gnu: Add java-htsjdk-2.10.1.
[jackhill/guix/guix.git] / gnu / packages / bioinformatics.scm
1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 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, 2017, 2018 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;;
13 ;;; This file is part of GNU Guix.
14 ;;;
15 ;;; GNU Guix is free software; you can redistribute it and/or modify it
16 ;;; under the terms of the GNU General Public License as published by
17 ;;; the Free Software Foundation; either version 3 of the License, or (at
18 ;;; your option) any later version.
19 ;;;
20 ;;; GNU Guix is distributed in the hope that it will be useful, but
21 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
22 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23 ;;; GNU General Public License for more details.
24 ;;;
25 ;;; You should have received a copy of the GNU General Public License
26 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
27
28 (define-module (gnu packages bioinformatics)
29 #:use-module ((guix licenses) #:prefix license:)
30 #:use-module (guix packages)
31 #:use-module (guix utils)
32 #:use-module (guix download)
33 #:use-module (guix git-download)
34 #:use-module (guix hg-download)
35 #:use-module (guix build-system ant)
36 #:use-module (guix build-system gnu)
37 #:use-module (guix build-system cmake)
38 #:use-module (guix build-system ocaml)
39 #:use-module (guix build-system perl)
40 #:use-module (guix build-system python)
41 #:use-module (guix build-system r)
42 #:use-module (guix build-system ruby)
43 #:use-module (guix build-system scons)
44 #:use-module (guix build-system trivial)
45 #:use-module (gnu packages)
46 #:use-module (gnu packages autotools)
47 #:use-module (gnu packages algebra)
48 #:use-module (gnu packages base)
49 #:use-module (gnu packages bash)
50 #:use-module (gnu packages bison)
51 #:use-module (gnu packages boost)
52 #:use-module (gnu packages check)
53 #:use-module (gnu packages compression)
54 #:use-module (gnu packages cpio)
55 #:use-module (gnu packages cran)
56 #:use-module (gnu packages curl)
57 #:use-module (gnu packages documentation)
58 #:use-module (gnu packages databases)
59 #:use-module (gnu packages datastructures)
60 #:use-module (gnu packages file)
61 #:use-module (gnu packages flex)
62 #:use-module (gnu packages gawk)
63 #:use-module (gnu packages gcc)
64 #:use-module (gnu packages gd)
65 #:use-module (gnu packages gtk)
66 #:use-module (gnu packages glib)
67 #:use-module (gnu packages graph)
68 #:use-module (gnu packages groff)
69 #:use-module (gnu packages guile)
70 #:use-module (gnu packages haskell)
71 #:use-module (gnu packages image)
72 #:use-module (gnu packages imagemagick)
73 #:use-module (gnu packages java)
74 #:use-module (gnu packages jemalloc)
75 #:use-module (gnu packages ldc)
76 #:use-module (gnu packages linux)
77 #:use-module (gnu packages logging)
78 #:use-module (gnu packages machine-learning)
79 #:use-module (gnu packages man)
80 #:use-module (gnu packages maths)
81 #:use-module (gnu packages mpi)
82 #:use-module (gnu packages ncurses)
83 #:use-module (gnu packages ocaml)
84 #:use-module (gnu packages pcre)
85 #:use-module (gnu packages parallel)
86 #:use-module (gnu packages pdf)
87 #:use-module (gnu packages perl)
88 #:use-module (gnu packages perl-check)
89 #:use-module (gnu packages pkg-config)
90 #:use-module (gnu packages popt)
91 #:use-module (gnu packages protobuf)
92 #:use-module (gnu packages python)
93 #:use-module (gnu packages python-web)
94 #:use-module (gnu packages readline)
95 #:use-module (gnu packages ruby)
96 #:use-module (gnu packages serialization)
97 #:use-module (gnu packages shells)
98 #:use-module (gnu packages statistics)
99 #:use-module (gnu packages swig)
100 #:use-module (gnu packages tbb)
101 #:use-module (gnu packages tex)
102 #:use-module (gnu packages texinfo)
103 #:use-module (gnu packages textutils)
104 #:use-module (gnu packages time)
105 #:use-module (gnu packages tls)
106 #:use-module (gnu packages vim)
107 #:use-module (gnu packages web)
108 #:use-module (gnu packages xml)
109 #:use-module (gnu packages xorg)
110 #:use-module (srfi srfi-1)
111 #:use-module (ice-9 match))
112
113 (define-public r-ape
114 (package
115 (name "r-ape")
116 (version "5.0")
117 (source
118 (origin
119 (method url-fetch)
120 (uri (cran-uri "ape" version))
121 (sha256
122 (base32
123 "0q59pmxawz498cb9mv5m49lhiwxib8ak94yyydz7qg8b6lpd4bn3"))))
124 (build-system r-build-system)
125 (propagated-inputs
126 `(("r-lattice" ,r-lattice)
127 ("r-nlme" ,r-nlme)
128 ("r-rcpp" ,r-rcpp)))
129 (home-page "http://ape-package.ird.fr/")
130 (synopsis "Analyses of phylogenetics and evolution")
131 (description
132 "This package provides functions for reading, writing, plotting, and
133 manipulating phylogenetic trees, analyses of comparative data in a
134 phylogenetic framework, ancestral character analyses, analyses of
135 diversification and macroevolution, computing distances from DNA sequences,
136 and several other tools.")
137 (license license:gpl2+)))
138
139 (define-public aragorn
140 (package
141 (name "aragorn")
142 (version "1.2.38")
143 (source (origin
144 (method url-fetch)
145 (uri (string-append
146 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
147 version ".tgz"))
148 (sha256
149 (base32
150 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
151 (build-system gnu-build-system)
152 (arguments
153 `(#:tests? #f ; there are no tests
154 #:phases
155 (modify-phases %standard-phases
156 (delete 'configure)
157 (replace 'build
158 (lambda _
159 (zero? (system* "gcc"
160 "-O3"
161 "-ffast-math"
162 "-finline-functions"
163 "-o"
164 "aragorn"
165 (string-append "aragorn" ,version ".c")))))
166 (replace 'install
167 (lambda* (#:key outputs #:allow-other-keys)
168 (let* ((out (assoc-ref outputs "out"))
169 (bin (string-append out "/bin"))
170 (man (string-append out "/share/man/man1")))
171 (mkdir-p bin)
172 (install-file "aragorn" bin)
173 (mkdir-p man)
174 (install-file "aragorn.1" man))
175 #t)))))
176 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
177 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
178 (description
179 "Aragorn identifies transfer RNA, mitochondrial RNA and
180 transfer-messenger RNA from nucleotide sequences, based on homology to known
181 tRNA consensus sequences and RNA structure. It also outputs the secondary
182 structure of the predicted RNA.")
183 (license license:gpl2)))
184
185 (define-public bamm
186 (package
187 (name "bamm")
188 (version "1.7.3")
189 (source (origin
190 (method url-fetch)
191 ;; BamM is not available on pypi.
192 (uri (string-append
193 "https://github.com/Ecogenomics/BamM/archive/"
194 version ".tar.gz"))
195 (file-name (string-append name "-" version ".tar.gz"))
196 (sha256
197 (base32
198 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
199 (modules '((guix build utils)))
200 (snippet
201 `(begin
202 ;; Delete bundled htslib.
203 (delete-file-recursively "c/htslib-1.3.1")
204 #t))))
205 (build-system python-build-system)
206 (arguments
207 `(#:python ,python-2 ; BamM is Python 2 only.
208 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
209 ;; been modified from its original form.
210 #:configure-flags
211 (let ((htslib (assoc-ref %build-inputs "htslib")))
212 (list "--with-libhts-lib" (string-append htslib "/lib")
213 "--with-libhts-inc" (string-append htslib "/include/htslib")))
214 #:phases
215 (modify-phases %standard-phases
216 (add-after 'unpack 'autogen
217 (lambda _
218 (with-directory-excursion "c"
219 (let ((sh (which "sh")))
220 ;; Use autogen so that 'configure' works.
221 (substitute* "autogen.sh" (("/bin/sh") sh))
222 (setenv "CONFIG_SHELL" sh)
223 (substitute* "configure" (("/bin/sh") sh))
224 (zero? (system* "./autogen.sh"))))))
225 (delete 'build)
226 ;; Run tests after installation so compilation only happens once.
227 (delete 'check)
228 (add-after 'install 'wrap-executable
229 (lambda* (#:key outputs #:allow-other-keys)
230 (let* ((out (assoc-ref outputs "out"))
231 (path (getenv "PATH")))
232 (wrap-program (string-append out "/bin/bamm")
233 `("PATH" ":" prefix (,path))))
234 #t))
235 (add-after 'wrap-executable 'post-install-check
236 (lambda* (#:key inputs outputs #:allow-other-keys)
237 (setenv "PATH"
238 (string-append (assoc-ref outputs "out")
239 "/bin:"
240 (getenv "PATH")))
241 (setenv "PYTHONPATH"
242 (string-append
243 (assoc-ref outputs "out")
244 "/lib/python"
245 (string-take (string-take-right
246 (assoc-ref inputs "python") 5) 3)
247 "/site-packages:"
248 (getenv "PYTHONPATH")))
249 ;; There are 2 errors printed, but they are safe to ignore:
250 ;; 1) [E::hts_open_format] fail to open file ...
251 ;; 2) samtools view: failed to open ...
252 (zero? (system* "nosetests")))))))
253 (native-inputs
254 `(("autoconf" ,autoconf)
255 ("automake" ,automake)
256 ("libtool" ,libtool)
257 ("zlib" ,zlib)
258 ("python-nose" ,python2-nose)
259 ("python-pysam" ,python2-pysam)))
260 (inputs
261 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
262 ("samtools" ,samtools)
263 ("bwa" ,bwa)
264 ("grep" ,grep)
265 ("sed" ,sed)
266 ("coreutils" ,coreutils)))
267 (propagated-inputs
268 `(("python-numpy" ,python2-numpy)))
269 (home-page "http://ecogenomics.github.io/BamM/")
270 (synopsis "Metagenomics-focused BAM file manipulator")
271 (description
272 "BamM is a C library, wrapped in python, to efficiently generate and
273 parse BAM files, specifically for the analysis of metagenomic data. For
274 instance, it implements several methods to assess contig-wise read coverage.")
275 (license license:lgpl3+)))
276
277 (define-public bamtools
278 (package
279 (name "bamtools")
280 (version "2.4.1")
281 (source (origin
282 (method url-fetch)
283 (uri (string-append
284 "https://github.com/pezmaster31/bamtools/archive/v"
285 version ".tar.gz"))
286 (file-name (string-append name "-" version ".tar.gz"))
287 (sha256
288 (base32
289 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
290 (build-system cmake-build-system)
291 (arguments
292 `(#:tests? #f ;no "check" target
293 #:phases
294 (modify-phases %standard-phases
295 (add-before
296 'configure 'set-ldflags
297 (lambda* (#:key outputs #:allow-other-keys)
298 (setenv "LDFLAGS"
299 (string-append
300 "-Wl,-rpath="
301 (assoc-ref outputs "out") "/lib/bamtools")))))))
302 (inputs `(("zlib" ,zlib)))
303 (home-page "https://github.com/pezmaster31/bamtools")
304 (synopsis "C++ API and command-line toolkit for working with BAM data")
305 (description
306 "BamTools provides both a C++ API and a command-line toolkit for handling
307 BAM files.")
308 (license license:expat)))
309
310 (define-public bcftools
311 (package
312 (name "bcftools")
313 (version "1.5")
314 (source (origin
315 (method url-fetch)
316 (uri (string-append
317 "https://github.com/samtools/bcftools/releases/download/"
318 version "/bcftools-" version ".tar.bz2"))
319 (sha256
320 (base32
321 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
322 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
323 (modules '((guix build utils)))
324 (snippet
325 ;; Delete bundled htslib.
326 '(delete-file-recursively "htslib-1.5"))))
327 (build-system gnu-build-system)
328 (arguments
329 `(#:test-target "test"
330 #:configure-flags (list "--with-htslib=system")
331 #:make-flags
332 (list
333 "USE_GPL=1"
334 "LIBS=-lgsl -lgslcblas"
335 (string-append "prefix=" (assoc-ref %outputs "out"))
336 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
337 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
338 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
339 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
340 (string-append "PACKAGE_VERSION=" ,version))
341 #:phases
342 (modify-phases %standard-phases
343 (add-before 'check 'patch-tests
344 (lambda _
345 (substitute* "test/test.pl"
346 (("/bin/bash") (which "bash")))
347 #t)))))
348 (native-inputs
349 `(("htslib" ,htslib)
350 ("perl" ,perl)))
351 (inputs
352 `(("gsl" ,gsl)
353 ("zlib" ,zlib)))
354 (home-page "https://samtools.github.io/bcftools/")
355 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
356 (description
357 "BCFtools is a set of utilities that manipulate variant calls in the
358 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
359 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
360 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
361 (license (list license:gpl3+ license:expat))))
362
363 (define-public bedops
364 (package
365 (name "bedops")
366 (version "2.4.14")
367 (source (origin
368 (method url-fetch)
369 (uri (string-append "https://github.com/bedops/bedops/archive/v"
370 version ".tar.gz"))
371 (file-name (string-append name "-" version ".tar.gz"))
372 (sha256
373 (base32
374 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
375 (build-system gnu-build-system)
376 (arguments
377 '(#:tests? #f
378 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
379 #:phases
380 (modify-phases %standard-phases
381 (add-after 'unpack 'unpack-tarballs
382 (lambda _
383 ;; FIXME: Bedops includes tarballs of minimally patched upstream
384 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
385 ;; libraries because at least one of the libraries (zlib) is
386 ;; patched to add a C++ function definition (deflateInit2cpp).
387 ;; Until the Bedops developers offer a way to link against system
388 ;; libraries we have to build the in-tree copies of these three
389 ;; libraries.
390
391 ;; See upstream discussion:
392 ;; https://github.com/bedops/bedops/issues/124
393
394 ;; Unpack the tarballs to benefit from shebang patching.
395 (with-directory-excursion "third-party"
396 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
397 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
398 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
399 ;; Disable unpacking of tarballs in Makefile.
400 (substitute* "system.mk/Makefile.linux"
401 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
402 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
403 (substitute* "third-party/zlib-1.2.7/Makefile.in"
404 (("^SHELL=.*$") "SHELL=bash\n"))
405 #t))
406 (delete 'configure))))
407 (home-page "https://github.com/bedops/bedops")
408 (synopsis "Tools for high-performance genomic feature operations")
409 (description
410 "BEDOPS is a suite of tools to address common questions raised in genomic
411 studies---mostly with regard to overlap and proximity relationships between
412 data sets. It aims to be scalable and flexible, facilitating the efficient
413 and accurate analysis and management of large-scale genomic data.
414
415 BEDOPS provides tools that perform highly efficient and scalable Boolean and
416 other set operations, statistical calculations, archiving, conversion and
417 other management of genomic data of arbitrary scale. Tasks can be easily
418 split by chromosome for distributing whole-genome analyses across a
419 computational cluster.")
420 (license license:gpl2+)))
421
422 (define-public bedtools
423 (package
424 (name "bedtools")
425 (version "2.27.1")
426 (source (origin
427 (method url-fetch)
428 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
429 "download/v" version "/"
430 "bedtools-" version ".tar.gz"))
431 (sha256
432 (base32
433 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
434 (build-system gnu-build-system)
435 (arguments
436 '(#:test-target "test"
437 #:make-flags
438 (list (string-append "prefix=" (assoc-ref %outputs "out")))
439 #:phases
440 (modify-phases %standard-phases
441 (delete 'configure))))
442 (native-inputs `(("python" ,python-2)))
443 (inputs
444 `(("samtools" ,samtools)
445 ("zlib" ,zlib)))
446 (home-page "https://github.com/arq5x/bedtools2")
447 (synopsis "Tools for genome analysis and arithmetic")
448 (description
449 "Collectively, the bedtools utilities are a swiss-army knife of tools for
450 a wide-range of genomics analysis tasks. The most widely-used tools enable
451 genome arithmetic: that is, set theory on the genome. For example, bedtools
452 allows one to intersect, merge, count, complement, and shuffle genomic
453 intervals from multiple files in widely-used genomic file formats such as BAM,
454 BED, GFF/GTF, VCF.")
455 (license license:gpl2)))
456
457 ;; Later releases of bedtools produce files with more columns than
458 ;; what Ribotaper expects.
459 (define-public bedtools-2.18
460 (package (inherit bedtools)
461 (name "bedtools")
462 (version "2.18.0")
463 (source (origin
464 (method url-fetch)
465 (uri (string-append "https://github.com/arq5x/bedtools2/"
466 "archive/v" version ".tar.gz"))
467 (file-name (string-append name "-" version ".tar.gz"))
468 (sha256
469 (base32
470 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))
471 (arguments
472 '(#:test-target "test"
473 #:phases
474 (modify-phases %standard-phases
475 (delete 'configure)
476 (replace 'install
477 (lambda* (#:key outputs #:allow-other-keys)
478 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
479 (for-each (lambda (file)
480 (install-file file bin))
481 (find-files "bin" ".*")))
482 #t)))))))
483
484 (define-public ribotaper
485 (package
486 (name "ribotaper")
487 (version "1.3.1")
488 (source (origin
489 (method url-fetch)
490 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
491 "files/RiboTaper/RiboTaper_Version_"
492 version ".tar.gz"))
493 (sha256
494 (base32
495 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
496 (build-system gnu-build-system)
497 (arguments
498 `(#:phases
499 (modify-phases %standard-phases
500 (add-after 'install 'wrap-executables
501 (lambda* (#:key inputs outputs #:allow-other-keys)
502 (let* ((out (assoc-ref outputs "out")))
503 (for-each
504 (lambda (script)
505 (wrap-program (string-append out "/bin/" script)
506 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
507 '("create_annotations_files.bash"
508 "create_metaplots.bash"
509 "Ribotaper_ORF_find.sh"
510 "Ribotaper.sh"))))))))
511 (inputs
512 `(("bedtools" ,bedtools-2.18)
513 ("samtools" ,samtools-0.1)
514 ("r-minimal" ,r-minimal)
515 ("r-foreach" ,r-foreach)
516 ("r-xnomial" ,r-xnomial)
517 ("r-domc" ,r-domc)
518 ("r-multitaper" ,r-multitaper)
519 ("r-seqinr" ,r-seqinr)))
520 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
521 (synopsis "Define translated ORFs using ribosome profiling data")
522 (description
523 "Ribotaper is a method for defining translated @dfn{open reading
524 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
525 provides the Ribotaper pipeline.")
526 (license license:gpl3+)))
527
528 (define-public ribodiff
529 (package
530 (name "ribodiff")
531 (version "0.2.2")
532 (source
533 (origin
534 (method url-fetch)
535 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
536 "archive/v" version ".tar.gz"))
537 (file-name (string-append name "-" version ".tar.gz"))
538 (sha256
539 (base32
540 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
541 (build-system python-build-system)
542 (arguments
543 `(#:python ,python-2
544 #:phases
545 (modify-phases %standard-phases
546 ;; Generate an installable executable script wrapper.
547 (add-after 'unpack 'patch-setup.py
548 (lambda _
549 (substitute* "setup.py"
550 (("^(.*)packages=.*" line prefix)
551 (string-append line "\n"
552 prefix "scripts=['scripts/TE.py'],\n")))
553 #t)))))
554 (inputs
555 `(("python-numpy" ,python2-numpy)
556 ("python-matplotlib" ,python2-matplotlib)
557 ("python-scipy" ,python2-scipy)
558 ("python-statsmodels" ,python2-statsmodels)))
559 (native-inputs
560 `(("python-mock" ,python2-mock)
561 ("python-nose" ,python2-nose)))
562 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
563 (synopsis "Detect translation efficiency changes from ribosome footprints")
564 (description "RiboDiff is a statistical tool that detects the protein
565 translational efficiency change from Ribo-Seq (ribosome footprinting) and
566 RNA-Seq data. It uses a generalized linear model to detect genes showing
567 difference in translational profile taking mRNA abundance into account. It
568 facilitates us to decipher the translational regulation that behave
569 independently with transcriptional regulation.")
570 (license license:gpl3+)))
571
572 (define-public bioawk
573 (package
574 (name "bioawk")
575 (version "1.0")
576 (source (origin
577 (method url-fetch)
578 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
579 version ".tar.gz"))
580 (file-name (string-append name "-" version ".tar.gz"))
581 (sha256
582 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
583 (build-system gnu-build-system)
584 (inputs
585 `(("zlib" ,zlib)))
586 (native-inputs
587 `(("bison" ,bison)))
588 (arguments
589 `(#:tests? #f ; There are no tests to run.
590 ;; Bison must generate files, before other targets can build.
591 #:parallel-build? #f
592 #:phases
593 (modify-phases %standard-phases
594 (delete 'configure) ; There is no configure phase.
595 (replace 'install
596 (lambda* (#:key outputs #:allow-other-keys)
597 (let* ((out (assoc-ref outputs "out"))
598 (bin (string-append out "/bin"))
599 (man (string-append out "/share/man/man1")))
600 (mkdir-p man)
601 (copy-file "awk.1" (string-append man "/bioawk.1"))
602 (install-file "bioawk" bin)))))))
603 (home-page "https://github.com/lh3/bioawk")
604 (synopsis "AWK with bioinformatics extensions")
605 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
606 support of several common biological data formats, including optionally gzip'ed
607 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
608 also adds a few built-in functions and a command line option to use TAB as the
609 input/output delimiter. When the new functionality is not used, bioawk is
610 intended to behave exactly the same as the original BWK awk.")
611 (license license:x11)))
612
613 (define-public python2-pybedtools
614 (package
615 (name "python2-pybedtools")
616 (version "0.6.9")
617 (source (origin
618 (method url-fetch)
619 (uri (string-append
620 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
621 version ".tar.gz"))
622 (sha256
623 (base32
624 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
625 (build-system python-build-system)
626 (arguments `(#:python ,python-2)) ; no Python 3 support
627 (inputs
628 `(("python-matplotlib" ,python2-matplotlib)))
629 (propagated-inputs
630 `(("bedtools" ,bedtools)
631 ("samtools" ,samtools)))
632 (native-inputs
633 `(("python-cython" ,python2-cython)
634 ("python-pyyaml" ,python2-pyyaml)
635 ("python-nose" ,python2-nose)))
636 (home-page "https://pythonhosted.org/pybedtools/")
637 (synopsis "Python wrapper for BEDtools programs")
638 (description
639 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
640 which are widely used for genomic interval manipulation or \"genome algebra\".
641 pybedtools extends BEDTools by offering feature-level manipulations from with
642 Python.")
643 (license license:gpl2+)))
644
645 (define-public python-biom-format
646 (package
647 (name "python-biom-format")
648 (version "2.1.6")
649 (source
650 (origin
651 (method url-fetch)
652 ;; Use GitHub as source because PyPI distribution does not contain
653 ;; test data: https://github.com/biocore/biom-format/issues/693
654 (uri (string-append "https://github.com/biocore/biom-format/archive/"
655 version ".tar.gz"))
656 (file-name (string-append name "-" version ".tar.gz"))
657 (sha256
658 (base32
659 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
660 (build-system python-build-system)
661 (propagated-inputs
662 `(("python-numpy" ,python-numpy)
663 ("python-scipy" ,python-scipy)
664 ("python-future" ,python-future)
665 ("python-click" ,python-click)
666 ("python-h5py" ,python-h5py)
667 ("python-pandas" ,python-pandas)))
668 (native-inputs
669 `(("python-nose" ,python-nose)))
670 (home-page "http://www.biom-format.org")
671 (synopsis "Biological Observation Matrix (BIOM) format utilities")
672 (description
673 "The BIOM file format is designed to be a general-use format for
674 representing counts of observations e.g. operational taxonomic units, KEGG
675 orthology groups or lipid types, in one or more biological samples
676 e.g. microbiome samples, genomes, metagenomes.")
677 (license license:bsd-3)
678 (properties `((python2-variant . ,(delay python2-biom-format))))))
679
680 (define-public python2-biom-format
681 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
682 (package
683 (inherit base)
684 (arguments
685 `(#:phases
686 (modify-phases %standard-phases
687 ;; Do not require the unmaintained pyqi library.
688 (add-after 'unpack 'remove-pyqi
689 (lambda _
690 (substitute* "setup.py"
691 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
692 #t)))
693 ,@(package-arguments base))))))
694
695 (define-public bioperl-minimal
696 (let* ((inputs `(("perl-module-build" ,perl-module-build)
697 ("perl-data-stag" ,perl-data-stag)
698 ("perl-libwww" ,perl-libwww)
699 ("perl-uri" ,perl-uri)))
700 (transitive-inputs
701 (map (compose package-name cadr)
702 (delete-duplicates
703 (concatenate
704 (map (compose package-transitive-target-inputs cadr) inputs))))))
705 (package
706 (name "bioperl-minimal")
707 (version "1.7.0")
708 (source
709 (origin
710 (method url-fetch)
711 (uri (string-append "https://github.com/bioperl/bioperl-live/"
712 "archive/release-"
713 (string-map (lambda (c)
714 (if (char=? c #\.)
715 #\- c)) version)
716 ".tar.gz"))
717 (sha256
718 (base32
719 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
720 (build-system perl-build-system)
721 (arguments
722 `(#:phases
723 (modify-phases %standard-phases
724 (add-after
725 'install 'wrap-programs
726 (lambda* (#:key outputs #:allow-other-keys)
727 ;; Make sure all executables in "bin" find the required Perl
728 ;; modules at runtime. As the PERL5LIB variable contains also
729 ;; the paths of native inputs, we pick the transitive target
730 ;; inputs from %build-inputs.
731 (let* ((out (assoc-ref outputs "out"))
732 (bin (string-append out "/bin/"))
733 (path (string-join
734 (cons (string-append out "/lib/perl5/site_perl")
735 (map (lambda (name)
736 (assoc-ref %build-inputs name))
737 ',transitive-inputs))
738 ":")))
739 (for-each (lambda (file)
740 (wrap-program file
741 `("PERL5LIB" ":" prefix (,path))))
742 (find-files bin "\\.pl$"))
743 #t))))))
744 (inputs inputs)
745 (native-inputs
746 `(("perl-test-most" ,perl-test-most)))
747 (home-page "http://search.cpan.org/dist/BioPerl")
748 (synopsis "Bioinformatics toolkit")
749 (description
750 "BioPerl is the product of a community effort to produce Perl code which
751 is useful in biology. Examples include Sequence objects, Alignment objects
752 and database searching objects. These objects not only do what they are
753 advertised to do in the documentation, but they also interact - Alignment
754 objects are made from the Sequence objects, Sequence objects have access to
755 Annotation and SeqFeature objects and databases, Blast objects can be
756 converted to Alignment objects, and so on. This means that the objects
757 provide a coordinated and extensible framework to do computational biology.")
758 (license license:perl-license))))
759
760 (define-public python-biopython
761 (package
762 (name "python-biopython")
763 (version "1.70")
764 (source (origin
765 (method url-fetch)
766 ;; use PyPi rather than biopython.org to ease updating
767 (uri (pypi-uri "biopython" version))
768 (sha256
769 (base32
770 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
771 (build-system python-build-system)
772 (arguments
773 `(#:phases
774 (modify-phases %standard-phases
775 (add-before 'check 'set-home
776 ;; Some tests require a home directory to be set.
777 (lambda _ (setenv "HOME" "/tmp") #t)))))
778 (propagated-inputs
779 `(("python-numpy" ,python-numpy)))
780 (home-page "http://biopython.org/")
781 (synopsis "Tools for biological computation in Python")
782 (description
783 "Biopython is a set of tools for biological computation including parsers
784 for bioinformatics files into Python data structures; interfaces to common
785 bioinformatics programs; a standard sequence class and tools for performing
786 common operations on them; code to perform data classification; code for
787 dealing with alignments; code making it easy to split up parallelizable tasks
788 into separate processes; and more.")
789 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
790
791 (define-public python2-biopython
792 (package-with-python2 python-biopython))
793
794 (define-public bpp-core
795 ;; The last release was in 2014 and the recommended way to install from source
796 ;; is to clone the git repository, so we do this.
797 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
798 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
799 (package
800 (name "bpp-core")
801 (version (string-append "2.2.0-1." (string-take commit 7)))
802 (source (origin
803 (method git-fetch)
804 (uri (git-reference
805 (url "http://biopp.univ-montp2.fr/git/bpp-core")
806 (commit commit)))
807 (file-name (string-append name "-" version "-checkout"))
808 (sha256
809 (base32
810 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
811 (build-system cmake-build-system)
812 (arguments
813 `(#:parallel-build? #f))
814 (inputs
815 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
816 ; compile all of the bpp packages with GCC 5.
817 (home-page "http://biopp.univ-montp2.fr")
818 (synopsis "C++ libraries for Bioinformatics")
819 (description
820 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
821 analysis, phylogenetics, molecular evolution and population genetics. It is
822 Object Oriented and is designed to be both easy to use and computer efficient.
823 Bio++ intends to help programmers to write computer expensive programs, by
824 providing them a set of re-usable tools.")
825 (license license:cecill-c))))
826
827 (define-public bpp-phyl
828 ;; The last release was in 2014 and the recommended way to install from source
829 ;; is to clone the git repository, so we do this.
830 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
831 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
832 (package
833 (name "bpp-phyl")
834 (version (string-append "2.2.0-1." (string-take commit 7)))
835 (source (origin
836 (method git-fetch)
837 (uri (git-reference
838 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
839 (commit commit)))
840 (file-name (string-append name "-" version "-checkout"))
841 (sha256
842 (base32
843 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
844 (build-system cmake-build-system)
845 (arguments
846 `(#:parallel-build? #f
847 ;; If out-of-source, test data is not copied into the build directory
848 ;; so the tests fail.
849 #:out-of-source? #f))
850 (inputs
851 `(("bpp-core" ,bpp-core)
852 ("bpp-seq" ,bpp-seq)
853 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
854 ;; modern GCC.
855 ("gcc" ,gcc-5)))
856 (home-page "http://biopp.univ-montp2.fr")
857 (synopsis "Bio++ phylogenetic Library")
858 (description
859 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
860 analysis, phylogenetics, molecular evolution and population genetics. This
861 library provides phylogenetics-related modules.")
862 (license license:cecill-c))))
863
864 (define-public bpp-popgen
865 ;; The last release was in 2014 and the recommended way to install from source
866 ;; is to clone the git repository, so we do this.
867 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
868 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
869 (package
870 (name "bpp-popgen")
871 (version (string-append "2.2.0-1." (string-take commit 7)))
872 (source (origin
873 (method git-fetch)
874 (uri (git-reference
875 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
876 (commit commit)))
877 (file-name (string-append name "-" version "-checkout"))
878 (sha256
879 (base32
880 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
881 (build-system cmake-build-system)
882 (arguments
883 `(#:parallel-build? #f
884 #:tests? #f)) ; There are no tests.
885 (inputs
886 `(("bpp-core" ,bpp-core)
887 ("bpp-seq" ,bpp-seq)
888 ("gcc" ,gcc-5)))
889 (home-page "http://biopp.univ-montp2.fr")
890 (synopsis "Bio++ population genetics library")
891 (description
892 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
893 analysis, phylogenetics, molecular evolution and population genetics. This
894 library provides population genetics-related modules.")
895 (license license:cecill-c))))
896
897 (define-public bpp-seq
898 ;; The last release was in 2014 and the recommended way to install from source
899 ;; is to clone the git repository, so we do this.
900 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
901 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
902 (package
903 (name "bpp-seq")
904 (version (string-append "2.2.0-1." (string-take commit 7)))
905 (source (origin
906 (method git-fetch)
907 (uri (git-reference
908 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
909 (commit commit)))
910 (file-name (string-append name "-" version "-checkout"))
911 (sha256
912 (base32
913 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
914 (build-system cmake-build-system)
915 (arguments
916 `(#:parallel-build? #f
917 ;; If out-of-source, test data is not copied into the build directory
918 ;; so the tests fail.
919 #:out-of-source? #f))
920 (inputs
921 `(("bpp-core" ,bpp-core)
922 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
923 (home-page "http://biopp.univ-montp2.fr")
924 (synopsis "Bio++ sequence library")
925 (description
926 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
927 analysis, phylogenetics, molecular evolution and population genetics. This
928 library provides sequence-related modules.")
929 (license license:cecill-c))))
930
931 (define-public bppsuite
932 ;; The last release was in 2014 and the recommended way to install from source
933 ;; is to clone the git repository, so we do this.
934 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
935 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
936 (package
937 (name "bppsuite")
938 (version (string-append "2.2.0-1." (string-take commit 7)))
939 (source (origin
940 (method git-fetch)
941 (uri (git-reference
942 (url "http://biopp.univ-montp2.fr/git/bppsuite")
943 (commit commit)))
944 (file-name (string-append name "-" version "-checkout"))
945 (sha256
946 (base32
947 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
948 (build-system cmake-build-system)
949 (arguments
950 `(#:parallel-build? #f
951 #:tests? #f)) ; There are no tests.
952 (native-inputs
953 `(("groff" ,groff)
954 ("man-db" ,man-db)
955 ("texinfo" ,texinfo)))
956 (inputs
957 `(("bpp-core" ,bpp-core)
958 ("bpp-seq" ,bpp-seq)
959 ("bpp-phyl" ,bpp-phyl)
960 ("bpp-phyl" ,bpp-popgen)
961 ("gcc" ,gcc-5)))
962 (home-page "http://biopp.univ-montp2.fr")
963 (synopsis "Bioinformatics tools written with the Bio++ libraries")
964 (description
965 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
966 analysis, phylogenetics, molecular evolution and population genetics. This
967 package provides command line tools using the Bio++ library.")
968 (license license:cecill-c))))
969
970 (define-public blast+
971 (package
972 (name "blast+")
973 (version "2.6.0")
974 (source (origin
975 (method url-fetch)
976 (uri (string-append
977 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
978 version "/ncbi-blast-" version "+-src.tar.gz"))
979 (sha256
980 (base32
981 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
982 (patches (search-patches "blast+-fix-makefile.patch"))
983 (modules '((guix build utils)))
984 (snippet
985 '(begin
986 ;; Remove bundled bzip2, zlib and pcre.
987 (delete-file-recursively "c++/src/util/compress/bzip2")
988 (delete-file-recursively "c++/src/util/compress/zlib")
989 (delete-file-recursively "c++/src/util/regexp")
990 (substitute* "c++/src/util/compress/Makefile.in"
991 (("bzip2 zlib api") "api"))
992 ;; Remove useless msbuild directory
993 (delete-file-recursively
994 "c++/src/build-system/project_tree_builder/msbuild")
995 #t))))
996 (build-system gnu-build-system)
997 (arguments
998 `(;; There are two(!) tests for this massive library, and both fail with
999 ;; "unparsable timing stats".
1000 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1001 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1002 #:tests? #f
1003 #:out-of-source? #t
1004 #:parallel-build? #f ; not supported
1005 #:phases
1006 (modify-phases %standard-phases
1007 (add-before
1008 'configure 'set-HOME
1009 ;; $HOME needs to be set at some point during the configure phase
1010 (lambda _ (setenv "HOME" "/tmp") #t))
1011 (add-after
1012 'unpack 'enter-dir
1013 (lambda _ (chdir "c++") #t))
1014 (add-after
1015 'enter-dir 'fix-build-system
1016 (lambda _
1017 (define (which* cmd)
1018 (cond ((string=? cmd "date")
1019 ;; make call to "date" deterministic
1020 "date -d @0")
1021 ((which cmd)
1022 => identity)
1023 (else
1024 (format (current-error-port)
1025 "WARNING: Unable to find absolute path for ~s~%"
1026 cmd)
1027 #f)))
1028
1029 ;; Rewrite hardcoded paths to various tools
1030 (substitute* (append '("src/build-system/configure.ac"
1031 "src/build-system/configure"
1032 "src/build-system/helpers/run_with_lock.c"
1033 "scripts/common/impl/if_diff.sh"
1034 "scripts/common/impl/run_with_lock.sh"
1035 "src/build-system/Makefile.configurables.real"
1036 "src/build-system/Makefile.in.top"
1037 "src/build-system/Makefile.meta.gmake=no"
1038 "src/build-system/Makefile.meta.in"
1039 "src/build-system/Makefile.meta_l"
1040 "src/build-system/Makefile.meta_p"
1041 "src/build-system/Makefile.meta_r"
1042 "src/build-system/Makefile.mk.in"
1043 "src/build-system/Makefile.requirements"
1044 "src/build-system/Makefile.rules_with_autodep.in")
1045 (find-files "scripts/common/check" "\\.sh$"))
1046 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1047 (or (which* cmd) all)))
1048
1049 (substitute* (find-files "src/build-system" "^config.*")
1050 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1051 (("^PATH=.*") ""))
1052
1053 ;; rewrite "/var/tmp" in check script
1054 (substitute* "scripts/common/check/check_make_unix.sh"
1055 (("/var/tmp") "/tmp"))
1056
1057 ;; do not reset PATH
1058 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1059 (("^ *PATH=.*") "")
1060 (("action=/bin/") "action=")
1061 (("export PATH") ":"))
1062 #t))
1063 (replace
1064 'configure
1065 (lambda* (#:key inputs outputs #:allow-other-keys)
1066 (let ((out (assoc-ref outputs "out"))
1067 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1068 (include (string-append (assoc-ref outputs "include")
1069 "/include/ncbi-tools++")))
1070 ;; The 'configure' script doesn't recognize things like
1071 ;; '--enable-fast-install'.
1072 (zero? (system* "./configure.orig"
1073 (string-append "--with-build-root=" (getcwd) "/build")
1074 (string-append "--prefix=" out)
1075 (string-append "--libdir=" lib)
1076 (string-append "--includedir=" include)
1077 (string-append "--with-bz2="
1078 (assoc-ref inputs "bzip2"))
1079 (string-append "--with-z="
1080 (assoc-ref inputs "zlib"))
1081 (string-append "--with-pcre="
1082 (assoc-ref inputs "pcre"))
1083 ;; Each library is built twice by default, once
1084 ;; with "-static" in its name, and again
1085 ;; without.
1086 "--without-static"
1087 "--with-dll"))))))))
1088 (outputs '("out" ; 21 MB
1089 "lib" ; 226 MB
1090 "include")) ; 33 MB
1091 (inputs
1092 `(("bzip2" ,bzip2)
1093 ("zlib" ,zlib)
1094 ("pcre" ,pcre)
1095 ("perl" ,perl)
1096 ("python" ,python-wrapper)))
1097 (native-inputs
1098 `(("cpio" ,cpio)))
1099 (home-page "http://blast.ncbi.nlm.nih.gov")
1100 (synopsis "Basic local alignment search tool")
1101 (description
1102 "BLAST is a popular method of performing a DNA or protein sequence
1103 similarity search, using heuristics to produce results quickly. It also
1104 calculates an “expect value” that estimates how many matches would have
1105 occurred at a given score by chance, which can aid a user in judging how much
1106 confidence to have in an alignment.")
1107 ;; Most of the sources are in the public domain, with the following
1108 ;; exceptions:
1109 ;; * Expat:
1110 ;; * ./c++/include/util/bitset/
1111 ;; * ./c++/src/html/ncbi_menu*.js
1112 ;; * Boost license:
1113 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1114 ;; * LGPL 2+:
1115 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1116 ;; * ASL 2.0:
1117 ;; * ./c++/src/corelib/teamcity_*
1118 (license (list license:public-domain
1119 license:expat
1120 license:boost1.0
1121 license:lgpl2.0+
1122 license:asl2.0))))
1123
1124 (define-public bless
1125 (package
1126 (name "bless")
1127 (version "1p02")
1128 (source (origin
1129 (method url-fetch)
1130 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1131 version ".tgz"))
1132 (sha256
1133 (base32
1134 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1135 (modules '((guix build utils)))
1136 (snippet
1137 `(begin
1138 ;; Remove bundled boost, pigz, zlib, and .git directory
1139 ;; FIXME: also remove bundled sources for murmurhash3 and
1140 ;; kmc once packaged.
1141 (delete-file-recursively "boost")
1142 (delete-file-recursively "pigz")
1143 (delete-file-recursively "google-sparsehash")
1144 (delete-file-recursively "zlib")
1145 (delete-file-recursively ".git")
1146 #t))))
1147 (build-system gnu-build-system)
1148 (arguments
1149 '(#:tests? #f ;no "check" target
1150 #:make-flags
1151 (list (string-append "ZLIB="
1152 (assoc-ref %build-inputs "zlib")
1153 "/lib/libz.a")
1154 (string-append "LDFLAGS="
1155 (string-join '("-lboost_filesystem"
1156 "-lboost_system"
1157 "-lboost_iostreams"
1158 "-lz"
1159 "-fopenmp"
1160 "-std=c++11"))))
1161 #:phases
1162 (modify-phases %standard-phases
1163 (add-after 'unpack 'do-not-build-bundled-pigz
1164 (lambda* (#:key inputs outputs #:allow-other-keys)
1165 (substitute* "Makefile"
1166 (("cd pigz/pigz-2.3.3; make") ""))
1167 #t))
1168 (add-after 'unpack 'patch-paths-to-executables
1169 (lambda* (#:key inputs outputs #:allow-other-keys)
1170 (substitute* "parse_args.cpp"
1171 (("kmc_binary = .*")
1172 (string-append "kmc_binary = \""
1173 (assoc-ref outputs "out")
1174 "/bin/kmc\";"))
1175 (("pigz_binary = .*")
1176 (string-append "pigz_binary = \""
1177 (assoc-ref inputs "pigz")
1178 "/bin/pigz\";")))
1179 #t))
1180 (replace 'install
1181 (lambda* (#:key outputs #:allow-other-keys)
1182 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1183 (for-each (lambda (file)
1184 (install-file file bin))
1185 '("bless" "kmc/bin/kmc"))
1186 #t)))
1187 (delete 'configure))))
1188 (native-inputs
1189 `(("perl" ,perl)))
1190 (inputs
1191 `(("openmpi" ,openmpi)
1192 ("boost" ,boost)
1193 ("sparsehash" ,sparsehash)
1194 ("pigz" ,pigz)
1195 ("zlib" ,zlib)))
1196 (supported-systems '("x86_64-linux"))
1197 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1198 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1199 (description
1200 "@dfn{Bloom-filter-based error correction solution for high-throughput
1201 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1202 correction tool for genomic reads produced by @dfn{Next-generation
1203 sequencing} (NGS). BLESS produces accurate correction results with much less
1204 memory compared with previous solutions and is also able to tolerate a higher
1205 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1206 errors at the end of reads.")
1207 (license license:gpl3+)))
1208
1209 (define-public bowtie
1210 (package
1211 (name "bowtie")
1212 (version "2.3.2")
1213 (source (origin
1214 (method url-fetch)
1215 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1216 version ".tar.gz"))
1217 (file-name (string-append name "-" version ".tar.gz"))
1218 (sha256
1219 (base32
1220 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1221 (modules '((guix build utils)))
1222 (snippet
1223 '(substitute* "Makefile"
1224 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1225 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1226 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1227 (build-system gnu-build-system)
1228 (inputs
1229 `(("perl" ,perl)
1230 ("perl-clone" ,perl-clone)
1231 ("perl-test-deep" ,perl-test-deep)
1232 ("perl-test-simple" ,perl-test-simple)
1233 ("python" ,python-2)
1234 ("tbb" ,tbb)
1235 ("zlib" ,zlib)))
1236 (arguments
1237 '(#:make-flags
1238 (list "allall"
1239 "WITH_TBB=1"
1240 (string-append "prefix=" (assoc-ref %outputs "out")))
1241 #:phases
1242 (modify-phases %standard-phases
1243 (delete 'configure)
1244 (replace 'check
1245 (lambda* (#:key outputs #:allow-other-keys)
1246 (zero? (system* "perl"
1247 "scripts/test/simple_tests.pl"
1248 "--bowtie2=./bowtie2"
1249 "--bowtie2-build=./bowtie2-build")))))))
1250 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1251 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1252 (description
1253 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1254 reads to long reference sequences. It is particularly good at aligning reads
1255 of about 50 up to 100s or 1,000s of characters, and particularly good at
1256 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1257 genome with an FM Index to keep its memory footprint small: for the human
1258 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1259 gapped, local, and paired-end alignment modes.")
1260 (supported-systems '("x86_64-linux"))
1261 (license license:gpl3+)))
1262
1263 (define-public tophat
1264 (package
1265 (name "tophat")
1266 (version "2.1.0")
1267 (source (origin
1268 (method url-fetch)
1269 (uri (string-append
1270 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1271 version ".tar.gz"))
1272 (sha256
1273 (base32
1274 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1275 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1276 (modules '((guix build utils)))
1277 (snippet
1278 '(begin
1279 ;; Remove bundled SeqAn and samtools
1280 (delete-file-recursively "src/SeqAn-1.3")
1281 (delete-file-recursively "src/samtools-0.1.18")
1282 #t))))
1283 (build-system gnu-build-system)
1284 (arguments
1285 '(#:parallel-build? #f ; not supported
1286 #:phases
1287 (modify-phases %standard-phases
1288 (add-after 'unpack 'use-system-samtools
1289 (lambda* (#:key inputs #:allow-other-keys)
1290 (substitute* "src/Makefile.in"
1291 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1292 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1293 (("SAMPROG = samtools_0\\.1\\.18") "")
1294 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1295 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1296 (substitute* '("src/common.cpp"
1297 "src/tophat.py")
1298 (("samtools_0.1.18") (which "samtools")))
1299 (substitute* '("src/common.h"
1300 "src/bam2fastx.cpp")
1301 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1302 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1303 (substitute* '("src/bwt_map.h"
1304 "src/map2gtf.h"
1305 "src/align_status.h")
1306 (("#include <bam.h>") "#include <samtools/bam.h>")
1307 (("#include <sam.h>") "#include <samtools/sam.h>"))
1308 #t)))))
1309 (inputs
1310 `(("boost" ,boost)
1311 ("bowtie" ,bowtie)
1312 ("samtools" ,samtools-0.1)
1313 ("ncurses" ,ncurses)
1314 ("python" ,python-2)
1315 ("perl" ,perl)
1316 ("zlib" ,zlib)
1317 ("seqan" ,seqan)))
1318 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1319 (synopsis "Spliced read mapper for RNA-Seq data")
1320 (description
1321 "TopHat is a fast splice junction mapper for nucleotide sequence
1322 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1323 mammalian-sized genomes using the ultra high-throughput short read
1324 aligner Bowtie, and then analyzes the mapping results to identify
1325 splice junctions between exons.")
1326 ;; TopHat is released under the Boost Software License, Version 1.0
1327 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1328 (license license:boost1.0)))
1329
1330 (define-public bwa
1331 (package
1332 (name "bwa")
1333 (version "0.7.17")
1334 (source (origin
1335 (method url-fetch)
1336 (uri (string-append
1337 "https://github.com/lh3/bwa/releases/download/v"
1338 version "/bwa-" version ".tar.bz2"))
1339 (sha256
1340 (base32
1341 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1342 (build-system gnu-build-system)
1343 (arguments
1344 '(#:tests? #f ;no "check" target
1345 #:phases
1346 (modify-phases %standard-phases
1347 (replace 'install
1348 (lambda* (#:key outputs #:allow-other-keys)
1349 (let ((bin (string-append
1350 (assoc-ref outputs "out") "/bin"))
1351 (doc (string-append
1352 (assoc-ref outputs "out") "/share/doc/bwa"))
1353 (man (string-append
1354 (assoc-ref outputs "out") "/share/man/man1")))
1355 (install-file "bwa" bin)
1356 (install-file "README.md" doc)
1357 (install-file "bwa.1" man))
1358 #t))
1359 ;; no "configure" script
1360 (delete 'configure))))
1361 (inputs `(("zlib" ,zlib)))
1362 ;; Non-portable SSE instructions are used so building fails on platforms
1363 ;; other than x86_64.
1364 (supported-systems '("x86_64-linux"))
1365 (home-page "http://bio-bwa.sourceforge.net/")
1366 (synopsis "Burrows-Wheeler sequence aligner")
1367 (description
1368 "BWA is a software package for mapping low-divergent sequences against a
1369 large reference genome, such as the human genome. It consists of three
1370 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1371 designed for Illumina sequence reads up to 100bp, while the rest two for
1372 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1373 features such as long-read support and split alignment, but BWA-MEM, which is
1374 the latest, is generally recommended for high-quality queries as it is faster
1375 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1376 70-100bp Illumina reads.")
1377 (license license:gpl3+)))
1378
1379 (define-public bwa-pssm
1380 (package (inherit bwa)
1381 (name "bwa-pssm")
1382 (version "0.5.11")
1383 (source (origin
1384 (method url-fetch)
1385 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1386 "archive/" version ".tar.gz"))
1387 (file-name (string-append name "-" version ".tar.gz"))
1388 (sha256
1389 (base32
1390 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1391 (build-system gnu-build-system)
1392 (inputs
1393 `(("gdsl" ,gdsl)
1394 ("zlib" ,zlib)
1395 ("perl" ,perl)))
1396 (home-page "http://bwa-pssm.binf.ku.dk/")
1397 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1398 (description
1399 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1400 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1401 existing aligners it is fast and sensitive. Unlike most other aligners,
1402 however, it is also adaptible in the sense that one can direct the alignment
1403 based on known biases within the data set. It is coded as a modification of
1404 the original BWA alignment program and shares the genome index structure as
1405 well as many of the command line options.")
1406 (license license:gpl3+)))
1407
1408 (define-public python2-bx-python
1409 (package
1410 (name "python2-bx-python")
1411 (version "0.7.3")
1412 (source (origin
1413 (method url-fetch)
1414 (uri (pypi-uri "bx-python" version))
1415 (sha256
1416 (base32
1417 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1418 (modules '((guix build utils)))
1419 (snippet
1420 '(substitute* "setup.py"
1421 ;; remove dependency on outdated "distribute" module
1422 (("^from distribute_setup import use_setuptools") "")
1423 (("^use_setuptools\\(\\)") "")))))
1424 (build-system python-build-system)
1425 (arguments
1426 `(#:tests? #f ;tests fail because test data are not included
1427 #:python ,python-2))
1428 (inputs
1429 `(("python-numpy" ,python2-numpy)
1430 ("zlib" ,zlib)))
1431 (native-inputs
1432 `(("python-nose" ,python2-nose)))
1433 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1434 (synopsis "Tools for manipulating biological data")
1435 (description
1436 "bx-python provides tools for manipulating biological data, particularly
1437 multiple sequence alignments.")
1438 (license license:expat)))
1439
1440 (define-public python-pysam
1441 (package
1442 (name "python-pysam")
1443 (version "0.13.0")
1444 (source (origin
1445 (method url-fetch)
1446 ;; Test data is missing on PyPi.
1447 (uri (string-append
1448 "https://github.com/pysam-developers/pysam/archive/v"
1449 version ".tar.gz"))
1450 (file-name (string-append name "-" version ".tar.gz"))
1451 (sha256
1452 (base32
1453 "0dzap2axin9cbbl0d825w294bpn00zagfm1sigamm4v2pm5bj9lp"))
1454 (modules '((guix build utils)))
1455 (snippet
1456 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1457 '(delete-file-recursively "htslib"))))
1458 (build-system python-build-system)
1459 (arguments
1460 `(#:modules ((ice-9 ftw)
1461 (srfi srfi-26)
1462 (guix build python-build-system)
1463 (guix build utils))
1464 #:phases
1465 (modify-phases %standard-phases
1466 (add-before 'build 'set-flags
1467 (lambda* (#:key inputs #:allow-other-keys)
1468 (setenv "HTSLIB_MODE" "external")
1469 (setenv "HTSLIB_LIBRARY_DIR"
1470 (string-append (assoc-ref inputs "htslib") "/lib"))
1471 (setenv "HTSLIB_INCLUDE_DIR"
1472 (string-append (assoc-ref inputs "htslib") "/include"))
1473 (setenv "LDFLAGS" "-lncurses")
1474 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1475 #t))
1476 (replace 'check
1477 (lambda* (#:key inputs outputs #:allow-other-keys)
1478 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1479 (setenv "PYTHONPATH"
1480 (string-append
1481 (getenv "PYTHONPATH")
1482 ":" (getcwd) "/build/"
1483 (car (scandir "build"
1484 (negate (cut string-prefix? "." <>))))))
1485 ;; Step out of source dir so python does not import from CWD.
1486 (with-directory-excursion "tests"
1487 (setenv "HOME" "/tmp")
1488 (and (zero? (system* "make" "-C" "pysam_data"))
1489 (zero? (system* "make" "-C" "cbcf_data"))
1490 ;; Running nosetests without explicitly asking for a
1491 ;; single process leads to a crash. Running with multiple
1492 ;; processes fails because the tests are not designed to
1493 ;; run in parallel.
1494
1495 ;; FIXME: tests keep timing out on some systems.
1496 ;; (zero? (system* "nosetests" "-v"
1497 ;; "--processes" "1"))
1498 )))))))
1499 (propagated-inputs
1500 `(("htslib" ,htslib))) ; Included from installed header files.
1501 (inputs
1502 `(("ncurses" ,ncurses)
1503 ("zlib" ,zlib)))
1504 (native-inputs
1505 `(("python-cython" ,python-cython)
1506 ;; Dependencies below are are for tests only.
1507 ("samtools" ,samtools)
1508 ("bcftools" ,bcftools)
1509 ("python-nose" ,python-nose)))
1510 (home-page "https://github.com/pysam-developers/pysam")
1511 (synopsis "Python bindings to the SAMtools C API")
1512 (description
1513 "Pysam is a Python module for reading and manipulating files in the
1514 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1515 also includes an interface for tabix.")
1516 (license license:expat)))
1517
1518 (define-public python2-pysam
1519 (package-with-python2 python-pysam))
1520
1521 (define-public python-twobitreader
1522 (package
1523 (name "python-twobitreader")
1524 (version "3.1.4")
1525 (source (origin
1526 (method url-fetch)
1527 (uri (pypi-uri "twobitreader" version))
1528 (sha256
1529 (base32
1530 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1531 (build-system python-build-system)
1532 (arguments
1533 '(;; Tests are not distributed in the PyPi release.
1534 ;; TODO Try building from the Git repo or asking the upstream maintainer
1535 ;; to distribute the tests on PyPi.
1536 #:tests? #f))
1537 (native-inputs
1538 `(("python-sphinx" ,python-sphinx)))
1539 (home-page "https://github.com/benjschiller/twobitreader")
1540 (synopsis "Python library for reading .2bit files")
1541 (description
1542 "twobitreader is a Python library for reading .2bit files as used by the
1543 UCSC genome browser.")
1544 (license license:artistic2.0)))
1545
1546 (define-public python2-twobitreader
1547 (package-with-python2 python-twobitreader))
1548
1549 (define-public python-plastid
1550 (package
1551 (name "python-plastid")
1552 (version "0.4.8")
1553 (source (origin
1554 (method url-fetch)
1555 (uri (pypi-uri "plastid" version))
1556 (sha256
1557 (base32
1558 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1559 (build-system python-build-system)
1560 (arguments
1561 ;; Some test files are not included.
1562 `(#:tests? #f))
1563 (propagated-inputs
1564 `(("python-numpy" ,python-numpy)
1565 ("python-scipy" ,python-scipy)
1566 ("python-pandas" ,python-pandas)
1567 ("python-pysam" ,python-pysam)
1568 ("python-matplotlib" ,python-matplotlib)
1569 ("python-biopython" ,python-biopython)
1570 ("python-twobitreader" ,python-twobitreader)
1571 ("python-termcolor" ,python-termcolor)))
1572 (native-inputs
1573 `(("python-cython" ,python-cython)
1574 ("python-nose" ,python-nose)))
1575 (home-page "https://github.com/joshuagryphon/plastid")
1576 (synopsis "Python library for genomic analysis")
1577 (description
1578 "plastid is a Python library for genomic analysis – in particular,
1579 high-throughput sequencing data – with an emphasis on simplicity.")
1580 (license license:bsd-3)))
1581
1582 (define-public python2-plastid
1583 (package-with-python2 python-plastid))
1584
1585 (define-public cd-hit
1586 (package
1587 (name "cd-hit")
1588 (version "4.6.8")
1589 (source (origin
1590 (method url-fetch)
1591 (uri (string-append "https://github.com/weizhongli/cdhit"
1592 "/releases/download/V" version
1593 "/cd-hit-v" version
1594 "-2017-0621-source.tar.gz"))
1595 (sha256
1596 (base32
1597 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1598 (build-system gnu-build-system)
1599 (arguments
1600 `(#:tests? #f ; there are no tests
1601 #:make-flags
1602 ;; Executables are copied directly to the PREFIX.
1603 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1604 #:phases
1605 (modify-phases %standard-phases
1606 ;; No "configure" script
1607 (delete 'configure)
1608 ;; Remove sources of non-determinism
1609 (add-after 'unpack 'be-timeless
1610 (lambda _
1611 (substitute* "cdhit-utility.c++"
1612 ((" \\(built on \" __DATE__ \"\\)") ""))
1613 (substitute* "cdhit-common.c++"
1614 (("__DATE__") "\"0\"")
1615 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1616 #t))
1617 ;; The "install" target does not create the target directory.
1618 (add-before 'install 'create-target-dir
1619 (lambda* (#:key outputs #:allow-other-keys)
1620 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1621 #t)))))
1622 (inputs
1623 `(("perl" ,perl)))
1624 (home-page "http://weizhongli-lab.org/cd-hit/")
1625 (synopsis "Cluster and compare protein or nucleotide sequences")
1626 (description
1627 "CD-HIT is a program for clustering and comparing protein or nucleotide
1628 sequences. CD-HIT is designed to be fast and handle extremely large
1629 databases.")
1630 ;; The manual says: "It can be copied under the GNU General Public License
1631 ;; version 2 (GPLv2)."
1632 (license license:gpl2)))
1633
1634 (define-public clipper
1635 (package
1636 (name "clipper")
1637 (version "1.1")
1638 (source (origin
1639 (method url-fetch)
1640 (uri (string-append
1641 "https://github.com/YeoLab/clipper/archive/"
1642 version ".tar.gz"))
1643 (file-name (string-append name "-" version ".tar.gz"))
1644 (sha256
1645 (base32
1646 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1647 (modules '((guix build utils)))
1648 (snippet
1649 '(begin
1650 ;; remove unnecessary setup dependency
1651 (substitute* "setup.py"
1652 (("setup_requires = .*") ""))
1653 (for-each delete-file
1654 '("clipper/src/peaks.so"
1655 "clipper/src/readsToWiggle.so"))
1656 (delete-file-recursively "dist/")
1657 #t))))
1658 (build-system python-build-system)
1659 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1660 (inputs
1661 `(("htseq" ,python2-htseq)
1662 ("python-pybedtools" ,python2-pybedtools)
1663 ("python-cython" ,python2-cython)
1664 ("python-scikit-learn" ,python2-scikit-learn)
1665 ("python-matplotlib" ,python2-matplotlib)
1666 ("python-pandas" ,python2-pandas)
1667 ("python-pysam" ,python2-pysam)
1668 ("python-numpy" ,python2-numpy)
1669 ("python-scipy" ,python2-scipy)))
1670 (native-inputs
1671 `(("python-mock" ,python2-mock) ; for tests
1672 ("python-nose" ,python2-nose) ; for tests
1673 ("python-pytz" ,python2-pytz))) ; for tests
1674 (home-page "https://github.com/YeoLab/clipper")
1675 (synopsis "CLIP peak enrichment recognition")
1676 (description
1677 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1678 (license license:gpl2)))
1679
1680 (define-public codingquarry
1681 (package
1682 (name "codingquarry")
1683 (version "2.0")
1684 (source (origin
1685 (method url-fetch)
1686 (uri (string-append
1687 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1688 version ".tar.gz"))
1689 (sha256
1690 (base32
1691 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1692 (build-system gnu-build-system)
1693 (arguments
1694 '(#:tests? #f ; no "check" target
1695 #:phases
1696 (modify-phases %standard-phases
1697 (delete 'configure)
1698 (replace 'install
1699 (lambda* (#:key outputs #:allow-other-keys)
1700 (let* ((out (assoc-ref outputs "out"))
1701 (bin (string-append out "/bin"))
1702 (doc (string-append out "/share/doc/codingquarry")))
1703 (install-file "INSTRUCTIONS.pdf" doc)
1704 (copy-recursively "QuarryFiles"
1705 (string-append out "/QuarryFiles"))
1706 (install-file "CodingQuarry" bin)
1707 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1708 (inputs `(("openmpi" ,openmpi)))
1709 (native-search-paths
1710 (list (search-path-specification
1711 (variable "QUARRY_PATH")
1712 (files '("QuarryFiles")))))
1713 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1714 (synopsis "Fungal gene predictor")
1715 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1716 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1717 (home-page "https://sourceforge.net/projects/codingquarry/")
1718 (license license:gpl3+)))
1719
1720 (define-public couger
1721 (package
1722 (name "couger")
1723 (version "1.8.2")
1724 (source (origin
1725 (method url-fetch)
1726 (uri (string-append
1727 "http://couger.oit.duke.edu/static/assets/COUGER"
1728 version ".zip"))
1729 (sha256
1730 (base32
1731 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1732 (build-system gnu-build-system)
1733 (arguments
1734 `(#:tests? #f
1735 #:phases
1736 (modify-phases %standard-phases
1737 (delete 'configure)
1738 (delete 'build)
1739 (replace
1740 'install
1741 (lambda* (#:key outputs #:allow-other-keys)
1742 (let* ((out (assoc-ref outputs "out"))
1743 (bin (string-append out "/bin")))
1744 (copy-recursively "src" (string-append out "/src"))
1745 (mkdir bin)
1746 ;; Add "src" directory to module lookup path.
1747 (substitute* "couger"
1748 (("from argparse")
1749 (string-append "import sys\nsys.path.append(\""
1750 out "\")\nfrom argparse")))
1751 (install-file "couger" bin))
1752 #t))
1753 (add-after
1754 'install 'wrap-program
1755 (lambda* (#:key inputs outputs #:allow-other-keys)
1756 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1757 (let* ((out (assoc-ref outputs "out"))
1758 (path (getenv "PYTHONPATH")))
1759 (wrap-program (string-append out "/bin/couger")
1760 `("PYTHONPATH" ":" prefix (,path))))
1761 #t)))))
1762 (inputs
1763 `(("python" ,python-2)
1764 ("python2-pillow" ,python2-pillow)
1765 ("python2-numpy" ,python2-numpy)
1766 ("python2-scipy" ,python2-scipy)
1767 ("python2-matplotlib" ,python2-matplotlib)))
1768 (propagated-inputs
1769 `(("r-minimal" ,r-minimal)
1770 ("libsvm" ,libsvm)
1771 ("randomjungle" ,randomjungle)))
1772 (native-inputs
1773 `(("unzip" ,unzip)))
1774 (home-page "http://couger.oit.duke.edu")
1775 (synopsis "Identify co-factors in sets of genomic regions")
1776 (description
1777 "COUGER can be applied to any two sets of genomic regions bound by
1778 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1779 putative co-factors that provide specificity to each TF. The framework
1780 determines the genomic targets uniquely-bound by each TF, and identifies a
1781 small set of co-factors that best explain the in vivo binding differences
1782 between the two TFs.
1783
1784 COUGER uses classification algorithms (support vector machines and random
1785 forests) with features that reflect the DNA binding specificities of putative
1786 co-factors. The features are generated either from high-throughput TF-DNA
1787 binding data (from protein binding microarray experiments), or from large
1788 collections of DNA motifs.")
1789 (license license:gpl3+)))
1790
1791 (define-public clustal-omega
1792 (package
1793 (name "clustal-omega")
1794 (version "1.2.4")
1795 (source (origin
1796 (method url-fetch)
1797 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1798 version ".tar.gz"))
1799 (sha256
1800 (base32
1801 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1802 (build-system gnu-build-system)
1803 (inputs
1804 `(("argtable" ,argtable)))
1805 (home-page "http://www.clustal.org/omega/")
1806 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1807 (description
1808 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1809 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1810 of handling data-sets of hundreds of thousands of sequences in reasonable
1811 time.")
1812 (license license:gpl2+)))
1813
1814 (define-public crossmap
1815 (package
1816 (name "crossmap")
1817 (version "0.2.1")
1818 (source (origin
1819 (method url-fetch)
1820 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1821 version ".tar.gz"))
1822 (sha256
1823 (base32
1824 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1825 ;; This patch has been sent upstream already and is available
1826 ;; for download from Sourceforge, but it has not been merged.
1827 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1828 (modules '((guix build utils)))
1829 ;; remove bundled copy of pysam
1830 (snippet
1831 '(delete-file-recursively "lib/pysam"))))
1832 (build-system python-build-system)
1833 (arguments
1834 `(#:python ,python-2
1835 #:phases
1836 (modify-phases %standard-phases
1837 (add-after 'unpack 'set-env
1838 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1839 (inputs
1840 `(("python-numpy" ,python2-numpy)
1841 ("python-pysam" ,python2-pysam)
1842 ("zlib" ,zlib)))
1843 (native-inputs
1844 `(("python-cython" ,python2-cython)
1845 ("python-nose" ,python2-nose)))
1846 (home-page "http://crossmap.sourceforge.net/")
1847 (synopsis "Convert genome coordinates between assemblies")
1848 (description
1849 "CrossMap is a program for conversion of genome coordinates or annotation
1850 files between different genome assemblies. It supports most commonly used
1851 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1852 (license license:gpl2+)))
1853
1854 (define-public cutadapt
1855 (package
1856 (name "cutadapt")
1857 (version "1.16")
1858 (source (origin
1859 (method git-fetch)
1860 (uri (git-reference
1861 (url "https://github.com/marcelm/cutadapt.git")
1862 (commit (string-append "v" version))))
1863 (file-name (string-append name "-" version "-checkout"))
1864 (sha256
1865 (base32
1866 "09pr02067jiks19nc0aby4xp70hhgvb554i2y1c04rv1m401w7q8"))))
1867 (build-system python-build-system)
1868 (inputs
1869 `(("python-xopen" ,python-xopen)))
1870 (native-inputs
1871 `(("python-cython" ,python-cython)
1872 ("python-pytest" ,python-pytest)))
1873 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1874 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1875 (description
1876 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1877 other types of unwanted sequence from high-throughput sequencing reads.")
1878 (license license:expat)))
1879
1880 (define-public libbigwig
1881 (package
1882 (name "libbigwig")
1883 (version "0.1.4")
1884 (source (origin
1885 (method url-fetch)
1886 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1887 "archive/" version ".tar.gz"))
1888 (file-name (string-append name "-" version ".tar.gz"))
1889 (sha256
1890 (base32
1891 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1892 (build-system gnu-build-system)
1893 (arguments
1894 `(#:test-target "test"
1895 #:make-flags
1896 (list "CC=gcc"
1897 (string-append "prefix=" (assoc-ref %outputs "out")))
1898 #:phases
1899 (modify-phases %standard-phases
1900 (delete 'configure)
1901 (add-before 'check 'disable-curl-test
1902 (lambda _
1903 (substitute* "Makefile"
1904 (("./test/testRemote.*") ""))
1905 #t))
1906 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1907 ;; there has not yet been a release containing this change.
1908 (add-before 'install 'create-target-dirs
1909 (lambda* (#:key outputs #:allow-other-keys)
1910 (let ((out (assoc-ref outputs "out")))
1911 (mkdir-p (string-append out "/lib"))
1912 (mkdir-p (string-append out "/include"))
1913 #t))))))
1914 (inputs
1915 `(("zlib" ,zlib)
1916 ("curl" ,curl)))
1917 (native-inputs
1918 `(("doxygen" ,doxygen)))
1919 (home-page "https://github.com/dpryan79/libBigWig")
1920 (synopsis "C library for handling bigWig files")
1921 (description
1922 "This package provides a C library for parsing local and remote BigWig
1923 files.")
1924 (license license:expat)))
1925
1926 (define-public python-pybigwig
1927 (package
1928 (name "python-pybigwig")
1929 (version "0.2.5")
1930 (source (origin
1931 (method url-fetch)
1932 (uri (pypi-uri "pyBigWig" version))
1933 (sha256
1934 (base32
1935 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1936 (modules '((guix build utils)))
1937 (snippet
1938 '(begin
1939 ;; Delete bundled libBigWig sources
1940 (delete-file-recursively "libBigWig")))))
1941 (build-system python-build-system)
1942 (arguments
1943 `(#:phases
1944 (modify-phases %standard-phases
1945 (add-after 'unpack 'link-with-libBigWig
1946 (lambda* (#:key inputs #:allow-other-keys)
1947 (substitute* "setup.py"
1948 (("libs=\\[") "libs=[\"BigWig\", "))
1949 #t)))))
1950 (inputs
1951 `(("libbigwig" ,libbigwig)
1952 ("zlib" ,zlib)
1953 ("curl" ,curl)))
1954 (home-page "https://github.com/dpryan79/pyBigWig")
1955 (synopsis "Access bigWig files in Python using libBigWig")
1956 (description
1957 "This package provides Python bindings to the libBigWig library for
1958 accessing bigWig files.")
1959 (license license:expat)))
1960
1961 (define-public python2-pybigwig
1962 (package-with-python2 python-pybigwig))
1963
1964 (define-public python-dendropy
1965 (package
1966 (name "python-dendropy")
1967 (version "4.2.0")
1968 (source
1969 (origin
1970 (method url-fetch)
1971 (uri (pypi-uri "DendroPy" version))
1972 (sha256
1973 (base32
1974 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1975 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1976 (build-system python-build-system)
1977 (home-page "http://packages.python.org/DendroPy/")
1978 (synopsis "Library for phylogenetics and phylogenetic computing")
1979 (description
1980 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1981 writing, simulation, processing and manipulation of phylogenetic
1982 trees (phylogenies) and characters.")
1983 (license license:bsd-3)
1984 (properties `((python2-variant . ,(delay python2-dendropy))))))
1985
1986 (define-public python2-dendropy
1987 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1988 (package
1989 (inherit base)
1990 (arguments
1991 `(#:python ,python-2
1992 #:phases
1993 (modify-phases %standard-phases
1994 (replace 'check
1995 ;; There is currently a test failure that only happens on some
1996 ;; systems, and only using "setup.py test"
1997 (lambda _ (zero? (system* "nosetests")))))))
1998 (native-inputs `(("python2-nose" ,python2-nose)
1999 ,@(package-native-inputs base))))))
2000
2001 (define-public python-py2bit
2002 (package
2003 (name "python-py2bit")
2004 (version "0.2.1")
2005 (source
2006 (origin
2007 (method url-fetch)
2008 (uri (pypi-uri "py2bit" version))
2009 (sha256
2010 (base32
2011 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2012 (build-system python-build-system)
2013 (home-page "https://github.com/dpryan79/py2bit")
2014 (synopsis "Access 2bit files using lib2bit")
2015 (description
2016 "This package provides Python bindings for lib2bit to access 2bit files
2017 with Python.")
2018 (license license:expat)))
2019
2020 (define-public deeptools
2021 (package
2022 (name "deeptools")
2023 (version "2.5.1")
2024 (source (origin
2025 (method url-fetch)
2026 (uri (string-append "https://github.com/deeptools/deepTools/"
2027 "archive/" version ".tar.gz"))
2028 (file-name (string-append name "-" version ".tar.gz"))
2029 (sha256
2030 (base32
2031 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2032 (build-system python-build-system)
2033 (inputs
2034 `(("python-scipy" ,python-scipy)
2035 ("python-numpy" ,python-numpy)
2036 ("python-numpydoc" ,python-numpydoc)
2037 ("python-matplotlib" ,python-matplotlib)
2038 ("python-pysam" ,python-pysam)
2039 ("python-py2bit" ,python-py2bit)
2040 ("python-pybigwig" ,python-pybigwig)))
2041 (native-inputs
2042 `(("python-mock" ,python-mock) ;for tests
2043 ("python-nose" ,python-nose) ;for tests
2044 ("python-pytz" ,python-pytz))) ;for tests
2045 (home-page "https://github.com/deeptools/deepTools")
2046 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2047 (description
2048 "DeepTools addresses the challenge of handling the large amounts of data
2049 that are now routinely generated from DNA sequencing centers. To do so,
2050 deepTools contains useful modules to process the mapped reads data to create
2051 coverage files in standard bedGraph and bigWig file formats. By doing so,
2052 deepTools allows the creation of normalized coverage files or the comparison
2053 between two files (for example, treatment and control). Finally, using such
2054 normalized and standardized files, multiple visualizations can be created to
2055 identify enrichments with functional annotations of the genome.")
2056 (license license:gpl3+)))
2057
2058 (define-public diamond
2059 (package
2060 (name "diamond")
2061 (version "0.9.18")
2062 (source (origin
2063 (method url-fetch)
2064 (uri (string-append
2065 "https://github.com/bbuchfink/diamond/archive/v"
2066 version ".tar.gz"))
2067 (file-name (string-append name "-" version ".tar.gz"))
2068 (sha256
2069 (base32
2070 "1vi2nddmy7knrv8gsprwqp6a40k63n3f2dfvx22ipjhrg9xir96f"))))
2071 (build-system cmake-build-system)
2072 (arguments
2073 '(#:tests? #f ; no "check" target
2074 #:phases
2075 (modify-phases %standard-phases
2076 (add-after 'unpack 'remove-native-compilation
2077 (lambda _
2078 (substitute* "CMakeLists.txt" (("-march=native") ""))
2079 #t)))))
2080 (inputs
2081 `(("zlib" ,zlib)))
2082 (home-page "https://github.com/bbuchfink/diamond")
2083 (synopsis "Accelerated BLAST compatible local sequence aligner")
2084 (description
2085 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2086 translated DNA query sequences against a protein reference database (BLASTP
2087 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2088 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2089 data and settings.")
2090 (license license:agpl3+)))
2091
2092 (define-public discrover
2093 (package
2094 (name "discrover")
2095 (version "1.6.0")
2096 (source
2097 (origin
2098 (method url-fetch)
2099 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2100 version ".tar.gz"))
2101 (file-name (string-append name "-" version ".tar.gz"))
2102 (sha256
2103 (base32
2104 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2105 (build-system cmake-build-system)
2106 (arguments
2107 `(#:tests? #f ; there are no tests
2108 #:phases
2109 (modify-phases %standard-phases
2110 (add-after 'unpack 'add-missing-includes
2111 (lambda _
2112 (substitute* "src/executioninformation.hpp"
2113 (("#define EXECUTIONINFORMATION_HPP" line)
2114 (string-append line "\n#include <random>")))
2115 (substitute* "src/plasma/fasta.hpp"
2116 (("#define FASTA_HPP" line)
2117 (string-append line "\n#include <random>")))
2118 #t)))))
2119 (inputs
2120 `(("boost" ,boost)
2121 ("cairo" ,cairo)))
2122 (native-inputs
2123 `(("texlive" ,texlive)
2124 ("imagemagick" ,imagemagick)))
2125 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2126 (synopsis "Discover discriminative nucleotide sequence motifs")
2127 (description "Discrover is a motif discovery method to find binding sites
2128 of nucleic acid binding proteins.")
2129 (license license:gpl3+)))
2130
2131 (define-public eigensoft
2132 (let ((revision "1")
2133 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2134 (package
2135 (name "eigensoft")
2136 (version (string-append "6.1.2-"
2137 revision "."
2138 (string-take commit 9)))
2139 (source
2140 (origin
2141 (method git-fetch)
2142 (uri (git-reference
2143 (url "https://github.com/DReichLab/EIG.git")
2144 (commit commit)))
2145 (file-name (string-append "eigensoft-" commit "-checkout"))
2146 (sha256
2147 (base32
2148 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2149 (modules '((guix build utils)))
2150 ;; Remove pre-built binaries.
2151 (snippet '(begin
2152 (delete-file-recursively "bin")
2153 (mkdir "bin")
2154 #t))))
2155 (build-system gnu-build-system)
2156 (arguments
2157 `(#:tests? #f ; There are no tests.
2158 #:make-flags '("CC=gcc")
2159 #:phases
2160 (modify-phases %standard-phases
2161 ;; There is no configure phase, but the Makefile is in a
2162 ;; sub-directory.
2163 (replace 'configure
2164 (lambda _
2165 (chdir "src")
2166 ;; The link flags are incomplete.
2167 (substitute* "Makefile"
2168 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2169 #t))
2170 ;; The provided install target only copies executables to
2171 ;; the "bin" directory in the build root.
2172 (add-after 'install 'actually-install
2173 (lambda* (#:key outputs #:allow-other-keys)
2174 (let* ((out (assoc-ref outputs "out"))
2175 (bin (string-append out "/bin")))
2176 (for-each (lambda (file)
2177 (install-file file bin))
2178 (find-files "../bin" ".*"))
2179 #t))))))
2180 (inputs
2181 `(("gsl" ,gsl)
2182 ("lapack" ,lapack)
2183 ("openblas" ,openblas)
2184 ("perl" ,perl)
2185 ("gfortran" ,gfortran "lib")))
2186 (home-page "https://github.com/DReichLab/EIG")
2187 (synopsis "Tools for population genetics")
2188 (description "The EIGENSOFT package provides tools for population
2189 genetics and stratification correction. EIGENSOFT implements methods commonly
2190 used in population genetics analyses such as PCA, computation of Tracy-Widom
2191 statistics, and finding related individuals in structured populations. It
2192 comes with a built-in plotting script and supports multiple file formats and
2193 quantitative phenotypes.")
2194 ;; The license of the eigensoft tools is Expat, but since it's
2195 ;; linking with the GNU Scientific Library (GSL) the effective
2196 ;; license is the GPL.
2197 (license license:gpl3+))))
2198
2199 (define-public edirect
2200 (package
2201 (name "edirect")
2202 (version "4.10")
2203 (source (origin
2204 (method url-fetch)
2205 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2206 "versions/2016-05-03/edirect.tar.gz"))
2207 (sha256
2208 (base32
2209 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2210 (build-system perl-build-system)
2211 (arguments
2212 `(#:tests? #f ;no "check" target
2213 #:phases
2214 (modify-phases %standard-phases
2215 (delete 'configure)
2216 (delete 'build)
2217 (replace 'install
2218 (lambda* (#:key outputs #:allow-other-keys)
2219 (let ((target (string-append (assoc-ref outputs "out")
2220 "/bin")))
2221 (mkdir-p target)
2222 (install-file "edirect.pl" target)
2223 #t)))
2224 (add-after
2225 'install 'wrap-program
2226 (lambda* (#:key inputs outputs #:allow-other-keys)
2227 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2228 (let* ((out (assoc-ref outputs "out"))
2229 (path (getenv "PERL5LIB")))
2230 (wrap-program (string-append out "/bin/edirect.pl")
2231 `("PERL5LIB" ":" prefix (,path)))))))))
2232 (inputs
2233 `(("perl-html-parser" ,perl-html-parser)
2234 ("perl-encode-locale" ,perl-encode-locale)
2235 ("perl-file-listing" ,perl-file-listing)
2236 ("perl-html-tagset" ,perl-html-tagset)
2237 ("perl-html-tree" ,perl-html-tree)
2238 ("perl-http-cookies" ,perl-http-cookies)
2239 ("perl-http-date" ,perl-http-date)
2240 ("perl-http-message" ,perl-http-message)
2241 ("perl-http-negotiate" ,perl-http-negotiate)
2242 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2243 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2244 ("perl-net-http" ,perl-net-http)
2245 ("perl-uri" ,perl-uri)
2246 ("perl-www-robotrules" ,perl-www-robotrules)
2247 ("perl" ,perl)))
2248 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2249 (synopsis "Tools for accessing the NCBI's set of databases")
2250 (description
2251 "Entrez Direct (EDirect) is a method for accessing the National Center
2252 for Biotechnology Information's (NCBI) set of interconnected
2253 databases (publication, sequence, structure, gene, variation, expression,
2254 etc.) from a terminal. Functions take search terms from command-line
2255 arguments. Individual operations are combined to build multi-step queries.
2256 Record retrieval and formatting normally complete the process.
2257
2258 EDirect also provides an argument-driven function that simplifies the
2259 extraction of data from document summaries or other results that are returned
2260 in structured XML format. This can eliminate the need for writing custom
2261 software to answer ad hoc questions.")
2262 (license license:public-domain)))
2263
2264 (define-public exonerate
2265 (package
2266 (name "exonerate")
2267 (version "2.4.0")
2268 (source
2269 (origin
2270 (method url-fetch)
2271 (uri
2272 (string-append
2273 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2274 "exonerate-" version ".tar.gz"))
2275 (sha256
2276 (base32
2277 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2278 (build-system gnu-build-system)
2279 (arguments
2280 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2281 (native-inputs
2282 `(("pkg-config" ,pkg-config)))
2283 (inputs
2284 `(("glib" ,glib)))
2285 (home-page
2286 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2287 (synopsis "Generic tool for biological sequence alignment")
2288 (description
2289 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2290 the alignment of sequences using a many alignment models, either exhaustive
2291 dynamic programming or a variety of heuristics.")
2292 (license license:gpl3)))
2293
2294 (define-public express
2295 (package
2296 (name "express")
2297 (version "1.5.1")
2298 (source (origin
2299 (method url-fetch)
2300 (uri
2301 (string-append
2302 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2303 version "/express-" version "-src.tgz"))
2304 (sha256
2305 (base32
2306 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2307 (build-system cmake-build-system)
2308 (arguments
2309 `(#:tests? #f ;no "check" target
2310 #:phases
2311 (modify-phases %standard-phases
2312 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2313 (lambda* (#:key inputs #:allow-other-keys)
2314 (substitute* "CMakeLists.txt"
2315 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2316 "set(Boost_USE_STATIC_LIBS OFF)")
2317 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2318 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2319 (substitute* "src/CMakeLists.txt"
2320 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2321 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2322 #t)))))
2323 (inputs
2324 `(("boost" ,boost)
2325 ("bamtools" ,bamtools)
2326 ("protobuf" ,protobuf)
2327 ("zlib" ,zlib)))
2328 (home-page "http://bio.math.berkeley.edu/eXpress")
2329 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2330 (description
2331 "eXpress is a streaming tool for quantifying the abundances of a set of
2332 target sequences from sampled subsequences. Example applications include
2333 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2334 analysis (from RNA-Seq), transcription factor binding quantification in
2335 ChIP-Seq, and analysis of metagenomic data.")
2336 (license license:artistic2.0)))
2337
2338 (define-public express-beta-diversity
2339 (package
2340 (name "express-beta-diversity")
2341 (version "1.0.7")
2342 (source (origin
2343 (method url-fetch)
2344 (uri
2345 (string-append
2346 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2347 version ".tar.gz"))
2348 (file-name (string-append name "-" version ".tar.gz"))
2349 (sha256
2350 (base32
2351 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2352 (build-system gnu-build-system)
2353 (arguments
2354 `(#:phases
2355 (modify-phases %standard-phases
2356 (delete 'configure)
2357 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2358 (replace 'check
2359 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2360 "-u"))))
2361 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2362 (replace 'install
2363 (lambda* (#:key outputs #:allow-other-keys)
2364 (let ((bin (string-append (assoc-ref outputs "out")
2365 "/bin")))
2366 (mkdir-p bin)
2367 (install-file "scripts/convertToEBD.py" bin)
2368 (install-file "bin/ExpressBetaDiversity" bin)
2369 #t))))))
2370 (inputs
2371 `(("python" ,python-2)))
2372 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2373 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2374 (description
2375 "Express Beta Diversity (EBD) calculates ecological beta diversity
2376 (dissimilarity) measures between biological communities. EBD implements a
2377 variety of diversity measures including those that make use of phylogenetic
2378 similarity of community members.")
2379 (license license:gpl3+)))
2380
2381 (define-public fasttree
2382 (package
2383 (name "fasttree")
2384 (version "2.1.10")
2385 (source (origin
2386 (method url-fetch)
2387 (uri (string-append
2388 "http://www.microbesonline.org/fasttree/FastTree-"
2389 version ".c"))
2390 (sha256
2391 (base32
2392 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2393 (build-system gnu-build-system)
2394 (arguments
2395 `(#:tests? #f ; no "check" target
2396 #:phases
2397 (modify-phases %standard-phases
2398 (delete 'unpack)
2399 (delete 'configure)
2400 (replace 'build
2401 (lambda* (#:key source #:allow-other-keys)
2402 (and (zero? (system* "gcc"
2403 "-O3"
2404 "-finline-functions"
2405 "-funroll-loops"
2406 "-Wall"
2407 "-o"
2408 "FastTree"
2409 source
2410 "-lm"))
2411 (zero? (system* "gcc"
2412 "-DOPENMP"
2413 "-fopenmp"
2414 "-O3"
2415 "-finline-functions"
2416 "-funroll-loops"
2417 "-Wall"
2418 "-o"
2419 "FastTreeMP"
2420 source
2421 "-lm")))))
2422 (replace 'install
2423 (lambda* (#:key outputs #:allow-other-keys)
2424 (let ((bin (string-append (assoc-ref outputs "out")
2425 "/bin")))
2426 (mkdir-p bin)
2427 (install-file "FastTree" bin)
2428 (install-file "FastTreeMP" bin)
2429 #t))))))
2430 (home-page "http://www.microbesonline.org/fasttree")
2431 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2432 (description
2433 "FastTree can handle alignments with up to a million of sequences in a
2434 reasonable amount of time and memory. For large alignments, FastTree is
2435 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2436 (license license:gpl2+)))
2437
2438 (define-public fastx-toolkit
2439 (package
2440 (name "fastx-toolkit")
2441 (version "0.0.14")
2442 (source (origin
2443 (method url-fetch)
2444 (uri
2445 (string-append
2446 "https://github.com/agordon/fastx_toolkit/releases/download/"
2447 version "/fastx_toolkit-" version ".tar.bz2"))
2448 (sha256
2449 (base32
2450 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2451 (build-system gnu-build-system)
2452 (inputs
2453 `(("libgtextutils" ,libgtextutils)))
2454 (native-inputs
2455 `(("pkg-config" ,pkg-config)))
2456 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2457 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2458 (description
2459 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2460 FASTA/FASTQ files preprocessing.
2461
2462 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2463 containing multiple short-reads sequences. The main processing of such
2464 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2465 is sometimes more productive to preprocess the files before mapping the
2466 sequences to the genome---manipulating the sequences to produce better mapping
2467 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2468 (license license:agpl3+)))
2469
2470 (define-public flexbar
2471 (package
2472 (name "flexbar")
2473 (version "2.5")
2474 (source (origin
2475 (method url-fetch)
2476 (uri
2477 (string-append "mirror://sourceforge/flexbar/"
2478 version "/flexbar_v" version "_src.tgz"))
2479 (sha256
2480 (base32
2481 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2482 (build-system cmake-build-system)
2483 (arguments
2484 `(#:configure-flags (list
2485 (string-append "-DFLEXBAR_BINARY_DIR="
2486 (assoc-ref %outputs "out")
2487 "/bin/"))
2488 #:phases
2489 (modify-phases %standard-phases
2490 (replace 'check
2491 (lambda* (#:key outputs #:allow-other-keys)
2492 (setenv "PATH" (string-append
2493 (assoc-ref outputs "out") "/bin:"
2494 (getenv "PATH")))
2495 (chdir "../flexbar_v2.5_src/test")
2496 (zero? (system* "bash" "flexbar_validate.sh"))))
2497 (delete 'install))))
2498 (inputs
2499 `(("tbb" ,tbb)
2500 ("zlib" ,zlib)))
2501 (native-inputs
2502 `(("pkg-config" ,pkg-config)
2503 ("seqan" ,seqan)))
2504 (home-page "http://flexbar.sourceforge.net")
2505 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2506 (description
2507 "Flexbar preprocesses high-throughput nucleotide sequencing data
2508 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2509 Moreover, trimming and filtering features are provided. Flexbar increases
2510 read mapping rates and improves genome and transcriptome assemblies. It
2511 supports next-generation sequencing data in fasta/q and csfasta/q format from
2512 Illumina, Roche 454, and the SOLiD platform.")
2513 (license license:gpl3)))
2514
2515 (define-public fraggenescan
2516 (package
2517 (name "fraggenescan")
2518 (version "1.30")
2519 (source
2520 (origin
2521 (method url-fetch)
2522 (uri
2523 (string-append "mirror://sourceforge/fraggenescan/"
2524 "FragGeneScan" version ".tar.gz"))
2525 (sha256
2526 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2527 (build-system gnu-build-system)
2528 (arguments
2529 `(#:phases
2530 (modify-phases %standard-phases
2531 (delete 'configure)
2532 (add-before 'build 'patch-paths
2533 (lambda* (#:key outputs #:allow-other-keys)
2534 (let* ((out (string-append (assoc-ref outputs "out")))
2535 (share (string-append out "/share/fraggenescan/")))
2536 (substitute* "run_FragGeneScan.pl"
2537 (("system\\(\"rm")
2538 (string-append "system(\"" (which "rm")))
2539 (("system\\(\"mv")
2540 (string-append "system(\"" (which "mv")))
2541 (("\\\"awk") (string-append "\"" (which "awk")))
2542 ;; This script and other programs expect the training files
2543 ;; to be in the non-standard location bin/train/XXX. Change
2544 ;; this to be share/fraggenescan/train/XXX instead.
2545 (("^\\$train.file = \\$dir.*")
2546 (string-append "$train_file = \""
2547 share
2548 "train/\".$FGS_train_file;")))
2549 (substitute* "run_hmm.c"
2550 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2551 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2552 #t))
2553 (replace 'build
2554 (lambda _ (and (zero? (system* "make" "clean"))
2555 (zero? (system* "make" "fgs")))))
2556 (replace 'install
2557 (lambda* (#:key outputs #:allow-other-keys)
2558 (let* ((out (string-append (assoc-ref outputs "out")))
2559 (bin (string-append out "/bin/"))
2560 (share (string-append out "/share/fraggenescan/train")))
2561 (install-file "run_FragGeneScan.pl" bin)
2562 (install-file "FragGeneScan" bin)
2563 (copy-recursively "train" share))))
2564 (delete 'check)
2565 (add-after 'install 'post-install-check
2566 ;; In lieu of 'make check', run one of the examples and check the
2567 ;; output files gets created.
2568 (lambda* (#:key outputs #:allow-other-keys)
2569 (let* ((out (string-append (assoc-ref outputs "out")))
2570 (bin (string-append out "/bin/"))
2571 (frag (string-append bin "run_FragGeneScan.pl")))
2572 (and (zero? (system* frag ; Test complete genome.
2573 "-genome=./example/NC_000913.fna"
2574 "-out=./test2"
2575 "-complete=1"
2576 "-train=complete"))
2577 (file-exists? "test2.faa")
2578 (file-exists? "test2.ffn")
2579 (file-exists? "test2.gff")
2580 (file-exists? "test2.out")
2581 (zero? (system* ; Test incomplete sequences.
2582 frag
2583 "-genome=./example/NC_000913-fgs.ffn"
2584 "-out=out"
2585 "-complete=0"
2586 "-train=454_30")))))))))
2587 (inputs
2588 `(("perl" ,perl)
2589 ("python" ,python-2))) ;not compatible with python 3.
2590 (home-page "https://sourceforge.net/projects/fraggenescan/")
2591 (synopsis "Finds potentially fragmented genes in short reads")
2592 (description
2593 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2594 short and error-prone DNA sequencing reads. It can also be applied to predict
2595 genes in incomplete assemblies or complete genomes.")
2596 ;; GPL3+ according to private correspondense with the authors.
2597 (license license:gpl3+)))
2598
2599 (define-public fxtract
2600 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2601 (package
2602 (name "fxtract")
2603 (version "2.3")
2604 (source
2605 (origin
2606 (method url-fetch)
2607 (uri (string-append
2608 "https://github.com/ctSkennerton/fxtract/archive/"
2609 version ".tar.gz"))
2610 (file-name (string-append "ctstennerton-util-"
2611 (string-take util-commit 7)
2612 "-checkout"))
2613 (sha256
2614 (base32
2615 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2616 (build-system gnu-build-system)
2617 (arguments
2618 `(#:make-flags (list
2619 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2620 "CC=gcc")
2621 #:test-target "fxtract_test"
2622 #:phases
2623 (modify-phases %standard-phases
2624 (delete 'configure)
2625 (add-before 'build 'copy-util
2626 (lambda* (#:key inputs #:allow-other-keys)
2627 (rmdir "util")
2628 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2629 #t))
2630 ;; Do not use make install as this requires additional dependencies.
2631 (replace 'install
2632 (lambda* (#:key outputs #:allow-other-keys)
2633 (let* ((out (assoc-ref outputs "out"))
2634 (bin (string-append out"/bin")))
2635 (install-file "fxtract" bin)
2636 #t))))))
2637 (inputs
2638 `(("pcre" ,pcre)
2639 ("zlib" ,zlib)))
2640 (native-inputs
2641 ;; ctskennerton-util is licensed under GPL2.
2642 `(("ctskennerton-util"
2643 ,(origin
2644 (method git-fetch)
2645 (uri (git-reference
2646 (url "https://github.com/ctSkennerton/util.git")
2647 (commit util-commit)))
2648 (file-name (string-append
2649 "ctstennerton-util-" util-commit "-checkout"))
2650 (sha256
2651 (base32
2652 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2653 (home-page "https://github.com/ctSkennerton/fxtract")
2654 (synopsis "Extract sequences from FASTA and FASTQ files")
2655 (description
2656 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2657 or FASTQ) file given a subsequence. It uses a simple substring search for
2658 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2659 lookups or multi-pattern searching as required. By default fxtract looks in
2660 the sequence of each record but can also be told to look in the header,
2661 comment or quality sections.")
2662 ;; 'util' requires SSE instructions.
2663 (supported-systems '("x86_64-linux"))
2664 (license license:expat))))
2665
2666 (define-public gemma
2667 (package
2668 (name "gemma")
2669 (version "0.96")
2670 (source (origin
2671 (method url-fetch)
2672 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2673 version ".tar.gz"))
2674 (file-name (string-append name "-" version ".tar.gz"))
2675 (sha256
2676 (base32
2677 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2678 (patches (search-patches "gemma-intel-compat.patch"))))
2679 (inputs
2680 `(("gsl" ,gsl)
2681 ("lapack" ,lapack)
2682 ("zlib" ,zlib)))
2683 (build-system gnu-build-system)
2684 (arguments
2685 `(#:make-flags
2686 '(,@(match (%current-system)
2687 ("x86_64-linux"
2688 '("FORCE_DYNAMIC=1"))
2689 ("i686-linux"
2690 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2691 (_
2692 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2693 #:phases
2694 (modify-phases %standard-phases
2695 (delete 'configure)
2696 (add-before 'build 'bin-mkdir
2697 (lambda _
2698 (mkdir-p "bin")
2699 #t))
2700 (replace 'install
2701 (lambda* (#:key outputs #:allow-other-keys)
2702 (let ((out (assoc-ref outputs "out")))
2703 (install-file "bin/gemma"
2704 (string-append
2705 out "/bin")))
2706 #t)))
2707 #:tests? #f)) ; no tests included yet
2708 (home-page "https://github.com/xiangzhou/GEMMA")
2709 (synopsis "Tool for genome-wide efficient mixed model association")
2710 (description
2711 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2712 standard linear mixed model resolver with application in genome-wide
2713 association studies (GWAS).")
2714 (license license:gpl3)))
2715
2716 (define-public grit
2717 (package
2718 (name "grit")
2719 (version "2.0.2")
2720 (source (origin
2721 (method url-fetch)
2722 (uri (string-append
2723 "https://github.com/nboley/grit/archive/"
2724 version ".tar.gz"))
2725 (file-name (string-append name "-" version ".tar.gz"))
2726 (sha256
2727 (base32
2728 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2729 (build-system python-build-system)
2730 (arguments
2731 `(#:python ,python-2
2732 #:phases
2733 (modify-phases %standard-phases
2734 (add-after 'unpack 'generate-from-cython-sources
2735 (lambda* (#:key inputs outputs #:allow-other-keys)
2736 ;; Delete these C files to force fresh generation from pyx sources.
2737 (delete-file "grit/sparsify_support_fns.c")
2738 (delete-file "grit/call_peaks_support_fns.c")
2739 (substitute* "setup.py"
2740 (("Cython.Setup") "Cython.Build")
2741 ;; Add numpy include path to fix compilation
2742 (("pyx\", \\]")
2743 (string-append "pyx\", ], include_dirs = ['"
2744 (assoc-ref inputs "python-numpy")
2745 "/lib/python2.7/site-packages/numpy/core/include/"
2746 "']")))
2747 #t)))))
2748 (inputs
2749 `(("python-scipy" ,python2-scipy)
2750 ("python-numpy" ,python2-numpy)
2751 ("python-pysam" ,python2-pysam)
2752 ("python-networkx" ,python2-networkx)))
2753 (native-inputs
2754 `(("python-cython" ,python2-cython)))
2755 (home-page "http://grit-bio.org")
2756 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2757 (description
2758 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2759 full length transcript models. When none of these data sources are available,
2760 GRIT can be run by providing a candidate set of TES or TSS sites. In
2761 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2762 also be run in quantification mode, where it uses a provided GTF file and just
2763 estimates transcript expression.")
2764 (license license:gpl3+)))
2765
2766 (define-public hisat
2767 (package
2768 (name "hisat")
2769 (version "0.1.4")
2770 (source (origin
2771 (method url-fetch)
2772 (uri (string-append
2773 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2774 version "-beta-source.zip"))
2775 (sha256
2776 (base32
2777 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2778 (build-system gnu-build-system)
2779 (arguments
2780 `(#:tests? #f ;no check target
2781 #:make-flags '("allall"
2782 ;; Disable unsupported `popcnt' instructions on
2783 ;; architectures other than x86_64
2784 ,@(if (string-prefix? "x86_64"
2785 (or (%current-target-system)
2786 (%current-system)))
2787 '()
2788 '("POPCNT_CAPABILITY=0")))
2789 #:phases
2790 (modify-phases %standard-phases
2791 (add-after 'unpack 'patch-sources
2792 (lambda _
2793 ;; XXX Cannot use snippet because zip files are not supported
2794 (substitute* "Makefile"
2795 (("^CC = .*$") "CC = gcc")
2796 (("^CPP = .*$") "CPP = g++")
2797 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2798 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2799 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2800 (substitute* '("hisat-build" "hisat-inspect")
2801 (("/usr/bin/env") (which "env")))
2802 #t))
2803 (replace 'install
2804 (lambda* (#:key outputs #:allow-other-keys)
2805 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2806 (for-each (lambda (file)
2807 (install-file file bin))
2808 (find-files
2809 "."
2810 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2811 #t))
2812 (delete 'configure))))
2813 (native-inputs
2814 `(("unzip" ,unzip)))
2815 (inputs
2816 `(("perl" ,perl)
2817 ("python" ,python)
2818 ("zlib" ,zlib)))
2819 ;; Non-portable SSE instructions are used so building fails on platforms
2820 ;; other than x86_64.
2821 (supported-systems '("x86_64-linux"))
2822 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2823 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2824 (description
2825 "HISAT is a fast and sensitive spliced alignment program for mapping
2826 RNA-seq reads. In addition to one global FM index that represents a whole
2827 genome, HISAT uses a large set of small FM indexes that collectively cover the
2828 whole genome. These small indexes (called local indexes) combined with
2829 several alignment strategies enable effective alignment of RNA-seq reads, in
2830 particular, reads spanning multiple exons.")
2831 (license license:gpl3+)))
2832
2833 (define-public hisat2
2834 (package
2835 (name "hisat2")
2836 (version "2.0.5")
2837 (source
2838 (origin
2839 (method url-fetch)
2840 ;; FIXME: a better source URL is
2841 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2842 ;; "/downloads/hisat2-" version "-source.zip")
2843 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2844 ;; but it is currently unavailable.
2845 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2846 (file-name (string-append name "-" version ".tar.gz"))
2847 (sha256
2848 (base32
2849 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2850 (build-system gnu-build-system)
2851 (arguments
2852 `(#:tests? #f ; no check target
2853 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2854 #:modules ((guix build gnu-build-system)
2855 (guix build utils)
2856 (srfi srfi-26))
2857 #:phases
2858 (modify-phases %standard-phases
2859 (add-after 'unpack 'make-deterministic
2860 (lambda _
2861 (substitute* "Makefile"
2862 (("`date`") "0"))
2863 #t))
2864 (delete 'configure)
2865 (replace 'install
2866 (lambda* (#:key outputs #:allow-other-keys)
2867 (let* ((out (assoc-ref outputs "out"))
2868 (bin (string-append out "/bin/"))
2869 (doc (string-append out "/share/doc/hisat2/")))
2870 (for-each
2871 (cut install-file <> bin)
2872 (find-files "."
2873 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2874 (mkdir-p doc)
2875 (install-file "doc/manual.inc.html" doc))
2876 #t)))))
2877 (native-inputs
2878 `(("unzip" ,unzip) ; needed for archive from ftp
2879 ("perl" ,perl)
2880 ("pandoc" ,ghc-pandoc))) ; for documentation
2881 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2882 (synopsis "Graph-based alignment of genomic sequencing reads")
2883 (description "HISAT2 is a fast and sensitive alignment program for mapping
2884 next-generation sequencing reads (both DNA and RNA) to a population of human
2885 genomes (as well as to a single reference genome). In addition to using one
2886 global @dfn{graph FM} (GFM) index that represents a population of human
2887 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2888 the whole genome. These small indexes, combined with several alignment
2889 strategies, enable rapid and accurate alignment of sequencing reads. This new
2890 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2891 ;; HISAT2 contains files from Bowtie2, which is released under
2892 ;; GPLv2 or later. The HISAT2 source files are released under
2893 ;; GPLv3 or later.
2894 (license license:gpl3+)))
2895
2896 (define-public hmmer
2897 (package
2898 (name "hmmer")
2899 (version "3.1b2")
2900 (source
2901 (origin
2902 (method url-fetch)
2903 (uri (string-append
2904 "http://eddylab.org/software/hmmer"
2905 (version-major version) "/"
2906 version "/hmmer-" version ".tar.gz"))
2907 (sha256
2908 (base32
2909 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2910 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2911 (build-system gnu-build-system)
2912 (native-inputs `(("perl" ,perl)))
2913 (home-page "http://hmmer.org/")
2914 (synopsis "Biosequence analysis using profile hidden Markov models")
2915 (description
2916 "HMMER is used for searching sequence databases for homologs of protein
2917 sequences, and for making protein sequence alignments. It implements methods
2918 using probabilistic models called profile hidden Markov models (profile
2919 HMMs).")
2920 (license (list license:gpl3+
2921 ;; The bundled library 'easel' is distributed
2922 ;; under The Janelia Farm Software License.
2923 (license:non-copyleft
2924 "file://easel/LICENSE"
2925 "See easel/LICENSE in the distribution.")))))
2926
2927 (define-public htseq
2928 (package
2929 (name "htseq")
2930 (version "0.9.1")
2931 (source (origin
2932 (method url-fetch)
2933 (uri (pypi-uri "HTSeq" version))
2934 (sha256
2935 (base32
2936 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2937 (build-system python-build-system)
2938 (native-inputs
2939 `(("python-cython" ,python-cython)))
2940 ;; Numpy needs to be propagated when htseq is used as a Python library.
2941 (propagated-inputs
2942 `(("python-numpy" ,python-numpy)))
2943 (inputs
2944 `(("python-pysam" ,python-pysam)
2945 ("python-matplotlib" ,python-matplotlib)))
2946 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2947 (synopsis "Analysing high-throughput sequencing data with Python")
2948 (description
2949 "HTSeq is a Python package that provides infrastructure to process data
2950 from high-throughput sequencing assays.")
2951 (license license:gpl3+)))
2952
2953 (define-public python2-htseq
2954 (package-with-python2 htseq))
2955
2956 (define-public java-htsjdk
2957 (package
2958 (name "java-htsjdk")
2959 (version "2.3.0") ; last version without build dependency on gradle
2960 (source (origin
2961 (method url-fetch)
2962 (uri (string-append
2963 "https://github.com/samtools/htsjdk/archive/"
2964 version ".tar.gz"))
2965 (file-name (string-append name "-" version ".tar.gz"))
2966 (sha256
2967 (base32
2968 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
2969 (modules '((guix build utils)))
2970 (snippet
2971 ;; Delete pre-built binaries
2972 '(begin
2973 (delete-file-recursively "lib")
2974 (mkdir-p "lib")
2975 #t))))
2976 (build-system ant-build-system)
2977 (arguments
2978 `(#:tests? #f ; test require Internet access
2979 #:jdk ,icedtea-8
2980 #:make-flags
2981 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2982 "/share/java/htsjdk/"))
2983 #:build-target "all"
2984 #:phases
2985 (modify-phases %standard-phases
2986 ;; The build phase also installs the jars
2987 (delete 'install))))
2988 (inputs
2989 `(("java-ngs" ,java-ngs)
2990 ("java-snappy-1" ,java-snappy-1)
2991 ("java-commons-compress" ,java-commons-compress)
2992 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
2993 ("java-commons-jexl-2" ,java-commons-jexl-2)
2994 ("java-xz" ,java-xz)))
2995 (native-inputs
2996 `(("java-testng" ,java-testng)))
2997 (home-page "http://samtools.github.io/htsjdk/")
2998 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2999 (description
3000 "HTSJDK is an implementation of a unified Java library for accessing
3001 common file formats, such as SAM and VCF, used for high-throughput
3002 sequencing (HTS) data. There are also an number of useful utilities for
3003 manipulating HTS data.")
3004 (license license:expat)))
3005
3006 (define-public java-htsjdk-latest
3007 (package
3008 (name "java-htsjdk")
3009 (version "2.14.3")
3010 (source (origin
3011 (method git-fetch)
3012 (uri (git-reference
3013 (url "https://github.com/samtools/htsjdk.git")
3014 (commit version)))
3015 (file-name (string-append name "-" version "-checkout"))
3016 (sha256
3017 (base32
3018 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3019 (build-system ant-build-system)
3020 (arguments
3021 `(#:tests? #f ; test require Scala
3022 #:jdk ,icedtea-8
3023 #:jar-name "htsjdk.jar"
3024 #:phases
3025 (modify-phases %standard-phases
3026 (add-after 'unpack 'remove-useless-build.xml
3027 (lambda _ (delete-file "build.xml") #t))
3028 ;; The tests require the scalatest package.
3029 (add-after 'unpack 'remove-tests
3030 (lambda _ (delete-file-recursively "src/test") #t)))))
3031 (inputs
3032 `(("java-ngs" ,java-ngs)
3033 ("java-snappy-1" ,java-snappy-1)
3034 ("java-commons-compress" ,java-commons-compress)
3035 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3036 ("java-commons-jexl-2" ,java-commons-jexl-2)
3037 ("java-xz" ,java-xz)))
3038 (native-inputs
3039 `(("java-junit" ,java-junit)))
3040 (home-page "http://samtools.github.io/htsjdk/")
3041 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3042 (description
3043 "HTSJDK is an implementation of a unified Java library for accessing
3044 common file formats, such as SAM and VCF, used for high-throughput
3045 sequencing (HTS) data. There are also an number of useful utilities for
3046 manipulating HTS data.")
3047 (license license:expat)))
3048
3049 ;; This is needed for picard 2.10.3
3050 (define-public java-htsjdk-2.10.1
3051 (package (inherit java-htsjdk-latest)
3052 (name "java-htsjdk")
3053 (version "2.10.1")
3054 (source (origin
3055 (method git-fetch)
3056 (uri (git-reference
3057 (url "https://github.com/samtools/htsjdk.git")
3058 (commit version)))
3059 (file-name (string-append name "-" version "-checkout"))
3060 (sha256
3061 (base32
3062 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3063 (build-system ant-build-system)
3064 (arguments
3065 `(#:tests? #f ; tests require Scala
3066 #:jdk ,icedtea-8
3067 #:jar-name "htsjdk.jar"
3068 #:phases
3069 (modify-phases %standard-phases
3070 (add-after 'unpack 'remove-useless-build.xml
3071 (lambda _ (delete-file "build.xml") #t))
3072 ;; The tests require the scalatest package.
3073 (add-after 'unpack 'remove-tests
3074 (lambda _ (delete-file-recursively "src/test") #t)))))))
3075
3076 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3077 ;; recent version of java-htsjdk, which depends on gradle.
3078 (define-public java-picard
3079 (package
3080 (name "java-picard")
3081 (version "2.3.0")
3082 (source (origin
3083 (method git-fetch)
3084 (uri (git-reference
3085 (url "https://github.com/broadinstitute/picard.git")
3086 (commit version)))
3087 (file-name (string-append "java-picard-" version "-checkout"))
3088 (sha256
3089 (base32
3090 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3091 (modules '((guix build utils)))
3092 (snippet
3093 '(begin
3094 ;; Delete pre-built binaries.
3095 (delete-file-recursively "lib")
3096 (mkdir-p "lib")
3097 (substitute* "build.xml"
3098 ;; Remove build-time dependency on git.
3099 (("failifexecutionfails=\"true\"")
3100 "failifexecutionfails=\"false\"")
3101 ;; Use our htsjdk.
3102 (("depends=\"compile-htsjdk, ")
3103 "depends=\"")
3104 (("depends=\"compile-htsjdk-tests, ")
3105 "depends=\"")
3106 ;; Build picard-lib.jar before building picard.jar
3107 (("name=\"picard-jar\" depends=\"" line)
3108 (string-append line "picard-lib-jar, ")))
3109 #t))))
3110 (build-system ant-build-system)
3111 (arguments
3112 `(#:build-target "picard-jar"
3113 #:test-target "test"
3114 ;; Tests require jacoco:coverage.
3115 #:tests? #f
3116 #:make-flags
3117 (list (string-append "-Dhtsjdk_lib_dir="
3118 (assoc-ref %build-inputs "java-htsjdk")
3119 "/share/java/htsjdk/")
3120 "-Dhtsjdk-classes=dist/tmp"
3121 (string-append "-Dhtsjdk-version="
3122 ,(package-version java-htsjdk)))
3123 #:jdk ,icedtea-8
3124 #:phases
3125 (modify-phases %standard-phases
3126 (add-after 'unpack 'use-our-htsjdk
3127 (lambda* (#:key inputs #:allow-other-keys)
3128 (substitute* "build.xml"
3129 (("\\$\\{htsjdk\\}/lib")
3130 (string-append (assoc-ref inputs "java-htsjdk")
3131 "/share/java/htsjdk/")))
3132 #t))
3133 (add-after 'unpack 'make-test-target-independent
3134 (lambda* (#:key inputs #:allow-other-keys)
3135 (substitute* "build.xml"
3136 (("name=\"test\" depends=\"compile, ")
3137 "name=\"test\" depends=\""))
3138 #t))
3139 (replace 'install (install-jars "dist")))))
3140 (inputs
3141 `(("java-htsjdk" ,java-htsjdk)
3142 ("java-guava" ,java-guava)))
3143 (native-inputs
3144 `(("java-testng" ,java-testng)))
3145 (home-page "http://broadinstitute.github.io/picard/")
3146 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3147 (description "Picard is a set of Java command line tools for manipulating
3148 high-throughput sequencing (HTS) data and formats. Picard is implemented
3149 using the HTSJDK Java library to support accessing file formats that are
3150 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3151 VCF.")
3152 (license license:expat)))
3153
3154 ;; This is the last version of Picard to provide net.sf.samtools
3155 (define-public java-picard-1.113
3156 (package (inherit java-picard)
3157 (name "java-picard")
3158 (version "1.113")
3159 (source (origin
3160 (method git-fetch)
3161 (uri (git-reference
3162 (url "https://github.com/broadinstitute/picard.git")
3163 (commit version)))
3164 (file-name (string-append "java-picard-" version "-checkout"))
3165 (sha256
3166 (base32
3167 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3168 (modules '((guix build utils)))
3169 (snippet
3170 '(begin
3171 ;; Delete pre-built binaries.
3172 (delete-file-recursively "lib")
3173 (mkdir-p "lib")
3174 #t))))
3175 (build-system ant-build-system)
3176 (arguments
3177 `(#:build-target "picard-jar"
3178 #:test-target "test"
3179 ;; FIXME: the class path at test time is wrong.
3180 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3181 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3182 #:tests? #f
3183 #:jdk ,icedtea-8
3184 ;; This is only used for tests.
3185 #:make-flags
3186 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3187 #:phases
3188 (modify-phases %standard-phases
3189 ;; Do not use bundled ant bzip2.
3190 (add-after 'unpack 'use-ant-bzip
3191 (lambda* (#:key inputs #:allow-other-keys)
3192 (substitute* "build.xml"
3193 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3194 (string-append (assoc-ref inputs "ant")
3195 "/lib/ant.jar")))
3196 #t))
3197 (add-after 'unpack 'make-test-target-independent
3198 (lambda* (#:key inputs #:allow-other-keys)
3199 (substitute* "build.xml"
3200 (("name=\"test\" depends=\"compile, ")
3201 "name=\"test\" depends=\"compile-tests, ")
3202 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3203 "name=\"compile\" depends=\"compile-src\""))
3204 #t))
3205 (add-after 'unpack 'fix-deflater-path
3206 (lambda* (#:key outputs #:allow-other-keys)
3207 (substitute* "src/java/net/sf/samtools/Defaults.java"
3208 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3209 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3210 (assoc-ref outputs "out")
3211 "/lib/jni/libIntelDeflater.so"
3212 "\")")))
3213 #t))
3214 ;; Build the deflater library, because we've previously deleted the
3215 ;; pre-built one. This can only be built with access to the JDK
3216 ;; sources.
3217 (add-after 'build 'build-jni
3218 (lambda* (#:key inputs #:allow-other-keys)
3219 (mkdir-p "lib/jni")
3220 (mkdir-p "jdk-src")
3221 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3222 "-xf" (assoc-ref inputs "jdk-src")))
3223 (zero? (system* "javah" "-jni"
3224 "-classpath" "classes"
3225 "-d" "lib/"
3226 "net.sf.samtools.util.zip.IntelDeflater"))
3227 (with-directory-excursion "src/c/inteldeflater"
3228 (zero? (system* "gcc" "-I../../../lib" "-I."
3229 (string-append "-I" (assoc-ref inputs "jdk")
3230 "/include/linux")
3231 "-I../../../jdk-src/src/share/native/common/"
3232 "-I../../../jdk-src/src/solaris/native/common/"
3233 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3234 (zero? (system* "gcc" "-shared"
3235 "-o" "../../../lib/jni/libIntelDeflater.so"
3236 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3237 ;; We can only build everything else after building the JNI library.
3238 (add-after 'build-jni 'build-rest
3239 (lambda* (#:key make-flags #:allow-other-keys)
3240 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3241 (add-before 'build 'set-JAVA6_HOME
3242 (lambda _
3243 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3244 #t))
3245 (replace 'install (install-jars "dist"))
3246 (add-after 'install 'install-jni-lib
3247 (lambda* (#:key outputs #:allow-other-keys)
3248 (let ((jni (string-append (assoc-ref outputs "out")
3249 "/lib/jni")))
3250 (mkdir-p jni)
3251 (install-file "lib/jni/libIntelDeflater.so" jni)
3252 #t))))))
3253 (inputs
3254 `(("java-snappy-1" ,java-snappy-1)
3255 ("java-commons-jexl-2" ,java-commons-jexl-2)
3256 ("java-cofoja" ,java-cofoja)
3257 ("ant" ,ant) ; for bzip2 support at runtime
3258 ("zlib" ,zlib)))
3259 (native-inputs
3260 `(("ant-apache-bcel" ,ant-apache-bcel)
3261 ("ant-junit" ,ant-junit)
3262 ("java-testng" ,java-testng)
3263 ("java-commons-bcel" ,java-commons-bcel)
3264 ("java-jcommander" ,java-jcommander)
3265 ("jdk" ,icedtea-8 "jdk")
3266 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3267
3268 (define-public fastqc
3269 (package
3270 (name "fastqc")
3271 (version "0.11.5")
3272 (source
3273 (origin
3274 (method url-fetch)
3275 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3276 "projects/fastqc/fastqc_v"
3277 version "_source.zip"))
3278 (sha256
3279 (base32
3280 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3281 (build-system ant-build-system)
3282 (arguments
3283 `(#:tests? #f ; there are no tests
3284 #:build-target "build"
3285 #:phases
3286 (modify-phases %standard-phases
3287 (add-after 'unpack 'fix-dependencies
3288 (lambda* (#:key inputs #:allow-other-keys)
3289 (substitute* "build.xml"
3290 (("jbzip2-0.9.jar")
3291 (string-append (assoc-ref inputs "java-jbzip2")
3292 "/share/java/jbzip2.jar"))
3293 (("sam-1.103.jar")
3294 (string-append (assoc-ref inputs "java-picard-1.113")
3295 "/share/java/sam-1.112.jar"))
3296 (("cisd-jhdf5.jar")
3297 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3298 "/share/java/sis-jhdf5.jar")))
3299 #t))
3300 ;; There is no installation target
3301 (replace 'install
3302 (lambda* (#:key inputs outputs #:allow-other-keys)
3303 (let* ((out (assoc-ref outputs "out"))
3304 (bin (string-append out "/bin"))
3305 (share (string-append out "/share/fastqc/"))
3306 (exe (string-append share "/fastqc")))
3307 (for-each mkdir-p (list bin share))
3308 (copy-recursively "bin" share)
3309 (substitute* exe
3310 (("my \\$java_bin = 'java';")
3311 (string-append "my $java_bin = '"
3312 (assoc-ref inputs "java")
3313 "/bin/java';")))
3314 (chmod exe #o555)
3315 (symlink exe (string-append bin "/fastqc"))
3316 #t))))))
3317 (inputs
3318 `(("java" ,icedtea)
3319 ("perl" ,perl) ; needed for the wrapper script
3320 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3321 ("java-picard-1.113" ,java-picard-1.113)
3322 ("java-jbzip2" ,java-jbzip2)))
3323 (native-inputs
3324 `(("unzip" ,unzip)))
3325 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3326 (synopsis "Quality control tool for high throughput sequence data")
3327 (description
3328 "FastQC aims to provide a simple way to do some quality control
3329 checks on raw sequence data coming from high throughput sequencing
3330 pipelines. It provides a modular set of analyses which you can use to
3331 give a quick impression of whether your data has any problems of which
3332 you should be aware before doing any further analysis.
3333
3334 The main functions of FastQC are:
3335
3336 @itemize
3337 @item Import of data from BAM, SAM or FastQ files (any variant);
3338 @item Providing a quick overview to tell you in which areas there may
3339 be problems;
3340 @item Summary graphs and tables to quickly assess your data;
3341 @item Export of results to an HTML based permanent report;
3342 @item Offline operation to allow automated generation of reports
3343 without running the interactive application.
3344 @end itemize\n")
3345 (license license:gpl3+)))
3346
3347 (define-public htslib
3348 (package
3349 (name "htslib")
3350 (version "1.6")
3351 (source (origin
3352 (method url-fetch)
3353 (uri (string-append
3354 "https://github.com/samtools/htslib/releases/download/"
3355 version "/htslib-" version ".tar.bz2"))
3356 (sha256
3357 (base32
3358 "1jsca3hg4rbr6iqq6imkj4lsvgl8g9768bcmny3hlff2w25vx24m"))))
3359 (build-system gnu-build-system)
3360 (arguments
3361 `(#:phases
3362 (modify-phases %standard-phases
3363 (add-after
3364 'unpack 'patch-tests
3365 (lambda _
3366 (substitute* "test/test.pl"
3367 (("/bin/bash") (which "bash")))
3368 #t)))))
3369 (inputs
3370 `(("openssl" ,openssl)
3371 ("curl" ,curl)
3372 ("zlib" ,zlib)))
3373 (native-inputs
3374 `(("perl" ,perl)))
3375 (home-page "http://www.htslib.org")
3376 (synopsis "C library for reading/writing high-throughput sequencing data")
3377 (description
3378 "HTSlib is a C library for reading/writing high-throughput sequencing
3379 data. It also provides the @command{bgzip}, @command{htsfile}, and
3380 @command{tabix} utilities.")
3381 ;; Files under cram/ are released under the modified BSD license;
3382 ;; the rest is released under the Expat license
3383 (license (list license:expat license:bsd-3))))
3384
3385 ;; This package should be removed once no packages rely upon it.
3386 (define htslib-1.3
3387 (package
3388 (inherit htslib)
3389 (version "1.3.1")
3390 (source (origin
3391 (method url-fetch)
3392 (uri (string-append
3393 "https://github.com/samtools/htslib/releases/download/"
3394 version "/htslib-" version ".tar.bz2"))
3395 (sha256
3396 (base32
3397 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3398
3399 (define-public idr
3400 (package
3401 (name "idr")
3402 (version "2.0.3")
3403 (source (origin
3404 (method url-fetch)
3405 (uri (string-append
3406 "https://github.com/nboley/idr/archive/"
3407 version ".tar.gz"))
3408 (file-name (string-append name "-" version ".tar.gz"))
3409 (sha256
3410 (base32
3411 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3412 ;; Delete generated C code.
3413 (snippet
3414 '(begin (delete-file "idr/inv_cdf.c") #t))))
3415 (build-system python-build-system)
3416 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3417 ;; are no longer part of this package. It also asserts False, which
3418 ;; causes the tests to always fail.
3419 (arguments `(#:tests? #f))
3420 (propagated-inputs
3421 `(("python-scipy" ,python-scipy)
3422 ("python-sympy" ,python-sympy)
3423 ("python-numpy" ,python-numpy)
3424 ("python-matplotlib" ,python-matplotlib)))
3425 (native-inputs
3426 `(("python-cython" ,python-cython)))
3427 (home-page "https://github.com/nboley/idr")
3428 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3429 (description
3430 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3431 to measure the reproducibility of findings identified from replicate
3432 experiments and provide highly stable thresholds based on reproducibility.")
3433 (license license:gpl2+)))
3434
3435 (define-public jellyfish
3436 (package
3437 (name "jellyfish")
3438 (version "2.2.7")
3439 (source (origin
3440 (method url-fetch)
3441 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3442 "releases/download/v" version
3443 "/jellyfish-" version ".tar.gz"))
3444 (sha256
3445 (base32
3446 "1a1iwq9pq54k2m9ypvwl5s0bqfl64gwh9dx5af9i382ajas2016q"))))
3447 (build-system gnu-build-system)
3448 (outputs '("out" ;for library
3449 "ruby" ;for Ruby bindings
3450 "python")) ;for Python bindings
3451 (arguments
3452 `(#:configure-flags
3453 (list (string-append "--enable-ruby-binding="
3454 (assoc-ref %outputs "ruby"))
3455 (string-append "--enable-python-binding="
3456 (assoc-ref %outputs "python")))
3457 #:phases
3458 (modify-phases %standard-phases
3459 (add-before 'check 'set-SHELL-variable
3460 (lambda _
3461 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3462 ;; to run tests.
3463 (setenv "SHELL" (which "bash"))
3464 #t)))))
3465 (native-inputs
3466 `(("bc" ,bc)
3467 ("time" ,time)
3468 ("ruby" ,ruby)
3469 ("python" ,python-2)
3470 ("pkg-config" ,pkg-config)))
3471 (inputs
3472 `(("htslib" ,htslib)))
3473 (synopsis "Tool for fast counting of k-mers in DNA")
3474 (description
3475 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3476 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3477 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3478 is a command-line program that reads FASTA and multi-FASTA files containing
3479 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3480 translated into a human-readable text format using the @code{jellyfish dump}
3481 command, or queried for specific k-mers with @code{jellyfish query}.")
3482 (home-page "http://www.genome.umd.edu/jellyfish.html")
3483 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3484 (supported-systems '("x86_64-linux"))
3485 ;; The combined work is published under the GPLv3 or later. Individual
3486 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3487 (license (list license:gpl3+ license:expat))))
3488
3489 (define-public khmer
3490 (package
3491 (name "khmer")
3492 (version "2.0")
3493 (source
3494 (origin
3495 (method url-fetch)
3496 (uri (pypi-uri "khmer" version))
3497 (sha256
3498 (base32
3499 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3500 (patches (search-patches "khmer-use-libraries.patch"))))
3501 (build-system python-build-system)
3502 (arguments
3503 `(#:phases
3504 (modify-phases %standard-phases
3505 (add-after 'unpack 'set-paths
3506 (lambda* (#:key inputs outputs #:allow-other-keys)
3507 ;; Delete bundled libraries.
3508 (delete-file-recursively "third-party/zlib")
3509 (delete-file-recursively "third-party/bzip2")
3510 ;; Replace bundled seqan.
3511 (let* ((seqan-all "third-party/seqan")
3512 (seqan-include (string-append
3513 seqan-all "/core/include")))
3514 (delete-file-recursively seqan-all)
3515 (copy-recursively (string-append (assoc-ref inputs "seqan")
3516 "/include/seqan")
3517 (string-append seqan-include "/seqan")))
3518 ;; We do not replace the bundled MurmurHash as the canonical
3519 ;; repository for this code 'SMHasher' is unsuitable for
3520 ;; providing a library. See
3521 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3522 #t))
3523 (add-after 'unpack 'set-cc
3524 (lambda _
3525 (setenv "CC" "gcc")
3526 #t))
3527 ;; It is simpler to test after installation.
3528 (delete 'check)
3529 (add-after 'install 'post-install-check
3530 (lambda* (#:key inputs outputs #:allow-other-keys)
3531 (let ((out (assoc-ref outputs "out")))
3532 (setenv "PATH"
3533 (string-append
3534 (getenv "PATH")
3535 ":"
3536 (assoc-ref outputs "out")
3537 "/bin"))
3538 (setenv "PYTHONPATH"
3539 (string-append
3540 (getenv "PYTHONPATH")
3541 ":"
3542 out
3543 "/lib/python"
3544 (string-take (string-take-right
3545 (assoc-ref inputs "python") 5) 3)
3546 "/site-packages"))
3547 (with-directory-excursion "build"
3548 (zero? (system* "nosetests" "khmer" "--attr"
3549 "!known_failing")))))))))
3550 (native-inputs
3551 `(("seqan" ,seqan)
3552 ("python-nose" ,python-nose)))
3553 (inputs
3554 `(("zlib" ,zlib)
3555 ("bzip2" ,bzip2)
3556 ("python-screed" ,python-screed)
3557 ("python-bz2file" ,python-bz2file)
3558 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3559 ;; until the next version of khmer (likely 2.1) is released.
3560 ("gcc" ,gcc-4.9)))
3561 (home-page "https://khmer.readthedocs.org/")
3562 (synopsis "K-mer counting, filtering and graph traversal library")
3563 (description "The khmer software is a set of command-line tools for
3564 working with DNA shotgun sequencing data from genomes, transcriptomes,
3565 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3566 sometimes better. Khmer can also identify and fix problems with shotgun
3567 data.")
3568 ;; When building on i686, armhf and mips64el, we get the following error:
3569 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3570 (supported-systems '("x86_64-linux" "aarch64-linux"))
3571 (license license:bsd-3)))
3572
3573 (define-public kaiju
3574 (package
3575 (name "kaiju")
3576 (version "1.5.0")
3577 (source (origin
3578 (method url-fetch)
3579 (uri (string-append
3580 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3581 version ".tar.gz"))
3582 (file-name (string-append name "-" version ".tar.gz"))
3583 (sha256
3584 (base32
3585 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3586 (build-system gnu-build-system)
3587 (arguments
3588 `(#:tests? #f ; There are no tests.
3589 #:phases
3590 (modify-phases %standard-phases
3591 (delete 'configure)
3592 (add-before 'build 'move-to-src-dir
3593 (lambda _ (chdir "src") #t))
3594 (replace 'install
3595 (lambda* (#:key inputs outputs #:allow-other-keys)
3596 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3597 (mkdir-p bin)
3598 (chdir "..")
3599 (copy-recursively "bin" bin)
3600 (copy-recursively "util" bin))
3601 #t)))))
3602 (inputs
3603 `(("perl" ,perl)))
3604 (home-page "http://kaiju.binf.ku.dk/")
3605 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3606 (description "Kaiju is a program for sensitive taxonomic classification
3607 of high-throughput sequencing reads from metagenomic whole genome sequencing
3608 experiments.")
3609 (license license:gpl3+)))
3610
3611 (define-public macs
3612 (package
3613 (name "macs")
3614 (version "2.1.0.20151222")
3615 (source (origin
3616 (method url-fetch)
3617 (uri (pypi-uri "MACS2" version))
3618 (sha256
3619 (base32
3620 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3621 (build-system python-build-system)
3622 (arguments
3623 `(#:python ,python-2 ; only compatible with Python 2.7
3624 #:tests? #f)) ; no test target
3625 (inputs
3626 `(("python-numpy" ,python2-numpy)))
3627 (home-page "https://github.com/taoliu/MACS/")
3628 (synopsis "Model based analysis for ChIP-Seq data")
3629 (description
3630 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3631 identifying transcript factor binding sites named Model-based Analysis of
3632 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3633 the significance of enriched ChIP regions and it improves the spatial
3634 resolution of binding sites through combining the information of both
3635 sequencing tag position and orientation.")
3636 (license license:bsd-3)))
3637
3638 (define-public mafft
3639 (package
3640 (name "mafft")
3641 (version "7.313")
3642 (source (origin
3643 (method url-fetch)
3644 (uri (string-append
3645 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3646 "-without-extensions-src.tgz"))
3647 (file-name (string-append name "-" version ".tgz"))
3648 (sha256
3649 (base32
3650 "0r83qmg2if8mi6jyx3xdf8ar2gcxl7r9nmj98jr7lxym97v61a2k"))))
3651 (build-system gnu-build-system)
3652 (arguments
3653 `(#:tests? #f ; no automated tests, though there are tests in the read me
3654 #:make-flags (let ((out (assoc-ref %outputs "out")))
3655 (list (string-append "PREFIX=" out)
3656 (string-append "BINDIR="
3657 (string-append out "/bin"))))
3658 #:phases
3659 (modify-phases %standard-phases
3660 (add-after 'unpack 'enter-dir
3661 (lambda _ (chdir "core") #t))
3662 (add-after 'enter-dir 'patch-makefile
3663 (lambda _
3664 ;; on advice from the MAFFT authors, there is no need to
3665 ;; distribute mafft-profile, mafft-distance, or
3666 ;; mafft-homologs.rb as they are too "specialised".
3667 (substitute* "Makefile"
3668 ;; remove mafft-homologs.rb from SCRIPTS
3669 (("^SCRIPTS = mafft mafft-homologs.rb")
3670 "SCRIPTS = mafft")
3671 ;; remove mafft-homologs from MANPAGES
3672 (("^MANPAGES = mafft.1 mafft-homologs.1")
3673 "MANPAGES = mafft.1")
3674 ;; remove mafft-distance from PROGS
3675 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3676 "PROGS = dvtditr dndfast7 dndblast sextet5")
3677 ;; remove mafft-profile from PROGS
3678 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3679 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3680 (("^rm -f mafft-profile mafft-profile.exe") "#")
3681 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3682 ;; do not install MAN pages in libexec folder
3683 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3684 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3685 #t))
3686 (add-after 'enter-dir 'patch-paths
3687 (lambda* (#:key inputs #:allow-other-keys)
3688 (substitute* '("pairash.c"
3689 "mafft.tmpl")
3690 (("perl") (which "perl"))
3691 (("([\"`| ])awk" _ prefix)
3692 (string-append prefix (which "awk")))
3693 (("grep") (which "grep")))
3694 #t))
3695 (delete 'configure)
3696 (add-after 'install 'wrap-programs
3697 (lambda* (#:key outputs #:allow-other-keys)
3698 (let* ((out (assoc-ref outputs "out"))
3699 (bin (string-append out "/bin"))
3700 (path (string-append
3701 (assoc-ref %build-inputs "coreutils") "/bin:")))
3702 (for-each (lambda (file)
3703 (wrap-program file
3704 `("PATH" ":" prefix (,path))))
3705 (find-files bin)))
3706 #t)))))
3707 (inputs
3708 `(("perl" ,perl)
3709 ("ruby" ,ruby)
3710 ("gawk" ,gawk)
3711 ("grep" ,grep)
3712 ("coreutils" ,coreutils)))
3713 (home-page "http://mafft.cbrc.jp/alignment/software/")
3714 (synopsis "Multiple sequence alignment program")
3715 (description
3716 "MAFFT offers a range of multiple alignment methods for nucleotide and
3717 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3718 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3719 sequences).")
3720 (license (license:non-copyleft
3721 "http://mafft.cbrc.jp/alignment/software/license.txt"
3722 "BSD-3 with different formatting"))))
3723
3724 (define-public mash
3725 (package
3726 (name "mash")
3727 (version "1.1.1")
3728 (source (origin
3729 (method url-fetch)
3730 (uri (string-append
3731 "https://github.com/marbl/mash/archive/v"
3732 version ".tar.gz"))
3733 (file-name (string-append name "-" version ".tar.gz"))
3734 (sha256
3735 (base32
3736 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3737 (modules '((guix build utils)))
3738 (snippet
3739 ;; Delete bundled kseq.
3740 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3741 '(delete-file "src/mash/kseq.h"))))
3742 (build-system gnu-build-system)
3743 (arguments
3744 `(#:tests? #f ; No tests.
3745 #:configure-flags
3746 (list
3747 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3748 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3749 #:make-flags (list "CC=gcc")
3750 #:phases
3751 (modify-phases %standard-phases
3752 (add-after 'unpack 'fix-includes
3753 (lambda _
3754 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3755 (("^#include \"kseq\\.h\"")
3756 "#include \"htslib/kseq.h\""))
3757 #t))
3758 (add-after 'fix-includes 'autoconf
3759 (lambda _ (zero? (system* "autoconf")))))))
3760 (native-inputs
3761 `(("autoconf" ,autoconf)
3762 ;; Capnproto and htslib are statically embedded in the final
3763 ;; application. Therefore we also list their licenses, below.
3764 ("capnproto" ,capnproto)
3765 ("htslib" ,htslib)))
3766 (inputs
3767 `(("gsl" ,gsl)
3768 ("zlib" ,zlib)))
3769 (supported-systems '("x86_64-linux"))
3770 (home-page "https://mash.readthedocs.io")
3771 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3772 (description "Mash is a fast sequence distance estimator that uses the
3773 MinHash algorithm and is designed to work with genomes and metagenomes in the
3774 form of assemblies or reads.")
3775 (license (list license:bsd-3 ; Mash
3776 license:expat ; HTSlib and capnproto
3777 license:public-domain ; MurmurHash 3
3778 license:cpl1.0)))) ; Open Bloom Filter
3779
3780 (define-public metabat
3781 (package
3782 (name "metabat")
3783 (version "2.12.1")
3784 (source
3785 (origin
3786 (method url-fetch)
3787 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3788 version ".tar.gz"))
3789 (file-name (string-append name "-" version ".tar.gz"))
3790 (sha256
3791 (base32
3792 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3793 (patches (search-patches "metabat-fix-compilation.patch"))))
3794 (build-system scons-build-system)
3795 (arguments
3796 `(#:scons ,scons-python2
3797 #:scons-flags
3798 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
3799 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
3800 #:tests? #f ;; Tests are run during the build phase.
3801 #:phases
3802 (modify-phases %standard-phases
3803 (add-after 'unpack 'fix-includes
3804 (lambda _
3805 (substitute* "src/BamUtils.h"
3806 (("^#include \"bam/bam\\.h\"")
3807 "#include \"samtools/bam.h\"")
3808 (("^#include \"bam/sam\\.h\"")
3809 "#include \"samtools/sam.h\""))
3810 (substitute* "src/KseqReader.h"
3811 (("^#include \"bam/kseq\\.h\"")
3812 "#include \"htslib/kseq.h\""))
3813 #t))
3814 (add-after 'unpack 'fix-scons
3815 (lambda* (#:key inputs #:allow-other-keys)
3816 (substitute* "SConstruct"
3817 (("^htslib_dir += 'samtools'")
3818 (string-append "htslib_dir = '"
3819 (assoc-ref inputs "htslib")
3820 "'"))
3821 (("^samtools_dir = 'samtools'")
3822 (string-append "samtools_dir = '"
3823 (assoc-ref inputs "samtools")
3824 "'"))
3825 (("^findStaticOrShared\\('bam', hts_lib")
3826 (string-append "findStaticOrShared('bam', '"
3827 (assoc-ref inputs "samtools")
3828 "/lib'"))
3829 ;; Do not distribute README.
3830 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3831 #t)))))
3832 (inputs
3833 `(("zlib" ,zlib)
3834 ("perl" ,perl)
3835 ("samtools" ,samtools)
3836 ("htslib" ,htslib)
3837 ("boost" ,boost)))
3838 (home-page "https://bitbucket.org/berkeleylab/metabat")
3839 (synopsis
3840 "Reconstruction of single genomes from complex microbial communities")
3841 (description
3842 "Grouping large genomic fragments assembled from shotgun metagenomic
3843 sequences to deconvolute complex microbial communities, or metagenome binning,
3844 enables the study of individual organisms and their interactions. MetaBAT is
3845 an automated metagenome binning software, which integrates empirical
3846 probabilistic distances of genome abundance and tetranucleotide frequency.")
3847 ;; The source code contains inline assembly.
3848 (supported-systems '("x86_64-linux" "i686-linux"))
3849 (license (license:non-copyleft "file://license.txt"
3850 "See license.txt in the distribution."))))
3851
3852 (define-public minced
3853 (package
3854 (name "minced")
3855 (version "0.2.0")
3856 (source (origin
3857 (method url-fetch)
3858 (uri (string-append
3859 "https://github.com/ctSkennerton/minced/archive/"
3860 version ".tar.gz"))
3861 (file-name (string-append name "-" version ".tar.gz"))
3862 (sha256
3863 (base32
3864 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3865 (build-system gnu-build-system)
3866 (arguments
3867 `(#:test-target "test"
3868 #:phases
3869 (modify-phases %standard-phases
3870 (delete 'configure)
3871 (add-before 'check 'fix-test
3872 (lambda _
3873 ;; Fix test for latest version.
3874 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3875 (("minced:0.1.6") "minced:0.2.0"))
3876 #t))
3877 (replace 'install ; No install target.
3878 (lambda* (#:key inputs outputs #:allow-other-keys)
3879 (let* ((out (assoc-ref outputs "out"))
3880 (bin (string-append out "/bin"))
3881 (wrapper (string-append bin "/minced")))
3882 ;; Minced comes with a wrapper script that tries to figure out where
3883 ;; it is located before running the JAR. Since these paths are known
3884 ;; to us, we build our own wrapper to avoid coreutils dependency.
3885 (install-file "minced.jar" bin)
3886 (with-output-to-file wrapper
3887 (lambda _
3888 (display
3889 (string-append
3890 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3891 (assoc-ref inputs "jre") "/bin/java -jar "
3892 bin "/minced.jar \"$@\"\n"))))
3893 (chmod wrapper #o555)))))))
3894 (native-inputs
3895 `(("jdk" ,icedtea "jdk")))
3896 (inputs
3897 `(("bash" ,bash)
3898 ("jre" ,icedtea "out")))
3899 (home-page "https://github.com/ctSkennerton/minced")
3900 (synopsis "Mining CRISPRs in Environmental Datasets")
3901 (description
3902 "MinCED is a program to find Clustered Regularly Interspaced Short
3903 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3904 unassembled metagenomic reads, but is mainly designed for full genomes and
3905 assembled metagenomic sequence.")
3906 (license license:gpl3+)))
3907
3908 (define-public miso
3909 (package
3910 (name "miso")
3911 (version "0.5.4")
3912 (source (origin
3913 (method url-fetch)
3914 (uri (pypi-uri "misopy" version))
3915 (sha256
3916 (base32
3917 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
3918 (modules '((guix build utils)))
3919 (snippet
3920 '(substitute* "setup.py"
3921 ;; Use setuptools, or else the executables are not
3922 ;; installed.
3923 (("distutils.core") "setuptools")
3924 ;; use "gcc" instead of "cc" for compilation
3925 (("^defines")
3926 "cc.set_executables(
3927 compiler='gcc',
3928 compiler_so='gcc',
3929 linker_exe='gcc',
3930 linker_so='gcc -shared'); defines")))))
3931 (build-system python-build-system)
3932 (arguments
3933 `(#:python ,python-2 ; only Python 2 is supported
3934 #:tests? #f)) ; no "test" target
3935 (inputs
3936 `(("samtools" ,samtools)
3937 ("python-numpy" ,python2-numpy)
3938 ("python-pysam" ,python2-pysam)
3939 ("python-scipy" ,python2-scipy)
3940 ("python-matplotlib" ,python2-matplotlib)))
3941 (native-inputs
3942 `(("python-mock" ,python2-mock) ;for tests
3943 ("python-pytz" ,python2-pytz))) ;for tests
3944 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3945 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3946 (description
3947 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3948 the expression level of alternatively spliced genes from RNA-Seq data, and
3949 identifies differentially regulated isoforms or exons across samples. By
3950 modeling the generative process by which reads are produced from isoforms in
3951 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3952 that a read originated from a particular isoform.")
3953 (license license:gpl2)))
3954
3955 (define-public muscle
3956 (package
3957 (name "muscle")
3958 (version "3.8.1551")
3959 (source (origin
3960 (method url-fetch/tarbomb)
3961 (uri (string-append
3962 "http://www.drive5.com/muscle/muscle_src_"
3963 version ".tar.gz"))
3964 (sha256
3965 (base32
3966 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3967 (build-system gnu-build-system)
3968 (arguments
3969 `(#:make-flags (list "LDLIBS = -lm")
3970 #:phases
3971 (modify-phases %standard-phases
3972 (delete 'configure)
3973 (replace 'check
3974 ;; There are no tests, so just test if it runs.
3975 (lambda _ (zero? (system* "./muscle" "-version"))))
3976 (replace 'install
3977 (lambda* (#:key outputs #:allow-other-keys)
3978 (let* ((out (assoc-ref outputs "out"))
3979 (bin (string-append out "/bin")))
3980 (install-file "muscle" bin)))))))
3981 (home-page "http://www.drive5.com/muscle")
3982 (synopsis "Multiple sequence alignment program")
3983 (description
3984 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3985 program for nucleotide and protein sequences.")
3986 ;; License information found in 'muscle -h' and usage.cpp.
3987 (license license:public-domain)))
3988
3989 (define-public newick-utils
3990 ;; There are no recent releases so we package from git.
3991 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3992 (package
3993 (name "newick-utils")
3994 (version (string-append "1.6-1." (string-take commit 8)))
3995 (source (origin
3996 (method git-fetch)
3997 (uri (git-reference
3998 (url "https://github.com/tjunier/newick_utils.git")
3999 (commit commit)))
4000 (file-name (string-append name "-" version "-checkout"))
4001 (sha256
4002 (base32
4003 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4004 (build-system gnu-build-system)
4005 (arguments
4006 `(#:phases
4007 (modify-phases %standard-phases
4008 (add-after 'unpack 'autoconf
4009 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4010 (inputs
4011 ;; XXX: TODO: Enable Lua and Guile bindings.
4012 ;; https://github.com/tjunier/newick_utils/issues/13
4013 `(("libxml2" ,libxml2)
4014 ("flex" ,flex)
4015 ("bison" ,bison)))
4016 (native-inputs
4017 `(("autoconf" ,autoconf)
4018 ("automake" ,automake)
4019 ("libtool" ,libtool)))
4020 (synopsis "Programs for working with newick format phylogenetic trees")
4021 (description
4022 "Newick-utils is a suite of utilities for processing phylogenetic trees
4023 in Newick format. Functions include re-rooting, extracting subtrees,
4024 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4025 (home-page "https://github.com/tjunier/newick_utils")
4026 (license license:bsd-3))))
4027
4028 (define-public orfm
4029 (package
4030 (name "orfm")
4031 (version "0.7.1")
4032 (source (origin
4033 (method url-fetch)
4034 (uri (string-append
4035 "https://github.com/wwood/OrfM/releases/download/v"
4036 version "/orfm-" version ".tar.gz"))
4037 (sha256
4038 (base32
4039 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4040 (build-system gnu-build-system)
4041 (inputs `(("zlib" ,zlib)))
4042 (native-inputs
4043 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4044 ("ruby-rspec" ,ruby-rspec)
4045 ("ruby" ,ruby)))
4046 (synopsis "Simple and not slow open reading frame (ORF) caller")
4047 (description
4048 "An ORF caller finds stretches of DNA that, when translated, are not
4049 interrupted by stop codons. OrfM finds and prints these ORFs.")
4050 (home-page "https://github.com/wwood/OrfM")
4051 (license license:lgpl3+)))
4052
4053 (define-public pplacer
4054 (let ((commit "g807f6f3"))
4055 (package
4056 (name "pplacer")
4057 ;; The commit should be updated with each version change.
4058 (version "1.1.alpha19")
4059 (source
4060 (origin
4061 (method url-fetch)
4062 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4063 version ".tar.gz"))
4064 (file-name (string-append name "-" version ".tar.gz"))
4065 (sha256
4066 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4067 (build-system ocaml-build-system)
4068 (arguments
4069 `(#:ocaml ,ocaml-4.01
4070 #:findlib ,ocaml4.01-findlib
4071 #:modules ((guix build ocaml-build-system)
4072 (guix build utils)
4073 (ice-9 ftw))
4074 #:phases
4075 (modify-phases %standard-phases
4076 (delete 'configure)
4077 (add-after 'unpack 'replace-bundled-cddlib
4078 (lambda* (#:key inputs #:allow-other-keys)
4079 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4080 (local-dir "cddlib_guix"))
4081 (mkdir local-dir)
4082 (with-directory-excursion local-dir
4083 (system* "tar" "xvf" cddlib-src))
4084 (let ((cddlib-src-folder
4085 (string-append local-dir "/"
4086 (list-ref (scandir local-dir) 2)
4087 "/lib-src")))
4088 (for-each
4089 (lambda (file)
4090 (copy-file file
4091 (string-append "cdd_src/" (basename file))))
4092 (find-files cddlib-src-folder ".*[ch]$")))
4093 #t)))
4094 (add-after 'unpack 'fix-makefile
4095 (lambda _
4096 ;; Remove system calls to 'git'.
4097 (substitute* "Makefile"
4098 (("^DESCRIPT:=pplacer-.*")
4099 (string-append
4100 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4101 (substitute* "myocamlbuild.ml"
4102 (("git describe --tags --long .*\\\" with")
4103 (string-append
4104 "echo -n v" ,version "-" ,commit "\" with")))
4105 #t))
4106 (replace 'install
4107 (lambda* (#:key outputs #:allow-other-keys)
4108 (let* ((out (assoc-ref outputs "out"))
4109 (bin (string-append out "/bin")))
4110 (copy-recursively "bin" bin))
4111 #t)))))
4112 (native-inputs
4113 `(("zlib" ,zlib)
4114 ("gsl" ,gsl)
4115 ("ocaml-ounit" ,ocaml4.01-ounit)
4116 ("ocaml-batteries" ,ocaml4.01-batteries)
4117 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4118 ("ocaml-csv" ,ocaml4.01-csv)
4119 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4120 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4121 ("ocaml-mcl" ,ocaml4.01-mcl)
4122 ("ocaml-gsl" ,ocaml4.01-gsl)
4123 ("cddlib-src" ,(package-source cddlib))))
4124 (propagated-inputs
4125 `(("pplacer-scripts" ,pplacer-scripts)))
4126 (synopsis "Phylogenetic placement of biological sequences")
4127 (description
4128 "Pplacer places query sequences on a fixed reference phylogenetic tree
4129 to maximize phylogenetic likelihood or posterior probability according to a
4130 reference alignment. Pplacer is designed to be fast, to give useful
4131 information about uncertainty, and to offer advanced visualization and
4132 downstream analysis.")
4133 (home-page "http://matsen.fhcrc.org/pplacer")
4134 (license license:gpl3))))
4135
4136 ;; This package is installed alongside 'pplacer'. It is a separate package so
4137 ;; that it can use the python-build-system for the scripts that are
4138 ;; distributed alongside the main OCaml binaries.
4139 (define pplacer-scripts
4140 (package
4141 (inherit pplacer)
4142 (name "pplacer-scripts")
4143 (build-system python-build-system)
4144 (arguments
4145 `(#:python ,python-2
4146 #:phases
4147 (modify-phases %standard-phases
4148 (add-after 'unpack 'enter-scripts-dir
4149 (lambda _ (chdir "scripts")))
4150 (replace 'check
4151 (lambda _
4152 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4153 (add-after 'install 'wrap-executables
4154 (lambda* (#:key inputs outputs #:allow-other-keys)
4155 (let* ((out (assoc-ref outputs "out"))
4156 (bin (string-append out "/bin")))
4157 (let ((path (string-append
4158 (assoc-ref inputs "hmmer") "/bin:"
4159 (assoc-ref inputs "infernal") "/bin")))
4160 (display path)
4161 (wrap-program (string-append bin "/refpkg_align.py")
4162 `("PATH" ":" prefix (,path))))
4163 (let ((path (string-append
4164 (assoc-ref inputs "hmmer") "/bin")))
4165 (wrap-program (string-append bin "/hrefpkg_query.py")
4166 `("PATH" ":" prefix (,path)))))
4167 #t)))))
4168 (inputs
4169 `(("infernal" ,infernal)
4170 ("hmmer" ,hmmer)))
4171 (propagated-inputs
4172 `(("python-biopython" ,python2-biopython)
4173 ("taxtastic" ,taxtastic)))
4174 (synopsis "Pplacer Python scripts")))
4175
4176 (define-public python2-pbcore
4177 (package
4178 (name "python2-pbcore")
4179 (version "1.2.10")
4180 (source (origin
4181 (method url-fetch)
4182 (uri (pypi-uri "pbcore" version))
4183 (sha256
4184 (base32
4185 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4186 (build-system python-build-system)
4187 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4188 (propagated-inputs
4189 `(("python-cython" ,python2-cython)
4190 ("python-numpy" ,python2-numpy)
4191 ("python-pysam" ,python2-pysam)
4192 ("python-h5py" ,python2-h5py)))
4193 (native-inputs
4194 `(("python-nose" ,python2-nose)
4195 ("python-sphinx" ,python2-sphinx)
4196 ("python-pyxb" ,python2-pyxb)))
4197 (home-page "http://pacificbiosciences.github.io/pbcore/")
4198 (synopsis "Library for reading and writing PacBio data files")
4199 (description
4200 "The pbcore package provides Python APIs for interacting with PacBio data
4201 files and writing bioinformatics applications.")
4202 (license license:bsd-3)))
4203
4204 (define-public python2-warpedlmm
4205 (package
4206 (name "python2-warpedlmm")
4207 (version "0.21")
4208 (source
4209 (origin
4210 (method url-fetch)
4211 (uri (string-append
4212 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4213 version ".zip"))
4214 (sha256
4215 (base32
4216 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4217 (build-system python-build-system)
4218 (arguments
4219 `(#:python ,python-2)) ; requires Python 2.7
4220 (propagated-inputs
4221 `(("python-scipy" ,python2-scipy)
4222 ("python-numpy" ,python2-numpy)
4223 ("python-matplotlib" ,python2-matplotlib)
4224 ("python-fastlmm" ,python2-fastlmm)
4225 ("python-pandas" ,python2-pandas)
4226 ("python-pysnptools" ,python2-pysnptools)))
4227 (native-inputs
4228 `(("python-mock" ,python2-mock)
4229 ("python-nose" ,python2-nose)
4230 ("unzip" ,unzip)))
4231 (home-page "https://github.com/PMBio/warpedLMM")
4232 (synopsis "Implementation of warped linear mixed models")
4233 (description
4234 "WarpedLMM is a Python implementation of the warped linear mixed model,
4235 which automatically learns an optimal warping function (or transformation) for
4236 the phenotype as it models the data.")
4237 (license license:asl2.0)))
4238
4239 (define-public pbtranscript-tofu
4240 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4241 (package
4242 (name "pbtranscript-tofu")
4243 (version (string-append "2.2.3." (string-take commit 7)))
4244 (source (origin
4245 (method git-fetch)
4246 (uri (git-reference
4247 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4248 (commit commit)))
4249 (file-name (string-append name "-" version "-checkout"))
4250 (sha256
4251 (base32
4252 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4253 (modules '((guix build utils)))
4254 (snippet
4255 '(begin
4256 ;; remove bundled Cython sources
4257 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4258 #t))))
4259 (build-system python-build-system)
4260 (arguments
4261 `(#:python ,python-2
4262 ;; FIXME: Tests fail with "No such file or directory:
4263 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4264 #:tests? #f
4265 #:phases
4266 (modify-phases %standard-phases
4267 (add-after 'unpack 'enter-directory
4268 (lambda _
4269 (chdir "pbtranscript-tofu/pbtranscript/")
4270 #t))
4271 ;; With setuptools version 18.0 and later this setup.py hack causes
4272 ;; a build error, so we disable it.
4273 (add-after 'enter-directory 'patch-setuppy
4274 (lambda _
4275 (substitute* "setup.py"
4276 (("if 'setuptools.extension' in sys.modules:")
4277 "if False:"))
4278 #t)))))
4279 (inputs
4280 `(("python-numpy" ,python2-numpy)
4281 ("python-bx-python" ,python2-bx-python)
4282 ("python-networkx" ,python2-networkx)
4283 ("python-scipy" ,python2-scipy)
4284 ("python-pbcore" ,python2-pbcore)
4285 ("python-h5py" ,python2-h5py)))
4286 (native-inputs
4287 `(("python-cython" ,python2-cython)
4288 ("python-nose" ,python2-nose)))
4289 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4290 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4291 (description
4292 "pbtranscript-tofu contains scripts to analyze transcriptome data
4293 generated using the PacBio Iso-Seq protocol.")
4294 (license license:bsd-3))))
4295
4296 (define-public prank
4297 (package
4298 (name "prank")
4299 (version "150803")
4300 (source (origin
4301 (method url-fetch)
4302 (uri (string-append
4303 "http://wasabiapp.org/download/prank/prank.source."
4304 version ".tgz"))
4305 (sha256
4306 (base32
4307 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4308 (build-system gnu-build-system)
4309 (arguments
4310 `(#:phases
4311 (modify-phases %standard-phases
4312 (add-after 'unpack 'enter-src-dir
4313 (lambda _
4314 (chdir "src")
4315 #t))
4316 (add-after 'unpack 'remove-m64-flag
4317 ;; Prank will build with the correct 'bit-ness' without this flag
4318 ;; and this allows building on 32-bit machines.
4319 (lambda _ (substitute* "src/Makefile"
4320 (("-m64") ""))
4321 #t))
4322 (delete 'configure)
4323 (replace 'install
4324 (lambda* (#:key outputs #:allow-other-keys)
4325 (let* ((out (assoc-ref outputs "out"))
4326 (bin (string-append out "/bin"))
4327 (man (string-append out "/share/man/man1"))
4328 (path (string-append
4329 (assoc-ref %build-inputs "mafft") "/bin:"
4330 (assoc-ref %build-inputs "exonerate") "/bin:"
4331 (assoc-ref %build-inputs "bppsuite") "/bin")))
4332 (install-file "prank" bin)
4333 (wrap-program (string-append bin "/prank")
4334 `("PATH" ":" prefix (,path)))
4335 (install-file "prank.1" man))
4336 #t)))))
4337 (inputs
4338 `(("mafft" ,mafft)
4339 ("exonerate" ,exonerate)
4340 ("bppsuite" ,bppsuite)))
4341 (home-page "http://wasabiapp.org/software/prank/")
4342 (synopsis "Probabilistic multiple sequence alignment program")
4343 (description
4344 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4345 codon and amino-acid sequences. It is based on a novel algorithm that treats
4346 insertions correctly and avoids over-estimation of the number of deletion
4347 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4348 in phylogenetics and correctly takes into account the evolutionary distances
4349 between sequences. Lastly, PRANK allows for defining a potential structure
4350 for sequences to be aligned and then, simultaneously with the alignment,
4351 predicts the locations of structural units in the sequences.")
4352 (license license:gpl2+)))
4353
4354 (define-public proteinortho
4355 (package
4356 (name "proteinortho")
4357 (version "5.16b")
4358 (source
4359 (origin
4360 (method url-fetch)
4361 (uri
4362 (string-append
4363 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4364 version "_src.tar.gz"))
4365 (sha256
4366 (base32
4367 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4368 (build-system gnu-build-system)
4369 (arguments
4370 `(#:test-target "test"
4371 #:phases
4372 (modify-phases %standard-phases
4373 (replace 'configure
4374 ;; There is no configure script, so we modify the Makefile directly.
4375 (lambda* (#:key outputs #:allow-other-keys)
4376 (substitute* "Makefile"
4377 (("INSTALLDIR=.*")
4378 (string-append
4379 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4380 #t))
4381 (add-before 'install 'make-install-directory
4382 ;; The install directory is not created during 'make install'.
4383 (lambda* (#:key outputs #:allow-other-keys)
4384 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4385 #t))
4386 (add-after 'install 'wrap-programs
4387 (lambda* (#:key inputs outputs #:allow-other-keys)
4388 (let* ((path (getenv "PATH"))
4389 (out (assoc-ref outputs "out"))
4390 (binary (string-append out "/bin/proteinortho5.pl")))
4391 (wrap-program binary `("PATH" ":" prefix (,path))))
4392 #t)))))
4393 (inputs
4394 `(("perl" ,perl)
4395 ("python" ,python-2)
4396 ("blast+" ,blast+)))
4397 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4398 (synopsis "Detect orthologous genes across species")
4399 (description
4400 "Proteinortho is a tool to detect orthologous genes across different
4401 species. For doing so, it compares similarities of given gene sequences and
4402 clusters them to find significant groups. The algorithm was designed to handle
4403 large-scale data and can be applied to hundreds of species at once.")
4404 (license license:gpl2+)))
4405
4406 (define-public pyicoteo
4407 (package
4408 (name "pyicoteo")
4409 (version "2.0.7")
4410 (source
4411 (origin
4412 (method url-fetch)
4413 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4414 "pyicoteo/get/v" version ".tar.bz2"))
4415 (file-name (string-append name "-" version ".tar.bz2"))
4416 (sha256
4417 (base32
4418 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4419 (build-system python-build-system)
4420 (arguments
4421 `(#:python ,python-2 ; does not work with Python 3
4422 #:tests? #f)) ; there are no tests
4423 (inputs
4424 `(("python2-matplotlib" ,python2-matplotlib)))
4425 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4426 (synopsis "Analyze high-throughput genetic sequencing data")
4427 (description
4428 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4429 sequencing data. It works with genomic coordinates. There are currently six
4430 different command-line tools:
4431
4432 @enumerate
4433 @item pyicoregion: for generating exploratory regions automatically;
4434 @item pyicoenrich: for differential enrichment between two conditions;
4435 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4436 @item pyicos: for genomic coordinates manipulation;
4437 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4438 @item pyicount: to count how many reads from N experiment files overlap in a
4439 region file;
4440 @item pyicotrocol: to combine operations from pyicoteo.
4441 @end enumerate\n")
4442 (license license:gpl3+)))
4443
4444 (define-public prodigal
4445 (package
4446 (name "prodigal")
4447 (version "2.6.3")
4448 (source (origin
4449 (method url-fetch)
4450 (uri (string-append
4451 "https://github.com/hyattpd/Prodigal/archive/v"
4452 version ".tar.gz"))
4453 (file-name (string-append name "-" version ".tar.gz"))
4454 (sha256
4455 (base32
4456 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4457 (build-system gnu-build-system)
4458 (arguments
4459 `(#:tests? #f ;no check target
4460 #:make-flags (list (string-append "INSTALLDIR="
4461 (assoc-ref %outputs "out")
4462 "/bin"))
4463 #:phases
4464 (modify-phases %standard-phases
4465 (delete 'configure))))
4466 (home-page "http://prodigal.ornl.gov")
4467 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4468 (description
4469 "Prodigal runs smoothly on finished genomes, draft genomes, and
4470 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4471 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4472 partial genes, and identifies translation initiation sites.")
4473 (license license:gpl3+)))
4474
4475 (define-public roary
4476 (package
4477 (name "roary")
4478 (version "3.11.0")
4479 (source
4480 (origin
4481 (method url-fetch)
4482 (uri (string-append
4483 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4484 version ".tar.gz"))
4485 (sha256
4486 (base32
4487 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4488 (build-system perl-build-system)
4489 (arguments
4490 `(#:phases
4491 (modify-phases %standard-phases
4492 (delete 'configure)
4493 (delete 'build)
4494 (replace 'check
4495 (lambda _
4496 ;; The tests are not run by default, so we run each test file
4497 ;; directly.
4498 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4499 (getenv "PATH")))
4500 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4501 (getenv "PERL5LIB")))
4502 (zero? (length (filter (lambda (file)
4503 (display file)(display "\n")
4504 (not (zero? (system* "perl" file))))
4505 (find-files "t" ".*\\.t$"))))))
4506 (replace 'install
4507 ;; There is no 'install' target in the Makefile.
4508 (lambda* (#:key outputs #:allow-other-keys)
4509 (let* ((out (assoc-ref outputs "out"))
4510 (bin (string-append out "/bin"))
4511 (perl (string-append out "/lib/perl5/site_perl"))
4512 (roary-plots "contrib/roary_plots"))
4513 (mkdir-p bin)
4514 (mkdir-p perl)
4515 (copy-recursively "bin" bin)
4516 (copy-recursively "lib" perl)
4517 #t)))
4518 (add-after 'install 'wrap-programs
4519 (lambda* (#:key inputs outputs #:allow-other-keys)
4520 (let* ((out (assoc-ref outputs "out"))
4521 (perl5lib (getenv "PERL5LIB"))
4522 (path (getenv "PATH")))
4523 (for-each (lambda (prog)
4524 (let ((binary (string-append out "/" prog)))
4525 (wrap-program binary
4526 `("PERL5LIB" ":" prefix
4527 (,(string-append perl5lib ":" out
4528 "/lib/perl5/site_perl"))))
4529 (wrap-program binary
4530 `("PATH" ":" prefix
4531 (,(string-append path ":" out "/bin"))))))
4532 (find-files "bin" ".*[^R]$"))
4533 (let ((file
4534 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4535 (r-site-lib (getenv "R_LIBS_SITE"))
4536 (coreutils-path
4537 (string-append (assoc-ref inputs "coreutils") "/bin")))
4538 (wrap-program file
4539 `("R_LIBS_SITE" ":" prefix
4540 (,(string-append r-site-lib ":" out "/site-library/"))))
4541 (wrap-program file
4542 `("PATH" ":" prefix
4543 (,(string-append coreutils-path ":" out "/bin"))))))
4544 #t)))))
4545 (native-inputs
4546 `(("perl-env-path" ,perl-env-path)
4547 ("perl-test-files" ,perl-test-files)
4548 ("perl-test-most" ,perl-test-most)
4549 ("perl-test-output" ,perl-test-output)))
4550 (inputs
4551 `(("perl-array-utils" ,perl-array-utils)
4552 ("bioperl" ,bioperl-minimal)
4553 ("perl-digest-md5-file" ,perl-digest-md5-file)
4554 ("perl-exception-class" ,perl-exception-class)
4555 ("perl-file-find-rule" ,perl-file-find-rule)
4556 ("perl-file-grep" ,perl-file-grep)
4557 ("perl-file-slurper" ,perl-file-slurper)
4558 ("perl-file-which" ,perl-file-which)
4559 ("perl-graph" ,perl-graph)
4560 ("perl-graph-readwrite" ,perl-graph-readwrite)
4561 ("perl-log-log4perl" ,perl-log-log4perl)
4562 ("perl-moose" ,perl-moose)
4563 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4564 ("perl-text-csv" ,perl-text-csv)
4565 ("bedtools" ,bedtools)
4566 ("cd-hit" ,cd-hit)
4567 ("blast+" ,blast+)
4568 ("mcl" ,mcl)
4569 ("parallel" ,parallel)
4570 ("prank" ,prank)
4571 ("mafft" ,mafft)
4572 ("fasttree" ,fasttree)
4573 ("grep" ,grep)
4574 ("sed" ,sed)
4575 ("gawk" ,gawk)
4576 ("r-minimal" ,r-minimal)
4577 ("r-ggplot2" ,r-ggplot2)
4578 ("coreutils" ,coreutils)))
4579 (home-page "http://sanger-pathogens.github.io/Roary")
4580 (synopsis "High speed stand-alone pan genome pipeline")
4581 (description
4582 "Roary is a high speed stand alone pan genome pipeline, which takes
4583 annotated assemblies in GFF3 format (produced by the Prokka program) and
4584 calculates the pan genome. Using a standard desktop PC, it can analyse
4585 datasets with thousands of samples, without compromising the quality of the
4586 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4587 single processor. Roary is not intended for metagenomics or for comparing
4588 extremely diverse sets of genomes.")
4589 (license license:gpl3)))
4590
4591 (define-public raxml
4592 (package
4593 (name "raxml")
4594 (version "8.2.10")
4595 (source
4596 (origin
4597 (method url-fetch)
4598 (uri
4599 (string-append
4600 "https://github.com/stamatak/standard-RAxML/archive/v"
4601 version ".tar.gz"))
4602 (file-name (string-append name "-" version ".tar.gz"))
4603 (sha256
4604 (base32
4605 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4606 (build-system gnu-build-system)
4607 (arguments
4608 `(#:tests? #f ; There are no tests.
4609 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4610 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4611 #:phases
4612 (modify-phases %standard-phases
4613 (delete 'configure)
4614 (replace 'install
4615 (lambda* (#:key outputs #:allow-other-keys)
4616 (let* ((out (assoc-ref outputs "out"))
4617 (bin (string-append out "/bin"))
4618 (executable "raxmlHPC-HYBRID"))
4619 (install-file executable bin)
4620 (symlink (string-append bin "/" executable) "raxml"))
4621 #t)))))
4622 (inputs
4623 `(("openmpi" ,openmpi)))
4624 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4625 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4626 (description
4627 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4628 phylogenies.")
4629 ;; The source includes x86 specific code
4630 (supported-systems '("x86_64-linux" "i686-linux"))
4631 (license license:gpl2+)))
4632
4633 (define-public rsem
4634 (package
4635 (name "rsem")
4636 (version "1.2.20")
4637 (source
4638 (origin
4639 (method url-fetch)
4640 (uri
4641 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4642 version ".tar.gz"))
4643 (sha256
4644 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4645 (patches (search-patches "rsem-makefile.patch"))
4646 (modules '((guix build utils)))
4647 (snippet
4648 '(begin
4649 ;; remove bundled copy of boost
4650 (delete-file-recursively "boost")
4651 #t))))
4652 (build-system gnu-build-system)
4653 (arguments
4654 `(#:tests? #f ;no "check" target
4655 #:phases
4656 (modify-phases %standard-phases
4657 ;; No "configure" script.
4658 ;; Do not build bundled samtools library.
4659 (replace 'configure
4660 (lambda _
4661 (substitute* "Makefile"
4662 (("^all : sam/libbam.a") "all : "))
4663 #t))
4664 (replace 'install
4665 (lambda* (#:key outputs #:allow-other-keys)
4666 (let* ((out (string-append (assoc-ref outputs "out")))
4667 (bin (string-append out "/bin/"))
4668 (perl (string-append out "/lib/perl5/site_perl")))
4669 (mkdir-p bin)
4670 (mkdir-p perl)
4671 (for-each (lambda (file)
4672 (install-file file bin))
4673 (find-files "." "rsem-.*"))
4674 (install-file "rsem_perl_utils.pm" perl))
4675 #t))
4676 (add-after
4677 'install 'wrap-program
4678 (lambda* (#:key outputs #:allow-other-keys)
4679 (let ((out (assoc-ref outputs "out")))
4680 (for-each (lambda (prog)
4681 (wrap-program (string-append out "/bin/" prog)
4682 `("PERL5LIB" ":" prefix
4683 (,(string-append out "/lib/perl5/site_perl")))))
4684 '("rsem-plot-transcript-wiggles"
4685 "rsem-calculate-expression"
4686 "rsem-generate-ngvector"
4687 "rsem-run-ebseq"
4688 "rsem-prepare-reference")))
4689 #t)))))
4690 (inputs
4691 `(("boost" ,boost)
4692 ("ncurses" ,ncurses)
4693 ("r-minimal" ,r-minimal)
4694 ("perl" ,perl)
4695 ("samtools" ,samtools-0.1)
4696 ("zlib" ,zlib)))
4697 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4698 (synopsis "Estimate gene expression levels from RNA-Seq data")
4699 (description
4700 "RSEM is a software package for estimating gene and isoform expression
4701 levels from RNA-Seq data. The RSEM package provides a user-friendly
4702 interface, supports threads for parallel computation of the EM algorithm,
4703 single-end and paired-end read data, quality scores, variable-length reads and
4704 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4705 interval estimates for expression levels. For visualization, it can generate
4706 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4707 (license license:gpl3+)))
4708
4709 (define-public rseqc
4710 (package
4711 (name "rseqc")
4712 (version "2.6.1")
4713 (source
4714 (origin
4715 (method url-fetch)
4716 (uri
4717 (string-append "mirror://sourceforge/rseqc/"
4718 "RSeQC-" version ".tar.gz"))
4719 (sha256
4720 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4721 (modules '((guix build utils)))
4722 (snippet
4723 '(begin
4724 ;; remove bundled copy of pysam
4725 (delete-file-recursively "lib/pysam")
4726 (substitute* "setup.py"
4727 ;; remove dependency on outdated "distribute" module
4728 (("^from distribute_setup import use_setuptools") "")
4729 (("^use_setuptools\\(\\)") "")
4730 ;; do not use bundled copy of pysam
4731 (("^have_pysam = False") "have_pysam = True"))))))
4732 (build-system python-build-system)
4733 (arguments `(#:python ,python-2))
4734 (inputs
4735 `(("python-cython" ,python2-cython)
4736 ("python-pysam" ,python2-pysam)
4737 ("python-numpy" ,python2-numpy)
4738 ("zlib" ,zlib)))
4739 (native-inputs
4740 `(("python-nose" ,python2-nose)))
4741 (home-page "http://rseqc.sourceforge.net/")
4742 (synopsis "RNA-seq quality control package")
4743 (description
4744 "RSeQC provides a number of modules that can comprehensively evaluate
4745 high throughput sequence data, especially RNA-seq data. Some basic modules
4746 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4747 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4748 distribution, coverage uniformity, strand specificity, etc.")
4749 (license license:gpl3+)))
4750
4751 (define-public seek
4752 ;; There are no release tarballs. According to the installation
4753 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4754 ;; stable release is identified by this changeset ID.
4755 (let ((changeset "2329130")
4756 (revision "1"))
4757 (package
4758 (name "seek")
4759 (version (string-append "0-" revision "." changeset))
4760 (source (origin
4761 (method hg-fetch)
4762 (uri (hg-reference
4763 (url "https://bitbucket.org/libsleipnir/sleipnir")
4764 (changeset changeset)))
4765 (sha256
4766 (base32
4767 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4768 (build-system gnu-build-system)
4769 (arguments
4770 `(#:modules ((srfi srfi-1)
4771 (guix build gnu-build-system)
4772 (guix build utils))
4773 #:phases
4774 (let ((dirs '("SeekMiner"
4775 "SeekEvaluator"
4776 "SeekPrep"
4777 "Distancer"
4778 "Data2DB"
4779 "PCL2Bin")))
4780 (modify-phases %standard-phases
4781 (add-before 'configure 'bootstrap
4782 (lambda _
4783 (zero? (system* "bash" "gen_auto"))))
4784 (add-after 'build 'build-additional-tools
4785 (lambda* (#:key make-flags #:allow-other-keys)
4786 (every (lambda (dir)
4787 (with-directory-excursion (string-append "tools/" dir)
4788 (zero? (apply system* "make" make-flags))))
4789 dirs)))
4790 (add-after 'install 'install-additional-tools
4791 (lambda* (#:key make-flags #:allow-other-keys)
4792 (fold (lambda (dir result)
4793 (with-directory-excursion (string-append "tools/" dir)
4794 (and result
4795 (zero? (apply system*
4796 `("make" ,@make-flags "install"))))))
4797 #t dirs)))))))
4798 (inputs
4799 `(("gsl" ,gsl)
4800 ("boost" ,boost)
4801 ("libsvm" ,libsvm)
4802 ("readline" ,readline)
4803 ("gengetopt" ,gengetopt)
4804 ("log4cpp" ,log4cpp)))
4805 (native-inputs
4806 `(("autoconf" ,autoconf)
4807 ("automake" ,automake)
4808 ("perl" ,perl)))
4809 (home-page "http://seek.princeton.edu")
4810 (synopsis "Gene co-expression search engine")
4811 (description
4812 "SEEK is a computational gene co-expression search engine. SEEK provides
4813 biologists with a way to navigate the massive human expression compendium that
4814 now contains thousands of expression datasets. SEEK returns a robust ranking
4815 of co-expressed genes in the biological area of interest defined by the user's
4816 query genes. It also prioritizes thousands of expression datasets according
4817 to the user's query of interest.")
4818 (license license:cc-by3.0))))
4819
4820 (define-public samtools
4821 (package
4822 (name "samtools")
4823 (version "1.5")
4824 (source
4825 (origin
4826 (method url-fetch)
4827 (uri
4828 (string-append "mirror://sourceforge/samtools/samtools/"
4829 version "/samtools-" version ".tar.bz2"))
4830 (sha256
4831 (base32
4832 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4833 (build-system gnu-build-system)
4834 (arguments
4835 `(#:modules ((ice-9 ftw)
4836 (ice-9 regex)
4837 (guix build gnu-build-system)
4838 (guix build utils))
4839 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4840 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4841 #:phases
4842 (modify-phases %standard-phases
4843 (add-after 'unpack 'patch-tests
4844 (lambda _
4845 (substitute* "test/test.pl"
4846 ;; The test script calls out to /bin/bash
4847 (("/bin/bash") (which "bash")))
4848 #t))
4849 (add-after 'install 'install-library
4850 (lambda* (#:key outputs #:allow-other-keys)
4851 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4852 (install-file "libbam.a" lib)
4853 #t)))
4854 (add-after 'install 'install-headers
4855 (lambda* (#:key outputs #:allow-other-keys)
4856 (let ((include (string-append (assoc-ref outputs "out")
4857 "/include/samtools/")))
4858 (for-each (lambda (file)
4859 (install-file file include))
4860 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4861 #t))))))
4862 (native-inputs `(("pkg-config" ,pkg-config)))
4863 (inputs
4864 `(("htslib" ,htslib)
4865 ("ncurses" ,ncurses)
4866 ("perl" ,perl)
4867 ("python" ,python)
4868 ("zlib" ,zlib)))
4869 (home-page "http://samtools.sourceforge.net")
4870 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4871 (description
4872 "Samtools implements various utilities for post-processing nucleotide
4873 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4874 variant calling (in conjunction with bcftools), and a simple alignment
4875 viewer.")
4876 (license license:expat)))
4877
4878 (define-public samtools-0.1
4879 ;; This is the most recent version of the 0.1 line of samtools. The input
4880 ;; and output formats differ greatly from that used and produced by samtools
4881 ;; 1.x and is still used in many bioinformatics pipelines.
4882 (package (inherit samtools)
4883 (version "0.1.19")
4884 (source
4885 (origin
4886 (method url-fetch)
4887 (uri
4888 (string-append "mirror://sourceforge/samtools/samtools/"
4889 version "/samtools-" version ".tar.bz2"))
4890 (sha256
4891 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4892 (arguments
4893 `(#:tests? #f ;no "check" target
4894 ,@(substitute-keyword-arguments (package-arguments samtools)
4895 ((#:make-flags flags)
4896 `(cons "LIBCURSES=-lncurses" ,flags))
4897 ((#:phases phases)
4898 `(modify-phases ,phases
4899 (replace 'install
4900 (lambda* (#:key outputs #:allow-other-keys)
4901 (let ((bin (string-append
4902 (assoc-ref outputs "out") "/bin")))
4903 (mkdir-p bin)
4904 (install-file "samtools" bin)
4905 #t)))
4906 (delete 'patch-tests)
4907 (delete 'configure))))))))
4908
4909 (define-public mosaik
4910 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4911 (package
4912 (name "mosaik")
4913 (version "2.2.30")
4914 (source (origin
4915 ;; There are no release tarballs nor tags.
4916 (method git-fetch)
4917 (uri (git-reference
4918 (url "https://github.com/wanpinglee/MOSAIK.git")
4919 (commit commit)))
4920 (file-name (string-append name "-" version))
4921 (sha256
4922 (base32
4923 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4924 (build-system gnu-build-system)
4925 (arguments
4926 `(#:tests? #f ; no tests
4927 #:make-flags (list "CC=gcc")
4928 #:phases
4929 (modify-phases %standard-phases
4930 (replace 'configure
4931 (lambda _ (chdir "src") #t))
4932 (replace 'install
4933 (lambda* (#:key outputs #:allow-other-keys)
4934 (let ((bin (string-append (assoc-ref outputs "out")
4935 "/bin")))
4936 (mkdir-p bin)
4937 (copy-recursively "../bin" bin)
4938 #t))))))
4939 (inputs
4940 `(("perl" ,perl)
4941 ("zlib" ,zlib)))
4942 (supported-systems '("x86_64-linux"))
4943 (home-page "https://github.com/wanpinglee/MOSAIK")
4944 (synopsis "Map nucleotide sequence reads to reference genomes")
4945 (description
4946 "MOSAIK is a program for mapping second and third-generation sequencing
4947 reads to a reference genome. MOSAIK can align reads generated by all the
4948 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4949 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4950 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4951 ;; code released into the public domain:
4952 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4953 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4954 (license (list license:gpl2+ license:public-domain)))))
4955
4956 (define-public ngs-sdk
4957 (package
4958 (name "ngs-sdk")
4959 (version "1.3.0")
4960 (source
4961 (origin
4962 (method url-fetch)
4963 (uri
4964 (string-append "https://github.com/ncbi/ngs/archive/"
4965 version ".tar.gz"))
4966 (file-name (string-append name "-" version ".tar.gz"))
4967 (sha256
4968 (base32
4969 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4970 (build-system gnu-build-system)
4971 (arguments
4972 `(#:parallel-build? #f ; not supported
4973 #:tests? #f ; no "check" target
4974 #:phases
4975 (modify-phases %standard-phases
4976 (replace 'configure
4977 (lambda* (#:key outputs #:allow-other-keys)
4978 (let ((out (assoc-ref outputs "out")))
4979 ;; Allow 'konfigure.perl' to find 'package.prl'.
4980 (setenv "PERL5LIB"
4981 (string-append ".:" (getenv "PERL5LIB")))
4982
4983 ;; The 'configure' script doesn't recognize things like
4984 ;; '--enable-fast-install'.
4985 (zero? (system* "./configure"
4986 (string-append "--build-prefix=" (getcwd) "/build")
4987 (string-append "--prefix=" out))))))
4988 (add-after 'unpack 'enter-dir
4989 (lambda _ (chdir "ngs-sdk") #t)))))
4990 (native-inputs `(("perl" ,perl)))
4991 ;; According to the test
4992 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4993 ;; in ngs-sdk/setup/konfigure.perl
4994 (supported-systems '("i686-linux" "x86_64-linux"))
4995 (home-page "https://github.com/ncbi/ngs")
4996 (synopsis "API for accessing Next Generation Sequencing data")
4997 (description
4998 "NGS is a domain-specific API for accessing reads, alignments and pileups
4999 produced from Next Generation Sequencing. The API itself is independent from
5000 any particular back-end implementation, and supports use of multiple back-ends
5001 simultaneously.")
5002 (license license:public-domain)))
5003
5004 (define-public java-ngs
5005 (package (inherit ngs-sdk)
5006 (name "java-ngs")
5007 (arguments
5008 `(,@(substitute-keyword-arguments
5009 `(#:modules ((guix build gnu-build-system)
5010 (guix build utils)
5011 (srfi srfi-1)
5012 (srfi srfi-26))
5013 ,@(package-arguments ngs-sdk))
5014 ((#:phases phases)
5015 `(modify-phases ,phases
5016 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5017 (inputs
5018 `(("jdk" ,icedtea "jdk")
5019 ("ngs-sdk" ,ngs-sdk)))
5020 (synopsis "Java bindings for NGS SDK")))
5021
5022 (define-public ncbi-vdb
5023 (package
5024 (name "ncbi-vdb")
5025 (version "2.8.2")
5026 (source
5027 (origin
5028 (method url-fetch)
5029 (uri
5030 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5031 version ".tar.gz"))
5032 (file-name (string-append name "-" version ".tar.gz"))
5033 (sha256
5034 (base32
5035 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5036 (build-system gnu-build-system)
5037 (arguments
5038 `(#:parallel-build? #f ; not supported
5039 #:tests? #f ; no "check" target
5040 #:phases
5041 (modify-phases %standard-phases
5042 (add-before 'configure 'set-perl-search-path
5043 (lambda _
5044 ;; Work around "dotless @INC" build failure.
5045 (setenv "PERL5LIB"
5046 (string-append (getcwd) "/setup:"
5047 (getenv "PERL5LIB")))
5048 #t))
5049 (replace 'configure
5050 (lambda* (#:key inputs outputs #:allow-other-keys)
5051 (let ((out (assoc-ref outputs "out")))
5052 ;; Override include path for libmagic
5053 (substitute* "setup/package.prl"
5054 (("name => 'magic', Include => '/usr/include'")
5055 (string-append "name=> 'magic', Include => '"
5056 (assoc-ref inputs "libmagic")
5057 "/include" "'")))
5058
5059 ;; Install kdf5 library (needed by sra-tools)
5060 (substitute* "build/Makefile.install"
5061 (("LIBRARIES_TO_INSTALL =")
5062 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5063
5064 (substitute* "build/Makefile.env"
5065 (("CFLAGS =" prefix)
5066 (string-append prefix "-msse2 ")))
5067
5068 ;; Override search path for ngs-java
5069 (substitute* "setup/package.prl"
5070 (("/usr/local/ngs/ngs-java")
5071 (assoc-ref inputs "java-ngs")))
5072
5073 ;; The 'configure' script doesn't recognize things like
5074 ;; '--enable-fast-install'.
5075 (zero? (system*
5076 "./configure"
5077 (string-append "--build-prefix=" (getcwd) "/build")
5078 (string-append "--prefix=" (assoc-ref outputs "out"))
5079 (string-append "--debug")
5080 (string-append "--with-xml2-prefix="
5081 (assoc-ref inputs "libxml2"))
5082 (string-append "--with-ngs-sdk-prefix="
5083 (assoc-ref inputs "ngs-sdk"))
5084 (string-append "--with-hdf5-prefix="
5085 (assoc-ref inputs "hdf5")))))))
5086 (add-after 'install 'install-interfaces
5087 (lambda* (#:key outputs #:allow-other-keys)
5088 ;; Install interface libraries. On i686 the interface libraries
5089 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5090 ;; architecture name ("i386") instead of the target system prefix
5091 ;; ("i686").
5092 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5093 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5094 ,(system->linux-architecture
5095 (or (%current-target-system)
5096 (%current-system)))
5097 "/rel/ilib")
5098 (string-append (assoc-ref outputs "out")
5099 "/ilib"))
5100 ;; Install interface headers
5101 (copy-recursively "interfaces"
5102 (string-append (assoc-ref outputs "out")
5103 "/include"))
5104 #t))
5105 ;; These files are needed by sra-tools.
5106 (add-after 'install 'install-configuration-files
5107 (lambda* (#:key outputs #:allow-other-keys)
5108 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5109 (mkdir target)
5110 (install-file "libs/kfg/default.kfg" target)
5111 (install-file "libs/kfg/certs.kfg" target))
5112 #t)))))
5113 (inputs
5114 `(("libxml2" ,libxml2)
5115 ("ngs-sdk" ,ngs-sdk)
5116 ("java-ngs" ,java-ngs)
5117 ("libmagic" ,file)
5118 ("hdf5" ,hdf5)))
5119 (native-inputs `(("perl" ,perl)))
5120 ;; NCBI-VDB requires SSE capability.
5121 (supported-systems '("i686-linux" "x86_64-linux"))
5122 (home-page "https://github.com/ncbi/ncbi-vdb")
5123 (synopsis "Database engine for genetic information")
5124 (description
5125 "The NCBI-VDB library implements a highly compressed columnar data
5126 warehousing engine that is most often used to store genetic information.
5127 Databases are stored in a portable image within the file system, and can be
5128 accessed/downloaded on demand across HTTP.")
5129 (license license:public-domain)))
5130
5131 (define-public plink
5132 (package
5133 (name "plink")
5134 (version "1.07")
5135 (source
5136 (origin
5137 (method url-fetch)
5138 (uri (string-append
5139 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5140 version "-src.zip"))
5141 (sha256
5142 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5143 (patches (search-patches "plink-1.07-unclobber-i.patch"
5144 "plink-endian-detection.patch"))))
5145 (build-system gnu-build-system)
5146 (arguments
5147 '(#:tests? #f ;no "check" target
5148 #:make-flags (list (string-append "LIB_LAPACK="
5149 (assoc-ref %build-inputs "lapack")
5150 "/lib/liblapack.so")
5151 "WITH_LAPACK=1"
5152 "FORCE_DYNAMIC=1"
5153 ;; disable phoning home
5154 "WITH_WEBCHECK=")
5155 #:phases
5156 (modify-phases %standard-phases
5157 ;; no "configure" script
5158 (delete 'configure)
5159 (replace 'install
5160 (lambda* (#:key outputs #:allow-other-keys)
5161 (let ((bin (string-append (assoc-ref outputs "out")
5162 "/bin/")))
5163 (install-file "plink" bin)
5164 #t))))))
5165 (inputs
5166 `(("zlib" ,zlib)
5167 ("lapack" ,lapack)))
5168 (native-inputs
5169 `(("unzip" ,unzip)))
5170 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5171 (synopsis "Whole genome association analysis toolset")
5172 (description
5173 "PLINK is a whole genome association analysis toolset, designed to
5174 perform a range of basic, large-scale analyses in a computationally efficient
5175 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5176 so there is no support for steps prior to this (e.g. study design and
5177 planning, generating genotype or CNV calls from raw data). Through
5178 integration with gPLINK and Haploview, there is some support for the
5179 subsequent visualization, annotation and storage of results.")
5180 ;; Code is released under GPLv2, except for fisher.h, which is under
5181 ;; LGPLv2.1+
5182 (license (list license:gpl2 license:lgpl2.1+))))
5183
5184 (define-public plink-ng
5185 (package (inherit plink)
5186 (name "plink-ng")
5187 (version "1.90b4")
5188 (source
5189 (origin
5190 (method url-fetch)
5191 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5192 version ".tar.gz"))
5193 (file-name (string-append name "-" version ".tar.gz"))
5194 (sha256
5195 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5196 (build-system gnu-build-system)
5197 (arguments
5198 '(#:tests? #f ;no "check" target
5199 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5200 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5201 "ZLIB=-lz"
5202 "-f" "Makefile.std")
5203 #:phases
5204 (modify-phases %standard-phases
5205 (add-after 'unpack 'chdir
5206 (lambda _ (chdir "1.9") #t))
5207 (delete 'configure) ; no "configure" script
5208 (replace 'install
5209 (lambda* (#:key outputs #:allow-other-keys)
5210 (let ((bin (string-append (assoc-ref outputs "out")
5211 "/bin/")))
5212 (install-file "plink" bin)
5213 #t))))))
5214 (inputs
5215 `(("zlib" ,zlib)
5216 ("lapack" ,lapack)
5217 ("openblas" ,openblas)))
5218 (home-page "https://www.cog-genomics.org/plink/")
5219 (license license:gpl3+)))
5220
5221 (define-public smithlab-cpp
5222 (let ((revision "1")
5223 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5224 (package
5225 (name "smithlab-cpp")
5226 (version (string-append "0." revision "." (string-take commit 7)))
5227 (source (origin
5228 (method git-fetch)
5229 (uri (git-reference
5230 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5231 (commit commit)))
5232 (file-name (string-append name "-" version "-checkout"))
5233 (sha256
5234 (base32
5235 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5236 (build-system gnu-build-system)
5237 (arguments
5238 `(#:modules ((guix build gnu-build-system)
5239 (guix build utils)
5240 (srfi srfi-26))
5241 #:tests? #f ;no "check" target
5242 #:phases
5243 (modify-phases %standard-phases
5244 (add-after 'unpack 'use-samtools-headers
5245 (lambda _
5246 (substitute* '("SAM.cpp"
5247 "SAM.hpp")
5248 (("sam.h") "samtools/sam.h"))
5249 #t))
5250 (replace 'install
5251 (lambda* (#:key outputs #:allow-other-keys)
5252 (let* ((out (assoc-ref outputs "out"))
5253 (lib (string-append out "/lib"))
5254 (include (string-append out "/include/smithlab-cpp")))
5255 (mkdir-p lib)
5256 (mkdir-p include)
5257 (for-each (cut install-file <> lib)
5258 (find-files "." "\\.o$"))
5259 (for-each (cut install-file <> include)
5260 (find-files "." "\\.hpp$")))
5261 #t))
5262 (delete 'configure))))
5263 (inputs
5264 `(("samtools" ,samtools-0.1)
5265 ("zlib" ,zlib)))
5266 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5267 (synopsis "C++ helper library for functions used in Smith lab projects")
5268 (description
5269 "Smithlab CPP is a C++ library that includes functions used in many of
5270 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5271 structures, classes for genomic regions, mapped sequencing reads, etc.")
5272 (license license:gpl3+))))
5273
5274 (define-public preseq
5275 (package
5276 (name "preseq")
5277 (version "2.0")
5278 (source (origin
5279 (method url-fetch)
5280 (uri (string-append "https://github.com/smithlabcode/"
5281 "preseq/archive/v" version ".tar.gz"))
5282 (file-name (string-append name "-" version ".tar.gz"))
5283 (sha256
5284 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5285 (modules '((guix build utils)))
5286 (snippet
5287 ;; Remove bundled samtools.
5288 '(delete-file-recursively "samtools"))))
5289 (build-system gnu-build-system)
5290 (arguments
5291 `(#:tests? #f ;no "check" target
5292 #:phases
5293 (modify-phases %standard-phases
5294 (delete 'configure))
5295 #:make-flags
5296 (list (string-append "PREFIX="
5297 (assoc-ref %outputs "out"))
5298 (string-append "LIBBAM="
5299 (assoc-ref %build-inputs "samtools")
5300 "/lib/libbam.a")
5301 (string-append "SMITHLAB_CPP="
5302 (assoc-ref %build-inputs "smithlab-cpp")
5303 "/lib")
5304 "PROGS=preseq"
5305 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5306 (inputs
5307 `(("gsl" ,gsl)
5308 ("samtools" ,samtools-0.1)
5309 ("smithlab-cpp" ,smithlab-cpp)
5310 ("zlib" ,zlib)))
5311 (home-page "http://smithlabresearch.org/software/preseq/")
5312 (synopsis "Program for analyzing library complexity")
5313 (description
5314 "The preseq package is aimed at predicting and estimating the complexity
5315 of a genomic sequencing library, equivalent to predicting and estimating the
5316 number of redundant reads from a given sequencing depth and how many will be
5317 expected from additional sequencing using an initial sequencing experiment.
5318 The estimates can then be used to examine the utility of further sequencing,
5319 optimize the sequencing depth, or to screen multiple libraries to avoid low
5320 complexity samples.")
5321 (license license:gpl3+)))
5322
5323 (define-public python-screed
5324 (package
5325 (name "python-screed")
5326 (version "0.9")
5327 (source
5328 (origin
5329 (method url-fetch)
5330 (uri (pypi-uri "screed" version))
5331 (sha256
5332 (base32
5333 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5334 (build-system python-build-system)
5335 (arguments
5336 `(#:phases
5337 (modify-phases %standard-phases
5338 (replace 'check
5339 (lambda _
5340 (setenv "PYTHONPATH"
5341 (string-append (getenv "PYTHONPATH") ":."))
5342 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5343 (native-inputs
5344 `(("python-nose" ,python-nose)))
5345 (inputs
5346 `(("python-bz2file" ,python-bz2file)))
5347 (home-page "https://github.com/dib-lab/screed/")
5348 (synopsis "Short read sequence database utilities")
5349 (description "Screed parses FASTA and FASTQ files and generates databases.
5350 Values such as sequence name, sequence description, sequence quality and the
5351 sequence itself can be retrieved from these databases.")
5352 (license license:bsd-3)))
5353
5354 (define-public python2-screed
5355 (package-with-python2 python-screed))
5356
5357 (define-public sra-tools
5358 (package
5359 (name "sra-tools")
5360 (version "2.8.2-1")
5361 (source
5362 (origin
5363 (method url-fetch)
5364 (uri
5365 (string-append "https://github.com/ncbi/sra-tools/archive/"
5366 version ".tar.gz"))
5367 (file-name (string-append name "-" version ".tar.gz"))
5368 (sha256
5369 (base32
5370 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5371 (build-system gnu-build-system)
5372 (arguments
5373 `(#:parallel-build? #f ; not supported
5374 #:tests? #f ; no "check" target
5375 #:make-flags
5376 (list (string-append "DEFAULT_CRT="
5377 (assoc-ref %build-inputs "ncbi-vdb")
5378 "/kfg/certs.kfg")
5379 (string-append "DEFAULT_KFG="
5380 (assoc-ref %build-inputs "ncbi-vdb")
5381 "/kfg/default.kfg")
5382 (string-append "VDB_LIBDIR="
5383 (assoc-ref %build-inputs "ncbi-vdb")
5384 ,(if (string-prefix? "x86_64"
5385 (or (%current-target-system)
5386 (%current-system)))
5387 "/lib64"
5388 "/lib32")))
5389 #:phases
5390 (modify-phases %standard-phases
5391 (add-before 'configure 'set-perl-search-path
5392 (lambda _
5393 ;; Work around "dotless @INC" build failure.
5394 (setenv "PERL5LIB"
5395 (string-append (getcwd) "/setup:"
5396 (getenv "PERL5LIB")))
5397 #t))
5398 (replace 'configure
5399 (lambda* (#:key inputs outputs #:allow-other-keys)
5400 ;; The build system expects a directory containing the sources and
5401 ;; raw build output of ncbi-vdb, including files that are not
5402 ;; installed. Since we are building against an installed version of
5403 ;; ncbi-vdb, the following modifications are needed.
5404 (substitute* "setup/konfigure.perl"
5405 ;; Make the configure script look for the "ilib" directory of
5406 ;; "ncbi-vdb" without first checking for the existence of a
5407 ;; matching library in its "lib" directory.
5408 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5409 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5410 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5411 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5412 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5413
5414 ;; Dynamic linking
5415 (substitute* "tools/copycat/Makefile"
5416 (("smagic-static") "lmagic"))
5417
5418 ;; The 'configure' script doesn't recognize things like
5419 ;; '--enable-fast-install'.
5420 (zero? (system*
5421 "./configure"
5422 (string-append "--build-prefix=" (getcwd) "/build")
5423 (string-append "--prefix=" (assoc-ref outputs "out"))
5424 (string-append "--debug")
5425 (string-append "--with-fuse-prefix="
5426 (assoc-ref inputs "fuse"))
5427 (string-append "--with-magic-prefix="
5428 (assoc-ref inputs "libmagic"))
5429 ;; TODO: building with libxml2 fails with linker errors
5430 ;; (string-append "--with-xml2-prefix="
5431 ;; (assoc-ref inputs "libxml2"))
5432 (string-append "--with-ncbi-vdb-sources="
5433 (assoc-ref inputs "ncbi-vdb"))
5434 (string-append "--with-ncbi-vdb-build="
5435 (assoc-ref inputs "ncbi-vdb"))
5436 (string-append "--with-ngs-sdk-prefix="
5437 (assoc-ref inputs "ngs-sdk"))
5438 (string-append "--with-hdf5-prefix="
5439 (assoc-ref inputs "hdf5"))))))
5440 ;; This version of sra-tools fails to build with glibc because of a
5441 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5442 ;; contains a definition of "canonicalize", so we rename it.
5443 ;;
5444 ;; See upstream bug report:
5445 ;; https://github.com/ncbi/sra-tools/issues/67
5446 (add-after 'unpack 'patch-away-glibc-conflict
5447 (lambda _
5448 (substitute* "tools/bam-loader/bam.c"
5449 (("canonicalize\\(" line)
5450 (string-append "sra_tools_" line)))
5451 #t)))))
5452 (native-inputs `(("perl" ,perl)))
5453 (inputs
5454 `(("ngs-sdk" ,ngs-sdk)
5455 ("ncbi-vdb" ,ncbi-vdb)
5456 ("libmagic" ,file)
5457 ("fuse" ,fuse)
5458 ("hdf5" ,hdf5)
5459 ("zlib" ,zlib)))
5460 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5461 (synopsis "Tools and libraries for reading and writing sequencing data")
5462 (description
5463 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5464 reading of sequencing files from the Sequence Read Archive (SRA) database and
5465 writing files into the .sra format.")
5466 (license license:public-domain)))
5467
5468 (define-public seqan
5469 (package
5470 (name "seqan")
5471 (version "1.4.2")
5472 (source (origin
5473 (method url-fetch)
5474 (uri (string-append "http://packages.seqan.de/seqan-library/"
5475 "seqan-library-" version ".tar.bz2"))
5476 (sha256
5477 (base32
5478 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5479 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5480 ;; makes sense to split the outputs.
5481 (outputs '("out" "doc"))
5482 (build-system trivial-build-system)
5483 (arguments
5484 `(#:modules ((guix build utils))
5485 #:builder
5486 (begin
5487 (use-modules (guix build utils))
5488 (let ((tar (assoc-ref %build-inputs "tar"))
5489 (bzip (assoc-ref %build-inputs "bzip2"))
5490 (out (assoc-ref %outputs "out"))
5491 (doc (assoc-ref %outputs "doc")))
5492 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5493 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5494 (chdir (string-append "seqan-library-" ,version))
5495 (copy-recursively "include" (string-append out "/include"))
5496 (copy-recursively "share" (string-append doc "/share"))))))
5497 (native-inputs
5498 `(("source" ,source)
5499 ("tar" ,tar)
5500 ("bzip2" ,bzip2)))
5501 (home-page "http://www.seqan.de")
5502 (synopsis "Library for nucleotide sequence analysis")
5503 (description
5504 "SeqAn is a C++ library of efficient algorithms and data structures for
5505 the analysis of sequences with the focus on biological data. It contains
5506 algorithms and data structures for string representation and their
5507 manipulation, online and indexed string search, efficient I/O of
5508 bioinformatics file formats, sequence alignment, and more.")
5509 (license license:bsd-3)))
5510
5511 (define-public seqmagick
5512 (package
5513 (name "seqmagick")
5514 (version "0.7.0")
5515 (source
5516 (origin
5517 (method url-fetch)
5518 (uri (pypi-uri "seqmagick" version))
5519 (sha256
5520 (base32
5521 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5522 (build-system python-build-system)
5523 (inputs
5524 `(("python-biopython" ,python-biopython)))
5525 (native-inputs
5526 `(("python-nose" ,python-nose)))
5527 (home-page "https://github.com/fhcrc/seqmagick")
5528 (synopsis "Tools for converting and modifying sequence files")
5529 (description
5530 "Bioinformaticians often have to convert sequence files between formats
5531 and do little manipulations on them, and it's not worth writing scripts for
5532 that. Seqmagick is a utility to expose the file format conversion in
5533 BioPython in a convenient way. Instead of having a big mess of scripts, there
5534 is one that takes arguments.")
5535 (license license:gpl3)))
5536
5537 (define-public seqtk
5538 (package
5539 (name "seqtk")
5540 (version "1.2")
5541 (source (origin
5542 (method url-fetch)
5543 (uri (string-append
5544 "https://github.com/lh3/seqtk/archive/v"
5545 version ".tar.gz"))
5546 (file-name (string-append name "-" version ".tar.gz"))
5547 (sha256
5548 (base32
5549 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5550 (modules '((guix build utils)))
5551 (snippet
5552 '(begin
5553 ;; Remove extraneous header files, as is done in the seqtk
5554 ;; master branch.
5555 (for-each (lambda (file) (delete-file file))
5556 (list "ksort.h" "kstring.h" "kvec.h"))
5557 #t))))
5558 (build-system gnu-build-system)
5559 (arguments
5560 `(#:phases
5561 (modify-phases %standard-phases
5562 (delete 'configure)
5563 (replace 'check
5564 ;; There are no tests, so we just run a sanity check.
5565 (lambda _ (zero? (system* "./seqtk" "seq"))))
5566 (replace 'install
5567 (lambda* (#:key outputs #:allow-other-keys)
5568 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5569 (install-file "seqtk" bin)))))))
5570 (inputs
5571 `(("zlib" ,zlib)))
5572 (home-page "https://github.com/lh3/seqtk")
5573 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5574 (description
5575 "Seqtk is a fast and lightweight tool for processing sequences in the
5576 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5577 optionally compressed by gzip.")
5578 (license license:expat)))
5579
5580 (define-public snap-aligner
5581 (package
5582 (name "snap-aligner")
5583 (version "1.0beta.18")
5584 (source (origin
5585 (method url-fetch)
5586 (uri (string-append
5587 "https://github.com/amplab/snap/archive/v"
5588 version ".tar.gz"))
5589 (file-name (string-append name "-" version ".tar.gz"))
5590 (sha256
5591 (base32
5592 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5593 (build-system gnu-build-system)
5594 (arguments
5595 '(#:phases
5596 (modify-phases %standard-phases
5597 (delete 'configure)
5598 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5599 (replace 'install
5600 (lambda* (#:key outputs #:allow-other-keys)
5601 (let* ((out (assoc-ref outputs "out"))
5602 (bin (string-append out "/bin")))
5603 (install-file "snap-aligner" bin)
5604 (install-file "SNAPCommand" bin)
5605 #t))))))
5606 (native-inputs
5607 `(("zlib" ,zlib)))
5608 (home-page "http://snap.cs.berkeley.edu/")
5609 (synopsis "Short read DNA sequence aligner")
5610 (description
5611 "SNAP is a fast and accurate aligner for short DNA reads. It is
5612 optimized for modern read lengths of 100 bases or higher, and takes advantage
5613 of these reads to align data quickly through a hash-based indexing scheme.")
5614 ;; 32-bit systems are not supported by the unpatched code.
5615 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5616 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5617 ;; systems without a lot of memory cannot make good use of this program.
5618 (supported-systems '("x86_64-linux"))
5619 (license license:asl2.0)))
5620
5621 (define-public sortmerna
5622 (package
5623 (name "sortmerna")
5624 (version "2.1b")
5625 (source
5626 (origin
5627 (method url-fetch)
5628 (uri (string-append
5629 "https://github.com/biocore/sortmerna/archive/"
5630 version ".tar.gz"))
5631 (file-name (string-append name "-" version ".tar.gz"))
5632 (sha256
5633 (base32
5634 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5635 (build-system gnu-build-system)
5636 (outputs '("out" ;for binaries
5637 "db")) ;for sequence databases
5638 (arguments
5639 `(#:phases
5640 (modify-phases %standard-phases
5641 (replace 'install
5642 (lambda* (#:key outputs #:allow-other-keys)
5643 (let* ((out (assoc-ref outputs "out"))
5644 (bin (string-append out "/bin"))
5645 (db (assoc-ref outputs "db"))
5646 (share
5647 (string-append db "/share/sortmerna/rRNA_databases")))
5648 (install-file "sortmerna" bin)
5649 (install-file "indexdb_rna" bin)
5650 (for-each (lambda (file)
5651 (install-file file share))
5652 (find-files "rRNA_databases" ".*fasta"))
5653 #t))))))
5654 (inputs
5655 `(("zlib" ,zlib)))
5656 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5657 (synopsis "Biological sequence analysis tool for NGS reads")
5658 (description
5659 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5660 and operational taxonomic unit (OTU) picking of next generation
5661 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5662 allows for fast and sensitive analyses of nucleotide sequences. The main
5663 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5664 ;; The source includes x86 specific code
5665 (supported-systems '("x86_64-linux" "i686-linux"))
5666 (license license:lgpl3)))
5667
5668 (define-public star
5669 (package
5670 (name "star")
5671 (version "2.5.3a")
5672 (source (origin
5673 (method url-fetch)
5674 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5675 version ".tar.gz"))
5676 (file-name (string-append name "-" version ".tar.gz"))
5677 (sha256
5678 (base32
5679 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5680 (modules '((guix build utils)))
5681 (snippet
5682 '(begin
5683 (substitute* "source/Makefile"
5684 (("/bin/rm") "rm"))
5685 ;; Remove pre-built binaries and bundled htslib sources.
5686 (delete-file-recursively "bin/MacOSX_x86_64")
5687 (delete-file-recursively "bin/Linux_x86_64")
5688 (delete-file-recursively "bin/Linux_x86_64_static")
5689 (delete-file-recursively "source/htslib")
5690 #t))))
5691 (build-system gnu-build-system)
5692 (arguments
5693 '(#:tests? #f ;no check target
5694 #:make-flags '("STAR")
5695 #:phases
5696 (modify-phases %standard-phases
5697 (add-after 'unpack 'enter-source-dir
5698 (lambda _ (chdir "source") #t))
5699 (add-after 'enter-source-dir 'make-reproducible
5700 (lambda _
5701 (substitute* "Makefile"
5702 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
5703 (string-append pre "Built with Guix" post)))))
5704 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5705 (lambda _
5706 (substitute* "Makefile"
5707 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5708 _ prefix) prefix))
5709 (substitute* '("BAMfunctions.cpp"
5710 "signalFromBAM.h"
5711 "bam_cat.h"
5712 "bam_cat.c"
5713 "STAR.cpp"
5714 "bamRemoveDuplicates.cpp")
5715 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5716 (string-append "#include <" header ">")))
5717 (substitute* "IncludeDefine.h"
5718 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5719 (string-append "<" header ">")))
5720 #t))
5721 (replace 'install
5722 (lambda* (#:key outputs #:allow-other-keys)
5723 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5724 (install-file "STAR" bin))
5725 #t))
5726 (delete 'configure))))
5727 (native-inputs
5728 `(("xxd" ,xxd)))
5729 (inputs
5730 `(("htslib" ,htslib)
5731 ("zlib" ,zlib)))
5732 (home-page "https://github.com/alexdobin/STAR")
5733 (synopsis "Universal RNA-seq aligner")
5734 (description
5735 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5736 based on a previously undescribed RNA-seq alignment algorithm that uses
5737 sequential maximum mappable seed search in uncompressed suffix arrays followed
5738 by seed clustering and stitching procedure. In addition to unbiased de novo
5739 detection of canonical junctions, STAR can discover non-canonical splices and
5740 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5741 sequences.")
5742 ;; Only 64-bit systems are supported according to the README.
5743 (supported-systems '("x86_64-linux" "mips64el-linux"))
5744 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5745 (license license:gpl3+)))
5746
5747 (define-public subread
5748 (package
5749 (name "subread")
5750 (version "1.6.0")
5751 (source (origin
5752 (method url-fetch)
5753 (uri (string-append "mirror://sourceforge/subread/subread-"
5754 version "/subread-" version "-source.tar.gz"))
5755 (sha256
5756 (base32
5757 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
5758 (build-system gnu-build-system)
5759 (arguments
5760 `(#:tests? #f ;no "check" target
5761 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5762 ;; optimizations by default, so we override these flags such that x86_64
5763 ;; flags are only added when the build target is an x86_64 system.
5764 #:make-flags
5765 (list (let ((system ,(or (%current-target-system)
5766 (%current-system)))
5767 (flags '("-ggdb" "-fomit-frame-pointer"
5768 "-ffast-math" "-funroll-loops"
5769 "-fmessage-length=0"
5770 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5771 "-DMAKE_STANDALONE"
5772 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5773 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5774 (if (string-prefix? "x86_64" system)
5775 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5776 (string-append "CCFLAGS=" (string-join flags))))
5777 "-f" "Makefile.Linux"
5778 "CC=gcc ${CCFLAGS}")
5779 #:phases
5780 (modify-phases %standard-phases
5781 (add-after 'unpack 'enter-dir
5782 (lambda _ (chdir "src") #t))
5783 (replace 'install
5784 (lambda* (#:key outputs #:allow-other-keys)
5785 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5786 (mkdir-p bin)
5787 (copy-recursively "../bin" bin))))
5788 ;; no "configure" script
5789 (delete 'configure))))
5790 (inputs `(("zlib" ,zlib)))
5791 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5792 (synopsis "Tool kit for processing next-gen sequencing data")
5793 (description
5794 "The subread package contains the following tools: subread aligner, a
5795 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5796 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5797 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5798 against local background noises.")
5799 (license license:gpl3+)))
5800
5801 (define-public stringtie
5802 (package
5803 (name "stringtie")
5804 (version "1.2.1")
5805 (source (origin
5806 (method url-fetch)
5807 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5808 "stringtie-" version ".tar.gz"))
5809 (sha256
5810 (base32
5811 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5812 (modules '((guix build utils)))
5813 (snippet
5814 '(begin
5815 (delete-file-recursively "samtools-0.1.18")
5816 #t))))
5817 (build-system gnu-build-system)
5818 (arguments
5819 `(#:tests? #f ;no test suite
5820 #:phases
5821 (modify-phases %standard-phases
5822 ;; no configure script
5823 (delete 'configure)
5824 (add-before 'build 'use-system-samtools
5825 (lambda _
5826 (substitute* "Makefile"
5827 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5828 "stringtie: "))
5829 (substitute* '("gclib/GBam.h"
5830 "gclib/GBam.cpp")
5831 (("#include \"(bam|sam|kstring).h\"" _ header)
5832 (string-append "#include <samtools/" header ".h>")))
5833 #t))
5834 (add-after 'unpack 'remove-duplicate-typedef
5835 (lambda _
5836 ;; This typedef conflicts with the typedef in
5837 ;; glibc-2.25/include/bits/types.h
5838 (substitute* "gclib/GThreads.h"
5839 (("typedef long long __intmax_t;") ""))
5840 #t))
5841 (replace 'install
5842 (lambda* (#:key outputs #:allow-other-keys)
5843 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5844 (install-file "stringtie" bin)
5845 #t))))))
5846 (inputs
5847 `(("samtools" ,samtools-0.1)
5848 ("zlib" ,zlib)))
5849 (home-page "http://ccb.jhu.edu/software/stringtie/")
5850 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5851 (description
5852 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5853 alignments into potential transcripts. It uses a novel network flow algorithm
5854 as well as an optional de novo assembly step to assemble and quantitate
5855 full-length transcripts representing multiple splice variants for each gene
5856 locus. Its input can include not only the alignments of raw reads used by
5857 other transcript assemblers, but also alignments of longer sequences that have
5858 been assembled from those reads. To identify differentially expressed genes
5859 between experiments, StringTie's output can be processed either by the
5860 Cuffdiff or Ballgown programs.")
5861 (license license:artistic2.0)))
5862
5863 (define-public taxtastic
5864 (package
5865 (name "taxtastic")
5866 (version "0.6.4")
5867 (source (origin
5868 (method url-fetch)
5869 (uri (pypi-uri "taxtastic" version))
5870 (sha256
5871 (base32
5872 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5873 (build-system python-build-system)
5874 (arguments
5875 `(#:python ,python-2
5876 #:phases
5877 (modify-phases %standard-phases
5878 (replace 'check
5879 (lambda _
5880 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5881 (propagated-inputs
5882 `(("python-sqlalchemy" ,python2-sqlalchemy)
5883 ("python-decorator" ,python2-decorator)
5884 ("python-biopython" ,python2-biopython)
5885 ("python-pandas" ,python2-pandas)))
5886 (home-page "https://github.com/fhcrc/taxtastic")
5887 (synopsis "Tools for taxonomic naming and annotation")
5888 (description
5889 "Taxtastic is software written in python used to build and maintain
5890 reference packages i.e. collections of reference trees, reference alignments,
5891 profiles, and associated taxonomic information.")
5892 (license license:gpl3+)))
5893
5894 (define-public vcftools
5895 (package
5896 (name "vcftools")
5897 (version "0.1.15")
5898 (source (origin
5899 (method url-fetch)
5900 (uri (string-append
5901 "https://github.com/vcftools/vcftools/releases/download/v"
5902 version "/vcftools-" version ".tar.gz"))
5903 (sha256
5904 (base32
5905 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5906 (build-system gnu-build-system)
5907 (arguments
5908 `(#:tests? #f ; no "check" target
5909 #:make-flags (list
5910 "CFLAGS=-O2" ; override "-m64" flag
5911 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5912 (string-append "MANDIR=" (assoc-ref %outputs "out")
5913 "/share/man/man1"))))
5914 (native-inputs
5915 `(("pkg-config" ,pkg-config)))
5916 (inputs
5917 `(("perl" ,perl)
5918 ("zlib" ,zlib)))
5919 (home-page "https://vcftools.github.io/")
5920 (synopsis "Tools for working with VCF files")
5921 (description
5922 "VCFtools is a program package designed for working with VCF files, such
5923 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5924 provide easily accessible methods for working with complex genetic variation
5925 data in the form of VCF files.")
5926 ;; The license is declared as LGPLv3 in the README and
5927 ;; at https://vcftools.github.io/license.html
5928 (license license:lgpl3)))
5929
5930 (define-public infernal
5931 (package
5932 (name "infernal")
5933 (version "1.1.2")
5934 (source (origin
5935 (method url-fetch)
5936 (uri (string-append "http://eddylab.org/software/infernal/"
5937 "infernal-" version ".tar.gz"))
5938 (sha256
5939 (base32
5940 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5941 (build-system gnu-build-system)
5942 (native-inputs
5943 `(("perl" ,perl))) ; for tests
5944 (home-page "http://eddylab.org/infernal/")
5945 (synopsis "Inference of RNA alignments")
5946 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5947 searching DNA sequence databases for RNA structure and sequence similarities.
5948 It is an implementation of a special case of profile stochastic context-free
5949 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5950 profile, but it scores a combination of sequence consensus and RNA secondary
5951 structure consensus, so in many cases, it is more capable of identifying RNA
5952 homologs that conserve their secondary structure more than their primary
5953 sequence.")
5954 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5955 (supported-systems '("i686-linux" "x86_64-linux"))
5956 (license license:bsd-3)))
5957
5958 (define-public r-centipede
5959 (package
5960 (name "r-centipede")
5961 (version "1.2")
5962 (source (origin
5963 (method url-fetch)
5964 (uri (string-append "http://download.r-forge.r-project.org/"
5965 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5966 (sha256
5967 (base32
5968 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5969 (build-system r-build-system)
5970 (home-page "http://centipede.uchicago.edu/")
5971 (synopsis "Predict transcription factor binding sites")
5972 (description
5973 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5974 of the genome that are bound by particular transcription factors. It starts
5975 by identifying a set of candidate binding sites, and then aims to classify the
5976 sites according to whether each site is bound or not bound by a transcription
5977 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5978 between two different types of motif instances using as much relevant
5979 information as possible.")
5980 (license (list license:gpl2+ license:gpl3+))))
5981
5982 (define-public r-vegan
5983 (package
5984 (name "r-vegan")
5985 (version "2.4-6")
5986 (source
5987 (origin
5988 (method url-fetch)
5989 (uri (cran-uri "vegan" version))
5990 (sha256
5991 (base32
5992 "175mqr42mmxy98gpf3rky8alnkw3w1k90ggdw3cispl36841p76w"))))
5993 (build-system r-build-system)
5994 (native-inputs
5995 `(("gfortran" ,gfortran)))
5996 (propagated-inputs
5997 `(("r-cluster" ,r-cluster)
5998 ("r-lattice" ,r-lattice)
5999 ("r-mass" ,r-mass)
6000 ("r-mgcv" ,r-mgcv)
6001 ("r-permute" ,r-permute)))
6002 (home-page "https://cran.r-project.org/web/packages/vegan")
6003 (synopsis "Functions for community ecology")
6004 (description
6005 "The vegan package provides tools for descriptive community ecology. It
6006 has most basic functions of diversity analysis, community ordination and
6007 dissimilarity analysis. Most of its multivariate tools can be used for other
6008 data types as well.")
6009 (license license:gpl2+)))
6010
6011 (define-public r-annotate
6012 (package
6013 (name "r-annotate")
6014 (version "1.56.1")
6015 (source
6016 (origin
6017 (method url-fetch)
6018 (uri (bioconductor-uri "annotate" version))
6019 (sha256
6020 (base32
6021 "14c5xd9kasvcwg5gbjys2c1vizxhlqlzxakqc2kml0kw97hmx0rq"))))
6022 (build-system r-build-system)
6023 (propagated-inputs
6024 `(("r-annotationdbi" ,r-annotationdbi)
6025 ("r-biobase" ,r-biobase)
6026 ("r-biocgenerics" ,r-biocgenerics)
6027 ("r-dbi" ,r-dbi)
6028 ("r-rcurl" ,r-rcurl)
6029 ("r-xml" ,r-xml)
6030 ("r-xtable" ,r-xtable)))
6031 (home-page
6032 "https://bioconductor.org/packages/annotate")
6033 (synopsis "Annotation for microarrays")
6034 (description "This package provides R environments for the annotation of
6035 microarrays.")
6036 (license license:artistic2.0)))
6037
6038 (define-public r-copynumber
6039 (package
6040 (name "r-copynumber")
6041 (version "1.18.0")
6042 (source (origin
6043 (method url-fetch)
6044 (uri (bioconductor-uri "copynumber" version))
6045 (sha256
6046 (base32
6047 "01kcwzl485yjrkgyg8117b1il957ss0v6rq4bbxf4ksd5fzcjmyx"))))
6048 (build-system r-build-system)
6049 (propagated-inputs
6050 `(("r-s4vectors" ,r-s4vectors)
6051 ("r-iranges" ,r-iranges)
6052 ("r-genomicranges" ,r-genomicranges)
6053 ("r-biocgenerics" ,r-biocgenerics)))
6054 (home-page "https://bioconductor.org/packages/copynumber")
6055 (synopsis "Segmentation of single- and multi-track copy number data")
6056 (description
6057 "This package segments single- and multi-track copy number data by a
6058 penalized least squares regression method.")
6059 (license license:artistic2.0)))
6060
6061 (define-public r-geneplotter
6062 (package
6063 (name "r-geneplotter")
6064 (version "1.56.0")
6065 (source
6066 (origin
6067 (method url-fetch)
6068 (uri (bioconductor-uri "geneplotter" version))
6069 (sha256
6070 (base32
6071 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
6072 (build-system r-build-system)
6073 (propagated-inputs
6074 `(("r-annotate" ,r-annotate)
6075 ("r-annotationdbi" ,r-annotationdbi)
6076 ("r-biobase" ,r-biobase)
6077 ("r-biocgenerics" ,r-biocgenerics)
6078 ("r-lattice" ,r-lattice)
6079 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6080 (home-page "https://bioconductor.org/packages/geneplotter")
6081 (synopsis "Graphics functions for genomic data")
6082 (description
6083 "This package provides functions for plotting genomic data.")
6084 (license license:artistic2.0)))
6085
6086 (define-public r-genefilter
6087 (package
6088 (name "r-genefilter")
6089 (version "1.60.0")
6090 (source
6091 (origin
6092 (method url-fetch)
6093 (uri (bioconductor-uri "genefilter" version))
6094 (sha256
6095 (base32
6096 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
6097 (build-system r-build-system)
6098 (native-inputs
6099 `(("gfortran" ,gfortran)))
6100 (propagated-inputs
6101 `(("r-annotate" ,r-annotate)
6102 ("r-annotationdbi" ,r-annotationdbi)
6103 ("r-biobase" ,r-biobase)
6104 ("r-s4vectors" ,r-s4vectors)
6105 ("r-survival" ,r-survival)))
6106 (home-page "https://bioconductor.org/packages/genefilter")
6107 (synopsis "Filter genes from high-throughput experiments")
6108 (description
6109 "This package provides basic functions for filtering genes from
6110 high-throughput sequencing experiments.")
6111 (license license:artistic2.0)))
6112
6113 (define-public r-deseq2
6114 (package
6115 (name "r-deseq2")
6116 (version "1.18.1")
6117 (source
6118 (origin
6119 (method url-fetch)
6120 (uri (bioconductor-uri "DESeq2" version))
6121 (sha256
6122 (base32
6123 "1iyimg1s0x5pdmvl8x08s8h0v019y0nhjzs50chagbpk2x91fsmv"))))
6124 (properties `((upstream-name . "DESeq2")))
6125 (build-system r-build-system)
6126 (propagated-inputs
6127 `(("r-biobase" ,r-biobase)
6128 ("r-biocgenerics" ,r-biocgenerics)
6129 ("r-biocparallel" ,r-biocparallel)
6130 ("r-genefilter" ,r-genefilter)
6131 ("r-geneplotter" ,r-geneplotter)
6132 ("r-genomicranges" ,r-genomicranges)
6133 ("r-ggplot2" ,r-ggplot2)
6134 ("r-hmisc" ,r-hmisc)
6135 ("r-iranges" ,r-iranges)
6136 ("r-locfit" ,r-locfit)
6137 ("r-rcpp" ,r-rcpp)
6138 ("r-rcpparmadillo" ,r-rcpparmadillo)
6139 ("r-s4vectors" ,r-s4vectors)
6140 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6141 (home-page "https://bioconductor.org/packages/DESeq2")
6142 (synopsis "Differential gene expression analysis")
6143 (description
6144 "This package provides functions to estimate variance-mean dependence in
6145 count data from high-throughput nucleotide sequencing assays and test for
6146 differential expression based on a model using the negative binomial
6147 distribution.")
6148 (license license:lgpl3+)))
6149
6150 (define-public r-dexseq
6151 (package
6152 (name "r-dexseq")
6153 (version "1.24.3")
6154 (source
6155 (origin
6156 (method url-fetch)
6157 (uri (bioconductor-uri "DEXSeq" version))
6158 (sha256
6159 (base32
6160 "0xip73hlbr3zry9d7ly9vvvsbb3xjcmfa09lr9fdy528dwjrf084"))))
6161 (properties `((upstream-name . "DEXSeq")))
6162 (build-system r-build-system)
6163 (propagated-inputs
6164 `(("r-annotationdbi" ,r-annotationdbi)
6165 ("r-biobase" ,r-biobase)
6166 ("r-biocgenerics" ,r-biocgenerics)
6167 ("r-biocparallel" ,r-biocparallel)
6168 ("r-biomart" ,r-biomart)
6169 ("r-deseq2" ,r-deseq2)
6170 ("r-genefilter" ,r-genefilter)
6171 ("r-geneplotter" ,r-geneplotter)
6172 ("r-genomicranges" ,r-genomicranges)
6173 ("r-hwriter" ,r-hwriter)
6174 ("r-iranges" ,r-iranges)
6175 ("r-rcolorbrewer" ,r-rcolorbrewer)
6176 ("r-rsamtools" ,r-rsamtools)
6177 ("r-s4vectors" ,r-s4vectors)
6178 ("r-statmod" ,r-statmod)
6179 ("r-stringr" ,r-stringr)
6180 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6181 (home-page "https://bioconductor.org/packages/DEXSeq")
6182 (synopsis "Inference of differential exon usage in RNA-Seq")
6183 (description
6184 "This package is focused on finding differential exon usage using RNA-seq
6185 exon counts between samples with different experimental designs. It provides
6186 functions that allows the user to make the necessary statistical tests based
6187 on a model that uses the negative binomial distribution to estimate the
6188 variance between biological replicates and generalized linear models for
6189 testing. The package also provides functions for the visualization and
6190 exploration of the results.")
6191 (license license:gpl3+)))
6192
6193 (define-public r-annotationforge
6194 (package
6195 (name "r-annotationforge")
6196 (version "1.20.0")
6197 (source
6198 (origin
6199 (method url-fetch)
6200 (uri (bioconductor-uri "AnnotationForge" version))
6201 (sha256
6202 (base32
6203 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
6204 (properties
6205 `((upstream-name . "AnnotationForge")))
6206 (build-system r-build-system)
6207 (propagated-inputs
6208 `(("r-annotationdbi" ,r-annotationdbi)
6209 ("r-biobase" ,r-biobase)
6210 ("r-biocgenerics" ,r-biocgenerics)
6211 ("r-dbi" ,r-dbi)
6212 ("r-rcurl" ,r-rcurl)
6213 ("r-rsqlite" ,r-rsqlite)
6214 ("r-s4vectors" ,r-s4vectors)
6215 ("r-xml" ,r-xml)))
6216 (home-page "https://bioconductor.org/packages/AnnotationForge")
6217 (synopsis "Code for building annotation database packages")
6218 (description
6219 "This package provides code for generating Annotation packages and their
6220 databases. Packages produced are intended to be used with AnnotationDbi.")
6221 (license license:artistic2.0)))
6222
6223 (define-public r-rbgl
6224 (package
6225 (name "r-rbgl")
6226 (version "1.54.0")
6227 (source
6228 (origin
6229 (method url-fetch)
6230 (uri (bioconductor-uri "RBGL" version))
6231 (sha256
6232 (base32
6233 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
6234 (properties `((upstream-name . "RBGL")))
6235 (build-system r-build-system)
6236 (propagated-inputs `(("r-graph" ,r-graph)))
6237 (home-page "https://www.bioconductor.org/packages/RBGL")
6238 (synopsis "Interface to the Boost graph library")
6239 (description
6240 "This package provides a fairly extensive and comprehensive interface to
6241 the graph algorithms contained in the Boost library.")
6242 (license license:artistic2.0)))
6243
6244 (define-public r-gseabase
6245 (package
6246 (name "r-gseabase")
6247 (version "1.40.1")
6248 (source
6249 (origin
6250 (method url-fetch)
6251 (uri (bioconductor-uri "GSEABase" version))
6252 (sha256
6253 (base32
6254 "10cmjxahg2plwacfan6g0k8cwyzya96ypc7m1r79gwqkyykxw5fz"))))
6255 (properties `((upstream-name . "GSEABase")))
6256 (build-system r-build-system)
6257 (propagated-inputs
6258 `(("r-annotate" ,r-annotate)
6259 ("r-annotationdbi" ,r-annotationdbi)
6260 ("r-biobase" ,r-biobase)
6261 ("r-biocgenerics" ,r-biocgenerics)
6262 ("r-graph" ,r-graph)
6263 ("r-xml" ,r-xml)))
6264 (home-page "https://bioconductor.org/packages/GSEABase")
6265 (synopsis "Gene set enrichment data structures and methods")
6266 (description
6267 "This package provides classes and methods to support @dfn{Gene Set
6268 Enrichment Analysis} (GSEA).")
6269 (license license:artistic2.0)))
6270
6271 (define-public r-category
6272 (package
6273 (name "r-category")
6274 (version "2.44.0")
6275 (source
6276 (origin
6277 (method url-fetch)
6278 (uri (bioconductor-uri "Category" version))
6279 (sha256
6280 (base32
6281 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
6282 (properties `((upstream-name . "Category")))
6283 (build-system r-build-system)
6284 (propagated-inputs
6285 `(("r-annotate" ,r-annotate)
6286 ("r-annotationdbi" ,r-annotationdbi)
6287 ("r-biobase" ,r-biobase)
6288 ("r-biocgenerics" ,r-biocgenerics)
6289 ("r-genefilter" ,r-genefilter)
6290 ("r-graph" ,r-graph)
6291 ("r-gseabase" ,r-gseabase)
6292 ("r-matrix" ,r-matrix)
6293 ("r-rbgl" ,r-rbgl)
6294 ("r-dbi" ,r-dbi)))
6295 (home-page "https://bioconductor.org/packages/Category")
6296 (synopsis "Category analysis")
6297 (description
6298 "This package provides a collection of tools for performing category
6299 analysis.")
6300 (license license:artistic2.0)))
6301
6302 (define-public r-gostats
6303 (package
6304 (name "r-gostats")
6305 (version "2.44.0")
6306 (source
6307 (origin
6308 (method url-fetch)
6309 (uri (bioconductor-uri "GOstats" version))
6310 (sha256
6311 (base32
6312 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
6313 (properties `((upstream-name . "GOstats")))
6314 (build-system r-build-system)
6315 (propagated-inputs
6316 `(("r-annotate" ,r-annotate)
6317 ("r-annotationdbi" ,r-annotationdbi)
6318 ("r-annotationforge" ,r-annotationforge)
6319 ("r-biobase" ,r-biobase)
6320 ("r-category" ,r-category)
6321 ("r-go-db" ,r-go-db)
6322 ("r-graph" ,r-graph)
6323 ("r-rgraphviz" ,r-rgraphviz)
6324 ("r-rbgl" ,r-rbgl)))
6325 (home-page "https://bioconductor.org/packages/GOstats")
6326 (synopsis "Tools for manipulating GO and microarrays")
6327 (description
6328 "This package provides a set of tools for interacting with GO and
6329 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6330 testing and other simple calculations.")
6331 (license license:artistic2.0)))
6332
6333 (define-public r-shortread
6334 (package
6335 (name "r-shortread")
6336 (version "1.36.1")
6337 (source
6338 (origin
6339 (method url-fetch)
6340 (uri (bioconductor-uri "ShortRead" version))
6341 (sha256
6342 (base32
6343 "1cyv47632m9ljkxfsvnvmd19sb607ys5kz8fwh6v39dnw16g0a6m"))))
6344 (properties `((upstream-name . "ShortRead")))
6345 (build-system r-build-system)
6346 (inputs
6347 `(("zlib" ,zlib)))
6348 (propagated-inputs
6349 `(("r-biobase" ,r-biobase)
6350 ("r-biocgenerics" ,r-biocgenerics)
6351 ("r-biocparallel" ,r-biocparallel)
6352 ("r-biostrings" ,r-biostrings)
6353 ("r-genomeinfodb" ,r-genomeinfodb)
6354 ("r-genomicalignments" ,r-genomicalignments)
6355 ("r-genomicranges" ,r-genomicranges)
6356 ("r-hwriter" ,r-hwriter)
6357 ("r-iranges" ,r-iranges)
6358 ("r-lattice" ,r-lattice)
6359 ("r-latticeextra" ,r-latticeextra)
6360 ("r-rsamtools" ,r-rsamtools)
6361 ("r-s4vectors" ,r-s4vectors)
6362 ("r-xvector" ,r-xvector)
6363 ("r-zlibbioc" ,r-zlibbioc)))
6364 (home-page "https://bioconductor.org/packages/ShortRead")
6365 (synopsis "FASTQ input and manipulation tools")
6366 (description
6367 "This package implements sampling, iteration, and input of FASTQ files.
6368 It includes functions for filtering and trimming reads, and for generating a
6369 quality assessment report. Data are represented as
6370 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6371 purposes. The package also contains legacy support for early single-end,
6372 ungapped alignment formats.")
6373 (license license:artistic2.0)))
6374
6375 (define-public r-systempiper
6376 (package
6377 (name "r-systempiper")
6378 (version "1.12.0")
6379 (source
6380 (origin
6381 (method url-fetch)
6382 (uri (bioconductor-uri "systemPipeR" version))
6383 (sha256
6384 (base32
6385 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6386 (properties `((upstream-name . "systemPipeR")))
6387 (build-system r-build-system)
6388 (propagated-inputs
6389 `(("r-annotate" ,r-annotate)
6390 ("r-batchjobs" ,r-batchjobs)
6391 ("r-biocgenerics" ,r-biocgenerics)
6392 ("r-biostrings" ,r-biostrings)
6393 ("r-deseq2" ,r-deseq2)
6394 ("r-edger" ,r-edger)
6395 ("r-genomicfeatures" ,r-genomicfeatures)
6396 ("r-genomicranges" ,r-genomicranges)
6397 ("r-ggplot2" ,r-ggplot2)
6398 ("r-go-db" ,r-go-db)
6399 ("r-gostats" ,r-gostats)
6400 ("r-limma" ,r-limma)
6401 ("r-pheatmap" ,r-pheatmap)
6402 ("r-rjson" ,r-rjson)
6403 ("r-rsamtools" ,r-rsamtools)
6404 ("r-shortread" ,r-shortread)
6405 ("r-summarizedexperiment" ,r-summarizedexperiment)
6406 ("r-variantannotation" ,r-variantannotation)))
6407 (home-page "https://github.com/tgirke/systemPipeR")
6408 (synopsis "Next generation sequencing workflow and reporting environment")
6409 (description
6410 "This R package provides tools for building and running automated
6411 end-to-end analysis workflows for a wide range of @dfn{next generation
6412 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6413 Important features include a uniform workflow interface across different NGS
6414 applications, automated report generation, and support for running both R and
6415 command-line software, such as NGS aligners or peak/variant callers, on local
6416 computers or compute clusters. Efficient handling of complex sample sets and
6417 experimental designs is facilitated by a consistently implemented sample
6418 annotation infrastructure.")
6419 (license license:artistic2.0)))
6420
6421 (define-public r-grohmm
6422 (package
6423 (name "r-grohmm")
6424 (version "1.12.0")
6425 (source
6426 (origin
6427 (method url-fetch)
6428 (uri (bioconductor-uri "groHMM" version))
6429 (sha256
6430 (base32
6431 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6432 (properties `((upstream-name . "groHMM")))
6433 (build-system r-build-system)
6434 (propagated-inputs
6435 `(("r-genomeinfodb" ,r-genomeinfodb)
6436 ("r-genomicalignments" ,r-genomicalignments)
6437 ("r-genomicranges" ,r-genomicranges)
6438 ("r-iranges" ,r-iranges)
6439 ("r-mass" ,r-mass)
6440 ("r-rtracklayer" ,r-rtracklayer)
6441 ("r-s4vectors" ,r-s4vectors)))
6442 (home-page "https://github.com/Kraus-Lab/groHMM")
6443 (synopsis "GRO-seq analysis pipeline")
6444 (description
6445 "This package provides a pipeline for the analysis of GRO-seq data.")
6446 (license license:gpl3+)))
6447
6448 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6449 (package
6450 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6451 (version "3.2.2")
6452 (source (origin
6453 (method url-fetch)
6454 ;; We cannot use bioconductor-uri here because this tarball is
6455 ;; located under "data/annotation/" instead of "bioc/".
6456 (uri (string-append "https://bioconductor.org/packages/"
6457 "release/data/annotation/src/contrib"
6458 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6459 version ".tar.gz"))
6460 (sha256
6461 (base32
6462 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6463 (properties
6464 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6465 (build-system r-build-system)
6466 ;; As this package provides little more than a very large data file it
6467 ;; doesn't make sense to build substitutes.
6468 (arguments `(#:substitutable? #f))
6469 (propagated-inputs
6470 `(("r-genomicfeatures" ,r-genomicfeatures)))
6471 (home-page
6472 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6473 (synopsis "Annotation package for human genome in TxDb format")
6474 (description
6475 "This package provides an annotation database of Homo sapiens genome
6476 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6477 track. The database is exposed as a @code{TxDb} object.")
6478 (license license:artistic2.0)))
6479
6480 (define-public r-sparql
6481 (package
6482 (name "r-sparql")
6483 (version "1.16")
6484 (source (origin
6485 (method url-fetch)
6486 (uri (cran-uri "SPARQL" version))
6487 (sha256
6488 (base32
6489 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6490 (properties `((upstream-name . "SPARQL")))
6491 (build-system r-build-system)
6492 (propagated-inputs
6493 `(("r-rcurl" ,r-rcurl)
6494 ("r-xml" ,r-xml)))
6495 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6496 (synopsis "SPARQL client for R")
6497 (description "This package provides an interface to use SPARQL to pose
6498 SELECT or UPDATE queries to an end-point.")
6499 ;; The only license indication is found in the DESCRIPTION file,
6500 ;; which states GPL-3. So we cannot assume GPLv3+.
6501 (license license:gpl3)))
6502
6503 (define-public vsearch
6504 (package
6505 (name "vsearch")
6506 (version "2.7.1")
6507 (source
6508 (origin
6509 (method url-fetch)
6510 (uri (string-append
6511 "https://github.com/torognes/vsearch/archive/v"
6512 version ".tar.gz"))
6513 (file-name (string-append name "-" version ".tar.gz"))
6514 (sha256
6515 (base32
6516 "0jlzfgh79fzmb4g7sngzdjjsjyc37icvs1k7vmc2ksxglj6x5i7f"))
6517 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6518 (snippet
6519 '(begin
6520 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6521 ;; for this in the patch.
6522 (delete-file "src/city.h")
6523 (delete-file "src/citycrc.h")
6524 (delete-file "src/city.cc")
6525 #t))))
6526 (build-system gnu-build-system)
6527 (arguments
6528 `(#:phases
6529 (modify-phases %standard-phases
6530 (add-after 'unpack 'autogen
6531 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6532 (inputs
6533 `(("zlib" ,zlib)
6534 ("bzip2" ,bzip2)
6535 ("cityhash" ,cityhash)))
6536 (native-inputs
6537 `(("autoconf" ,autoconf)
6538 ("automake" ,automake)))
6539 (synopsis "Sequence search tools for metagenomics")
6540 (description
6541 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6542 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6543 masking. The tool takes advantage of parallelism in the form of SIMD
6544 vectorization as well as multiple threads to perform accurate alignments at
6545 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6546 Needleman-Wunsch).")
6547 (home-page "https://github.com/torognes/vsearch")
6548 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6549 ;; platforms.
6550 (supported-systems '("x86_64-linux"))
6551 ;; Dual licensed; also includes public domain source.
6552 (license (list license:gpl3 license:bsd-2))))
6553
6554 (define-public pardre
6555 (package
6556 (name "pardre")
6557 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6558 (version "1.1.5-1")
6559 (source
6560 (origin
6561 (method url-fetch)
6562 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6563 "1.1.5" ".tar.gz"))
6564 (sha256
6565 (base32
6566 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6567 (build-system gnu-build-system)
6568 (arguments
6569 `(#:tests? #f ; no tests included
6570 #:phases
6571 (modify-phases %standard-phases
6572 (delete 'configure)
6573 (replace 'install
6574 (lambda* (#:key outputs #:allow-other-keys)
6575 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6576 (install-file "ParDRe" bin)
6577 #t))))))
6578 (inputs
6579 `(("openmpi" ,openmpi)
6580 ("zlib" ,zlib)))
6581 (synopsis "Parallel tool to remove duplicate DNA reads")
6582 (description
6583 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6584 Duplicate reads can be seen as identical or nearly identical sequences with
6585 some mismatches. This tool lets users avoid the analysis of unnecessary
6586 reads, reducing the time of subsequent procedures with the
6587 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6588 in order to exploit the parallel capabilities of multicore clusters. It is
6589 faster than multithreaded counterparts (end of 2015) for the same number of
6590 cores and, thanks to the message-passing technology, it can be executed on
6591 clusters.")
6592 (home-page "https://sourceforge.net/projects/pardre/")
6593 (license license:gpl3+)))
6594
6595 (define-public ruby-bio-kseq
6596 (package
6597 (name "ruby-bio-kseq")
6598 (version "0.0.2")
6599 (source
6600 (origin
6601 (method url-fetch)
6602 (uri (rubygems-uri "bio-kseq" version))
6603 (sha256
6604 (base32
6605 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6606 (build-system ruby-build-system)
6607 (arguments
6608 `(#:test-target "spec"))
6609 (native-inputs
6610 `(("bundler" ,bundler)
6611 ("ruby-rspec" ,ruby-rspec)
6612 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6613 (inputs
6614 `(("zlib" ,zlib)))
6615 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6616 (description
6617 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6618 FASTQ parsing code. It provides a fast iterator over sequences and their
6619 quality scores.")
6620 (home-page "https://github.com/gusevfe/bio-kseq")
6621 (license license:expat)))
6622
6623 (define-public bio-locus
6624 (package
6625 (name "bio-locus")
6626 (version "0.0.7")
6627 (source
6628 (origin
6629 (method url-fetch)
6630 (uri (rubygems-uri "bio-locus" version))
6631 (sha256
6632 (base32
6633 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6634 (build-system ruby-build-system)
6635 (native-inputs
6636 `(("ruby-rspec" ,ruby-rspec)))
6637 (synopsis "Tool for fast querying of genome locations")
6638 (description
6639 "Bio-locus is a tabix-like tool for fast querying of genome
6640 locations. Many file formats in bioinformatics contain records that
6641 start with a chromosome name and a position for a SNP, or a start-end
6642 position for indels. Bio-locus allows users to store this chr+pos or
6643 chr+pos+alt information in a database.")
6644 (home-page "https://github.com/pjotrp/bio-locus")
6645 (license license:expat)))
6646
6647 (define-public bio-blastxmlparser
6648 (package
6649 (name "bio-blastxmlparser")
6650 (version "2.0.4")
6651 (source (origin
6652 (method url-fetch)
6653 (uri (rubygems-uri "bio-blastxmlparser" version))
6654 (sha256
6655 (base32
6656 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6657 (build-system ruby-build-system)
6658 (propagated-inputs
6659 `(("ruby-bio-logger" ,ruby-bio-logger)
6660 ("ruby-nokogiri" ,ruby-nokogiri)))
6661 (inputs
6662 `(("ruby-rspec" ,ruby-rspec)))
6663 (synopsis "Fast big data BLAST XML parser and library")
6664 (description
6665 "Very fast parallel big-data BLAST XML file parser which can be used as
6666 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6667 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6668 (home-page "https://github.com/pjotrp/blastxmlparser")
6669 (license license:expat)))
6670
6671 (define-public bioruby
6672 (package
6673 (name "bioruby")
6674 (version "1.5.1")
6675 (source
6676 (origin
6677 (method url-fetch)
6678 (uri (rubygems-uri "bio" version))
6679 (sha256
6680 (base32
6681 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6682 (build-system ruby-build-system)
6683 (propagated-inputs
6684 `(("ruby-libxml" ,ruby-libxml)))
6685 (native-inputs
6686 `(("which" ,which))) ; required for test phase
6687 (arguments
6688 `(#:phases
6689 (modify-phases %standard-phases
6690 (add-before 'build 'patch-test-command
6691 (lambda _
6692 (substitute* '("test/functional/bio/test_command.rb")
6693 (("/bin/sh") (which "sh")))
6694 (substitute* '("test/functional/bio/test_command.rb")
6695 (("/bin/ls") (which "ls")))
6696 (substitute* '("test/functional/bio/test_command.rb")
6697 (("which") (which "which")))
6698 (substitute* '("test/functional/bio/test_command.rb",
6699 "test/data/command/echoarg2.sh")
6700 (("/bin/echo") (which "echo")))
6701 #t)))))
6702 (synopsis "Ruby library, shell and utilities for bioinformatics")
6703 (description "BioRuby comes with a comprehensive set of Ruby development
6704 tools and libraries for bioinformatics and molecular biology. BioRuby has
6705 components for sequence analysis, pathway analysis, protein modelling and
6706 phylogenetic analysis; it supports many widely used data formats and provides
6707 easy access to databases, external programs and public web services, including
6708 BLAST, KEGG, GenBank, MEDLINE and GO.")
6709 (home-page "http://bioruby.org/")
6710 ;; Code is released under Ruby license, except for setup
6711 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6712 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6713
6714 (define-public r-acsnminer
6715 (package
6716 (name "r-acsnminer")
6717 (version "0.16.8.25")
6718 (source (origin
6719 (method url-fetch)
6720 (uri (cran-uri "ACSNMineR" version))
6721 (sha256
6722 (base32
6723 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6724 (properties `((upstream-name . "ACSNMineR")))
6725 (build-system r-build-system)
6726 (propagated-inputs
6727 `(("r-ggplot2" ,r-ggplot2)
6728 ("r-gridextra" ,r-gridextra)))
6729 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6730 (synopsis "Gene enrichment analysis")
6731 (description
6732 "This package provides tools to compute and represent gene set enrichment
6733 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6734 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6735 enrichment can be run with hypergeometric test or Fisher exact test, and can
6736 use multiple corrections. Visualization of data can be done either by
6737 barplots or heatmaps.")
6738 (license license:gpl2+)))
6739
6740 (define-public r-biocgenerics
6741 (package
6742 (name "r-biocgenerics")
6743 (version "0.24.0")
6744 (source (origin
6745 (method url-fetch)
6746 (uri (bioconductor-uri "BiocGenerics" version))
6747 (sha256
6748 (base32
6749 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6750 (properties
6751 `((upstream-name . "BiocGenerics")))
6752 (build-system r-build-system)
6753 (home-page "https://bioconductor.org/packages/BiocGenerics")
6754 (synopsis "S4 generic functions for Bioconductor")
6755 (description
6756 "This package provides S4 generic functions needed by many Bioconductor
6757 packages.")
6758 (license license:artistic2.0)))
6759
6760 (define-public r-biocinstaller
6761 (package
6762 (name "r-biocinstaller")
6763 (version "1.28.0")
6764 (source (origin
6765 (method url-fetch)
6766 (uri (bioconductor-uri "BiocInstaller" version))
6767 (sha256
6768 (base32
6769 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6770 (properties
6771 `((upstream-name . "BiocInstaller")))
6772 (build-system r-build-system)
6773 (home-page "https://bioconductor.org/packages/BiocInstaller")
6774 (synopsis "Install Bioconductor packages")
6775 (description "This package is used to install and update R packages from
6776 Bioconductor, CRAN, and Github.")
6777 (license license:artistic2.0)))
6778
6779 (define-public r-biocviews
6780 (package
6781 (name "r-biocviews")
6782 (version "1.46.0")
6783 (source (origin
6784 (method url-fetch)
6785 (uri (bioconductor-uri "biocViews" version))
6786 (sha256
6787 (base32
6788 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6789 (properties
6790 `((upstream-name . "biocViews")))
6791 (build-system r-build-system)
6792 (propagated-inputs
6793 `(("r-biobase" ,r-biobase)
6794 ("r-graph" ,r-graph)
6795 ("r-rbgl" ,r-rbgl)
6796 ("r-rcurl" ,r-rcurl)
6797 ("r-xml" ,r-xml)
6798 ("r-runit" ,r-runit)))
6799 (home-page "https://bioconductor.org/packages/biocViews")
6800 (synopsis "Bioconductor package categorization helper")
6801 (description "The purpose of biocViews is to create HTML pages that
6802 categorize packages in a Bioconductor package repository according to keywords,
6803 also known as views, in a controlled vocabulary.")
6804 (license license:artistic2.0)))
6805
6806 (define-public r-bookdown
6807 (package
6808 (name "r-bookdown")
6809 (version "0.7")
6810 (source (origin
6811 (method url-fetch)
6812 (uri (cran-uri "bookdown" version))
6813 (sha256
6814 (base32
6815 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
6816 (build-system r-build-system)
6817 (propagated-inputs
6818 `(("r-htmltools" ,r-htmltools)
6819 ("r-knitr" ,r-knitr)
6820 ("r-rmarkdown" ,r-rmarkdown)
6821 ("r-tinytex" ,r-tinytex)
6822 ("r-yaml" ,r-yaml)
6823 ("r-xfun" ,r-xfun)
6824 ("ghc-pandoc" ,ghc-pandoc)))
6825 (home-page "https://github.com/rstudio/bookdown")
6826 (synopsis "Authoring books and technical documents with R markdown")
6827 (description "This package provides output formats and utilities for
6828 authoring books and technical documents with R Markdown.")
6829 (license license:gpl3)))
6830
6831 (define-public r-biocstyle
6832 (package
6833 (name "r-biocstyle")
6834 (version "2.6.1")
6835 (source (origin
6836 (method url-fetch)
6837 (uri (bioconductor-uri "BiocStyle" version))
6838 (sha256
6839 (base32
6840 "03pp04pkcq99kdv2spzr995h2cxsza7l6w3d4gp4112m06prcybm"))))
6841 (properties
6842 `((upstream-name . "BiocStyle")))
6843 (build-system r-build-system)
6844 (propagated-inputs
6845 `(("r-bookdown" ,r-bookdown)
6846 ("r-knitr" ,r-knitr)
6847 ("r-rmarkdown" ,r-rmarkdown)
6848 ("r-yaml" ,r-yaml)))
6849 (home-page "https://bioconductor.org/packages/BiocStyle")
6850 (synopsis "Bioconductor formatting styles")
6851 (description "This package provides standard formatting styles for
6852 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6853 functionality.")
6854 (license license:artistic2.0)))
6855
6856 (define-public r-bioccheck
6857 (package
6858 (name "r-bioccheck")
6859 (version "1.14.0")
6860 (source (origin
6861 (method url-fetch)
6862 (uri (bioconductor-uri "BiocCheck" version))
6863 (sha256
6864 (base32
6865 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6866 (properties
6867 `((upstream-name . "BiocCheck")))
6868 (build-system r-build-system)
6869 (arguments
6870 '(#:phases
6871 (modify-phases %standard-phases
6872 ;; This package can be used by calling BiocCheck(<package>) from
6873 ;; within R, or by running R CMD BiocCheck <package>. This phase
6874 ;; makes sure the latter works. For this to work, the BiocCheck
6875 ;; script must be somewhere on the PATH (not the R bin directory).
6876 (add-after 'install 'install-bioccheck-subcommand
6877 (lambda* (#:key outputs #:allow-other-keys)
6878 (let* ((out (assoc-ref outputs "out"))
6879 (dest-dir (string-append out "/bin"))
6880 (script-dir
6881 (string-append out "/site-library/BiocCheck/script/")))
6882 (mkdir-p dest-dir)
6883 (symlink (string-append script-dir "/checkBadDeps.R")
6884 (string-append dest-dir "/checkBadDeps.R"))
6885 (symlink (string-append script-dir "/BiocCheck")
6886 (string-append dest-dir "/BiocCheck")))
6887 #t)))))
6888 (propagated-inputs
6889 `(("r-codetools" ,r-codetools)
6890 ("r-graph" ,r-graph)
6891 ("r-httr" ,r-httr)
6892 ("r-optparse" ,r-optparse)
6893 ("r-biocinstaller" ,r-biocinstaller)
6894 ("r-biocviews" ,r-biocviews)
6895 ("r-stringdist" ,r-stringdist)))
6896 (home-page "https://bioconductor.org/packages/BiocCheck")
6897 (synopsis "Executes Bioconductor-specific package checks")
6898 (description "This package contains tools to perform additional quality
6899 checks on R packages that are to be submitted to the Bioconductor repository.")
6900 (license license:artistic2.0)))
6901
6902 (define-public r-getopt
6903 (package
6904 (name "r-getopt")
6905 (version "1.20.2")
6906 (source
6907 (origin
6908 (method url-fetch)
6909 (uri (cran-uri "getopt" version))
6910 (sha256
6911 (base32
6912 "13p35lbpy7i578752fa71sbfvcsqw5qfa9p6kf8b5m3c5p9i4v1x"))))
6913 (build-system r-build-system)
6914 (home-page "https://github.com/trevorld/getopt")
6915 (synopsis "Command-line option processor for R")
6916 (description
6917 "This package is designed to be used with Rscript to write shebang
6918 scripts that accept short and long options. Many users will prefer to
6919 use the packages @code{optparse} or @code{argparse} which add extra
6920 features like automatically generated help options and usage texts,
6921 support for default values, positional argument support, etc.")
6922 (license license:gpl2+)))
6923
6924 (define-public r-optparse
6925 (package
6926 (name "r-optparse")
6927 (version "1.4.4")
6928 (source
6929 (origin
6930 (method url-fetch)
6931 (uri (cran-uri "optparse" version))
6932 (sha256
6933 (base32
6934 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6935 (build-system r-build-system)
6936 (propagated-inputs
6937 `(("r-getopt" ,r-getopt)))
6938 (home-page
6939 "https://github.com/trevorld/optparse")
6940 (synopsis "Command line option parser")
6941 (description
6942 "This package provides a command line parser inspired by Python's
6943 @code{optparse} library to be used with Rscript to write shebang scripts
6944 that accept short and long options.")
6945 (license license:gpl2+)))
6946
6947 (define-public r-dnacopy
6948 (package
6949 (name "r-dnacopy")
6950 (version "1.52.0")
6951 (source (origin
6952 (method url-fetch)
6953 (uri (bioconductor-uri "DNAcopy" version))
6954 (sha256
6955 (base32
6956 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
6957 (properties
6958 `((upstream-name . "DNAcopy")))
6959 (build-system r-build-system)
6960 (inputs
6961 `(("gfortran" ,gfortran)))
6962 (home-page "https://bioconductor.org/packages/DNAcopy")
6963 (synopsis "Implementation of a circular binary segmentation algorithm")
6964 (description "This package implements the circular binary segmentation (CBS)
6965 algorithm to segment DNA copy number data and identify genomic regions with
6966 abnormal copy number.")
6967 (license license:gpl2+)))
6968
6969 (define-public r-s4vectors
6970 (package
6971 (name "r-s4vectors")
6972 (version "0.16.0")
6973 (source (origin
6974 (method url-fetch)
6975 (uri (bioconductor-uri "S4Vectors" version))
6976 (sha256
6977 (base32
6978 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
6979 (properties
6980 `((upstream-name . "S4Vectors")))
6981 (build-system r-build-system)
6982 (propagated-inputs
6983 `(("r-biocgenerics" ,r-biocgenerics)))
6984 (home-page "https://bioconductor.org/packages/S4Vectors")
6985 (synopsis "S4 implementation of vectors and lists")
6986 (description
6987 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6988 classes and a set of generic functions that extend the semantic of ordinary
6989 vectors and lists in R. Package developers can easily implement vector-like
6990 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6991 In addition, a few low-level concrete subclasses of general interest (e.g.
6992 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6993 S4Vectors package itself.")
6994 (license license:artistic2.0)))
6995
6996 (define-public r-seqinr
6997 (package
6998 (name "r-seqinr")
6999 (version "3.4-5")
7000 (source
7001 (origin
7002 (method url-fetch)
7003 (uri (cran-uri "seqinr" version))
7004 (sha256
7005 (base32
7006 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7007 (build-system r-build-system)
7008 (propagated-inputs
7009 `(("r-ade4" ,r-ade4)
7010 ("r-segmented" ,r-segmented)))
7011 (inputs
7012 `(("zlib" ,zlib)))
7013 (home-page "http://seqinr.r-forge.r-project.org/")
7014 (synopsis "Biological sequences retrieval and analysis")
7015 (description
7016 "This package provides tools for exploratory data analysis and data
7017 visualization of biological sequence (DNA and protein) data. It also includes
7018 utilities for sequence data management under the ACNUC system.")
7019 (license license:gpl2+)))
7020
7021 (define-public r-iranges
7022 (package
7023 (name "r-iranges")
7024 (version "2.12.0")
7025 (source (origin
7026 (method url-fetch)
7027 (uri (bioconductor-uri "IRanges" version))
7028 (sha256
7029 (base32
7030 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
7031 (properties
7032 `((upstream-name . "IRanges")))
7033 (build-system r-build-system)
7034 (propagated-inputs
7035 `(("r-biocgenerics" ,r-biocgenerics)
7036 ("r-s4vectors" ,r-s4vectors)))
7037 (home-page "https://bioconductor.org/packages/IRanges")
7038 (synopsis "Infrastructure for manipulating intervals on sequences")
7039 (description
7040 "This package provides efficient low-level and highly reusable S4 classes
7041 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7042 generally, data that can be organized sequentially (formally defined as
7043 @code{Vector} objects), as well as views on these @code{Vector} objects.
7044 Efficient list-like classes are also provided for storing big collections of
7045 instances of the basic classes. All classes in the package use consistent
7046 naming and share the same rich and consistent \"Vector API\" as much as
7047 possible.")
7048 (license license:artistic2.0)))
7049
7050 (define-public r-genomeinfodbdata
7051 (package
7052 (name "r-genomeinfodbdata")
7053 (version "0.99.1")
7054 (source (origin
7055 (method url-fetch)
7056 ;; We cannot use bioconductor-uri here because this tarball is
7057 ;; located under "data/annotation/" instead of "bioc/".
7058 (uri (string-append "https://bioconductor.org/packages/release/"
7059 "data/annotation/src/contrib/GenomeInfoDbData_"
7060 version ".tar.gz"))
7061 (sha256
7062 (base32
7063 "0hipipvyvrh75n68hsjg35sxbcfzrghzxv547vnkk2f8ya99g01r"))))
7064 (properties
7065 `((upstream-name . "GenomeInfoDbData")))
7066 (build-system r-build-system)
7067 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7068 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7069 (description "This package contains data for mapping between NCBI taxonomy
7070 ID and species. It is used by functions in the GenomeInfoDb package.")
7071 (license license:artistic2.0)))
7072
7073 (define-public r-genomeinfodb
7074 (package
7075 (name "r-genomeinfodb")
7076 (version "1.14.0")
7077 (source (origin
7078 (method url-fetch)
7079 (uri (bioconductor-uri "GenomeInfoDb" version))
7080 (sha256
7081 (base32
7082 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
7083 (properties
7084 `((upstream-name . "GenomeInfoDb")))
7085 (build-system r-build-system)
7086 (propagated-inputs
7087 `(("r-biocgenerics" ,r-biocgenerics)
7088 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7089 ("r-iranges" ,r-iranges)
7090 ("r-rcurl" ,r-rcurl)
7091 ("r-s4vectors" ,r-s4vectors)))
7092 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7093 (synopsis "Utilities for manipulating chromosome identifiers")
7094 (description
7095 "This package contains data and functions that define and allow
7096 translation between different chromosome sequence naming conventions (e.g.,
7097 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7098 names in their natural, rather than lexicographic, order.")
7099 (license license:artistic2.0)))
7100
7101 (define-public r-edger
7102 (package
7103 (name "r-edger")
7104 (version "3.20.9")
7105 (source (origin
7106 (method url-fetch)
7107 (uri (bioconductor-uri "edgeR" version))
7108 (sha256
7109 (base32
7110 "0y52snwbz37xzdd7gihdkqczbndlfzmmypv6hri3ymjyfmlx6qaw"))))
7111 (properties `((upstream-name . "edgeR")))
7112 (build-system r-build-system)
7113 (propagated-inputs
7114 `(("r-limma" ,r-limma)
7115 ("r-locfit" ,r-locfit)
7116 ("r-rcpp" ,r-rcpp)
7117 ("r-statmod" ,r-statmod))) ;for estimateDisp
7118 (home-page "http://bioinf.wehi.edu.au/edgeR")
7119 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7120 (description "This package can do differential expression analysis of
7121 RNA-seq expression profiles with biological replication. It implements a range
7122 of statistical methodology based on the negative binomial distributions,
7123 including empirical Bayes estimation, exact tests, generalized linear models
7124 and quasi-likelihood tests. It be applied to differential signal analysis of
7125 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7126 CAGE.")
7127 (license license:gpl2+)))
7128
7129 (define-public r-variantannotation
7130 (package
7131 (name "r-variantannotation")
7132 (version "1.24.5")
7133 (source (origin
7134 (method url-fetch)
7135 (uri (bioconductor-uri "VariantAnnotation" version))
7136 (sha256
7137 (base32
7138 "07ywn3c4w83l3sr76d0z3b1nv9icgdh3phsjlc6cfx7i6nfmvxw2"))))
7139 (properties
7140 `((upstream-name . "VariantAnnotation")))
7141 (inputs
7142 `(("zlib" ,zlib)))
7143 (propagated-inputs
7144 `(("r-annotationdbi" ,r-annotationdbi)
7145 ("r-biobase" ,r-biobase)
7146 ("r-biocgenerics" ,r-biocgenerics)
7147 ("r-biostrings" ,r-biostrings)
7148 ("r-bsgenome" ,r-bsgenome)
7149 ("r-dbi" ,r-dbi)
7150 ("r-genomeinfodb" ,r-genomeinfodb)
7151 ("r-genomicfeatures" ,r-genomicfeatures)
7152 ("r-genomicranges" ,r-genomicranges)
7153 ("r-iranges" ,r-iranges)
7154 ("r-summarizedexperiment" ,r-summarizedexperiment)
7155 ("r-rsamtools" ,r-rsamtools)
7156 ("r-rtracklayer" ,r-rtracklayer)
7157 ("r-s4vectors" ,r-s4vectors)
7158 ("r-xvector" ,r-xvector)
7159 ("r-zlibbioc" ,r-zlibbioc)))
7160 (build-system r-build-system)
7161 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7162 (synopsis "Package for annotation of genetic variants")
7163 (description "This R package can annotate variants, compute amino acid
7164 coding changes and predict coding outcomes.")
7165 (license license:artistic2.0)))
7166
7167 (define-public r-limma
7168 (package
7169 (name "r-limma")
7170 (version "3.34.9")
7171 (source (origin
7172 (method url-fetch)
7173 (uri (bioconductor-uri "limma" version))
7174 (sha256
7175 (base32
7176 "1y2fm61g5i0fn0j3l31xvwh9zww9bpkc4nwzb1d0yv1cag20jkdc"))))
7177 (build-system r-build-system)
7178 (home-page "http://bioinf.wehi.edu.au/limma")
7179 (synopsis "Package for linear models for microarray and RNA-seq data")
7180 (description "This package can be used for the analysis of gene expression
7181 studies, especially the use of linear models for analysing designed experiments
7182 and the assessment of differential expression. The analysis methods apply to
7183 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7184 (license license:gpl2+)))
7185
7186 (define-public r-xvector
7187 (package
7188 (name "r-xvector")
7189 (version "0.18.0")
7190 (source (origin
7191 (method url-fetch)
7192 (uri (bioconductor-uri "XVector" version))
7193 (sha256
7194 (base32
7195 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
7196 (properties
7197 `((upstream-name . "XVector")))
7198 (build-system r-build-system)
7199 (arguments
7200 `(#:phases
7201 (modify-phases %standard-phases
7202 (add-after 'unpack 'use-system-zlib
7203 (lambda _
7204 (substitute* "DESCRIPTION"
7205 (("zlibbioc, ") ""))
7206 (substitute* "NAMESPACE"
7207 (("import\\(zlibbioc\\)") ""))
7208 #t)))))
7209 (inputs
7210 `(("zlib" ,zlib)))
7211 (propagated-inputs
7212 `(("r-biocgenerics" ,r-biocgenerics)
7213 ("r-iranges" ,r-iranges)
7214 ("r-s4vectors" ,r-s4vectors)))
7215 (home-page "https://bioconductor.org/packages/XVector")
7216 (synopsis "Representation and manpulation of external sequences")
7217 (description
7218 "This package provides memory efficient S4 classes for storing sequences
7219 \"externally\" (behind an R external pointer, or on disk).")
7220 (license license:artistic2.0)))
7221
7222 (define-public r-genomicranges
7223 (package
7224 (name "r-genomicranges")
7225 (version "1.30.3")
7226 (source (origin
7227 (method url-fetch)
7228 (uri (bioconductor-uri "GenomicRanges" version))
7229 (sha256
7230 (base32
7231 "07cszc9ri94nzk4dffwnsj247ih6pchnrzrvnb0q4dkk33gwy8n1"))))
7232 (properties
7233 `((upstream-name . "GenomicRanges")))
7234 (build-system r-build-system)
7235 (propagated-inputs
7236 `(("r-biocgenerics" ,r-biocgenerics)
7237 ("r-genomeinfodb" ,r-genomeinfodb)
7238 ("r-iranges" ,r-iranges)
7239 ("r-s4vectors" ,r-s4vectors)
7240 ("r-xvector" ,r-xvector)))
7241 (home-page "https://bioconductor.org/packages/GenomicRanges")
7242 (synopsis "Representation and manipulation of genomic intervals")
7243 (description
7244 "This package provides tools to efficiently represent and manipulate
7245 genomic annotations and alignments is playing a central role when it comes to
7246 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7247 GenomicRanges package defines general purpose containers for storing and
7248 manipulating genomic intervals and variables defined along a genome.")
7249 (license license:artistic2.0)))
7250
7251 (define-public r-biobase
7252 (package
7253 (name "r-biobase")
7254 (version "2.38.0")
7255 (source (origin
7256 (method url-fetch)
7257 (uri (bioconductor-uri "Biobase" version))
7258 (sha256
7259 (base32
7260 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
7261 (properties
7262 `((upstream-name . "Biobase")))
7263 (build-system r-build-system)
7264 (propagated-inputs
7265 `(("r-biocgenerics" ,r-biocgenerics)))
7266 (home-page "https://bioconductor.org/packages/Biobase")
7267 (synopsis "Base functions for Bioconductor")
7268 (description
7269 "This package provides functions that are needed by many other packages
7270 on Bioconductor or which replace R functions.")
7271 (license license:artistic2.0)))
7272
7273 (define-public r-annotationdbi
7274 (package
7275 (name "r-annotationdbi")
7276 (version "1.40.0")
7277 (source (origin
7278 (method url-fetch)
7279 (uri (bioconductor-uri "AnnotationDbi" version))
7280 (sha256
7281 (base32
7282 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
7283 (properties
7284 `((upstream-name . "AnnotationDbi")))
7285 (build-system r-build-system)
7286 (propagated-inputs
7287 `(("r-biobase" ,r-biobase)
7288 ("r-biocgenerics" ,r-biocgenerics)
7289 ("r-dbi" ,r-dbi)
7290 ("r-iranges" ,r-iranges)
7291 ("r-rsqlite" ,r-rsqlite)
7292 ("r-s4vectors" ,r-s4vectors)))
7293 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7294 (synopsis "Annotation database interface")
7295 (description
7296 "This package provides user interface and database connection code for
7297 annotation data packages using SQLite data storage.")
7298 (license license:artistic2.0)))
7299
7300 (define-public r-biomart
7301 (package
7302 (name "r-biomart")
7303 (version "2.34.2")
7304 (source (origin
7305 (method url-fetch)
7306 (uri (bioconductor-uri "biomaRt" version))
7307 (sha256
7308 (base32
7309 "1zlgs2zg0lmnk572p55n7m34nkxka8w10x8f2ndssjkffl2csy79"))))
7310 (properties
7311 `((upstream-name . "biomaRt")))
7312 (build-system r-build-system)
7313 (propagated-inputs
7314 `(("r-annotationdbi" ,r-annotationdbi)
7315 ("r-httr" ,r-httr)
7316 ("r-progress" ,r-progress)
7317 ("r-rcurl" ,r-rcurl)
7318 ("r-stringr" ,r-stringr)
7319 ("r-xml" ,r-xml)))
7320 (home-page "https://bioconductor.org/packages/biomaRt")
7321 (synopsis "Interface to BioMart databases")
7322 (description
7323 "biomaRt provides an interface to a growing collection of databases
7324 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7325 package enables retrieval of large amounts of data in a uniform way without
7326 the need to know the underlying database schemas or write complex SQL queries.
7327 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7328 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7329 users direct access to a diverse set of data and enable a wide range of
7330 powerful online queries from gene annotation to database mining.")
7331 (license license:artistic2.0)))
7332
7333 (define-public r-biocparallel
7334 (package
7335 (name "r-biocparallel")
7336 (version "1.12.0")
7337 (source (origin
7338 (method url-fetch)
7339 (uri (bioconductor-uri "BiocParallel" version))
7340 (sha256
7341 (base32
7342 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
7343 (properties
7344 `((upstream-name . "BiocParallel")))
7345 (build-system r-build-system)
7346 (propagated-inputs
7347 `(("r-futile-logger" ,r-futile-logger)
7348 ("r-snow" ,r-snow)
7349 ("r-bh" ,r-bh)))
7350 (home-page "https://bioconductor.org/packages/BiocParallel")
7351 (synopsis "Bioconductor facilities for parallel evaluation")
7352 (description
7353 "This package provides modified versions and novel implementation of
7354 functions for parallel evaluation, tailored to use with Bioconductor
7355 objects.")
7356 (license (list license:gpl2+ license:gpl3+))))
7357
7358 (define-public r-biostrings
7359 (package
7360 (name "r-biostrings")
7361 (version "2.46.0")
7362 (source (origin
7363 (method url-fetch)
7364 (uri (bioconductor-uri "Biostrings" version))
7365 (sha256
7366 (base32
7367 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7368 (properties
7369 `((upstream-name . "Biostrings")))
7370 (build-system r-build-system)
7371 (propagated-inputs
7372 `(("r-biocgenerics" ,r-biocgenerics)
7373 ("r-iranges" ,r-iranges)
7374 ("r-s4vectors" ,r-s4vectors)
7375 ("r-xvector" ,r-xvector)))
7376 (home-page "https://bioconductor.org/packages/Biostrings")
7377 (synopsis "String objects and algorithms for biological sequences")
7378 (description
7379 "This package provides memory efficient string containers, string
7380 matching algorithms, and other utilities, for fast manipulation of large
7381 biological sequences or sets of sequences.")
7382 (license license:artistic2.0)))
7383
7384 (define-public r-rsamtools
7385 (package
7386 (name "r-rsamtools")
7387 (version "1.30.0")
7388 (source (origin
7389 (method url-fetch)
7390 (uri (bioconductor-uri "Rsamtools" version))
7391 (sha256
7392 (base32
7393 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7394 (properties
7395 `((upstream-name . "Rsamtools")))
7396 (build-system r-build-system)
7397 (arguments
7398 `(#:phases
7399 (modify-phases %standard-phases
7400 (add-after 'unpack 'use-system-zlib
7401 (lambda _
7402 (substitute* "DESCRIPTION"
7403 (("zlibbioc, ") ""))
7404 (substitute* "NAMESPACE"
7405 (("import\\(zlibbioc\\)") ""))
7406 #t)))))
7407 (inputs
7408 `(("zlib" ,zlib)))
7409 (propagated-inputs
7410 `(("r-biocgenerics" ,r-biocgenerics)
7411 ("r-biocparallel" ,r-biocparallel)
7412 ("r-biostrings" ,r-biostrings)
7413 ("r-bitops" ,r-bitops)
7414 ("r-genomeinfodb" ,r-genomeinfodb)
7415 ("r-genomicranges" ,r-genomicranges)
7416 ("r-iranges" ,r-iranges)
7417 ("r-s4vectors" ,r-s4vectors)
7418 ("r-xvector" ,r-xvector)))
7419 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7420 (synopsis "Interface to samtools, bcftools, and tabix")
7421 (description
7422 "This package provides an interface to the 'samtools', 'bcftools', and
7423 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7424 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7425 files.")
7426 (license license:expat)))
7427
7428 (define-public r-delayedarray
7429 (package
7430 (name "r-delayedarray")
7431 (version "0.4.1")
7432 (source (origin
7433 (method url-fetch)
7434 (uri (bioconductor-uri "DelayedArray" version))
7435 (sha256
7436 (base32
7437 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7438 (properties
7439 `((upstream-name . "DelayedArray")))
7440 (build-system r-build-system)
7441 (propagated-inputs
7442 `(("r-biocgenerics" ,r-biocgenerics)
7443 ("r-s4vectors" ,r-s4vectors)
7444 ("r-iranges" ,r-iranges)
7445 ("r-matrixstats" ,r-matrixstats)))
7446 (home-page "https://bioconductor.org/packages/DelayedArray")
7447 (synopsis "Delayed operations on array-like objects")
7448 (description
7449 "Wrapping an array-like object (typically an on-disk object) in a
7450 @code{DelayedArray} object allows one to perform common array operations on it
7451 without loading the object in memory. In order to reduce memory usage and
7452 optimize performance, operations on the object are either delayed or executed
7453 using a block processing mechanism. Note that this also works on in-memory
7454 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7455 @code{Matrix} objects, and ordinary arrays and data frames.")
7456 (license license:artistic2.0)))
7457
7458 (define-public r-summarizedexperiment
7459 (package
7460 (name "r-summarizedexperiment")
7461 (version "1.8.1")
7462 (source (origin
7463 (method url-fetch)
7464 (uri (bioconductor-uri "SummarizedExperiment" version))
7465 (sha256
7466 (base32
7467 "19vlwnby83fqjrilsxvnvgz0gvby7mrxvlmx18nb3p1w591ddfjh"))))
7468 (properties
7469 `((upstream-name . "SummarizedExperiment")))
7470 (build-system r-build-system)
7471 (propagated-inputs
7472 `(("r-biobase" ,r-biobase)
7473 ("r-biocgenerics" ,r-biocgenerics)
7474 ("r-delayedarray" ,r-delayedarray)
7475 ("r-genomeinfodb" ,r-genomeinfodb)
7476 ("r-genomicranges" ,r-genomicranges)
7477 ("r-iranges" ,r-iranges)
7478 ("r-matrix" ,r-matrix)
7479 ("r-s4vectors" ,r-s4vectors)))
7480 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7481 (synopsis "Container for representing genomic ranges by sample")
7482 (description
7483 "The SummarizedExperiment container contains one or more assays, each
7484 represented by a matrix-like object of numeric or other mode. The rows
7485 typically represent genomic ranges of interest and the columns represent
7486 samples.")
7487 (license license:artistic2.0)))
7488
7489 (define-public r-genomicalignments
7490 (package
7491 (name "r-genomicalignments")
7492 (version "1.14.1")
7493 (source (origin
7494 (method url-fetch)
7495 (uri (bioconductor-uri "GenomicAlignments" version))
7496 (sha256
7497 (base32
7498 "033p6fw46sn7w2yyn14nb9qcnkf30cl0nv6zh014ixflm3iifz39"))))
7499 (properties
7500 `((upstream-name . "GenomicAlignments")))
7501 (build-system r-build-system)
7502 (propagated-inputs
7503 `(("r-biocgenerics" ,r-biocgenerics)
7504 ("r-biocparallel" ,r-biocparallel)
7505 ("r-biostrings" ,r-biostrings)
7506 ("r-genomeinfodb" ,r-genomeinfodb)
7507 ("r-genomicranges" ,r-genomicranges)
7508 ("r-iranges" ,r-iranges)
7509 ("r-rsamtools" ,r-rsamtools)
7510 ("r-s4vectors" ,r-s4vectors)
7511 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7512 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7513 (synopsis "Representation and manipulation of short genomic alignments")
7514 (description
7515 "This package provides efficient containers for storing and manipulating
7516 short genomic alignments (typically obtained by aligning short reads to a
7517 reference genome). This includes read counting, computing the coverage,
7518 junction detection, and working with the nucleotide content of the
7519 alignments.")
7520 (license license:artistic2.0)))
7521
7522 (define-public r-rtracklayer
7523 (package
7524 (name "r-rtracklayer")
7525 (version "1.38.3")
7526 (source (origin
7527 (method url-fetch)
7528 (uri (bioconductor-uri "rtracklayer" version))
7529 (sha256
7530 (base32
7531 "1khzfczm35k5lq9h0jlqrq01192spzjyh8s6is89spj006flwn4k"))))
7532 (build-system r-build-system)
7533 (arguments
7534 `(#:phases
7535 (modify-phases %standard-phases
7536 (add-after 'unpack 'use-system-zlib
7537 (lambda _
7538 (substitute* "DESCRIPTION"
7539 ((" zlibbioc,") ""))
7540 (substitute* "NAMESPACE"
7541 (("import\\(zlibbioc\\)") ""))
7542 #t)))))
7543 (inputs
7544 `(("zlib" ,zlib)))
7545 (propagated-inputs
7546 `(("r-biocgenerics" ,r-biocgenerics)
7547 ("r-biostrings" ,r-biostrings)
7548 ("r-genomeinfodb" ,r-genomeinfodb)
7549 ("r-genomicalignments" ,r-genomicalignments)
7550 ("r-genomicranges" ,r-genomicranges)
7551 ("r-iranges" ,r-iranges)
7552 ("r-rcurl" ,r-rcurl)
7553 ("r-rsamtools" ,r-rsamtools)
7554 ("r-s4vectors" ,r-s4vectors)
7555 ("r-xml" ,r-xml)
7556 ("r-xvector" ,r-xvector)))
7557 (home-page "https://bioconductor.org/packages/rtracklayer")
7558 (synopsis "R interface to genome browsers and their annotation tracks")
7559 (description
7560 "rtracklayer is an extensible framework for interacting with multiple
7561 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7562 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7563 built-in). The user may export/import tracks to/from the supported browsers,
7564 as well as query and modify the browser state, such as the current viewport.")
7565 (license license:artistic2.0)))
7566
7567 (define-public r-genomicfeatures
7568 (package
7569 (name "r-genomicfeatures")
7570 (version "1.30.3")
7571 (source (origin
7572 (method url-fetch)
7573 (uri (bioconductor-uri "GenomicFeatures" version))
7574 (sha256
7575 (base32
7576 "010vn8hlwbnw12pd1d8pv6m12yp3xwx557gba5rbjq9p4qypnn3z"))))
7577 (properties
7578 `((upstream-name . "GenomicFeatures")))
7579 (build-system r-build-system)
7580 (propagated-inputs
7581 `(("r-annotationdbi" ,r-annotationdbi)
7582 ("r-biobase" ,r-biobase)
7583 ("r-biocgenerics" ,r-biocgenerics)
7584 ("r-biomart" ,r-biomart)
7585 ("r-biostrings" ,r-biostrings)
7586 ("r-dbi" ,r-dbi)
7587 ("r-genomeinfodb" ,r-genomeinfodb)
7588 ("r-genomicranges" ,r-genomicranges)
7589 ("r-iranges" ,r-iranges)
7590 ("r-rcurl" ,r-rcurl)
7591 ("r-rsqlite" ,r-rsqlite)
7592 ("r-rmysql" ,r-rmysql)
7593 ("r-rtracklayer" ,r-rtracklayer)
7594 ("r-s4vectors" ,r-s4vectors)
7595 ("r-xvector" ,r-xvector)))
7596 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7597 (synopsis "Tools for working with transcript centric annotations")
7598 (description
7599 "This package provides a set of tools and methods for making and
7600 manipulating transcript centric annotations. With these tools the user can
7601 easily download the genomic locations of the transcripts, exons and cds of a
7602 given organism, from either the UCSC Genome Browser or a BioMart
7603 database (more sources will be supported in the future). This information is
7604 then stored in a local database that keeps track of the relationship between
7605 transcripts, exons, cds and genes. Flexible methods are provided for
7606 extracting the desired features in a convenient format.")
7607 (license license:artistic2.0)))
7608
7609 (define-public r-go-db
7610 (package
7611 (name "r-go-db")
7612 (version "3.5.0")
7613 (source (origin
7614 (method url-fetch)
7615 (uri (string-append "https://www.bioconductor.org/packages/"
7616 "release/data/annotation/src/contrib/GO.db_"
7617 version ".tar.gz"))
7618 (sha256
7619 (base32
7620 "02d1mn1al3q7qvhx1ylrr3ar4w4iw0qyi5d89v2336rzwk9maq35"))))
7621 (properties
7622 `((upstream-name . "GO.db")))
7623 (build-system r-build-system)
7624 (propagated-inputs
7625 `(("r-annotationdbi" ,r-annotationdbi)))
7626 (home-page "https://bioconductor.org/packages/GO.db")
7627 (synopsis "Annotation maps describing the entire Gene Ontology")
7628 (description
7629 "The purpose of this GO.db annotation package is to provide detailed
7630 information about the latest version of the Gene Ontologies.")
7631 (license license:artistic2.0)))
7632
7633 (define-public r-graph
7634 (package
7635 (name "r-graph")
7636 (version "1.56.0")
7637 (source (origin
7638 (method url-fetch)
7639 (uri (bioconductor-uri "graph" version))
7640 (sha256
7641 (base32
7642 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7643 (build-system r-build-system)
7644 (propagated-inputs
7645 `(("r-biocgenerics" ,r-biocgenerics)))
7646 (home-page "https://bioconductor.org/packages/graph")
7647 (synopsis "Handle graph data structures in R")
7648 (description
7649 "This package implements some simple graph handling capabilities for R.")
7650 (license license:artistic2.0)))
7651
7652 (define-public r-topgo
7653 (package
7654 (name "r-topgo")
7655 (version "2.30.1")
7656 (source (origin
7657 (method url-fetch)
7658 (uri (bioconductor-uri "topGO" version))
7659 (sha256
7660 (base32
7661 "1cgz4knxr328xfqlhl6ypxl6x86rfrlqz748kn94ainxjzz55i6x"))))
7662 (properties
7663 `((upstream-name . "topGO")))
7664 (build-system r-build-system)
7665 (propagated-inputs
7666 `(("r-annotationdbi" ,r-annotationdbi)
7667 ("r-dbi" ,r-dbi)
7668 ("r-biobase" ,r-biobase)
7669 ("r-biocgenerics" ,r-biocgenerics)
7670 ("r-go-db" ,r-go-db)
7671 ("r-graph" ,r-graph)
7672 ("r-lattice" ,r-lattice)
7673 ("r-matrixstats" ,r-matrixstats)
7674 ("r-sparsem" ,r-sparsem)))
7675 (home-page "https://bioconductor.org/packages/topGO")
7676 (synopsis "Enrichment analysis for gene ontology")
7677 (description
7678 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7679 terms while accounting for the topology of the GO graph. Different test
7680 statistics and different methods for eliminating local similarities and
7681 dependencies between GO terms can be implemented and applied.")
7682 ;; Any version of the LGPL applies.
7683 (license license:lgpl2.1+)))
7684
7685 (define-public r-bsgenome
7686 (package
7687 (name "r-bsgenome")
7688 (version "1.46.0")
7689 (source (origin
7690 (method url-fetch)
7691 (uri (bioconductor-uri "BSgenome" version))
7692 (sha256
7693 (base32
7694 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7695 (properties
7696 `((upstream-name . "BSgenome")))
7697 (build-system r-build-system)
7698 (propagated-inputs
7699 `(("r-biocgenerics" ,r-biocgenerics)
7700 ("r-biostrings" ,r-biostrings)
7701 ("r-genomeinfodb" ,r-genomeinfodb)
7702 ("r-genomicranges" ,r-genomicranges)
7703 ("r-iranges" ,r-iranges)
7704 ("r-rsamtools" ,r-rsamtools)
7705 ("r-rtracklayer" ,r-rtracklayer)
7706 ("r-s4vectors" ,r-s4vectors)
7707 ("r-xvector" ,r-xvector)))
7708 (home-page "https://bioconductor.org/packages/BSgenome")
7709 (synopsis "Infrastructure for Biostrings-based genome data packages")
7710 (description
7711 "This package provides infrastructure shared by all Biostrings-based
7712 genome data packages and support for efficient SNP representation.")
7713 (license license:artistic2.0)))
7714
7715 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7716 (package
7717 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7718 (version "0.99.1")
7719 (source (origin
7720 (method url-fetch)
7721 ;; We cannot use bioconductor-uri here because this tarball is
7722 ;; located under "data/annotation/" instead of "bioc/".
7723 (uri (string-append "https://www.bioconductor.org/packages/"
7724 "release/data/annotation/src/contrib/"
7725 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7726 version ".tar.gz"))
7727 (sha256
7728 (base32
7729 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7730 (properties
7731 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7732 (build-system r-build-system)
7733 ;; As this package provides little more than a very large data file it
7734 ;; doesn't make sense to build substitutes.
7735 (arguments `(#:substitutable? #f))
7736 (propagated-inputs
7737 `(("r-bsgenome" ,r-bsgenome)))
7738 (home-page
7739 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7740 (synopsis "Full genome sequences for Homo sapiens")
7741 (description
7742 "This package provides full genome sequences for Homo sapiens from
7743 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7744 (license license:artistic2.0)))
7745
7746 (define-public r-impute
7747 (package
7748 (name "r-impute")
7749 (version "1.52.0")
7750 (source (origin
7751 (method url-fetch)
7752 (uri (bioconductor-uri "impute" version))
7753 (sha256
7754 (base32
7755 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7756 (inputs
7757 `(("gfortran" ,gfortran)))
7758 (build-system r-build-system)
7759 (home-page "https://bioconductor.org/packages/impute")
7760 (synopsis "Imputation for microarray data")
7761 (description
7762 "This package provides a function to impute missing gene expression
7763 microarray data, using nearest neighbor averaging.")
7764 (license license:gpl2+)))
7765
7766 (define-public r-seqpattern
7767 (package
7768 (name "r-seqpattern")
7769 (version "1.10.0")
7770 (source (origin
7771 (method url-fetch)
7772 (uri (bioconductor-uri "seqPattern" version))
7773 (sha256
7774 (base32
7775 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7776 (properties
7777 `((upstream-name . "seqPattern")))
7778 (build-system r-build-system)
7779 (propagated-inputs
7780 `(("r-biostrings" ,r-biostrings)
7781 ("r-genomicranges" ,r-genomicranges)
7782 ("r-iranges" ,r-iranges)
7783 ("r-kernsmooth" ,r-kernsmooth)
7784 ("r-plotrix" ,r-plotrix)))
7785 (home-page "https://bioconductor.org/packages/seqPattern")
7786 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7787 (description
7788 "This package provides tools to visualize oligonucleotide patterns and
7789 sequence motif occurrences across a large set of sequences centred at a common
7790 reference point and sorted by a user defined feature.")
7791 (license license:gpl3+)))
7792
7793 (define-public r-genomation
7794 (package
7795 (name "r-genomation")
7796 (version "1.11.3")
7797 (source (origin
7798 (method url-fetch)
7799 (uri (bioconductor-uri "genomation" version))
7800 (sha256
7801 (base32
7802 "1d2g1v6xhrf3gm86pv8ln22df5g6v6k6i4i39v4j82zn4apany6v"))))
7803 (build-system r-build-system)
7804 (propagated-inputs
7805 `(("r-biostrings" ,r-biostrings)
7806 ("r-bsgenome" ,r-bsgenome)
7807 ("r-data-table" ,r-data-table)
7808 ("r-genomeinfodb" ,r-genomeinfodb)
7809 ("r-genomicalignments" ,r-genomicalignments)
7810 ("r-genomicranges" ,r-genomicranges)
7811 ("r-ggplot2" ,r-ggplot2)
7812 ("r-gridbase" ,r-gridbase)
7813 ("r-impute" ,r-impute)
7814 ("r-iranges" ,r-iranges)
7815 ("r-matrixstats" ,r-matrixstats)
7816 ("r-plotrix" ,r-plotrix)
7817 ("r-plyr" ,r-plyr)
7818 ("r-rcpp" ,r-rcpp)
7819 ("r-readr" ,r-readr)
7820 ("r-reshape2" ,r-reshape2)
7821 ("r-rsamtools" ,r-rsamtools)
7822 ("r-rtracklayer" ,r-rtracklayer)
7823 ("r-runit" ,r-runit)
7824 ("r-s4vectors" ,r-s4vectors)
7825 ("r-seqpattern" ,r-seqpattern)))
7826 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7827 (synopsis "Summary, annotation and visualization of genomic data")
7828 (description
7829 "This package provides a package for summary and annotation of genomic
7830 intervals. Users can visualize and quantify genomic intervals over
7831 pre-defined functional regions, such as promoters, exons, introns, etc. The
7832 genomic intervals represent regions with a defined chromosome position, which
7833 may be associated with a score, such as aligned reads from HT-seq experiments,
7834 TF binding sites, methylation scores, etc. The package can use any tabular
7835 genomic feature data as long as it has minimal information on the locations of
7836 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7837 (license license:artistic2.0)))
7838
7839 (define-public r-genomationdata
7840 (package
7841 (name "r-genomationdata")
7842 (version "1.10.0")
7843 (source (origin
7844 (method url-fetch)
7845 ;; We cannot use bioconductor-uri here because this tarball is
7846 ;; located under "data/annotation/" instead of "bioc/".
7847 (uri (string-append "https://bioconductor.org/packages/"
7848 "release/data/experiment/src/contrib/"
7849 "genomationData_" version ".tar.gz"))
7850 (sha256
7851 (base32
7852 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7853 (build-system r-build-system)
7854 ;; As this package provides little more than large data files, it doesn't
7855 ;; make sense to build substitutes.
7856 (arguments `(#:substitutable? #f))
7857 (native-inputs
7858 `(("r-knitr" ,r-knitr)))
7859 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7860 (synopsis "Experimental data for use with the genomation package")
7861 (description
7862 "This package contains experimental genetic data for use with the
7863 genomation package. Included are Chip Seq, Methylation and Cage data,
7864 downloaded from Encode.")
7865 (license license:gpl3+)))
7866
7867 (define-public r-org-hs-eg-db
7868 (package
7869 (name "r-org-hs-eg-db")
7870 (version "3.5.0")
7871 (source (origin
7872 (method url-fetch)
7873 ;; We cannot use bioconductor-uri here because this tarball is
7874 ;; located under "data/annotation/" instead of "bioc/".
7875 (uri (string-append "https://www.bioconductor.org/packages/"
7876 "release/data/annotation/src/contrib/"
7877 "org.Hs.eg.db_" version ".tar.gz"))
7878 (sha256
7879 (base32
7880 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7881 (properties
7882 `((upstream-name . "org.Hs.eg.db")))
7883 (build-system r-build-system)
7884 (propagated-inputs
7885 `(("r-annotationdbi" ,r-annotationdbi)))
7886 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7887 (synopsis "Genome wide annotation for Human")
7888 (description
7889 "This package contains genome-wide annotations for Human, primarily based
7890 on mapping using Entrez Gene identifiers.")
7891 (license license:artistic2.0)))
7892
7893 (define-public r-org-ce-eg-db
7894 (package
7895 (name "r-org-ce-eg-db")
7896 (version "3.5.0")
7897 (source (origin
7898 (method url-fetch)
7899 ;; We cannot use bioconductor-uri here because this tarball is
7900 ;; located under "data/annotation/" instead of "bioc/".
7901 (uri (string-append "https://www.bioconductor.org/packages/"
7902 "release/data/annotation/src/contrib/"
7903 "org.Ce.eg.db_" version ".tar.gz"))
7904 (sha256
7905 (base32
7906 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
7907 (properties
7908 `((upstream-name . "org.Ce.eg.db")))
7909 (build-system r-build-system)
7910 (propagated-inputs
7911 `(("r-annotationdbi" ,r-annotationdbi)))
7912 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7913 (synopsis "Genome wide annotation for Worm")
7914 (description
7915 "This package provides mappings from Entrez gene identifiers to various
7916 annotations for the genome of the model worm Caenorhabditis elegans.")
7917 (license license:artistic2.0)))
7918
7919 (define-public r-org-dm-eg-db
7920 (package
7921 (name "r-org-dm-eg-db")
7922 (version "3.5.0")
7923 (source (origin
7924 (method url-fetch)
7925 ;; We cannot use bioconductor-uri here because this tarball is
7926 ;; located under "data/annotation/" instead of "bioc/".
7927 (uri (string-append "https://www.bioconductor.org/packages/"
7928 "release/data/annotation/src/contrib/"
7929 "org.Dm.eg.db_" version ".tar.gz"))
7930 (sha256
7931 (base32
7932 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
7933 (properties
7934 `((upstream-name . "org.Dm.eg.db")))
7935 (build-system r-build-system)
7936 (propagated-inputs
7937 `(("r-annotationdbi" ,r-annotationdbi)))
7938 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
7939 (synopsis "Genome wide annotation for Fly")
7940 (description
7941 "This package provides mappings from Entrez gene identifiers to various
7942 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7943 (license license:artistic2.0)))
7944
7945 (define-public r-org-mm-eg-db
7946 (package
7947 (name "r-org-mm-eg-db")
7948 (version "3.5.0")
7949 (source (origin
7950 (method url-fetch)
7951 ;; We cannot use bioconductor-uri here because this tarball is
7952 ;; located under "data/annotation/" instead of "bioc/".
7953 (uri (string-append "https://www.bioconductor.org/packages/"
7954 "release/data/annotation/src/contrib/"
7955 "org.Mm.eg.db_" version ".tar.gz"))
7956 (sha256
7957 (base32
7958 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
7959 (properties
7960 `((upstream-name . "org.Mm.eg.db")))
7961 (build-system r-build-system)
7962 (propagated-inputs
7963 `(("r-annotationdbi" ,r-annotationdbi)))
7964 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
7965 (synopsis "Genome wide annotation for Mouse")
7966 (description
7967 "This package provides mappings from Entrez gene identifiers to various
7968 annotations for the genome of the model mouse Mus musculus.")
7969 (license license:artistic2.0)))
7970
7971 (define-public r-seqlogo
7972 (package
7973 (name "r-seqlogo")
7974 (version "1.44.0")
7975 (source
7976 (origin
7977 (method url-fetch)
7978 (uri (bioconductor-uri "seqLogo" version))
7979 (sha256
7980 (base32
7981 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
7982 (properties `((upstream-name . "seqLogo")))
7983 (build-system r-build-system)
7984 (home-page "https://bioconductor.org/packages/seqLogo")
7985 (synopsis "Sequence logos for DNA sequence alignments")
7986 (description
7987 "seqLogo takes the position weight matrix of a DNA sequence motif and
7988 plots the corresponding sequence logo as introduced by Schneider and
7989 Stephens (1990).")
7990 (license license:lgpl2.0+)))
7991
7992 (define-public r-bsgenome-hsapiens-ucsc-hg19
7993 (package
7994 (name "r-bsgenome-hsapiens-ucsc-hg19")
7995 (version "1.4.0")
7996 (source (origin
7997 (method url-fetch)
7998 ;; We cannot use bioconductor-uri here because this tarball is
7999 ;; located under "data/annotation/" instead of "bioc/".
8000 (uri (string-append "https://www.bioconductor.org/packages/"
8001 "release/data/annotation/src/contrib/"
8002 "BSgenome.Hsapiens.UCSC.hg19_"
8003 version ".tar.gz"))
8004 (sha256
8005 (base32
8006 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8007 (properties
8008 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8009 (build-system r-build-system)
8010 ;; As this package provides little more than a very large data file it
8011 ;; doesn't make sense to build substitutes.
8012 (arguments `(#:substitutable? #f))
8013 (propagated-inputs
8014 `(("r-bsgenome" ,r-bsgenome)))
8015 (home-page
8016 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8017 (synopsis "Full genome sequences for Homo sapiens")
8018 (description
8019 "This package provides full genome sequences for Homo sapiens as provided
8020 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8021 (license license:artistic2.0)))
8022
8023 (define-public r-bsgenome-mmusculus-ucsc-mm9
8024 (package
8025 (name "r-bsgenome-mmusculus-ucsc-mm9")
8026 (version "1.4.0")
8027 (source (origin
8028 (method url-fetch)
8029 ;; We cannot use bioconductor-uri here because this tarball is
8030 ;; located under "data/annotation/" instead of "bioc/".
8031 (uri (string-append "https://www.bioconductor.org/packages/"
8032 "release/data/annotation/src/contrib/"
8033 "BSgenome.Mmusculus.UCSC.mm9_"
8034 version ".tar.gz"))
8035 (sha256
8036 (base32
8037 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8038 (properties
8039 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8040 (build-system r-build-system)
8041 ;; As this package provides little more than a very large data file it
8042 ;; doesn't make sense to build substitutes.
8043 (arguments `(#:substitutable? #f))
8044 (propagated-inputs
8045 `(("r-bsgenome" ,r-bsgenome)))
8046 (home-page
8047 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8048 (synopsis "Full genome sequences for Mouse")
8049 (description
8050 "This package provides full genome sequences for Mus musculus (Mouse) as
8051 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8052 (license license:artistic2.0)))
8053
8054 (define-public r-bsgenome-mmusculus-ucsc-mm10
8055 (package
8056 (name "r-bsgenome-mmusculus-ucsc-mm10")
8057 (version "1.4.0")
8058 (source (origin
8059 (method url-fetch)
8060 ;; We cannot use bioconductor-uri here because this tarball is
8061 ;; located under "data/annotation/" instead of "bioc/".
8062 (uri (string-append "https://www.bioconductor.org/packages/"
8063 "release/data/annotation/src/contrib/"
8064 "BSgenome.Mmusculus.UCSC.mm10_"
8065 version ".tar.gz"))
8066 (sha256
8067 (base32
8068 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8069 (properties
8070 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8071 (build-system r-build-system)
8072 ;; As this package provides little more than a very large data file it
8073 ;; doesn't make sense to build substitutes.
8074 (arguments `(#:substitutable? #f))
8075 (propagated-inputs
8076 `(("r-bsgenome" ,r-bsgenome)))
8077 (home-page
8078 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8079 (synopsis "Full genome sequences for Mouse")
8080 (description
8081 "This package provides full genome sequences for Mus
8082 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8083 in Biostrings objects.")
8084 (license license:artistic2.0)))
8085
8086 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8087 (package
8088 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8089 (version "3.4.0")
8090 (source (origin
8091 (method url-fetch)
8092 ;; We cannot use bioconductor-uri here because this tarball is
8093 ;; located under "data/annotation/" instead of "bioc/".
8094 (uri (string-append "https://www.bioconductor.org/packages/"
8095 "release/data/annotation/src/contrib/"
8096 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8097 version ".tar.gz"))
8098 (sha256
8099 (base32
8100 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8101 (properties
8102 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8103 (build-system r-build-system)
8104 ;; As this package provides little more than a very large data file it
8105 ;; doesn't make sense to build substitutes.
8106 (arguments `(#:substitutable? #f))
8107 (propagated-inputs
8108 `(("r-bsgenome" ,r-bsgenome)
8109 ("r-genomicfeatures" ,r-genomicfeatures)
8110 ("r-annotationdbi" ,r-annotationdbi)))
8111 (home-page
8112 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8113 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8114 (description
8115 "This package loads a TxDb object, which is an R interface to
8116 prefabricated databases contained in this package. This package provides
8117 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8118 based on the knownGene track.")
8119 (license license:artistic2.0)))
8120
8121 (define-public r-bsgenome-celegans-ucsc-ce6
8122 (package
8123 (name "r-bsgenome-celegans-ucsc-ce6")
8124 (version "1.4.0")
8125 (source (origin
8126 (method url-fetch)
8127 ;; We cannot use bioconductor-uri here because this tarball is
8128 ;; located under "data/annotation/" instead of "bioc/".
8129 (uri (string-append "https://www.bioconductor.org/packages/"
8130 "release/data/annotation/src/contrib/"
8131 "BSgenome.Celegans.UCSC.ce6_"
8132 version ".tar.gz"))
8133 (sha256
8134 (base32
8135 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8136 (properties
8137 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8138 (build-system r-build-system)
8139 ;; As this package provides little more than a very large data file it
8140 ;; doesn't make sense to build substitutes.
8141 (arguments `(#:substitutable? #f))
8142 (propagated-inputs
8143 `(("r-bsgenome" ,r-bsgenome)))
8144 (home-page
8145 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8146 (synopsis "Full genome sequences for Worm")
8147 (description
8148 "This package provides full genome sequences for Caenorhabditis
8149 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8150 objects.")
8151 (license license:artistic2.0)))
8152
8153 (define-public r-bsgenome-celegans-ucsc-ce10
8154 (package
8155 (name "r-bsgenome-celegans-ucsc-ce10")
8156 (version "1.4.0")
8157 (source (origin
8158 (method url-fetch)
8159 ;; We cannot use bioconductor-uri here because this tarball is
8160 ;; located under "data/annotation/" instead of "bioc/".
8161 (uri (string-append "https://www.bioconductor.org/packages/"
8162 "release/data/annotation/src/contrib/"
8163 "BSgenome.Celegans.UCSC.ce10_"
8164 version ".tar.gz"))
8165 (sha256
8166 (base32
8167 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8168 (properties
8169 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8170 (build-system r-build-system)
8171 ;; As this package provides little more than a very large data file it
8172 ;; doesn't make sense to build substitutes.
8173 (arguments `(#:substitutable? #f))
8174 (propagated-inputs
8175 `(("r-bsgenome" ,r-bsgenome)))
8176 (home-page
8177 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8178 (synopsis "Full genome sequences for Worm")
8179 (description
8180 "This package provides full genome sequences for Caenorhabditis
8181 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8182 objects.")
8183 (license license:artistic2.0)))
8184
8185 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8186 (package
8187 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8188 (version "1.4.0")
8189 (source (origin
8190 (method url-fetch)
8191 ;; We cannot use bioconductor-uri here because this tarball is
8192 ;; located under "data/annotation/" instead of "bioc/".
8193 (uri (string-append "https://www.bioconductor.org/packages/"
8194 "release/data/annotation/src/contrib/"
8195 "BSgenome.Dmelanogaster.UCSC.dm3_"
8196 version ".tar.gz"))
8197 (sha256
8198 (base32
8199 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8200 (properties
8201 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8202 (build-system r-build-system)
8203 ;; As this package provides little more than a very large data file it
8204 ;; doesn't make sense to build substitutes.
8205 (arguments `(#:substitutable? #f))
8206 (propagated-inputs
8207 `(("r-bsgenome" ,r-bsgenome)))
8208 (home-page
8209 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8210 (synopsis "Full genome sequences for Fly")
8211 (description
8212 "This package provides full genome sequences for Drosophila
8213 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8214 Biostrings objects.")
8215 (license license:artistic2.0)))
8216
8217 (define-public r-motifrg
8218 (package
8219 (name "r-motifrg")
8220 (version "1.22.0")
8221 (source
8222 (origin
8223 (method url-fetch)
8224 (uri (bioconductor-uri "motifRG" version))
8225 (sha256
8226 (base32
8227 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
8228 (properties `((upstream-name . "motifRG")))
8229 (build-system r-build-system)
8230 (propagated-inputs
8231 `(("r-biostrings" ,r-biostrings)
8232 ("r-bsgenome" ,r-bsgenome)
8233 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8234 ("r-iranges" ,r-iranges)
8235 ("r-seqlogo" ,r-seqlogo)
8236 ("r-xvector" ,r-xvector)))
8237 (home-page "https://bioconductor.org/packages/motifRG")
8238 (synopsis "Discover motifs in high throughput sequencing data")
8239 (description
8240 "This package provides tools for discriminative motif discovery in high
8241 throughput genetic sequencing data sets using regression methods.")
8242 (license license:artistic2.0)))
8243
8244 (define-public r-qtl
8245 (package
8246 (name "r-qtl")
8247 (version "1.42-8")
8248 (source
8249 (origin
8250 (method url-fetch)
8251 (uri (string-append "mirror://cran/src/contrib/qtl_"
8252 version ".tar.gz"))
8253 (sha256
8254 (base32
8255 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8256 (build-system r-build-system)
8257 (home-page "http://rqtl.org/")
8258 (synopsis "R package for analyzing QTL experiments in genetics")
8259 (description "R/qtl is an extension library for the R statistics
8260 system. It is used to analyze experimental crosses for identifying
8261 genes contributing to variation in quantitative traits (so-called
8262 quantitative trait loci, QTLs).
8263
8264 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8265 identify genotyping errors, and to perform single-QTL and two-QTL,
8266 two-dimensional genome scans.")
8267 (license license:gpl3)))
8268
8269 (define-public r-zlibbioc
8270 (package
8271 (name "r-zlibbioc")
8272 (version "1.24.0")
8273 (source (origin
8274 (method url-fetch)
8275 (uri (bioconductor-uri "zlibbioc" version))
8276 (sha256
8277 (base32
8278 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
8279 (properties
8280 `((upstream-name . "zlibbioc")))
8281 (build-system r-build-system)
8282 (home-page "https://bioconductor.org/packages/zlibbioc")
8283 (synopsis "Provider for zlib-1.2.5 to R packages")
8284 (description "This package uses the source code of zlib-1.2.5 to create
8285 libraries for systems that do not have these available via other means.")
8286 (license license:artistic2.0)))
8287
8288 (define-public r-r4rna
8289 (package
8290 (name "r-r4rna")
8291 (version "0.1.4")
8292 (source
8293 (origin
8294 (method url-fetch)
8295 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8296 version ".tar.gz"))
8297 (sha256
8298 (base32
8299 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8300 (build-system r-build-system)
8301 (propagated-inputs
8302 `(("r-optparse" ,r-optparse)
8303 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8304 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8305 (synopsis "Analysis framework for RNA secondary structure")
8306 (description
8307 "The R4RNA package aims to be a general framework for the analysis of RNA
8308 secondary structure and comparative analysis in R.")
8309 (license license:gpl3+)))
8310
8311 (define-public r-rhtslib
8312 (package
8313 (name "r-rhtslib")
8314 (version "1.10.0")
8315 (source
8316 (origin
8317 (method url-fetch)
8318 (uri (bioconductor-uri "Rhtslib" version))
8319 (sha256
8320 (base32
8321 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
8322 (properties `((upstream-name . "Rhtslib")))
8323 (build-system r-build-system)
8324 (propagated-inputs
8325 `(("r-zlibbioc" ,r-zlibbioc)))
8326 (inputs
8327 `(("zlib" ,zlib)))
8328 (native-inputs
8329 `(("autoconf" ,autoconf)))
8330 (home-page "https://github.com/nhayden/Rhtslib")
8331 (synopsis "High-throughput sequencing library as an R package")
8332 (description
8333 "This package provides the HTSlib C library for high-throughput
8334 nucleotide sequence analysis. The package is primarily useful to developers
8335 of other R packages who wish to make use of HTSlib.")
8336 (license license:lgpl2.0+)))
8337
8338 (define-public r-bamsignals
8339 (package
8340 (name "r-bamsignals")
8341 (version "1.10.0")
8342 (source
8343 (origin
8344 (method url-fetch)
8345 (uri (bioconductor-uri "bamsignals" version))
8346 (sha256
8347 (base32
8348 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
8349 (build-system r-build-system)
8350 (propagated-inputs
8351 `(("r-biocgenerics" ,r-biocgenerics)
8352 ("r-genomicranges" ,r-genomicranges)
8353 ("r-iranges" ,r-iranges)
8354 ("r-rcpp" ,r-rcpp)
8355 ("r-rhtslib" ,r-rhtslib)
8356 ("r-zlibbioc" ,r-zlibbioc)))
8357 (inputs
8358 `(("zlib" ,zlib)))
8359 (home-page "https://bioconductor.org/packages/bamsignals")
8360 (synopsis "Extract read count signals from bam files")
8361 (description
8362 "This package allows to efficiently obtain count vectors from indexed bam
8363 files. It counts the number of nucleotide sequence reads in given genomic
8364 ranges and it computes reads profiles and coverage profiles. It also handles
8365 paired-end data.")
8366 (license license:gpl2+)))
8367
8368 (define-public r-rcas
8369 (package
8370 (name "r-rcas")
8371 (version "1.3.4")
8372 (source (origin
8373 (method url-fetch)
8374 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8375 version ".tar.gz"))
8376 (file-name (string-append name "-" version ".tar.gz"))
8377 (sha256
8378 (base32
8379 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8380 (build-system r-build-system)
8381 (native-inputs
8382 `(("r-knitr" ,r-knitr)
8383 ("r-testthat" ,r-testthat)
8384 ;; During vignette building knitr checks that "pandoc-citeproc"
8385 ;; is in the PATH.
8386 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8387 (propagated-inputs
8388 `(("r-data-table" ,r-data-table)
8389 ("r-biomart" ,r-biomart)
8390 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8391 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8392 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8393 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8394 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8395 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8396 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8397 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8398 ("r-topgo" ,r-topgo)
8399 ("r-dt" ,r-dt)
8400 ("r-pbapply" ,r-pbapply)
8401 ("r-plotly" ,r-plotly)
8402 ("r-plotrix" ,r-plotrix)
8403 ("r-motifrg" ,r-motifrg)
8404 ("r-genomation" ,r-genomation)
8405 ("r-genomicfeatures" ,r-genomicfeatures)
8406 ("r-rtracklayer" ,r-rtracklayer)
8407 ("r-rmarkdown" ,r-rmarkdown)))
8408 (synopsis "RNA-centric annotation system")
8409 (description
8410 "RCAS aims to be a standalone RNA-centric annotation system that provides
8411 intuitive reports and publication-ready graphics. This package provides the R
8412 library implementing most of the pipeline's features.")
8413 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8414 (license license:artistic2.0)))
8415
8416 (define-public rcas-web
8417 (package
8418 (name "rcas-web")
8419 (version "0.0.4")
8420 (source
8421 (origin
8422 (method url-fetch)
8423 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8424 "releases/download/v" version
8425 "/rcas-web-" version ".tar.gz"))
8426 (sha256
8427 (base32
8428 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8429 (build-system gnu-build-system)
8430 (arguments
8431 `(#:phases
8432 (modify-phases %standard-phases
8433 (add-after 'install 'wrap-executable
8434 (lambda* (#:key inputs outputs #:allow-other-keys)
8435 (let* ((out (assoc-ref outputs "out"))
8436 (json (assoc-ref inputs "guile-json"))
8437 (redis (assoc-ref inputs "guile-redis"))
8438 (path (string-append
8439 json "/share/guile/site/2.2:"
8440 redis "/share/guile/site/2.2")))
8441 (wrap-program (string-append out "/bin/rcas-web")
8442 `("GUILE_LOAD_PATH" ":" = (,path))
8443 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8444 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8445 #t)))))
8446 (inputs
8447 `(("r-minimal" ,r-minimal)
8448 ("r-rcas" ,r-rcas)
8449 ("guile-next" ,guile-2.2)
8450 ("guile-json" ,guile-json)
8451 ("guile-redis" ,guile2.2-redis)))
8452 (native-inputs
8453 `(("pkg-config" ,pkg-config)))
8454 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8455 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8456 (description "This package provides a simple web interface for the
8457 @dfn{RNA-centric annotation system} (RCAS).")
8458 (license license:agpl3+)))
8459
8460 (define-public r-mutationalpatterns
8461 (package
8462 (name "r-mutationalpatterns")
8463 (version "1.4.2")
8464 (source
8465 (origin
8466 (method url-fetch)
8467 (uri (bioconductor-uri "MutationalPatterns" version))
8468 (sha256
8469 (base32
8470 "08ay9h5cqsi8ypb6r0g4rfa5l1g06jgfzl64wmhgz134yqbl7vfv"))))
8471 (build-system r-build-system)
8472 (propagated-inputs
8473 `(("r-biocgenerics" ,r-biocgenerics)
8474 ("r-biostrings" ,r-biostrings)
8475 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8476 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8477 ("r-genomicranges" ,r-genomicranges)
8478 ("r-genomeinfodb" ,r-genomeinfodb)
8479 ("r-ggplot2" ,r-ggplot2)
8480 ("r-gridextra" ,r-gridextra)
8481 ("r-iranges" ,r-iranges)
8482 ("r-nmf" ,r-nmf)
8483 ("r-plyr" ,r-plyr)
8484 ("r-pracma" ,r-pracma)
8485 ("r-reshape2" ,r-reshape2)
8486 ("r-cowplot" ,r-cowplot)
8487 ("r-ggdendro" ,r-ggdendro)
8488 ("r-s4vectors" ,r-s4vectors)
8489 ("r-summarizedexperiment" ,r-summarizedexperiment)
8490 ("r-variantannotation" ,r-variantannotation)))
8491 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8492 (synopsis "Extract and visualize mutational patterns in genomic data")
8493 (description "This package provides an extensive toolset for the
8494 characterization and visualization of a wide range of mutational patterns
8495 in SNV base substitution data.")
8496 (license license:expat)))
8497
8498 (define-public r-wgcna
8499 (package
8500 (name "r-wgcna")
8501 (version "1.63")
8502 (source
8503 (origin
8504 (method url-fetch)
8505 (uri (cran-uri "WGCNA" version))
8506 (sha256
8507 (base32
8508 "1225dqm68bynkmklnsxdqdd3zqrpzbvqwyly8ibxmk75z33xz309"))))
8509 (properties `((upstream-name . "WGCNA")))
8510 (build-system r-build-system)
8511 (propagated-inputs
8512 `(("r-annotationdbi" ,r-annotationdbi)
8513 ("r-doparallel" ,r-doparallel)
8514 ("r-dynamictreecut" ,r-dynamictreecut)
8515 ("r-fastcluster" ,r-fastcluster)
8516 ("r-foreach" ,r-foreach)
8517 ("r-go-db" ,r-go-db)
8518 ("r-hmisc" ,r-hmisc)
8519 ("r-impute" ,r-impute)
8520 ("r-rcpp" ,r-rcpp)
8521 ("r-robust" ,r-robust)
8522 ("r-survival" ,r-survival)
8523 ("r-matrixstats" ,r-matrixstats)
8524 ("r-preprocesscore" ,r-preprocesscore)))
8525 (home-page
8526 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8527 (synopsis "Weighted correlation network analysis")
8528 (description
8529 "This package provides functions necessary to perform Weighted
8530 Correlation Network Analysis on high-dimensional data. It includes functions
8531 for rudimentary data cleaning, construction and summarization of correlation
8532 networks, module identification and functions for relating both variables and
8533 modules to sample traits. It also includes a number of utility functions for
8534 data manipulation and visualization.")
8535 (license license:gpl2+)))
8536
8537 (define-public r-chipkernels
8538 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8539 (revision "1"))
8540 (package
8541 (name "r-chipkernels")
8542 (version (string-append "1.1-" revision "." (string-take commit 9)))
8543 (source
8544 (origin
8545 (method git-fetch)
8546 (uri (git-reference
8547 (url "https://github.com/ManuSetty/ChIPKernels.git")
8548 (commit commit)))
8549 (file-name (string-append name "-" version))
8550 (sha256
8551 (base32
8552 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8553 (build-system r-build-system)
8554 (propagated-inputs
8555 `(("r-iranges" ,r-iranges)
8556 ("r-xvector" ,r-xvector)
8557 ("r-biostrings" ,r-biostrings)
8558 ("r-bsgenome" ,r-bsgenome)
8559 ("r-gtools" ,r-gtools)
8560 ("r-genomicranges" ,r-genomicranges)
8561 ("r-sfsmisc" ,r-sfsmisc)
8562 ("r-kernlab" ,r-kernlab)
8563 ("r-s4vectors" ,r-s4vectors)
8564 ("r-biocgenerics" ,r-biocgenerics)))
8565 (home-page "https://github.com/ManuSetty/ChIPKernels")
8566 (synopsis "Build string kernels for DNA Sequence analysis")
8567 (description "ChIPKernels is an R package for building different string
8568 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8569 must be built and this dictionary can be used for determining kernels for DNA
8570 Sequences.")
8571 (license license:gpl2+))))
8572
8573 (define-public r-seqgl
8574 (package
8575 (name "r-seqgl")
8576 (version "1.1.4")
8577 (source
8578 (origin
8579 (method url-fetch)
8580 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8581 "archive/" version ".tar.gz"))
8582 (file-name (string-append name "-" version ".tar.gz"))
8583 (sha256
8584 (base32
8585 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8586 (build-system r-build-system)
8587 (propagated-inputs
8588 `(("r-biostrings" ,r-biostrings)
8589 ("r-chipkernels" ,r-chipkernels)
8590 ("r-genomicranges" ,r-genomicranges)
8591 ("r-spams" ,r-spams)
8592 ("r-wgcna" ,r-wgcna)
8593 ("r-fastcluster" ,r-fastcluster)))
8594 (home-page "https://github.com/ManuSetty/SeqGL")
8595 (synopsis "Group lasso for Dnase/ChIP-seq data")
8596 (description "SeqGL is a group lasso based algorithm to extract
8597 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8598 This package presents a method which uses group lasso to discriminate between
8599 bound and non bound genomic regions to accurately identify transcription
8600 factors bound at the specific regions.")
8601 (license license:gpl2+)))
8602
8603 (define-public r-gkmsvm
8604 (package
8605 (name "r-gkmsvm")
8606 (version "0.79.0")
8607 (source
8608 (origin
8609 (method url-fetch)
8610 (uri (cran-uri "gkmSVM" version))
8611 (sha256
8612 (base32
8613 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8614 (properties `((upstream-name . "gkmSVM")))
8615 (build-system r-build-system)
8616 (propagated-inputs
8617 `(("r-biocgenerics" ,r-biocgenerics)
8618 ("r-biostrings" ,r-biostrings)
8619 ("r-genomeinfodb" ,r-genomeinfodb)
8620 ("r-genomicranges" ,r-genomicranges)
8621 ("r-iranges" ,r-iranges)
8622 ("r-kernlab" ,r-kernlab)
8623 ("r-rcpp" ,r-rcpp)
8624 ("r-rocr" ,r-rocr)
8625 ("r-rtracklayer" ,r-rtracklayer)
8626 ("r-s4vectors" ,r-s4vectors)
8627 ("r-seqinr" ,r-seqinr)))
8628 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8629 (synopsis "Gapped-kmer support vector machine")
8630 (description
8631 "This R package provides tools for training gapped-kmer SVM classifiers
8632 for DNA and protein sequences. This package supports several sequence
8633 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8634 (license license:gpl2+)))
8635
8636 (define-public r-tximport
8637 (package
8638 (name "r-tximport")
8639 (version "1.6.0")
8640 (source (origin
8641 (method url-fetch)
8642 (uri (bioconductor-uri "tximport" version))
8643 (sha256
8644 (base32
8645 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8646 (build-system r-build-system)
8647 (home-page "https://bioconductor.org/packages/tximport")
8648 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8649 (description
8650 "This package provides tools to import transcript-level abundance,
8651 estimated counts and transcript lengths, and to summarize them into matrices
8652 for use with downstream gene-level analysis packages. Average transcript
8653 length, weighted by sample-specific transcript abundance estimates, is
8654 provided as a matrix which can be used as an offset for different expression
8655 of gene-level counts.")
8656 (license license:gpl2+)))
8657
8658 (define-public r-rhdf5
8659 (package
8660 (name "r-rhdf5")
8661 (version "2.22.0")
8662 (source (origin
8663 (method url-fetch)
8664 (uri (bioconductor-uri "rhdf5" version))
8665 (sha256
8666 (base32
8667 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8668 (build-system r-build-system)
8669 (arguments
8670 `(#:phases
8671 (modify-phases %standard-phases
8672 (add-after 'unpack 'unpack-smallhdf5
8673 (lambda* (#:key outputs #:allow-other-keys)
8674 (system* "tar" "-xzvf"
8675 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8676 (substitute* "src/hdf5/configure"
8677 (("/bin/mv") "mv"))
8678 #t)))))
8679 (propagated-inputs
8680 `(("r-zlibbioc" ,r-zlibbioc)))
8681 (inputs
8682 `(("perl" ,perl)
8683 ("zlib" ,zlib)))
8684 (home-page "https://bioconductor.org/packages/rhdf5")
8685 (synopsis "HDF5 interface to R")
8686 (description
8687 "This R/Bioconductor package provides an interface between HDF5 and R.
8688 HDF5's main features are the ability to store and access very large and/or
8689 complex datasets and a wide variety of metadata on mass storage (disk) through
8690 a completely portable file format. The rhdf5 package is thus suited for the
8691 exchange of large and/or complex datasets between R and other software
8692 package, and for letting R applications work on datasets that are larger than
8693 the available RAM.")
8694 (license license:artistic2.0)))
8695
8696 (define-public r-annotationfilter
8697 (package
8698 (name "r-annotationfilter")
8699 (version "1.2.0")
8700 (source (origin
8701 (method url-fetch)
8702 (uri (bioconductor-uri "AnnotationFilter" version))
8703 (sha256
8704 (base32
8705 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8706 (properties
8707 `((upstream-name . "AnnotationFilter")))
8708 (build-system r-build-system)
8709 (propagated-inputs
8710 `(("r-genomicranges" ,r-genomicranges)
8711 ("r-lazyeval" ,r-lazyeval)))
8712 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8713 (synopsis "Facilities for filtering Bioconductor annotation resources")
8714 (description
8715 "This package provides classes and other infrastructure to implement
8716 filters for manipulating Bioconductor annotation resources. The filters are
8717 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8718 (license license:artistic2.0)))
8719
8720 (define-public emboss
8721 (package
8722 (name "emboss")
8723 (version "6.5.7")
8724 (source (origin
8725 (method url-fetch)
8726 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8727 (version-major+minor version) ".0/"
8728 "EMBOSS-" version ".tar.gz"))
8729 (sha256
8730 (base32
8731 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8732 (build-system gnu-build-system)
8733 (arguments
8734 `(#:configure-flags
8735 (list (string-append "--with-hpdf="
8736 (assoc-ref %build-inputs "libharu")))
8737 #:phases
8738 (modify-phases %standard-phases
8739 (add-after 'unpack 'fix-checks
8740 (lambda _
8741 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8742 ;; and zlib, but assume that they are all found at the same
8743 ;; prefix.
8744 (substitute* "configure.in"
8745 (("CHECK_PNGDRIVER")
8746 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8747 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8748 AM_CONDITIONAL(AMPNG, true)"))
8749 #t))
8750 (add-after 'fix-checks 'disable-update-check
8751 (lambda _
8752 ;; At build time there is no connection to the Internet, so
8753 ;; looking for updates will not work.
8754 (substitute* "Makefile.am"
8755 (("\\$\\(bindir\\)/embossupdate") ""))
8756 #t))
8757 (add-after 'disable-update-check 'autogen
8758 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8759 (inputs
8760 `(("perl" ,perl)
8761 ("libpng" ,libpng)
8762 ("gd" ,gd)
8763 ("libx11" ,libx11)
8764 ("libharu" ,libharu)
8765 ("zlib" ,zlib)))
8766 (native-inputs
8767 `(("autoconf" ,autoconf)
8768 ("automake" ,automake)
8769 ("libtool" ,libtool)
8770 ("pkg-config" ,pkg-config)))
8771 (home-page "http://emboss.sourceforge.net")
8772 (synopsis "Molecular biology analysis suite")
8773 (description "EMBOSS is the \"European Molecular Biology Open Software
8774 Suite\". EMBOSS is an analysis package specially developed for the needs of
8775 the molecular biology (e.g. EMBnet) user community. The software
8776 automatically copes with data in a variety of formats and even allows
8777 transparent retrieval of sequence data from the web. It also provides a
8778 number of libraries for the development of software in the field of molecular
8779 biology. EMBOSS also integrates a range of currently available packages and
8780 tools for sequence analysis into a seamless whole.")
8781 (license license:gpl2+)))
8782
8783 (define-public bits
8784 (let ((revision "1")
8785 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8786 (package
8787 (name "bits")
8788 ;; The version is 2.13.0 even though no release archives have been
8789 ;; published as yet.
8790 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8791 (source (origin
8792 (method git-fetch)
8793 (uri (git-reference
8794 (url "https://github.com/arq5x/bits.git")
8795 (commit commit)))
8796 (file-name (string-append name "-" version "-checkout"))
8797 (sha256
8798 (base32
8799 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8800 (build-system gnu-build-system)
8801 (arguments
8802 `(#:tests? #f ;no tests included
8803 #:phases
8804 (modify-phases %standard-phases
8805 (delete 'configure)
8806 (add-after 'unpack 'remove-cuda
8807 (lambda _
8808 (substitute* "Makefile"
8809 ((".*_cuda") "")
8810 (("(bits_test_intersections) \\\\" _ match) match))
8811 #t))
8812 (replace 'install
8813 (lambda* (#:key outputs #:allow-other-keys)
8814 (copy-recursively
8815 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8816 #t)))))
8817 (inputs
8818 `(("gsl" ,gsl)
8819 ("zlib" ,zlib)))
8820 (home-page "https://github.com/arq5x/bits")
8821 (synopsis "Implementation of binary interval search algorithm")
8822 (description "This package provides an implementation of the
8823 BITS (Binary Interval Search) algorithm, an approach to interval set
8824 intersection. It is especially suited for the comparison of diverse genomic
8825 datasets and the exploration of large datasets of genome
8826 intervals (e.g. genes, sequence alignments).")
8827 (license license:gpl2))))
8828
8829 (define-public piranha
8830 ;; There is no release tarball for the latest version. The latest commit is
8831 ;; older than one year at the time of this writing.
8832 (let ((revision "1")
8833 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8834 (package
8835 (name "piranha")
8836 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8837 (source (origin
8838 (method git-fetch)
8839 (uri (git-reference
8840 (url "https://github.com/smithlabcode/piranha.git")
8841 (commit commit)))
8842 (sha256
8843 (base32
8844 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8845 (build-system gnu-build-system)
8846 (arguments
8847 `(#:test-target "test"
8848 #:phases
8849 (modify-phases %standard-phases
8850 (add-after 'unpack 'copy-smithlab-cpp
8851 (lambda* (#:key inputs #:allow-other-keys)
8852 (for-each (lambda (file)
8853 (install-file file "./src/smithlab_cpp/"))
8854 (find-files (assoc-ref inputs "smithlab-cpp")))
8855 #t))
8856 (add-after 'install 'install-to-store
8857 (lambda* (#:key outputs #:allow-other-keys)
8858 (let* ((out (assoc-ref outputs "out"))
8859 (bin (string-append out "/bin")))
8860 (for-each (lambda (file)
8861 (install-file file bin))
8862 (find-files "bin" ".*")))
8863 #t)))
8864 #:configure-flags
8865 (list (string-append "--with-bam_tools_headers="
8866 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8867 (string-append "--with-bam_tools_library="
8868 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8869 (inputs
8870 `(("bamtools" ,bamtools)
8871 ("samtools" ,samtools-0.1)
8872 ("gsl" ,gsl)
8873 ("smithlab-cpp"
8874 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8875 (origin
8876 (method git-fetch)
8877 (uri (git-reference
8878 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8879 (commit commit)))
8880 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8881 (sha256
8882 (base32
8883 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8884 (native-inputs
8885 `(("python" ,python-2)))
8886 (home-page "https://github.com/smithlabcode/piranha")
8887 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8888 (description
8889 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8890 RIP-seq experiments. It takes input in BED or BAM format and identifies
8891 regions of statistically significant read enrichment. Additional covariates
8892 may optionally be provided to further inform the peak-calling process.")
8893 (license license:gpl3+))))
8894
8895 (define-public pepr
8896 (package
8897 (name "pepr")
8898 (version "1.0.9")
8899 (source (origin
8900 (method url-fetch)
8901 (uri (string-append "https://pypi.python.org/packages/source/P"
8902 "/PePr/PePr-" version ".tar.gz"))
8903 (sha256
8904 (base32
8905 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8906 (build-system python-build-system)
8907 (arguments
8908 `(#:python ,python-2 ; python2 only
8909 #:tests? #f)) ; no tests included
8910 (propagated-inputs
8911 `(("python2-numpy" ,python2-numpy)
8912 ("python2-scipy" ,python2-scipy)
8913 ("python2-pysam" ,python2-pysam)))
8914 (home-page "https://github.com/shawnzhangyx/PePr")
8915 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8916 (description
8917 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8918 that is primarily designed for data with biological replicates. It uses a
8919 negative binomial distribution to model the read counts among the samples in
8920 the same group, and look for consistent differences between ChIP and control
8921 group or two ChIP groups run under different conditions.")
8922 (license license:gpl3+)))
8923
8924 (define-public filevercmp
8925 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8926 (package
8927 (name "filevercmp")
8928 (version (string-append "0-1." (string-take commit 7)))
8929 (source (origin
8930 (method url-fetch)
8931 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8932 commit ".tar.gz"))
8933 (file-name (string-append name "-" version ".tar.gz"))
8934 (sha256
8935 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8936 (build-system gnu-build-system)
8937 (arguments
8938 `(#:tests? #f ; There are no tests to run.
8939 #:phases
8940 (modify-phases %standard-phases
8941 (delete 'configure) ; There is no configure phase.
8942 (replace 'install
8943 (lambda* (#:key outputs #:allow-other-keys)
8944 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8945 (install-file "filevercmp" bin)))))))
8946 (home-page "https://github.com/ekg/filevercmp")
8947 (synopsis "This program compares version strings")
8948 (description "This program compares version strings. It intends to be a
8949 replacement for strverscmp.")
8950 (license license:gpl3+))))
8951
8952 (define-public multiqc
8953 (package
8954 (name "multiqc")
8955 (version "1.4")
8956 (source
8957 (origin
8958 (method url-fetch)
8959 (uri (pypi-uri "multiqc" version))
8960 (sha256
8961 (base32
8962 "0ihx4rzmsfphv4byn05qv6f1y95g2dxs6viwziipl4wjk96acgm8"))))
8963 (build-system python-build-system)
8964 (propagated-inputs
8965 `(("python-jinja2" ,python-jinja2)
8966 ("python-simplejson" ,python-simplejson)
8967 ("python-pyyaml" ,python-pyyaml)
8968 ("python-click" ,python-click)
8969 ("python-spectra" ,python-spectra)
8970 ("python-requests" ,python-requests)
8971 ("python-markdown" ,python-markdown)
8972 ("python-lzstring" ,python-lzstring)
8973 ("python-matplotlib" ,python-matplotlib)
8974 ("python-numpy" ,python-numpy)
8975 ;; MultQC checks for the presence of nose at runtime.
8976 ("python-nose" ,python-nose)))
8977 (home-page "http://multiqc.info")
8978 (synopsis "Aggregate bioinformatics analysis reports")
8979 (description
8980 "MultiQC is a tool to aggregate bioinformatics results across many
8981 samples into a single report. It contains modules for a large number of
8982 common bioinformatics tools.")
8983 (license license:gpl3+)))
8984
8985 (define-public r-chipseq
8986 (package
8987 (name "r-chipseq")
8988 (version "1.28.0")
8989 (source
8990 (origin
8991 (method url-fetch)
8992 (uri (bioconductor-uri "chipseq" version))
8993 (sha256
8994 (base32
8995 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
8996 (build-system r-build-system)
8997 (propagated-inputs
8998 `(("r-biocgenerics" ,r-biocgenerics)
8999 ("r-genomicranges" ,r-genomicranges)
9000 ("r-iranges" ,r-iranges)
9001 ("r-lattice" ,r-lattice)
9002 ("r-s4vectors" ,r-s4vectors)
9003 ("r-shortread" ,r-shortread)))
9004 (home-page "https://bioconductor.org/packages/chipseq")
9005 (synopsis "Package for analyzing ChIPseq data")
9006 (description
9007 "This package provides tools for processing short read data from ChIPseq
9008 experiments.")
9009 (license license:artistic2.0)))
9010
9011 (define-public r-copyhelper
9012 (package
9013 (name "r-copyhelper")
9014 (version "1.6.0")
9015 (source
9016 (origin
9017 (method url-fetch)
9018 (uri (string-append "https://bioconductor.org/packages/release/"
9019 "data/experiment/src/contrib/CopyhelpeR_"
9020 version ".tar.gz"))
9021 (sha256
9022 (base32
9023 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9024 (properties `((upstream-name . "CopyhelpeR")))
9025 (build-system r-build-system)
9026 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9027 (synopsis "Helper files for CopywriteR")
9028 (description
9029 "This package contains the helper files that are required to run the
9030 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9031 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9032 mm10. In addition, it contains a blacklist filter to remove regions that
9033 display copy number variation. Files are stored as GRanges objects from the
9034 GenomicRanges Bioconductor package.")
9035 (license license:gpl2)))
9036
9037 (define-public r-copywriter
9038 (package
9039 (name "r-copywriter")
9040 (version "2.10.0")
9041 (source
9042 (origin
9043 (method url-fetch)
9044 (uri (bioconductor-uri "CopywriteR" version))
9045 (sha256
9046 (base32
9047 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
9048 (properties `((upstream-name . "CopywriteR")))
9049 (build-system r-build-system)
9050 (propagated-inputs
9051 `(("r-biocparallel" ,r-biocparallel)
9052 ("r-chipseq" ,r-chipseq)
9053 ("r-copyhelper" ,r-copyhelper)
9054 ("r-data-table" ,r-data-table)
9055 ("r-dnacopy" ,r-dnacopy)
9056 ("r-futile-logger" ,r-futile-logger)
9057 ("r-genomeinfodb" ,r-genomeinfodb)
9058 ("r-genomicalignments" ,r-genomicalignments)
9059 ("r-genomicranges" ,r-genomicranges)
9060 ("r-gtools" ,r-gtools)
9061 ("r-iranges" ,r-iranges)
9062 ("r-matrixstats" ,r-matrixstats)
9063 ("r-rsamtools" ,r-rsamtools)
9064 ("r-s4vectors" ,r-s4vectors)))
9065 (home-page "https://github.com/PeeperLab/CopywriteR")
9066 (synopsis "Copy number information from targeted sequencing")
9067 (description
9068 "CopywriteR extracts DNA copy number information from targeted sequencing
9069 by utilizing off-target reads. It allows for extracting uniformly distributed
9070 copy number information, can be used without reference, and can be applied to
9071 sequencing data obtained from various techniques including chromatin
9072 immunoprecipitation and target enrichment on small gene panels. Thereby,
9073 CopywriteR constitutes a widely applicable alternative to available copy
9074 number detection tools.")
9075 (license license:gpl2)))
9076
9077 (define-public r-methylkit
9078 (package
9079 (name "r-methylkit")
9080 (version "1.4.1")
9081 (source (origin
9082 (method url-fetch)
9083 (uri (bioconductor-uri "methylKit" version))
9084 (sha256
9085 (base32
9086 "1k0nfn9318sgwm4z963bhnbp4c3zv85v3f9886vc5hgaisr0yvai"))))
9087 (properties `((upstream-name . "methylKit")))
9088 (build-system r-build-system)
9089 (propagated-inputs
9090 `(("r-data-table" ,r-data-table)
9091 ("r-emdbook" ,r-emdbook)
9092 ("r-fastseg" ,r-fastseg)
9093 ("r-genomeinfodb" ,r-genomeinfodb)
9094 ("r-genomicranges" ,r-genomicranges)
9095 ("r-gtools" ,r-gtools)
9096 ("r-iranges" ,r-iranges)
9097 ("r-kernsmooth" ,r-kernsmooth)
9098 ("r-limma" ,r-limma)
9099 ("r-mclust" ,r-mclust)
9100 ("r-qvalue" ,r-qvalue)
9101 ("r-r-utils" ,r-r-utils)
9102 ("r-rcpp" ,r-rcpp)
9103 ("r-rhtslib" ,r-rhtslib)
9104 ("r-rsamtools" ,r-rsamtools)
9105 ("r-rtracklayer" ,r-rtracklayer)
9106 ("r-s4vectors" ,r-s4vectors)
9107 ("r-zlibbioc" ,r-zlibbioc)))
9108 (inputs
9109 `(("zlib" ,zlib)))
9110 (home-page "https://github.com/al2na/methylKit")
9111 (synopsis
9112 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9113 (description
9114 "MethylKit is an R package for DNA methylation analysis and annotation
9115 from high-throughput bisulfite sequencing. The package is designed to deal
9116 with sequencing data from @dfn{Reduced representation bisulfite
9117 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9118 genome bisulfite sequencing. It also has functions to analyze base-pair
9119 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9120 TAB-Seq.")
9121 (license license:artistic2.0)))
9122
9123 (define-public r-sva
9124 (package
9125 (name "r-sva")
9126 (version "3.26.0")
9127 (source
9128 (origin
9129 (method url-fetch)
9130 (uri (bioconductor-uri "sva" version))
9131 (sha256
9132 (base32
9133 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
9134 (build-system r-build-system)
9135 (propagated-inputs
9136 `(("r-genefilter" ,r-genefilter)
9137 ("r-mgcv" ,r-mgcv)
9138 ("r-biocparallel" ,r-biocparallel)
9139 ("r-matrixstats" ,r-matrixstats)
9140 ("r-limma" ,r-limma)))
9141 (home-page "https://bioconductor.org/packages/sva")
9142 (synopsis "Surrogate variable analysis")
9143 (description
9144 "This package contains functions for removing batch effects and other
9145 unwanted variation in high-throughput experiment. It also contains functions
9146 for identifying and building surrogate variables for high-dimensional data
9147 sets. Surrogate variables are covariates constructed directly from
9148 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9149 imaging data that can be used in subsequent analyses to adjust for unknown,
9150 unmodeled, or latent sources of noise.")
9151 (license license:artistic2.0)))
9152
9153 (define-public r-seqminer
9154 (package
9155 (name "r-seqminer")
9156 (version "6.0")
9157 (source
9158 (origin
9159 (method url-fetch)
9160 (uri (cran-uri "seqminer" version))
9161 (sha256
9162 (base32
9163 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
9164 (build-system r-build-system)
9165 (inputs
9166 `(("zlib" ,zlib)))
9167 (home-page "http://seqminer.genomic.codes")
9168 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9169 (description
9170 "This package provides tools to integrate nucleotide sequencing
9171 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9172 ;; Any version of the GPL is acceptable
9173 (license (list license:gpl2+ license:gpl3+))))
9174
9175 (define-public r-raremetals2
9176 (package
9177 (name "r-raremetals2")
9178 (version "0.1")
9179 (source
9180 (origin
9181 (method url-fetch)
9182 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9183 "b/b7/RareMETALS2_" version ".tar.gz"))
9184 (sha256
9185 (base32
9186 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9187 (properties `((upstream-name . "RareMETALS2")))
9188 (build-system r-build-system)
9189 (propagated-inputs
9190 `(("r-seqminer" ,r-seqminer)
9191 ("r-mvtnorm" ,r-mvtnorm)
9192 ("r-mass" ,r-mass)
9193 ("r-compquadform" ,r-compquadform)
9194 ("r-getopt" ,r-getopt)))
9195 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9196 (synopsis "Analyze gene-level association tests for binary trait")
9197 (description
9198 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9199 It was designed to meta-analyze gene-level association tests for binary trait.
9200 While rareMETALS offers a near-complete solution for meta-analysis of
9201 gene-level tests for quantitative trait, it does not offer the optimal
9202 solution for binary trait. The package rareMETALS2 offers improved features
9203 for analyzing gene-level association tests in meta-analyses for binary
9204 trait.")
9205 (license license:gpl3)))
9206
9207 (define-public r-maldiquant
9208 (package
9209 (name "r-maldiquant")
9210 (version "1.17")
9211 (source
9212 (origin
9213 (method url-fetch)
9214 (uri (cran-uri "MALDIquant" version))
9215 (sha256
9216 (base32
9217 "047s6007ydc38x8wm027mlb4mngz15n0d4238fr8h43wyll5zy0z"))))
9218 (properties `((upstream-name . "MALDIquant")))
9219 (build-system r-build-system)
9220 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9221 (synopsis "Quantitative analysis of mass spectrometry data")
9222 (description
9223 "This package provides a complete analysis pipeline for matrix-assisted
9224 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9225 two-dimensional mass spectrometry data. In addition to commonly used plotting
9226 and processing methods it includes distinctive features, namely baseline
9227 subtraction methods such as morphological filters (TopHat) or the
9228 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9229 alignment using warping functions, handling of replicated measurements as well
9230 as allowing spectra with different resolutions.")
9231 (license license:gpl3+)))
9232
9233 (define-public r-protgenerics
9234 (package
9235 (name "r-protgenerics")
9236 (version "1.10.0")
9237 (source
9238 (origin
9239 (method url-fetch)
9240 (uri (bioconductor-uri "ProtGenerics" version))
9241 (sha256
9242 (base32
9243 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
9244 (properties `((upstream-name . "ProtGenerics")))
9245 (build-system r-build-system)
9246 (home-page "https://github.com/lgatto/ProtGenerics")
9247 (synopsis "S4 generic functions for proteomics infrastructure")
9248 (description
9249 "This package provides S4 generic functions needed by Bioconductor
9250 proteomics packages.")
9251 (license license:artistic2.0)))
9252
9253 (define-public r-mzr
9254 (package
9255 (name "r-mzr")
9256 (version "2.12.0")
9257 (source
9258 (origin
9259 (method url-fetch)
9260 (uri (bioconductor-uri "mzR" version))
9261 (sha256
9262 (base32
9263 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
9264 (modules '((guix build utils)))
9265 (snippet
9266 '(begin
9267 (delete-file-recursively "src/boost")
9268 #t))))
9269 (properties `((upstream-name . "mzR")))
9270 (build-system r-build-system)
9271 (arguments
9272 `(#:phases
9273 (modify-phases %standard-phases
9274 (add-after 'unpack 'use-system-boost
9275 (lambda _
9276 (substitute* "src/Makevars"
9277 (("\\./boost/libs.*") "")
9278 (("ARCH_OBJS=" line)
9279 (string-append line
9280 "\nARCH_LIBS=-lboost_system -lboost_regex \
9281 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9282 #t)))))
9283 (inputs
9284 `(("boost" ,boost) ; use this instead of the bundled boost sources
9285 ("netcdf" ,netcdf)))
9286 (propagated-inputs
9287 `(("r-biobase" ,r-biobase)
9288 ("r-biocgenerics" ,r-biocgenerics)
9289 ("r-protgenerics" ,r-protgenerics)
9290 ("r-rcpp" ,r-rcpp)
9291 ("r-zlibbioc" ,r-zlibbioc)))
9292 (home-page "https://github.com/sneumann/mzR/")
9293 (synopsis "Parser for mass spectrometry data files")
9294 (description
9295 "The mzR package provides a unified API to the common file formats and
9296 parsers available for mass spectrometry data. It comes with a wrapper for the
9297 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9298 The package contains the original code written by the ISB, and a subset of the
9299 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9300 previously been used in XCMS.")
9301 (license license:artistic2.0)))
9302
9303 (define-public r-affyio
9304 (package
9305 (name "r-affyio")
9306 (version "1.48.0")
9307 (source
9308 (origin
9309 (method url-fetch)
9310 (uri (bioconductor-uri "affyio" version))
9311 (sha256
9312 (base32
9313 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
9314 (build-system r-build-system)
9315 (propagated-inputs
9316 `(("r-zlibbioc" ,r-zlibbioc)))
9317 (inputs
9318 `(("zlib" ,zlib)))
9319 (home-page "https://github.com/bmbolstad/affyio")
9320 (synopsis "Tools for parsing Affymetrix data files")
9321 (description
9322 "This package provides routines for parsing Affymetrix data files based
9323 upon file format information. The primary focus is on accessing the CEL and
9324 CDF file formats.")
9325 (license license:lgpl2.0+)))
9326
9327 (define-public r-affy
9328 (package
9329 (name "r-affy")
9330 (version "1.56.0")
9331 (source
9332 (origin
9333 (method url-fetch)
9334 (uri (bioconductor-uri "affy" version))
9335 (sha256
9336 (base32
9337 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
9338 (build-system r-build-system)
9339 (propagated-inputs
9340 `(("r-affyio" ,r-affyio)
9341 ("r-biobase" ,r-biobase)
9342 ("r-biocgenerics" ,r-biocgenerics)
9343 ("r-biocinstaller" ,r-biocinstaller)
9344 ("r-preprocesscore" ,r-preprocesscore)
9345 ("r-zlibbioc" ,r-zlibbioc)))
9346 (home-page "https://bioconductor.org/packages/affy")
9347 (synopsis "Methods for affymetrix oligonucleotide arrays")
9348 (description
9349 "This package contains functions for exploratory oligonucleotide array
9350 analysis.")
9351 (license license:lgpl2.0+)))
9352
9353 (define-public r-vsn
9354 (package
9355 (name "r-vsn")
9356 (version "3.46.0")
9357 (source
9358 (origin
9359 (method url-fetch)
9360 (uri (bioconductor-uri "vsn" version))
9361 (sha256
9362 (base32
9363 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9364 (build-system r-build-system)
9365 (propagated-inputs
9366 `(("r-affy" ,r-affy)
9367 ("r-biobase" ,r-biobase)
9368 ("r-ggplot2" ,r-ggplot2)
9369 ("r-lattice" ,r-lattice)
9370 ("r-limma" ,r-limma)))
9371 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9372 (synopsis "Variance stabilization and calibration for microarray data")
9373 (description
9374 "The package implements a method for normalising microarray intensities,
9375 and works for single- and multiple-color arrays. It can also be used for data
9376 from other technologies, as long as they have similar format. The method uses
9377 a robust variant of the maximum-likelihood estimator for an
9378 additive-multiplicative error model and affine calibration. The model
9379 incorporates data calibration step (a.k.a. normalization), a model for the
9380 dependence of the variance on the mean intensity and a variance stabilizing
9381 data transformation. Differences between transformed intensities are
9382 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9383 their variance is independent of the mean, and they are usually more sensitive
9384 and specific in detecting differential transcription.")
9385 (license license:artistic2.0)))
9386
9387 (define-public r-mzid
9388 (package
9389 (name "r-mzid")
9390 (version "1.16.0")
9391 (source
9392 (origin
9393 (method url-fetch)
9394 (uri (bioconductor-uri "mzID" version))
9395 (sha256
9396 (base32
9397 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9398 (properties `((upstream-name . "mzID")))
9399 (build-system r-build-system)
9400 (propagated-inputs
9401 `(("r-doparallel" ,r-doparallel)
9402 ("r-foreach" ,r-foreach)
9403 ("r-iterators" ,r-iterators)
9404 ("r-plyr" ,r-plyr)
9405 ("r-protgenerics" ,r-protgenerics)
9406 ("r-rcpp" ,r-rcpp)
9407 ("r-xml" ,r-xml)))
9408 (home-page "https://bioconductor.org/packages/mzID")
9409 (synopsis "Parser for mzIdentML files")
9410 (description
9411 "This package provides a parser for mzIdentML files implemented using the
9412 XML package. The parser tries to be general and able to handle all types of
9413 mzIdentML files with the drawback of having less pretty output than a vendor
9414 specific parser.")
9415 (license license:gpl2+)))
9416
9417 (define-public r-pcamethods
9418 (package
9419 (name "r-pcamethods")
9420 (version "1.70.0")
9421 (source
9422 (origin
9423 (method url-fetch)
9424 (uri (bioconductor-uri "pcaMethods" version))
9425 (sha256
9426 (base32
9427 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9428 (properties `((upstream-name . "pcaMethods")))
9429 (build-system r-build-system)
9430 (propagated-inputs
9431 `(("r-biobase" ,r-biobase)
9432 ("r-biocgenerics" ,r-biocgenerics)
9433 ("r-mass" ,r-mass)
9434 ("r-rcpp" ,r-rcpp)))
9435 (home-page "https://github.com/hredestig/pcamethods")
9436 (synopsis "Collection of PCA methods")
9437 (description
9438 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9439 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9440 for missing value estimation is included for comparison. BPCA, PPCA and
9441 NipalsPCA may be used to perform PCA on incomplete data as well as for
9442 accurate missing value estimation. A set of methods for printing and plotting
9443 the results is also provided. All PCA methods make use of the same data
9444 structure (pcaRes) to provide a common interface to the PCA results.")
9445 (license license:gpl3+)))
9446
9447 (define-public r-msnbase
9448 (package
9449 (name "r-msnbase")
9450 (version "2.4.2")
9451 (source
9452 (origin
9453 (method url-fetch)
9454 (uri (bioconductor-uri "MSnbase" version))
9455 (sha256
9456 (base32
9457 "1ig64bf881p118dwqfr0ry41m7yhnyv165smv8fdwfv7sb6sagif"))))
9458 (properties `((upstream-name . "MSnbase")))
9459 (build-system r-build-system)
9460 (propagated-inputs
9461 `(("r-affy" ,r-affy)
9462 ("r-biobase" ,r-biobase)
9463 ("r-biocgenerics" ,r-biocgenerics)
9464 ("r-biocparallel" ,r-biocparallel)
9465 ("r-digest" ,r-digest)
9466 ("r-ggplot2" ,r-ggplot2)
9467 ("r-impute" ,r-impute)
9468 ("r-iranges" ,r-iranges)
9469 ("r-lattice" ,r-lattice)
9470 ("r-maldiquant" ,r-maldiquant)
9471 ("r-mzid" ,r-mzid)
9472 ("r-mzr" ,r-mzr)
9473 ("r-pcamethods" ,r-pcamethods)
9474 ("r-plyr" ,r-plyr)
9475 ("r-preprocesscore" ,r-preprocesscore)
9476 ("r-protgenerics" ,r-protgenerics)
9477 ("r-rcpp" ,r-rcpp)
9478 ("r-s4vectors" ,r-s4vectors)
9479 ("r-vsn" ,r-vsn)
9480 ("r-xml" ,r-xml)))
9481 (home-page "https://github.com/lgatto/MSnbase")
9482 (synopsis "Base functions and classes for MS-based proteomics")
9483 (description
9484 "This package provides basic plotting, data manipulation and processing
9485 of mass spectrometry based proteomics data.")
9486 (license license:artistic2.0)))
9487
9488 (define-public r-msnid
9489 (package
9490 (name "r-msnid")
9491 (version "1.12.1")
9492 (source
9493 (origin
9494 (method url-fetch)
9495 (uri (bioconductor-uri "MSnID" version))
9496 (sha256
9497 (base32
9498 "1zw508kk4f8brg69674wp18gqkpx2kpya5f6x9cl3qng7v4h5pxx"))))
9499 (properties `((upstream-name . "MSnID")))
9500 (build-system r-build-system)
9501 (propagated-inputs
9502 `(("r-biobase" ,r-biobase)
9503 ("r-data-table" ,r-data-table)
9504 ("r-doparallel" ,r-doparallel)
9505 ("r-dplyr" ,r-dplyr)
9506 ("r-foreach" ,r-foreach)
9507 ("r-iterators" ,r-iterators)
9508 ("r-msnbase" ,r-msnbase)
9509 ("r-mzid" ,r-mzid)
9510 ("r-mzr" ,r-mzr)
9511 ("r-protgenerics" ,r-protgenerics)
9512 ("r-r-cache" ,r-r-cache)
9513 ("r-rcpp" ,r-rcpp)
9514 ("r-reshape2" ,r-reshape2)))
9515 (home-page "https://bioconductor.org/packages/MSnID")
9516 (synopsis "Utilities for LC-MSn proteomics identifications")
9517 (description
9518 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9519 from mzIdentML (leveraging the mzID package) or text files. After collating
9520 the search results from multiple datasets it assesses their identification
9521 quality and optimize filtering criteria to achieve the maximum number of
9522 identifications while not exceeding a specified false discovery rate. It also
9523 contains a number of utilities to explore the MS/MS results and assess missed
9524 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9525 (license license:artistic2.0)))
9526
9527 (define-public r-seurat
9528 (package
9529 (name "r-seurat")
9530 (version "2.2.1")
9531 (source (origin
9532 (method url-fetch)
9533 (uri (cran-uri "Seurat" version))
9534 (sha256
9535 (base32
9536 "1sr82nf38hq07avrfn8vlrzjq7dfm4pcr8l1nh6mnglcql2bk9z2"))
9537 ;; Delete pre-built jar.
9538 (snippet
9539 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9540 #t))))
9541 (properties `((upstream-name . "Seurat")))
9542 (build-system r-build-system)
9543 (arguments
9544 `(#:phases
9545 (modify-phases %standard-phases
9546 (add-after 'unpack 'build-jar
9547 (lambda* (#:key inputs #:allow-other-keys)
9548 (let ((classesdir "tmp-classes"))
9549 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9550 (mkdir classesdir)
9551 (with-output-to-file "manifest"
9552 (lambda _
9553 (display "Manifest-Version: 1.0
9554 Main-Class: ModularityOptimizer\n")))
9555 (and (zero? (apply system* `("javac" "-d" ,classesdir
9556 ,@(find-files "java" "\\.java$"))))
9557 (zero? (system* "jar"
9558 "-cmf" "manifest"
9559 "inst/java/ModularityOptimizer.jar"
9560 "-C" classesdir ".")))))))))
9561 (native-inputs
9562 `(("jdk" ,icedtea "jdk")))
9563 (propagated-inputs
9564 `(("r-ape" ,r-ape)
9565 ("r-caret" ,r-caret)
9566 ("r-cowplot" ,r-cowplot)
9567 ("r-diffusionmap" ,r-diffusionmap)
9568 ("r-dplyr" ,r-dplyr)
9569 ("r-dtw" ,r-dtw)
9570 ("r-fnn" ,r-fnn)
9571 ("r-fpc" ,r-fpc)
9572 ("r-gdata" ,r-gdata)
9573 ("r-ggplot2" ,r-ggplot2)
9574 ("r-ggridges" ,r-ggridges)
9575 ("r-gplots" ,r-gplots)
9576 ("r-gridextra" ,r-gridextra)
9577 ("r-hmisc" ,r-hmisc)
9578 ("r-ica" ,r-ica)
9579 ("r-igraph" ,r-igraph)
9580 ("r-irlba" ,r-irlba)
9581 ("r-lars" ,r-lars)
9582 ("r-mass" ,r-mass)
9583 ("r-matrix" ,r-matrix)
9584 ("r-metap" ,r-metap)
9585 ("r-mixtools" ,r-mixtools)
9586 ("r-pbapply" ,r-pbapply)
9587 ("r-plotly" ,r-plotly)
9588 ("r-ranger" ,r-ranger)
9589 ("r-rcolorbrewer" ,r-rcolorbrewer)
9590 ("r-rcpp" ,r-rcpp)
9591 ("r-rcppeigen" ,r-rcppeigen)
9592 ("r-rcppprogress" ,r-rcppprogress)
9593 ("r-reshape2" ,r-reshape2)
9594 ("r-rocr" ,r-rocr)
9595 ("r-rtsne" ,r-rtsne)
9596 ("r-sdmtools" ,r-sdmtools)
9597 ("r-stringr" ,r-stringr)
9598 ("r-tclust" ,r-tclust)
9599 ("r-tidyr" ,r-tidyr)
9600 ("r-tsne" ,r-tsne)
9601 ("r-vgam" ,r-vgam)))
9602 (home-page "http://www.satijalab.org/seurat")
9603 (synopsis "Seurat is an R toolkit for single cell genomics")
9604 (description
9605 "This package is an R package designed for QC, analysis, and
9606 exploration of single cell RNA-seq data. It easily enables widely-used
9607 analytical techniques, including the identification of highly variable genes,
9608 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9609 algorithms; density clustering, hierarchical clustering, k-means, and the
9610 discovery of differentially expressed genes and markers.")
9611 (license license:gpl3)))
9612
9613 (define-public r-aroma-light
9614 (package
9615 (name "r-aroma-light")
9616 (version "3.8.0")
9617 (source
9618 (origin
9619 (method url-fetch)
9620 (uri (bioconductor-uri "aroma.light" version))
9621 (sha256
9622 (base32
9623 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9624 (properties `((upstream-name . "aroma.light")))
9625 (build-system r-build-system)
9626 (propagated-inputs
9627 `(("r-matrixstats" ,r-matrixstats)
9628 ("r-r-methodss3" ,r-r-methodss3)
9629 ("r-r-oo" ,r-r-oo)
9630 ("r-r-utils" ,r-r-utils)))
9631 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9632 (synopsis "Methods for normalization and visualization of microarray data")
9633 (description
9634 "This package provides methods for microarray analysis that take basic
9635 data types such as matrices and lists of vectors. These methods can be used
9636 standalone, be utilized in other packages, or be wrapped up in higher-level
9637 classes.")
9638 (license license:gpl2+)))
9639
9640 (define-public r-deseq
9641 (package
9642 (name "r-deseq")
9643 (version "1.30.0")
9644 (source
9645 (origin
9646 (method url-fetch)
9647 (uri (bioconductor-uri "DESeq" version))
9648 (sha256
9649 (base32
9650 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9651 (properties `((upstream-name . "DESeq")))
9652 (build-system r-build-system)
9653 (propagated-inputs
9654 `(("r-biobase" ,r-biobase)
9655 ("r-biocgenerics" ,r-biocgenerics)
9656 ("r-genefilter" ,r-genefilter)
9657 ("r-geneplotter" ,r-geneplotter)
9658 ("r-lattice" ,r-lattice)
9659 ("r-locfit" ,r-locfit)
9660 ("r-mass" ,r-mass)
9661 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9662 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9663 (synopsis "Differential gene expression analysis")
9664 (description
9665 "This package provides tools for estimating variance-mean dependence in
9666 count data from high-throughput genetic sequencing assays and for testing for
9667 differential expression based on a model using the negative binomial
9668 distribution.")
9669 (license license:gpl3+)))
9670
9671 (define-public r-edaseq
9672 (package
9673 (name "r-edaseq")
9674 (version "2.12.0")
9675 (source
9676 (origin
9677 (method url-fetch)
9678 (uri (bioconductor-uri "EDASeq" version))
9679 (sha256
9680 (base32
9681 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9682 (properties `((upstream-name . "EDASeq")))
9683 (build-system r-build-system)
9684 (propagated-inputs
9685 `(("r-annotationdbi" ,r-annotationdbi)
9686 ("r-aroma-light" ,r-aroma-light)
9687 ("r-biobase" ,r-biobase)
9688 ("r-biocgenerics" ,r-biocgenerics)
9689 ("r-biomart" ,r-biomart)
9690 ("r-biostrings" ,r-biostrings)
9691 ("r-deseq" ,r-deseq)
9692 ("r-genomicfeatures" ,r-genomicfeatures)
9693 ("r-genomicranges" ,r-genomicranges)
9694 ("r-iranges" ,r-iranges)
9695 ("r-rsamtools" ,r-rsamtools)
9696 ("r-shortread" ,r-shortread)))
9697 (home-page "https://github.com/drisso/EDASeq")
9698 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9699 (description
9700 "This package provides support for numerical and graphical summaries of
9701 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9702 adjust for GC-content effect (or other gene-level effects) on read counts:
9703 loess robust local regression, global-scaling, and full-quantile
9704 normalization. Between-lane normalization procedures to adjust for
9705 distributional differences between lanes (e.g., sequencing depth):
9706 global-scaling and full-quantile normalization.")
9707 (license license:artistic2.0)))
9708
9709 (define-public r-interactivedisplaybase
9710 (package
9711 (name "r-interactivedisplaybase")
9712 (version "1.16.0")
9713 (source
9714 (origin
9715 (method url-fetch)
9716 (uri (bioconductor-uri "interactiveDisplayBase" version))
9717 (sha256
9718 (base32
9719 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9720 (properties
9721 `((upstream-name . "interactiveDisplayBase")))
9722 (build-system r-build-system)
9723 (propagated-inputs
9724 `(("r-biocgenerics" ,r-biocgenerics)
9725 ("r-shiny" ,r-shiny)))
9726 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9727 (synopsis "Base package for web displays of Bioconductor objects")
9728 (description
9729 "This package contains the basic methods needed to generate interactive
9730 Shiny-based display methods for Bioconductor objects.")
9731 (license license:artistic2.0)))
9732
9733 (define-public r-annotationhub
9734 (package
9735 (name "r-annotationhub")
9736 (version "2.10.1")
9737 (source
9738 (origin
9739 (method url-fetch)
9740 (uri (bioconductor-uri "AnnotationHub" version))
9741 (sha256
9742 (base32
9743 "14v8g44a6zg9j2rwn9x9y8509k0wr2cw8yccliz24glplb40wva4"))))
9744 (properties `((upstream-name . "AnnotationHub")))
9745 (build-system r-build-system)
9746 (propagated-inputs
9747 `(("r-annotationdbi" ,r-annotationdbi)
9748 ("r-biocgenerics" ,r-biocgenerics)
9749 ("r-biocinstaller" ,r-biocinstaller)
9750 ("r-curl" ,r-curl)
9751 ("r-httr" ,r-httr)
9752 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9753 ("r-rsqlite" ,r-rsqlite)
9754 ("r-s4vectors" ,r-s4vectors)
9755 ("r-yaml" ,r-yaml)))
9756 (home-page "https://bioconductor.org/packages/AnnotationHub")
9757 (synopsis "Client to access AnnotationHub resources")
9758 (description
9759 "This package provides a client for the Bioconductor AnnotationHub web
9760 resource. The AnnotationHub web resource provides a central location where
9761 genomic files (e.g. VCF, bed, wig) and other resources from standard
9762 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9763 metadata about each resource, e.g., a textual description, tags, and date of
9764 modification. The client creates and manages a local cache of files retrieved
9765 by the user, helping with quick and reproducible access.")
9766 (license license:artistic2.0)))
9767
9768 (define-public r-fastseg
9769 (package
9770 (name "r-fastseg")
9771 (version "1.24.0")
9772 (source
9773 (origin
9774 (method url-fetch)
9775 (uri (bioconductor-uri "fastseg" version))
9776 (sha256
9777 (base32
9778 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9779 (build-system r-build-system)
9780 (propagated-inputs
9781 `(("r-biobase" ,r-biobase)
9782 ("r-biocgenerics" ,r-biocgenerics)
9783 ("r-genomicranges" ,r-genomicranges)
9784 ("r-iranges" ,r-iranges)
9785 ("r-s4vectors" ,r-s4vectors)))
9786 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9787 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9788 (description
9789 "Fastseg implements a very fast and efficient segmentation algorithm.
9790 It can segment data from DNA microarrays and data from next generation
9791 sequencing for example to detect copy number segments. Further it can segment
9792 data from RNA microarrays like tiling arrays to identify transcripts. Most
9793 generally, it can segment data given as a matrix or as a vector. Various data
9794 formats can be used as input to fastseg like expression set objects for
9795 microarrays or GRanges for sequencing data.")
9796 (license license:lgpl2.0+)))
9797
9798 (define-public r-keggrest
9799 (package
9800 (name "r-keggrest")
9801 (version "1.18.1")
9802 (source
9803 (origin
9804 (method url-fetch)
9805 (uri (bioconductor-uri "KEGGREST" version))
9806 (sha256
9807 (base32
9808 "02gwmm79djj55a90dzc80hlgwc6bafl7xd7fnx2q59pk945k3z9c"))))
9809 (properties `((upstream-name . "KEGGREST")))
9810 (build-system r-build-system)
9811 (propagated-inputs
9812 `(("r-biostrings" ,r-biostrings)
9813 ("r-httr" ,r-httr)
9814 ("r-png" ,r-png)))
9815 (home-page "https://bioconductor.org/packages/KEGGREST")
9816 (synopsis "Client-side REST access to KEGG")
9817 (description
9818 "This package provides a package that provides a client interface to the
9819 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9820 (license license:artistic2.0)))
9821
9822 (define-public r-gage
9823 (package
9824 (name "r-gage")
9825 (version "2.28.2")
9826 (source
9827 (origin
9828 (method url-fetch)
9829 (uri (bioconductor-uri "gage" version))
9830 (sha256
9831 (base32
9832 "0h0mlhns9j7cpfksvdlvx9jb7szm3r1dwqb3s4s8p8hmkb9byyii"))))
9833 (build-system r-build-system)
9834 (propagated-inputs
9835 `(("r-annotationdbi" ,r-annotationdbi)
9836 ("r-graph" ,r-graph)
9837 ("r-keggrest" ,r-keggrest)))
9838 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9839 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9840 (description
9841 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9842 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9843 data attributes including sample sizes, experimental designs, assay platforms,
9844 and other types of heterogeneity. The gage package provides functions for
9845 basic GAGE analysis, result processing and presentation. In addition, it
9846 provides demo microarray data and commonly used gene set data based on KEGG
9847 pathways and GO terms. These funtions and data are also useful for gene set
9848 analysis using other methods.")
9849 (license license:gpl2+)))
9850
9851 (define-public r-genomicfiles
9852 (package
9853 (name "r-genomicfiles")
9854 (version "1.14.0")
9855 (source
9856 (origin
9857 (method url-fetch)
9858 (uri (bioconductor-uri "GenomicFiles" version))
9859 (sha256
9860 (base32
9861 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9862 (properties `((upstream-name . "GenomicFiles")))
9863 (build-system r-build-system)
9864 (propagated-inputs
9865 `(("r-biocgenerics" ,r-biocgenerics)
9866 ("r-biocparallel" ,r-biocparallel)
9867 ("r-genomeinfodb" ,r-genomeinfodb)
9868 ("r-genomicalignments" ,r-genomicalignments)
9869 ("r-genomicranges" ,r-genomicranges)
9870 ("r-iranges" ,r-iranges)
9871 ("r-rsamtools" ,r-rsamtools)
9872 ("r-rtracklayer" ,r-rtracklayer)
9873 ("r-s4vectors" ,r-s4vectors)
9874 ("r-summarizedexperiment" ,r-summarizedexperiment)
9875 ("r-variantannotation" ,r-variantannotation)))
9876 (home-page "https://bioconductor.org/packages/GenomicFiles")
9877 (synopsis "Distributed computing by file or by range")
9878 (description
9879 "This package provides infrastructure for parallel computations
9880 distributed by file or by range. User defined mapper and reducer functions
9881 provide added flexibility for data combination and manipulation.")
9882 (license license:artistic2.0)))
9883
9884 (define-public r-complexheatmap
9885 (package
9886 (name "r-complexheatmap")
9887 (version "1.17.1")
9888 (source
9889 (origin
9890 (method url-fetch)
9891 (uri (bioconductor-uri "ComplexHeatmap" version))
9892 (sha256
9893 (base32
9894 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9895 (properties
9896 `((upstream-name . "ComplexHeatmap")))
9897 (build-system r-build-system)
9898 (propagated-inputs
9899 `(("r-circlize" ,r-circlize)
9900 ("r-colorspace" ,r-colorspace)
9901 ("r-getoptlong" ,r-getoptlong)
9902 ("r-globaloptions" ,r-globaloptions)
9903 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9904 (home-page
9905 "https://github.com/jokergoo/ComplexHeatmap")
9906 (synopsis "Making Complex Heatmaps")
9907 (description
9908 "Complex heatmaps are efficient to visualize associations between
9909 different sources of data sets and reveal potential structures. This package
9910 provides a highly flexible way to arrange multiple heatmaps and supports
9911 self-defined annotation graphics.")
9912 (license license:gpl2+)))
9913
9914 (define-public r-dirichletmultinomial
9915 (package
9916 (name "r-dirichletmultinomial")
9917 (version "1.20.0")
9918 (source
9919 (origin
9920 (method url-fetch)
9921 (uri (bioconductor-uri "DirichletMultinomial" version))
9922 (sha256
9923 (base32
9924 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9925 (properties
9926 `((upstream-name . "DirichletMultinomial")))
9927 (build-system r-build-system)
9928 (inputs
9929 `(("gsl" ,gsl)))
9930 (propagated-inputs
9931 `(("r-biocgenerics" ,r-biocgenerics)
9932 ("r-iranges" ,r-iranges)
9933 ("r-s4vectors" ,r-s4vectors)))
9934 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9935 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9936 (description
9937 "Dirichlet-multinomial mixture models can be used to describe variability
9938 in microbial metagenomic data. This package is an interface to code
9939 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9940 1-15.")
9941 (license license:lgpl3)))
9942
9943 (define-public r-ensembldb
9944 (package
9945 (name "r-ensembldb")
9946 (version "2.2.2")
9947 (source
9948 (origin
9949 (method url-fetch)
9950 (uri (bioconductor-uri "ensembldb" version))
9951 (sha256
9952 (base32
9953 "1yngndkf3588z91z0a2fvkg423p26ajm6xv1p27x0l9mzhhaqq3k"))))
9954 (build-system r-build-system)
9955 (propagated-inputs
9956 `(("r-annotationdbi" ,r-annotationdbi)
9957 ("r-annotationfilter" ,r-annotationfilter)
9958 ("r-annotationhub" ,r-annotationhub)
9959 ("r-biobase" ,r-biobase)
9960 ("r-biocgenerics" ,r-biocgenerics)
9961 ("r-biostrings" ,r-biostrings)
9962 ("r-curl" ,r-curl)
9963 ("r-dbi" ,r-dbi)
9964 ("r-genomeinfodb" ,r-genomeinfodb)
9965 ("r-genomicfeatures" ,r-genomicfeatures)
9966 ("r-genomicranges" ,r-genomicranges)
9967 ("r-iranges" ,r-iranges)
9968 ("r-protgenerics" ,r-protgenerics)
9969 ("r-rsamtools" ,r-rsamtools)
9970 ("r-rsqlite" ,r-rsqlite)
9971 ("r-rtracklayer" ,r-rtracklayer)
9972 ("r-s4vectors" ,r-s4vectors)))
9973 (home-page "https://github.com/jotsetung/ensembldb")
9974 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9975 (description
9976 "The package provides functions to create and use transcript-centric
9977 annotation databases/packages. The annotation for the databases are directly
9978 fetched from Ensembl using their Perl API. The functionality and data is
9979 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9980 but, in addition to retrieve all gene/transcript models and annotations from
9981 the database, the @code{ensembldb} package also provides a filter framework
9982 allowing to retrieve annotations for specific entries like genes encoded on a
9983 chromosome region or transcript models of lincRNA genes.")
9984 ;; No version specified
9985 (license license:lgpl3+)))
9986
9987 (define-public r-organismdbi
9988 (package
9989 (name "r-organismdbi")
9990 (version "1.20.0")
9991 (source
9992 (origin
9993 (method url-fetch)
9994 (uri (bioconductor-uri "OrganismDbi" version))
9995 (sha256
9996 (base32
9997 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
9998 (properties `((upstream-name . "OrganismDbi")))
9999 (build-system r-build-system)
10000 (propagated-inputs
10001 `(("r-annotationdbi" ,r-annotationdbi)
10002 ("r-biobase" ,r-biobase)
10003 ("r-biocgenerics" ,r-biocgenerics)
10004 ("r-biocinstaller" ,r-biocinstaller)
10005 ("r-dbi" ,r-dbi)
10006 ("r-genomicfeatures" ,r-genomicfeatures)
10007 ("r-genomicranges" ,r-genomicranges)
10008 ("r-graph" ,r-graph)
10009 ("r-iranges" ,r-iranges)
10010 ("r-rbgl" ,r-rbgl)
10011 ("r-s4vectors" ,r-s4vectors)))
10012 (home-page "https://bioconductor.org/packages/OrganismDbi")
10013 (synopsis "Software to enable the smooth interfacing of database packages")
10014 (description "The package enables a simple unified interface to several
10015 annotation packages each of which has its own schema by taking advantage of
10016 the fact that each of these packages implements a select methods.")
10017 (license license:artistic2.0)))
10018
10019 (define-public r-biovizbase
10020 (package
10021 (name "r-biovizbase")
10022 (version "1.26.0")
10023 (source
10024 (origin
10025 (method url-fetch)
10026 (uri (bioconductor-uri "biovizBase" version))
10027 (sha256
10028 (base32
10029 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
10030 (properties `((upstream-name . "biovizBase")))
10031 (build-system r-build-system)
10032 (propagated-inputs
10033 `(("r-annotationdbi" ,r-annotationdbi)
10034 ("r-annotationfilter" ,r-annotationfilter)
10035 ("r-biocgenerics" ,r-biocgenerics)
10036 ("r-biostrings" ,r-biostrings)
10037 ("r-dichromat" ,r-dichromat)
10038 ("r-ensembldb" ,r-ensembldb)
10039 ("r-genomeinfodb" ,r-genomeinfodb)
10040 ("r-genomicalignments" ,r-genomicalignments)
10041 ("r-genomicfeatures" ,r-genomicfeatures)
10042 ("r-genomicranges" ,r-genomicranges)
10043 ("r-hmisc" ,r-hmisc)
10044 ("r-iranges" ,r-iranges)
10045 ("r-rcolorbrewer" ,r-rcolorbrewer)
10046 ("r-rsamtools" ,r-rsamtools)
10047 ("r-s4vectors" ,r-s4vectors)
10048 ("r-scales" ,r-scales)
10049 ("r-summarizedexperiment" ,r-summarizedexperiment)
10050 ("r-variantannotation" ,r-variantannotation)))
10051 (home-page "https://bioconductor.org/packages/biovizBase")
10052 (synopsis "Basic graphic utilities for visualization of genomic data")
10053 (description
10054 "The biovizBase package is designed to provide a set of utilities, color
10055 schemes and conventions for genomic data. It serves as the base for various
10056 high-level packages for biological data visualization. This saves development
10057 effort and encourages consistency.")
10058 (license license:artistic2.0)))
10059
10060 (define-public r-ggbio
10061 (package
10062 (name "r-ggbio")
10063 (version "1.26.0")
10064 (source
10065 (origin
10066 (method url-fetch)
10067 (uri (bioconductor-uri "ggbio" version))
10068 (sha256
10069 (base32
10070 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
10071 (build-system r-build-system)
10072 (propagated-inputs
10073 `(("r-annotationdbi" ,r-annotationdbi)
10074 ("r-annotationfilter" ,r-annotationfilter)
10075 ("r-biobase" ,r-biobase)
10076 ("r-biocgenerics" ,r-biocgenerics)
10077 ("r-biostrings" ,r-biostrings)
10078 ("r-biovizbase" ,r-biovizbase)
10079 ("r-bsgenome" ,r-bsgenome)
10080 ("r-ensembldb" ,r-ensembldb)
10081 ("r-genomeinfodb" ,r-genomeinfodb)
10082 ("r-genomicalignments" ,r-genomicalignments)
10083 ("r-genomicfeatures" ,r-genomicfeatures)
10084 ("r-genomicranges" ,r-genomicranges)
10085 ("r-ggally" ,r-ggally)
10086 ("r-ggplot2" ,r-ggplot2)
10087 ("r-gridextra" ,r-gridextra)
10088 ("r-gtable" ,r-gtable)
10089 ("r-hmisc" ,r-hmisc)
10090 ("r-iranges" ,r-iranges)
10091 ("r-organismdbi" ,r-organismdbi)
10092 ("r-reshape2" ,r-reshape2)
10093 ("r-rsamtools" ,r-rsamtools)
10094 ("r-rtracklayer" ,r-rtracklayer)
10095 ("r-s4vectors" ,r-s4vectors)
10096 ("r-scales" ,r-scales)
10097 ("r-summarizedexperiment" ,r-summarizedexperiment)
10098 ("r-variantannotation" ,r-variantannotation)))
10099 (home-page "http://www.tengfei.name/ggbio/")
10100 (synopsis "Visualization tools for genomic data")
10101 (description
10102 "The ggbio package extends and specializes the grammar of graphics for
10103 biological data. The graphics are designed to answer common scientific
10104 questions, in particular those often asked of high throughput genomics data.
10105 All core Bioconductor data structures are supported, where appropriate. The
10106 package supports detailed views of particular genomic regions, as well as
10107 genome-wide overviews. Supported overviews include ideograms and grand linear
10108 views. High-level plots include sequence fragment length, edge-linked
10109 interval to data view, mismatch pileup, and several splicing summaries.")
10110 (license license:artistic2.0)))
10111
10112 (define-public r-gprofiler
10113 (package
10114 (name "r-gprofiler")
10115 (version "0.6.4")
10116 (source
10117 (origin
10118 (method url-fetch)
10119 (uri (cran-uri "gProfileR" version))
10120 (sha256
10121 (base32
10122 "1cka02zbz1rbppm782qpxk1xn9qxbrv2gp5rgf970j906hxm2y0b"))))
10123 (properties `((upstream-name . "gProfileR")))
10124 (build-system r-build-system)
10125 (propagated-inputs
10126 `(("r-plyr" ,r-plyr)
10127 ("r-rcurl" ,r-rcurl)))
10128 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10129 (synopsis "Interface to the g:Profiler toolkit")
10130 (description
10131 "This package provides tools for functional enrichment analysis,
10132 gene identifier conversion and mapping homologous genes across related
10133 organisms via the @code{g:Profiler} toolkit.")
10134 (license license:gpl2+)))
10135
10136 (define-public r-gqtlbase
10137 (package
10138 (name "r-gqtlbase")
10139 (version "1.10.0")
10140 (source
10141 (origin
10142 (method url-fetch)
10143 (uri (bioconductor-uri "gQTLBase" version))
10144 (sha256
10145 (base32
10146 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
10147 (properties `((upstream-name . "gQTLBase")))
10148 (build-system r-build-system)
10149 (propagated-inputs
10150 `(("r-batchjobs" ,r-batchjobs)
10151 ("r-bbmisc" ,r-bbmisc)
10152 ("r-biocgenerics" ,r-biocgenerics)
10153 ("r-bit" ,r-bit)
10154 ("r-doparallel" ,r-doparallel)
10155 ("r-ff" ,r-ff)
10156 ("r-ffbase" ,r-ffbase)
10157 ("r-foreach" ,r-foreach)
10158 ("r-genomicfiles" ,r-genomicfiles)
10159 ("r-genomicranges" ,r-genomicranges)
10160 ("r-rtracklayer" ,r-rtracklayer)
10161 ("r-s4vectors" ,r-s4vectors)
10162 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10163 (home-page "https://bioconductor.org/packages/gQTLBase")
10164 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10165 (description
10166 "The purpose of this package is to simplify the storage and interrogation
10167 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10168 and more.")
10169 (license license:artistic2.0)))
10170
10171 (define-public r-snpstats
10172 (package
10173 (name "r-snpstats")
10174 (version "1.28.0")
10175 (source
10176 (origin
10177 (method url-fetch)
10178 (uri (bioconductor-uri "snpStats" version))
10179 (sha256
10180 (base32
10181 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
10182 (properties `((upstream-name . "snpStats")))
10183 (build-system r-build-system)
10184 (inputs `(("zlib" ,zlib)))
10185 (propagated-inputs
10186 `(("r-biocgenerics" ,r-biocgenerics)
10187 ("r-matrix" ,r-matrix)
10188 ("r-survival" ,r-survival)
10189 ("r-zlibbioc" ,r-zlibbioc)))
10190 (home-page "https://bioconductor.org/packages/snpStats")
10191 (synopsis "Methods for SNP association studies")
10192 (description
10193 "This package provides classes and statistical methods for large
10194 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10195 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10196 (license license:gpl3)))
10197
10198 (define-public r-homo-sapiens
10199 (package
10200 (name "r-homo-sapiens")
10201 (version "1.3.1")
10202 (source (origin
10203 (method url-fetch)
10204 ;; We cannot use bioconductor-uri here because this tarball is
10205 ;; located under "data/annotation/" instead of "bioc/".
10206 (uri (string-append "http://www.bioconductor.org/packages/"
10207 "release/data/annotation/src/contrib/"
10208 "Homo.sapiens_"
10209 version ".tar.gz"))
10210 (sha256
10211 (base32
10212 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10213 (properties
10214 `((upstream-name . "Homo.sapiens")))
10215 (build-system r-build-system)
10216 (propagated-inputs
10217 `(("r-genomicfeatures" ,r-genomicfeatures)
10218 ("r-go-db" ,r-go-db)
10219 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10220 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10221 ("r-organismdbi" ,r-organismdbi)
10222 ("r-annotationdbi" ,r-annotationdbi)))
10223 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10224 (synopsis "Annotation package for the Homo.sapiens object")
10225 (description
10226 "This package contains the Homo.sapiens object to access data from
10227 several related annotation packages.")
10228 (license license:artistic2.0)))
10229
10230 (define-public r-erma
10231 (package
10232 (name "r-erma")
10233 (version "0.10.0")
10234 (source
10235 (origin
10236 (method url-fetch)
10237 (uri (bioconductor-uri "erma" version))
10238 (sha256
10239 (base32
10240 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
10241 (build-system r-build-system)
10242 (propagated-inputs
10243 `(("r-annotationdbi" ,r-annotationdbi)
10244 ("r-biobase" ,r-biobase)
10245 ("r-biocgenerics" ,r-biocgenerics)
10246 ("r-foreach" ,r-foreach)
10247 ("r-genomicfiles" ,r-genomicfiles)
10248 ("r-genomicranges" ,r-genomicranges)
10249 ("r-ggplot2" ,r-ggplot2)
10250 ("r-homo-sapiens" ,r-homo-sapiens)
10251 ("r-rtracklayer" ,r-rtracklayer)
10252 ("r-s4vectors" ,r-s4vectors)
10253 ("r-shiny" ,r-shiny)
10254 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10255 (home-page "https://bioconductor.org/packages/erma")
10256 (synopsis "Epigenomic road map adventures")
10257 (description
10258 "The epigenomics road map describes locations of epigenetic marks in DNA
10259 from a variety of cell types. Of interest are locations of histone
10260 modifications, sites of DNA methylation, and regions of accessible chromatin.
10261 This package presents a selection of elements of the road map including
10262 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10263 by Ernst and Kellis.")
10264 (license license:artistic2.0)))
10265
10266 (define-public r-ldblock
10267 (package
10268 (name "r-ldblock")
10269 (version "1.8.0")
10270 (source
10271 (origin
10272 (method url-fetch)
10273 (uri (bioconductor-uri "ldblock" version))
10274 (sha256
10275 (base32
10276 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
10277 (build-system r-build-system)
10278 (propagated-inputs
10279 `(("r-erma" ,r-erma)
10280 ("r-genomeinfodb" ,r-genomeinfodb)
10281 ("r-genomicfiles" ,r-genomicfiles)
10282 ("r-go-db" ,r-go-db)
10283 ("r-homo-sapiens" ,r-homo-sapiens)
10284 ("r-matrix" ,r-matrix)
10285 ("r-rsamtools" ,r-rsamtools)
10286 ("r-snpstats" ,r-snpstats)
10287 ("r-variantannotation" ,r-variantannotation)))
10288 (home-page "https://bioconductor.org/packages/ldblock")
10289 (synopsis "Data structures for linkage disequilibrium measures in populations")
10290 (description
10291 "This package defines data structures for @dfn{linkage
10292 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10293 handling of existing population-level data for the purpose of flexibly
10294 defining LD blocks.")
10295 (license license:artistic2.0)))
10296
10297 (define-public r-gqtlstats
10298 (package
10299 (name "r-gqtlstats")
10300 (version "1.10.1")
10301 (source
10302 (origin
10303 (method url-fetch)
10304 (uri (bioconductor-uri "gQTLstats" version))
10305 (sha256
10306 (base32
10307 "0gvq1sf2zjbkk431x40z6wql3c1rpclnnwa2f1hvykb8mmw70kmq"))))
10308 (properties `((upstream-name . "gQTLstats")))
10309 (build-system r-build-system)
10310 (propagated-inputs
10311 `(("r-annotationdbi" ,r-annotationdbi)
10312 ("r-batchjobs" ,r-batchjobs)
10313 ("r-bbmisc" ,r-bbmisc)
10314 ("r-beeswarm" ,r-beeswarm)
10315 ("r-biobase" ,r-biobase)
10316 ("r-biocgenerics" ,r-biocgenerics)
10317 ("r-doparallel" ,r-doparallel)
10318 ("r-dplyr" ,r-dplyr)
10319 ("r-erma" ,r-erma)
10320 ("r-ffbase" ,r-ffbase)
10321 ("r-foreach" ,r-foreach)
10322 ("r-genomeinfodb" ,r-genomeinfodb)
10323 ("r-genomicfeatures" ,r-genomicfeatures)
10324 ("r-genomicfiles" ,r-genomicfiles)
10325 ("r-genomicranges" ,r-genomicranges)
10326 ("r-ggbeeswarm" ,r-ggbeeswarm)
10327 ("r-ggplot2" ,r-ggplot2)
10328 ("r-gqtlbase" ,r-gqtlbase)
10329 ("r-hardyweinberg" ,r-hardyweinberg)
10330 ("r-iranges" ,r-iranges)
10331 ("r-ldblock" ,r-ldblock)
10332 ("r-limma" ,r-limma)
10333 ("r-mgcv" ,r-mgcv)
10334 ("r-plotly" ,r-plotly)
10335 ("r-reshape2" ,r-reshape2)
10336 ("r-s4vectors" ,r-s4vectors)
10337 ("r-shiny" ,r-shiny)
10338 ("r-snpstats" ,r-snpstats)
10339 ("r-summarizedexperiment" ,r-summarizedexperiment)
10340 ("r-variantannotation" ,r-variantannotation)))
10341 (home-page "https://bioconductor.org/packages/gQTLstats")
10342 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10343 (description
10344 "This package provides tools for the computationally efficient analysis
10345 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10346 The software in this package aims to support refinements and functional
10347 interpretation of members of a collection of association statistics on a
10348 family of feature/genome hypotheses.")
10349 (license license:artistic2.0)))
10350
10351 (define-public r-gviz
10352 (package
10353 (name "r-gviz")
10354 (version "1.22.3")
10355 (source
10356 (origin
10357 (method url-fetch)
10358 (uri (bioconductor-uri "Gviz" version))
10359 (sha256
10360 (base32
10361 "1grjzrjpzkw572pbvpsvdnfkfgwybl0cnjd7nnk2xdr26wnbsi9a"))))
10362 (properties `((upstream-name . "Gviz")))
10363 (build-system r-build-system)
10364 (propagated-inputs
10365 `(("r-annotationdbi" ,r-annotationdbi)
10366 ("r-biobase" ,r-biobase)
10367 ("r-biocgenerics" ,r-biocgenerics)
10368 ("r-biomart" ,r-biomart)
10369 ("r-biostrings" ,r-biostrings)
10370 ("r-biovizbase" ,r-biovizbase)
10371 ("r-bsgenome" ,r-bsgenome)
10372 ("r-digest" ,r-digest)
10373 ("r-genomeinfodb" ,r-genomeinfodb)
10374 ("r-genomicalignments" ,r-genomicalignments)
10375 ("r-genomicfeatures" ,r-genomicfeatures)
10376 ("r-genomicranges" ,r-genomicranges)
10377 ("r-iranges" ,r-iranges)
10378 ("r-lattice" ,r-lattice)
10379 ("r-latticeextra" ,r-latticeextra)
10380 ("r-matrixstats" ,r-matrixstats)
10381 ("r-rcolorbrewer" ,r-rcolorbrewer)
10382 ("r-rsamtools" ,r-rsamtools)
10383 ("r-rtracklayer" ,r-rtracklayer)
10384 ("r-s4vectors" ,r-s4vectors)
10385 ("r-xvector" ,r-xvector)))
10386 (home-page "https://bioconductor.org/packages/Gviz")
10387 (synopsis "Plotting data and annotation information along genomic coordinates")
10388 (description
10389 "Genomic data analyses requires integrated visualization of known genomic
10390 information and new experimental data. Gviz uses the biomaRt and the
10391 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10392 and translates this to e.g. gene/transcript structures in viewports of the
10393 grid graphics package. This results in genomic information plotted together
10394 with your data.")
10395 (license license:artistic2.0)))
10396
10397 (define-public r-gwascat
10398 (package
10399 (name "r-gwascat")
10400 (version "2.10.0")
10401 (source
10402 (origin
10403 (method url-fetch)
10404 (uri (bioconductor-uri "gwascat" version))
10405 (sha256
10406 (base32
10407 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10408 (build-system r-build-system)
10409 (propagated-inputs
10410 `(("r-annotationdbi" ,r-annotationdbi)
10411 ("r-annotationhub" ,r-annotationhub)
10412 ("r-biocgenerics" ,r-biocgenerics)
10413 ("r-biostrings" ,r-biostrings)
10414 ("r-genomeinfodb" ,r-genomeinfodb)
10415 ("r-genomicfeatures" ,r-genomicfeatures)
10416 ("r-genomicranges" ,r-genomicranges)
10417 ("r-ggbio" ,r-ggbio)
10418 ("r-ggplot2" ,r-ggplot2)
10419 ("r-gqtlstats" ,r-gqtlstats)
10420 ("r-graph" ,r-graph)
10421 ("r-gviz" ,r-gviz)
10422 ("r-homo-sapiens" ,r-homo-sapiens)
10423 ("r-iranges" ,r-iranges)
10424 ("r-rsamtools" ,r-rsamtools)
10425 ("r-rtracklayer" ,r-rtracklayer)
10426 ("r-s4vectors" ,r-s4vectors)
10427 ("r-snpstats" ,r-snpstats)
10428 ("r-summarizedexperiment" ,r-summarizedexperiment)
10429 ("r-variantannotation" ,r-variantannotation)))
10430 (home-page "https://bioconductor.org/packages/gwascat")
10431 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10432 (description
10433 "This package provides tools for representing and modeling data in the
10434 EMBL-EBI GWAS catalog.")
10435 (license license:artistic2.0)))
10436
10437 (define-public r-sushi
10438 (package
10439 (name "r-sushi")
10440 (version "1.16.0")
10441 (source (origin
10442 (method url-fetch)
10443 (uri (bioconductor-uri "Sushi" version))
10444 (sha256
10445 (base32
10446 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10447 (properties `((upstream-name . "Sushi")))
10448 (build-system r-build-system)
10449 (propagated-inputs
10450 `(("r-biomart" ,r-biomart)
10451 ("r-zoo" ,r-zoo)))
10452 (home-page "https://bioconductor.org/packages/Sushi")
10453 (synopsis "Tools for visualizing genomics data")
10454 (description
10455 "This package provides flexible, quantitative, and integrative genomic
10456 visualizations for publication-quality multi-panel figures.")
10457 (license license:gpl2+)))
10458
10459 (define-public r-fithic
10460 (package
10461 (name "r-fithic")
10462 (version "1.4.0")
10463 (source (origin
10464 (method url-fetch)
10465 (uri (bioconductor-uri "FitHiC" version))
10466 (sha256
10467 (base32
10468 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10469 (properties `((upstream-name . "FitHiC")))
10470 (build-system r-build-system)
10471 (propagated-inputs
10472 `(("r-data-table" ,r-data-table)
10473 ("r-fdrtool" ,r-fdrtool)
10474 ("r-rcpp" ,r-rcpp)))
10475 (home-page "https://bioconductor.org/packages/FitHiC")
10476 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10477 (description
10478 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10479 intra-chromosomal contact maps produced by genome-wide genome architecture
10480 assays such as Hi-C.")
10481 (license license:gpl2+)))
10482
10483 (define-public r-hitc
10484 (package
10485 (name "r-hitc")
10486 (version "1.22.0")
10487 (source (origin
10488 (method url-fetch)
10489 (uri (bioconductor-uri "HiTC" version))
10490 (sha256
10491 (base32
10492 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10493 (properties `((upstream-name . "HiTC")))
10494 (build-system r-build-system)
10495 (propagated-inputs
10496 `(("r-biostrings" ,r-biostrings)
10497 ("r-genomeinfodb" ,r-genomeinfodb)
10498 ("r-genomicranges" ,r-genomicranges)
10499 ("r-iranges" ,r-iranges)
10500 ("r-matrix" ,r-matrix)
10501 ("r-rcolorbrewer" ,r-rcolorbrewer)
10502 ("r-rtracklayer" ,r-rtracklayer)))
10503 (home-page "https://bioconductor.org/packages/HiTC")
10504 (synopsis "High throughput chromosome conformation capture analysis")
10505 (description
10506 "The HiTC package was developed to explore high-throughput \"C\" data
10507 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10508 quality controls, normalization, visualization, and further analysis are also
10509 provided.")
10510 (license license:artistic2.0)))
10511
10512 (define-public r-qvalue
10513 (package
10514 (name "r-qvalue")
10515 (version "2.10.0")
10516 (source
10517 (origin
10518 (method url-fetch)
10519 (uri (bioconductor-uri "qvalue" version))
10520 (sha256
10521 (base32
10522 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10523 (build-system r-build-system)
10524 (propagated-inputs
10525 `(("r-ggplot2" ,r-ggplot2)
10526 ("r-reshape2" ,r-reshape2)))
10527 (home-page "http://github.com/jdstorey/qvalue")
10528 (synopsis "Q-value estimation for false discovery rate control")
10529 (description
10530 "This package takes a list of p-values resulting from the simultaneous
10531 testing of many hypotheses and estimates their q-values and local @dfn{false
10532 discovery rate} (FDR) values. The q-value of a test measures the proportion
10533 of false positives incurred when that particular test is called significant.
10534 The local FDR measures the posterior probability the null hypothesis is true
10535 given the test's p-value. Various plots are automatically generated, allowing
10536 one to make sensible significance cut-offs. The software can be applied to
10537 problems in genomics, brain imaging, astrophysics, and data mining.")
10538 ;; Any version of the LGPL.
10539 (license license:lgpl3+)))
10540
10541 (define-public r-hdf5array
10542 (package
10543 (name "r-hdf5array")
10544 (version "1.6.0")
10545 (source
10546 (origin
10547 (method url-fetch)
10548 (uri (bioconductor-uri "HDF5Array" version))
10549 (sha256
10550 (base32
10551 "0kcdza41saqv6vlpvqd841awbiwkg84lh0plx6c7fmfgbqv7a0jh"))))
10552 (properties `((upstream-name . "HDF5Array")))
10553 (build-system r-build-system)
10554 (propagated-inputs
10555 `(("r-biocgenerics" ,r-biocgenerics)
10556 ("r-delayedarray" ,r-delayedarray)
10557 ("r-iranges" ,r-iranges)
10558 ("r-rhdf5" ,r-rhdf5)
10559 ("r-s4vectors" ,r-s4vectors)))
10560 (home-page "https://bioconductor.org/packages/HDF5Array")
10561 (synopsis "HDF5 back end for DelayedArray objects")
10562 (description "This package provides an array-like container for convenient
10563 access and manipulation of HDF5 datasets. It supports delayed operations and
10564 block processing.")
10565 (license license:artistic2.0)))
10566
10567 (define-public r-rhdf5lib
10568 (package
10569 (name "r-rhdf5lib")
10570 (version "1.0.0")
10571 (source
10572 (origin
10573 (method url-fetch)
10574 (uri (bioconductor-uri "Rhdf5lib" version))
10575 (sha256
10576 (base32
10577 "0kkc4rprjbqn2wvbx4d49kk9l91vihccxbl4843qr1wqk6v33r1w"))))
10578 (properties `((upstream-name . "Rhdf5lib")))
10579 (build-system r-build-system)
10580 (arguments
10581 `(#:phases
10582 (modify-phases %standard-phases
10583 (add-after 'unpack 'do-not-use-bundled-hdf5
10584 (lambda* (#:key inputs #:allow-other-keys)
10585 (for-each delete-file '("configure" "configure.ac"))
10586 ;; Do not make other packages link with the proprietary libsz.
10587 (substitute* "R/zzz.R"
10588 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a'")
10589 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a'")
10590 (("'%s/libhdf5.a %s/libsz.a'")
10591 "'%s/libhdf5.a %s/libhdf5.a'"))
10592 (with-directory-excursion "src"
10593 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10594 (rename-file (string-append "hdf5-" ,(package-version hdf5))
10595 "hdf5")
10596 (rename-file "Makevars.in" "Makevars")
10597 (substitute* "Makevars"
10598 (("HDF5_CXX_LIB=.*")
10599 (string-append "HDF5_CXX_LIB="
10600 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10601 (("HDF5_LIB=.*")
10602 (string-append "HDF5_LIB="
10603 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10604 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10605 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10606 ;; szip is non-free software
10607 (("cp \\$\\{SZIP_LIB\\}.*") "")
10608 (("PKG_LIBS = \\$\\{HDF5_LIB\\} \\$\\{SZIP_LIB\\}")
10609 "PKG_LIBS = ${HDF5_LIB}\n")))
10610 #t)))))
10611 (inputs
10612 `(("zlib" ,zlib)))
10613 (propagated-inputs
10614 `(("hdf5" ,hdf5)))
10615 (native-inputs
10616 `(("hdf5-source" ,(package-source hdf5))))
10617 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10618 (synopsis "HDF5 library as an R package")
10619 (description "This package provides C and C++ HDF5 libraries for use in R
10620 packages.")
10621 (license license:artistic2.0)))
10622
10623 (define-public r-beachmat
10624 (package
10625 (name "r-beachmat")
10626 (version "1.0.2")
10627 (source
10628 (origin
10629 (method url-fetch)
10630 (uri (bioconductor-uri "beachmat" version))
10631 (sha256
10632 (base32
10633 "0b6dzja5fbx4dawb7ixj67mlhw4fy62pfp20mfp918fy96zmdwqz"))))
10634 (build-system r-build-system)
10635 (inputs
10636 `(("hdf5" ,hdf5)))
10637 (propagated-inputs
10638 `(("r-delayedarray" ,r-delayedarray)
10639 ("r-hdf5array" ,r-hdf5array)
10640 ("r-rcpp" ,r-rcpp)
10641 ("r-rhdf5" ,r-rhdf5)
10642 ("r-rhdf5lib" ,r-rhdf5lib)))
10643 (home-page "https://bioconductor.org/packages/beachmat")
10644 (synopsis "Compiling Bioconductor to handle each matrix type")
10645 (description "This package provides a consistent C++ class interface for a
10646 variety of commonly used matrix types, including sparse and HDF5-backed
10647 matrices.")
10648 (license license:gpl3)))
10649
10650 (define-public r-singlecellexperiment
10651 (package
10652 (name "r-singlecellexperiment")
10653 (version "1.0.0")
10654 (source
10655 (origin
10656 (method url-fetch)
10657 (uri (bioconductor-uri "SingleCellExperiment" version))
10658 (sha256
10659 (base32
10660 "1r276i97w64a5vdlg6952gkj7bls909p42zl8fn8yz87cdwyaars"))))
10661 (properties
10662 `((upstream-name . "SingleCellExperiment")))
10663 (build-system r-build-system)
10664 (propagated-inputs
10665 `(("r-biocgenerics" ,r-biocgenerics)
10666 ("r-s4vectors" ,r-s4vectors)
10667 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10668 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10669 (synopsis "S4 classes for single cell data")
10670 (description "This package defines an S4 class for storing data from
10671 single-cell experiments. This includes specialized methods to store and
10672 retrieve spike-in information, dimensionality reduction coordinates and size
10673 factors for each cell, along with the usual metadata for genes and
10674 libraries.")
10675 (license license:gpl3)))
10676
10677 (define-public r-scater
10678 (package
10679 (name "r-scater")
10680 (version "1.6.3")
10681 (source (origin
10682 (method url-fetch)
10683 (uri (bioconductor-uri "scater" version))
10684 (sha256
10685 (base32
10686 "0q3s96gf8saa1dq2fvmpl0jyj7bx3wrdfck3hanb8pxkcir2p7dn"))))
10687 (build-system r-build-system)
10688 (propagated-inputs
10689 `(("r-beachmat" ,r-beachmat)
10690 ("r-biobase" ,r-biobase)
10691 ("r-biocgenerics" ,r-biocgenerics)
10692 ("r-biomart" ,r-biomart)
10693 ("r-data-table" ,r-data-table)
10694 ("r-dplyr" ,r-dplyr)
10695 ("r-edger" ,r-edger)
10696 ("r-ggbeeswarm" ,r-ggbeeswarm)
10697 ("r-ggplot2" ,r-ggplot2)
10698 ("r-limma" ,r-limma)
10699 ("r-matrix" ,r-matrix)
10700 ("r-matrixstats" ,r-matrixstats)
10701 ("r-plyr" ,r-plyr)
10702 ("r-rcpp" ,r-rcpp)
10703 ("r-reshape2" ,r-reshape2)
10704 ("r-rhdf5" ,r-rhdf5)
10705 ("r-rhdf5lib" ,r-rhdf5lib)
10706 ("r-rjson" ,r-rjson)
10707 ("r-s4vectors" ,r-s4vectors)
10708 ("r-shiny" ,r-shiny)
10709 ("r-shinydashboard" ,r-shinydashboard)
10710 ("r-singlecellexperiment" ,r-singlecellexperiment)
10711 ("r-summarizedexperiment" ,r-summarizedexperiment)
10712 ("r-tximport" ,r-tximport)
10713 ("r-viridis" ,r-viridis)))
10714 (home-page "https://github.com/davismcc/scater")
10715 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10716 (description "This package provides a collection of tools for doing
10717 various analyses of single-cell RNA-seq gene expression data, with a focus on
10718 quality control.")
10719 (license license:gpl2+)))
10720
10721 (define-public r-scran
10722 (package
10723 (name "r-scran")
10724 (version "1.6.8")
10725 (source
10726 (origin
10727 (method url-fetch)
10728 (uri (bioconductor-uri "scran" version))
10729 (sha256
10730 (base32
10731 "07wniyrh2fhhkz28v0bfgpvpi1hkkn2cvhacrvvvck142j79944x"))))
10732 (build-system r-build-system)
10733 (propagated-inputs
10734 `(("r-beachmat" ,r-beachmat)
10735 ("r-biocgenerics" ,r-biocgenerics)
10736 ("r-biocparallel" ,r-biocparallel)
10737 ("r-dt" ,r-dt)
10738 ("r-dynamictreecut" ,r-dynamictreecut)
10739 ("r-edger" ,r-edger)
10740 ("r-fnn" ,r-fnn)
10741 ("r-ggplot2" ,r-ggplot2)
10742 ("r-igraph" ,r-igraph)
10743 ("r-limma" ,r-limma)
10744 ("r-matrix" ,r-matrix)
10745 ("r-rcpp" ,r-rcpp)
10746 ("r-rhdf5lib" ,r-rhdf5lib)
10747 ("r-s4vectors" ,r-s4vectors)
10748 ("r-scater" ,r-scater)
10749 ("r-shiny" ,r-shiny)
10750 ("r-singlecellexperiment" ,r-singlecellexperiment)
10751 ("r-statmod" ,r-statmod)
10752 ("r-summarizedexperiment" ,r-summarizedexperiment)
10753 ("r-viridis" ,r-viridis)
10754 ("r-zoo" ,r-zoo)))
10755 (home-page "https://bioconductor.org/packages/scran")
10756 (synopsis "Methods for single-cell RNA-Seq data analysis")
10757 (description "This package implements a variety of low-level analyses of
10758 single-cell RNA-seq data. Methods are provided for normalization of
10759 cell-specific biases, assignment of cell cycle phase, and detection of highly
10760 variable and significantly correlated genes.")
10761 (license license:gpl3)))
10762
10763 (define-public r-delayedmatrixstats
10764 (package
10765 (name "r-delayedmatrixstats")
10766 (version "1.0.3")
10767 (source
10768 (origin
10769 (method url-fetch)
10770 (uri (bioconductor-uri "DelayedMatrixStats" version))
10771 (sha256
10772 (base32
10773 "1cxjbjdq9hg9cm95rci0al7a4pk2h73ym276ahw9q4977zbg6381"))))
10774 (properties
10775 `((upstream-name . "DelayedMatrixStats")))
10776 (build-system r-build-system)
10777 (propagated-inputs
10778 `(("r-delayedarray" ,r-delayedarray)
10779 ("r-iranges" ,r-iranges)
10780 ("r-matrix" ,r-matrix)
10781 ("r-matrixstats" ,r-matrixstats)
10782 ("r-s4vectors" ,r-s4vectors)))
10783 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10784 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10785 (description
10786 "This package provides a port of the @code{matrixStats} API for use with
10787 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10788 contains high-performing functions operating on rows and columns of
10789 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10790 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10791 are optimized per data type and for subsetted calculations such that both
10792 memory usage and processing time is minimized.")
10793 (license license:expat)))
10794
10795 (define-public r-dropbead
10796 (let ((commit "cf0be5ae5302684bd03e78ab65b142900bbbb840")
10797 (revision "1"))
10798 (package
10799 (name "r-dropbead")
10800 (version (string-append "0-" revision "." (string-take commit 7)))
10801 (source
10802 (origin
10803 (method git-fetch)
10804 (uri (git-reference
10805 (url "https://github.com/rajewsky-lab/dropbead.git")
10806 (commit commit)))
10807 (sha256
10808 (base32
10809 "1b2lphsc236s1rdzlijxg8yl1jnqpwcvj4x938r89rqpj93jb780"))))
10810 (build-system r-build-system)
10811 (propagated-inputs
10812 `(("r-ggplot2" ,r-ggplot2)
10813 ("r-rcolorbrewer" ,r-rcolorbrewer)
10814 ("r-gridextra" ,r-gridextra)
10815 ("r-gplots" ,r-gplots)
10816 ("r-plyr" ,r-plyr)))
10817 (home-page "https://github.com/rajewsky-lab/dropbead")
10818 (synopsis "Basic exploration and analysis of Drop-seq data")
10819 (description "This package offers a quick and straight-forward way to
10820 explore and perform basic analysis of single cell sequencing data coming from
10821 droplet sequencing. It has been particularly tailored for Drop-seq.")
10822 (license license:gpl3))))
10823
10824 (define htslib-for-sambamba
10825 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10826 (package
10827 (inherit htslib)
10828 (name "htslib-for-sambamba")
10829 (version (string-append "1.3.1-1." (string-take commit 9)))
10830 (source
10831 (origin
10832 (method git-fetch)
10833 (uri (git-reference
10834 (url "https://github.com/lomereiter/htslib.git")
10835 (commit commit)))
10836 (file-name (string-append "htslib-" version "-checkout"))
10837 (sha256
10838 (base32
10839 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10840 (arguments
10841 (substitute-keyword-arguments (package-arguments htslib)
10842 ((#:phases phases)
10843 `(modify-phases ,phases
10844 (add-after 'unpack 'bootstrap
10845 (lambda _
10846 (zero? (system* "autoreconf" "-vif"))))))))
10847 (native-inputs
10848 `(("autoconf" ,autoconf)
10849 ("automake" ,automake)
10850 ,@(package-native-inputs htslib))))))
10851
10852 (define-public sambamba
10853 (package
10854 (name "sambamba")
10855 (version "0.6.5")
10856 (source
10857 (origin
10858 (method url-fetch)
10859 (uri (string-append "https://github.com/lomereiter/sambamba/"
10860 "archive/v" version ".tar.gz"))
10861 (file-name (string-append name "-" version ".tar.gz"))
10862 (sha256
10863 (base32
10864 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10865 (build-system gnu-build-system)
10866 (arguments
10867 `(#:tests? #f ; there is no test target
10868 #:make-flags
10869 '("D_COMPILER=ldc2"
10870 ;; Override "--compiler" flag only.
10871 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10872 "sambamba-ldmd2-64")
10873 #:phases
10874 (modify-phases %standard-phases
10875 (delete 'configure)
10876 (add-after 'unpack 'place-biod
10877 (lambda* (#:key inputs #:allow-other-keys)
10878 (copy-recursively (assoc-ref inputs "biod") "BioD")
10879 #t))
10880 (add-after 'unpack 'unbundle-prerequisites
10881 (lambda _
10882 (substitute* "Makefile"
10883 ((" htslib-static lz4-static") ""))
10884 #t))
10885 (replace 'install
10886 (lambda* (#:key outputs #:allow-other-keys)
10887 (let* ((out (assoc-ref outputs "out"))
10888 (bin (string-append out "/bin")))
10889 (mkdir-p bin)
10890 (install-file "build/sambamba" bin)
10891 #t))))))
10892 (native-inputs
10893 `(("ldc" ,ldc)
10894 ("rdmd" ,rdmd)
10895 ("biod"
10896 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10897 (origin
10898 (method git-fetch)
10899 (uri (git-reference
10900 (url "https://github.com/biod/BioD.git")
10901 (commit commit)))
10902 (file-name (string-append "biod-"
10903 (string-take commit 9)
10904 "-checkout"))
10905 (sha256
10906 (base32
10907 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
10908 (inputs
10909 `(("lz4" ,lz4)
10910 ("htslib" ,htslib-for-sambamba)))
10911 (home-page "http://lomereiter.github.io/sambamba")
10912 (synopsis "Tools for working with SAM/BAM data")
10913 (description "Sambamba is a high performance modern robust and
10914 fast tool (and library), written in the D programming language, for
10915 working with SAM and BAM files. Current parallelised functionality is
10916 an important subset of samtools functionality, including view, index,
10917 sort, markdup, and depth.")
10918 (license license:gpl2+)))
10919
10920 (define-public ritornello
10921 (package
10922 (name "ritornello")
10923 (version "1.0.0")
10924 (source (origin
10925 (method url-fetch)
10926 (uri (string-append "https://github.com/KlugerLab/"
10927 "Ritornello/archive/v"
10928 version ".tar.gz"))
10929 (file-name (string-append name "-" version ".tar.gz"))
10930 (sha256
10931 (base32
10932 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
10933 (build-system gnu-build-system)
10934 (arguments
10935 `(#:tests? #f ; there are no tests
10936 #:phases
10937 (modify-phases %standard-phases
10938 (add-after 'unpack 'patch-samtools-references
10939 (lambda* (#:key inputs #:allow-other-keys)
10940 (substitute* '("src/SamStream.h"
10941 "src/BufferedGenomeReader.h")
10942 (("<sam.h>") "<samtools/sam.h>"))
10943 #t))
10944 (delete 'configure)
10945 (replace 'install
10946 (lambda* (#:key inputs outputs #:allow-other-keys)
10947 (let* ((out (assoc-ref outputs "out"))
10948 (bin (string-append out "/bin/")))
10949 (mkdir-p bin)
10950 (install-file "bin/Ritornello" bin)
10951 #t))))))
10952 (inputs
10953 `(("samtools" ,samtools-0.1)
10954 ("fftw" ,fftw)
10955 ("boost" ,boost)
10956 ("zlib" ,zlib)))
10957 (home-page "https://github.com/KlugerLab/Ritornello")
10958 (synopsis "Control-free peak caller for ChIP-seq data")
10959 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10960 signal processing that can accurately call binding events without the need to
10961 do a pair total DNA input or IgG control sample. It has been tested for use
10962 with narrow binding events such as transcription factor ChIP-seq.")
10963 (license license:gpl3+)))
10964
10965 (define-public trim-galore
10966 (package
10967 (name "trim-galore")
10968 (version "0.4.2")
10969 (source
10970 (origin
10971 (method url-fetch)
10972 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
10973 "projects/trim_galore/trim_galore_v"
10974 version ".zip"))
10975 (sha256
10976 (base32
10977 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
10978 (build-system gnu-build-system)
10979 (arguments
10980 `(#:tests? #f ; no tests
10981 #:phases
10982 (modify-phases %standard-phases
10983 ;; The archive contains plain files.
10984 (replace 'unpack
10985 (lambda* (#:key source #:allow-other-keys)
10986 (zero? (system* "unzip" source))))
10987 (delete 'configure)
10988 (delete 'build)
10989 (add-after 'unpack 'hardcode-tool-references
10990 (lambda* (#:key inputs #:allow-other-keys)
10991 (substitute* "trim_galore"
10992 (("\\$path_to_cutadapt = 'cutadapt'")
10993 (string-append "$path_to_cutadapt = '"
10994 (assoc-ref inputs "cutadapt")
10995 "/bin/cutadapt'"))
10996 (("\\| gzip")
10997 (string-append "| "
10998 (assoc-ref inputs "gzip")
10999 "/bin/gzip"))
11000 (("\"gunzip")
11001 (string-append "\""
11002 (assoc-ref inputs "gzip")
11003 "/bin/gunzip")))
11004 #t))
11005 (replace 'install
11006 (lambda* (#:key outputs #:allow-other-keys)
11007 (let ((bin (string-append (assoc-ref outputs "out")
11008 "/bin")))
11009 (mkdir-p bin)
11010 (install-file "trim_galore" bin)
11011 #t))))))
11012 (inputs
11013 `(("gzip" ,gzip)
11014 ("perl" ,perl)
11015 ("cutadapt" ,cutadapt)))
11016 (native-inputs
11017 `(("unzip" ,unzip)))
11018 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11019 (synopsis "Wrapper around Cutadapt and FastQC")
11020 (description "Trim Galore! is a wrapper script to automate quality and
11021 adapter trimming as well as quality control, with some added functionality to
11022 remove biased methylation positions for RRBS sequence files.")
11023 (license license:gpl3+)))
11024
11025 (define-public gess
11026 (package
11027 (name "gess")
11028 (version "1.0")
11029 (source (origin
11030 (method url-fetch)
11031 (uri (string-append "http://compbio.uthscsa.edu/"
11032 "GESS_Web/files/"
11033 "gess-" version ".src.tar.gz"))
11034 (sha256
11035 (base32
11036 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11037 (build-system gnu-build-system)
11038 (arguments
11039 `(#:tests? #f ; no tests
11040 #:phases
11041 (modify-phases %standard-phases
11042 (delete 'configure)
11043 (delete 'build)
11044 (replace 'install
11045 (lambda* (#:key inputs outputs #:allow-other-keys)
11046 (let* ((python (assoc-ref inputs "python"))
11047 (out (assoc-ref outputs "out"))
11048 (bin (string-append out "/bin/"))
11049 (target (string-append
11050 out "/lib/python2.7/site-packages/gess/")))
11051 (mkdir-p target)
11052 (copy-recursively "." target)
11053 ;; Make GESS.py executable
11054 (chmod (string-append target "GESS.py") #o555)
11055 ;; Add Python shebang to the top and make Matplotlib
11056 ;; usable.
11057 (substitute* (string-append target "GESS.py")
11058 (("\"\"\"Description:" line)
11059 (string-append "#!" (which "python") "
11060 import matplotlib
11061 matplotlib.use('Agg')
11062 " line)))
11063 ;; Make sure GESS has all modules in its path
11064 (wrap-program (string-append target "GESS.py")
11065 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11066 (mkdir-p bin)
11067 (symlink (string-append target "GESS.py")
11068 (string-append bin "GESS.py"))
11069 #t))))))
11070 (inputs
11071 `(("python" ,python-2)
11072 ("python2-pysam" ,python2-pysam)
11073 ("python2-scipy" ,python2-scipy)
11074 ("python2-numpy" ,python2-numpy)
11075 ("python2-networkx" ,python2-networkx)
11076 ("python2-biopython" ,python2-biopython)))
11077 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11078 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11079 (description
11080 "GESS is an implementation of a novel computational method to detect de
11081 novo exon-skipping events directly from raw RNA-seq data without the prior
11082 knowledge of gene annotation information. GESS stands for the graph-based
11083 exon-skipping scanner detection scheme.")
11084 (license license:bsd-3)))
11085
11086 (define-public phylip
11087 (package
11088 (name "phylip")
11089 (version "3.696")
11090 (source
11091 (origin
11092 (method url-fetch)
11093 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11094 "download/phylip-" version ".tar.gz"))
11095 (sha256
11096 (base32
11097 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11098 (build-system gnu-build-system)
11099 (arguments
11100 `(#:tests? #f ; no check target
11101 #:make-flags (list "-f" "Makefile.unx" "install")
11102 #:parallel-build? #f ; not supported
11103 #:phases
11104 (modify-phases %standard-phases
11105 (add-after 'unpack 'enter-dir
11106 (lambda _ (chdir "src") #t))
11107 (delete 'configure)
11108 (replace 'install
11109 (lambda* (#:key inputs outputs #:allow-other-keys)
11110 (let ((target (string-append (assoc-ref outputs "out")
11111 "/bin")))
11112 (mkdir-p target)
11113 (for-each (lambda (file)
11114 (install-file file target))
11115 (find-files "../exe" ".*")))
11116 #t)))))
11117 (home-page "http://evolution.genetics.washington.edu/phylip/")
11118 (synopsis "Tools for inferring phylogenies")
11119 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11120 programs for inferring phylogenies (evolutionary trees).")
11121 (license license:bsd-2)))
11122
11123 (define-public imp
11124 (package
11125 (name "imp")
11126 (version "2.6.2")
11127 (source
11128 (origin
11129 (method url-fetch)
11130 (uri (string-append "https://integrativemodeling.org/"
11131 version "/download/imp-" version ".tar.gz"))
11132 (sha256
11133 (base32
11134 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11135 (build-system cmake-build-system)
11136 (arguments
11137 `(;; FIXME: Some tests fail because they produce warnings, others fail
11138 ;; because the PYTHONPATH does not include the modeller's directory.
11139 #:tests? #f))
11140 (inputs
11141 `(("boost" ,boost)
11142 ("gsl" ,gsl)
11143 ("swig" ,swig)
11144 ("hdf5" ,hdf5)
11145 ("fftw" ,fftw)
11146 ("python" ,python-2)))
11147 (propagated-inputs
11148 `(("python2-numpy" ,python2-numpy)
11149 ("python2-scipy" ,python2-scipy)
11150 ("python2-pandas" ,python2-pandas)
11151 ("python2-scikit-learn" ,python2-scikit-learn)
11152 ("python2-networkx" ,python2-networkx)))
11153 (home-page "https://integrativemodeling.org")
11154 (synopsis "Integrative modeling platform")
11155 (description "IMP's broad goal is to contribute to a comprehensive
11156 structural characterization of biomolecules ranging in size and complexity
11157 from small peptides to large macromolecular assemblies, by integrating data
11158 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11159 Python toolbox for solving complex modeling problems, and a number of
11160 applications for tackling some common problems in a user-friendly way.")
11161 ;; IMP is largely available under the GNU Lesser GPL; see the file
11162 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11163 ;; available under the GNU GPL (see the file COPYING.GPL).
11164 (license (list license:lgpl2.1+
11165 license:gpl3+))))
11166
11167 (define-public tadbit
11168 (package
11169 (name "tadbit")
11170 (version "0.2")
11171 (source (origin
11172 (method url-fetch)
11173 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11174 "archive/v" version ".tar.gz"))
11175 (file-name (string-append name "-" version ".tar.gz"))
11176 (sha256
11177 (base32
11178 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11179 (build-system python-build-system)
11180 (arguments
11181 `(;; Tests are included and must be run after installation, but
11182 ;; they are incomplete and thus cannot be run.
11183 #:tests? #f
11184 #:python ,python-2
11185 #:phases
11186 (modify-phases %standard-phases
11187 (add-after 'unpack 'fix-problems-with-setup.py
11188 (lambda* (#:key outputs #:allow-other-keys)
11189 ;; setup.py opens these files for writing
11190 (chmod "_pytadbit/_version.py" #o664)
11191 (chmod "README.rst" #o664)
11192
11193 ;; Don't attempt to install the bash completions to
11194 ;; the home directory.
11195 (rename-file "extras/.bash_completion"
11196 "extras/tadbit")
11197 (substitute* "setup.py"
11198 (("\\(path.expanduser\\('~'\\)")
11199 (string-append "(\""
11200 (assoc-ref outputs "out")
11201 "/etc/bash_completion.d\""))
11202 (("extras/\\.bash_completion")
11203 "extras/tadbit"))
11204 #t)))))
11205 (inputs
11206 ;; TODO: add Chimera for visualization
11207 `(("imp" ,imp)
11208 ("mcl" ,mcl)
11209 ("python2-scipy" ,python2-scipy)
11210 ("python2-numpy" ,python2-numpy)
11211 ("python2-matplotlib" ,python2-matplotlib)
11212 ("python2-pysam" ,python2-pysam)))
11213 (home-page "http://3dgenomes.github.io/TADbit/")
11214 (synopsis "Analyze, model, and explore 3C-based data")
11215 (description
11216 "TADbit is a complete Python library to deal with all steps to analyze,
11217 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11218 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11219 correct interaction matrices, identify and compare the so-called
11220 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11221 interaction matrices, and finally, extract structural properties from the
11222 models. TADbit is complemented by TADkit for visualizing 3D models.")
11223 (license license:gpl3+)))
11224
11225 (define-public kentutils
11226 (package
11227 (name "kentutils")
11228 ;; 302.1.0 is out, but the only difference is the inclusion of
11229 ;; pre-built binaries.
11230 (version "302.0.0")
11231 (source
11232 (origin
11233 (method url-fetch)
11234 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11235 "archive/v" version ".tar.gz"))
11236 (file-name (string-append name "-" version ".tar.gz"))
11237 (sha256
11238 (base32
11239 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11240 (modules '((guix build utils)
11241 (srfi srfi-26)
11242 (ice-9 ftw)))
11243 (snippet
11244 '(begin
11245 ;; Only the contents of the specified directories are free
11246 ;; for all uses, so we remove the rest. "hg/autoSql" and
11247 ;; "hg/autoXml" are nominally free, but they depend on a
11248 ;; library that is built from the sources in "hg/lib",
11249 ;; which is nonfree.
11250 (let ((free (list "." ".."
11251 "utils" "lib" "inc" "tagStorm"
11252 "parasol" "htslib"))
11253 (directory? (lambda (file)
11254 (eq? 'directory (stat:type (stat file))))))
11255 (for-each (lambda (file)
11256 (and (directory? file)
11257 (delete-file-recursively file)))
11258 (map (cut string-append "src/" <>)
11259 (scandir "src"
11260 (lambda (file)
11261 (not (member file free)))))))
11262 ;; Only make the utils target, not the userApps target,
11263 ;; because that requires libraries we won't build.
11264 (substitute* "Makefile"
11265 ((" userApps") " utils"))
11266 ;; Only build libraries that are free.
11267 (substitute* "src/makefile"
11268 (("DIRS =.*") "DIRS =\n")
11269 (("cd jkOwnLib.*") "")
11270 ((" hgLib") "")
11271 (("cd hg.*") ""))
11272 (substitute* "src/utils/makefile"
11273 ;; These tools depend on "jkhgap.a", which is part of the
11274 ;; nonfree "src/hg/lib" directory.
11275 (("raSqlQuery") "")
11276 (("pslLiftSubrangeBlat") "")
11277
11278 ;; Do not build UCSC tools, which may require nonfree
11279 ;; components.
11280 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11281 #t))))
11282 (build-system gnu-build-system)
11283 (arguments
11284 `( ;; There is no global test target and the test target for
11285 ;; individual tools depends on input files that are not
11286 ;; included.
11287 #:tests? #f
11288 #:phases
11289 (modify-phases %standard-phases
11290 (add-after 'unpack 'fix-paths
11291 (lambda _
11292 (substitute* "Makefile"
11293 (("/bin/echo") (which "echo")))
11294 #t))
11295 (add-after 'unpack 'prepare-samtabix
11296 (lambda* (#:key inputs #:allow-other-keys)
11297 (copy-recursively (assoc-ref inputs "samtabix")
11298 "samtabix")
11299 #t))
11300 (delete 'configure)
11301 (replace 'install
11302 (lambda* (#:key outputs #:allow-other-keys)
11303 (let ((bin (string-append (assoc-ref outputs "out")
11304 "/bin")))
11305 (copy-recursively "bin" bin))
11306 #t)))))
11307 (native-inputs
11308 `(("samtabix"
11309 ,(origin
11310 (method git-fetch)
11311 (uri (git-reference
11312 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11313 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11314 (sha256
11315 (base32
11316 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11317 (inputs
11318 `(("zlib" ,zlib)
11319 ("tcsh" ,tcsh)
11320 ("perl" ,perl)
11321 ("libpng" ,libpng)
11322 ("mysql" ,mysql)
11323 ("openssl" ,openssl)))
11324 (home-page "http://genome.cse.ucsc.edu/index.html")
11325 (synopsis "Assorted bioinformatics utilities")
11326 (description "This package provides the kentUtils, a selection of
11327 bioinformatics utilities used in combination with the UCSC genome
11328 browser.")
11329 ;; Only a subset of the sources are released under a non-copyleft
11330 ;; free software license. All other sources are removed in a
11331 ;; snippet. See this bug report for an explanation of how the
11332 ;; license statements apply:
11333 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11334 (license (license:non-copyleft
11335 "http://genome.ucsc.edu/license/"
11336 "The contents of this package are free for all uses."))))
11337
11338 (define-public f-seq
11339 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11340 (revision "1"))
11341 (package
11342 (name "f-seq")
11343 (version (string-append "1.1-" revision "." (string-take commit 7)))
11344 (source (origin
11345 (method git-fetch)
11346 (uri (git-reference
11347 (url "https://github.com/aboyle/F-seq.git")
11348 (commit commit)))
11349 (file-name (string-append name "-" version))
11350 (sha256
11351 (base32
11352 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11353 (modules '((guix build utils)))
11354 ;; Remove bundled Java library archives.
11355 (snippet
11356 '(begin
11357 (for-each delete-file (find-files "lib" ".*"))
11358 #t))))
11359 (build-system ant-build-system)
11360 (arguments
11361 `(#:tests? #f ; no tests included
11362 #:phases
11363 (modify-phases %standard-phases
11364 (replace 'install
11365 (lambda* (#:key inputs outputs #:allow-other-keys)
11366 (let* ((target (assoc-ref outputs "out"))
11367 (doc (string-append target "/share/doc/f-seq/")))
11368 (mkdir-p target)
11369 (mkdir-p doc)
11370 (substitute* "bin/linux/fseq"
11371 (("java") (which "java"))
11372 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11373 (string-append (assoc-ref inputs "java-commons-cli")
11374 "/share/java/commons-cli.jar"))
11375 (("REALDIR=.*")
11376 (string-append "REALDIR=" target "/bin\n")))
11377 (install-file "README.txt" doc)
11378 (install-file "bin/linux/fseq" (string-append target "/bin"))
11379 (install-file "build~/fseq.jar" (string-append target "/lib"))
11380 (copy-recursively "lib" (string-append target "/lib"))
11381 #t))))))
11382 (inputs
11383 `(("perl" ,perl)
11384 ("java-commons-cli" ,java-commons-cli)))
11385 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11386 (synopsis "Feature density estimator for high-throughput sequence tags")
11387 (description
11388 "F-Seq is a software package that generates a continuous tag sequence
11389 density estimation allowing identification of biologically meaningful sites
11390 such as transcription factor binding sites (ChIP-seq) or regions of open
11391 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11392 Browser.")
11393 (license license:gpl3+))))
11394
11395 (define-public bismark
11396 (package
11397 (name "bismark")
11398 (version "0.16.3")
11399 (source
11400 (origin
11401 (method url-fetch)
11402 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
11403 "archive/" version ".tar.gz"))
11404 (file-name (string-append name "-" version ".tar.gz"))
11405 (sha256
11406 (base32
11407 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
11408 (build-system perl-build-system)
11409 (arguments
11410 `(#:tests? #f ; there are no tests
11411 #:phases
11412 (modify-phases %standard-phases
11413 (delete 'configure)
11414 (delete 'build)
11415 (replace 'install
11416 (lambda* (#:key outputs #:allow-other-keys)
11417 (let ((bin (string-append (assoc-ref outputs "out")
11418 "/bin"))
11419 (docdir (string-append (assoc-ref outputs "out")
11420 "/share/doc/bismark"))
11421 (docs '("Bismark_User_Guide.pdf"
11422 "RELEASE_NOTES.txt"))
11423 (scripts '("bismark"
11424 "bismark_genome_preparation"
11425 "bismark_methylation_extractor"
11426 "bismark2bedGraph"
11427 "bismark2report"
11428 "coverage2cytosine"
11429 "deduplicate_bismark"
11430 "bismark_sitrep.tpl"
11431 "bam2nuc"
11432 "bismark2summary")))
11433 (mkdir-p docdir)
11434 (mkdir-p bin)
11435 (for-each (lambda (file) (install-file file bin))
11436 scripts)
11437 (for-each (lambda (file) (install-file file docdir))
11438 docs)
11439 #t))))))
11440 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11441 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11442 (description "Bismark is a program to map bisulfite treated sequencing
11443 reads to a genome of interest and perform methylation calls in a single step.
11444 The output can be easily imported into a genome viewer, such as SeqMonk, and
11445 enables a researcher to analyse the methylation levels of their samples
11446 straight away. Its main features are:
11447
11448 @itemize
11449 @item Bisulfite mapping and methylation calling in one single step
11450 @item Supports single-end and paired-end read alignments
11451 @item Supports ungapped and gapped alignments
11452 @item Alignment seed length, number of mismatches etc are adjustable
11453 @item Output discriminates between cytosine methylation in CpG, CHG
11454 and CHH context
11455 @end itemize\n")
11456 (license license:gpl3+)))
11457
11458 (define-public paml
11459 (package
11460 (name "paml")
11461 (version "4.9e")
11462 (source (origin
11463 (method url-fetch)
11464 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11465 "paml" version ".tgz"))
11466 (sha256
11467 (base32
11468 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11469 (modules '((guix build utils)))
11470 ;; Remove Windows binaries
11471 (snippet
11472 '(begin
11473 (for-each delete-file (find-files "." "\\.exe$"))
11474 #t))))
11475 (build-system gnu-build-system)
11476 (arguments
11477 `(#:tests? #f ; there are no tests
11478 #:make-flags '("CC=gcc")
11479 #:phases
11480 (modify-phases %standard-phases
11481 (replace 'configure
11482 (lambda _
11483 (substitute* "src/BFdriver.c"
11484 (("/bin/bash") (which "bash")))
11485 (chdir "src")
11486 #t))
11487 (replace 'install
11488 (lambda* (#:key outputs #:allow-other-keys)
11489 (let ((tools '("baseml" "basemlg" "codeml"
11490 "pamp" "evolver" "yn00" "chi2"))
11491 (bin (string-append (assoc-ref outputs "out") "/bin"))
11492 (docdir (string-append (assoc-ref outputs "out")
11493 "/share/doc/paml")))
11494 (mkdir-p bin)
11495 (for-each (lambda (file) (install-file file bin)) tools)
11496 (copy-recursively "../doc" docdir)
11497 #t))))))
11498 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11499 (synopsis "Phylogentic analysis by maximum likelihood")
11500 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11501 contains a few programs for model fitting and phylogenetic tree reconstruction
11502 using nucleotide or amino-acid sequence data.")
11503 ;; GPLv3 only
11504 (license license:gpl3)))
11505
11506 (define-public kallisto
11507 (package
11508 (name "kallisto")
11509 (version "0.43.1")
11510 (source (origin
11511 (method url-fetch)
11512 (uri (string-append "https://github.com/pachterlab/"
11513 "kallisto/archive/v" version ".tar.gz"))
11514 (file-name (string-append name "-" version ".tar.gz"))
11515 (sha256
11516 (base32
11517 "03j3iqhvq7ya3c91gidly3k3jvgm97vjq4scihrlxh315j696r11"))))
11518 (build-system cmake-build-system)
11519 (arguments `(#:tests? #f)) ; no "check" target
11520 (inputs
11521 `(("hdf5" ,hdf5)
11522 ("zlib" ,zlib)))
11523 (home-page "http://pachterlab.github.io/kallisto/")
11524 (synopsis "Near-optimal RNA-Seq quantification")
11525 (description
11526 "Kallisto is a program for quantifying abundances of transcripts from
11527 RNA-Seq data, or more generally of target sequences using high-throughput
11528 sequencing reads. It is based on the novel idea of pseudoalignment for
11529 rapidly determining the compatibility of reads with targets, without the need
11530 for alignment. Pseudoalignment of reads preserves the key information needed
11531 for quantification, and kallisto is therefore not only fast, but also as
11532 accurate as existing quantification tools.")
11533 (license license:bsd-2)))
11534
11535 (define-public libgff
11536 (package
11537 (name "libgff")
11538 (version "1.0")
11539 (source (origin
11540 (method url-fetch)
11541 (uri (string-append
11542 "https://github.com/Kingsford-Group/"
11543 "libgff/archive/v" version ".tar.gz"))
11544 (file-name (string-append name "-" version ".tar.gz"))
11545 (sha256
11546 (base32
11547 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11548 (build-system cmake-build-system)
11549 (arguments `(#:tests? #f)) ; no tests included
11550 (home-page "https://github.com/Kingsford-Group/libgff")
11551 (synopsis "Parser library for reading/writing GFF files")
11552 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11553 code that is used in the Cufflinks codebase. The goal of this library is to
11554 provide this functionality without the necessity of drawing in a heavy-weight
11555 dependency like SeqAn.")
11556 (license (license:x11-style "http://www.boost.org/LICENSE_1_0.txt"))))
11557
11558 (define-public libdivsufsort
11559 (package
11560 (name "libdivsufsort")
11561 (version "2.0.1")
11562 (source (origin
11563 (method git-fetch)
11564 (uri (git-reference
11565 (url "https://github.com/y-256/libdivsufsort.git")
11566 (commit version)))
11567 (sha256
11568 (base32
11569 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11570 (build-system cmake-build-system)
11571 (arguments
11572 '(#:tests? #f ; there are no tests
11573 #:configure-flags
11574 ;; Needed for rapmap and sailfish.
11575 '("-DBUILD_DIVSUFSORT64=ON")))
11576 (home-page "https://github.com/y-256/libdivsufsort")
11577 (synopsis "Lightweight suffix-sorting library")
11578 (description "libdivsufsort is a software library that implements a
11579 lightweight suffix array construction algorithm. This library provides a
11580 simple and an efficient C API to construct a suffix array and a
11581 Burrows-Wheeler transformed string from a given string over a constant-size
11582 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11583 bytes of memory space, where n is the length of the string.")
11584 (license license:expat)))
11585
11586 (define-public sailfish
11587 (package
11588 (name "sailfish")
11589 (version "0.10.1")
11590 (source (origin
11591 (method url-fetch)
11592 (uri
11593 (string-append "https://github.com/kingsfordgroup/"
11594 "sailfish/archive/v" version ".tar.gz"))
11595 (file-name (string-append name "-" version ".tar.gz"))
11596 (sha256
11597 (base32
11598 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11599 (modules '((guix build utils)))
11600 (snippet
11601 '(begin
11602 ;; Delete bundled headers for eigen3.
11603 (delete-file-recursively "include/eigen3/")
11604 #t))))
11605 (build-system cmake-build-system)
11606 (arguments
11607 `(#:configure-flags
11608 (list (string-append "-DBOOST_INCLUDEDIR="
11609 (assoc-ref %build-inputs "boost")
11610 "/include/")
11611 (string-append "-DBOOST_LIBRARYDIR="
11612 (assoc-ref %build-inputs "boost")
11613 "/lib/")
11614 (string-append "-DBoost_LIBRARIES="
11615 "-lboost_iostreams "
11616 "-lboost_filesystem "
11617 "-lboost_system "
11618 "-lboost_thread "
11619 "-lboost_timer "
11620 "-lboost_chrono "
11621 "-lboost_program_options")
11622 "-DBoost_FOUND=TRUE"
11623 ;; Don't download RapMap---we already have it!
11624 "-DFETCHED_RAPMAP=1")
11625 ;; Tests must be run after installation and the location of the test
11626 ;; data file must be overridden. But the tests fail. It looks like
11627 ;; they are not really meant to be run.
11628 #:tests? #f
11629 #:phases
11630 (modify-phases %standard-phases
11631 ;; Boost cannot be found, even though it's right there.
11632 (add-after 'unpack 'do-not-look-for-boost
11633 (lambda* (#:key inputs #:allow-other-keys)
11634 (substitute* "CMakeLists.txt"
11635 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11636 (add-after 'unpack 'do-not-assign-to-macro
11637 (lambda _
11638 (substitute* "include/spdlog/details/format.cc"
11639 (("const unsigned CHAR_WIDTH = 1;") ""))))
11640 (add-after 'unpack 'prepare-rapmap
11641 (lambda* (#:key inputs #:allow-other-keys)
11642 (let ((src "external/install/src/rapmap/")
11643 (include "external/install/include/rapmap/")
11644 (rapmap (assoc-ref inputs "rapmap")))
11645 (mkdir-p "/tmp/rapmap")
11646 (system* "tar" "xf"
11647 (assoc-ref inputs "rapmap")
11648 "-C" "/tmp/rapmap"
11649 "--strip-components=1")
11650 (mkdir-p src)
11651 (mkdir-p include)
11652 (for-each (lambda (file)
11653 (install-file file src))
11654 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11655 (copy-recursively "/tmp/rapmap/include" include))))
11656 (add-after 'unpack 'use-system-libraries
11657 (lambda* (#:key inputs #:allow-other-keys)
11658 (substitute* '("src/SailfishIndexer.cpp"
11659 "src/SailfishUtils.cpp"
11660 "src/SailfishQuantify.cpp"
11661 "src/FASTAParser.cpp"
11662 "include/PCA.hpp"
11663 "include/SailfishUtils.hpp"
11664 "include/SailfishIndex.hpp"
11665 "include/CollapsedEMOptimizer.hpp"
11666 "src/CollapsedEMOptimizer.cpp")
11667 (("#include \"jellyfish/config.h\"") ""))
11668 (substitute* "src/CMakeLists.txt"
11669 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11670 (string-append (assoc-ref inputs "jellyfish")
11671 "/include/jellyfish-" ,(package-version jellyfish)))
11672 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11673 (string-append (assoc-ref inputs "jellyfish")
11674 "/lib/libjellyfish-2.0.a"))
11675 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11676 (string-append (assoc-ref inputs "libdivsufsort")
11677 "/lib/libdivsufsort.so"))
11678 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11679 (string-append (assoc-ref inputs "libdivsufsort")
11680 "/lib/libdivsufsort64.so")))
11681 (substitute* "CMakeLists.txt"
11682 ;; Don't prefer static libs
11683 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11684 (("find_package\\(Jellyfish.*") "")
11685 (("ExternalProject_Add\\(libjellyfish") "message(")
11686 (("ExternalProject_Add\\(libgff") "message(")
11687 (("ExternalProject_Add\\(libsparsehash") "message(")
11688 (("ExternalProject_Add\\(libdivsufsort") "message("))
11689
11690 ;; Ensure that Eigen headers can be found
11691 (setenv "CPLUS_INCLUDE_PATH"
11692 (string-append (getenv "CPLUS_INCLUDE_PATH")
11693 ":"
11694 (assoc-ref inputs "eigen")
11695 "/include/eigen3")))))))
11696 (inputs
11697 `(("boost" ,boost)
11698 ("eigen" ,eigen)
11699 ("jemalloc" ,jemalloc)
11700 ("jellyfish" ,jellyfish)
11701 ("sparsehash" ,sparsehash)
11702 ("rapmap" ,(origin
11703 (method git-fetch)
11704 (uri (git-reference
11705 (url "https://github.com/COMBINE-lab/RapMap.git")
11706 (commit (string-append "sf-v" version))))
11707 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11708 (sha256
11709 (base32
11710 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11711 (modules '((guix build utils)))
11712 ;; These files are expected to be excluded.
11713 (snippet
11714 '(begin (delete-file-recursively "include/spdlog")
11715 (for-each delete-file '("include/xxhash.h"
11716 "src/xxhash.c"))))))
11717 ("libdivsufsort" ,libdivsufsort)
11718 ("libgff" ,libgff)
11719 ("tbb" ,tbb)
11720 ("zlib" ,zlib)))
11721 (native-inputs
11722 `(("pkg-config" ,pkg-config)))
11723 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11724 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11725 (description "Sailfish is a tool for genomic transcript quantification
11726 from RNA-seq data. It requires a set of target transcripts (either from a
11727 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11728 fasta file containing your reference transcripts and a (set of) fasta/fastq
11729 file(s) containing your reads.")
11730 (license license:gpl3+)))
11731
11732 (define libstadenio-for-salmon
11733 (package
11734 (name "libstadenio")
11735 (version "1.14.8")
11736 (source (origin
11737 (method git-fetch)
11738 (uri (git-reference
11739 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11740 (commit (string-append "v" version))))
11741 (file-name (string-append name "-" version "-checkout"))
11742 (sha256
11743 (base32
11744 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11745 (build-system gnu-build-system)
11746 (arguments '(#:parallel-tests? #f)) ; not supported
11747 (inputs
11748 `(("zlib" ,zlib)))
11749 (native-inputs
11750 `(("perl" ,perl))) ; for tests
11751 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11752 (synopsis "General purpose trace and experiment file library")
11753 (description "This package provides a library of file reading and writing
11754 code to provide a general purpose Trace file (and Experiment File) reading
11755 interface.
11756
11757 The following file formats are supported:
11758
11759 @enumerate
11760 @item SCF trace files
11761 @item ABI trace files
11762 @item ALF trace files
11763 @item ZTR trace files
11764 @item SFF trace archives
11765 @item SRF trace archives
11766 @item Experiment files
11767 @item Plain text files
11768 @item SAM/BAM sequence files
11769 @item CRAM sequence files
11770 @end enumerate\n")
11771 (license license:bsd-3)))
11772
11773 (define spdlog-for-salmon
11774 (package
11775 (name "spdlog")
11776 (version "0.14.0")
11777 (source (origin
11778 (method git-fetch)
11779 (uri (git-reference
11780 (url "https://github.com/COMBINE-lab/spdlog.git")
11781 (commit (string-append "v" version))))
11782 (file-name (string-append name "-" version "-checkout"))
11783 (sha256
11784 (base32
11785 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11786 (build-system cmake-build-system)
11787 (home-page "https://github.com/COMBINE-lab/spdlog")
11788 (synopsis "Very fast C++ logging library")
11789 (description "Spdlog is a very fast header-only C++ logging library with
11790 performance as its primary goal.")
11791 (license license:expat)))
11792
11793 ;; This is a modified variant of bwa for use with Salmon. It installs a
11794 ;; library to avoid having to build this as part of Salmon.
11795 (define bwa-for-salmon
11796 (package (inherit bwa)
11797 (name "bwa")
11798 (version "0.7.12.5")
11799 (source (origin
11800 (method git-fetch)
11801 (uri (git-reference
11802 (url "https://github.com/COMBINE-lab/bwa.git")
11803 (commit (string-append "v" version))))
11804 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11805 (sha256
11806 (base32
11807 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11808 (build-system gnu-build-system)
11809 (arguments
11810 '(#:tests? #f ;no "check" target
11811 #:phases
11812 (modify-phases %standard-phases
11813 (replace 'install
11814 (lambda* (#:key outputs #:allow-other-keys)
11815 (let* ((out (assoc-ref outputs "out"))
11816 (bin (string-append out "/bin"))
11817 (lib (string-append out "/lib"))
11818 (doc (string-append out "/share/doc/bwa"))
11819 (man (string-append out "/share/man/man1"))
11820 (inc (string-append out "/include/bwa")))
11821 (install-file "bwa" bin)
11822 (install-file "README.md" doc)
11823 (install-file "bwa.1" man)
11824 (install-file "libbwa.a" lib)
11825 (mkdir-p lib)
11826 (mkdir-p inc)
11827 (for-each (lambda (file)
11828 (install-file file inc))
11829 (find-files "." "\\.h$")))
11830 #t))
11831 ;; no "configure" script
11832 (delete 'configure))))))
11833
11834 (define-public salmon
11835 (package
11836 (name "salmon")
11837 (version "0.9.1")
11838 (source (origin
11839 (method git-fetch)
11840 (uri (git-reference
11841 (url "https://github.com/COMBINE-lab/salmon.git")
11842 (commit (string-append "v" version))))
11843 (file-name (string-append name "-" version "-checkout"))
11844 (sha256
11845 (base32
11846 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11847 (modules '((guix build utils)))
11848 (snippet
11849 '(begin
11850 ;; Delete bundled headers for eigen3.
11851 (delete-file-recursively "include/eigen3/")
11852 #t))))
11853 (build-system cmake-build-system)
11854 (arguments
11855 `(#:configure-flags
11856 (list (string-append "-DBOOST_INCLUDEDIR="
11857 (assoc-ref %build-inputs "boost")
11858 "/include/")
11859 (string-append "-DBOOST_LIBRARYDIR="
11860 (assoc-ref %build-inputs "boost")
11861 "/lib/")
11862 (string-append "-DBoost_LIBRARIES="
11863 "-lboost_iostreams "
11864 "-lboost_filesystem "
11865 "-lboost_system "
11866 "-lboost_thread "
11867 "-lboost_timer "
11868 "-lboost_chrono "
11869 "-lboost_program_options")
11870 "-DBoost_FOUND=TRUE"
11871 "-DTBB_LIBRARIES=tbb tbbmalloc"
11872 ;; Don't download RapMap---we already have it!
11873 "-DFETCHED_RAPMAP=1")
11874 #:phases
11875 (modify-phases %standard-phases
11876 ;; Boost cannot be found, even though it's right there.
11877 (add-after 'unpack 'do-not-look-for-boost
11878 (lambda* (#:key inputs #:allow-other-keys)
11879 (substitute* "CMakeLists.txt"
11880 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11881 (add-after 'unpack 'do-not-phone-home
11882 (lambda _
11883 (substitute* "src/Salmon.cpp"
11884 (("getVersionMessage\\(\\)") "\"\""))))
11885 (add-after 'unpack 'prepare-rapmap
11886 (lambda* (#:key inputs #:allow-other-keys)
11887 (let ((src "external/install/src/rapmap/")
11888 (include "external/install/include/rapmap/")
11889 (rapmap (assoc-ref inputs "rapmap")))
11890 (mkdir-p src)
11891 (mkdir-p include)
11892 (for-each (lambda (file)
11893 (install-file file src))
11894 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
11895 (copy-recursively (string-append rapmap "/include") include)
11896 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11897 "external/install/include/rapmap/FastxParser.hpp"
11898 "external/install/include/rapmap/concurrentqueue.h"
11899 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11900 "external/install/src/rapmap/FastxParser.cpp"
11901 "external/install/src/rapmap/xxhash.c")))))
11902 (add-after 'unpack 'use-system-libraries
11903 (lambda* (#:key inputs #:allow-other-keys)
11904 (substitute* "src/CMakeLists.txt"
11905 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11906 (string-append (assoc-ref inputs "jellyfish")
11907 "/include/jellyfish-" ,(package-version jellyfish)))
11908 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11909 (string-append (assoc-ref inputs "jellyfish")
11910 "/lib/libjellyfish-2.0.a"))
11911 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11912 (string-append (assoc-ref inputs "libdivsufsort")
11913 "/lib/libdivsufsort.so"))
11914 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11915 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11916 "/lib/libstaden-read.a"))
11917 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
11918 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
11919 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11920 (string-append (assoc-ref inputs "libdivsufsort")
11921 "/lib/libdivsufsort64.so")))
11922 (substitute* "CMakeLists.txt"
11923 ;; Don't prefer static libs
11924 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11925 (("set\\(TBB_LIBRARIES") "message(")
11926 (("find_package\\(Jellyfish.*") "")
11927 (("ExternalProject_Add\\(libcereal") "message(")
11928 (("ExternalProject_Add\\(libbwa") "message(")
11929 (("ExternalProject_Add\\(libjellyfish") "message(")
11930 (("ExternalProject_Add\\(libgff") "message(")
11931 (("ExternalProject_Add\\(libtbb") "message(")
11932 (("ExternalProject_Add\\(libspdlog") "message(")
11933 (("ExternalProject_Add\\(libdivsufsort") "message(")
11934 (("ExternalProject_Add\\(libstadenio") "message(")
11935 (("ExternalProject_Add_Step\\(") "message("))
11936
11937 ;; Ensure that all headers can be found
11938 (setenv "CPLUS_INCLUDE_PATH"
11939 (string-append (getenv "CPLUS_INCLUDE_PATH")
11940 ":"
11941 (assoc-ref inputs "bwa")
11942 "/include/bwa"
11943 ":"
11944 (assoc-ref inputs "eigen")
11945 "/include/eigen3"))
11946 (setenv "CPATH"
11947 (string-append (assoc-ref inputs "bwa")
11948 "/include/bwa"
11949 ":"
11950 (assoc-ref inputs "eigen")
11951 "/include/eigen3"))
11952 #t))
11953 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11954 ;; run. It only exists after the install phase.
11955 (add-after 'unpack 'fix-tests
11956 (lambda _
11957 (substitute* "src/CMakeLists.txt"
11958 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11959 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11960 #t)))))
11961 (inputs
11962 `(("boost" ,boost)
11963 ("bwa" ,bwa-for-salmon)
11964 ("bzip2" ,bzip2)
11965 ("cereal" ,cereal)
11966 ("eigen" ,eigen)
11967 ("rapmap" ,(origin
11968 (method git-fetch)
11969 (uri (git-reference
11970 (url "https://github.com/COMBINE-lab/RapMap.git")
11971 (commit (string-append "salmon-v" version))))
11972 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11973 (sha256
11974 (base32
11975 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
11976 ("jemalloc" ,jemalloc)
11977 ("jellyfish" ,jellyfish)
11978 ("libgff" ,libgff)
11979 ("tbb" ,tbb)
11980 ("libdivsufsort" ,libdivsufsort)
11981 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11982 ("spdlog-for-salmon" ,spdlog-for-salmon)
11983 ("xz" ,xz)
11984 ("zlib" ,zlib)))
11985 (home-page "https://github.com/COMBINE-lab/salmon")
11986 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11987 (description "Salmon is a program to produce highly-accurate,
11988 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11989 its accuracy and speed via a number of different innovations, including the
11990 use of lightweight alignments (accurate but fast-to-compute proxies for
11991 traditional read alignments) and massively-parallel stochastic collapsed
11992 variational inference.")
11993 (license license:gpl3+)))
11994
11995 (define-public python-loompy
11996 (package
11997 (name "python-loompy")
11998 (version "2.0.2")
11999 (source
12000 (origin
12001 (method url-fetch)
12002 (uri (pypi-uri "loompy" version))
12003 (sha256
12004 (base32
12005 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12006 (build-system python-build-system)
12007 ;; There are no tests
12008 (arguments '(#:tests? #f))
12009 (propagated-inputs
12010 `(("python-h5py" ,python-h5py)
12011 ("python-numpy" ,python-numpy)
12012 ("python-scipy" ,python-scipy)
12013 ("python-typing" ,python-typing)))
12014 (home-page "https://github.com/linnarsson-lab/loompy")
12015 (synopsis "Work with .loom files for single-cell RNA-seq data")
12016 (description "The loom file format is an efficient format for very large
12017 omics datasets, consisting of a main matrix, optional additional layers, a
12018 variable number of row and column annotations. Loom also supports sparse
12019 graphs. This library makes it easy to work with @file{.loom} files for
12020 single-cell RNA-seq data.")
12021 (license license:bsd-3)))
12022
12023 ;; We cannot use the latest commit because it requires Java 9.
12024 (define-public java-forester
12025 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12026 (revision "1"))
12027 (package
12028 (name "java-forester")
12029 (version (string-append "0-" revision "." (string-take commit 7)))
12030 (source (origin
12031 (method git-fetch)
12032 (uri (git-reference
12033 (url "https://github.com/cmzmasek/forester.git")
12034 (commit commit)))
12035 (file-name (string-append name "-" version "-checkout"))
12036 (sha256
12037 (base32
12038 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12039 (modules '((guix build utils)))
12040 (snippet
12041 '(begin
12042 ;; Delete bundled jars and pre-built classes
12043 (delete-file-recursively "forester/java/resources")
12044 (delete-file-recursively "forester/java/classes")
12045 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12046 ;; Delete bundled applications
12047 (delete-file-recursively "forester_applications")
12048 #t))))
12049 (build-system ant-build-system)
12050 (arguments
12051 `(#:tests? #f ; there are none
12052 #:jdk ,icedtea-8
12053 #:modules ((guix build ant-build-system)
12054 (guix build utils)
12055 (guix build java-utils)
12056 (sxml simple)
12057 (sxml transform))
12058 #:phases
12059 (modify-phases %standard-phases
12060 (add-after 'unpack 'chdir
12061 (lambda _ (chdir "forester/java") #t))
12062 (add-after 'chdir 'fix-dependencies
12063 (lambda _
12064 (chmod "build.xml" #o664)
12065 (call-with-output-file "build.xml.new"
12066 (lambda (port)
12067 (sxml->xml
12068 (pre-post-order
12069 (with-input-from-file "build.xml"
12070 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12071 `(;; Remove all unjar tags to avoid repacking classes.
12072 (unjar . ,(lambda _ '()))
12073 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12074 (*text* . ,(lambda (_ txt) txt))))
12075 port)))
12076 (rename-file "build.xml.new" "build.xml")
12077 #t))
12078 ;; FIXME: itext is difficult to package as it depends on a few
12079 ;; unpackaged libraries.
12080 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12081 (lambda _
12082 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12083 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12084 (("pdf_written_to = PdfExporter.*")
12085 "throw new IOException(\"PDF export is not available.\");"))
12086 #t))
12087 ;; There is no install target
12088 (replace 'install (install-jars ".")))))
12089 (propagated-inputs
12090 `(("java-commons-codec" ,java-commons-codec)
12091 ("java-openchart2" ,java-openchart2)))
12092 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12093 (synopsis "Phylogenomics libraries for Java")
12094 (description "Forester is a collection of Java libraries for
12095 phylogenomics and evolutionary biology research. It includes support for
12096 reading, writing, and exporting phylogenetic trees.")
12097 (license license:lgpl2.1+))))
12098
12099 (define-public java-forester-1.005
12100 (package
12101 (name "java-forester")
12102 (version "1.005")
12103 (source (origin
12104 (method url-fetch)
12105 (uri (string-append "http://search.maven.org/remotecontent?"
12106 "filepath=org/biojava/thirdparty/forester/"
12107 version "/forester-" version "-sources.jar"))
12108 (file-name (string-append name "-" version ".jar"))
12109 (sha256
12110 (base32
12111 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12112 (build-system ant-build-system)
12113 (arguments
12114 `(#:tests? #f ; there are none
12115 #:jdk ,icedtea-8
12116 #:modules ((guix build ant-build-system)
12117 (guix build utils)
12118 (guix build java-utils)
12119 (sxml simple)
12120 (sxml transform))
12121 #:phases
12122 (modify-phases %standard-phases
12123 (add-after 'unpack 'fix-dependencies
12124 (lambda* (#:key inputs #:allow-other-keys)
12125 (call-with-output-file "build.xml"
12126 (lambda (port)
12127 (sxml->xml
12128 (pre-post-order
12129 (with-input-from-file "src/build.xml"
12130 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12131 `(;; Remove all unjar tags to avoid repacking classes.
12132 (unjar . ,(lambda _ '()))
12133 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12134 (*text* . ,(lambda (_ txt) txt))))
12135 port)))
12136 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12137 "synth_look_and_feel_1.xml")
12138 (copy-file (assoc-ref inputs "phyloxml.xsd")
12139 "phyloxml.xsd")
12140 (substitute* "build.xml"
12141 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12142 "synth_look_and_feel_1.xml")
12143 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12144 "phyloxml.xsd"))
12145 #t))
12146 ;; FIXME: itext is difficult to package as it depends on a few
12147 ;; unpackaged libraries.
12148 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12149 (lambda _
12150 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12151 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12152 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12153 (("pdf_written_to = PdfExporter.*")
12154 "throw new IOException(\"PDF export is not available.\"); /*")
12155 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12156 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12157 #t))
12158 (add-after 'unpack 'delete-pre-built-classes
12159 (lambda _ (delete-file-recursively "src/classes") #t))
12160 ;; There is no install target
12161 (replace 'install (install-jars ".")))))
12162 (propagated-inputs
12163 `(("java-commons-codec" ,java-commons-codec)
12164 ("java-openchart2" ,java-openchart2)))
12165 ;; The source archive does not contain the resources.
12166 (native-inputs
12167 `(("phyloxml.xsd"
12168 ,(origin
12169 (method url-fetch)
12170 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12171 "b61cc2dcede0bede317db362472333115756b8c6/"
12172 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12173 (file-name (string-append name "-phyloxml-" version ".xsd"))
12174 (sha256
12175 (base32
12176 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12177 ("synth_look_and_feel_1.xml"
12178 ,(origin
12179 (method url-fetch)
12180 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12181 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12182 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12183 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12184 (sha256
12185 (base32
12186 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12187 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12188 (synopsis "Phylogenomics libraries for Java")
12189 (description "Forester is a collection of Java libraries for
12190 phylogenomics and evolutionary biology research. It includes support for
12191 reading, writing, and exporting phylogenetic trees.")
12192 (license license:lgpl2.1+)))
12193
12194 (define-public java-biojava-core
12195 (package
12196 (name "java-biojava-core")
12197 (version "4.2.11")
12198 (source (origin
12199 (method git-fetch)
12200 (uri (git-reference
12201 (url "https://github.com/biojava/biojava")
12202 (commit (string-append "biojava-" version))))
12203 (file-name (string-append name "-" version "-checkout"))
12204 (sha256
12205 (base32
12206 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12207 (build-system ant-build-system)
12208 (arguments
12209 `(#:jdk ,icedtea-8
12210 #:jar-name "biojava-core.jar"
12211 #:source-dir "biojava-core/src/main/java/"
12212 #:test-dir "biojava-core/src/test"
12213 ;; These tests seem to require internet access.
12214 #:test-exclude (list "**/SearchIOTest.java"
12215 "**/BlastXMLParserTest.java"
12216 "**/GenbankCookbookTest.java"
12217 "**/GenbankProxySequenceReaderTest.java")
12218 #:phases
12219 (modify-phases %standard-phases
12220 (add-before 'build 'copy-resources
12221 (lambda _
12222 (copy-recursively "biojava-core/src/main/resources"
12223 "build/classes")
12224 #t))
12225 (add-before 'check 'copy-test-resources
12226 (lambda _
12227 (copy-recursively "biojava-core/src/test/resources"
12228 "build/test-classes")
12229 #t)))))
12230 (propagated-inputs
12231 `(("java-log4j-api" ,java-log4j-api)
12232 ("java-log4j-core" ,java-log4j-core)
12233 ("java-slf4j-api" ,java-slf4j-api)
12234 ("java-slf4j-simple" ,java-slf4j-simple)))
12235 (native-inputs
12236 `(("java-junit" ,java-junit)
12237 ("java-hamcrest-core" ,java-hamcrest-core)))
12238 (home-page "http://biojava.org")
12239 (synopsis "Core libraries of Java framework for processing biological data")
12240 (description "BioJava is a project dedicated to providing a Java framework
12241 for processing biological data. It provides analytical and statistical
12242 routines, parsers for common file formats, reference implementations of
12243 popular algorithms, and allows the manipulation of sequences and 3D
12244 structures. The goal of the biojava project is to facilitate rapid
12245 application development for bioinformatics.
12246
12247 This package provides the core libraries.")
12248 (license license:lgpl2.1+)))
12249
12250 (define-public java-biojava-phylo
12251 (package (inherit java-biojava-core)
12252 (name "java-biojava-phylo")
12253 (build-system ant-build-system)
12254 (arguments
12255 `(#:jdk ,icedtea-8
12256 #:jar-name "biojava-phylo.jar"
12257 #:source-dir "biojava-phylo/src/main/java/"
12258 #:test-dir "biojava-phylo/src/test"
12259 #:phases
12260 (modify-phases %standard-phases
12261 (add-before 'build 'copy-resources
12262 (lambda _
12263 (copy-recursively "biojava-phylo/src/main/resources"
12264 "build/classes")
12265 #t))
12266 (add-before 'check 'copy-test-resources
12267 (lambda _
12268 (copy-recursively "biojava-phylo/src/test/resources"
12269 "build/test-classes")
12270 #t)))))
12271 (propagated-inputs
12272 `(("java-log4j-api" ,java-log4j-api)
12273 ("java-log4j-core" ,java-log4j-core)
12274 ("java-slf4j-api" ,java-slf4j-api)
12275 ("java-slf4j-simple" ,java-slf4j-simple)
12276 ("java-biojava-core" ,java-biojava-core)
12277 ("java-forester" ,java-forester)))
12278 (native-inputs
12279 `(("java-junit" ,java-junit)
12280 ("java-hamcrest-core" ,java-hamcrest-core)))
12281 (home-page "http://biojava.org")
12282 (synopsis "Biojava interface to the forester phylogenomics library")
12283 (description "The phylo module provides a biojava interface layer to the
12284 forester phylogenomics library for constructing phylogenetic trees.")))
12285
12286 (define-public java-biojava-alignment
12287 (package (inherit java-biojava-core)
12288 (name "java-biojava-alignment")
12289 (build-system ant-build-system)
12290 (arguments
12291 `(#:jdk ,icedtea-8
12292 #:jar-name "biojava-alignment.jar"
12293 #:source-dir "biojava-alignment/src/main/java/"
12294 #:test-dir "biojava-alignment/src/test"
12295 #:phases
12296 (modify-phases %standard-phases
12297 (add-before 'build 'copy-resources
12298 (lambda _
12299 (copy-recursively "biojava-alignment/src/main/resources"
12300 "build/classes")
12301 #t))
12302 (add-before 'check 'copy-test-resources
12303 (lambda _
12304 (copy-recursively "biojava-alignment/src/test/resources"
12305 "build/test-classes")
12306 #t)))))
12307 (propagated-inputs
12308 `(("java-log4j-api" ,java-log4j-api)
12309 ("java-log4j-core" ,java-log4j-core)
12310 ("java-slf4j-api" ,java-slf4j-api)
12311 ("java-slf4j-simple" ,java-slf4j-simple)
12312 ("java-biojava-core" ,java-biojava-core)
12313 ("java-biojava-phylo" ,java-biojava-phylo)
12314 ("java-forester" ,java-forester)))
12315 (native-inputs
12316 `(("java-junit" ,java-junit)
12317 ("java-hamcrest-core" ,java-hamcrest-core)))
12318 (home-page "http://biojava.org")
12319 (synopsis "Biojava API for genetic sequence alignment")
12320 (description "The alignment module of BioJava provides an API that
12321 contains
12322
12323 @itemize
12324 @item implementations of dynamic programming algorithms for sequence
12325 alignment;
12326 @item reading and writing of popular alignment file formats;
12327 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12328 @end itemize\n")))
12329
12330 (define-public java-biojava-core-4.0
12331 (package (inherit java-biojava-core)
12332 (name "java-biojava-core")
12333 (version "4.0.0")
12334 (source (origin
12335 (method git-fetch)
12336 (uri (git-reference
12337 (url "https://github.com/biojava/biojava")
12338 (commit (string-append "biojava-" version))))
12339 (file-name (string-append name "-" version "-checkout"))
12340 (sha256
12341 (base32
12342 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12343
12344 (define-public java-biojava-phylo-4.0
12345 (package (inherit java-biojava-core-4.0)
12346 (name "java-biojava-phylo")
12347 (build-system ant-build-system)
12348 (arguments
12349 `(#:jdk ,icedtea-8
12350 #:jar-name "biojava-phylo.jar"
12351 #:source-dir "biojava-phylo/src/main/java/"
12352 #:test-dir "biojava-phylo/src/test"
12353 #:phases
12354 (modify-phases %standard-phases
12355 (add-before 'build 'copy-resources
12356 (lambda _
12357 (copy-recursively "biojava-phylo/src/main/resources"
12358 "build/classes")
12359 #t))
12360 (add-before 'check 'copy-test-resources
12361 (lambda _
12362 (copy-recursively "biojava-phylo/src/test/resources"
12363 "build/test-classes")
12364 #t)))))
12365 (propagated-inputs
12366 `(("java-log4j-api" ,java-log4j-api)
12367 ("java-log4j-core" ,java-log4j-core)
12368 ("java-slf4j-api" ,java-slf4j-api)
12369 ("java-slf4j-simple" ,java-slf4j-simple)
12370 ("java-biojava-core" ,java-biojava-core-4.0)
12371 ("java-forester" ,java-forester-1.005)))
12372 (native-inputs
12373 `(("java-junit" ,java-junit)
12374 ("java-hamcrest-core" ,java-hamcrest-core)))
12375 (home-page "http://biojava.org")
12376 (synopsis "Biojava interface to the forester phylogenomics library")
12377 (description "The phylo module provides a biojava interface layer to the
12378 forester phylogenomics library for constructing phylogenetic trees.")))
12379
12380 (define-public java-biojava-alignment-4.0
12381 (package (inherit java-biojava-core-4.0)
12382 (name "java-biojava-alignment")
12383 (build-system ant-build-system)
12384 (arguments
12385 `(#:jdk ,icedtea-8
12386 #:jar-name "biojava-alignment.jar"
12387 #:source-dir "biojava-alignment/src/main/java/"
12388 #:test-dir "biojava-alignment/src/test"
12389 #:phases
12390 (modify-phases %standard-phases
12391 (add-before 'build 'copy-resources
12392 (lambda _
12393 (copy-recursively "biojava-alignment/src/main/resources"
12394 "build/classes")
12395 #t))
12396 (add-before 'check 'copy-test-resources
12397 (lambda _
12398 (copy-recursively "biojava-alignment/src/test/resources"
12399 "build/test-classes")
12400 #t)))))
12401 (propagated-inputs
12402 `(("java-log4j-api" ,java-log4j-api)
12403 ("java-log4j-core" ,java-log4j-core)
12404 ("java-slf4j-api" ,java-slf4j-api)
12405 ("java-slf4j-simple" ,java-slf4j-simple)
12406 ("java-biojava-core" ,java-biojava-core-4.0)
12407 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12408 ("java-forester" ,java-forester-1.005)))
12409 (native-inputs
12410 `(("java-junit" ,java-junit)
12411 ("java-hamcrest-core" ,java-hamcrest-core)))
12412 (home-page "http://biojava.org")
12413 (synopsis "Biojava API for genetic sequence alignment")
12414 (description "The alignment module of BioJava provides an API that
12415 contains
12416
12417 @itemize
12418 @item implementations of dynamic programming algorithms for sequence
12419 alignment;
12420 @item reading and writing of popular alignment file formats;
12421 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12422 @end itemize\n")))