program binary
4187 `("PERL5LIB" ":" prefix
4188 (,(string-append perl5lib ":" out
4189 "/lib/perl5/site_perl"))))
4190 (wrap-program binary
4191 `("PATH" ":" prefix
4192 (,(string-append path ":" out "/bin"))))))
4193 (find-files "bin" ".*[^R]$"))
4194 (let ((file
4195 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4196 (r-site-lib (getenv "R_LIBS_SITE"))
4197 (coreutils-path
4198 (string-append (assoc-ref inputs "coreutils") "/bin")))
4199 (wrap-program file
4200 `("R_LIBS_SITE" ":" prefix
4201 (,(string-append r-site-lib ":" out "/site-library/"))))
4202 (wrap-program file
4203 `("PATH" ":" prefix
4204 (,(string-append coreutils-path ":" out "/bin"))))))
4205 #t)))))
4206 (native-inputs
4207 `(("perl-env-path" ,perl-env-path)
4208 ("perl-test-files" ,perl-test-files)
4209 ("perl-test-most" ,perl-test-most)
4210 ("perl-test-output" ,perl-test-output)))
4211 (inputs
4212 `(("perl-array-utils" ,perl-array-utils)
4213 ("bioperl" ,bioperl-minimal)
4214 ("perl-exception-class" ,perl-exception-class)
4215 ("perl-file-find-rule" ,perl-file-find-rule)
4216 ("perl-file-grep" ,perl-file-grep)
4217 ("perl-file-slurper" ,perl-file-slurper)
4218 ("perl-file-which" ,perl-file-which)
4219 ("perl-graph" ,perl-graph)
4220 ("perl-graph-readwrite" ,perl-graph-readwrite)
4221 ("perl-log-log4perl" ,perl-log-log4perl)
4222 ("perl-moose" ,perl-moose)
4223 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4224 ("perl-text-csv" ,perl-text-csv)
4225 ("bedtools" ,bedtools)
4226 ("cd-hit" ,cd-hit)
4227 ("blast+" ,blast+)
4228 ("mcl" ,mcl)
4229 ("parallel" ,parallel)
4230 ("prank" ,prank)
4231 ("mafft" ,mafft)
4232 ("fasttree" ,fasttree)
4233 ("grep" ,grep)
4234 ("sed" ,sed)
4235 ("gawk" ,gawk)
4236 ("r-minimal" ,r-minimal)
4237 ("r-ggplot2" ,r-ggplot2)
4238 ("coreutils" ,coreutils)))
4239 (home-page "http://sanger-pathogens.github.io/Roary")
4240 (synopsis "High speed stand-alone pan genome pipeline")
4241 (description
4242 "Roary is a high speed stand alone pan genome pipeline, which takes
4243 annotated assemblies in GFF3 format (produced by the Prokka program) and
4244 calculates the pan genome. Using a standard desktop PC, it can analyse
4245 datasets with thousands of samples, without compromising the quality of the
4246 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4247 single processor. Roary is not intended for metagenomics or for comparing
4248 extremely diverse sets of genomes.")
4249 (license license:gpl3)))
4250
4251 (define-public raxml
4252 (package
4253 (name "raxml")
4254 (version "8.2.10")
4255 (source
4256 (origin
4257 (method url-fetch)
4258 (uri
4259 (string-append
4260 "https://github.com/stamatak/standard-RAxML/archive/v"
4261 version ".tar.gz"))
4262 (file-name (string-append name "-" version ".tar.gz"))
4263 (sha256
4264 (base32
4265 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4266 (build-system gnu-build-system)
4267 (arguments
4268 `(#:tests? #f ; There are no tests.
4269 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4270 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4271 #:phases
4272 (modify-phases %standard-phases
4273 (delete 'configure)
4274 (replace 'install
4275 (lambda* (#:key outputs #:allow-other-keys)
4276 (let* ((out (assoc-ref outputs "out"))
4277 (bin (string-append out "/bin"))
4278 (executable "raxmlHPC-HYBRID"))
4279 (install-file executable bin)
4280 (symlink (string-append bin "/" executable) "raxml"))
4281 #t)))))
4282 (inputs
4283 `(("openmpi" ,openmpi)))
4284 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4285 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4286 (description
4287 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4288 phylogenies.")
4289 (license license:gpl2+)))
4290
4291 (define-public rsem
4292 (package
4293 (name "rsem")
4294 (version "1.2.20")
4295 (source
4296 (origin
4297 (method url-fetch)
4298 (uri
4299 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4300 version ".tar.gz"))
4301 (sha256
4302 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4303 (patches (search-patches "rsem-makefile.patch"))
4304 (modules '((guix build utils)))
4305 (snippet
4306 '(begin
4307 ;; remove bundled copy of boost
4308 (delete-file-recursively "boost")
4309 #t))))
4310 (build-system gnu-build-system)
4311 (arguments
4312 `(#:tests? #f ;no "check" target
4313 #:phases
4314 (modify-phases %standard-phases
4315 ;; No "configure" script.
4316 ;; Do not build bundled samtools library.
4317 (replace 'configure
4318 (lambda _
4319 (substitute* "Makefile"
4320 (("^all : sam/libbam.a") "all : "))
4321 #t))
4322 (replace 'install
4323 (lambda* (#:key outputs #:allow-other-keys)
4324 (let* ((out (string-append (assoc-ref outputs "out")))
4325 (bin (string-append out "/bin/"))
4326 (perl (string-append out "/lib/perl5/site_perl")))
4327 (mkdir-p bin)
4328 (mkdir-p perl)
4329 (for-each (lambda (file)
4330 (install-file file bin))
4331 (find-files "." "rsem-.*"))
4332 (install-file "rsem_perl_utils.pm" perl))
4333 #t))
4334 (add-after
4335 'install 'wrap-program
4336 (lambda* (#:key outputs #:allow-other-keys)
4337 (let ((out (assoc-ref outputs "out")))
4338 (for-each (lambda (prog)
4339 (wrap-program (string-append out "/bin/" prog)
4340 `("PERL5LIB" ":" prefix
4341 (,(string-append out "/lib/perl5/site_perl")))))
4342 '("rsem-plot-transcript-wiggles"
4343 "rsem-calculate-expression"
4344 "rsem-generate-ngvector"
4345 "rsem-run-ebseq"
4346 "rsem-prepare-reference")))
4347 #t)))))
4348 (inputs
4349 `(("boost" ,boost)
4350 ("ncurses" ,ncurses)
4351 ("r-minimal" ,r-minimal)
4352 ("perl" ,perl)
4353 ("samtools" ,samtools-0.1)
4354 ("zlib" ,zlib)))
4355 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4356 (synopsis "Estimate gene expression levels from RNA-Seq data")
4357 (description
4358 "RSEM is a software package for estimating gene and isoform expression
4359 levels from RNA-Seq data. The RSEM package provides a user-friendly
4360 interface, supports threads for parallel computation of the EM algorithm,
4361 single-end and paired-end read data, quality scores, variable-length reads and
4362 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4363 interval estimates for expression levels. For visualization, it can generate
4364 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4365 (license license:gpl3+)))
4366
4367 (define-public rseqc
4368 (package
4369 (name "rseqc")
4370 (version "2.6.1")
4371 (source
4372 (origin
4373 (method url-fetch)
4374 (uri
4375 (string-append "mirror://sourceforge/rseqc/"
4376 "RSeQC-" version ".tar.gz"))
4377 (sha256
4378 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4379 (modules '((guix build utils)))
4380 (snippet
4381 '(begin
4382 ;; remove bundled copy of pysam
4383 (delete-file-recursively "lib/pysam")
4384 (substitute* "setup.py"
4385 ;; remove dependency on outdated "distribute" module
4386 (("^from distribute_setup import use_setuptools") "")
4387 (("^use_setuptools\\(\\)") "")
4388 ;; do not use bundled copy of pysam
4389 (("^have_pysam = False") "have_pysam = True"))))))
4390 (build-system python-build-system)
4391 (arguments `(#:python ,python-2))
4392 (inputs
4393 `(("python-cython" ,python2-cython)
4394 ("python-pysam" ,python2-pysam)
4395 ("python-numpy" ,python2-numpy)
4396 ("zlib" ,zlib)))
4397 (native-inputs
4398 `(("python-nose" ,python2-nose)))
4399 (home-page "http://rseqc.sourceforge.net/")
4400 (synopsis "RNA-seq quality control package")
4401 (description
4402 "RSeQC provides a number of modules that can comprehensively evaluate
4403 high throughput sequence data, especially RNA-seq data. Some basic modules
4404 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4405 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4406 distribution, coverage uniformity, strand specificity, etc.")
4407 (license license:gpl3+)))
4408
4409 (define-public seek
4410 ;; There are no release tarballs. According to the installation
4411 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4412 ;; stable release is identified by this changeset ID.
4413 (let ((changeset "2329130")
4414 (revision "1"))
4415 (package
4416 (name "seek")
4417 (version (string-append "0-" revision "." changeset))
4418 (source (origin
4419 (method hg-fetch)
4420 (uri (hg-reference
4421 (url "https://bitbucket.org/libsleipnir/sleipnir")
4422 (changeset changeset)))
4423 (sha256
4424 (base32
4425 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4426 (build-system gnu-build-system)
4427 (arguments
4428 `(#:modules ((srfi srfi-1)
4429 (guix build gnu-build-system)
4430 (guix build utils))
4431 #:phases
4432 (let ((dirs '("SeekMiner"
4433 "SeekEvaluator"
4434 "SeekPrep"
4435 "Distancer"
4436 "Data2DB"
4437 "PCL2Bin")))
4438 (modify-phases %standard-phases
4439 (add-before 'configure 'bootstrap
4440 (lambda _
4441 (zero? (system* "bash" "gen_auto"))))
4442 (add-after 'build 'build-additional-tools
4443 (lambda* (#:key make-flags #:allow-other-keys)
4444 (every (lambda (dir)
4445 (with-directory-excursion (string-append "tools/" dir)
4446 (zero? (apply system* "make" make-flags))))
4447 dirs)))
4448 (add-after 'install 'install-additional-tools
4449 (lambda* (#:key make-flags #:allow-other-keys)
4450 (fold (lambda (dir result)
4451 (with-directory-excursion (string-append "tools/" dir)
4452 (and result
4453 (zero? (apply system*
4454 `("make" ,@make-flags "install"))))))
4455 #t dirs)))))))
4456 (inputs
4457 `(("gsl" ,gsl)
4458 ("boost" ,boost)
4459 ("libsvm" ,libsvm)
4460 ("readline" ,readline)
4461 ("gengetopt" ,gengetopt)
4462 ("log4cpp" ,log4cpp)))
4463 (native-inputs
4464 `(("autoconf" ,autoconf)
4465 ("automake" ,automake)
4466 ("perl" ,perl)))
4467 (home-page "http://seek.princeton.edu")
4468 (synopsis "Gene co-expression search engine")
4469 (description
4470 "SEEK is a computational gene co-expression search engine. SEEK provides
4471 biologists with a way to navigate the massive human expression compendium that
4472 now contains thousands of expression datasets. SEEK returns a robust ranking
4473 of co-expressed genes in the biological area of interest defined by the user's
4474 query genes. It also prioritizes thousands of expression datasets according
4475 to the user's query of interest.")
4476 (license license:cc-by3.0))))
4477
4478 (define-public samtools
4479 (package
4480 (name "samtools")
4481 (version "1.3.1")
4482 (source
4483 (origin
4484 (method url-fetch)
4485 (uri
4486 (string-append "mirror://sourceforge/samtools/samtools/"
4487 version "/samtools-" version ".tar.bz2"))
4488 (sha256
4489 (base32
4490 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4491 (build-system gnu-build-system)
4492 (arguments
4493 `(#:modules ((ice-9 ftw)
4494 (ice-9 regex)
4495 (guix build gnu-build-system)
4496 (guix build utils))
4497 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4498 #:configure-flags (list "--with-ncurses")
4499 #:phases
4500 (alist-cons-after
4501 'unpack 'patch-tests
4502 (lambda _
4503 (substitute* "test/test.pl"
4504 ;; The test script calls out to /bin/bash
4505 (("/bin/bash") (which "bash")))
4506 #t)
4507 (alist-cons-after
4508 'install 'install-library
4509 (lambda* (#:key outputs #:allow-other-keys)
4510 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4511 (install-file "libbam.a" lib)
4512 #t))
4513 (alist-cons-after
4514 'install 'install-headers
4515 (lambda* (#:key outputs #:allow-other-keys)
4516 (let ((include (string-append (assoc-ref outputs "out")
4517 "/include/samtools/")))
4518 (for-each (lambda (file)
4519 (install-file file include))
4520 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4521 #t))
4522 %standard-phases)))))
4523 (native-inputs `(("pkg-config" ,pkg-config)))
4524 (inputs `(("ncurses" ,ncurses)
4525 ("perl" ,perl)
4526 ("python" ,python)
4527 ("zlib" ,zlib)))
4528 (home-page "http://samtools.sourceforge.net")
4529 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4530 (description
4531 "Samtools implements various utilities for post-processing nucleotide
4532 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4533 variant calling (in conjunction with bcftools), and a simple alignment
4534 viewer.")
4535 (license license:expat)))
4536
4537 (define-public samtools-0.1
4538 ;; This is the most recent version of the 0.1 line of samtools. The input
4539 ;; and output formats differ greatly from that used and produced by samtools
4540 ;; 1.x and is still used in many bioinformatics pipelines.
4541 (package (inherit samtools)
4542 (version "0.1.19")
4543 (source
4544 (origin
4545 (method url-fetch)
4546 (uri
4547 (string-append "mirror://sourceforge/samtools/samtools/"
4548 version "/samtools-" version ".tar.bz2"))
4549 (sha256
4550 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4551 (arguments
4552 `(#:tests? #f ;no "check" target
4553 ,@(substitute-keyword-arguments (package-arguments samtools)
4554 ((#:make-flags flags)
4555 `(cons "LIBCURSES=-lncurses" ,flags))
4556 ((#:phases phases)
4557 `(modify-phases ,phases
4558 (replace 'install
4559 (lambda* (#:key outputs #:allow-other-keys)
4560 (let ((bin (string-append
4561 (assoc-ref outputs "out") "/bin")))
4562 (mkdir-p bin)
4563 (install-file "samtools" bin)
4564 #t)))
4565 (delete 'patch-tests)
4566 (delete 'configure))))))))
4567
4568 (define-public mosaik
4569 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4570 (package
4571 (name "mosaik")
4572 (version "2.2.30")
4573 (source (origin
4574 ;; There are no release tarballs nor tags.
4575 (method git-fetch)
4576 (uri (git-reference
4577 (url "https://github.com/wanpinglee/MOSAIK.git")
4578 (commit commit)))
4579 (file-name (string-append name "-" version))
4580 (sha256
4581 (base32
4582 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4583 (build-system gnu-build-system)
4584 (arguments
4585 `(#:tests? #f ; no tests
4586 #:make-flags (list "CC=gcc")
4587 #:phases
4588 (modify-phases %standard-phases
4589 (replace 'configure
4590 (lambda _ (chdir "src") #t))
4591 (replace 'install
4592 (lambda* (#:key outputs #:allow-other-keys)
4593 (let ((bin (string-append (assoc-ref outputs "out")
4594 "/bin")))
4595 (mkdir-p bin)
4596 (copy-recursively "../bin" bin)
4597 #t))))))
4598 (inputs
4599 `(("perl" ,perl)
4600 ("zlib" ,zlib)))
4601 (supported-systems '("x86_64-linux"))
4602 (home-page "https://github.com/wanpinglee/MOSAIK")
4603 (synopsis "Map nucleotide sequence reads to reference genomes")
4604 (description
4605 "MOSAIK is a program for mapping second and third-generation sequencing
4606 reads to a reference genome. MOSAIK can align reads generated by all the
4607 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4608 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4609 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4610 ;; code released into the public domain:
4611 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4612 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4613 (license (list license:gpl2+ license:public-domain)))))
4614
4615 (define-public ngs-sdk
4616 (package
4617 (name "ngs-sdk")
4618 (version "1.3.0")
4619 (source
4620 (origin
4621 (method url-fetch)
4622 (uri
4623 (string-append "https://github.com/ncbi/ngs/archive/"
4624 version ".tar.gz"))
4625 (file-name (string-append name "-" version ".tar.gz"))
4626 (sha256
4627 (base32
4628 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4629 (build-system gnu-build-system)
4630 (arguments
4631 `(#:parallel-build? #f ; not supported
4632 #:tests? #f ; no "check" target
4633 #:phases
4634 (alist-replace
4635 'configure
4636 (lambda* (#:key outputs #:allow-other-keys)
4637 (let ((out (assoc-ref outputs "out")))
4638 ;; The 'configure' script doesn't recognize things like
4639 ;; '--enable-fast-install'.
4640 (zero? (system* "./configure"
4641 (string-append "--build-prefix=" (getcwd) "/build")
4642 (string-append "--prefix=" out)))))
4643 (alist-cons-after
4644 'unpack 'enter-dir
4645 (lambda _ (chdir "ngs-sdk") #t)
4646 %standard-phases))))
4647 (native-inputs `(("perl" ,perl)))
4648 ;; According to the test
4649 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4650 ;; in ngs-sdk/setup/konfigure.perl
4651 (supported-systems '("i686-linux" "x86_64-linux"))
4652 (home-page "https://github.com/ncbi/ngs")
4653 (synopsis "API for accessing Next Generation Sequencing data")
4654 (description
4655 "NGS is a domain-specific API for accessing reads, alignments and pileups
4656 produced from Next Generation Sequencing. The API itself is independent from
4657 any particular back-end implementation, and supports use of multiple back-ends
4658 simultaneously.")
4659 (license license:public-domain)))
4660
4661 (define-public java-ngs
4662 (package (inherit ngs-sdk)
4663 (name "java-ngs")
4664 (arguments
4665 `(,@(substitute-keyword-arguments
4666 `(#:modules ((guix build gnu-build-system)
4667 (guix build utils)
4668 (srfi srfi-1)
4669 (srfi srfi-26))
4670 ,@(package-arguments ngs-sdk))
4671 ((#:phases phases)
4672 `(modify-phases ,phases
4673 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4674 (inputs
4675 `(("jdk" ,icedtea "jdk")
4676 ("ngs-sdk" ,ngs-sdk)))
4677 (synopsis "Java bindings for NGS SDK")))
4678
4679 (define-public ncbi-vdb
4680 (package
4681 (name "ncbi-vdb")
4682 (version "2.8.2")
4683 (source
4684 (origin
4685 (method url-fetch)
4686 (uri
4687 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4688 version ".tar.gz"))
4689 (file-name (string-append name "-" version ".tar.gz"))
4690 (sha256
4691 (base32
4692 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4693 (build-system gnu-build-system)
4694 (arguments
4695 `(#:parallel-build? #f ; not supported
4696 #:tests? #f ; no "check" target
4697 #:phases
4698 (modify-phases %standard-phases
4699 (replace 'configure
4700 (lambda* (#:key inputs outputs #:allow-other-keys)
4701 (let ((out (assoc-ref outputs "out")))
4702 ;; Override include path for libmagic
4703 (substitute* "setup/package.prl"
4704 (("name => 'magic', Include => '/usr/include'")
4705 (string-append "name=> 'magic', Include => '"
4706 (assoc-ref inputs "libmagic")
4707 "/include" "'")))
4708
4709 ;; Install kdf5 library (needed by sra-tools)
4710 (substitute* "build/Makefile.install"
4711 (("LIBRARIES_TO_INSTALL =")
4712 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4713
4714 (substitute* "build/Makefile.env"
4715 (("CFLAGS =" prefix)
4716 (string-append prefix "-msse2 ")))
4717
4718 ;; Override search path for ngs-java
4719 (substitute* "setup/package.prl"
4720 (("/usr/local/ngs/ngs-java")
4721 (assoc-ref inputs "java-ngs")))
4722
4723 ;; The 'configure' script doesn't recognize things like
4724 ;; '--enable-fast-install'.
4725 (zero? (system*
4726 "./configure"
4727 (string-append "--build-prefix=" (getcwd) "/build")
4728 (string-append "--prefix=" (assoc-ref outputs "out"))
4729 (string-append "--debug")
4730 (string-append "--with-xml2-prefix="
4731 (assoc-ref inputs "libxml2"))
4732 (string-append "--with-ngs-sdk-prefix="
4733 (assoc-ref inputs "ngs-sdk"))
4734 (string-append "--with-hdf5-prefix="
4735 (assoc-ref inputs "hdf5")))))))
4736 (add-after 'install 'install-interfaces
4737 (lambda* (#:key outputs #:allow-other-keys)
4738 ;; Install interface libraries. On i686 the interface libraries
4739 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4740 ;; architecture name ("i386") instead of the target system prefix
4741 ;; ("i686").
4742 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4743 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4744 ,(system->linux-architecture
4745 (or (%current-target-system)
4746 (%current-system)))
4747 "/rel/ilib")
4748 (string-append (assoc-ref outputs "out")
4749 "/ilib"))
4750 ;; Install interface headers
4751 (copy-recursively "interfaces"
4752 (string-append (assoc-ref outputs "out")
4753 "/include"))
4754 #t))
4755 ;; These files are needed by sra-tools.
4756 (add-after 'install 'install-configuration-files
4757 (lambda* (#:key outputs #:allow-other-keys)
4758 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4759 (mkdir target)
4760 (install-file "libs/kfg/default.kfg" target)
4761 (install-file "libs/kfg/certs.kfg" target))
4762 #t)))))
4763 (inputs
4764 `(("libxml2" ,libxml2)
4765 ("ngs-sdk" ,ngs-sdk)
4766 ("java-ngs" ,java-ngs)
4767 ("libmagic" ,file)
4768 ("hdf5" ,hdf5)))
4769 (native-inputs `(("perl" ,perl)))
4770 ;; NCBI-VDB requires SSE capability.
4771 (supported-systems '("i686-linux" "x86_64-linux"))
4772 (home-page "https://github.com/ncbi/ncbi-vdb")
4773 (synopsis "Database engine for genetic information")
4774 (description
4775 "The NCBI-VDB library implements a highly compressed columnar data
4776 warehousing engine that is most often used to store genetic information.
4777 Databases are stored in a portable image within the file system, and can be
4778 accessed/downloaded on demand across HTTP.")
4779 (license license:public-domain)))
4780
4781 (define-public plink
4782 (package
4783 (name "plink")
4784 (version "1.07")
4785 (source
4786 (origin
4787 (method url-fetch)
4788 (uri (string-append
4789 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4790 version "-src.zip"))
4791 (sha256
4792 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4793 (patches (search-patches "plink-1.07-unclobber-i.patch"
4794 "plink-endian-detection.patch"))))
4795 (build-system gnu-build-system)
4796 (arguments
4797 '(#:tests? #f ;no "check" target
4798 #:make-flags (list (string-append "LIB_LAPACK="
4799 (assoc-ref %build-inputs "lapack")
4800 "/lib/liblapack.so")
4801 "WITH_LAPACK=1"
4802 "FORCE_DYNAMIC=1"
4803 ;; disable phoning home
4804 "WITH_WEBCHECK=")
4805 #:phases
4806 (modify-phases %standard-phases
4807 ;; no "configure" script
4808 (delete 'configure)
4809 (replace 'install
4810 (lambda* (#:key outputs #:allow-other-keys)
4811 (let ((bin (string-append (assoc-ref outputs "out")
4812 "/bin/")))
4813 (install-file "plink" bin)
4814 #t))))))
4815 (inputs
4816 `(("zlib" ,zlib)
4817 ("lapack" ,lapack)))
4818 (native-inputs
4819 `(("unzip" ,unzip)))
4820 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4821 (synopsis "Whole genome association analysis toolset")
4822 (description
4823 "PLINK is a whole genome association analysis toolset, designed to
4824 perform a range of basic, large-scale analyses in a computationally efficient
4825 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4826 so there is no support for steps prior to this (e.g. study design and
4827 planning, generating genotype or CNV calls from raw data). Through
4828 integration with gPLINK and Haploview, there is some support for the
4829 subsequent visualization, annotation and storage of results.")
4830 ;; Code is released under GPLv2, except for fisher.h, which is under
4831 ;; LGPLv2.1+
4832 (license (list license:gpl2 license:lgpl2.1+))))
4833
4834 (define-public smithlab-cpp
4835 (let ((revision "1")
4836 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4837 (package
4838 (name "smithlab-cpp")
4839 (version (string-append "0." revision "." (string-take commit 7)))
4840 (source (origin
4841 (method git-fetch)
4842 (uri (git-reference
4843 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4844 (commit commit)))
4845 (file-name (string-append name "-" version "-checkout"))
4846 (sha256
4847 (base32
4848 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4849 (build-system gnu-build-system)
4850 (arguments
4851 `(#:modules ((guix build gnu-build-system)
4852 (guix build utils)
4853 (srfi srfi-26))
4854 #:tests? #f ;no "check" target
4855 #:phases
4856 (modify-phases %standard-phases
4857 (add-after 'unpack 'use-samtools-headers
4858 (lambda _
4859 (substitute* '("SAM.cpp"
4860 "SAM.hpp")
4861 (("sam.h") "samtools/sam.h"))
4862 #t))
4863 (replace 'install
4864 (lambda* (#:key outputs #:allow-other-keys)
4865 (let* ((out (assoc-ref outputs "out"))
4866 (lib (string-append out "/lib"))
4867 (include (string-append out "/include/smithlab-cpp")))
4868 (mkdir-p lib)
4869 (mkdir-p include)
4870 (for-each (cut install-file <> lib)
4871 (find-files "." "\\.o$"))
4872 (for-each (cut install-file <> include)
4873 (find-files "." "\\.hpp$")))
4874 #t))
4875 (delete 'configure))))
4876 (inputs
4877 `(("samtools" ,samtools-0.1)
4878 ("zlib" ,zlib)))
4879 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4880 (synopsis "C++ helper library for functions used in Smith lab projects")
4881 (description
4882 "Smithlab CPP is a C++ library that includes functions used in many of
4883 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4884 structures, classes for genomic regions, mapped sequencing reads, etc.")
4885 (license license:gpl3+))))
4886
4887 (define-public preseq
4888 (package
4889 (name "preseq")
4890 (version "2.0")
4891 (source (origin
4892 (method url-fetch)
4893 (uri (string-append "https://github.com/smithlabcode/"
4894 "preseq/archive/v" version ".tar.gz"))
4895 (file-name (string-append name "-" version ".tar.gz"))
4896 (sha256
4897 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4898 (modules '((guix build utils)))
4899 (snippet
4900 ;; Remove bundled samtools.
4901 '(delete-file-recursively "samtools"))))
4902 (build-system gnu-build-system)
4903 (arguments
4904 `(#:tests? #f ;no "check" target
4905 #:phases
4906 (modify-phases %standard-phases
4907 (delete 'configure))
4908 #:make-flags
4909 (list (string-append "PREFIX="
4910 (assoc-ref %outputs "out"))
4911 (string-append "LIBBAM="
4912 (assoc-ref %build-inputs "samtools")
4913 "/lib/libbam.a")
4914 (string-append "SMITHLAB_CPP="
4915 (assoc-ref %build-inputs "smithlab-cpp")
4916 "/lib")
4917 "PROGS=preseq"
4918 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4919 (inputs
4920 `(("gsl" ,gsl)
4921 ("samtools" ,samtools-0.1)
4922 ("smithlab-cpp" ,smithlab-cpp)
4923 ("zlib" ,zlib)))
4924 (home-page "http://smithlabresearch.org/software/preseq/")
4925 (synopsis "Program for analyzing library complexity")
4926 (description
4927 "The preseq package is aimed at predicting and estimating the complexity
4928 of a genomic sequencing library, equivalent to predicting and estimating the
4929 number of redundant reads from a given sequencing depth and how many will be
4930 expected from additional sequencing using an initial sequencing experiment.
4931 The estimates can then be used to examine the utility of further sequencing,
4932 optimize the sequencing depth, or to screen multiple libraries to avoid low
4933 complexity samples.")
4934 (license license:gpl3+)))
4935
4936 (define-public python-screed
4937 (package
4938 (name "python-screed")
4939 (version "0.9")
4940 (source
4941 (origin
4942 (method url-fetch)
4943 (uri (pypi-uri "screed" version))
4944 (sha256
4945 (base32
4946 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4947 (build-system python-build-system)
4948 (arguments
4949 `(#:phases
4950 (modify-phases %standard-phases
4951 (replace 'check
4952 (lambda _
4953 (setenv "PYTHONPATH"
4954 (string-append (getenv "PYTHONPATH") ":."))
4955 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4956 (native-inputs
4957 `(("python-nose" ,python-nose)))
4958 (inputs
4959 `(("python-bz2file" ,python-bz2file)))
4960 (home-page "https://github.com/dib-lab/screed/")
4961 (synopsis "Short read sequence database utilities")
4962 (description "Screed parses FASTA and FASTQ files and generates databases.
4963 Values such as sequence name, sequence description, sequence quality and the
4964 sequence itself can be retrieved from these databases.")
4965 (license license:bsd-3)))
4966
4967 (define-public python2-screed
4968 (package-with-python2 python-screed))
4969
4970 (define-public sra-tools
4971 (package
4972 (name "sra-tools")
4973 (version "2.8.2-1")
4974 (source
4975 (origin
4976 (method url-fetch)
4977 (uri
4978 (string-append "https://github.com/ncbi/sra-tools/archive/"
4979 version ".tar.gz"))
4980 (file-name (string-append name "-" version ".tar.gz"))
4981 (sha256
4982 (base32
4983 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
4984 (build-system gnu-build-system)
4985 (arguments
4986 `(#:parallel-build? #f ; not supported
4987 #:tests? #f ; no "check" target
4988 #:make-flags
4989 (list (string-append "DEFAULT_CRT="
4990 (assoc-ref %build-inputs "ncbi-vdb")
4991 "/kfg/certs.kfg")
4992 (string-append "DEFAULT_KFG="
4993 (assoc-ref %build-inputs "ncbi-vdb")
4994 "/kfg/default.kfg")
4995 (string-append "VDB_LIBDIR="
4996 (assoc-ref %build-inputs "ncbi-vdb")
4997 ,(if (string-prefix? "x86_64"
4998 (or (%current-target-system)
4999 (%current-system)))
5000 "/lib64"
5001 "/lib32")))
5002 #:phases
5003 (modify-phases %standard-phases
5004 (replace 'configure
5005 (lambda* (#:key inputs outputs #:allow-other-keys)
5006 ;; The build system expects a directory containing the sources and
5007 ;; raw build output of ncbi-vdb, including files that are not
5008 ;; installed. Since we are building against an installed version of
5009 ;; ncbi-vdb, the following modifications are needed.
5010 (substitute* "setup/konfigure.perl"
5011 ;; Make the configure script look for the "ilib" directory of
5012 ;; "ncbi-vdb" without first checking for the existence of a
5013 ;; matching library in its "lib" directory.
5014 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5015 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5016 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5017 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5018 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5019
5020 ;; Dynamic linking
5021 (substitute* "tools/copycat/Makefile"
5022 (("smagic-static") "lmagic"))
5023
5024 ;; The 'configure' script doesn't recognize things like
5025 ;; '--enable-fast-install'.
5026 (zero? (system*
5027 "./configure"
5028 (string-append "--build-prefix=" (getcwd) "/build")
5029 (string-append "--prefix=" (assoc-ref outputs "out"))
5030 (string-append "--debug")
5031 (string-append "--with-fuse-prefix="
5032 (assoc-ref inputs "fuse"))
5033 (string-append "--with-magic-prefix="
5034 (assoc-ref inputs "libmagic"))
5035 ;; TODO: building with libxml2 fails with linker errors
5036 ;; (string-append "--with-xml2-prefix="
5037 ;; (assoc-ref inputs "libxml2"))
5038 (string-append "--with-ncbi-vdb-sources="
5039 (assoc-ref inputs "ncbi-vdb"))
5040 (string-append "--with-ncbi-vdb-build="
5041 (assoc-ref inputs "ncbi-vdb"))
5042 (string-append "--with-ngs-sdk-prefix="
5043 (assoc-ref inputs "ngs-sdk"))
5044 (string-append "--with-hdf5-prefix="
5045 (assoc-ref inputs "hdf5"))))))
5046 ;; This version of sra-tools fails to build with glibc because of a
5047 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5048 ;; contains a definition of "canonicalize", so we rename it.
5049 ;;
5050 ;; See upstream bug report:
5051 ;; https://github.com/ncbi/sra-tools/issues/67
5052 (add-after 'unpack 'patch-away-glibc-conflict
5053 (lambda _
5054 (substitute* "tools/bam-loader/bam.c"
5055 (("canonicalize\\(" line)
5056 (string-append "sra_tools_" line)))
5057 #t)))))
5058 (native-inputs `(("perl" ,perl)))
5059 (inputs
5060 `(("ngs-sdk" ,ngs-sdk)
5061 ("ncbi-vdb" ,ncbi-vdb)
5062 ("libmagic" ,file)
5063 ("fuse" ,fuse)
5064 ("hdf5" ,hdf5)
5065 ("zlib" ,zlib)))
5066 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5067 (synopsis "Tools and libraries for reading and writing sequencing data")
5068 (description
5069 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5070 reading of sequencing files from the Sequence Read Archive (SRA) database and
5071 writing files into the .sra format.")
5072 (license license:public-domain)))
5073
5074 (define-public seqan
5075 (package
5076 (name "seqan")
5077 (version "1.4.2")
5078 (source (origin
5079 (method url-fetch)
5080 (uri (string-append "http://packages.seqan.de/seqan-library/"
5081 "seqan-library-" version ".tar.bz2"))
5082 (sha256
5083 (base32
5084 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5085 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5086 ;; makes sense to split the outputs.
5087 (outputs '("out" "doc"))
5088 (build-system trivial-build-system)
5089 (arguments
5090 `(#:modules ((guix build utils))
5091 #:builder
5092 (begin
5093 (use-modules (guix build utils))
5094 (let ((tar (assoc-ref %build-inputs "tar"))
5095 (bzip (assoc-ref %build-inputs "bzip2"))
5096 (out (assoc-ref %outputs "out"))
5097 (doc (assoc-ref %outputs "doc")))
5098 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5099 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5100 (chdir (string-append "seqan-library-" ,version))
5101 (copy-recursively "include" (string-append out "/include"))
5102 (copy-recursively "share" (string-append doc "/share"))))))
5103 (native-inputs
5104 `(("source" ,source)
5105 ("tar" ,tar)
5106 ("bzip2" ,bzip2)))
5107 (home-page "http://www.seqan.de")
5108 (synopsis "Library for nucleotide sequence analysis")
5109 (description
5110 "SeqAn is a C++ library of efficient algorithms and data structures for
5111 the analysis of sequences with the focus on biological data. It contains
5112 algorithms and data structures for string representation and their
5113 manipulation, online and indexed string search, efficient I/O of
5114 bioinformatics file formats, sequence alignment, and more.")
5115 (license license:bsd-3)))
5116
5117 (define-public seqmagick
5118 (package
5119 (name "seqmagick")
5120 (version "0.6.1")
5121 (source
5122 (origin
5123 (method url-fetch)
5124 (uri (string-append
5125 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5126 version ".tar.gz"))
5127 (sha256
5128 (base32
5129 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5130 (build-system python-build-system)
5131 (arguments
5132 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5133 `(#:python ,python-2
5134 #:phases
5135 (modify-phases %standard-phases
5136 ;; Current test in setup.py does not work as of 0.6.1,
5137 ;; so use nose to run tests instead for now. See
5138 ;; https://github.com/fhcrc/seqmagick/issues/55
5139 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5140 (inputs
5141 ;; biopython-1.66 is required due to
5142 ;; https://github.com/fhcrc/seqmagick/issues/59
5143 ;; When that issue is resolved the 'python2-biopython-1.66' package
5144 ;; should be removed.
5145 `(("python-biopython" ,python2-biopython-1.66)))
5146 (native-inputs
5147 `(("python-nose" ,python2-nose)))
5148 (home-page "https://github.com/fhcrc/seqmagick")
5149 (synopsis "Tools for converting and modifying sequence files")
5150 (description
5151 "Bioinformaticians often have to convert sequence files between formats
5152 and do little manipulations on them, and it's not worth writing scripts for
5153 that. Seqmagick is a utility to expose the file format conversion in
5154 BioPython in a convenient way. Instead of having a big mess of scripts, there
5155 is one that takes arguments.")
5156 (license license:gpl3)))
5157
5158 (define-public seqtk
5159 (package
5160 (name "seqtk")
5161 (version "1.2")
5162 (source (origin
5163 (method url-fetch)
5164 (uri (string-append
5165 "https://github.com/lh3/seqtk/archive/v"
5166 version ".tar.gz"))
5167 (file-name (string-append name "-" version ".tar.gz"))
5168 (sha256
5169 (base32
5170 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5171 (modules '((guix build utils)))
5172 (snippet
5173 '(begin
5174 ;; Remove extraneous header files, as is done in the seqtk
5175 ;; master branch.
5176 (for-each (lambda (file) (delete-file file))
5177 (list "ksort.h" "kstring.h" "kvec.h"))
5178 #t))))
5179 (build-system gnu-build-system)
5180 (arguments
5181 `(#:phases
5182 (modify-phases %standard-phases
5183 (delete 'configure)
5184 (replace 'check
5185 ;; There are no tests, so we just run a sanity check.
5186 (lambda _ (zero? (system* "./seqtk" "seq"))))
5187 (replace 'install
5188 (lambda* (#:key outputs #:allow-other-keys)
5189 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5190 (install-file "seqtk" bin)))))))
5191 (inputs
5192 `(("zlib" ,zlib)))
5193 (home-page "https://github.com/lh3/seqtk")
5194 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5195 (description
5196 "Seqtk is a fast and lightweight tool for processing sequences in the
5197 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5198 optionally compressed by gzip.")
5199 (license license:expat)))
5200
5201 (define-public snap-aligner
5202 (package
5203 (name "snap-aligner")
5204 (version "1.0beta.18")
5205 (source (origin
5206 (method url-fetch)
5207 (uri (string-append
5208 "https://github.com/amplab/snap/archive/v"
5209 version ".tar.gz"))
5210 (file-name (string-append name "-" version ".tar.gz"))
5211 (sha256
5212 (base32
5213 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5214 (build-system gnu-build-system)
5215 (arguments
5216 '(#:phases
5217 (modify-phases %standard-phases
5218 (delete 'configure)
5219 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5220 (replace 'install
5221 (lambda* (#:key outputs #:allow-other-keys)
5222 (let* ((out (assoc-ref outputs "out"))
5223 (bin (string-append out "/bin")))
5224 (install-file "snap-aligner" bin)
5225 (install-file "SNAPCommand" bin)
5226 #t))))))
5227 (native-inputs
5228 `(("zlib" ,zlib)))
5229 (home-page "http://snap.cs.berkeley.edu/")
5230 (synopsis "Short read DNA sequence aligner")
5231 (description
5232 "SNAP is a fast and accurate aligner for short DNA reads. It is
5233 optimized for modern read lengths of 100 bases or higher, and takes advantage
5234 of these reads to align data quickly through a hash-based indexing scheme.")
5235 ;; 32-bit systems are not supported by the unpatched code.
5236 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5237 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5238 ;; systems without a lot of memory cannot make good use of this program.
5239 (supported-systems '("x86_64-linux"))
5240 (license license:asl2.0)))
5241
5242 (define-public sortmerna
5243 (package
5244 (name "sortmerna")
5245 (version "2.1b")
5246 (source
5247 (origin
5248 (method url-fetch)
5249 (uri (string-append
5250 "https://github.com/biocore/sortmerna/archive/"
5251 version ".tar.gz"))
5252 (file-name (string-append name "-" version ".tar.gz"))
5253 (sha256
5254 (base32
5255 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5256 (build-system gnu-build-system)
5257 (outputs '("out" ;for binaries
5258 "db")) ;for sequence databases
5259 (arguments
5260 `(#:phases
5261 (modify-phases %standard-phases
5262 (replace 'install
5263 (lambda* (#:key outputs #:allow-other-keys)
5264 (let* ((out (assoc-ref outputs "out"))
5265 (bin (string-append out "/bin"))
5266 (db (assoc-ref outputs "db"))
5267 (share
5268 (string-append db "/share/sortmerna/rRNA_databases")))
5269 (install-file "sortmerna" bin)
5270 (install-file "indexdb_rna" bin)
5271 (for-each (lambda (file)
5272 (install-file file share))
5273 (find-files "rRNA_databases" ".*fasta"))
5274 #t))))))
5275 (inputs
5276 `(("zlib" ,zlib)))
5277 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5278 (synopsis "Biological sequence analysis tool for NGS reads")
5279 (description
5280 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5281 and operational taxonomic unit (OTU) picking of next generation
5282 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5283 allows for fast and sensitive analyses of nucleotide sequences. The main
5284 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5285 (license license:lgpl3)))
5286
5287 (define-public star
5288 (package
5289 (name "star")
5290 (version "2.5.3a")
5291 (source (origin
5292 (method url-fetch)
5293 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5294 version ".tar.gz"))
5295 (file-name (string-append name "-" version ".tar.gz"))
5296 (sha256
5297 (base32
5298 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5299 (modules '((guix build utils)))
5300 (snippet
5301 '(begin
5302 (substitute* "source/Makefile"
5303 (("/bin/rm") "rm"))
5304 ;; Remove pre-built binaries and bundled htslib sources.
5305 (delete-file-recursively "bin/MacOSX_x86_64")
5306 (delete-file-recursively "bin/Linux_x86_64")
5307 (delete-file-recursively "bin/Linux_x86_64_static")
5308 (delete-file-recursively "source/htslib")
5309 #t))))
5310 (build-system gnu-build-system)
5311 (arguments
5312 '(#:tests? #f ;no check target
5313 #:make-flags '("STAR")
5314 #:phases
5315 (modify-phases %standard-phases
5316 (add-after 'unpack 'enter-source-dir
5317 (lambda _ (chdir "source") #t))
5318 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5319 (lambda _
5320 (substitute* "Makefile"
5321 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5322 _ prefix) prefix))
5323 (substitute* '("BAMfunctions.cpp"
5324 "signalFromBAM.h"
5325 "bam_cat.h"
5326 "bam_cat.c"
5327 "STAR.cpp"
5328 "bamRemoveDuplicates.cpp")
5329 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5330 (string-append "#include <" header ">")))
5331 (substitute* "IncludeDefine.h"
5332 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5333 (string-append "<" header ">")))
5334 #t))
5335 (replace 'install
5336 (lambda* (#:key outputs #:allow-other-keys)
5337 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5338 (install-file "STAR" bin))
5339 #t))
5340 (delete 'configure))))
5341 (native-inputs
5342 `(("vim" ,vim))) ; for xxd
5343 (inputs
5344 `(("htslib" ,htslib)
5345 ("zlib" ,zlib)))
5346 (home-page "https://github.com/alexdobin/STAR")
5347 (synopsis "Universal RNA-seq aligner")
5348 (description
5349 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5350 based on a previously undescribed RNA-seq alignment algorithm that uses
5351 sequential maximum mappable seed search in uncompressed suffix arrays followed
5352 by seed clustering and stitching procedure. In addition to unbiased de novo
5353 detection of canonical junctions, STAR can discover non-canonical splices and
5354 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5355 sequences.")
5356 ;; Only 64-bit systems are supported according to the README.
5357 (supported-systems '("x86_64-linux" "mips64el-linux"))
5358 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5359 (license license:gpl3+)))
5360
5361 (define-public subread
5362 (package
5363 (name "subread")
5364 (version "1.5.1")
5365 (source (origin
5366 (method url-fetch)
5367 (uri (string-append "mirror://sourceforge/subread/subread-"
5368 version "/subread-" version "-source.tar.gz"))
5369 (sha256
5370 (base32
5371 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5372 (build-system gnu-build-system)
5373 (arguments
5374 `(#:tests? #f ;no "check" target
5375 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5376 ;; optimizations by default, so we override these flags such that x86_64
5377 ;; flags are only added when the build target is an x86_64 system.
5378 #:make-flags
5379 (list (let ((system ,(or (%current-target-system)
5380 (%current-system)))
5381 (flags '("-ggdb" "-fomit-frame-pointer"
5382 "-ffast-math" "-funroll-loops"
5383 "-fmessage-length=0"
5384 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5385 "-DMAKE_STANDALONE"
5386 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5387 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5388 (if (string-prefix? "x86_64" system)
5389 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5390 (string-append "CCFLAGS=" (string-join flags))))
5391 "-f" "Makefile.Linux"
5392 "CC=gcc ${CCFLAGS}")
5393 #:phases
5394 (alist-cons-after
5395 'unpack 'enter-dir
5396 (lambda _ (chdir "src") #t)
5397 (alist-replace
5398 'install
5399 (lambda* (#:key outputs #:allow-other-keys)
5400 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5401 (mkdir-p bin)
5402 (copy-recursively "../bin" bin)))
5403 ;; no "configure" script
5404 (alist-delete 'configure %standard-phases)))))
5405 (inputs `(("zlib" ,zlib)))
5406 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5407 (synopsis "Tool kit for processing next-gen sequencing data")
5408 (description
5409 "The subread package contains the following tools: subread aligner, a
5410 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5411 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5412 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5413 against local background noises.")
5414 (license license:gpl3+)))
5415
5416 (define-public stringtie
5417 (package
5418 (name "stringtie")
5419 (version "1.2.1")
5420 (source (origin
5421 (method url-fetch)
5422 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5423 "stringtie-" version ".tar.gz"))
5424 (sha256
5425 (base32
5426 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5427 (modules '((guix build utils)))
5428 (snippet
5429 '(begin
5430 (delete-file-recursively "samtools-0.1.18")
5431 #t))))
5432 (build-system gnu-build-system)
5433 (arguments
5434 `(#:tests? #f ;no test suite
5435 #:phases
5436 (modify-phases %standard-phases
5437 ;; no configure script
5438 (delete 'configure)
5439 (add-before 'build 'use-system-samtools
5440 (lambda _
5441 (substitute* "Makefile"
5442 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5443 "stringtie: "))
5444 (substitute* '("gclib/GBam.h"
5445 "gclib/GBam.cpp")
5446 (("#include \"(bam|sam|kstring).h\"" _ header)
5447 (string-append "#include <samtools/" header ".h>")))
5448 #t))
5449 (add-after 'unpack 'remove-duplicate-typedef
5450 (lambda _
5451 ;; This typedef conflicts with the typedef in
5452 ;; glibc-2.25/include/bits/types.h
5453 (substitute* "gclib/GThreads.h"
5454 (("typedef long long __intmax_t;") ""))
5455 #t))
5456 (replace 'install
5457 (lambda* (#:key outputs #:allow-other-keys)
5458 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5459 (install-file "stringtie" bin)
5460 #t))))))
5461 (inputs
5462 `(("samtools" ,samtools-0.1)
5463 ("zlib" ,zlib)))
5464 (home-page "http://ccb.jhu.edu/software/stringtie/")
5465 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5466 (description
5467 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5468 alignments into potential transcripts. It uses a novel network flow algorithm
5469 as well as an optional de novo assembly step to assemble and quantitate
5470 full-length transcripts representing multiple splice variants for each gene
5471 locus. Its input can include not only the alignments of raw reads used by
5472 other transcript assemblers, but also alignments of longer sequences that have
5473 been assembled from those reads. To identify differentially expressed genes
5474 between experiments, StringTie's output can be processed either by the
5475 Cuffdiff or Ballgown programs.")
5476 (license license:artistic2.0)))
5477
5478 (define-public taxtastic
5479 (package
5480 (name "taxtastic")
5481 (version "0.6.4")
5482 (source (origin
5483 (method url-fetch)
5484 (uri (pypi-uri "taxtastic" version))
5485 (sha256
5486 (base32
5487 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5488 (build-system python-build-system)
5489 (arguments
5490 `(#:python ,python-2
5491 #:phases
5492 (modify-phases %standard-phases
5493 (replace 'check
5494 (lambda _
5495 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5496 (propagated-inputs
5497 `(("python-sqlalchemy" ,python2-sqlalchemy)
5498 ("python-decorator" ,python2-decorator)
5499 ("python-biopython" ,python2-biopython)
5500 ("python-pandas" ,python2-pandas)))
5501 (home-page "https://github.com/fhcrc/taxtastic")
5502 (synopsis "Tools for taxonomic naming and annotation")
5503 (description
5504 "Taxtastic is software written in python used to build and maintain
5505 reference packages i.e. collections of reference trees, reference alignments,
5506 profiles, and associated taxonomic information.")
5507 (license license:gpl3+)))
5508
5509 (define-public vcftools
5510 (package
5511 (name "vcftools")
5512 (version "0.1.15")
5513 (source (origin
5514 (method url-fetch)
5515 (uri (string-append
5516 "https://github.com/vcftools/vcftools/releases/download/v"
5517 version "/vcftools-" version ".tar.gz"))
5518 (sha256
5519 (base32
5520 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5521 (build-system gnu-build-system)
5522 (arguments
5523 `(#:tests? #f ; no "check" target
5524 #:make-flags (list
5525 "CFLAGS=-O2" ; override "-m64" flag
5526 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5527 (string-append "MANDIR=" (assoc-ref %outputs "out")
5528 "/share/man/man1"))))
5529 (native-inputs
5530 `(("pkg-config" ,pkg-config)))
5531 (inputs
5532 `(("perl" ,perl)
5533 ("zlib" ,zlib)))
5534 (home-page "https://vcftools.github.io/")
5535 (synopsis "Tools for working with VCF files")
5536 (description
5537 "VCFtools is a program package designed for working with VCF files, such
5538 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5539 provide easily accessible methods for working with complex genetic variation
5540 data in the form of VCF files.")
5541 ;; The license is declared as LGPLv3 in the README and
5542 ;; at https://vcftools.github.io/license.html
5543 (license license:lgpl3)))
5544
5545 (define-public infernal
5546 (package
5547 (name "infernal")
5548 (version "1.1.2")
5549 (source (origin
5550 (method url-fetch)
5551 (uri (string-append "http://eddylab.org/software/infernal/"
5552 "infernal-" version ".tar.gz"))
5553 (sha256
5554 (base32
5555 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5556 (build-system gnu-build-system)
5557 (native-inputs
5558 `(("perl" ,perl))) ; for tests
5559 (home-page "http://eddylab.org/infernal/")
5560 (synopsis "Inference of RNA alignments")
5561 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5562 searching DNA sequence databases for RNA structure and sequence similarities.
5563 It is an implementation of a special case of profile stochastic context-free
5564 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5565 profile, but it scores a combination of sequence consensus and RNA secondary
5566 structure consensus, so in many cases, it is more capable of identifying RNA
5567 homologs that conserve their secondary structure more than their primary
5568 sequence.")
5569 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5570 (supported-systems '("i686-linux" "x86_64-linux"))
5571 (license license:bsd-3)))
5572
5573 (define-public r-centipede
5574 (package
5575 (name "r-centipede")
5576 (version "1.2")
5577 (source (origin
5578 (method url-fetch)
5579 (uri (string-append "http://download.r-forge.r-project.org/"
5580 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5581 (sha256
5582 (base32
5583 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5584 (build-system r-build-system)
5585 (home-page "http://centipede.uchicago.edu/")
5586 (synopsis "Predict transcription factor binding sites")
5587 (description
5588 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5589 of the genome that are bound by particular transcription factors. It starts
5590 by identifying a set of candidate binding sites, and then aims to classify the
5591 sites according to whether each site is bound or not bound by a transcription
5592 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5593 between two different types of motif instances using as much relevant
5594 information as possible.")
5595 (license (list license:gpl2+ license:gpl3+))))
5596
5597 (define-public r-vegan
5598 (package
5599 (name "r-vegan")
5600 (version "2.4-3")
5601 (source
5602 (origin
5603 (method url-fetch)
5604 (uri (cran-uri "vegan" version))
5605 (sha256
5606 (base32
5607 "15zcxfix2d854897k1lr0sfmj2n00339nlsppcr3zrb238lb2mi5"))))
5608 (build-system r-build-system)
5609 (native-inputs
5610 `(("gfortran" ,gfortran)
5611 ("r-knitr" ,r-knitr)))
5612 (propagated-inputs
5613 `(("r-cluster" ,r-cluster)
5614 ("r-lattice" ,r-lattice)
5615 ("r-mass" ,r-mass)
5616 ("r-mgcv" ,r-mgcv)
5617 ("r-permute" ,r-permute)))
5618 (home-page "https://cran.r-project.org/web/packages/vegan")
5619 (synopsis "Functions for community ecology")
5620 (description
5621 "The vegan package provides tools for descriptive community ecology. It
5622 has most basic functions of diversity analysis, community ordination and
5623 dissimilarity analysis. Most of its multivariate tools can be used for other
5624 data types as well.")
5625 (license license:gpl2+)))
5626
5627 (define-public r-annotate
5628 (package
5629 (name "r-annotate")
5630 (version "1.54.0")
5631 (source
5632 (origin
5633 (method url-fetch)
5634 (uri (bioconductor-uri "annotate" version))
5635 (sha256
5636 (base32
5637 "03hmbvp3i6lvd307fqdg7akxi2qp322rlky3bzw0zccgm0i0221g"))))
5638 (build-system r-build-system)
5639 (propagated-inputs
5640 `(("r-annotationdbi" ,r-annotationdbi)
5641 ("r-biobase" ,r-biobase)
5642 ("r-biocgenerics" ,r-biocgenerics)
5643 ("r-dbi" ,r-dbi)
5644 ("r-rcurl" ,r-rcurl)
5645 ("r-xml" ,r-xml)
5646 ("r-xtable" ,r-xtable)))
5647 (home-page
5648 "http://bioconductor.org/packages/annotate")
5649 (synopsis "Annotation for microarrays")
5650 (description "This package provides R environments for the annotation of
5651 microarrays.")
5652 (license license:artistic2.0)))
5653
5654 (define-public r-geneplotter
5655 (package
5656 (name "r-geneplotter")
5657 (version "1.54.0")
5658 (source
5659 (origin
5660 (method url-fetch)
5661 (uri (bioconductor-uri "geneplotter" version))
5662 (sha256
5663 (base32
5664 "0a0ajns21db5rrjl16bq6wawggsnxr00fg184pc38nmfghv4z4b6"))))
5665 (build-system r-build-system)
5666 (propagated-inputs
5667 `(("r-annotate" ,r-annotate)
5668 ("r-annotationdbi" ,r-annotationdbi)
5669 ("r-biobase" ,r-biobase)
5670 ("r-biocgenerics" ,r-biocgenerics)
5671 ("r-lattice" ,r-lattice)
5672 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5673 (home-page "http://bioconductor.org/packages/geneplotter")
5674 (synopsis "Graphics functions for genomic data")
5675 (description
5676 "This package provides functions for plotting genomic data.")
5677 (license license:artistic2.0)))
5678
5679 (define-public r-genefilter
5680 (package
5681 (name "r-genefilter")
5682 (version "1.58.0")
5683 (source
5684 (origin
5685 (method url-fetch)
5686 (uri (bioconductor-uri "genefilter" version))
5687 (sha256
5688 (base32
5689 "0sf2hdi9nv6r83vn1y65m4jiba8pffddpj46d6yjn5rlsixplmqg"))))
5690 (build-system r-build-system)
5691 (native-inputs
5692 `(("gfortran" ,gfortran)))
5693 (propagated-inputs
5694 `(("r-annotate" ,r-annotate)
5695 ("r-annotationdbi" ,r-annotationdbi)
5696 ("r-biobase" ,r-biobase)
5697 ("r-s4vectors" ,r-s4vectors)
5698 ("r-survival" ,r-survival)))
5699 (home-page "http://bioconductor.org/packages/genefilter")
5700 (synopsis "Filter genes from high-throughput experiments")
5701 (description
5702 "This package provides basic functions for filtering genes from
5703 high-throughput sequencing experiments.")
5704 (license license:artistic2.0)))
5705
5706 (define-public r-deseq2
5707 (package
5708 (name "r-deseq2")
5709 (version "1.16.0")
5710 (source
5711 (origin
5712 (method url-fetch)
5713 (uri (bioconductor-uri "DESeq2" version))
5714 (sha256
5715 (base32
5716 "0m0apn3xi4kdkinsj4xkw5cwysicyjr6xxlxhpa4scyv589am1s5"))))
5717 (properties `((upstream-name . "DESeq2")))
5718 (build-system r-build-system)
5719 (propagated-inputs
5720 `(("r-biobase" ,r-biobase)
5721 ("r-biocgenerics" ,r-biocgenerics)
5722 ("r-biocparallel" ,r-biocparallel)
5723 ("r-genefilter" ,r-genefilter)
5724 ("r-geneplotter" ,r-geneplotter)
5725 ("r-genomicranges" ,r-genomicranges)
5726 ("r-ggplot2" ,r-ggplot2)
5727 ("r-hmisc" ,r-hmisc)
5728 ("r-iranges" ,r-iranges)
5729 ("r-locfit" ,r-locfit)
5730 ("r-rcpp" ,r-rcpp)
5731 ("r-rcpparmadillo" ,r-rcpparmadillo)
5732 ("r-s4vectors" ,r-s4vectors)
5733 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5734 (home-page "http://bioconductor.org/packages/DESeq2")
5735 (synopsis "Differential gene expression analysis")
5736 (description
5737 "This package provides functions to estimate variance-mean dependence in
5738 count data from high-throughput nucleotide sequencing assays and test for
5739 differential expression based on a model using the negative binomial
5740 distribution.")
5741 (license license:lgpl3+)))
5742
5743 (define-public r-annotationforge
5744 (package
5745 (name "r-annotationforge")
5746 (version "1.18.0")
5747 (source
5748 (origin
5749 (method url-fetch)
5750 (uri (bioconductor-uri "AnnotationForge" version))
5751 (sha256
5752 (base32
5753 "01kd86vvgpa4a5zivcy4g6z8rhcykasdskrz8yqsqz211sd1xsr3"))))
5754 (properties
5755 `((upstream-name . "AnnotationForge")))
5756 (build-system r-build-system)
5757 (propagated-inputs
5758 `(("r-annotationdbi" ,r-annotationdbi)
5759 ("r-biobase" ,r-biobase)
5760 ("r-biocgenerics" ,r-biocgenerics)
5761 ("r-dbi" ,r-dbi)
5762 ("r-rcurl" ,r-rcurl)
5763 ("r-rsqlite" ,r-rsqlite)
5764 ("r-s4vectors" ,r-s4vectors)
5765 ("r-xml" ,r-xml)))
5766 (home-page "http://bioconductor.org/packages/AnnotationForge")
5767 (synopsis "Code for building annotation database packages")
5768 (description
5769 "This package provides code for generating Annotation packages and their
5770 databases. Packages produced are intended to be used with AnnotationDbi.")
5771 (license license:artistic2.0)))
5772
5773 (define-public r-rbgl
5774 (package
5775 (name "r-rbgl")
5776 (version "1.52.0")
5777 (source
5778 (origin
5779 (method url-fetch)
5780 (uri (bioconductor-uri "RBGL" version))
5781 (sha256
5782 (base32
5783 "11db6kvz453ypj9ds3xpjqzwrrjck84ijn4wlhkfyz2dzdgd5ryv"))))
5784 (properties `((upstream-name . "RBGL")))
5785 (build-system r-build-system)
5786 (propagated-inputs `(("r-graph" ,r-graph)))
5787 (home-page "http://www.bioconductor.org/packages/RBGL")
5788 (synopsis "Interface to the Boost graph library")
5789 (description
5790 "This package provides a fairly extensive and comprehensive interface to
5791 the graph algorithms contained in the Boost library.")
5792 (license license:artistic2.0)))
5793
5794 (define-public r-gseabase
5795 (package
5796 (name "r-gseabase")
5797 (version "1.38.0")
5798 (source
5799 (origin
5800 (method url-fetch)
5801 (uri (bioconductor-uri "GSEABase" version))
5802 (sha256
5803 (base32
5804 "1c6i6g4fj3b8wjyxyygr7i3v8sxrq1ffb2bbicya5ah2gdaclfad"))))
5805 (properties `((upstream-name . "GSEABase")))
5806 (build-system r-build-system)
5807 (propagated-inputs
5808 `(("r-annotate" ,r-annotate)
5809 ("r-annotationdbi" ,r-annotationdbi)
5810 ("r-biobase" ,r-biobase)
5811 ("r-biocgenerics" ,r-biocgenerics)
5812 ("r-graph" ,r-graph)
5813 ("r-xml" ,r-xml)))
5814 (home-page "http://bioconductor.org/packages/GSEABase")
5815 (synopsis "Gene set enrichment data structures and methods")
5816 (description
5817 "This package provides classes and methods to support @dfn{Gene Set
5818 Enrichment Analysis} (GSEA).")
5819 (license license:artistic2.0)))
5820
5821 (define-public r-category
5822 (package
5823 (name "r-category")
5824 (version "2.42.0")
5825 (source
5826 (origin
5827 (method url-fetch)
5828 (uri (bioconductor-uri "Category" version))
5829 (sha256
5830 (base32
5831 "0swcmihyjg0fhaaydl9hm24aj9zffw3bibza9y6sqs6jaqd97f09"))))
5832 (properties `((upstream-name . "Category")))
5833 (build-system r-build-system)
5834 (propagated-inputs
5835 `(("r-annotate" ,r-annotate)
5836 ("r-annotationdbi" ,r-annotationdbi)
5837 ("r-biobase" ,r-biobase)
5838 ("r-biocgenerics" ,r-biocgenerics)
5839 ("r-genefilter" ,r-genefilter)
5840 ("r-graph" ,r-graph)
5841 ("r-gseabase" ,r-gseabase)
5842 ("r-matrix" ,r-matrix)
5843 ("r-rbgl" ,r-rbgl)
5844 ("r-rsqlite" ,r-rsqlite)))
5845 (home-page "http://bioconductor.org/packages/Category")
5846 (synopsis "Category analysis")
5847 (description
5848 "This package provides a collection of tools for performing category
5849 analysis.")
5850 (license license:artistic2.0)))
5851
5852 (define-public r-gostats
5853 (package
5854 (name "r-gostats")
5855 (version "2.42.0")
5856 (source
5857 (origin
5858 (method url-fetch)
5859 (uri (bioconductor-uri "GOstats" version))
5860 (sha256
5861 (base32
5862 "0qvqjgfnd9ap4rikvyxa9p4dhcnccvkw8phzv88vghh6pq463d62"))))
5863 (properties `((upstream-name . "GOstats")))
5864 (build-system r-build-system)
5865 (propagated-inputs
5866 `(("r-annotate" ,r-annotate)
5867 ("r-annotationdbi" ,r-annotationdbi)
5868 ("r-annotationforge" ,r-annotationforge)
5869 ("r-biobase" ,r-biobase)
5870 ("r-category" ,r-category)
5871 ("r-go-db" ,r-go-db)
5872 ("r-graph" ,r-graph)
5873 ("r-rbgl" ,r-rbgl)))
5874 (home-page "http://bioconductor.org/packages/GOstats")
5875 (synopsis "Tools for manipulating GO and microarrays")
5876 (description
5877 "This package provides a set of tools for interacting with GO and
5878 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5879 testing and other simple calculations.")
5880 (license license:artistic2.0)))
5881
5882 (define-public r-shortread
5883 (package
5884 (name "r-shortread")
5885 (version "1.34.0")
5886 (source
5887 (origin
5888 (method url-fetch)
5889 (uri (bioconductor-uri "ShortRead" version))
5890 (sha256
5891 (base32
5892 "0ayk3d5625ymb5g2gycq6banzqmyd642xrwjzhdshz2dwid7kly8"))))
5893 (properties `((upstream-name . "ShortRead")))
5894 (build-system r-build-system)
5895 (inputs
5896 `(("zlib" ,zlib)))
5897 (propagated-inputs
5898 `(("r-biobase" ,r-biobase)
5899 ("r-biocgenerics" ,r-biocgenerics)
5900 ("r-biocparallel" ,r-biocparallel)
5901 ("r-biostrings" ,r-biostrings)
5902 ("r-genomeinfodb" ,r-genomeinfodb)
5903 ("r-genomicalignments" ,r-genomicalignments)
5904 ("r-genomicranges" ,r-genomicranges)
5905 ("r-hwriter" ,r-hwriter)
5906 ("r-iranges" ,r-iranges)
5907 ("r-lattice" ,r-lattice)
5908 ("r-latticeextra" ,r-latticeextra)
5909 ("r-rsamtools" ,r-rsamtools)
5910 ("r-s4vectors" ,r-s4vectors)
5911 ("r-xvector" ,r-xvector)
5912 ("r-zlibbioc" ,r-zlibbioc)))
5913 (home-page "http://bioconductor.org/packages/ShortRead")
5914 (synopsis "FASTQ input and manipulation tools")
5915 (description
5916 "This package implements sampling, iteration, and input of FASTQ files.
5917 It includes functions for filtering and trimming reads, and for generating a
5918 quality assessment report. Data are represented as
5919 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5920 purposes. The package also contains legacy support for early single-end,
5921 ungapped alignment formats.")
5922 (license license:artistic2.0)))
5923
5924 (define-public r-systempiper
5925 (package
5926 (name "r-systempiper")
5927 (version "1.10.0")
5928 (source
5929 (origin
5930 (method url-fetch)
5931 (uri (bioconductor-uri "systemPipeR" version))
5932 (sha256
5933 (base32
5934 "0c3m5rq63ypv15yca97yag5d4vgd7xj9by2a4sd8z0pcmpajz0hw"))))
5935 (properties `((upstream-name . "systemPipeR")))
5936 (build-system r-build-system)
5937 (propagated-inputs
5938 `(("r-annotate" ,r-annotate)
5939 ("r-batchjobs" ,r-batchjobs)
5940 ("r-biocgenerics" ,r-biocgenerics)
5941 ("r-biostrings" ,r-biostrings)
5942 ("r-deseq2" ,r-deseq2)
5943 ("r-edger" ,r-edger)
5944 ("r-genomicfeatures" ,r-genomicfeatures)
5945 ("r-genomicranges" ,r-genomicranges)
5946 ("r-ggplot2" ,r-ggplot2)
5947 ("r-go-db" ,r-go-db)
5948 ("r-gostats" ,r-gostats)
5949 ("r-limma" ,r-limma)
5950 ("r-pheatmap" ,r-pheatmap)
5951 ("r-rjson" ,r-rjson)
5952 ("r-rsamtools" ,r-rsamtools)
5953 ("r-shortread" ,r-shortread)
5954 ("r-summarizedexperiment" ,r-summarizedexperiment)
5955 ("r-variantannotation" ,r-variantannotation)))
5956 (home-page "https://github.com/tgirke/systemPipeR")
5957 (synopsis "Next generation sequencing workflow and reporting environment")
5958 (description
5959 "This R package provides tools for building and running automated
5960 end-to-end analysis workflows for a wide range of @dfn{next generation
5961 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5962 Important features include a uniform workflow interface across different NGS
5963 applications, automated report generation, and support for running both R and
5964 command-line software, such as NGS aligners or peak/variant callers, on local
5965 computers or compute clusters. Efficient handling of complex sample sets and
5966 experimental designs is facilitated by a consistently implemented sample
5967 annotation infrastructure.")
5968 (license license:artistic2.0)))
5969
5970 (define-public r-grohmm
5971 (package
5972 (name "r-grohmm")
5973 (version "1.10.0")
5974 (source
5975 (origin
5976 (method url-fetch)
5977 (uri (bioconductor-uri "groHMM" version))
5978 (sha256
5979 (base32
5980 "16k1kp4sbhh0vp7dzywafq52csq42ksqfrqfy4bdv1qbd7536dpd"))))
5981 (properties `((upstream-name . "groHMM")))
5982 (build-system r-build-system)
5983 (propagated-inputs
5984 `(("r-genomeinfodb" ,r-genomeinfodb)
5985 ("r-genomicalignments" ,r-genomicalignments)
5986 ("r-genomicranges" ,r-genomicranges)
5987 ("r-iranges" ,r-iranges)
5988 ("r-mass" ,r-mass)
5989 ("r-rtracklayer" ,r-rtracklayer)
5990 ("r-s4vectors" ,r-s4vectors)))
5991 (home-page "https://github.com/Kraus-Lab/groHMM")
5992 (synopsis "GRO-seq analysis pipeline")
5993 (description
5994 "This package provides a pipeline for the analysis of GRO-seq data.")
5995 (license license:gpl3+)))
5996
5997 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
5998 (package
5999 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6000 (version "3.2.2")
6001 (source (origin
6002 (method url-fetch)
6003 ;; We cannot use bioconductor-uri here because this tarball is
6004 ;; located under "data/annotation/" instead of "bioc/".
6005 (uri (string-append "http://bioconductor.org/packages/"
6006 "release/data/annotation/src/contrib"
6007 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6008 version ".tar.gz"))
6009 (sha256
6010 (base32
6011 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6012 (properties
6013 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6014 (build-system r-build-system)
6015 ;; As this package provides little more than a very large data file it
6016 ;; doesn't make sense to build substitutes.
6017 (arguments `(#:substitutable? #f))
6018 (propagated-inputs
6019 `(("r-genomicfeatures" ,r-genomicfeatures)))
6020 (home-page
6021 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6022 (synopsis "Annotation package for human genome in TxDb format")
6023 (description
6024 "This package provides an annotation database of Homo sapiens genome
6025 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6026 track. The database is exposed as a @code{TxDb} object.")
6027 (license license:artistic2.0)))
6028
6029 (define-public vsearch
6030 (package
6031 (name "vsearch")
6032 (version "2.4.3")
6033 (source
6034 (origin
6035 (method url-fetch)
6036 (uri (string-append
6037 "https://github.com/torognes/vsearch/archive/v"
6038 version ".tar.gz"))
6039 (file-name (string-append name "-" version ".tar.gz"))
6040 (sha256
6041 (base32
6042 "0hc110ycqpa54nr6x173qg7190hk08qp7yz7zzqxlsypqnpc5zzp"))
6043 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6044 (snippet
6045 '(begin
6046 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6047 ;; for this in the patch.
6048 (delete-file "src/city.h")
6049 (delete-file "src/citycrc.h")
6050 (delete-file "src/city.cc")
6051 #t))))
6052 (build-system gnu-build-system)
6053 (arguments
6054 `(#:phases
6055 (modify-phases %standard-phases
6056 (add-before 'configure 'autogen
6057 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6058 (inputs
6059 `(("zlib" ,zlib)
6060 ("bzip2" ,bzip2)
6061 ("cityhash" ,cityhash)))
6062 (native-inputs
6063 `(("autoconf" ,autoconf)
6064 ("automake" ,automake)))
6065 (synopsis "Sequence search tools for metagenomics")
6066 (description
6067 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6068 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6069 masking. The tool takes advantage of parallelism in the form of SIMD
6070 vectorization as well as multiple threads to perform accurate alignments at
6071 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6072 Needleman-Wunsch).")
6073 (home-page "https://github.com/torognes/vsearch")
6074 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6075 ;; platforms.
6076 (supported-systems '("x86_64-linux"))
6077 ;; Dual licensed; also includes public domain source.
6078 (license (list license:gpl3 license:bsd-2))))
6079
6080 (define-public pardre
6081 (package
6082 (name "pardre")
6083 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6084 (version "1.1.5-1")
6085 (source
6086 (origin
6087 (method url-fetch)
6088 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6089 "1.1.5" ".tar.gz"))
6090 (sha256
6091 (base32
6092 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6093 (build-system gnu-build-system)
6094 (arguments
6095 `(#:tests? #f ; no tests included
6096 #:phases
6097 (modify-phases %standard-phases
6098 (delete 'configure)
6099 (replace 'install
6100 (lambda* (#:key outputs #:allow-other-keys)
6101 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6102 (install-file "ParDRe" bin)
6103 #t))))))
6104 (inputs
6105 `(("openmpi" ,openmpi)
6106 ("zlib" ,zlib)))
6107 (synopsis "Parallel tool to remove duplicate DNA reads")
6108 (description
6109 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6110 Duplicate reads can be seen as identical or nearly identical sequences with
6111 some mismatches. This tool lets users avoid the analysis of unnecessary
6112 reads, reducing the time of subsequent procedures with the
6113 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6114 in order to exploit the parallel capabilities of multicore clusters. It is
6115 faster than multithreaded counterparts (end of 2015) for the same number of
6116 cores and, thanks to the message-passing technology, it can be executed on
6117 clusters.")
6118 (home-page "https://sourceforge.net/projects/pardre/")
6119 (license license:gpl3+)))
6120
6121 (define-public ruby-bio-kseq
6122 (package
6123 (name "ruby-bio-kseq")
6124 (version "0.0.2")
6125 (source
6126 (origin
6127 (method url-fetch)
6128 (uri (rubygems-uri "bio-kseq" version))
6129 (sha256
6130 (base32
6131 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6132 (build-system ruby-build-system)
6133 (arguments
6134 `(#:test-target "spec"))
6135 (native-inputs
6136 `(("bundler" ,bundler)
6137 ("ruby-rspec" ,ruby-rspec)
6138 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6139 (inputs
6140 `(("zlib" ,zlib)))
6141 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6142 (description
6143 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6144 FASTQ parsing code. It provides a fast iterator over sequences and their
6145 quality scores.")
6146 (home-page "https://github.com/gusevfe/bio-kseq")
6147 (license license:expat)))
6148
6149 (define-public bio-locus
6150 (package
6151 (name "bio-locus")
6152 (version "0.0.7")
6153 (source
6154 (origin
6155 (method url-fetch)
6156 (uri (rubygems-uri "bio-locus" version))
6157 (sha256
6158 (base32
6159 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6160 (build-system ruby-build-system)
6161 (native-inputs
6162 `(("ruby-rspec" ,ruby-rspec)))
6163 (synopsis "Tool for fast querying of genome locations")
6164 (description
6165 "Bio-locus is a tabix-like tool for fast querying of genome
6166 locations. Many file formats in bioinformatics contain records that
6167 start with a chromosome name and a position for a SNP, or a start-end
6168 position for indels. Bio-locus allows users to store this chr+pos or
6169 chr+pos+alt information in a database.")
6170 (home-page "https://github.com/pjotrp/bio-locus")
6171 (license license:expat)))
6172
6173 (define-public bio-blastxmlparser
6174 (package
6175 (name "bio-blastxmlparser")
6176 (version "2.0.4")
6177 (source (origin
6178 (method url-fetch)
6179 (uri (rubygems-uri "bio-blastxmlparser" version))
6180 (sha256
6181 (base32
6182 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6183 (build-system ruby-build-system)
6184 (propagated-inputs
6185 `(("ruby-bio-logger" ,ruby-bio-logger)
6186 ("ruby-nokogiri" ,ruby-nokogiri)))
6187 (inputs
6188 `(("ruby-rspec" ,ruby-rspec)))
6189 (synopsis "Fast big data BLAST XML parser and library")
6190 (description
6191 "Very fast parallel big-data BLAST XML file parser which can be used as
6192 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6193 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6194 (home-page "https://github.com/pjotrp/blastxmlparser")
6195 (license license:expat)))
6196
6197 (define-public bioruby
6198 (package
6199 (name "bioruby")
6200 (version "1.5.1")
6201 (source
6202 (origin
6203 (method url-fetch)
6204 (uri (rubygems-uri "bio" version))
6205 (sha256
6206 (base32
6207 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6208 (build-system ruby-build-system)
6209 (propagated-inputs
6210 `(("ruby-libxml" ,ruby-libxml)))
6211 (native-inputs
6212 `(("which" ,which))) ; required for test phase
6213 (arguments
6214 `(#:phases
6215 (modify-phases %standard-phases
6216 (add-before 'build 'patch-test-command
6217 (lambda _
6218 (substitute* '("test/functional/bio/test_command.rb")
6219 (("/bin/sh") (which "sh")))
6220 (substitute* '("test/functional/bio/test_command.rb")
6221 (("/bin/ls") (which "ls")))
6222 (substitute* '("test/functional/bio/test_command.rb")
6223 (("which") (which "which")))
6224 (substitute* '("test/functional/bio/test_command.rb",
6225 "test/data/command/echoarg2.sh")
6226 (("/bin/echo") (which "echo")))
6227 #t)))))
6228 (synopsis "Ruby library, shell and utilities for bioinformatics")
6229 (description "BioRuby comes with a comprehensive set of Ruby development
6230 tools and libraries for bioinformatics and molecular biology. BioRuby has
6231 components for sequence analysis, pathway analysis, protein modelling and
6232 phylogenetic analysis; it supports many widely used data formats and provides
6233 easy access to databases, external programs and public web services, including
6234 BLAST, KEGG, GenBank, MEDLINE and GO.")
6235 (home-page "http://bioruby.org/")
6236 ;; Code is released under Ruby license, except for setup
6237 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6238 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6239
6240 (define-public r-acsnminer
6241 (package
6242 (name "r-acsnminer")
6243 (version "0.16.8.25")
6244 (source (origin
6245 (method url-fetch)
6246 (uri (cran-uri "ACSNMineR" version))
6247 (sha256
6248 (base32
6249 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6250 (properties `((upstream-name . "ACSNMineR")))
6251 (build-system r-build-system)
6252 (propagated-inputs
6253 `(("r-ggplot2" ,r-ggplot2)
6254 ("r-gridextra" ,r-gridextra)))
6255 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6256 (synopsis "Gene enrichment analysis")
6257 (description
6258 "This package provides tools to compute and represent gene set enrichment
6259 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6260 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6261 enrichment can be run with hypergeometric test or Fisher exact test, and can
6262 use multiple corrections. Visualization of data can be done either by
6263 barplots or heatmaps.")
6264 (license license:gpl2+)))
6265
6266 (define-public r-biocgenerics
6267 (package
6268 (name "r-biocgenerics")
6269 (version "0.22.0")
6270 (source (origin
6271 (method url-fetch)
6272 (uri (bioconductor-uri "BiocGenerics" version))
6273 (sha256
6274 (base32
6275 "0qbmz2qxwwi30xpxpvp2h1h7l494rbbz5d9pls5cfhqdv3wnpzsv"))))
6276 (properties
6277 `((upstream-name . "BiocGenerics")))
6278 (build-system r-build-system)
6279 (home-page "http://bioconductor.org/packages/BiocGenerics")
6280 (synopsis "S4 generic functions for Bioconductor")
6281 (description
6282 "This package provides S4 generic functions needed by many Bioconductor
6283 packages.")
6284 (license license:artistic2.0)))
6285
6286 (define-public r-biocinstaller
6287 (package
6288 (name "r-biocinstaller")
6289 (version "1.26.0")
6290 (source (origin
6291 (method url-fetch)
6292 (uri (bioconductor-uri "BiocInstaller" version))
6293 (sha256
6294 (base32
6295 "0njw2q3lq1rrjx8qzw5d2130l72bmd3g2z8qlxqmkdcbmmgliyj2"))))
6296 (properties
6297 `((upstream-name . "BiocInstaller")))
6298 (build-system r-build-system)
6299 (home-page "http://bioconductor.org/packages/BiocInstaller")
6300 (synopsis "Install Bioconductor packages")
6301 (description "This package is used to install and update R packages from
6302 Bioconductor, CRAN, and Github.")
6303 (license license:artistic2.0)))
6304
6305 (define-public r-biocviews
6306 (package
6307 (name "r-biocviews")
6308 (version "1.44.0")
6309 (source (origin
6310 (method url-fetch)
6311 (uri (bioconductor-uri "biocViews" version))
6312 (sha256
6313 (base32
6314 "17hi8w0w63f5yc43kid5pbld3ca78sj6n8x9dmkbl8h48818xbga"))))
6315 (properties
6316 `((upstream-name . "biocViews")))
6317 (build-system r-build-system)
6318 (propagated-inputs
6319 `(("r-biobase" ,r-biobase)
6320 ("r-graph" ,r-graph)
6321 ("r-rbgl" ,r-rbgl)
6322 ("r-rcurl" ,r-rcurl)
6323 ("r-xml" ,r-xml)
6324 ("r-knitr" ,r-knitr)
6325 ("r-runit" ,r-runit)))
6326 (home-page "http://bioconductor.org/packages/biocViews")
6327 (synopsis "Bioconductor package categorization helper")
6328 (description "The purpose of biocViews is to create HTML pages that
6329 categorize packages in a Bioconductor package repository according to keywords,
6330 also known as views, in a controlled vocabulary.")
6331 (license license:artistic2.0)))
6332
6333 (define-public r-bookdown
6334 (package
6335 (name "r-bookdown")
6336 (version "0.3")
6337 (source (origin
6338 (method url-fetch)
6339 (uri (cran-uri "bookdown" version))
6340 (sha256
6341 (base32
6342 "0r9bchzg7im6psc3jphvshzbidc5bv5xaih1qg7b5518jy4iyvb9"))))
6343 (build-system r-build-system)
6344 (propagated-inputs
6345 `(("r-htmltools" ,r-htmltools)
6346 ("r-knitr" ,r-knitr)
6347 ("r-rmarkdown" ,r-rmarkdown)
6348 ("r-yaml" ,r-yaml)))
6349 (home-page "https://github.com/rstudio/bookdown")
6350 (synopsis "Authoring books and technical documents with R markdown")
6351 (description "This package provides output formats and utilities for
6352 authoring books and technical documents with R Markdown.")
6353 (license license:gpl3)))
6354
6355 (define-public r-biocstyle
6356 (package
6357 (name "r-biocstyle")
6358 (version "2.4.0")
6359 (source (origin
6360 (method url-fetch)
6361 (uri (bioconductor-uri "BiocStyle" version))
6362 (sha256
6363 (base32
6364 "1n2c8rj920wmk3q2khmjfnhn5i4b3lmhx1whnghk0zk3jf88hvbi"))))
6365 (properties
6366 `((upstream-name . "BiocStyle")))
6367 (build-system r-build-system)
6368 (propagated-inputs
6369 `(("r-bookdown" ,r-bookdown)
6370 ("r-knitr" ,r-knitr)
6371 ("r-rmarkdown" ,r-rmarkdown)
6372 ("r-yaml" ,r-yaml)))
6373 (home-page "http://bioconductor.org/packages/BiocStyle")
6374 (synopsis "Bioconductor formatting styles")
6375 (description "This package provides standard formatting styles for
6376 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6377 functionality.")
6378 (license license:artistic2.0)))
6379
6380 (define-public r-bioccheck
6381 (package
6382 (name "r-bioccheck")
6383 (version "1.12.0")
6384 (source (origin
6385 (method url-fetch)
6386 (uri (bioconductor-uri "BiocCheck" version))
6387 (sha256
6388 (base32
6389 "01zkw5hggzvn0wj4msac71k1mknq4h2inn1c2hwqgw4cy1675wl0"))))
6390 (properties
6391 `((upstream-name . "BiocCheck")))
6392 (build-system r-build-system)
6393 (arguments
6394 '(#:phases
6395 (modify-phases %standard-phases
6396 ;; This package can be used by calling BiocCheck(<package>) from
6397 ;; within R, or by running R CMD BiocCheck <package>. This phase
6398 ;; makes sure the latter works. For this to work, the BiocCheck
6399 ;; script must be somewhere on the PATH (not the R bin directory).
6400 (add-after 'install 'install-bioccheck-subcommand
6401 (lambda* (#:key outputs #:allow-other-keys)
6402 (let* ((out (assoc-ref outputs "out"))
6403 (dest-dir (string-append out "/bin"))
6404 (script-dir
6405 (string-append out "/site-library/BiocCheck/script/")))
6406 (mkdir-p dest-dir)
6407 (symlink (string-append script-dir "/checkBadDeps.R")
6408 (string-append dest-dir "/checkBadDeps.R"))
6409 (symlink (string-append script-dir "/BiocCheck")
6410 (string-append dest-dir "/BiocCheck")))
6411 #t)))))
6412 (native-inputs
6413 `(("which" ,which)))
6414 (propagated-inputs
6415 `(("r-codetools" ,r-codetools)
6416 ("r-graph" ,r-graph)
6417 ("r-httr" ,r-httr)
6418 ("r-optparse" ,r-optparse)
6419 ("r-biocinstaller" ,r-biocinstaller)
6420 ("r-biocviews" ,r-biocviews)))
6421 (home-page "http://bioconductor.org/packages/BiocCheck")
6422 (synopsis "Executes Bioconductor-specific package checks")
6423 (description "This package contains tools to perform additional quality
6424 checks on R packages that are to be submitted to the Bioconductor repository.")
6425 (license license:artistic2.0)))
6426
6427 (define-public r-getopt
6428 (package
6429 (name "r-getopt")
6430 (version "1.20.0")
6431 (source
6432 (origin
6433 (method url-fetch)
6434 (uri (cran-uri "getopt" version))
6435 (sha256
6436 (base32
6437 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6438 (build-system r-build-system)
6439 (home-page "https://github.com/trevorld/getopt")
6440 (synopsis "Command-line option processor for R")
6441 (description
6442 "This package is designed to be used with Rscript to write shebang
6443 scripts that accept short and long options. Many users will prefer to
6444 use the packages @code{optparse} or @code{argparse} which add extra
6445 features like automatically generated help options and usage texts,
6446 support for default values, positional argument support, etc.")
6447 (license license:gpl2+)))
6448
6449 (define-public r-optparse
6450 (package
6451 (name "r-optparse")
6452 (version "1.3.2")
6453 (source
6454 (origin
6455 (method url-fetch)
6456 (uri (cran-uri "optparse" version))
6457 (sha256
6458 (base32
6459 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6460 (build-system r-build-system)
6461 (propagated-inputs
6462 `(("r-getopt" ,r-getopt)))
6463 (home-page
6464 "https://github.com/trevorld/optparse")
6465 (synopsis "Command line option parser")
6466 (description
6467 "This package provides a command line parser inspired by Python's
6468 @code{optparse} library to be used with Rscript to write shebang scripts
6469 that accept short and long options.")
6470 (license license:gpl2+)))
6471
6472 (define-public r-dnacopy
6473 (package
6474 (name "r-dnacopy")
6475 (version "1.50.0")
6476 (source (origin
6477 (method url-fetch)
6478 (uri (bioconductor-uri "DNAcopy" version))
6479 (sha256
6480 (base32
6481 "0112ry62z18m7rdyrn3gvbxq2f6m44cawhcfb1f02z9xzlsj0k28"))))
6482 (properties
6483 `((upstream-name . "DNAcopy")))
6484 (build-system r-build-system)
6485 (inputs
6486 `(("gfortran" ,gfortran)))
6487 (home-page "https://bioconductor.org/packages/DNAcopy")
6488 (synopsis "Implementation of a circular binary segmentation algorithm")
6489 (description "This package implements the circular binary segmentation (CBS)
6490 algorithm to segment DNA copy number data and identify genomic regions with
6491 abnormal copy number.")
6492 (license license:gpl2+)))
6493
6494 (define-public r-s4vectors
6495 (package
6496 (name "r-s4vectors")
6497 (version "0.14.0")
6498 (source (origin
6499 (method url-fetch)
6500 (uri (bioconductor-uri "S4Vectors" version))
6501 (sha256
6502 (base32
6503 "0ywwrs4d752xfk0p0w122kvi0xvp6nmxnyynchbsa8zciqymhgv8"))))
6504 (properties
6505 `((upstream-name . "S4Vectors")))
6506 (build-system r-build-system)
6507 (propagated-inputs
6508 `(("r-biocgenerics" ,r-biocgenerics)))
6509 (home-page "http://bioconductor.org/packages/S4Vectors")
6510 (synopsis "S4 implementation of vectors and lists")
6511 (description
6512 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6513 classes and a set of generic functions that extend the semantic of ordinary
6514 vectors and lists in R. Package developers can easily implement vector-like
6515 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6516 In addition, a few low-level concrete subclasses of general interest (e.g.
6517 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6518 S4Vectors package itself.")
6519 (license license:artistic2.0)))
6520
6521 (define-public r-seqinr
6522 (package
6523 (name "r-seqinr")
6524 (version "3.3-6")
6525 (source
6526 (origin
6527 (method url-fetch)
6528 (uri (cran-uri "seqinr" version))
6529 (sha256
6530 (base32
6531 "13d0qxm2244wgdl2dy2s8vnrnf5fx4n47if9gkb49dqx6c0sx8s2"))))
6532 (build-system r-build-system)
6533 (propagated-inputs
6534 `(("r-ade4" ,r-ade4)
6535 ("r-segmented" ,r-segmented)))
6536 (inputs
6537 `(("zlib" ,zlib)))
6538 (home-page "http://seqinr.r-forge.r-project.org/")
6539 (synopsis "Biological sequences retrieval and analysis")
6540 (description
6541 "This package provides tools for exploratory data analysis and data
6542 visualization of biological sequence (DNA and protein) data. It also includes
6543 utilities for sequence data management under the ACNUC system.")
6544 (license license:gpl2+)))
6545
6546 (define-public r-iranges
6547 (package
6548 (name "r-iranges")
6549 (version "2.10.0")
6550 (source (origin
6551 (method url-fetch)
6552 (uri (bioconductor-uri "IRanges" version))
6553 (sha256
6554 (base32
6555 "0zp4mxm9h1p4krj7m7cinkvwa2ibqkq59jwpan97yvhb4z8q0d6n"))))
6556 (properties
6557 `((upstream-name . "IRanges")))
6558 (build-system r-build-system)
6559 (propagated-inputs
6560 `(("r-biocgenerics" ,r-biocgenerics)
6561 ("r-s4vectors" ,r-s4vectors)))
6562 (home-page "http://bioconductor.org/packages/IRanges")
6563 (synopsis "Infrastructure for manipulating intervals on sequences")
6564 (description
6565 "This package provides efficient low-level and highly reusable S4 classes
6566 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6567 generally, data that can be organized sequentially (formally defined as
6568 @code{Vector} objects), as well as views on these @code{Vector} objects.
6569 Efficient list-like classes are also provided for storing big collections of
6570 instances of the basic classes. All classes in the package use consistent
6571 naming and share the same rich and consistent \"Vector API\" as much as
6572 possible.")
6573 (license license:artistic2.0)))
6574
6575 (define-public r-genomeinfodbdata
6576 (package
6577 (name "r-genomeinfodbdata")
6578 (version "0.99.0")
6579 (source (origin
6580 (method url-fetch)
6581 ;; We cannot use bioconductor-uri here because this tarball is
6582 ;; located under "data/annotation/" instead of "bioc/".
6583 (uri (string-append "https://bioconductor.org/packages/release/"
6584 "data/annotation/src/contrib/GenomeInfoDbData_"
6585 version ".tar.gz"))
6586 (sha256
6587 (base32
6588 "120qvhb0pvkzd65lsgja62vyrgc37si6fh68q4cg4w5x9f04jw25"))))
6589 (properties
6590 `((upstream-name . "GenomeInfoDbData")))
6591 (build-system r-build-system)
6592 (home-page "http://bioconductor.org/packages/GenomeInfoDbData")
6593 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6594 (description "This package contains data for mapping between NCBI taxonomy
6595 ID and species. It is used by functions in the GenomeInfoDb package.")
6596 (license license:artistic2.0)))
6597
6598 (define-public r-genomeinfodb
6599 (package
6600 (name "r-genomeinfodb")
6601 (version "1.12.0")
6602 (source (origin
6603 (method url-fetch)
6604 (uri (bioconductor-uri "GenomeInfoDb" version))
6605 (sha256
6606 (base32
6607 "1bwwhscjl376a5p43mx8ijrqajxmgypbqhv049pgagl22hkkf0y3"))))
6608 (properties
6609 `((upstream-name . "GenomeInfoDb")))
6610 (build-system r-build-system)
6611 (propagated-inputs
6612 `(("r-biocgenerics" ,r-biocgenerics)
6613 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6614 ("r-iranges" ,r-iranges)
6615 ("r-rcurl" ,r-rcurl)
6616 ("r-s4vectors" ,r-s4vectors)))
6617 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6618 (synopsis "Utilities for manipulating chromosome identifiers")
6619 (description
6620 "This package contains data and functions that define and allow
6621 translation between different chromosome sequence naming conventions (e.g.,
6622 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6623 names in their natural, rather than lexicographic, order.")
6624 (license license:artistic2.0)))
6625
6626 (define-public r-edger
6627 (package
6628 (name "r-edger")
6629 (version "3.18.0")
6630 (source (origin
6631 (method url-fetch)
6632 (uri (bioconductor-uri "edgeR" version))
6633 (sha256
6634 (base32
6635 "02l17i6xh33dv10swwvyfxrmv5kp23iv278iwvkfq2mnipasfnb9"))))
6636 (properties `((upstream-name . "edgeR")))
6637 (build-system r-build-system)
6638 (propagated-inputs
6639 `(("r-limma" ,r-limma)
6640 ("r-locfit" ,r-locfit)
6641 ("r-statmod" ,r-statmod))) ;for estimateDisp
6642 (home-page "http://bioinf.wehi.edu.au/edgeR")
6643 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6644 (description "This package can do differential expression analysis of
6645 RNA-seq expression profiles with biological replication. It implements a range
6646 of statistical methodology based on the negative binomial distributions,
6647 including empirical Bayes estimation, exact tests, generalized linear models
6648 and quasi-likelihood tests. It be applied to differential signal analysis of
6649 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6650 CAGE.")
6651 (license license:gpl2+)))
6652
6653 (define-public r-variantannotation
6654 (package
6655 (name "r-variantannotation")
6656 (version "1.22.0")
6657 (source (origin
6658 (method url-fetch)
6659 (uri (bioconductor-uri "VariantAnnotation" version))
6660 (sha256
6661 (base32
6662 "05hpm4as36kvpiqhgnkfjwfx0a05p304c21ggba29iac4nanm8b3"))))
6663 (properties
6664 `((upstream-name . "VariantAnnotation")))
6665 (inputs
6666 `(("zlib" ,zlib)))
6667 (propagated-inputs
6668 `(("r-annotationdbi" ,r-annotationdbi)
6669 ("r-biobase" ,r-biobase)
6670 ("r-biocgenerics" ,r-biocgenerics)
6671 ("r-biostrings" ,r-biostrings)
6672 ("r-bsgenome" ,r-bsgenome)
6673 ("r-dbi" ,r-dbi)
6674 ("r-genomeinfodb" ,r-genomeinfodb)
6675 ("r-genomicfeatures" ,r-genomicfeatures)
6676 ("r-genomicranges" ,r-genomicranges)
6677 ("r-iranges" ,r-iranges)
6678 ("r-summarizedexperiment" ,r-summarizedexperiment)
6679 ("r-rsamtools" ,r-rsamtools)
6680 ("r-rtracklayer" ,r-rtracklayer)
6681 ("r-s4vectors" ,r-s4vectors)
6682 ("r-xvector" ,r-xvector)
6683 ("r-zlibbioc" ,r-zlibbioc)))
6684 (build-system r-build-system)
6685 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6686 (synopsis "Package for annotation of genetic variants")
6687 (description "This R package can annotate variants, compute amino acid
6688 coding changes and predict coding outcomes.")
6689 (license license:artistic2.0)))
6690
6691 (define-public r-limma
6692 (package
6693 (name "r-limma")
6694 (version "3.32.0")
6695 (source (origin
6696 (method url-fetch)
6697 (uri (bioconductor-uri "limma" version))
6698 (sha256
6699 (base32
6700 "0q7rqm86nwq0rg4fjggfr7xqybjrxj425vni3cva70b4c8d1h425"))))
6701 (build-system r-build-system)
6702 (home-page "http://bioinf.wehi.edu.au/limma")
6703 (synopsis "Package for linear models for microarray and RNA-seq data")
6704 (description "This package can be used for the analysis of gene expression
6705 studies, especially the use of linear models for analysing designed experiments
6706 and the assessment of differential expression. The analysis methods apply to
6707 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6708 (license license:gpl2+)))
6709
6710 (define-public r-xvector
6711 (package
6712 (name "r-xvector")
6713 (version "0.16.0")
6714 (source (origin
6715 (method url-fetch)
6716 (uri (bioconductor-uri "XVector" version))
6717 (sha256
6718 (base32
6719 "01n09f4jdm60684lzikp02zf9gjan8bdrjx740vggr21q9fa69wn"))))
6720 (properties
6721 `((upstream-name . "XVector")))
6722 (build-system r-build-system)
6723 (arguments
6724 `(#:phases
6725 (modify-phases %standard-phases
6726 (add-after 'unpack 'use-system-zlib
6727 (lambda _
6728 (substitute* "DESCRIPTION"
6729 (("zlibbioc, ") ""))
6730 (substitute* "NAMESPACE"
6731 (("import\\(zlibbioc\\)") ""))
6732 #t)))))
6733 (inputs
6734 `(("zlib" ,zlib)))
6735 (propagated-inputs
6736 `(("r-biocgenerics" ,r-biocgenerics)
6737 ("r-iranges" ,r-iranges)
6738 ("r-s4vectors" ,r-s4vectors)))
6739 (home-page "http://bioconductor.org/packages/XVector")
6740 (synopsis "Representation and manpulation of external sequences")
6741 (description
6742 "This package provides memory efficient S4 classes for storing sequences
6743 \"externally\" (behind an R external pointer, or on disk).")
6744 (license license:artistic2.0)))
6745
6746 (define-public r-genomicranges
6747 (package
6748 (name "r-genomicranges")
6749 (version "1.28.0")
6750 (source (origin
6751 (method url-fetch)
6752 (uri (bioconductor-uri "GenomicRanges" version))
6753 (sha256
6754 (base32
6755 "10x9zx0b7j05d1j6p0xs4q4f4wzbhf3rq64wzi9cgv7f44q43a5n"))))
6756 (properties
6757 `((upstream-name . "GenomicRanges")))
6758 (build-system r-build-system)
6759 (propagated-inputs
6760 `(("r-biocgenerics" ,r-biocgenerics)
6761 ("r-genomeinfodb" ,r-genomeinfodb)
6762 ("r-iranges" ,r-iranges)
6763 ("r-s4vectors" ,r-s4vectors)
6764 ("r-xvector" ,r-xvector)))
6765 (home-page "http://bioconductor.org/packages/GenomicRanges")
6766 (synopsis "Representation and manipulation of genomic intervals")
6767 (description
6768 "This package provides tools to efficiently represent and manipulate
6769 genomic annotations and alignments is playing a central role when it comes to
6770 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6771 GenomicRanges package defines general purpose containers for storing and
6772 manipulating genomic intervals and variables defined along a genome.")
6773 (license license:artistic2.0)))
6774
6775 (define-public r-biobase
6776 (package
6777 (name "r-biobase")
6778 (version "2.36.0")
6779 (source (origin
6780 (method url-fetch)
6781 (uri (bioconductor-uri "Biobase" version))
6782 (sha256
6783 (base32
6784 "0x7pf5xsdcj12dbf5qqki2c6bd5madqg2fbiq5xgisarpc9v6c1m"))))
6785 (properties
6786 `((upstream-name . "Biobase")))
6787 (build-system r-build-system)
6788 (propagated-inputs
6789 `(("r-biocgenerics" ,r-biocgenerics)))
6790 (home-page "http://bioconductor.org/packages/Biobase")
6791 (synopsis "Base functions for Bioconductor")
6792 (description
6793 "This package provides functions that are needed by many other packages
6794 on Bioconductor or which replace R functions.")
6795 (license license:artistic2.0)))
6796
6797 (define-public r-annotationdbi
6798 (package
6799 (name "r-annotationdbi")
6800 (version "1.38.0")
6801 (source (origin
6802 (method url-fetch)
6803 (uri (bioconductor-uri "AnnotationDbi" version))
6804 (sha256
6805 (base32
6806 "1xffm98s817mfc827cnr0by6167nlrl1glxzjawzz0rkghs41g27"))))
6807 (properties
6808 `((upstream-name . "AnnotationDbi")))
6809 (build-system r-build-system)
6810 (propagated-inputs
6811 `(("r-biobase" ,r-biobase)
6812 ("r-biocgenerics" ,r-biocgenerics)
6813 ("r-dbi" ,r-dbi)
6814 ("r-iranges" ,r-iranges)
6815 ("r-rsqlite" ,r-rsqlite)
6816 ("r-s4vectors" ,r-s4vectors)))
6817 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6818 (synopsis "Annotation database interface")
6819 (description
6820 "This package provides user interface and database connection code for
6821 annotation data packages using SQLite data storage.")
6822 (license license:artistic2.0)))
6823
6824 (define-public r-biomart
6825 (package
6826 (name "r-biomart")
6827 (version "2.32.0")
6828 (source (origin
6829 (method url-fetch)
6830 (uri (bioconductor-uri "biomaRt" version))
6831 (sha256
6832 (base32
6833 "0knkxh23vl9pa0by03xr6dy9aiah714cmf54jl828k51l9wv5l2j"))))
6834 (properties
6835 `((upstream-name . "biomaRt")))
6836 (build-system r-build-system)
6837 (propagated-inputs
6838 `(("r-annotationdbi" ,r-annotationdbi)
6839 ("r-rcurl" ,r-rcurl)
6840 ("r-xml" ,r-xml)))
6841 (home-page "http://bioconductor.org/packages/biomaRt")
6842 (synopsis "Interface to BioMart databases")
6843 (description
6844 "biomaRt provides an interface to a growing collection of databases
6845 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6846 package enables retrieval of large amounts of data in a uniform way without
6847 the need to know the underlying database schemas or write complex SQL queries.
6848 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6849 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6850 users direct access to a diverse set of data and enable a wide range of
6851 powerful online queries from gene annotation to database mining.")
6852 (license license:artistic2.0)))
6853
6854 (define-public r-biocparallel
6855 (package
6856 (name "r-biocparallel")
6857 (version "1.10.0")
6858 (source (origin
6859 (method url-fetch)
6860 (uri (bioconductor-uri "BiocParallel" version))
6861 (sha256
6862 (base32
6863 "01ph0kq70b5gkd7n6a4myjlvwzgc0hi4xfwz8h17h06n9p5sdwa9"))))
6864 (properties
6865 `((upstream-name . "BiocParallel")))
6866 (build-system r-build-system)
6867 (propagated-inputs
6868 `(("r-futile-logger" ,r-futile-logger)
6869 ("r-snow" ,r-snow)))
6870 (home-page "http://bioconductor.org/packages/BiocParallel")
6871 (synopsis "Bioconductor facilities for parallel evaluation")
6872 (description
6873 "This package provides modified versions and novel implementation of
6874 functions for parallel evaluation, tailored to use with Bioconductor
6875 objects.")
6876 (license (list license:gpl2+ license:gpl3+))))
6877
6878 (define-public r-biostrings
6879 (package
6880 (name "r-biostrings")
6881 (version "2.44.0")
6882 (source (origin
6883 (method url-fetch)
6884 (uri (bioconductor-uri "Biostrings" version))
6885 (sha256
6886 (base32
6887 "0ixgx12cx2z4n2khxq83crz9gc21qckj2v78y2p31567kfsw7clg"))))
6888 (properties
6889 `((upstream-name . "Biostrings")))
6890 (build-system r-build-system)
6891 (propagated-inputs
6892 `(("r-biocgenerics" ,r-biocgenerics)
6893 ("r-iranges" ,r-iranges)
6894 ("r-s4vectors" ,r-s4vectors)
6895 ("r-xvector" ,r-xvector)))
6896 (home-page "http://bioconductor.org/packages/Biostrings")
6897 (synopsis "String objects and algorithms for biological sequences")
6898 (description
6899 "This package provides memory efficient string containers, string
6900 matching algorithms, and other utilities, for fast manipulation of large
6901 biological sequences or sets of sequences.")
6902 (license license:artistic2.0)))
6903
6904 (define-public r-rsamtools
6905 (package
6906 (name "r-rsamtools")
6907 (version "1.28.0")
6908 (source (origin
6909 (method url-fetch)
6910 (uri (bioconductor-uri "Rsamtools" version))
6911 (sha256
6912 (base32
6913 "1zx6vhdz3lksbfy98jj3qzl7cxgspigm2pbsd5835b12r6mc5w6d"))))
6914 (properties
6915 `((upstream-name . "Rsamtools")))
6916 (build-system r-build-system)
6917 (arguments
6918 `(#:phases
6919 (modify-phases %standard-phases
6920 (add-after 'unpack 'use-system-zlib
6921 (lambda _
6922 (substitute* "DESCRIPTION"
6923 (("zlibbioc, ") ""))
6924 (substitute* "NAMESPACE"
6925 (("import\\(zlibbioc\\)") ""))
6926 #t)))))
6927 (inputs
6928 `(("zlib" ,zlib)))
6929 (propagated-inputs
6930 `(("r-biocgenerics" ,r-biocgenerics)
6931 ("r-biocparallel" ,r-biocparallel)
6932 ("r-biostrings" ,r-biostrings)
6933 ("r-bitops" ,r-bitops)
6934 ("r-genomeinfodb" ,r-genomeinfodb)
6935 ("r-genomicranges" ,r-genomicranges)
6936 ("r-iranges" ,r-iranges)
6937 ("r-s4vectors" ,r-s4vectors)
6938 ("r-xvector" ,r-xvector)))
6939 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6940 (synopsis "Interface to samtools, bcftools, and tabix")
6941 (description
6942 "This package provides an interface to the 'samtools', 'bcftools', and
6943 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6944 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6945 files.")
6946 (license license:expat)))
6947
6948 (define-public r-delayedarray
6949 (package
6950 (name "r-delayedarray")
6951 (version "0.2.0")
6952 (source (origin
6953 (method url-fetch)
6954 (uri (bioconductor-uri "DelayedArray" version))
6955 (sha256
6956 (base32
6957 "0pcsk0f2dg2ldzprs1cccqrk53jrysmm6ccgjj5wh6z3x17g7g2r"))))
6958 (properties
6959 `((upstream-name . "DelayedArray")))
6960 (build-system r-build-system)
6961 (propagated-inputs
6962 `(("r-biocgenerics" ,r-biocgenerics)
6963 ("r-s4vectors" ,r-s4vectors)
6964 ("r-iranges" ,r-iranges)
6965 ("r-matrixstats" ,r-matrixstats)))
6966 (home-page "http://bioconductor.org/packages/DelayedArray")
6967 (synopsis "Delayed operations on array-like objects")
6968 (description
6969 "Wrapping an array-like object (typically an on-disk object) in a
6970 @code{DelayedArray} object allows one to perform common array operations on it
6971 without loading the object in memory. In order to reduce memory usage and
6972 optimize performance, operations on the object are either delayed or executed
6973 using a block processing mechanism. Note that this also works on in-memory
6974 array-like objects like @code{DataFrame} objects (typically with Rle columns),
6975 @code{Matrix} objects, and ordinary arrays and data frames.")
6976 (license license:artistic2.0)))
6977
6978 (define-public r-summarizedexperiment
6979 (package
6980 (name "r-summarizedexperiment")
6981 (version "1.6.0")
6982 (source (origin
6983 (method url-fetch)
6984 (uri (bioconductor-uri "SummarizedExperiment" version))
6985 (sha256
6986 (base32
6987 "1szjbzzz4pyip891nji71caalxh0rhqiv7rpv6q54swlrqpfkqkw"))))
6988 (properties
6989 `((upstream-name . "SummarizedExperiment")))
6990 (build-system r-build-system)
6991 (propagated-inputs
6992 `(("r-biobase" ,r-biobase)
6993 ("r-biocgenerics" ,r-biocgenerics)
6994 ("r-delayedarray" ,r-delayedarray)
6995 ("r-genomeinfodb" ,r-genomeinfodb)
6996 ("r-genomicranges" ,r-genomicranges)
6997 ("r-iranges" ,r-iranges)
6998 ("r-matrix" ,r-matrix)
6999 ("r-s4vectors" ,r-s4vectors)))
7000 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
7001 (synopsis "Container for representing genomic ranges by sample")
7002 (description
7003 "The SummarizedExperiment container contains one or more assays, each
7004 represented by a matrix-like object of numeric or other mode. The rows
7005 typically represent genomic ranges of interest and the columns represent
7006 samples.")
7007 (license license:artistic2.0)))
7008
7009 (define-public r-genomicalignments
7010 (package
7011 (name "r-genomicalignments")
7012 (version "1.12.0")
7013 (source (origin
7014 (method url-fetch)
7015 (uri (bioconductor-uri "GenomicAlignments" version))
7016 (sha256
7017 (base32
7018 "1aagyrdk5309a7awg42lg0bpirp91i6i2ddvpmrs38pzriwahnjy"))))
7019 (properties
7020 `((upstream-name . "GenomicAlignments")))
7021 (build-system r-build-system)
7022 (propagated-inputs
7023 `(("r-biocgenerics" ,r-biocgenerics)
7024 ("r-biocparallel" ,r-biocparallel)
7025 ("r-biostrings" ,r-biostrings)
7026 ("r-genomeinfodb" ,r-genomeinfodb)
7027 ("r-genomicranges" ,r-genomicranges)
7028 ("r-iranges" ,r-iranges)
7029 ("r-rsamtools" ,r-rsamtools)
7030 ("r-s4vectors" ,r-s4vectors)
7031 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7032 (home-page "http://bioconductor.org/packages/GenomicAlignments")
7033 (synopsis "Representation and manipulation of short genomic alignments")
7034 (description
7035 "This package provides efficient containers for storing and manipulating
7036 short genomic alignments (typically obtained by aligning short reads to a
7037 reference genome). This includes read counting, computing the coverage,
7038 junction detection, and working with the nucleotide content of the
7039 alignments.")
7040 (license license:artistic2.0)))
7041
7042 (define-public r-rtracklayer
7043 (package
7044 (name "r-rtracklayer")
7045 (version "1.36.0")
7046 (source (origin
7047 (method url-fetch)
7048 (uri (bioconductor-uri "rtracklayer" version))
7049 (sha256
7050 (base32
7051 "0dv7p3wzmx57inznf6fb06417zcm48g7fpazyahxny7bqgzwq0ig"))))
7052 (build-system r-build-system)
7053 (arguments
7054 `(#:phases
7055 (modify-phases %standard-phases
7056 (add-after 'unpack 'use-system-zlib
7057 (lambda _
7058 (substitute* "DESCRIPTION"
7059 (("zlibbioc, ") ""))
7060 (substitute* "NAMESPACE"
7061 (("import\\(zlibbioc\\)") ""))
7062 #t)))))
7063 (inputs
7064 `(("zlib" ,zlib)))
7065 (propagated-inputs
7066 `(("r-biocgenerics" ,r-biocgenerics)
7067 ("r-biostrings" ,r-biostrings)
7068 ("r-genomeinfodb" ,r-genomeinfodb)
7069 ("r-genomicalignments" ,r-genomicalignments)
7070 ("r-genomicranges" ,r-genomicranges)
7071 ("r-iranges" ,r-iranges)
7072 ("r-rcurl" ,r-rcurl)
7073 ("r-rsamtools" ,r-rsamtools)
7074 ("r-s4vectors" ,r-s4vectors)
7075 ("r-xml" ,r-xml)
7076 ("r-xvector" ,r-xvector)))
7077 (home-page "http://bioconductor.org/packages/rtracklayer")
7078 (synopsis "R interface to genome browsers and their annotation tracks")
7079 (description
7080 "rtracklayer is an extensible framework for interacting with multiple
7081 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7082 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7083 built-in). The user may export/import tracks to/from the supported browsers,
7084 as well as query and modify the browser state, such as the current viewport.")
7085 (license license:artistic2.0)))
7086
7087 (define-public r-genomicfeatures
7088 (package
7089 (name "r-genomicfeatures")
7090 (version "1.28.0")
7091 (source (origin
7092 (method url-fetch)
7093 (uri (bioconductor-uri "GenomicFeatures" version))
7094 (sha256
7095 (base32
7096 "1pjxlr34ygv8pvfwpyq268wpgqzphiwpij85fyhjqdwdp0a253ik"))))
7097 (properties
7098 `((upstream-name . "GenomicFeatures")))
7099 (build-system r-build-system)
7100 (propagated-inputs
7101 `(("r-annotationdbi" ,r-annotationdbi)
7102 ("r-biobase" ,r-biobase)
7103 ("r-biocgenerics" ,r-biocgenerics)
7104 ("r-biomart" ,r-biomart)
7105 ("r-biostrings" ,r-biostrings)
7106 ("r-dbi" ,r-dbi)
7107 ("r-genomeinfodb" ,r-genomeinfodb)
7108 ("r-genomicranges" ,r-genomicranges)
7109 ("r-iranges" ,r-iranges)
7110 ("r-rcurl" ,r-rcurl)
7111 ("r-rsqlite" ,r-rsqlite)
7112 ("r-rtracklayer" ,r-rtracklayer)
7113 ("r-s4vectors" ,r-s4vectors)
7114 ("r-xvector" ,r-xvector)))
7115 (home-page "http://bioconductor.org/packages/GenomicFeatures")
7116 (synopsis "Tools for working with transcript centric annotations")
7117 (description
7118 "This package provides a set of tools and methods for making and
7119 manipulating transcript centric annotations. With these tools the user can
7120 easily download the genomic locations of the transcripts, exons and cds of a
7121 given organism, from either the UCSC Genome Browser or a BioMart
7122 database (more sources will be supported in the future). This information is
7123 then stored in a local database that keeps track of the relationship between
7124 transcripts, exons, cds and genes. Flexible methods are provided for
7125 extracting the desired features in a convenient format.")
7126 (license license:artistic2.0)))
7127
7128 (define-public r-go-db
7129 (package
7130 (name "r-go-db")
7131 (version "3.4.0")
7132 (source (origin
7133 (method url-fetch)
7134 (uri (string-append "http://www.bioconductor.org/packages/"
7135 "release/data/annotation/src/contrib/GO.db_"
7136 version ".tar.gz"))
7137 (sha256
7138 (base32
7139 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
7140 (properties
7141 `((upstream-name . "GO.db")))
7142 (build-system r-build-system)
7143 (propagated-inputs
7144 `(("r-annotationdbi" ,r-annotationdbi)))
7145 (home-page "http://bioconductor.org/packages/GO.db")
7146 (synopsis "Annotation maps describing the entire Gene Ontology")
7147 (description
7148 "The purpose of this GO.db annotation package is to provide detailed
7149 information about the latest version of the Gene Ontologies.")
7150 (license license:artistic2.0)))
7151
7152 (define-public r-graph
7153 (package
7154 (name "r-graph")
7155 (version "1.54.0")
7156 (source (origin
7157 (method url-fetch)
7158 (uri (bioconductor-uri "graph" version))
7159 (sha256
7160 (base32
7161 "0hx9wslnrci7c5i1gd1zlpjmgrkdnx9gabfgmzzwfnykk1mdvvna"))))
7162 (build-system r-build-system)
7163 (propagated-inputs
7164 `(("r-biocgenerics" ,r-biocgenerics)))
7165 (home-page "http://bioconductor.org/packages/graph")
7166 (synopsis "Handle graph data structures in R")
7167 (description
7168 "This package implements some simple graph handling capabilities for R.")
7169 (license license:artistic2.0)))
7170
7171 (define-public r-topgo
7172 (package
7173 (name "r-topgo")
7174 (version "2.28.0")
7175 (source (origin
7176 (method url-fetch)
7177 (uri (bioconductor-uri "topGO" version))
7178 (sha256
7179 (base32
7180 "04kvxz9qsxfz0np7wlrzp4r95nykz94x7mqpyyk76f90g6m66vcc"))))
7181 (properties
7182 `((upstream-name . "topGO")))
7183 (build-system r-build-system)
7184 (propagated-inputs
7185 `(("r-annotationdbi" ,r-annotationdbi)
7186 ("r-dbi" ,r-dbi)
7187 ("r-biobase" ,r-biobase)
7188 ("r-biocgenerics" ,r-biocgenerics)
7189 ("r-go-db" ,r-go-db)
7190 ("r-graph" ,r-graph)
7191 ("r-lattice" ,r-lattice)
7192 ("r-matrixstats" ,r-matrixstats)
7193 ("r-sparsem" ,r-sparsem)))
7194 (home-page "http://bioconductor.org/packages/topGO")
7195 (synopsis "Enrichment analysis for gene ontology")
7196 (description
7197 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7198 terms while accounting for the topology of the GO graph. Different test
7199 statistics and different methods for eliminating local similarities and
7200 dependencies between GO terms can be implemented and applied.")
7201 ;; Any version of the LGPL applies.
7202 (license license:lgpl2.1+)))
7203
7204 (define-public r-bsgenome
7205 (package
7206 (name "r-bsgenome")
7207 (version "1.44.0")
7208 (source (origin
7209 (method url-fetch)
7210 (uri (bioconductor-uri "BSgenome" version))
7211 (sha256
7212 (base32
7213 "18dlknwk3xvi52hamxf9pl5bjc5806mpw98xwvx5xajn8mrxiy5h"))))
7214 (properties
7215 `((upstream-name . "BSgenome")))
7216 (build-system r-build-system)
7217 (propagated-inputs
7218 `(("r-biocgenerics" ,r-biocgenerics)
7219 ("r-biostrings" ,r-biostrings)
7220 ("r-genomeinfodb" ,r-genomeinfodb)
7221 ("r-genomicranges" ,r-genomicranges)
7222 ("r-iranges" ,r-iranges)
7223 ("r-rsamtools" ,r-rsamtools)
7224 ("r-rtracklayer" ,r-rtracklayer)
7225 ("r-s4vectors" ,r-s4vectors)
7226 ("r-xvector" ,r-xvector)))
7227 (home-page "http://bioconductor.org/packages/BSgenome")
7228 (synopsis "Infrastructure for Biostrings-based genome data packages")
7229 (description
7230 "This package provides infrastructure shared by all Biostrings-based
7231 genome data packages and support for efficient SNP representation.")
7232 (license license:artistic2.0)))
7233
7234 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7235 (package
7236 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7237 (version "0.99.1")
7238 (source (origin
7239 (method url-fetch)
7240 ;; We cannot use bioconductor-uri here because this tarball is
7241 ;; located under "data/annotation/" instead of "bioc/".
7242 (uri (string-append "http://www.bioconductor.org/packages/"
7243 "release/data/annotation/src/contrib/"
7244 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7245 version ".tar.gz"))
7246 (sha256
7247 (base32
7248 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7249 (properties
7250 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7251 (build-system r-build-system)
7252 ;; As this package provides little more than a very large data file it
7253 ;; doesn't make sense to build substitutes.
7254 (arguments `(#:substitutable? #f))
7255 (propagated-inputs
7256 `(("r-bsgenome" ,r-bsgenome)))
7257 (home-page
7258 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7259 (synopsis "Full genome sequences for Homo sapiens")
7260 (description
7261 "This package provides full genome sequences for Homo sapiens from
7262 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7263 (license license:artistic2.0)))
7264
7265 (define-public r-impute
7266 (package
7267 (name "r-impute")
7268 (version "1.50.0")
7269 (source (origin
7270 (method url-fetch)
7271 (uri (bioconductor-uri "impute" version))
7272 (sha256
7273 (base32
7274 "0va45vfixy3np549md87h3b3rbavm54gfnmnjhpr9hf02lll6zxs"))))
7275 (inputs
7276 `(("gfortran" ,gfortran)))
7277 (build-system r-build-system)
7278 (home-page "http://bioconductor.org/packages/impute")
7279 (synopsis "Imputation for microarray data")
7280 (description
7281 "This package provides a function to impute missing gene expression
7282 microarray data, using nearest neighbor averaging.")
7283 (license license:gpl2+)))
7284
7285 (define-public r-seqpattern
7286 (package
7287 (name "r-seqpattern")
7288 (version "1.8.0")
7289 (source (origin
7290 (method url-fetch)
7291 (uri (bioconductor-uri "seqPattern" version))
7292 (sha256
7293 (base32
7294 "0yw5251sirv3283xgmfmfbf900xp8dwvqfk88mr945s3by5hx99v"))))
7295 (properties
7296 `((upstream-name . "seqPattern")))
7297 (build-system r-build-system)
7298 (propagated-inputs
7299 `(("r-biostrings" ,r-biostrings)
7300 ("r-genomicranges" ,r-genomicranges)
7301 ("r-iranges" ,r-iranges)
7302 ("r-kernsmooth" ,r-kernsmooth)
7303 ("r-plotrix" ,r-plotrix)))
7304 (home-page "http://bioconductor.org/packages/seqPattern")
7305 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7306 (description
7307 "This package provides tools to visualize oligonucleotide patterns and
7308 sequence motif occurrences across a large set of sequences centred at a common
7309 reference point and sorted by a user defined feature.")
7310 (license license:gpl3+)))
7311
7312 (define-public r-genomation
7313 (package
7314 (name "r-genomation")
7315 (version "1.8.0")
7316 (source (origin
7317 (method url-fetch)
7318 (uri (bioconductor-uri "genomation" version))
7319 (sha256
7320 (base32
7321 "0r71nf8p3aq3yffqxg4yir1zmm7rar5a57nmy1kpqpn8kaf2svjl"))))
7322 (build-system r-build-system)
7323 (propagated-inputs
7324 `(("r-biostrings" ,r-biostrings)
7325 ("r-bsgenome" ,r-bsgenome)
7326 ("r-data-table" ,r-data-table)
7327 ("r-genomeinfodb" ,r-genomeinfodb)
7328 ("r-genomicalignments" ,r-genomicalignments)
7329 ("r-genomicranges" ,r-genomicranges)
7330 ("r-ggplot2" ,r-ggplot2)
7331 ("r-gridbase" ,r-gridbase)
7332 ("r-impute" ,r-impute)
7333 ("r-iranges" ,r-iranges)
7334 ("r-matrixstats" ,r-matrixstats)
7335 ("r-plotrix" ,r-plotrix)
7336 ("r-plyr" ,r-plyr)
7337 ("r-rcpp" ,r-rcpp)
7338 ("r-readr" ,r-readr)
7339 ("r-reshape2" ,r-reshape2)
7340 ("r-rhtslib" ,r-rhtslib)
7341 ("r-rsamtools" ,r-rsamtools)
7342 ("r-rtracklayer" ,r-rtracklayer)
7343 ("r-runit" ,r-runit)
7344 ("r-s4vectors" ,r-s4vectors)
7345 ("r-seqpattern" ,r-seqpattern)))
7346 (inputs
7347 `(("zlib" ,zlib)))
7348 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7349 (synopsis "Summary, annotation and visualization of genomic data")
7350 (description
7351 "This package provides a package for summary and annotation of genomic
7352 intervals. Users can visualize and quantify genomic intervals over
7353 pre-defined functional regions, such as promoters, exons, introns, etc. The
7354 genomic intervals represent regions with a defined chromosome position, which
7355 may be associated with a score, such as aligned reads from HT-seq experiments,
7356 TF binding sites, methylation scores, etc. The package can use any tabular
7357 genomic feature data as long as it has minimal information on the locations of
7358 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7359 (license license:artistic2.0)))
7360
7361 (define-public r-genomationdata
7362 (package
7363 (name "r-genomationdata")
7364 (version "1.6.0")
7365 (source (origin
7366 (method url-fetch)
7367 ;; We cannot use bioconductor-uri here because this tarball is
7368 ;; located under "data/annotation/" instead of "bioc/".
7369 (uri (string-append "https://bioconductor.org/packages/"
7370 "release/data/experiment/src/contrib/"
7371 "genomationData_" version ".tar.gz"))
7372 (sha256
7373 (base32
7374 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7375 (build-system r-build-system)
7376 ;; As this package provides little more than large data files, it doesn't
7377 ;; make sense to build substitutes.
7378 (arguments `(#:substitutable? #f))
7379 (native-inputs
7380 `(("r-knitr" ,r-knitr)))
7381 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7382 (synopsis "Experimental data for use with the genomation package")
7383 (description
7384 "This package contains experimental genetic data for use with the
7385 genomation package. Included are Chip Seq, Methylation and Cage data,
7386 downloaded from Encode.")
7387 (license license:gpl3+)))
7388
7389 (define-public r-org-hs-eg-db
7390 (package
7391 (name "r-org-hs-eg-db")
7392 (version "3.4.0")
7393 (source (origin
7394 (method url-fetch)
7395 ;; We cannot use bioconductor-uri here because this tarball is
7396 ;; located under "data/annotation/" instead of "bioc/".
7397 (uri (string-append "http://www.bioconductor.org/packages/"
7398 "release/data/annotation/src/contrib/"
7399 "org.Hs.eg.db_" version ".tar.gz"))
7400 (sha256
7401 (base32
7402 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7403 (properties
7404 `((upstream-name . "org.Hs.eg.db")))
7405 (build-system r-build-system)
7406 (propagated-inputs
7407 `(("r-annotationdbi" ,r-annotationdbi)))
7408 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
7409 (synopsis "Genome wide annotation for Human")
7410 (description
7411 "This package provides mappings from Entrez gene identifiers to various
7412 annotations for the human genome.")
7413 (license license:artistic2.0)))
7414
7415 (define-public r-org-ce-eg-db
7416 (package
7417 (name "r-org-ce-eg-db")
7418 (version "3.4.0")
7419 (source (origin
7420 (method url-fetch)
7421 ;; We cannot use bioconductor-uri here because this tarball is
7422 ;; located under "data/annotation/" instead of "bioc/".
7423 (uri (string-append "http://www.bioconductor.org/packages/"
7424 "release/data/annotation/src/contrib/"
7425 "org.Ce.eg.db_" version ".tar.gz"))
7426 (sha256
7427 (base32
7428 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7429 (properties
7430 `((upstream-name . "org.Ce.eg.db")))
7431 (build-system r-build-system)
7432 (propagated-inputs
7433 `(("r-annotationdbi" ,r-annotationdbi)))
7434 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
7435 (synopsis "Genome wide annotation for Worm")
7436 (description
7437 "This package provides mappings from Entrez gene identifiers to various
7438 annotations for the genome of the model worm Caenorhabditis elegans.")
7439 (license license:artistic2.0)))
7440
7441 (define-public r-org-dm-eg-db
7442 (package
7443 (name "r-org-dm-eg-db")
7444 (version "3.4.0")
7445 (source (origin
7446 (method url-fetch)
7447 ;; We cannot use bioconductor-uri here because this tarball is
7448 ;; located under "data/annotation/" instead of "bioc/".
7449 (uri (string-append "http://www.bioconductor.org/packages/"
7450 "release/data/annotation/src/contrib/"
7451 "org.Dm.eg.db_" version ".tar.gz"))
7452 (sha256
7453 (base32
7454 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7455 (properties
7456 `((upstream-name . "org.Dm.eg.db")))
7457 (build-system r-build-system)
7458 (propagated-inputs
7459 `(("r-annotationdbi" ,r-annotationdbi)))
7460 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
7461 (synopsis "Genome wide annotation for Fly")
7462 (description
7463 "This package provides mappings from Entrez gene identifiers to various
7464 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7465 (license license:artistic2.0)))
7466
7467 (define-public r-org-mm-eg-db
7468 (package
7469 (name "r-org-mm-eg-db")
7470 (version "3.4.0")
7471 (source (origin
7472 (method url-fetch)
7473 ;; We cannot use bioconductor-uri here because this tarball is
7474 ;; located under "data/annotation/" instead of "bioc/".
7475 (uri (string-append "http://www.bioconductor.org/packages/"
7476 "release/data/annotation/src/contrib/"
7477 "org.Mm.eg.db_" version ".tar.gz"))
7478 (sha256
7479 (base32
7480 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7481 (properties
7482 `((upstream-name . "org.Mm.eg.db")))
7483 (build-system r-build-system)
7484 (propagated-inputs
7485 `(("r-annotationdbi" ,r-annotationdbi)))
7486 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
7487 (synopsis "Genome wide annotation for Mouse")
7488 (description
7489 "This package provides mappings from Entrez gene identifiers to various
7490 annotations for the genome of the model mouse Mus musculus.")
7491 (license license:artistic2.0)))
7492
7493 (define-public r-seqlogo
7494 (package
7495 (name "r-seqlogo")
7496 (version "1.42.0")
7497 (source
7498 (origin
7499 (method url-fetch)
7500 (uri (bioconductor-uri "seqLogo" version))
7501 (sha256
7502 (base32
7503 "19d5zmy7m8svljwgbmrb4vxkq18slq0f3all6k2ayv42b8w44h6q"))))
7504 (properties `((upstream-name . "seqLogo")))
7505 (build-system r-build-system)
7506 (home-page "http://bioconductor.org/packages/seqLogo")
7507 (synopsis "Sequence logos for DNA sequence alignments")
7508 (description
7509 "seqLogo takes the position weight matrix of a DNA sequence motif and
7510 plots the corresponding sequence logo as introduced by Schneider and
7511 Stephens (1990).")
7512 (license license:lgpl2.0+)))
7513
7514 (define-public r-bsgenome-hsapiens-ucsc-hg19
7515 (package
7516 (name "r-bsgenome-hsapiens-ucsc-hg19")
7517 (version "1.4.0")
7518 (source (origin
7519 (method url-fetch)
7520 ;; We cannot use bioconductor-uri here because this tarball is
7521 ;; located under "data/annotation/" instead of "bioc/".
7522 (uri (string-append "http://www.bioconductor.org/packages/"
7523 "release/data/annotation/src/contrib/"
7524 "BSgenome.Hsapiens.UCSC.hg19_"
7525 version ".tar.gz"))
7526 (sha256
7527 (base32
7528 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7529 (properties
7530 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7531 (build-system r-build-system)
7532 ;; As this package provides little more than a very large data file it
7533 ;; doesn't make sense to build substitutes.
7534 (arguments `(#:substitutable? #f))
7535 (propagated-inputs
7536 `(("r-bsgenome" ,r-bsgenome)))
7537 (home-page
7538 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7539 (synopsis "Full genome sequences for Homo sapiens")
7540 (description
7541 "This package provides full genome sequences for Homo sapiens as provided
7542 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7543 (license license:artistic2.0)))
7544
7545 (define-public r-bsgenome-mmusculus-ucsc-mm9
7546 (package
7547 (name "r-bsgenome-mmusculus-ucsc-mm9")
7548 (version "1.4.0")
7549 (source (origin
7550 (method url-fetch)
7551 ;; We cannot use bioconductor-uri here because this tarball is
7552 ;; located under "data/annotation/" instead of "bioc/".
7553 (uri (string-append "http://www.bioconductor.org/packages/"
7554 "release/data/annotation/src/contrib/"
7555 "BSgenome.Mmusculus.UCSC.mm9_"
7556 version ".tar.gz"))
7557 (sha256
7558 (base32
7559 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7560 (properties
7561 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7562 (build-system r-build-system)
7563 ;; As this package provides little more than a very large data file it
7564 ;; doesn't make sense to build substitutes.
7565 (arguments `(#:substitutable? #f))
7566 (propagated-inputs
7567 `(("r-bsgenome" ,r-bsgenome)))
7568 (home-page
7569 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7570 (synopsis "Full genome sequences for Mouse")
7571 (description
7572 "This package provides full genome sequences for Mus musculus (Mouse) as
7573 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7574 (license license:artistic2.0)))
7575
7576 (define-public r-bsgenome-mmusculus-ucsc-mm10
7577 (package
7578 (name "r-bsgenome-mmusculus-ucsc-mm10")
7579 (version "1.4.0")
7580 (source (origin
7581 (method url-fetch)
7582 ;; We cannot use bioconductor-uri here because this tarball is
7583 ;; located under "data/annotation/" instead of "bioc/".
7584 (uri (string-append "http://www.bioconductor.org/packages/"
7585 "release/data/annotation/src/contrib/"
7586 "BSgenome.Mmusculus.UCSC.mm10_"
7587 version ".tar.gz"))
7588 (sha256
7589 (base32
7590 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7591 (properties
7592 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7593 (build-system r-build-system)
7594 ;; As this package provides little more than a very large data file it
7595 ;; doesn't make sense to build substitutes.
7596 (arguments `(#:substitutable? #f))
7597 (propagated-inputs
7598 `(("r-bsgenome" ,r-bsgenome)))
7599 (home-page
7600 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7601 (synopsis "Full genome sequences for Mouse")
7602 (description
7603 "This package provides full genome sequences for Mus
7604 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7605 in Biostrings objects.")
7606 (license license:artistic2.0)))
7607
7608 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7609 (package
7610 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7611 (version "3.4.0")
7612 (source (origin
7613 (method url-fetch)
7614 ;; We cannot use bioconductor-uri here because this tarball is
7615 ;; located under "data/annotation/" instead of "bioc/".
7616 (uri (string-append "http://www.bioconductor.org/packages/"
7617 "release/data/annotation/src/contrib/"
7618 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7619 version ".tar.gz"))
7620 (sha256
7621 (base32
7622 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7623 (properties
7624 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7625 (build-system r-build-system)
7626 ;; As this package provides little more than a very large data file it
7627 ;; doesn't make sense to build substitutes.
7628 (arguments `(#:substitutable? #f))
7629 (propagated-inputs
7630 `(("r-bsgenome" ,r-bsgenome)
7631 ("r-genomicfeatures" ,r-genomicfeatures)
7632 ("r-annotationdbi" ,r-annotationdbi)))
7633 (home-page
7634 "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7635 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7636 (description
7637 "This package loads a TxDb object, which is an R interface to
7638 prefabricated databases contained in this package. This package provides
7639 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7640 based on the knownGene track.")
7641 (license license:artistic2.0)))
7642
7643 (define-public r-bsgenome-celegans-ucsc-ce6
7644 (package
7645 (name "r-bsgenome-celegans-ucsc-ce6")
7646 (version "1.4.0")
7647 (source (origin
7648 (method url-fetch)
7649 ;; We cannot use bioconductor-uri here because this tarball is
7650 ;; located under "data/annotation/" instead of "bioc/".
7651 (uri (string-append "http://www.bioconductor.org/packages/"
7652 "release/data/annotation/src/contrib/"
7653 "BSgenome.Celegans.UCSC.ce6_"
7654 version ".tar.gz"))
7655 (sha256
7656 (base32
7657 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7658 (properties
7659 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7660 (build-system r-build-system)
7661 ;; As this package provides little more than a very large data file it
7662 ;; doesn't make sense to build substitutes.
7663 (arguments `(#:substitutable? #f))
7664 (propagated-inputs
7665 `(("r-bsgenome" ,r-bsgenome)))
7666 (home-page
7667 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7668 (synopsis "Full genome sequences for Worm")
7669 (description
7670 "This package provides full genome sequences for Caenorhabditis
7671 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7672 objects.")
7673 (license license:artistic2.0)))
7674
7675 (define-public r-bsgenome-celegans-ucsc-ce10
7676 (package
7677 (name "r-bsgenome-celegans-ucsc-ce10")
7678 (version "1.4.0")
7679 (source (origin
7680 (method url-fetch)
7681 ;; We cannot use bioconductor-uri here because this tarball is
7682 ;; located under "data/annotation/" instead of "bioc/".
7683 (uri (string-append "http://www.bioconductor.org/packages/"
7684 "release/data/annotation/src/contrib/"
7685 "BSgenome.Celegans.UCSC.ce10_"
7686 version ".tar.gz"))
7687 (sha256
7688 (base32
7689 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7690 (properties
7691 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7692 (build-system r-build-system)
7693 ;; As this package provides little more than a very large data file it
7694 ;; doesn't make sense to build substitutes.
7695 (arguments `(#:substitutable? #f))
7696 (propagated-inputs
7697 `(("r-bsgenome" ,r-bsgenome)))
7698 (home-page
7699 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7700 (synopsis "Full genome sequences for Worm")
7701 (description
7702 "This package provides full genome sequences for Caenorhabditis
7703 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7704 objects.")
7705 (license license:artistic2.0)))
7706
7707 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7708 (package
7709 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7710 (version "1.4.0")
7711 (source (origin
7712 (method url-fetch)
7713 ;; We cannot use bioconductor-uri here because this tarball is
7714 ;; located under "data/annotation/" instead of "bioc/".
7715 (uri (string-append "http://www.bioconductor.org/packages/"
7716 "release/data/annotation/src/contrib/"
7717 "BSgenome.Dmelanogaster.UCSC.dm3_"
7718 version ".tar.gz"))
7719 (sha256
7720 (base32
7721 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7722 (properties
7723 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7724 (build-system r-build-system)
7725 ;; As this package provides little more than a very large data file it
7726 ;; doesn't make sense to build substitutes.
7727 (arguments `(#:substitutable? #f))
7728 (propagated-inputs
7729 `(("r-bsgenome" ,r-bsgenome)))
7730 (home-page
7731 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7732 (synopsis "Full genome sequences for Fly")
7733 (description
7734 "This package provides full genome sequences for Drosophila
7735 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7736 Biostrings objects.")
7737 (license license:artistic2.0)))
7738
7739 (define-public r-motifrg
7740 (package
7741 (name "r-motifrg")
7742 (version "1.20.0")
7743 (source
7744 (origin
7745 (method url-fetch)
7746 (uri (bioconductor-uri "motifRG" version))
7747 (sha256
7748 (base32
7749 "0lxxpqyljiyk73vyq6ss46q13g81pm24q87mkzdsqlr5zx427ch6"))))
7750 (properties `((upstream-name . "motifRG")))
7751 (build-system r-build-system)
7752 (propagated-inputs
7753 `(("r-biostrings" ,r-biostrings)
7754 ("r-bsgenome" ,r-bsgenome)
7755 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7756 ("r-iranges" ,r-iranges)
7757 ("r-seqlogo" ,r-seqlogo)
7758 ("r-xvector" ,r-xvector)))
7759 (home-page "http://bioconductor.org/packages/motifRG")
7760 (synopsis "Discover motifs in high throughput sequencing data")
7761 (description
7762 "This package provides tools for discriminative motif discovery in high
7763 throughput genetic sequencing data sets using regression methods.")
7764 (license license:artistic2.0)))
7765
7766 (define-public r-qtl
7767 (package
7768 (name "r-qtl")
7769 (version "1.40-8")
7770 (source
7771 (origin
7772 (method url-fetch)
7773 (uri (string-append "mirror://cran/src/contrib/qtl_"
7774 version ".tar.gz"))
7775 (sha256
7776 (base32
7777 "05bj1x2ry0i7yqiydlswb3d2h4pxg70z8w1072az1mrv1m54k8sp"))))
7778 (build-system r-build-system)
7779 (home-page "http://rqtl.org/")
7780 (synopsis "R package for analyzing QTL experiments in genetics")
7781 (description "R/qtl is an extension library for the R statistics
7782 system. It is used to analyze experimental crosses for identifying
7783 genes contributing to variation in quantitative traits (so-called
7784 quantitative trait loci, QTLs).
7785
7786 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7787 identify genotyping errors, and to perform single-QTL and two-QTL,
7788 two-dimensional genome scans.")
7789 (license license:gpl3)))
7790
7791 (define-public r-zlibbioc
7792 (package
7793 (name "r-zlibbioc")
7794 (version "1.22.0")
7795 (source (origin
7796 (method url-fetch)
7797 (uri (bioconductor-uri "zlibbioc" version))
7798 (sha256
7799 (base32
7800 "1kdgwwlh39mgwzj3zq71za4iv40sq625ghnyrndv5wrivrcr2igv"))))
7801 (properties
7802 `((upstream-name . "zlibbioc")))
7803 (build-system r-build-system)
7804 (home-page "https://bioconductor.org/packages/zlibbioc")
7805 (synopsis "Provider for zlib-1.2.5 to R packages")
7806 (description "This package uses the source code of zlib-1.2.5 to create
7807 libraries for systems that do not have these available via other means.")
7808 (license license:artistic2.0)))
7809
7810 (define-public r-r4rna
7811 (package
7812 (name "r-r4rna")
7813 (version "0.1.4")
7814 (source
7815 (origin
7816 (method url-fetch)
7817 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7818 version ".tar.gz"))
7819 (sha256
7820 (base32
7821 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7822 (build-system r-build-system)
7823 (propagated-inputs
7824 `(("r-optparse" ,r-optparse)
7825 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7826 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7827 (synopsis "Analysis framework for RNA secondary structure")
7828 (description
7829 "The R4RNA package aims to be a general framework for the analysis of RNA
7830 secondary structure and comparative analysis in R.")
7831 (license license:gpl3+)))
7832
7833 (define-public r-rhtslib
7834 (package
7835 (name "r-rhtslib")
7836 (version "1.8.0")
7837 (source
7838 (origin
7839 (method url-fetch)
7840 (uri (bioconductor-uri "Rhtslib" version))
7841 (sha256
7842 (base32
7843 "0jj5h81z5gyf4j3lp2l3zsm6pgbmalgrngr8qdpygc20phndpp0b"))))
7844 (properties `((upstream-name . "Rhtslib")))
7845 (build-system r-build-system)
7846 (propagated-inputs
7847 `(("r-zlibbioc" ,r-zlibbioc)))
7848 (inputs
7849 `(("zlib" ,zlib)))
7850 (native-inputs
7851 `(("autoconf" ,autoconf)))
7852 (home-page "https://github.com/nhayden/Rhtslib")
7853 (synopsis "High-throughput sequencing library as an R package")
7854 (description
7855 "This package provides the HTSlib C library for high-throughput
7856 nucleotide sequence analysis. The package is primarily useful to developers
7857 of other R packages who wish to make use of HTSlib.")
7858 (license license:lgpl2.0+)))
7859
7860 (define-public r-bamsignals
7861 (package
7862 (name "r-bamsignals")
7863 (version "1.8.0")
7864 (source
7865 (origin
7866 (method url-fetch)
7867 (uri (bioconductor-uri "bamsignals" version))
7868 (sha256
7869 (base32
7870 "0knx69zzdaak2sjim8k9mygmcjxpa705m8013ld5zwpgi8dag9mc"))))
7871 (build-system r-build-system)
7872 (propagated-inputs
7873 `(("r-biocgenerics" ,r-biocgenerics)
7874 ("r-genomicranges" ,r-genomicranges)
7875 ("r-iranges" ,r-iranges)
7876 ("r-rcpp" ,r-rcpp)
7877 ("r-rhtslib" ,r-rhtslib)
7878 ("r-zlibbioc" ,r-zlibbioc)))
7879 (inputs
7880 `(("zlib" ,zlib)))
7881 (home-page "http://bioconductor.org/packages/bamsignals")
7882 (synopsis "Extract read count signals from bam files")
7883 (description
7884 "This package allows to efficiently obtain count vectors from indexed bam
7885 files. It counts the number of nucleotide sequence reads in given genomic
7886 ranges and it computes reads profiles and coverage profiles. It also handles
7887 paired-end data.")
7888 (license license:gpl2+)))
7889
7890 (define-public r-rcas
7891 (package
7892 (name "r-rcas")
7893 (version "1.1.1")
7894 (source (origin
7895 (method url-fetch)
7896 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7897 version ".tar.gz"))
7898 (file-name (string-append name "-" version ".tar.gz"))
7899 (sha256
7900 (base32
7901 "1hd0r66556bxbdd82ksjklq7nfli36l4k6y88ic7kkg9873wa1nw"))))
7902 (build-system r-build-system)
7903 (native-inputs
7904 `(("r-knitr" ,r-knitr)
7905 ("r-testthat" ,r-testthat)
7906 ;; During vignette building knitr checks that "pandoc-citeproc"
7907 ;; is in the PATH.
7908 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7909 (propagated-inputs
7910 `(("r-data-table" ,r-data-table)
7911 ("r-biomart" ,r-biomart)
7912 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7913 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7914 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7915 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7916 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7917 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7918 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7919 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7920 ("r-topgo" ,r-topgo)
7921 ("r-dt" ,r-dt)
7922 ("r-plotly" ,r-plotly)
7923 ("r-plotrix" ,r-plotrix)
7924 ("r-motifrg" ,r-motifrg)
7925 ("r-genomation" ,r-genomation)
7926 ("r-genomicfeatures" ,r-genomicfeatures)
7927 ("r-rtracklayer" ,r-rtracklayer)
7928 ("r-rmarkdown" ,r-rmarkdown)))
7929 (synopsis "RNA-centric annotation system")
7930 (description
7931 "RCAS aims to be a standalone RNA-centric annotation system that provides
7932 intuitive reports and publication-ready graphics. This package provides the R
7933 library implementing most of the pipeline's features.")
7934 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7935 (license license:expat)))
7936
7937 (define-public rcas-web
7938 (package
7939 (name "rcas-web")
7940 (version "0.0.3")
7941 (source
7942 (origin
7943 (method url-fetch)
7944 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7945 "releases/download/v" version
7946 "/rcas-web-" version ".tar.gz"))
7947 (sha256
7948 (base32
7949 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7950 (build-system gnu-build-system)
7951 (arguments
7952 `(#:phases
7953 (modify-phases %standard-phases
7954 (add-after 'install 'wrap-executable
7955 (lambda* (#:key inputs outputs #:allow-other-keys)
7956 (let* ((out (assoc-ref outputs "out"))
7957 (json (assoc-ref inputs "guile-json"))
7958 (redis (assoc-ref inputs "guile-redis"))
7959 (path (string-append
7960 json "/share/guile/site/2.2:"
7961 redis "/share/guile/site/2.2")))
7962 (wrap-program (string-append out "/bin/rcas-web")
7963 `("GUILE_LOAD_PATH" ":" = (,path))
7964 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
7965 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
7966 #t)))))
7967 (inputs
7968 `(("r-minimal" ,r-minimal)
7969 ("r-rcas" ,r-rcas)
7970 ("guile-next" ,guile-2.2)
7971 ("guile-json" ,guile-json)
7972 ("guile-redis" ,guile2.2-redis)))
7973 (native-inputs
7974 `(("pkg-config" ,pkg-config)))
7975 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
7976 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
7977 (description "This package provides a simple web interface for the
7978 @dfn{RNA-centric annotation system} (RCAS).")
7979 (license license:agpl3+)))
7980
7981 (define-public r-mutationalpatterns
7982 (package
7983 (name "r-mutationalpatterns")
7984 (version "1.2.1")
7985 (source
7986 (origin
7987 (method url-fetch)
7988 (uri (bioconductor-uri "MutationalPatterns" version))
7989 (sha256
7990 (base32
7991 "1s50diwh1j6vg3mgahh6bczvq74mfdbmwjrad4d5lh723gnc5pjg"))))
7992 (build-system r-build-system)
7993 (propagated-inputs
7994 `(("r-biocgenerics" ,r-biocgenerics)
7995 ("r-biostrings" ,r-biostrings)
7996 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
7997 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7998 ("r-genomicranges" ,r-genomicranges)
7999 ("r-genomeinfodb" ,r-genomeinfodb)
8000 ("r-ggplot2" ,r-ggplot2)
8001 ("r-gridextra" ,r-gridextra)
8002 ("r-iranges" ,r-iranges)
8003 ("r-nmf" ,r-nmf)
8004 ("r-plyr" ,r-plyr)
8005 ("r-pracma" ,r-pracma)
8006 ("r-reshape2" ,r-reshape2)
8007 ("r-summarizedexperiment" ,r-summarizedexperiment)
8008 ("r-variantannotation" ,r-variantannotation)))
8009 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
8010 (synopsis "Extract and visualize mutational patterns in genomic data")
8011 (description "This package provides an extensive toolset for the
8012 characterization and visualization of a wide range of mutational patterns
8013 in SNV base substitution data.")
8014 (license license:expat)))
8015
8016 (define-public r-wgcna
8017 (package
8018 (name "r-wgcna")
8019 (version "1.51")
8020 (source
8021 (origin
8022 (method url-fetch)
8023 (uri (cran-uri "WGCNA" version))
8024 (sha256
8025 (base32
8026 "0hzvnhw76vwg8bl8x368f0c5szpwb8323bmrb3bir93i5bmfjsxx"))))
8027 (properties `((upstream-name . "WGCNA")))
8028 (build-system r-build-system)
8029 (propagated-inputs
8030 `(("r-annotationdbi" ,r-annotationdbi)
8031 ("r-doparallel" ,r-doparallel)
8032 ("r-dynamictreecut" ,r-dynamictreecut)
8033 ("r-fastcluster" ,r-fastcluster)
8034 ("r-foreach" ,r-foreach)
8035 ("r-go-db" ,r-go-db)
8036 ("r-hmisc" ,r-hmisc)
8037 ("r-impute" ,r-impute)
8038 ("r-matrixstats" ,r-matrixstats)
8039 ("r-preprocesscore" ,r-preprocesscore)))
8040 (home-page
8041 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8042 (synopsis "Weighted correlation network analysis")
8043 (description
8044 "This package provides functions necessary to perform Weighted
8045 Correlation Network Analysis on high-dimensional data. It includes functions
8046 for rudimentary data cleaning, construction and summarization of correlation
8047 networks, module identification and functions for relating both variables and
8048 modules to sample traits. It also includes a number of utility functions for
8049 data manipulation and visualization.")
8050 (license license:gpl2+)))
8051
8052 (define-public r-chipkernels
8053 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8054 (revision "1"))
8055 (package
8056 (name "r-chipkernels")
8057 (version (string-append "1.1-" revision "." (string-take commit 9)))
8058 (source
8059 (origin
8060 (method git-fetch)
8061 (uri (git-reference
8062 (url "https://github.com/ManuSetty/ChIPKernels.git")
8063 (commit commit)))
8064 (file-name (string-append name "-" version))
8065 (sha256
8066 (base32
8067 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8068 (build-system r-build-system)
8069 (propagated-inputs
8070 `(("r-iranges" ,r-iranges)
8071 ("r-xvector" ,r-xvector)
8072 ("r-biostrings" ,r-biostrings)
8073 ("r-bsgenome" ,r-bsgenome)
8074 ("r-gtools" ,r-gtools)
8075 ("r-genomicranges" ,r-genomicranges)
8076 ("r-sfsmisc" ,r-sfsmisc)
8077 ("r-kernlab" ,r-kernlab)
8078 ("r-s4vectors" ,r-s4vectors)
8079 ("r-biocgenerics" ,r-biocgenerics)))
8080 (home-page "https://github.com/ManuSetty/ChIPKernels")
8081 (synopsis "Build string kernels for DNA Sequence analysis")
8082 (description "ChIPKernels is an R package for building different string
8083 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8084 must be built and this dictionary can be used for determining kernels for DNA
8085 Sequences.")
8086 (license license:gpl2+))))
8087
8088 (define-public r-seqgl
8089 (package
8090 (name "r-seqgl")
8091 (version "1.1.4")
8092 (source
8093 (origin
8094 (method url-fetch)
8095 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8096 "archive/" version ".tar.gz"))
8097 (file-name (string-append name "-" version ".tar.gz"))
8098 (sha256
8099 (base32
8100 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8101 (build-system r-build-system)
8102 (propagated-inputs
8103 `(("r-biostrings" ,r-biostrings)
8104 ("r-chipkernels" ,r-chipkernels)
8105 ("r-genomicranges" ,r-genomicranges)
8106 ("r-spams" ,r-spams)
8107 ("r-wgcna" ,r-wgcna)
8108 ("r-fastcluster" ,r-fastcluster)))
8109 (home-page "https://github.com/ManuSetty/SeqGL")
8110 (synopsis "Group lasso for Dnase/ChIP-seq data")
8111 (description "SeqGL is a group lasso based algorithm to extract
8112 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8113 This package presents a method which uses group lasso to discriminate between
8114 bound and non bound genomic regions to accurately identify transcription
8115 factors bound at the specific regions.")
8116 (license license:gpl2+)))
8117
8118 (define-public r-gkmsvm
8119 (package
8120 (name "r-gkmsvm")
8121 (version "0.71.0")
8122 (source
8123 (origin
8124 (method url-fetch)
8125 (uri (cran-uri "gkmSVM" version))
8126 (sha256
8127 (base32
8128 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8129 (properties `((upstream-name . "gkmSVM")))
8130 (build-system r-build-system)
8131 (propagated-inputs
8132 `(("r-biocgenerics" ,r-biocgenerics)
8133 ("r-biostrings" ,r-biostrings)
8134 ("r-genomeinfodb" ,r-genomeinfodb)
8135 ("r-genomicranges" ,r-genomicranges)
8136 ("r-iranges" ,r-iranges)
8137 ("r-kernlab" ,r-kernlab)
8138 ("r-rcpp" ,r-rcpp)
8139 ("r-rocr" ,r-rocr)
8140 ("r-rtracklayer" ,r-rtracklayer)
8141 ("r-s4vectors" ,r-s4vectors)
8142 ("r-seqinr" ,r-seqinr)))
8143 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8144 (synopsis "Gapped-kmer support vector machine")
8145 (description
8146 "This R package provides tools for training gapped-kmer SVM classifiers
8147 for DNA and protein sequences. This package supports several sequence
8148 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8149 (license license:gpl2+)))
8150
8151 (define-public r-tximport
8152 (package
8153 (name "r-tximport")
8154 (version "1.4.0")
8155 (source (origin
8156 (method url-fetch)
8157 (uri (bioconductor-uri "tximport" version))
8158 (sha256
8159 (base32
8160 "1mklb02bj4gnbjlmb7vv6k4lr3w9fp3pzli9rddbrwd0y5n8fcpx"))))
8161 (build-system r-build-system)
8162 (home-page "http://bioconductor.org/packages/tximport")
8163 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8164 (description
8165 "This package provides tools to import transcript-level abundance,
8166 estimated counts and transcript lengths, and to summarize them into matrices
8167 for use with downstream gene-level analysis packages. Average transcript
8168 length, weighted by sample-specific transcript abundance estimates, is
8169 provided as a matrix which can be used as an offset for different expression
8170 of gene-level counts.")
8171 (license license:gpl2+)))
8172
8173 (define-public r-rhdf5
8174 (package
8175 (name "r-rhdf5")
8176 (version "2.20.0")
8177 (source (origin
8178 (method url-fetch)
8179 (uri (bioconductor-uri "rhdf5" version))
8180 (sha256
8181 (base32
8182 "1p6f5i6l44phl772a38x9cav2sya37bkqbkjzdc4pmyfzkv1j6hy"))))
8183 (build-system r-build-system)
8184 (arguments
8185 `(#:phases
8186 (modify-phases %standard-phases
8187 (add-after 'unpack 'unpack-smallhdf5
8188 (lambda* (#:key outputs #:allow-other-keys)
8189 (system* "tar" "-xzvf"
8190 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8191 (substitute* "src/Makevars"
8192 (("^.*cd hdf5source &&.*$") "")
8193 (("^.*gunzip -dc hdf5small.tgz.*$") "")
8194 (("^.*rm -rf hdf5.*$") "")
8195 (("^.*mv hdf5source/hdf5 ..*$") ""))
8196 (substitute* "src/hdf5/configure"
8197 (("/bin/mv") "mv"))
8198 #t)))))
8199 (propagated-inputs
8200 `(("r-zlibbioc" ,r-zlibbioc)))
8201 (inputs
8202 `(("perl" ,perl)
8203 ("zlib" ,zlib)))
8204 (home-page "http://bioconductor.org/packages/rhdf5")
8205 (synopsis "HDF5 interface to R")
8206 (description
8207 "This R/Bioconductor package provides an interface between HDF5 and R.
8208 HDF5's main features are the ability to store and access very large and/or
8209 complex datasets and a wide variety of metadata on mass storage (disk) through
8210 a completely portable file format. The rhdf5 package is thus suited for the
8211 exchange of large and/or complex datasets between R and other software
8212 package, and for letting R applications work on datasets that are larger than
8213 the available RAM.")
8214 (license license:artistic2.0)))
8215
8216 (define-public emboss
8217 (package
8218 (name "emboss")
8219 (version "6.5.7")
8220 (source (origin
8221 (method url-fetch)
8222 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8223 (version-major+minor version) ".0/"
8224 "EMBOSS-" version ".tar.gz"))
8225 (sha256
8226 (base32
8227 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8228 (build-system gnu-build-system)
8229 (arguments
8230 `(#:configure-flags
8231 (list (string-append "--with-hpdf="
8232 (assoc-ref %build-inputs "libharu")))
8233 #:phases
8234 (modify-phases %standard-phases
8235 (add-after 'unpack 'fix-checks
8236 (lambda _
8237 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8238 ;; and zlib, but assume that they are all found at the same
8239 ;; prefix.
8240 (substitute* "configure.in"
8241 (("CHECK_PNGDRIVER")
8242 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8243 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8244 AM_CONDITIONAL(AMPNG, true)"))
8245 #t))
8246 (add-after 'unpack 'disable-update-check
8247 (lambda _
8248 ;; At build time there is no connection to the Internet, so
8249 ;; looking for updates will not work.
8250 (substitute* "Makefile.am"
8251 (("\\$\\(bindir\\)/embossupdate") ""))
8252 #t))
8253 (add-before 'configure 'autogen
8254 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8255 (inputs
8256 `(("perl" ,perl)
8257 ("libpng" ,libpng)
8258 ("gd" ,gd)
8259 ("libx11" ,libx11)
8260 ("libharu" ,libharu)
8261 ("zlib" ,zlib)))
8262 (native-inputs
8263 `(("autoconf" ,autoconf)
8264 ("automake" ,automake)
8265 ("libtool" ,libtool)
8266 ("pkg-config" ,pkg-config)))
8267 (home-page "http://emboss.sourceforge.net")
8268 (synopsis "Molecular biology analysis suite")
8269 (description "EMBOSS is the \"European Molecular Biology Open Software
8270 Suite\". EMBOSS is an analysis package specially developed for the needs of
8271 the molecular biology (e.g. EMBnet) user community. The software
8272 automatically copes with data in a variety of formats and even allows
8273 transparent retrieval of sequence data from the web. It also provides a
8274 number of libraries for the development of software in the field of molecular
8275 biology. EMBOSS also integrates a range of currently available packages and
8276 tools for sequence analysis into a seamless whole.")
8277 (license license:gpl2+)))
8278
8279 (define-public bits
8280 (let ((revision "1")
8281 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8282 (package
8283 (name "bits")
8284 ;; The version is 2.13.0 even though no release archives have been
8285 ;; published as yet.
8286 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8287 (source (origin
8288 (method git-fetch)
8289 (uri (git-reference
8290 (url "https://github.com/arq5x/bits.git")
8291 (commit commit)))
8292 (file-name (string-append name "-" version "-checkout"))
8293 (sha256
8294 (base32
8295 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8296 (build-system gnu-build-system)
8297 (arguments
8298 `(#:tests? #f ;no tests included
8299 #:phases
8300 (modify-phases %standard-phases
8301 (delete 'configure)
8302 (add-after 'unpack 'remove-cuda
8303 (lambda _
8304 (substitute* "Makefile"
8305 ((".*_cuda") "")
8306 (("(bits_test_intersections) \\\\" _ match) match))
8307 #t))
8308 (replace 'install
8309 (lambda* (#:key outputs #:allow-other-keys)
8310 (copy-recursively
8311 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8312 #t)))))
8313 (inputs
8314 `(("gsl" ,gsl)
8315 ("zlib" ,zlib)))
8316 (home-page "https://github.com/arq5x/bits")
8317 (synopsis "Implementation of binary interval search algorithm")
8318 (description "This package provides an implementation of the
8319 BITS (Binary Interval Search) algorithm, an approach to interval set
8320 intersection. It is especially suited for the comparison of diverse genomic
8321 datasets and the exploration of large datasets of genome
8322 intervals (e.g. genes, sequence alignments).")
8323 (license license:gpl2))))
8324
8325 (define-public piranha
8326 ;; There is no release tarball for the latest version. The latest commit is
8327 ;; older than one year at the time of this writing.
8328 (let ((revision "1")
8329 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8330 (package
8331 (name "piranha")
8332 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8333 (source (origin
8334 (method git-fetch)
8335 (uri (git-reference
8336 (url "https://github.com/smithlabcode/piranha.git")
8337 (commit commit)))
8338 (sha256
8339 (base32
8340 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8341 (build-system gnu-build-system)
8342 (arguments
8343 `(#:test-target "test"
8344 #:phases
8345 (modify-phases %standard-phases
8346 (add-after 'unpack 'copy-smithlab-cpp
8347 (lambda* (#:key inputs #:allow-other-keys)
8348 (for-each (lambda (file)
8349 (install-file file "./src/smithlab_cpp/"))
8350 (find-files (assoc-ref inputs "smithlab-cpp")))
8351 #t))
8352 (add-after 'install 'install-to-store
8353 (lambda* (#:key outputs #:allow-other-keys)
8354 (let* ((out (assoc-ref outputs "out"))
8355 (bin (string-append out "/bin")))
8356 (for-each (lambda (file)
8357 (install-file file bin))
8358 (find-files "bin" ".*")))
8359 #t)))
8360 #:configure-flags
8361 (list (string-append "--with-bam_tools_headers="
8362 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8363 (string-append "--with-bam_tools_library="
8364 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8365 (inputs
8366 `(("bamtools" ,bamtools)
8367 ("samtools" ,samtools-0.1)
8368 ("gsl" ,gsl)
8369 ("smithlab-cpp"
8370 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8371 (origin
8372 (method git-fetch)
8373 (uri (git-reference
8374 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8375 (commit commit)))
8376 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8377 (sha256
8378 (base32
8379 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8380 (native-inputs
8381 `(("python" ,python-2)))
8382 (home-page "https://github.com/smithlabcode/piranha")
8383 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8384 (description
8385 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8386 RIP-seq experiments. It takes input in BED or BAM format and identifies
8387 regions of statistically significant read enrichment. Additional covariates
8388 may optionally be provided to further inform the peak-calling process.")
8389 (license license:gpl3+))))
8390
8391 (define-public pepr
8392 (package
8393 (name "pepr")
8394 (version "1.0.9")
8395 (source (origin
8396 (method url-fetch)
8397 (uri (string-append "https://pypi.python.org/packages/source/P"
8398 "/PePr/PePr-" version ".tar.gz"))
8399 (sha256
8400 (base32
8401 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8402 (build-system python-build-system)
8403 (arguments
8404 `(#:python ,python-2 ; python2 only
8405 #:tests? #f)) ; no tests included
8406 (propagated-inputs
8407 `(("python2-numpy" ,python2-numpy)
8408 ("python2-scipy" ,python2-scipy)
8409 ("python2-pysam" ,python2-pysam)))
8410 (home-page "https://github.com/shawnzhangyx/PePr")
8411 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8412 (description
8413 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8414 that is primarily designed for data with biological replicates. It uses a
8415 negative binomial distribution to model the read counts among the samples in
8416 the same group, and look for consistent differences between ChIP and control
8417 group or two ChIP groups run under different conditions.")
8418 (license license:gpl3+)))
8419
8420 (define-public filevercmp
8421 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8422 (package
8423 (name "filevercmp")
8424 (version (string-append "0-1." (string-take commit 7)))
8425 (source (origin
8426 (method url-fetch)
8427 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8428 commit ".tar.gz"))
8429 (file-name (string-append name "-" version ".tar.gz"))
8430 (sha256
8431 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8432 (build-system gnu-build-system)
8433 (arguments
8434 `(#:tests? #f ; There are no tests to run.
8435 #:phases
8436 (modify-phases %standard-phases
8437 (delete 'configure) ; There is no configure phase.
8438 (replace 'install
8439 (lambda* (#:key outputs #:allow-other-keys)
8440 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8441 (install-file "filevercmp" bin)))))))
8442 (home-page "https://github.com/ekg/filevercmp")
8443 (synopsis "This program compares version strings")
8444 (description "This program compares version strings. It intends to be a
8445 replacement for strverscmp.")
8446 (license license:gpl3+))))
8447
8448 (define-public multiqc
8449 (package
8450 (name "multiqc")
8451 (version "0.9")
8452 (source
8453 (origin
8454 (method url-fetch)
8455 (uri (pypi-uri "multiqc" version))
8456 (sha256
8457 (base32
8458 "12gs1jw2jrxrij529rnl5kaqxfcqn15yzcsggxkfhdx634ml0cny"))
8459 (patches (search-patches "multiqc-fix-git-subprocess-error.patch"))))
8460 (build-system python-build-system)
8461 (arguments
8462 ;; Tests are to be introduced in the next version, see
8463 ;; https://github.com/ewels/MultiQC/issues/376
8464 `(#:tests? #f))
8465 (propagated-inputs
8466 `(("python-jinja2" ,python-jinja2)
8467 ("python-simplejson" ,python-simplejson)
8468 ("python-pyyaml" ,python-pyyaml)
8469 ("python-click" ,python-click)
8470 ("python-matplotlib" ,python-matplotlib)
8471 ("python-numpy" ,python-numpy)
8472 ;; MultQC checks for the presence of nose at runtime.
8473 ("python-nose" ,python-nose)))
8474 (home-page "http://multiqc.info")
8475 (synopsis "Aggregate bioinformatics analysis reports")
8476 (description
8477 "MultiQC is a tool to aggregate bioinformatics results across many
8478 samples into a single report. It contains modules for a large number of
8479 common bioinformatics tools.")
8480 (license license:gpl3)))
8481
8482 (define-public r-chipseq
8483 (package
8484 (name "r-chipseq")
8485 (version "1.26.0")
8486 (source
8487 (origin
8488 (method url-fetch)
8489 (uri (bioconductor-uri "chipseq" version))
8490 (sha256
8491 (base32
8492 "1hahyqiwb2ch8214xqpw0c3jpiwkmyf3dwz0xc87jx6cdnzipj3i"))))
8493 (build-system r-build-system)
8494 (propagated-inputs
8495 `(("r-biocgenerics" ,r-biocgenerics)
8496 ("r-genomicranges" ,r-genomicranges)
8497 ("r-iranges" ,r-iranges)
8498 ("r-s4vectors" ,r-s4vectors)
8499 ("r-shortread" ,r-shortread)))
8500 (home-page "http://bioconductor.org/packages/chipseq")
8501 (synopsis "Package for analyzing ChIPseq data")
8502 (description
8503 "This package provides tools for processing short read data from ChIPseq
8504 experiments.")
8505 (license license:artistic2.0)))
8506
8507 (define-public r-copyhelper
8508 (package
8509 (name "r-copyhelper")
8510 (version "1.6.0")
8511 (source
8512 (origin
8513 (method url-fetch)
8514 (uri (string-append "http://bioconductor.org/packages/release/"
8515 "data/experiment/src/contrib/CopyhelpeR_"
8516 version ".tar.gz"))
8517 (sha256
8518 (base32
8519 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8520 (properties `((upstream-name . "CopyhelpeR")))
8521 (build-system r-build-system)
8522 (home-page "http://bioconductor.org/packages/CopyhelpeR/")
8523 (synopsis "Helper files for CopywriteR")
8524 (description
8525 "This package contains the helper files that are required to run the
8526 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8527 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8528 mm10. In addition, it contains a blacklist filter to remove regions that
8529 display copy number variation. Files are stored as GRanges objects from the
8530 GenomicRanges Bioconductor package.")
8531 (license license:gpl2)))
8532
8533 (define-public r-copywriter
8534 (package
8535 (name "r-copywriter")
8536 (version "2.8.0")
8537 (source
8538 (origin
8539 (method url-fetch)
8540 (uri (bioconductor-uri "CopywriteR" version))
8541 (sha256
8542 (base32
8543 "183nmrqmdf9syqljslvwv7mhs9ar5xizzq98imgsc80q0m25ncjf"))))
8544 (properties `((upstream-name . "CopywriteR")))
8545 (build-system r-build-system)
8546 (propagated-inputs
8547 `(("r-biocparallel" ,r-biocparallel)
8548 ("r-chipseq" ,r-chipseq)
8549 ("r-copyhelper" ,r-copyhelper)
8550 ("r-data-table" ,r-data-table)
8551 ("r-dnacopy" ,r-dnacopy)
8552 ("r-futile-logger" ,r-futile-logger)
8553 ("r-genomeinfodb" ,r-genomeinfodb)
8554 ("r-genomicalignments" ,r-genomicalignments)
8555 ("r-genomicranges" ,r-genomicranges)
8556 ("r-gtools" ,r-gtools)
8557 ("r-iranges" ,r-iranges)
8558 ("r-matrixstats" ,r-matrixstats)
8559 ("r-rsamtools" ,r-rsamtools)
8560 ("r-s4vectors" ,r-s4vectors)))
8561 (home-page "https://github.com/PeeperLab/CopywriteR")
8562 (synopsis "Copy number information from targeted sequencing")
8563 (description
8564 "CopywriteR extracts DNA copy number information from targeted sequencing
8565 by utilizing off-target reads. It allows for extracting uniformly distributed
8566 copy number information, can be used without reference, and can be applied to
8567 sequencing data obtained from various techniques including chromatin
8568 immunoprecipitation and target enrichment on small gene panels. Thereby,
8569 CopywriteR constitutes a widely applicable alternative to available copy
8570 number detection tools.")
8571 (license license:gpl2)))
8572
8573 (define-public r-sva
8574 (package
8575 (name "r-sva")
8576 (version "3.24.0")
8577 (source
8578 (origin
8579 (method url-fetch)
8580 (uri (bioconductor-uri "sva" version))
8581 (sha256
8582 (base32
8583 "04pxl61iyc845wmqca1qv8kbb8zcp0qp72zgvgki3zzmrph9a362"))))
8584 (build-system r-build-system)
8585 (propagated-inputs
8586 `(("r-genefilter" ,r-genefilter)
8587 ("r-mgcv" ,r-mgcv)))
8588 (home-page "http://bioconductor.org/packages/sva")
8589 (synopsis "Surrogate variable analysis")
8590 (description
8591 "This package contains functions for removing batch effects and other
8592 unwanted variation in high-throughput experiment. It also contains functions
8593 for identifying and building surrogate variables for high-dimensional data
8594 sets. Surrogate variables are covariates constructed directly from
8595 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8596 imaging data that can be used in subsequent analyses to adjust for unknown,
8597 unmodeled, or latent sources of noise.")
8598 (license license:artistic2.0)))
8599
8600 (define-public r-seqminer
8601 (package
8602 (name "r-seqminer")
8603 (version "5.9")
8604 (source
8605 (origin
8606 (method url-fetch)
8607 (uri (cran-uri "seqminer" version))
8608 (sha256
8609 (base32
8610 "0sfkxrc9gy5a8fadzyzfzh7l5grasm8cj6cd2nnpv85ws6mqr6qd"))))
8611 (build-system r-build-system)
8612 (inputs
8613 `(("zlib" ,zlib)))
8614 (home-page "http://seqminer.genomic.codes")
8615 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8616 (description
8617 "This package provides tools to integrate nucleotide sequencing
8618 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8619 ;; Any version of the GPL is acceptable
8620 (license (list license:gpl2+ license:gpl3+))))
8621
8622 (define-public r-raremetals2
8623 (package
8624 (name "r-raremetals2")
8625 (version "0.1")
8626 (source
8627 (origin
8628 (method url-fetch)
8629 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8630 "b/b7/RareMETALS2_" version ".tar.gz"))
8631 (sha256
8632 (base32
8633 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8634 (properties `((upstream-name . "RareMETALS2")))
8635 (build-system r-build-system)
8636 (propagated-inputs
8637 `(("r-seqminer" ,r-seqminer)
8638 ("r-mvtnorm" ,r-mvtnorm)
8639 ("r-mass" ,r-mass)
8640 ("r-compquadform" ,r-compquadform)
8641 ("r-getopt" ,r-getopt)))
8642 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8643 (synopsis "Analyze gene-level association tests for binary trait")
8644 (description
8645 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8646 It was designed to meta-analyze gene-level association tests for binary trait.
8647 While rareMETALS offers a near-complete solution for meta-analysis of
8648 gene-level tests for quantitative trait, it does not offer the optimal
8649 solution for binary trait. The package rareMETALS2 offers improved features
8650 for analyzing gene-level association tests in meta-analyses for binary
8651 trait.")
8652 (license license:gpl3)))
8653
8654 (define-public r-maldiquant
8655 (package
8656 (name "r-maldiquant")
8657 (version "1.16.2")
8658 (source
8659 (origin
8660 (method url-fetch)
8661 (uri (cran-uri "MALDIquant" version))
8662 (sha256
8663 (base32
8664 "0z5srzsfgsgi4bssr4chls4ry6d18y2g9143znqmraylppwrrqzr"))))
8665 (properties `((upstream-name . "MALDIquant")))
8666 (build-system r-build-system)
8667 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8668 (synopsis "Quantitative analysis of mass spectrometry data")
8669 (description
8670 "This package provides a complete analysis pipeline for matrix-assisted
8671 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8672 two-dimensional mass spectrometry data. In addition to commonly used plotting
8673 and processing methods it includes distinctive features, namely baseline
8674 subtraction methods such as morphological filters (TopHat) or the
8675 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8676 alignment using warping functions, handling of replicated measurements as well
8677 as allowing spectra with different resolutions.")
8678 (license license:gpl3+)))
8679
8680 (define-public r-protgenerics
8681 (package
8682 (name "r-protgenerics")
8683 (version "1.8.0")
8684 (source
8685 (origin
8686 (method url-fetch)
8687 (uri (bioconductor-uri "ProtGenerics" version))
8688 (sha256
8689 (base32
8690 "08idb3rvxn4fl7rd66jasyqz47cb76dbc3968r1g26jr2ci3w1pl"))))
8691 (properties `((upstream-name . "ProtGenerics")))
8692 (build-system r-build-system)
8693 (home-page "https://github.com/lgatto/ProtGenerics")
8694 (synopsis "S4 generic functions for proteomics infrastructure")
8695 (description
8696 "This package provides S4 generic functions needed by Bioconductor
8697 proteomics packages.")
8698 (license license:artistic2.0)))
8699
8700 (define-public r-mzr
8701 (package
8702 (name "r-mzr")
8703 (version "2.10.0")
8704 (source
8705 (origin
8706 (method url-fetch)
8707 (uri (bioconductor-uri "mzR" version))
8708 (sha256
8709 (base32
8710 "1zir46h320n2vbrky6q3m8l221f3wdjlfsnx4ak9xca5min24xm7"))))
8711 (properties `((upstream-name . "mzR")))
8712 (build-system r-build-system)
8713 (inputs
8714 `(("netcdf" ,netcdf)))
8715 (propagated-inputs
8716 `(("r-biobase" ,r-biobase)
8717 ("r-biocgenerics" ,r-biocgenerics)
8718 ("r-protgenerics" ,r-protgenerics)
8719 ("r-rcpp" ,r-rcpp)
8720 ("r-zlibbioc" ,r-zlibbioc)))
8721 (home-page "https://github.com/sneumann/mzR/")
8722 (synopsis "Parser for mass spectrometry data files")
8723 (description
8724 "The mzR package provides a unified API to the common file formats and
8725 parsers available for mass spectrometry data. It comes with a wrapper for the
8726 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8727 The package contains the original code written by the ISB, and a subset of the
8728 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8729 previously been used in XCMS.")
8730 (license license:artistic2.0)))
8731
8732 (define-public r-affyio
8733 (package
8734 (name "r-affyio")
8735 (version "1.46.0")
8736 (source
8737 (origin
8738 (method url-fetch)
8739 (uri (bioconductor-uri "affyio" version))
8740 (sha256
8741 (base32
8742 "13w6al9296q916w0w6ngbsk25b21ahla1b6n40fcqhbvhyfii6sj"))))
8743 (build-system r-build-system)
8744 (propagated-inputs
8745 `(("r-zlibbioc" ,r-zlibbioc)))
8746 (inputs
8747 `(("zlib" ,zlib)))
8748 (home-page "https://github.com/bmbolstad/affyio")
8749 (synopsis "Tools for parsing Affymetrix data files")
8750 (description
8751 "This package provides routines for parsing Affymetrix data files based
8752 upon file format information. The primary focus is on accessing the CEL and
8753 CDF file formats.")
8754 (license license:lgpl2.0+)))
8755
8756 (define-public r-affy
8757 (package
8758 (name "r-affy")
8759 (version "1.54.0")
8760 (source
8761 (origin
8762 (method url-fetch)
8763 (uri (bioconductor-uri "affy" version))
8764 (sha256
8765 (base32
8766 "0azwg2qxzgflr1rjvbdln5i5rbcr9gs36kqlacd9cwl1szb9ad3m"))))
8767 (build-system r-build-system)
8768 (propagated-inputs
8769 `(("r-affyio" ,r-affyio)
8770 ("r-biobase" ,r-biobase)
8771 ("r-biocgenerics" ,r-biocgenerics)
8772 ("r-biocinstaller" ,r-biocinstaller)
8773 ("r-preprocesscore" ,r-preprocesscore)
8774 ("r-zlibbioc" ,r-zlibbioc)))
8775 (home-page "http://bioconductor.org/packages/affy")
8776 (synopsis "Methods for affymetrix oligonucleotide arrays")
8777 (description
8778 "This package contains functions for exploratory oligonucleotide array
8779 analysis.")
8780 (license license:lgpl2.0+)))
8781
8782 (define-public r-vsn
8783 (package
8784 (name "r-vsn")
8785 (version "3.44.0")
8786 (source
8787 (origin
8788 (method url-fetch)
8789 (uri (bioconductor-uri "vsn" version))
8790 (sha256
8791 (base32
8792 "0qhg3a4sc62pfdxcpvmk831rk138xh4zx4f1s39jhxpqqhmr7jvk"))))
8793 (build-system r-build-system)
8794 (propagated-inputs
8795 `(("r-affy" ,r-affy)
8796 ("r-biobase" ,r-biobase)
8797 ("r-ggplot2" ,r-ggplot2)
8798 ("r-hexbin" ,r-hexbin)
8799 ("r-lattice" ,r-lattice)
8800 ("r-limma" ,r-limma)))
8801 (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
8802 (synopsis "Variance stabilization and calibration for microarray data")
8803 (description
8804 "The package implements a method for normalising microarray intensities,
8805 and works for single- and multiple-color arrays. It can also be used for data
8806 from other technologies, as long as they have similar format. The method uses
8807 a robust variant of the maximum-likelihood estimator for an
8808 additive-multiplicative error model and affine calibration. The model
8809 incorporates data calibration step (a.k.a. normalization), a model for the
8810 dependence of the variance on the mean intensity and a variance stabilizing
8811 data transformation. Differences between transformed intensities are
8812 analogous to \"normalized log-ratios\". However, in contrast to the latter,
8813 their variance is independent of the mean, and they are usually more sensitive
8814 and specific in detecting differential transcription.")
8815 (license license:artistic2.0)))
8816
8817 (define-public r-mzid
8818 (package
8819 (name "r-mzid")
8820 (version "1.14.0")
8821 (source
8822 (origin
8823 (method url-fetch)
8824 (uri (bioconductor-uri "mzID" version))
8825 (sha256
8826 (base32
8827 "11xnild02jz24vbsfy92lb7jlqqwnrswg66a7r4rsw8d2ibrbk33"))))
8828 (properties `((upstream-name . "mzID")))
8829 (build-system r-build-system)
8830 (propagated-inputs
8831 `(("r-doparallel" ,r-doparallel)
8832 ("r-foreach" ,r-foreach)
8833 ("r-iterators" ,r-iterators)
8834 ("r-plyr" ,r-plyr)
8835 ("r-protgenerics" ,r-protgenerics)
8836 ("r-rcpp" ,r-rcpp)
8837 ("r-xml" ,r-xml)))
8838 (home-page "http://bioconductor.org/packages/mzID")
8839 (synopsis "Parser for mzIdentML files")
8840 (description
8841 "This package provides a parser for mzIdentML files implemented using the
8842 XML package. The parser tries to be general and able to handle all types of
8843 mzIdentML files with the drawback of having less pretty output than a vendor
8844 specific parser.")
8845 (license license:gpl2+)))
8846
8847 (define-public r-pcamethods
8848 (package
8849 (name "r-pcamethods")
8850 (version "1.68.0")
8851 (source
8852 (origin
8853 (method url-fetch)
8854 (uri (bioconductor-uri "pcaMethods" version))
8855 (sha256
8856 (base32
8857 "0c4lphqyzj577ws4s172391cgv00s5nhy152zp18k2k4diyhq6n0"))))
8858 (properties `((upstream-name . "pcaMethods")))
8859 (build-system r-build-system)
8860 (propagated-inputs
8861 `(("r-biobase" ,r-biobase)
8862 ("r-biocgenerics" ,r-biocgenerics)
8863 ("r-mass" ,r-mass)
8864 ("r-rcpp" ,r-rcpp)))
8865 (home-page "https://github.com/hredestig/pcamethods")
8866 (synopsis "Collection of PCA methods")
8867 (description
8868 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
8869 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
8870 for missing value estimation is included for comparison. BPCA, PPCA and
8871 NipalsPCA may be used to perform PCA on incomplete data as well as for
8872 accurate missing value estimation. A set of methods for printing and plotting
8873 the results is also provided. All PCA methods make use of the same data
8874 structure (pcaRes) to provide a common interface to the PCA results.")
8875 (license license:gpl3+)))
8876
8877 (define-public r-msnbase
8878 (package
8879 (name "r-msnbase")
8880 (version "2.2.0")
8881 (source
8882 (origin
8883 (method url-fetch)
8884 (uri (bioconductor-uri "MSnbase" version))
8885 (sha256
8886 (base32
8887 "1n9bbdlp8d8bx2mqby0c4yylz1yil42scbkxqgyrfr9s5sn6dqff"))))
8888 (properties `((upstream-name . "MSnbase")))
8889 (build-system r-build-system)
8890 (propagated-inputs
8891 `(("r-affy" ,r-affy)
8892 ("r-biobase" ,r-biobase)
8893 ("r-biocgenerics" ,r-biocgenerics)
8894 ("r-biocparallel" ,r-biocparallel)
8895 ("r-digest" ,r-digest)
8896 ("r-ggplot2" ,r-ggplot2)
8897 ("r-impute" ,r-impute)
8898 ("r-iranges" ,r-iranges)
8899 ("r-maldiquant" ,r-maldiquant)
8900 ("r-mzid" ,r-mzid)
8901 ("r-mzr" ,r-mzr)
8902 ("r-pcamethods" ,r-pcamethods)
8903 ("r-plyr" ,r-plyr)
8904 ("r-preprocesscore" ,r-preprocesscore)
8905 ("r-protgenerics" ,r-protgenerics)
8906 ("r-rcpp" ,r-rcpp)
8907 ("r-reshape2" ,r-reshape2)
8908 ("r-s4vectors" ,r-s4vectors)
8909 ("r-vsn" ,r-vsn)
8910 ("r-xml" ,r-xml)))
8911 (home-page "https://github.com/lgatto/MSnbase")
8912 (synopsis "Base functions and classes for MS-based proteomics")
8913 (description
8914 "This package provides basic plotting, data manipulation and processing
8915 of mass spectrometry based proteomics data.")
8916 (license license:artistic2.0)))
8917
8918 (define-public r-msnid
8919 (package
8920 (name "r-msnid")
8921 (version "1.10.0")
8922 (source
8923 (origin
8924 (method url-fetch)
8925 (uri (bioconductor-uri "MSnID" version))
8926 (sha256
8927 (base32
8928 "0pjwargi5lif8q53fd43ql67p3yk9w10jychafd9qgbaw5k3f68k"))))
8929 (properties `((upstream-name . "MSnID")))
8930 (build-system r-build-system)
8931 (propagated-inputs
8932 `(("r-biobase" ,r-biobase)
8933 ("r-data-table" ,r-data-table)
8934 ("r-doparallel" ,r-doparallel)
8935 ("r-dplyr" ,r-dplyr)
8936 ("r-foreach" ,r-foreach)
8937 ("r-iterators" ,r-iterators)
8938 ("r-msnbase" ,r-msnbase)
8939 ("r-mzid" ,r-mzid)
8940 ("r-mzr" ,r-mzr)
8941 ("r-protgenerics" ,r-protgenerics)
8942 ("r-r-cache" ,r-r-cache)
8943 ("r-rcpp" ,r-rcpp)
8944 ("r-reshape2" ,r-reshape2)))
8945 (home-page "http://bioconductor.org/packages/MSnID")
8946 (synopsis "Utilities for LC-MSn proteomics identifications")
8947 (description
8948 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
8949 from mzIdentML (leveraging the mzID package) or text files. After collating
8950 the search results from multiple datasets it assesses their identification
8951 quality and optimize filtering criteria to achieve the maximum number of
8952 identifications while not exceeding a specified false discovery rate. It also
8953 contains a number of utilities to explore the MS/MS results and assess missed
8954 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
8955 (license license:artistic2.0)))
8956
8957 (define-public r-seurat
8958 ;; Source releases are only made for new x.0 versions. All newer versions
8959 ;; are only released as pre-built binaries. At the time of this writing the
8960 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
8961 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
8962 (revision "1"))
8963 (package
8964 (name "r-seurat")
8965 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
8966 (source (origin
8967 (method git-fetch)
8968 (uri (git-reference
8969 (url "https://github.com/satijalab/seurat")
8970 (commit commit)))
8971 (file-name (string-append name "-" version "-checkout"))
8972 (sha256
8973 (base32
8974 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
8975 ;; Delete pre-built jar.
8976 (snippet
8977 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
8978 #t))))
8979 (build-system r-build-system)
8980 (arguments
8981 `(#:phases
8982 (modify-phases %standard-phases
8983 (add-after 'unpack 'build-jar
8984 (lambda* (#:key inputs #:allow-other-keys)
8985 (let ((classesdir "tmp-classes"))
8986 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
8987 (mkdir classesdir)
8988 (and (zero? (apply system* `("javac" "-d" ,classesdir
8989 ,@(find-files "java" "\\.java$"))))
8990 (zero? (system* "jar"
8991 "-cf" "inst/java/ModularityOptimizer.jar"
8992 "-C" classesdir ".")))))))))
8993 (native-inputs
8994 `(("jdk" ,icedtea "jdk")))
8995 (propagated-inputs
8996 `(("r-ape" ,r-ape)
8997 ("r-caret" ,r-caret)
8998 ("r-cowplot" ,r-cowplot)
8999 ("r-dplyr" ,r-dplyr)
9000 ("r-fastica" ,r-fastica)
9001 ("r-fnn" ,r-fnn)
9002 ("r-fpc" ,r-fpc)
9003 ("r-gdata" ,r-gdata)
9004 ("r-ggplot2" ,r-ggplot2)
9005 ("r-gplots" ,r-gplots)
9006 ("r-gridextra" ,r-gridextra)
9007 ("r-igraph" ,r-igraph)
9008 ("r-irlba" ,r-irlba)
9009 ("r-lars" ,r-lars)
9010 ("r-mixtools" ,r-mixtools)
9011 ("r-pbapply" ,r-pbapply)
9012 ("r-plyr" ,r-plyr)
9013 ("r-ranger" ,r-ranger)
9014 ("r-rcolorbrewer" ,r-rcolorbrewer)
9015 ("r-rcpp" ,r-rcpp)
9016 ("r-rcppeigen" ,r-rcppeigen)
9017 ("r-rcppprogress" ,r-rcppprogress)
9018 ("r-reshape2" ,r-reshape2)
9019 ("r-rocr" ,r-rocr)
9020 ("r-rtsne" ,r-rtsne)
9021 ("r-stringr" ,r-stringr)
9022 ("r-tclust" ,r-tclust)
9023 ("r-tsne" ,r-tsne)
9024 ("r-vgam" ,r-vgam)))
9025 (home-page "http://www.satijalab.org/seurat")
9026 (synopsis "Seurat is an R toolkit for single cell genomics")
9027 (description
9028 "This package is an R package designed for QC, analysis, and
9029 exploration of single cell RNA-seq data. It easily enables widely-used
9030 analytical techniques, including the identification of highly variable genes,
9031 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9032 algorithms; density clustering, hierarchical clustering, k-means, and the
9033 discovery of differentially expressed genes and markers.")
9034 (license license:gpl3))))
9035
9036 (define-public r-aroma-light
9037 (package
9038 (name "r-aroma-light")
9039 (version "3.6.0")
9040 (source
9041 (origin
9042 (method url-fetch)
9043 (uri (bioconductor-uri "aroma.light" version))
9044 (sha256
9045 (base32
9046 "10snykmmx36qaymyf5s1n1km8hsscyzpykcpf0mzsrcv8ml9rp8a"))))
9047 (properties `((upstream-name . "aroma.light")))
9048 (build-system r-build-system)
9049 (propagated-inputs
9050 `(("r-matrixstats" ,r-matrixstats)
9051 ("r-r-methodss3" ,r-r-methodss3)
9052 ("r-r-oo" ,r-r-oo)
9053 ("r-r-utils" ,r-r-utils)))
9054 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9055 (synopsis "Methods for normalization and visualization of microarray data")
9056 (description
9057 "This package provides methods for microarray analysis that take basic
9058 data types such as matrices and lists of vectors. These methods can be used
9059 standalone, be utilized in other packages, or be wrapped up in higher-level
9060 classes.")
9061 (license license:gpl2+)))
9062
9063 (define-public r-deseq
9064 (package
9065 (name "r-deseq")
9066 (version "1.28.0")
9067 (source
9068 (origin
9069 (method url-fetch)
9070 (uri (bioconductor-uri "DESeq" version))
9071 (sha256
9072 (base32
9073 "0j3dgcxd64m9qknmlcbdzvg4xhp981xd6nbwsvnqjfn6yypslgyw"))))
9074 (properties `((upstream-name . "DESeq")))
9075 (build-system r-build-system)
9076 (propagated-inputs
9077 `(("r-biobase" ,r-biobase)
9078 ("r-biocgenerics" ,r-biocgenerics)
9079 ("r-genefilter" ,r-genefilter)
9080 ("r-geneplotter" ,r-geneplotter)
9081 ("r-lattice" ,r-lattice)
9082 ("r-locfit" ,r-locfit)
9083 ("r-mass" ,r-mass)
9084 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9085 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9086 (synopsis "Differential gene expression analysis")
9087 (description
9088 "This package provides tools for estimating variance-mean dependence in
9089 count data from high-throughput genetic sequencing assays and for testing for
9090 differential expression based on a model using the negative binomial
9091 distribution.")
9092 (license license:gpl3+)))
9093
9094 (define-public r-edaseq
9095 (package
9096 (name "r-edaseq")
9097 (version "2.10.0")
9098 (source
9099 (origin
9100 (method url-fetch)
9101 (uri (bioconductor-uri "EDASeq" version))
9102 (sha256
9103 (base32
9104 "0f25dfc8hdii9fjm3bf89vy9jkxv23sa62fkcga5b4gkipwrvm9a"))))
9105 (properties `((upstream-name . "EDASeq")))
9106 (build-system r-build-system)
9107 (propagated-inputs
9108 `(("r-annotationdbi" ,r-annotationdbi)
9109 ("r-aroma-light" ,r-aroma-light)
9110 ("r-biobase" ,r-biobase)
9111 ("r-biocgenerics" ,r-biocgenerics)
9112 ("r-biomart" ,r-biomart)
9113 ("r-biostrings" ,r-biostrings)
9114 ("r-deseq" ,r-deseq)
9115 ("r-genomicfeatures" ,r-genomicfeatures)
9116 ("r-genomicranges" ,r-genomicranges)
9117 ("r-iranges" ,r-iranges)
9118 ("r-rsamtools" ,r-rsamtools)
9119 ("r-shortread" ,r-shortread)))
9120 (home-page "https://github.com/drisso/EDASeq")
9121 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9122 (description
9123 "This package provides support for numerical and graphical summaries of
9124 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9125 adjust for GC-content effect (or other gene-level effects) on read counts:
9126 loess robust local regression, global-scaling, and full-quantile
9127 normalization. Between-lane normalization procedures to adjust for
9128 distributional differences between lanes (e.g., sequencing depth):
9129 global-scaling and full-quantile normalization.")
9130 (license license:artistic2.0)))
9131
9132 (define htslib-for-sambamba
9133 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
9134 (package
9135 (inherit htslib)
9136 (name "htslib-for-sambamba")
9137 (version (string-append "1.3.1-1." (string-take commit 9)))
9138 (source
9139 (origin
9140 (method git-fetch)
9141 (uri (git-reference
9142 (url "https://github.com/lomereiter/htslib.git")
9143 (commit commit)))
9144 (file-name (string-append "htslib-" version "-checkout"))
9145 (sha256
9146 (base32
9147 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
9148 (arguments
9149 (substitute-keyword-arguments (package-arguments htslib)
9150 ((#:phases phases)
9151 `(modify-phases ,phases
9152 (add-before 'configure 'bootstrap
9153 (lambda _
9154 (zero? (system* "autoreconf" "-vif"))))))))
9155 (native-inputs
9156 `(("autoconf" ,autoconf)
9157 ("automake" ,automake)
9158 ,@(package-native-inputs htslib))))))
9159
9160 (define-public sambamba
9161 (package
9162 (name "sambamba")
9163 (version "0.6.5")
9164 (source
9165 (origin
9166 (method url-fetch)
9167 (uri (string-append "https://github.com/lomereiter/sambamba/"
9168 "archive/v" version ".tar.gz"))
9169 (file-name (string-append name "-" version ".tar.gz"))
9170 (sha256
9171 (base32
9172 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
9173 (build-system gnu-build-system)
9174 (arguments
9175 `(#:tests? #f ; there is no test target
9176 #:make-flags
9177 '("D_COMPILER=ldc2"
9178 ;; Override "--compiler" flag only.
9179 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
9180 "sambamba-ldmd2-64")
9181 #:phases
9182 (modify-phases %standard-phases
9183 (delete 'configure)
9184 (add-after 'unpack 'place-biod
9185 (lambda* (#:key inputs #:allow-other-keys)
9186 (copy-recursively (assoc-ref inputs "biod") "BioD")
9187 #t))
9188 (add-after 'unpack 'unbundle-prerequisites
9189 (lambda _
9190 (substitute* "Makefile"
9191 ((" htslib-static lz4-static") ""))
9192 #t))
9193 (replace 'install
9194 (lambda* (#:key outputs #:allow-other-keys)
9195 (let* ((out (assoc-ref outputs "out"))
9196 (bin (string-append out "/bin")))
9197 (mkdir-p bin)
9198 (install-file "build/sambamba" bin)
9199 #t))))))
9200 (native-inputs
9201 `(("ldc" ,ldc)
9202 ("rdmd" ,rdmd)
9203 ("biod"
9204 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
9205 (origin
9206 (method git-fetch)
9207 (uri (git-reference
9208 (url "https://github.com/biod/BioD.git")
9209 (commit commit)))
9210 (file-name (string-append "biod-"
9211 (string-take commit 9)
9212 "-checkout"))
9213 (sha256
9214 (base32
9215 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
9216 (inputs
9217 `(("lz4" ,lz4)
9218 ("htslib" ,htslib-for-sambamba)))
9219 (home-page "http://lomereiter.github.io/sambamba")
9220 (synopsis "Tools for working with SAM/BAM data")
9221 (description "Sambamba is a high performance modern robust and
9222 fast tool (and library), written in the D programming language, for
9223 working with SAM and BAM files. Current parallelised functionality is
9224 an important subset of samtools functionality, including view, index,
9225 sort, markdup, and depth.")
9226 (license license:gpl2+)))
9227
9228 (define-public ritornello
9229 (package
9230 (name "ritornello")
9231 (version "1.0.0")
9232 (source (origin
9233 (method url-fetch)
9234 (uri (string-append "https://github.com/KlugerLab/"
9235 "Ritornello/archive/v"
9236 version ".tar.gz"))
9237 (file-name (string-append name "-" version ".tar.gz"))
9238 (sha256
9239 (base32
9240 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
9241 (build-system gnu-build-system)
9242 (arguments
9243 `(#:tests? #f ; there are no tests
9244 #:phases
9245 (modify-phases %standard-phases
9246 (add-after 'unpack 'patch-samtools-references
9247 (lambda* (#:key inputs #:allow-other-keys)
9248 (substitute* '("src/SamStream.h"
9249 "src/BufferedGenomeReader.h")
9250 (("<sam.h>") "<samtools/sam.h>"))
9251 #t))
9252 (delete 'configure)
9253 (replace 'install
9254 (lambda* (#:key inputs outputs #:allow-other-keys)
9255 (let* ((out (assoc-ref outputs "out"))
9256 (bin (string-append out "/bin/")))
9257 (mkdir-p bin)
9258 (install-file "bin/Ritornello" bin)
9259 #t))))))
9260 (inputs
9261 `(("samtools" ,samtools-0.1)
9262 ("fftw" ,fftw)
9263 ("boost" ,boost)
9264 ("zlib" ,zlib)))
9265 (home-page "https://github.com/KlugerLab/Ritornello")
9266 (synopsis "Control-free peak caller for ChIP-seq data")
9267 (description "Ritornello is a ChIP-seq peak calling algorithm based on
9268 signal processing that can accurately call binding events without the need to
9269 do a pair total DNA input or IgG control sample. It has been tested for use
9270 with narrow binding events such as transcription factor ChIP-seq.")
9271 (license license:gpl3+)))
9272
9273 (define-public trim-galore
9274 (package
9275 (name "trim-galore")
9276 (version "0.4.2")
9277 (source
9278 (origin
9279 (method url-fetch)
9280 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
9281 "projects/trim_galore/trim_galore_v"
9282 version ".zip"))
9283 (sha256
9284 (base32
9285 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
9286 (build-system gnu-build-system)
9287 (arguments
9288 `(#:tests? #f ; no tests
9289 #:phases
9290 (modify-phases %standard-phases
9291 ;; The archive contains plain files.
9292 (replace 'unpack
9293 (lambda* (#:key source #:allow-other-keys)
9294 (zero? (system* "unzip" source))))
9295 (delete 'configure)
9296 (delete 'build)
9297 (add-after 'unpack 'hardcode-tool-references
9298 (lambda* (#:key inputs #:allow-other-keys)
9299 (substitute* "trim_galore"
9300 (("\\$path_to_cutadapt = 'cutadapt'")
9301 (string-append "$path_to_cutadapt = '"
9302 (assoc-ref inputs "cutadapt")
9303 "/bin/cutadapt'"))
9304 (("\\| gzip")
9305 (string-append "| "
9306 (assoc-ref inputs "gzip")
9307 "/bin/gzip"))
9308 (("\"gunzip")
9309 (string-append "\""
9310 (assoc-ref inputs "gzip")
9311 "/bin/gunzip")))
9312 #t))
9313 (replace 'install
9314 (lambda* (#:key outputs #:allow-other-keys)
9315 (let ((bin (string-append (assoc-ref outputs "out")
9316 "/bin")))
9317 (mkdir-p bin)
9318 (install-file "trim_galore" bin)
9319 #t))))))
9320 (inputs
9321 `(("gzip" ,gzip)
9322 ("perl" ,perl)
9323 ("cutadapt" ,cutadapt)))
9324 (native-inputs
9325 `(("unzip" ,unzip)))
9326 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
9327 (synopsis "Wrapper around Cutadapt and FastQC")
9328 (description "Trim Galore! is a wrapper script to automate quality and
9329 adapter trimming as well as quality control, with some added functionality to
9330 remove biased methylation positions for RRBS sequence files.")
9331 (license license:gpl3+)))
9332
9333 (define-public gess
9334 (package
9335 (name "gess")
9336 (version "1.0")
9337 (source (origin
9338 (method url-fetch)
9339 (uri (string-append "http://compbio.uthscsa.edu/"
9340 "GESS_Web/files/"
9341 "gess-" version ".src.tar.gz"))
9342 (sha256
9343 (base32
9344 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
9345 (build-system gnu-build-system)
9346 (arguments
9347 `(#:tests? #f ; no tests
9348 #:phases
9349 (modify-phases %standard-phases
9350 (delete 'configure)
9351 (delete 'build)
9352 (replace 'install
9353 (lambda* (#:key inputs outputs #:allow-other-keys)
9354 (let* ((python (assoc-ref inputs "python"))
9355 (out (assoc-ref outputs "out"))
9356 (bin (string-append out "/bin/"))
9357 (target (string-append
9358 out "/lib/python2.7/site-packages/gess/")))
9359 (mkdir-p target)
9360 (copy-recursively "." target)
9361 ;; Make GESS.py executable
9362 (chmod (string-append target "GESS.py") #o555)
9363 ;; Add Python shebang to the top and make Matplotlib
9364 ;; usable.
9365 (substitute* (string-append target "GESS.py")
9366 (("\"\"\"Description:" line)
9367 (string-append "#!" (which "python") "
9368 import matplotlib
9369 matplotlib.use('Agg')
9370 " line)))
9371 ;; Make sure GESS has all modules in its path
9372 (wrap-program (string-append target "GESS.py")
9373 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
9374 (mkdir-p bin)
9375 (symlink (string-append target "GESS.py")
9376 (string-append bin "GESS.py"))
9377 #t))))))
9378 (inputs
9379 `(("python" ,python-2)
9380 ("python2-pysam" ,python2-pysam)
9381 ("python2-scipy" ,python2-scipy)
9382 ("python2-numpy" ,python2-numpy)
9383 ("python2-networkx" ,python2-networkx)
9384 ("python2-biopython" ,python2-biopython)))
9385 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
9386 (synopsis "Detect exon-skipping events from raw RNA-seq data")
9387 (description
9388 "GESS is an implementation of a novel computational method to detect de
9389 novo exon-skipping events directly from raw RNA-seq data without the prior
9390 knowledge of gene annotation information. GESS stands for the graph-based
9391 exon-skipping scanner detection scheme.")
9392 (license license:bsd-3)))
9393
9394 (define-public phylip
9395 (package
9396 (name "phylip")
9397 (version "3.696")
9398 (source
9399 (origin
9400 (method url-fetch)
9401 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
9402 "download/phylip-" version ".tar.gz"))
9403 (sha256
9404 (base32
9405 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
9406 (build-system gnu-build-system)
9407 (arguments
9408 `(#:tests? #f ; no check target
9409 #:make-flags (list "-f" "Makefile.unx" "install")
9410 #:parallel-build? #f ; not supported
9411 #:phases
9412 (modify-phases %standard-phases
9413 (add-after 'unpack 'enter-dir
9414 (lambda _ (chdir "src") #t))
9415 (delete 'configure)
9416 (replace 'install
9417 (lambda* (#:key inputs outputs #:allow-other-keys)
9418 (let ((target (string-append (assoc-ref outputs "out")
9419 "/bin")))
9420 (mkdir-p target)
9421 (for-each (lambda (file)
9422 (install-file file target))
9423 (find-files "../exe" ".*")))
9424 #t)))))
9425 (home-page "http://evolution.genetics.washington.edu/phylip/")
9426 (synopsis "Tools for inferring phylogenies")
9427 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
9428 programs for inferring phylogenies (evolutionary trees).")
9429 (license license:bsd-2)))
9430
9431 (define-public imp
9432 (package
9433 (name "imp")
9434 (version "2.6.2")
9435 (source
9436 (origin
9437 (method url-fetch)
9438 (uri (string-append "https://integrativemodeling.org/"
9439 version "/download/imp-" version ".tar.gz"))
9440 (sha256
9441 (base32
9442 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
9443 (build-system cmake-build-system)
9444 (arguments
9445 `(;; FIXME: Some tests fail because they produce warnings, others fail
9446 ;; because the PYTHONPATH does not include the modeller's directory.
9447 #:tests? #f
9448 ;; Do not place libraries in an architecture-specific directory.
9449 #:configure-flags
9450 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
9451 (inputs
9452 `(("boost" ,boost)
9453 ("gsl" ,gsl)
9454 ("swig" ,swig)
9455 ("hdf5" ,hdf5)
9456 ("fftw" ,fftw)
9457 ("python" ,python-2)))
9458 (propagated-inputs
9459 `(("python2-numpy" ,python2-numpy)
9460 ("python2-scipy" ,python2-scipy)
9461 ("python2-pandas" ,python2-pandas)
9462 ("python2-scikit-learn" ,python2-scikit-learn)
9463 ("python2-networkx" ,python2-networkx)))
9464 (home-page "https://integrativemodeling.org")
9465 (synopsis "Integrative modeling platform")
9466 (description "IMP's broad goal is to contribute to a comprehensive
9467 structural characterization of biomolecules ranging in size and complexity
9468 from small peptides to large macromolecular assemblies, by integrating data
9469 from diverse biochemical and biophysical experiments. IMP provides a C++ and
9470 Python toolbox for solving complex modeling problems, and a number of
9471 applications for tackling some common problems in a user-friendly way.")
9472 ;; IMP is largely available under the GNU Lesser GPL; see the file
9473 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
9474 ;; available under the GNU GPL (see the file COPYING.GPL).
9475 (license (list license:lgpl2.1+
9476 license:gpl3+))))