gnu: bedtools-2.18: Fetch sources from stable URL.
[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 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;;
16 ;;; This file is part of GNU Guix.
17 ;;;
18 ;;; GNU Guix is free software; you can redistribute it and/or modify it
19 ;;; under the terms of the GNU General Public License as published by
20 ;;; the Free Software Foundation; either version 3 of the License, or (at
21 ;;; your option) any later version.
22 ;;;
23 ;;; GNU Guix is distributed in the hope that it will be useful, but
24 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
25 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
26 ;;; GNU General Public License for more details.
27 ;;;
28 ;;; You should have received a copy of the GNU General Public License
29 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
30
31 (define-module (gnu packages bioinformatics)
32 #:use-module ((guix licenses) #:prefix license:)
33 #:use-module (guix packages)
34 #:use-module (guix utils)
35 #:use-module (guix download)
36 #:use-module (guix git-download)
37 #:use-module (guix hg-download)
38 #:use-module (guix build-system ant)
39 #:use-module (guix build-system gnu)
40 #:use-module (guix build-system cmake)
41 #:use-module (guix build-system haskell)
42 #:use-module (guix build-system ocaml)
43 #:use-module (guix build-system perl)
44 #:use-module (guix build-system python)
45 #:use-module (guix build-system r)
46 #:use-module (guix build-system ruby)
47 #:use-module (guix build-system scons)
48 #:use-module (guix build-system trivial)
49 #:use-module (gnu packages)
50 #:use-module (gnu packages autotools)
51 #:use-module (gnu packages algebra)
52 #:use-module (gnu packages base)
53 #:use-module (gnu packages bash)
54 #:use-module (gnu packages bison)
55 #:use-module (gnu packages bioconductor)
56 #:use-module (gnu packages boost)
57 #:use-module (gnu packages check)
58 #:use-module (gnu packages compression)
59 #:use-module (gnu packages cpio)
60 #:use-module (gnu packages cran)
61 #:use-module (gnu packages curl)
62 #:use-module (gnu packages documentation)
63 #:use-module (gnu packages databases)
64 #:use-module (gnu packages datastructures)
65 #:use-module (gnu packages file)
66 #:use-module (gnu packages flex)
67 #:use-module (gnu packages gawk)
68 #:use-module (gnu packages gcc)
69 #:use-module (gnu packages gd)
70 #:use-module (gnu packages gtk)
71 #:use-module (gnu packages glib)
72 #:use-module (gnu packages graph)
73 #:use-module (gnu packages groff)
74 #:use-module (gnu packages guile)
75 #:use-module (gnu packages haskell)
76 #:use-module (gnu packages haskell-check)
77 #:use-module (gnu packages haskell-web)
78 #:use-module (gnu packages image)
79 #:use-module (gnu packages imagemagick)
80 #:use-module (gnu packages java)
81 #:use-module (gnu packages jemalloc)
82 #:use-module (gnu packages dlang)
83 #:use-module (gnu packages linux)
84 #:use-module (gnu packages logging)
85 #:use-module (gnu packages machine-learning)
86 #:use-module (gnu packages man)
87 #:use-module (gnu packages maths)
88 #:use-module (gnu packages mpi)
89 #:use-module (gnu packages ncurses)
90 #:use-module (gnu packages ocaml)
91 #:use-module (gnu packages pcre)
92 #:use-module (gnu packages parallel)
93 #:use-module (gnu packages pdf)
94 #:use-module (gnu packages perl)
95 #:use-module (gnu packages perl-check)
96 #:use-module (gnu packages pkg-config)
97 #:use-module (gnu packages popt)
98 #:use-module (gnu packages protobuf)
99 #:use-module (gnu packages python)
100 #:use-module (gnu packages python-web)
101 #:use-module (gnu packages readline)
102 #:use-module (gnu packages ruby)
103 #:use-module (gnu packages serialization)
104 #:use-module (gnu packages shells)
105 #:use-module (gnu packages statistics)
106 #:use-module (gnu packages swig)
107 #:use-module (gnu packages tbb)
108 #:use-module (gnu packages tex)
109 #:use-module (gnu packages texinfo)
110 #:use-module (gnu packages textutils)
111 #:use-module (gnu packages time)
112 #:use-module (gnu packages tls)
113 #:use-module (gnu packages vim)
114 #:use-module (gnu packages web)
115 #:use-module (gnu packages xml)
116 #:use-module (gnu packages xorg)
117 #:use-module (srfi srfi-1)
118 #:use-module (ice-9 match))
119
120 (define-public aragorn
121 (package
122 (name "aragorn")
123 (version "1.2.38")
124 (source (origin
125 (method url-fetch)
126 (uri (string-append
127 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
128 version ".tgz"))
129 (sha256
130 (base32
131 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
132 (build-system gnu-build-system)
133 (arguments
134 `(#:tests? #f ; there are no tests
135 #:phases
136 (modify-phases %standard-phases
137 (delete 'configure)
138 (replace 'build
139 (lambda _
140 (invoke "gcc"
141 "-O3"
142 "-ffast-math"
143 "-finline-functions"
144 "-o"
145 "aragorn"
146 (string-append "aragorn" ,version ".c"))
147 #t))
148 (replace 'install
149 (lambda* (#:key outputs #:allow-other-keys)
150 (let* ((out (assoc-ref outputs "out"))
151 (bin (string-append out "/bin"))
152 (man (string-append out "/share/man/man1")))
153 (install-file "aragorn" bin)
154 (install-file "aragorn.1" man))
155 #t)))))
156 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
157 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
158 (description
159 "Aragorn identifies transfer RNA, mitochondrial RNA and
160 transfer-messenger RNA from nucleotide sequences, based on homology to known
161 tRNA consensus sequences and RNA structure. It also outputs the secondary
162 structure of the predicted RNA.")
163 (license license:gpl2)))
164
165 (define-public bamm
166 (package
167 (name "bamm")
168 (version "1.7.3")
169 (source (origin
170 (method git-fetch)
171 ;; BamM is not available on pypi.
172 (uri (git-reference
173 (url "https://github.com/Ecogenomics/BamM.git")
174 (commit version)
175 (recursive? #t)))
176 (file-name (git-file-name name version))
177 (sha256
178 (base32
179 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
180 (modules '((guix build utils)))
181 (snippet
182 `(begin
183 ;; Delete bundled htslib.
184 (delete-file-recursively "c/htslib-1.3.1")
185 #t))))
186 (build-system python-build-system)
187 (arguments
188 `(#:python ,python-2 ; BamM is Python 2 only.
189 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
190 ;; been modified from its original form.
191 #:configure-flags
192 (let ((htslib (assoc-ref %build-inputs "htslib")))
193 (list "--with-libhts-lib" (string-append htslib "/lib")
194 "--with-libhts-inc" (string-append htslib "/include/htslib")))
195 #:phases
196 (modify-phases %standard-phases
197 (add-after 'unpack 'autogen
198 (lambda _
199 (with-directory-excursion "c"
200 (let ((sh (which "sh")))
201 (for-each make-file-writable (find-files "." ".*"))
202 ;; Use autogen so that 'configure' works.
203 (substitute* "autogen.sh" (("/bin/sh") sh))
204 (setenv "CONFIG_SHELL" sh)
205 (invoke "./autogen.sh")))
206 #t))
207 (delete 'build)
208 ;; Run tests after installation so compilation only happens once.
209 (delete 'check)
210 (add-after 'install 'wrap-executable
211 (lambda* (#:key outputs #:allow-other-keys)
212 (let* ((out (assoc-ref outputs "out"))
213 (path (getenv "PATH")))
214 (wrap-program (string-append out "/bin/bamm")
215 `("PATH" ":" prefix (,path))))
216 #t))
217 (add-after 'wrap-executable 'post-install-check
218 (lambda* (#:key inputs outputs #:allow-other-keys)
219 (setenv "PATH"
220 (string-append (assoc-ref outputs "out")
221 "/bin:"
222 (getenv "PATH")))
223 (setenv "PYTHONPATH"
224 (string-append
225 (assoc-ref outputs "out")
226 "/lib/python"
227 (string-take (string-take-right
228 (assoc-ref inputs "python") 5) 3)
229 "/site-packages:"
230 (getenv "PYTHONPATH")))
231 ;; There are 2 errors printed, but they are safe to ignore:
232 ;; 1) [E::hts_open_format] fail to open file ...
233 ;; 2) samtools view: failed to open ...
234 (invoke "nosetests")
235 #t)))))
236 (native-inputs
237 `(("autoconf" ,autoconf)
238 ("automake" ,automake)
239 ("libtool" ,libtool)
240 ("zlib" ,zlib)
241 ("python-nose" ,python2-nose)
242 ("python-pysam" ,python2-pysam)))
243 (inputs
244 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
245 ("samtools" ,samtools)
246 ("bwa" ,bwa)
247 ("grep" ,grep)
248 ("sed" ,sed)
249 ("coreutils" ,coreutils)))
250 (propagated-inputs
251 `(("python-numpy" ,python2-numpy)))
252 (home-page "http://ecogenomics.github.io/BamM/")
253 (synopsis "Metagenomics-focused BAM file manipulator")
254 (description
255 "BamM is a C library, wrapped in python, to efficiently generate and
256 parse BAM files, specifically for the analysis of metagenomic data. For
257 instance, it implements several methods to assess contig-wise read coverage.")
258 (license license:lgpl3+)))
259
260 (define-public bamtools
261 (package
262 (name "bamtools")
263 (version "2.5.1")
264 (source (origin
265 (method git-fetch)
266 (uri (git-reference
267 (url "https://github.com/pezmaster31/bamtools.git")
268 (commit (string-append "v" version))))
269 (file-name (git-file-name name version))
270 (sha256
271 (base32
272 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
273 (build-system cmake-build-system)
274 (arguments
275 `(#:tests? #f ;no "check" target
276 #:phases
277 (modify-phases %standard-phases
278 (add-before
279 'configure 'set-ldflags
280 (lambda* (#:key outputs #:allow-other-keys)
281 (setenv "LDFLAGS"
282 (string-append
283 "-Wl,-rpath="
284 (assoc-ref outputs "out") "/lib/bamtools")))))))
285 (inputs `(("zlib" ,zlib)))
286 (home-page "https://github.com/pezmaster31/bamtools")
287 (synopsis "C++ API and command-line toolkit for working with BAM data")
288 (description
289 "BamTools provides both a C++ API and a command-line toolkit for handling
290 BAM files.")
291 (license license:expat)))
292
293 (define-public bcftools
294 (package
295 (name "bcftools")
296 (version "1.9")
297 (source (origin
298 (method url-fetch)
299 (uri (string-append "https://github.com/samtools/bcftools/"
300 "releases/download/"
301 version "/bcftools-" version ".tar.bz2"))
302 (sha256
303 (base32
304 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
305 (modules '((guix build utils)))
306 (snippet '(begin
307 ;; Delete bundled htslib.
308 (delete-file-recursively "htslib-1.9")
309 #t))))
310 (build-system gnu-build-system)
311 (arguments
312 `(#:configure-flags
313 (list "--enable-libgsl")
314 #:test-target "test"
315 #:phases
316 (modify-phases %standard-phases
317 (add-before 'check 'patch-tests
318 (lambda _
319 (substitute* "test/test.pl"
320 (("/bin/bash") (which "bash")))
321 #t)))))
322 (native-inputs
323 `(("htslib" ,htslib)
324 ("perl" ,perl)))
325 (inputs
326 `(("gsl" ,gsl)
327 ("zlib" ,zlib)))
328 (home-page "https://samtools.github.io/bcftools/")
329 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
330 (description
331 "BCFtools is a set of utilities that manipulate variant calls in the
332 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
333 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
334 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
335 (license (list license:gpl3+ license:expat))))
336
337 (define-public bedops
338 (package
339 (name "bedops")
340 (version "2.4.35")
341 (source (origin
342 (method git-fetch)
343 (uri (git-reference
344 (url "https://github.com/bedops/bedops.git")
345 (commit (string-append "v" version))))
346 (file-name (git-file-name name version))
347 (sha256
348 (base32
349 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
350 (build-system gnu-build-system)
351 (arguments
352 '(#:tests? #f
353 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
354 #:phases
355 (modify-phases %standard-phases
356 (add-after 'unpack 'unpack-tarballs
357 (lambda _
358 ;; FIXME: Bedops includes tarballs of minimally patched upstream
359 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
360 ;; libraries because at least one of the libraries (zlib) is
361 ;; patched to add a C++ function definition (deflateInit2cpp).
362 ;; Until the Bedops developers offer a way to link against system
363 ;; libraries we have to build the in-tree copies of these three
364 ;; libraries.
365
366 ;; See upstream discussion:
367 ;; https://github.com/bedops/bedops/issues/124
368
369 ;; Unpack the tarballs to benefit from shebang patching.
370 (with-directory-excursion "third-party"
371 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
372 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
373 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
374 ;; Disable unpacking of tarballs in Makefile.
375 (substitute* "system.mk/Makefile.linux"
376 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
377 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
378 (substitute* "third-party/zlib-1.2.7/Makefile.in"
379 (("^SHELL=.*$") "SHELL=bash\n"))
380 #t))
381 (delete 'configure))))
382 (home-page "https://github.com/bedops/bedops")
383 (synopsis "Tools for high-performance genomic feature operations")
384 (description
385 "BEDOPS is a suite of tools to address common questions raised in genomic
386 studies---mostly with regard to overlap and proximity relationships between
387 data sets. It aims to be scalable and flexible, facilitating the efficient
388 and accurate analysis and management of large-scale genomic data.
389
390 BEDOPS provides tools that perform highly efficient and scalable Boolean and
391 other set operations, statistical calculations, archiving, conversion and
392 other management of genomic data of arbitrary scale. Tasks can be easily
393 split by chromosome for distributing whole-genome analyses across a
394 computational cluster.")
395 (license license:gpl2+)))
396
397 (define-public bedtools
398 (package
399 (name "bedtools")
400 (version "2.27.1")
401 (source (origin
402 (method url-fetch)
403 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
404 "download/v" version "/"
405 "bedtools-" version ".tar.gz"))
406 (sha256
407 (base32
408 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
409 (build-system gnu-build-system)
410 (arguments
411 '(#:test-target "test"
412 #:make-flags
413 (list (string-append "prefix=" (assoc-ref %outputs "out")))
414 #:phases
415 (modify-phases %standard-phases
416 (delete 'configure))))
417 (native-inputs `(("python" ,python-2)))
418 (inputs
419 `(("samtools" ,samtools)
420 ("zlib" ,zlib)))
421 (home-page "https://github.com/arq5x/bedtools2")
422 (synopsis "Tools for genome analysis and arithmetic")
423 (description
424 "Collectively, the bedtools utilities are a swiss-army knife of tools for
425 a wide-range of genomics analysis tasks. The most widely-used tools enable
426 genome arithmetic: that is, set theory on the genome. For example, bedtools
427 allows one to intersect, merge, count, complement, and shuffle genomic
428 intervals from multiple files in widely-used genomic file formats such as BAM,
429 BED, GFF/GTF, VCF.")
430 (license license:gpl2)))
431
432 ;; Later releases of bedtools produce files with more columns than
433 ;; what Ribotaper expects.
434 (define-public bedtools-2.18
435 (package (inherit bedtools)
436 (name "bedtools")
437 (version "2.18.0")
438 (source (origin
439 (method url-fetch)
440 (uri (string-append "https://github.com/arq5x/bedtools2/"
441 "releases/download/v" version
442 "/bedtools-" version ".tar.gz"))
443 (sha256
444 (base32
445 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
446 (arguments
447 '(#:test-target "test"
448 #:phases
449 (modify-phases %standard-phases
450 (delete 'configure)
451 (replace 'install
452 (lambda* (#:key outputs #:allow-other-keys)
453 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
454 (for-each (lambda (file)
455 (install-file file bin))
456 (find-files "bin" ".*")))
457 #t)))))))
458
459 ;; Needed for pybedtools.
460 (define-public bedtools-2.26
461 (package (inherit bedtools)
462 (name "bedtools")
463 (version "2.26.0")
464 (source (origin
465 (method url-fetch)
466 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
467 "download/v" version "/"
468 "bedtools-" version ".tar.gz"))
469 (sha256
470 (base32
471 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
472
473 (define-public ribotaper
474 (package
475 (name "ribotaper")
476 (version "1.3.1")
477 (source (origin
478 (method url-fetch)
479 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
480 "files/RiboTaper/RiboTaper_Version_"
481 version ".tar.gz"))
482 (sha256
483 (base32
484 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
485 (build-system gnu-build-system)
486 (arguments
487 `(#:phases
488 (modify-phases %standard-phases
489 (add-after 'install 'wrap-executables
490 (lambda* (#:key inputs outputs #:allow-other-keys)
491 (let* ((out (assoc-ref outputs "out")))
492 (for-each
493 (lambda (script)
494 (wrap-program (string-append out "/bin/" script)
495 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
496 '("create_annotations_files.bash"
497 "create_metaplots.bash"
498 "Ribotaper_ORF_find.sh"
499 "Ribotaper.sh"))))))))
500 (inputs
501 `(("bedtools" ,bedtools-2.18)
502 ("samtools" ,samtools-0.1)
503 ("r-minimal" ,r-minimal)
504 ("r-foreach" ,r-foreach)
505 ("r-xnomial" ,r-xnomial)
506 ("r-domc" ,r-domc)
507 ("r-multitaper" ,r-multitaper)
508 ("r-seqinr" ,r-seqinr)))
509 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
510 (synopsis "Define translated ORFs using ribosome profiling data")
511 (description
512 "Ribotaper is a method for defining translated @dfn{open reading
513 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
514 provides the Ribotaper pipeline.")
515 (license license:gpl3+)))
516
517 (define-public ribodiff
518 (package
519 (name "ribodiff")
520 (version "0.2.2")
521 (source
522 (origin
523 (method url-fetch)
524 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
525 "archive/v" version ".tar.gz"))
526 (file-name (string-append name "-" version ".tar.gz"))
527 (sha256
528 (base32
529 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
530 (build-system python-build-system)
531 (arguments
532 `(#:python ,python-2
533 #:phases
534 (modify-phases %standard-phases
535 ;; Generate an installable executable script wrapper.
536 (add-after 'unpack 'patch-setup.py
537 (lambda _
538 (substitute* "setup.py"
539 (("^(.*)packages=.*" line prefix)
540 (string-append line "\n"
541 prefix "scripts=['scripts/TE.py'],\n")))
542 #t)))))
543 (inputs
544 `(("python-numpy" ,python2-numpy)
545 ("python-matplotlib" ,python2-matplotlib)
546 ("python-scipy" ,python2-scipy)
547 ("python-statsmodels" ,python2-statsmodels)))
548 (native-inputs
549 `(("python-mock" ,python2-mock)
550 ("python-nose" ,python2-nose)))
551 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
552 (synopsis "Detect translation efficiency changes from ribosome footprints")
553 (description "RiboDiff is a statistical tool that detects the protein
554 translational efficiency change from Ribo-Seq (ribosome footprinting) and
555 RNA-Seq data. It uses a generalized linear model to detect genes showing
556 difference in translational profile taking mRNA abundance into account. It
557 facilitates us to decipher the translational regulation that behave
558 independently with transcriptional regulation.")
559 (license license:gpl3+)))
560
561 (define-public bioawk
562 (package
563 (name "bioawk")
564 (version "1.0")
565 (source (origin
566 (method url-fetch)
567 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
568 version ".tar.gz"))
569 (file-name (string-append name "-" version ".tar.gz"))
570 (sha256
571 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
572 (build-system gnu-build-system)
573 (inputs
574 `(("zlib" ,zlib)))
575 (native-inputs
576 `(("bison" ,bison)))
577 (arguments
578 `(#:tests? #f ; There are no tests to run.
579 ;; Bison must generate files, before other targets can build.
580 #:parallel-build? #f
581 #:phases
582 (modify-phases %standard-phases
583 (delete 'configure) ; There is no configure phase.
584 (replace 'install
585 (lambda* (#:key outputs #:allow-other-keys)
586 (let* ((out (assoc-ref outputs "out"))
587 (bin (string-append out "/bin"))
588 (man (string-append out "/share/man/man1")))
589 (mkdir-p man)
590 (copy-file "awk.1" (string-append man "/bioawk.1"))
591 (install-file "bioawk" bin)))))))
592 (home-page "https://github.com/lh3/bioawk")
593 (synopsis "AWK with bioinformatics extensions")
594 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
595 support of several common biological data formats, including optionally gzip'ed
596 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
597 also adds a few built-in functions and a command line option to use TAB as the
598 input/output delimiter. When the new functionality is not used, bioawk is
599 intended to behave exactly the same as the original BWK awk.")
600 (license license:x11)))
601
602 (define-public python-pybedtools
603 (package
604 (name "python-pybedtools")
605 (version "0.7.10")
606 (source (origin
607 (method url-fetch)
608 (uri (pypi-uri "pybedtools" version))
609 (sha256
610 (base32
611 "0l2b2wrnj85azfqgr0zwr60f7j58vlla1hcgxvr9rwikpl8j72ji"))))
612 (build-system python-build-system)
613 (arguments
614 `(#:phases
615 (modify-phases %standard-phases
616 ;; See https://github.com/daler/pybedtools/issues/261
617 (add-after 'unpack 'disable-broken-tests
618 (lambda _
619 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
620 ;; graphical environment.
621 (substitute* "pybedtools/test/test_scripts.py"
622 (("def test_venn_mpl")
623 "def _do_not_test_venn_mpl"))
624 ;; Requires internet access.
625 (substitute* "pybedtools/test/test_helpers.py"
626 (("def test_chromsizes")
627 "def _do_not_test_chromsizes"))
628 ;; FIXME: these two fail for no good reason.
629 (substitute* "pybedtools/test/test1.py"
630 (("def test_issue_157")
631 "def _do_not_test_issue_157")
632 (("def test_to_dataframe")
633 "def _do_not_test_to_dataframe"))
634 #t)))))
635 (propagated-inputs
636 ;; Tests don't pass with Bedtools 2.27.1.
637 ;; See https://github.com/daler/pybedtools/issues/260
638 `(("bedtools" ,bedtools-2.26)
639 ("samtools" ,samtools)
640 ("python-matplotlib" ,python-matplotlib)
641 ("python-pysam" ,python-pysam)
642 ("python-pyyaml" ,python-pyyaml)))
643 (native-inputs
644 `(("python-numpy" ,python-numpy)
645 ("python-pandas" ,python-pandas)
646 ("python-cython" ,python-cython)
647 ("python-nose" ,python-nose)
648 ("kentutils" ,kentutils) ; for bedGraphToBigWig
649 ("python-six" ,python-six)))
650 (home-page "https://pythonhosted.org/pybedtools/")
651 (synopsis "Python wrapper for BEDtools programs")
652 (description
653 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
654 which are widely used for genomic interval manipulation or \"genome algebra\".
655 pybedtools extends BEDTools by offering feature-level manipulations from with
656 Python.")
657 (license license:gpl2+)))
658
659 (define-public python2-pybedtools
660 (let ((pkg (package-with-python2 python-pybedtools)))
661 (package (inherit pkg)
662 (arguments
663 `(#:modules ((ice-9 ftw)
664 (srfi srfi-1)
665 (srfi srfi-26)
666 (guix build utils)
667 (guix build python-build-system))
668 ;; See https://github.com/daler/pybedtools/issues/192
669 ,@(substitute-keyword-arguments (package-arguments pkg)
670 ((#:phases phases)
671 `(modify-phases ,phases
672 (replace 'check
673 (lambda _
674 (let ((cwd (getcwd)))
675 (setenv "PYTHONPATH"
676 (string-append cwd "/build/"
677 (find (cut string-prefix? "lib" <>)
678 (scandir (string-append cwd "/build")))
679 ":" (getenv "PYTHONPATH"))))
680 ;; The tests need to be run from elsewhere...
681 (mkdir-p "/tmp/test")
682 (copy-recursively "pybedtools/test" "/tmp/test")
683 (with-directory-excursion "/tmp/test"
684 (invoke "nosetests"
685 ;; This test fails for unknown reasons
686 "--exclude=.*test_getting_example_beds"))
687 #t))))))))))
688
689 (define-public python-biom-format
690 (package
691 (name "python-biom-format")
692 (version "2.1.6")
693 (source
694 (origin
695 (method url-fetch)
696 ;; Use GitHub as source because PyPI distribution does not contain
697 ;; test data: https://github.com/biocore/biom-format/issues/693
698 (uri (string-append "https://github.com/biocore/biom-format/archive/"
699 version ".tar.gz"))
700 (file-name (string-append name "-" version ".tar.gz"))
701 (sha256
702 (base32
703 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
704 (build-system python-build-system)
705 (propagated-inputs
706 `(("python-numpy" ,python-numpy)
707 ("python-scipy" ,python-scipy)
708 ("python-future" ,python-future)
709 ("python-click" ,python-click)
710 ("python-h5py" ,python-h5py)
711 ("python-pandas" ,python-pandas)))
712 (native-inputs
713 `(("python-nose" ,python-nose)))
714 (home-page "http://www.biom-format.org")
715 (synopsis "Biological Observation Matrix (BIOM) format utilities")
716 (description
717 "The BIOM file format is designed to be a general-use format for
718 representing counts of observations e.g. operational taxonomic units, KEGG
719 orthology groups or lipid types, in one or more biological samples
720 e.g. microbiome samples, genomes, metagenomes.")
721 (license license:bsd-3)
722 (properties `((python2-variant . ,(delay python2-biom-format))))))
723
724 (define-public python2-biom-format
725 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
726 (package
727 (inherit base)
728 (arguments
729 `(#:phases
730 (modify-phases %standard-phases
731 ;; Do not require the unmaintained pyqi library.
732 (add-after 'unpack 'remove-pyqi
733 (lambda _
734 (substitute* "setup.py"
735 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
736 #t)))
737 ,@(package-arguments base))))))
738
739 (define-public bioperl-minimal
740 (let* ((inputs `(("perl-module-build" ,perl-module-build)
741 ("perl-data-stag" ,perl-data-stag)
742 ("perl-libwww" ,perl-libwww)
743 ("perl-uri" ,perl-uri)))
744 (transitive-inputs
745 (map (compose package-name cadr)
746 (delete-duplicates
747 (concatenate
748 (map (compose package-transitive-target-inputs cadr) inputs))))))
749 (package
750 (name "bioperl-minimal")
751 (version "1.7.0")
752 (source
753 (origin
754 (method url-fetch)
755 (uri (string-append "https://github.com/bioperl/bioperl-live/"
756 "archive/release-"
757 (string-map (lambda (c)
758 (if (char=? c #\.)
759 #\- c)) version)
760 ".tar.gz"))
761 (sha256
762 (base32
763 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
764 (build-system perl-build-system)
765 (arguments
766 `(#:phases
767 (modify-phases %standard-phases
768 (add-after
769 'install 'wrap-programs
770 (lambda* (#:key outputs #:allow-other-keys)
771 ;; Make sure all executables in "bin" find the required Perl
772 ;; modules at runtime. As the PERL5LIB variable contains also
773 ;; the paths of native inputs, we pick the transitive target
774 ;; inputs from %build-inputs.
775 (let* ((out (assoc-ref outputs "out"))
776 (bin (string-append out "/bin/"))
777 (path (string-join
778 (cons (string-append out "/lib/perl5/site_perl")
779 (map (lambda (name)
780 (assoc-ref %build-inputs name))
781 ',transitive-inputs))
782 ":")))
783 (for-each (lambda (file)
784 (wrap-program file
785 `("PERL5LIB" ":" prefix (,path))))
786 (find-files bin "\\.pl$"))
787 #t))))))
788 (inputs inputs)
789 (native-inputs
790 `(("perl-test-most" ,perl-test-most)))
791 (home-page "https://metacpan.org/release/BioPerl")
792 (synopsis "Bioinformatics toolkit")
793 (description
794 "BioPerl is the product of a community effort to produce Perl code which
795 is useful in biology. Examples include Sequence objects, Alignment objects
796 and database searching objects. These objects not only do what they are
797 advertised to do in the documentation, but they also interact - Alignment
798 objects are made from the Sequence objects, Sequence objects have access to
799 Annotation and SeqFeature objects and databases, Blast objects can be
800 converted to Alignment objects, and so on. This means that the objects
801 provide a coordinated and extensible framework to do computational biology.")
802 (license license:perl-license))))
803
804 (define-public python-biopython
805 (package
806 (name "python-biopython")
807 (version "1.70")
808 (source (origin
809 (method url-fetch)
810 ;; use PyPi rather than biopython.org to ease updating
811 (uri (pypi-uri "biopython" version))
812 (sha256
813 (base32
814 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
815 (build-system python-build-system)
816 (arguments
817 `(#:phases
818 (modify-phases %standard-phases
819 (add-before 'check 'set-home
820 ;; Some tests require a home directory to be set.
821 (lambda _ (setenv "HOME" "/tmp") #t)))))
822 (propagated-inputs
823 `(("python-numpy" ,python-numpy)))
824 (home-page "http://biopython.org/")
825 (synopsis "Tools for biological computation in Python")
826 (description
827 "Biopython is a set of tools for biological computation including parsers
828 for bioinformatics files into Python data structures; interfaces to common
829 bioinformatics programs; a standard sequence class and tools for performing
830 common operations on them; code to perform data classification; code for
831 dealing with alignments; code making it easy to split up parallelizable tasks
832 into separate processes; and more.")
833 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
834
835 (define-public python2-biopython
836 (package-with-python2 python-biopython))
837
838 (define-public python-fastalite
839 (package
840 (name "python-fastalite")
841 (version "0.3")
842 (source
843 (origin
844 (method url-fetch)
845 (uri (pypi-uri "fastalite" version))
846 (sha256
847 (base32
848 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
849 (build-system python-build-system)
850 (arguments
851 `(#:tests? #f)) ; Test data is not distributed.
852 (home-page "https://github.com/nhoffman/fastalite")
853 (synopsis "Simplest possible FASTA parser")
854 (description "This library implements a FASTA and a FASTQ parser without
855 relying on a complex dependency tree.")
856 (license license:expat)))
857
858 (define-public python2-fastalite
859 (package-with-python2 python-fastalite))
860
861 (define-public bpp-core
862 ;; The last release was in 2014 and the recommended way to install from source
863 ;; is to clone the git repository, so we do this.
864 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
865 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
866 (package
867 (name "bpp-core")
868 (version (string-append "2.2.0-1." (string-take commit 7)))
869 (source (origin
870 (method git-fetch)
871 (uri (git-reference
872 (url "http://biopp.univ-montp2.fr/git/bpp-core")
873 (commit commit)))
874 (file-name (string-append name "-" version "-checkout"))
875 (sha256
876 (base32
877 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
878 (build-system cmake-build-system)
879 (arguments
880 `(#:parallel-build? #f))
881 (inputs
882 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
883 ; compile all of the bpp packages with GCC 5.
884 (home-page "http://biopp.univ-montp2.fr")
885 (synopsis "C++ libraries for Bioinformatics")
886 (description
887 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
888 analysis, phylogenetics, molecular evolution and population genetics. It is
889 Object Oriented and is designed to be both easy to use and computer efficient.
890 Bio++ intends to help programmers to write computer expensive programs, by
891 providing them a set of re-usable tools.")
892 (license license:cecill-c))))
893
894 (define-public bpp-phyl
895 ;; The last release was in 2014 and the recommended way to install from source
896 ;; is to clone the git repository, so we do this.
897 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
898 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
899 (package
900 (name "bpp-phyl")
901 (version (string-append "2.2.0-1." (string-take commit 7)))
902 (source (origin
903 (method git-fetch)
904 (uri (git-reference
905 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
906 (commit commit)))
907 (file-name (string-append name "-" version "-checkout"))
908 (sha256
909 (base32
910 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
911 (build-system cmake-build-system)
912 (arguments
913 `(#:parallel-build? #f
914 ;; If out-of-source, test data is not copied into the build directory
915 ;; so the tests fail.
916 #:out-of-source? #f))
917 (inputs
918 `(("bpp-core" ,bpp-core)
919 ("bpp-seq" ,bpp-seq)
920 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
921 ;; modern GCC.
922 ("gcc" ,gcc-5)))
923 (home-page "http://biopp.univ-montp2.fr")
924 (synopsis "Bio++ phylogenetic 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 phylogenetics-related modules.")
929 (license license:cecill-c))))
930
931 (define-public bpp-popgen
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 "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
936 (package
937 (name "bpp-popgen")
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/bpp-popgen")
943 (commit commit)))
944 (file-name (string-append name "-" version "-checkout"))
945 (sha256
946 (base32
947 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
948 (build-system cmake-build-system)
949 (arguments
950 `(#:parallel-build? #f
951 #:tests? #f)) ; There are no tests.
952 (inputs
953 `(("bpp-core" ,bpp-core)
954 ("bpp-seq" ,bpp-seq)
955 ("gcc" ,gcc-5)))
956 (home-page "http://biopp.univ-montp2.fr")
957 (synopsis "Bio++ population genetics library")
958 (description
959 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
960 analysis, phylogenetics, molecular evolution and population genetics. This
961 library provides population genetics-related modules.")
962 (license license:cecill-c))))
963
964 (define-public bpp-seq
965 ;; The last release was in 2014 and the recommended way to install from source
966 ;; is to clone the git repository, so we do this.
967 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
968 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
969 (package
970 (name "bpp-seq")
971 (version (string-append "2.2.0-1." (string-take commit 7)))
972 (source (origin
973 (method git-fetch)
974 (uri (git-reference
975 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
976 (commit commit)))
977 (file-name (string-append name "-" version "-checkout"))
978 (sha256
979 (base32
980 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
981 (build-system cmake-build-system)
982 (arguments
983 `(#:parallel-build? #f
984 ;; If out-of-source, test data is not copied into the build directory
985 ;; so the tests fail.
986 #:out-of-source? #f))
987 (inputs
988 `(("bpp-core" ,bpp-core)
989 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
990 (home-page "http://biopp.univ-montp2.fr")
991 (synopsis "Bio++ sequence library")
992 (description
993 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
994 analysis, phylogenetics, molecular evolution and population genetics. This
995 library provides sequence-related modules.")
996 (license license:cecill-c))))
997
998 (define-public bppsuite
999 ;; The last release was in 2014 and the recommended way to install from source
1000 ;; is to clone the git repository, so we do this.
1001 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1002 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1003 (package
1004 (name "bppsuite")
1005 (version (string-append "2.2.0-1." (string-take commit 7)))
1006 (source (origin
1007 (method git-fetch)
1008 (uri (git-reference
1009 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1010 (commit commit)))
1011 (file-name (string-append name "-" version "-checkout"))
1012 (sha256
1013 (base32
1014 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1015 (build-system cmake-build-system)
1016 (arguments
1017 `(#:parallel-build? #f
1018 #:tests? #f)) ; There are no tests.
1019 (native-inputs
1020 `(("groff" ,groff)
1021 ("man-db" ,man-db)
1022 ("texinfo" ,texinfo)))
1023 (inputs
1024 `(("bpp-core" ,bpp-core)
1025 ("bpp-seq" ,bpp-seq)
1026 ("bpp-phyl" ,bpp-phyl)
1027 ("bpp-phyl" ,bpp-popgen)
1028 ("gcc" ,gcc-5)))
1029 (home-page "http://biopp.univ-montp2.fr")
1030 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1031 (description
1032 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1033 analysis, phylogenetics, molecular evolution and population genetics. This
1034 package provides command line tools using the Bio++ library.")
1035 (license license:cecill-c))))
1036
1037 (define-public blast+
1038 (package
1039 (name "blast+")
1040 (version "2.6.0")
1041 (source (origin
1042 (method url-fetch)
1043 (uri (string-append
1044 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1045 version "/ncbi-blast-" version "+-src.tar.gz"))
1046 (sha256
1047 (base32
1048 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
1049 (patches (search-patches "blast+-fix-makefile.patch"))
1050 (modules '((guix build utils)))
1051 (snippet
1052 '(begin
1053 ;; Remove bundled bzip2, zlib and pcre.
1054 (delete-file-recursively "c++/src/util/compress/bzip2")
1055 (delete-file-recursively "c++/src/util/compress/zlib")
1056 (delete-file-recursively "c++/src/util/regexp")
1057 (substitute* "c++/src/util/compress/Makefile.in"
1058 (("bzip2 zlib api") "api"))
1059 ;; Remove useless msbuild directory
1060 (delete-file-recursively
1061 "c++/src/build-system/project_tree_builder/msbuild")
1062 #t))))
1063 (build-system gnu-build-system)
1064 (arguments
1065 `(;; There are two(!) tests for this massive library, and both fail with
1066 ;; "unparsable timing stats".
1067 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1068 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1069 #:tests? #f
1070 #:out-of-source? #t
1071 #:parallel-build? #f ; not supported
1072 #:phases
1073 (modify-phases %standard-phases
1074 (add-before 'configure 'set-HOME
1075 ;; $HOME needs to be set at some point during the configure phase
1076 (lambda _ (setenv "HOME" "/tmp") #t))
1077 (add-after 'unpack 'enter-dir
1078 (lambda _ (chdir "c++") #t))
1079 (add-after 'enter-dir 'fix-build-system
1080 (lambda _
1081 (define (which* cmd)
1082 (cond ((string=? cmd "date")
1083 ;; make call to "date" deterministic
1084 "date -d @0")
1085 ((which cmd)
1086 => identity)
1087 (else
1088 (format (current-error-port)
1089 "WARNING: Unable to find absolute path for ~s~%"
1090 cmd)
1091 #f)))
1092
1093 ;; Rewrite hardcoded paths to various tools
1094 (substitute* (append '("src/build-system/configure.ac"
1095 "src/build-system/configure"
1096 "src/build-system/helpers/run_with_lock.c"
1097 "scripts/common/impl/if_diff.sh"
1098 "scripts/common/impl/run_with_lock.sh"
1099 "src/build-system/Makefile.configurables.real"
1100 "src/build-system/Makefile.in.top"
1101 "src/build-system/Makefile.meta.gmake=no"
1102 "src/build-system/Makefile.meta.in"
1103 "src/build-system/Makefile.meta_l"
1104 "src/build-system/Makefile.meta_p"
1105 "src/build-system/Makefile.meta_r"
1106 "src/build-system/Makefile.mk.in"
1107 "src/build-system/Makefile.requirements"
1108 "src/build-system/Makefile.rules_with_autodep.in")
1109 (find-files "scripts/common/check" "\\.sh$"))
1110 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1111 (or (which* cmd) all)))
1112
1113 (substitute* (find-files "src/build-system" "^config.*")
1114 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1115 (("^PATH=.*") ""))
1116
1117 ;; rewrite "/var/tmp" in check script
1118 (substitute* "scripts/common/check/check_make_unix.sh"
1119 (("/var/tmp") "/tmp"))
1120
1121 ;; do not reset PATH
1122 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1123 (("^ *PATH=.*") "")
1124 (("action=/bin/") "action=")
1125 (("export PATH") ":"))
1126 #t))
1127 (replace 'configure
1128 (lambda* (#:key inputs outputs #:allow-other-keys)
1129 (let ((out (assoc-ref outputs "out"))
1130 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1131 (include (string-append (assoc-ref outputs "include")
1132 "/include/ncbi-tools++")))
1133 ;; The 'configure' script doesn't recognize things like
1134 ;; '--enable-fast-install'.
1135 (invoke "./configure.orig"
1136 (string-append "--with-build-root=" (getcwd) "/build")
1137 (string-append "--prefix=" out)
1138 (string-append "--libdir=" lib)
1139 (string-append "--includedir=" include)
1140 (string-append "--with-bz2="
1141 (assoc-ref inputs "bzip2"))
1142 (string-append "--with-z="
1143 (assoc-ref inputs "zlib"))
1144 (string-append "--with-pcre="
1145 (assoc-ref inputs "pcre"))
1146 ;; Each library is built twice by default, once
1147 ;; with "-static" in its name, and again
1148 ;; without.
1149 "--without-static"
1150 "--with-dll")
1151 #t))))))
1152 (outputs '("out" ; 21 MB
1153 "lib" ; 226 MB
1154 "include")) ; 33 MB
1155 (inputs
1156 `(("bzip2" ,bzip2)
1157 ("zlib" ,zlib)
1158 ("pcre" ,pcre)
1159 ("perl" ,perl)
1160 ("python" ,python-wrapper)))
1161 (native-inputs
1162 `(("cpio" ,cpio)))
1163 (home-page "http://blast.ncbi.nlm.nih.gov")
1164 (synopsis "Basic local alignment search tool")
1165 (description
1166 "BLAST is a popular method of performing a DNA or protein sequence
1167 similarity search, using heuristics to produce results quickly. It also
1168 calculates an “expect value” that estimates how many matches would have
1169 occurred at a given score by chance, which can aid a user in judging how much
1170 confidence to have in an alignment.")
1171 ;; Most of the sources are in the public domain, with the following
1172 ;; exceptions:
1173 ;; * Expat:
1174 ;; * ./c++/include/util/bitset/
1175 ;; * ./c++/src/html/ncbi_menu*.js
1176 ;; * Boost license:
1177 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1178 ;; * LGPL 2+:
1179 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1180 ;; * ASL 2.0:
1181 ;; * ./c++/src/corelib/teamcity_*
1182 (license (list license:public-domain
1183 license:expat
1184 license:boost1.0
1185 license:lgpl2.0+
1186 license:asl2.0))))
1187
1188 (define-public bless
1189 (package
1190 (name "bless")
1191 (version "1p02")
1192 (source (origin
1193 (method url-fetch)
1194 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1195 version ".tgz"))
1196 (sha256
1197 (base32
1198 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1199 (modules '((guix build utils)))
1200 (snippet
1201 `(begin
1202 ;; Remove bundled boost, pigz, zlib, and .git directory
1203 ;; FIXME: also remove bundled sources for murmurhash3 and
1204 ;; kmc once packaged.
1205 (delete-file-recursively "boost")
1206 (delete-file-recursively "pigz")
1207 (delete-file-recursively "google-sparsehash")
1208 (delete-file-recursively "zlib")
1209 (delete-file-recursively ".git")
1210 #t))))
1211 (build-system gnu-build-system)
1212 (arguments
1213 '(#:tests? #f ;no "check" target
1214 #:make-flags
1215 (list (string-append "ZLIB="
1216 (assoc-ref %build-inputs "zlib")
1217 "/lib/libz.a")
1218 (string-append "LDFLAGS="
1219 (string-join '("-lboost_filesystem"
1220 "-lboost_system"
1221 "-lboost_iostreams"
1222 "-lz"
1223 "-fopenmp"
1224 "-std=c++11"))))
1225 #:phases
1226 (modify-phases %standard-phases
1227 (add-after 'unpack 'do-not-build-bundled-pigz
1228 (lambda* (#:key inputs outputs #:allow-other-keys)
1229 (substitute* "Makefile"
1230 (("cd pigz/pigz-2.3.3; make") ""))
1231 #t))
1232 (add-after 'unpack 'patch-paths-to-executables
1233 (lambda* (#:key inputs outputs #:allow-other-keys)
1234 (substitute* "parse_args.cpp"
1235 (("kmc_binary = .*")
1236 (string-append "kmc_binary = \""
1237 (assoc-ref outputs "out")
1238 "/bin/kmc\";"))
1239 (("pigz_binary = .*")
1240 (string-append "pigz_binary = \""
1241 (assoc-ref inputs "pigz")
1242 "/bin/pigz\";")))
1243 #t))
1244 (replace 'install
1245 (lambda* (#:key outputs #:allow-other-keys)
1246 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1247 (for-each (lambda (file)
1248 (install-file file bin))
1249 '("bless" "kmc/bin/kmc"))
1250 #t)))
1251 (delete 'configure))))
1252 (native-inputs
1253 `(("perl" ,perl)))
1254 (inputs
1255 `(("openmpi" ,openmpi)
1256 ("boost" ,boost)
1257 ("sparsehash" ,sparsehash)
1258 ("pigz" ,pigz)
1259 ("zlib" ,zlib)))
1260 (supported-systems '("x86_64-linux"))
1261 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1262 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1263 (description
1264 "@dfn{Bloom-filter-based error correction solution for high-throughput
1265 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1266 correction tool for genomic reads produced by @dfn{Next-generation
1267 sequencing} (NGS). BLESS produces accurate correction results with much less
1268 memory compared with previous solutions and is also able to tolerate a higher
1269 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1270 errors at the end of reads.")
1271 (license license:gpl3+)))
1272
1273 (define-public bowtie
1274 (package
1275 (name "bowtie")
1276 (version "2.3.4.3")
1277 (source (origin
1278 (method git-fetch)
1279 (uri (git-reference
1280 (url "https://github.com/BenLangmead/bowtie2.git")
1281 (commit (string-append "v" version))))
1282 (file-name (git-file-name name version))
1283 (sha256
1284 (base32
1285 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1286 (modules '((guix build utils)))
1287 (snippet
1288 '(begin
1289 (substitute* "Makefile"
1290 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1291 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1292 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1293 #t))))
1294 (build-system gnu-build-system)
1295 (arguments
1296 '(#:make-flags
1297 (list "allall"
1298 "WITH_TBB=1"
1299 (string-append "prefix=" (assoc-ref %outputs "out")))
1300 #:phases
1301 (modify-phases %standard-phases
1302 (delete 'configure)
1303 (replace 'check
1304 (lambda _
1305 (invoke "perl"
1306 "scripts/test/simple_tests.pl"
1307 "--bowtie2=./bowtie2"
1308 "--bowtie2-build=./bowtie2-build")
1309 #t)))))
1310 (inputs
1311 `(("tbb" ,tbb)
1312 ("zlib" ,zlib)
1313 ("python" ,python-wrapper)))
1314 (native-inputs
1315 `(("perl" ,perl)
1316 ("perl-clone" ,perl-clone)
1317 ("perl-test-deep" ,perl-test-deep)
1318 ("perl-test-simple" ,perl-test-simple)))
1319 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1320 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1321 (description
1322 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1323 reads to long reference sequences. It is particularly good at aligning reads
1324 of about 50 up to 100s or 1,000s of characters, and particularly good at
1325 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1326 genome with an FM Index to keep its memory footprint small: for the human
1327 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1328 gapped, local, and paired-end alignment modes.")
1329 (supported-systems '("x86_64-linux"))
1330 (license license:gpl3+)))
1331
1332 (define-public tophat
1333 (package
1334 (name "tophat")
1335 (version "2.1.1")
1336 (source (origin
1337 (method url-fetch)
1338 (uri (string-append
1339 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1340 version ".tar.gz"))
1341 (sha256
1342 (base32
1343 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1344 (modules '((guix build utils)))
1345 (snippet
1346 '(begin
1347 ;; Remove bundled SeqAn and samtools
1348 (delete-file-recursively "src/SeqAn-1.4.2")
1349 (delete-file-recursively "src/samtools-0.1.18")
1350 #t))))
1351 (build-system gnu-build-system)
1352 (arguments
1353 '(#:parallel-build? #f ; not supported
1354 #:phases
1355 (modify-phases %standard-phases
1356 (add-after 'unpack 'use-system-samtools
1357 (lambda* (#:key inputs #:allow-other-keys)
1358 (substitute* "src/Makefile.in"
1359 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1360 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1361 (("SAMPROG = samtools_0\\.1\\.18") "")
1362 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1363 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1364 (substitute* '("src/common.cpp"
1365 "src/tophat.py")
1366 (("samtools_0.1.18") (which "samtools")))
1367 (substitute* '("src/common.h"
1368 "src/bam2fastx.cpp")
1369 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1370 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1371 (substitute* '("src/bwt_map.h"
1372 "src/map2gtf.h"
1373 "src/align_status.h")
1374 (("#include <bam.h>") "#include <samtools/bam.h>")
1375 (("#include <sam.h>") "#include <samtools/sam.h>"))
1376 #t)))))
1377 (inputs
1378 `(("boost" ,boost)
1379 ("bowtie" ,bowtie)
1380 ("samtools" ,samtools-0.1)
1381 ("ncurses" ,ncurses)
1382 ("python" ,python-2)
1383 ("perl" ,perl)
1384 ("zlib" ,zlib)
1385 ("seqan" ,seqan-1)))
1386 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1387 (synopsis "Spliced read mapper for RNA-Seq data")
1388 (description
1389 "TopHat is a fast splice junction mapper for nucleotide sequence
1390 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1391 mammalian-sized genomes using the ultra high-throughput short read
1392 aligner Bowtie, and then analyzes the mapping results to identify
1393 splice junctions between exons.")
1394 ;; TopHat is released under the Boost Software License, Version 1.0
1395 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1396 (license license:boost1.0)))
1397
1398 (define-public bwa
1399 (package
1400 (name "bwa")
1401 (version "0.7.17")
1402 (source (origin
1403 (method url-fetch)
1404 (uri (string-append
1405 "https://github.com/lh3/bwa/releases/download/v"
1406 version "/bwa-" version ".tar.bz2"))
1407 (sha256
1408 (base32
1409 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1410 (build-system gnu-build-system)
1411 (arguments
1412 '(#:tests? #f ;no "check" target
1413 #:phases
1414 (modify-phases %standard-phases
1415 (replace 'install
1416 (lambda* (#:key outputs #:allow-other-keys)
1417 (let ((bin (string-append
1418 (assoc-ref outputs "out") "/bin"))
1419 (doc (string-append
1420 (assoc-ref outputs "out") "/share/doc/bwa"))
1421 (man (string-append
1422 (assoc-ref outputs "out") "/share/man/man1")))
1423 (install-file "bwa" bin)
1424 (install-file "README.md" doc)
1425 (install-file "bwa.1" man))
1426 #t))
1427 ;; no "configure" script
1428 (delete 'configure))))
1429 (inputs `(("zlib" ,zlib)))
1430 ;; Non-portable SSE instructions are used so building fails on platforms
1431 ;; other than x86_64.
1432 (supported-systems '("x86_64-linux"))
1433 (home-page "http://bio-bwa.sourceforge.net/")
1434 (synopsis "Burrows-Wheeler sequence aligner")
1435 (description
1436 "BWA is a software package for mapping low-divergent sequences against a
1437 large reference genome, such as the human genome. It consists of three
1438 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1439 designed for Illumina sequence reads up to 100bp, while the rest two for
1440 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1441 features such as long-read support and split alignment, but BWA-MEM, which is
1442 the latest, is generally recommended for high-quality queries as it is faster
1443 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1444 70-100bp Illumina reads.")
1445 (license license:gpl3+)))
1446
1447 (define-public bwa-pssm
1448 (package (inherit bwa)
1449 (name "bwa-pssm")
1450 (version "0.5.11")
1451 (source (origin
1452 (method git-fetch)
1453 (uri (git-reference
1454 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1455 (commit version)))
1456 (file-name (git-file-name name version))
1457 (sha256
1458 (base32
1459 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1460 (build-system gnu-build-system)
1461 (inputs
1462 `(("gdsl" ,gdsl)
1463 ("zlib" ,zlib)
1464 ("perl" ,perl)))
1465 (home-page "http://bwa-pssm.binf.ku.dk/")
1466 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1467 (description
1468 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1469 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1470 existing aligners it is fast and sensitive. Unlike most other aligners,
1471 however, it is also adaptible in the sense that one can direct the alignment
1472 based on known biases within the data set. It is coded as a modification of
1473 the original BWA alignment program and shares the genome index structure as
1474 well as many of the command line options.")
1475 (license license:gpl3+)))
1476
1477 (define-public python-bx-python
1478 (package
1479 (name "python-bx-python")
1480 (version "0.8.2")
1481 (source (origin
1482 (method url-fetch)
1483 (uri (pypi-uri "bx-python" version))
1484 (sha256
1485 (base32
1486 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1487 (build-system python-build-system)
1488 ;; Tests fail because test data are not included
1489 (arguments '(#:tests? #f))
1490 (propagated-inputs
1491 `(("python-numpy" ,python-numpy)
1492 ("python-six" ,python-six)))
1493 (inputs
1494 `(("zlib" ,zlib)))
1495 (native-inputs
1496 `(("python-lzo" ,python-lzo)
1497 ("python-nose" ,python-nose)
1498 ("python-cython" ,python-cython)))
1499 (home-page "https://github.com/bxlab/bx-python")
1500 (synopsis "Tools for manipulating biological data")
1501 (description
1502 "bx-python provides tools for manipulating biological data, particularly
1503 multiple sequence alignments.")
1504 (license license:expat)))
1505
1506 (define-public python2-bx-python
1507 (package-with-python2 python-bx-python))
1508
1509 (define-public python-pysam
1510 (package
1511 (name "python-pysam")
1512 (version "0.15.1")
1513 (source (origin
1514 (method git-fetch)
1515 ;; Test data is missing on PyPi.
1516 (uri (git-reference
1517 (url "https://github.com/pysam-developers/pysam.git")
1518 (commit (string-append "v" version))))
1519 (file-name (git-file-name name version))
1520 (sha256
1521 (base32
1522 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1523 (modules '((guix build utils)))
1524 (snippet '(begin
1525 ;; Drop bundled htslib. TODO: Also remove samtools
1526 ;; and bcftools.
1527 (delete-file-recursively "htslib")
1528 #t))))
1529 (build-system python-build-system)
1530 (arguments
1531 `(#:modules ((ice-9 ftw)
1532 (srfi srfi-26)
1533 (guix build python-build-system)
1534 (guix build utils))
1535 #:phases
1536 (modify-phases %standard-phases
1537 (add-before 'build 'set-flags
1538 (lambda* (#:key inputs #:allow-other-keys)
1539 (setenv "HTSLIB_MODE" "external")
1540 (setenv "HTSLIB_LIBRARY_DIR"
1541 (string-append (assoc-ref inputs "htslib") "/lib"))
1542 (setenv "HTSLIB_INCLUDE_DIR"
1543 (string-append (assoc-ref inputs "htslib") "/include"))
1544 (setenv "LDFLAGS" "-lncurses")
1545 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1546 #t))
1547 (replace 'check
1548 (lambda* (#:key inputs outputs #:allow-other-keys)
1549 ;; This file contains tests that require a connection to the
1550 ;; internet.
1551 (delete-file "tests/tabix_test.py")
1552 ;; FIXME: This test fails
1553 (delete-file "tests/AlignmentFile_test.py")
1554 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1555 (setenv "PYTHONPATH"
1556 (string-append
1557 (getenv "PYTHONPATH")
1558 ":" (getcwd) "/build/"
1559 (car (scandir "build"
1560 (negate (cut string-prefix? "." <>))))))
1561 ;; Step out of source dir so python does not import from CWD.
1562 (with-directory-excursion "tests"
1563 (setenv "HOME" "/tmp")
1564 (invoke "make" "-C" "pysam_data")
1565 (invoke "make" "-C" "cbcf_data")
1566 ;; Running nosetests without explicitly asking for a single
1567 ;; process leads to a crash. Running with multiple processes
1568 ;; fails because the tests are not designed to run in parallel.
1569
1570 ;; FIXME: tests keep timing out on some systems.
1571 (invoke "nosetests" "-v" "--processes" "1")))))))
1572 (propagated-inputs
1573 `(("htslib" ,htslib))) ; Included from installed header files.
1574 (inputs
1575 `(("ncurses" ,ncurses)
1576 ("curl" ,curl)
1577 ("zlib" ,zlib)))
1578 (native-inputs
1579 `(("python-cython" ,python-cython)
1580 ;; Dependencies below are are for tests only.
1581 ("samtools" ,samtools)
1582 ("bcftools" ,bcftools)
1583 ("python-nose" ,python-nose)))
1584 (home-page "https://github.com/pysam-developers/pysam")
1585 (synopsis "Python bindings to the SAMtools C API")
1586 (description
1587 "Pysam is a Python module for reading and manipulating files in the
1588 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1589 also includes an interface for tabix.")
1590 (license license:expat)))
1591
1592 (define-public python2-pysam
1593 (package-with-python2 python-pysam))
1594
1595 (define-public python-twobitreader
1596 (package
1597 (name "python-twobitreader")
1598 (version "3.1.6")
1599 (source (origin
1600 (method git-fetch)
1601 (uri (git-reference
1602 (url "https://github.com/benjschiller/twobitreader")
1603 (commit version)))
1604 (file-name (git-file-name name version))
1605 (sha256
1606 (base32
1607 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1608 (build-system python-build-system)
1609 ;; Tests are not included
1610 (arguments '(#:tests? #f))
1611 (native-inputs
1612 `(("python-sphinx" ,python-sphinx)))
1613 (home-page "https://github.com/benjschiller/twobitreader")
1614 (synopsis "Python library for reading .2bit files")
1615 (description
1616 "twobitreader is a Python library for reading .2bit files as used by the
1617 UCSC genome browser.")
1618 (license license:artistic2.0)))
1619
1620 (define-public python2-twobitreader
1621 (package-with-python2 python-twobitreader))
1622
1623 (define-public python-plastid
1624 (package
1625 (name "python-plastid")
1626 (version "0.4.8")
1627 (source (origin
1628 (method url-fetch)
1629 (uri (pypi-uri "plastid" version))
1630 (sha256
1631 (base32
1632 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1633 (build-system python-build-system)
1634 (arguments
1635 ;; Some test files are not included.
1636 `(#:tests? #f))
1637 (propagated-inputs
1638 `(("python-numpy" ,python-numpy)
1639 ("python-scipy" ,python-scipy)
1640 ("python-pandas" ,python-pandas)
1641 ("python-pysam" ,python-pysam)
1642 ("python-matplotlib" ,python-matplotlib)
1643 ("python-biopython" ,python-biopython)
1644 ("python-twobitreader" ,python-twobitreader)
1645 ("python-termcolor" ,python-termcolor)))
1646 (native-inputs
1647 `(("python-cython" ,python-cython)
1648 ("python-nose" ,python-nose)))
1649 (home-page "https://github.com/joshuagryphon/plastid")
1650 (synopsis "Python library for genomic analysis")
1651 (description
1652 "plastid is a Python library for genomic analysis – in particular,
1653 high-throughput sequencing data – with an emphasis on simplicity.")
1654 (license license:bsd-3)))
1655
1656 (define-public python2-plastid
1657 (package-with-python2 python-plastid))
1658
1659 (define-public cd-hit
1660 (package
1661 (name "cd-hit")
1662 (version "4.6.8")
1663 (source (origin
1664 (method url-fetch)
1665 (uri (string-append "https://github.com/weizhongli/cdhit"
1666 "/releases/download/V" version
1667 "/cd-hit-v" version
1668 "-2017-0621-source.tar.gz"))
1669 (sha256
1670 (base32
1671 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1672 (build-system gnu-build-system)
1673 (arguments
1674 `(#:tests? #f ; there are no tests
1675 #:make-flags
1676 ;; Executables are copied directly to the PREFIX.
1677 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1678 #:phases
1679 (modify-phases %standard-phases
1680 ;; No "configure" script
1681 (delete 'configure)
1682 ;; Remove sources of non-determinism
1683 (add-after 'unpack 'be-timeless
1684 (lambda _
1685 (substitute* "cdhit-utility.c++"
1686 ((" \\(built on \" __DATE__ \"\\)") ""))
1687 (substitute* "cdhit-common.c++"
1688 (("__DATE__") "\"0\"")
1689 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1690 #t))
1691 ;; The "install" target does not create the target directory.
1692 (add-before 'install 'create-target-dir
1693 (lambda* (#:key outputs #:allow-other-keys)
1694 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1695 #t)))))
1696 (inputs
1697 `(("perl" ,perl)))
1698 (home-page "http://weizhongli-lab.org/cd-hit/")
1699 (synopsis "Cluster and compare protein or nucleotide sequences")
1700 (description
1701 "CD-HIT is a program for clustering and comparing protein or nucleotide
1702 sequences. CD-HIT is designed to be fast and handle extremely large
1703 databases.")
1704 ;; The manual says: "It can be copied under the GNU General Public License
1705 ;; version 2 (GPLv2)."
1706 (license license:gpl2)))
1707
1708 (define-public clipper
1709 (package
1710 (name "clipper")
1711 (version "1.2.1")
1712 (source (origin
1713 (method git-fetch)
1714 (uri (git-reference
1715 (url "https://github.com/YeoLab/clipper.git")
1716 (commit version)))
1717 (file-name (git-file-name name version))
1718 (sha256
1719 (base32
1720 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
1721 (modules '((guix build utils)))
1722 (snippet
1723 '(begin
1724 ;; remove unnecessary setup dependency
1725 (substitute* "setup.py"
1726 (("setup_requires = .*") ""))
1727 #t))))
1728 (build-system python-build-system)
1729 (arguments
1730 `(#:python ,python-2 ; only Python 2 is supported
1731 #:phases
1732 (modify-phases %standard-phases
1733 ;; This is fixed in upstream commit
1734 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
1735 (add-after 'unpack 'fix-typo
1736 (lambda _
1737 (substitute* "clipper/src/readsToWiggle.pyx"
1738 (("^sc.*") ""))
1739 #t)))))
1740 (inputs
1741 `(("htseq" ,python2-htseq)
1742 ("python-pybedtools" ,python2-pybedtools)
1743 ("python-cython" ,python2-cython)
1744 ("python-scikit-learn" ,python2-scikit-learn)
1745 ("python-matplotlib" ,python2-matplotlib)
1746 ("python-pandas" ,python2-pandas)
1747 ("python-pysam" ,python2-pysam)
1748 ("python-numpy" ,python2-numpy)
1749 ("python-scipy" ,python2-scipy)))
1750 (native-inputs
1751 `(("python-mock" ,python2-mock) ; for tests
1752 ("python-nose" ,python2-nose) ; for tests
1753 ("python-pytz" ,python2-pytz))) ; for tests
1754 (home-page "https://github.com/YeoLab/clipper")
1755 (synopsis "CLIP peak enrichment recognition")
1756 (description
1757 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1758 (license license:gpl2)))
1759
1760 (define-public codingquarry
1761 (package
1762 (name "codingquarry")
1763 (version "2.0")
1764 (source (origin
1765 (method url-fetch)
1766 (uri (string-append
1767 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1768 version ".tar.gz"))
1769 (sha256
1770 (base32
1771 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1772 (build-system gnu-build-system)
1773 (arguments
1774 '(#:tests? #f ; no "check" target
1775 #:phases
1776 (modify-phases %standard-phases
1777 (delete 'configure)
1778 (replace 'install
1779 (lambda* (#:key outputs #:allow-other-keys)
1780 (let* ((out (assoc-ref outputs "out"))
1781 (bin (string-append out "/bin"))
1782 (doc (string-append out "/share/doc/codingquarry")))
1783 (install-file "INSTRUCTIONS.pdf" doc)
1784 (copy-recursively "QuarryFiles"
1785 (string-append out "/QuarryFiles"))
1786 (install-file "CodingQuarry" bin)
1787 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1788 (inputs `(("openmpi" ,openmpi)))
1789 (native-search-paths
1790 (list (search-path-specification
1791 (variable "QUARRY_PATH")
1792 (files '("QuarryFiles")))))
1793 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1794 (synopsis "Fungal gene predictor")
1795 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1796 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1797 (home-page "https://sourceforge.net/projects/codingquarry/")
1798 (license license:gpl3+)))
1799
1800 (define-public couger
1801 (package
1802 (name "couger")
1803 (version "1.8.2")
1804 (source (origin
1805 (method url-fetch)
1806 (uri (string-append
1807 "http://couger.oit.duke.edu/static/assets/COUGER"
1808 version ".zip"))
1809 (sha256
1810 (base32
1811 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1812 (build-system gnu-build-system)
1813 (arguments
1814 `(#:tests? #f
1815 #:phases
1816 (modify-phases %standard-phases
1817 (delete 'configure)
1818 (delete 'build)
1819 (replace
1820 'install
1821 (lambda* (#:key outputs #:allow-other-keys)
1822 (let* ((out (assoc-ref outputs "out"))
1823 (bin (string-append out "/bin")))
1824 (copy-recursively "src" (string-append out "/src"))
1825 (mkdir bin)
1826 ;; Add "src" directory to module lookup path.
1827 (substitute* "couger"
1828 (("from argparse")
1829 (string-append "import sys\nsys.path.append(\""
1830 out "\")\nfrom argparse")))
1831 (install-file "couger" bin))
1832 #t))
1833 (add-after
1834 'install 'wrap-program
1835 (lambda* (#:key inputs outputs #:allow-other-keys)
1836 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1837 (let* ((out (assoc-ref outputs "out"))
1838 (path (getenv "PYTHONPATH")))
1839 (wrap-program (string-append out "/bin/couger")
1840 `("PYTHONPATH" ":" prefix (,path))))
1841 #t)))))
1842 (inputs
1843 `(("python" ,python-2)
1844 ("python2-pillow" ,python2-pillow)
1845 ("python2-numpy" ,python2-numpy)
1846 ("python2-scipy" ,python2-scipy)
1847 ("python2-matplotlib" ,python2-matplotlib)))
1848 (propagated-inputs
1849 `(("r-minimal" ,r-minimal)
1850 ("libsvm" ,libsvm)
1851 ("randomjungle" ,randomjungle)))
1852 (native-inputs
1853 `(("unzip" ,unzip)))
1854 (home-page "http://couger.oit.duke.edu")
1855 (synopsis "Identify co-factors in sets of genomic regions")
1856 (description
1857 "COUGER can be applied to any two sets of genomic regions bound by
1858 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1859 putative co-factors that provide specificity to each TF. The framework
1860 determines the genomic targets uniquely-bound by each TF, and identifies a
1861 small set of co-factors that best explain the in vivo binding differences
1862 between the two TFs.
1863
1864 COUGER uses classification algorithms (support vector machines and random
1865 forests) with features that reflect the DNA binding specificities of putative
1866 co-factors. The features are generated either from high-throughput TF-DNA
1867 binding data (from protein binding microarray experiments), or from large
1868 collections of DNA motifs.")
1869 (license license:gpl3+)))
1870
1871 (define-public clustal-omega
1872 (package
1873 (name "clustal-omega")
1874 (version "1.2.4")
1875 (source (origin
1876 (method url-fetch)
1877 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1878 version ".tar.gz"))
1879 (sha256
1880 (base32
1881 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1882 (build-system gnu-build-system)
1883 (inputs
1884 `(("argtable" ,argtable)))
1885 (home-page "http://www.clustal.org/omega/")
1886 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1887 (description
1888 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1889 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1890 of handling data-sets of hundreds of thousands of sequences in reasonable
1891 time.")
1892 (license license:gpl2+)))
1893
1894 (define-public crossmap
1895 (package
1896 (name "crossmap")
1897 (version "0.2.9")
1898 (source (origin
1899 (method url-fetch)
1900 (uri (pypi-uri "CrossMap" version))
1901 (sha256
1902 (base32
1903 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
1904 (build-system python-build-system)
1905 (arguments `(#:python ,python-2))
1906 (inputs
1907 `(("python-bx-python" ,python2-bx-python)
1908 ("python-numpy" ,python2-numpy)
1909 ("python-pysam" ,python2-pysam)
1910 ("zlib" ,zlib)))
1911 (native-inputs
1912 `(("python-cython" ,python2-cython)
1913 ("python-nose" ,python2-nose)))
1914 (home-page "http://crossmap.sourceforge.net/")
1915 (synopsis "Convert genome coordinates between assemblies")
1916 (description
1917 "CrossMap is a program for conversion of genome coordinates or annotation
1918 files between different genome assemblies. It supports most commonly used
1919 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1920 (license license:gpl2+)))
1921
1922 (define-public python-dnaio
1923 (package
1924 (name "python-dnaio")
1925 (version "0.3")
1926 (source
1927 (origin
1928 (method url-fetch)
1929 (uri (pypi-uri "dnaio" version))
1930 (sha256
1931 (base32
1932 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
1933 (build-system python-build-system)
1934 (native-inputs
1935 `(("python-cython" ,python-cython)
1936 ("python-pytest" ,python-pytest)
1937 ("python-xopen" ,python-xopen)))
1938 (home-page "https://github.com/marcelm/dnaio/")
1939 (synopsis "Read FASTA and FASTQ files efficiently")
1940 (description
1941 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
1942 files. The code was previously part of the cutadapt tool.")
1943 (license license:expat)))
1944
1945 (define-public cutadapt
1946 (package
1947 (name "cutadapt")
1948 (version "1.18")
1949 (source (origin
1950 (method git-fetch)
1951 (uri (git-reference
1952 (url "https://github.com/marcelm/cutadapt.git")
1953 (commit (string-append "v" version))))
1954 (file-name (git-file-name name version))
1955 (sha256
1956 (base32
1957 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
1958 (build-system python-build-system)
1959 (inputs
1960 `(("python-dnaio" ,python-dnaio)
1961 ("python-xopen" ,python-xopen)))
1962 (native-inputs
1963 `(("python-cython" ,python-cython)
1964 ("python-pytest" ,python-pytest)))
1965 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1966 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1967 (description
1968 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1969 other types of unwanted sequence from high-throughput sequencing reads.")
1970 (license license:expat)))
1971
1972 (define-public libbigwig
1973 (package
1974 (name "libbigwig")
1975 (version "0.4.2")
1976 (source (origin
1977 (method git-fetch)
1978 (uri (git-reference
1979 (url "https://github.com/dpryan79/libBigWig.git")
1980 (commit version)))
1981 (file-name (string-append name "-" version "-checkout"))
1982 (sha256
1983 (base32
1984 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
1985 (build-system gnu-build-system)
1986 (arguments
1987 `(#:test-target "test"
1988 #:tests? #f ; tests require access to the web
1989 #:make-flags
1990 (list "CC=gcc"
1991 (string-append "prefix=" (assoc-ref %outputs "out")))
1992 #:phases
1993 (modify-phases %standard-phases
1994 (delete 'configure))))
1995 (inputs
1996 `(("zlib" ,zlib)
1997 ("curl" ,curl)))
1998 (native-inputs
1999 `(("doxygen" ,doxygen)
2000 ;; Need for tests
2001 ("python" ,python-2)))
2002 (home-page "https://github.com/dpryan79/libBigWig")
2003 (synopsis "C library for handling bigWig files")
2004 (description
2005 "This package provides a C library for parsing local and remote BigWig
2006 files.")
2007 (license license:expat)))
2008
2009 (define-public python-pybigwig
2010 (package
2011 (name "python-pybigwig")
2012 (version "0.3.12")
2013 (source (origin
2014 (method url-fetch)
2015 (uri (pypi-uri "pyBigWig" version))
2016 (sha256
2017 (base32
2018 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2019 (modules '((guix build utils)))
2020 (snippet
2021 '(begin
2022 ;; Delete bundled libBigWig sources
2023 (delete-file-recursively "libBigWig")
2024 #t))))
2025 (build-system python-build-system)
2026 (arguments
2027 `(#:phases
2028 (modify-phases %standard-phases
2029 (add-after 'unpack 'link-with-libBigWig
2030 (lambda* (#:key inputs #:allow-other-keys)
2031 (substitute* "setup.py"
2032 (("libs=\\[") "libs=[\"BigWig\", "))
2033 #t)))))
2034 (propagated-inputs
2035 `(("python-numpy" ,python-numpy)))
2036 (inputs
2037 `(("libbigwig" ,libbigwig)
2038 ("zlib" ,zlib)
2039 ("curl" ,curl)))
2040 (home-page "https://github.com/dpryan79/pyBigWig")
2041 (synopsis "Access bigWig files in Python using libBigWig")
2042 (description
2043 "This package provides Python bindings to the libBigWig library for
2044 accessing bigWig files.")
2045 (license license:expat)))
2046
2047 (define-public python2-pybigwig
2048 (package-with-python2 python-pybigwig))
2049
2050 (define-public python-dendropy
2051 (package
2052 (name "python-dendropy")
2053 (version "4.4.0")
2054 (source
2055 (origin
2056 (method git-fetch)
2057 ;; Source from GitHub so that tests are included.
2058 (uri (git-reference
2059 (url "https://github.com/jeetsukumaran/DendroPy.git")
2060 (commit (string-append "v" version))))
2061 (file-name (git-file-name name version))
2062 (sha256
2063 (base32
2064 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2065 (build-system python-build-system)
2066 (home-page "http://packages.python.org/DendroPy/")
2067 (synopsis "Library for phylogenetics and phylogenetic computing")
2068 (description
2069 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2070 writing, simulation, processing and manipulation of phylogenetic
2071 trees (phylogenies) and characters.")
2072 (license license:bsd-3)))
2073
2074 (define-public python2-dendropy
2075 (let ((base (package-with-python2 python-dendropy)))
2076 (package
2077 (inherit base)
2078 (arguments
2079 `(#:phases
2080 (modify-phases %standard-phases
2081 (add-after 'unpack 'remove-failing-test
2082 (lambda _
2083 ;; This test fails when the full test suite is run, as documented
2084 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2085 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2086 (("test_collection_comments_and_annotations")
2087 "do_not_test_collection_comments_and_annotations"))
2088 #t)))
2089 ,@(package-arguments base))))))
2090
2091 (define-public python-py2bit
2092 (package
2093 (name "python-py2bit")
2094 (version "0.3.0")
2095 (source
2096 (origin
2097 (method url-fetch)
2098 (uri (pypi-uri "py2bit" version))
2099 (sha256
2100 (base32
2101 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2102 (build-system python-build-system)
2103 (home-page "https://github.com/dpryan79/py2bit")
2104 (synopsis "Access 2bit files using lib2bit")
2105 (description
2106 "This package provides Python bindings for lib2bit to access 2bit files
2107 with Python.")
2108 (license license:expat)))
2109
2110 (define-public deeptools
2111 (package
2112 (name "deeptools")
2113 (version "3.1.3")
2114 (source (origin
2115 (method git-fetch)
2116 (uri (git-reference
2117 (url "https://github.com/deeptools/deepTools.git")
2118 (commit version)))
2119 (file-name (git-file-name name version))
2120 (sha256
2121 (base32
2122 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2123 (build-system python-build-system)
2124 (arguments
2125 `(#:phases
2126 (modify-phases %standard-phases
2127 ;; This phase fails, but it's not needed.
2128 (delete 'reset-gzip-timestamps))))
2129 (inputs
2130 `(("python-plotly" ,python-plotly)
2131 ("python-scipy" ,python-scipy)
2132 ("python-numpy" ,python-numpy)
2133 ("python-numpydoc" ,python-numpydoc)
2134 ("python-matplotlib" ,python-matplotlib)
2135 ("python-pysam" ,python-pysam)
2136 ("python-py2bit" ,python-py2bit)
2137 ("python-pybigwig" ,python-pybigwig)))
2138 (native-inputs
2139 `(("python-mock" ,python-mock) ;for tests
2140 ("python-nose" ,python-nose) ;for tests
2141 ("python-pytz" ,python-pytz))) ;for tests
2142 (home-page "https://github.com/deeptools/deepTools")
2143 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2144 (description
2145 "DeepTools addresses the challenge of handling the large amounts of data
2146 that are now routinely generated from DNA sequencing centers. To do so,
2147 deepTools contains useful modules to process the mapped reads data to create
2148 coverage files in standard bedGraph and bigWig file formats. By doing so,
2149 deepTools allows the creation of normalized coverage files or the comparison
2150 between two files (for example, treatment and control). Finally, using such
2151 normalized and standardized files, multiple visualizations can be created to
2152 identify enrichments with functional annotations of the genome.")
2153 (license license:gpl3+)))
2154
2155 (define-public delly
2156 (package
2157 (name "delly")
2158 (version "0.7.9")
2159 (source (origin
2160 (method git-fetch)
2161 (uri (git-reference
2162 (url "https://github.com/dellytools/delly.git")
2163 (commit (string-append "v" version))))
2164 (file-name (git-file-name name version))
2165 (sha256
2166 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2167 (modules '((guix build utils)))
2168 (snippet
2169 '(begin
2170 (delete-file-recursively "src/htslib")
2171 #t))))
2172 (build-system gnu-build-system)
2173 (arguments
2174 `(#:tests? #f ; There are no tests to run.
2175 #:make-flags
2176 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2177 (string-append "prefix=" (assoc-ref %outputs "out")))
2178 #:phases
2179 (modify-phases %standard-phases
2180 (delete 'configure) ; There is no configure phase.
2181 (add-after 'install 'install-templates
2182 (lambda* (#:key outputs #:allow-other-keys)
2183 (let ((templates (string-append (assoc-ref outputs "out")
2184 "/share/delly/templates")))
2185 (mkdir-p templates)
2186 (copy-recursively "excludeTemplates" templates)
2187 #t))))))
2188 (inputs
2189 `(("boost" ,boost)
2190 ("htslib" ,htslib)
2191 ("zlib" ,zlib)
2192 ("bzip2" ,bzip2)))
2193 (home-page "https://github.com/dellytools/delly")
2194 (synopsis "Integrated structural variant prediction method")
2195 (description "Delly is an integrated structural variant prediction method
2196 that can discover and genotype deletions, tandem duplications, inversions and
2197 translocations at single-nucleotide resolution in short-read massively parallel
2198 sequencing data. It uses paired-ends and split-reads to sensitively and
2199 accurately delineate genomic rearrangements throughout the genome.")
2200 (license license:gpl3+)))
2201
2202 (define-public diamond
2203 (package
2204 (name "diamond")
2205 (version "0.9.22")
2206 (source (origin
2207 (method git-fetch)
2208 (uri (git-reference
2209 (url "https://github.com/bbuchfink/diamond.git")
2210 (commit (string-append "v" version))))
2211 (file-name (git-file-name name version))
2212 (sha256
2213 (base32
2214 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2215 (build-system cmake-build-system)
2216 (arguments
2217 '(#:tests? #f ; no "check" target
2218 #:phases
2219 (modify-phases %standard-phases
2220 (add-after 'unpack 'remove-native-compilation
2221 (lambda _
2222 (substitute* "CMakeLists.txt" (("-march=native") ""))
2223 #t)))))
2224 (inputs
2225 `(("zlib" ,zlib)))
2226 (home-page "https://github.com/bbuchfink/diamond")
2227 (synopsis "Accelerated BLAST compatible local sequence aligner")
2228 (description
2229 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2230 translated DNA query sequences against a protein reference database (BLASTP
2231 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2232 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2233 data and settings.")
2234 (license license:agpl3+)))
2235
2236 (define-public discrover
2237 (package
2238 (name "discrover")
2239 (version "1.6.0")
2240 (source
2241 (origin
2242 (method git-fetch)
2243 (uri (git-reference
2244 (url "https://github.com/maaskola/discrover.git")
2245 (commit version)))
2246 (file-name (git-file-name name version))
2247 (sha256
2248 (base32
2249 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2250 (build-system cmake-build-system)
2251 (arguments
2252 `(#:tests? #f ; there are no tests
2253 #:phases
2254 (modify-phases %standard-phases
2255 (add-after 'unpack 'add-missing-includes
2256 (lambda _
2257 (substitute* "src/executioninformation.hpp"
2258 (("#define EXECUTIONINFORMATION_HPP" line)
2259 (string-append line "\n#include <random>")))
2260 (substitute* "src/plasma/fasta.hpp"
2261 (("#define FASTA_HPP" line)
2262 (string-append line "\n#include <random>")))
2263 #t)))))
2264 (inputs
2265 `(("boost" ,boost)
2266 ("cairo" ,cairo)))
2267 (native-inputs
2268 `(("texlive" ,texlive)
2269 ("imagemagick" ,imagemagick)))
2270 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2271 (synopsis "Discover discriminative nucleotide sequence motifs")
2272 (description "Discrover is a motif discovery method to find binding sites
2273 of nucleic acid binding proteins.")
2274 (license license:gpl3+)))
2275
2276 (define-public eigensoft
2277 (package
2278 (name "eigensoft")
2279 (version "7.2.1")
2280 (source
2281 (origin
2282 (method git-fetch)
2283 (uri (git-reference
2284 (url "https://github.com/DReichLab/EIG.git")
2285 (commit (string-append "v" version))))
2286 (file-name (git-file-name name version))
2287 (sha256
2288 (base32
2289 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2290 (modules '((guix build utils)))
2291 ;; Remove pre-built binaries.
2292 (snippet '(begin
2293 (delete-file-recursively "bin")
2294 (mkdir "bin")
2295 #t))))
2296 (build-system gnu-build-system)
2297 (arguments
2298 `(#:tests? #f ; There are no tests.
2299 #:make-flags '("CC=gcc")
2300 #:phases
2301 (modify-phases %standard-phases
2302 ;; There is no configure phase, but the Makefile is in a
2303 ;; sub-directory.
2304 (replace 'configure
2305 (lambda _ (chdir "src") #t))
2306 ;; The provided install target only copies executables to
2307 ;; the "bin" directory in the build root.
2308 (add-after 'install 'actually-install
2309 (lambda* (#:key outputs #:allow-other-keys)
2310 (let* ((out (assoc-ref outputs "out"))
2311 (bin (string-append out "/bin")))
2312 (for-each (lambda (file)
2313 (install-file file bin))
2314 (find-files "../bin" ".*"))
2315 #t))))))
2316 (inputs
2317 `(("gsl" ,gsl)
2318 ("lapack" ,lapack)
2319 ("openblas" ,openblas)
2320 ("perl" ,perl)
2321 ("gfortran" ,gfortran "lib")))
2322 (home-page "https://github.com/DReichLab/EIG")
2323 (synopsis "Tools for population genetics")
2324 (description "The EIGENSOFT package provides tools for population
2325 genetics and stratification correction. EIGENSOFT implements methods commonly
2326 used in population genetics analyses such as PCA, computation of Tracy-Widom
2327 statistics, and finding related individuals in structured populations. It
2328 comes with a built-in plotting script and supports multiple file formats and
2329 quantitative phenotypes.")
2330 ;; The license of the eigensoft tools is Expat, but since it's
2331 ;; linking with the GNU Scientific Library (GSL) the effective
2332 ;; license is the GPL.
2333 (license license:gpl3+)))
2334
2335 (define-public edirect
2336 (package
2337 (name "edirect")
2338 (version "10.2.20181018")
2339 (source (origin
2340 (method url-fetch)
2341 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2342 "/versions/" version
2343 "/edirect-" version ".tar.gz"))
2344 (sha256
2345 (base32
2346 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2347 (build-system perl-build-system)
2348 (arguments
2349 `(#:phases
2350 (modify-phases %standard-phases
2351 (delete 'configure)
2352 (delete 'build)
2353 (delete 'check) ; simple check after install
2354 (replace 'install
2355 (lambda* (#:key outputs #:allow-other-keys)
2356 (install-file "edirect.pl"
2357 (string-append (assoc-ref outputs "out") "/bin"))
2358 #t))
2359 (add-after 'install 'wrap-program
2360 (lambda* (#:key outputs #:allow-other-keys)
2361 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2362 (let* ((out (assoc-ref outputs "out"))
2363 (path (getenv "PERL5LIB")))
2364 (wrap-program (string-append out "/bin/edirect.pl")
2365 `("PERL5LIB" ":" prefix (,path))))
2366 #t))
2367 (add-after 'wrap-program 'check
2368 (lambda* (#:key outputs #:allow-other-keys)
2369 (invoke (string-append (assoc-ref outputs "out")
2370 "/bin/edirect.pl")
2371 "-filter" "-help")
2372 #t)))))
2373 (inputs
2374 `(("perl-html-parser" ,perl-html-parser)
2375 ("perl-encode-locale" ,perl-encode-locale)
2376 ("perl-file-listing" ,perl-file-listing)
2377 ("perl-html-tagset" ,perl-html-tagset)
2378 ("perl-html-tree" ,perl-html-tree)
2379 ("perl-http-cookies" ,perl-http-cookies)
2380 ("perl-http-date" ,perl-http-date)
2381 ("perl-http-message" ,perl-http-message)
2382 ("perl-http-negotiate" ,perl-http-negotiate)
2383 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2384 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2385 ("perl-net-http" ,perl-net-http)
2386 ("perl-uri" ,perl-uri)
2387 ("perl-www-robotrules" ,perl-www-robotrules)
2388 ("perl-xml-simple" ,perl-xml-simple)
2389 ("perl" ,perl)))
2390 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2391 (synopsis "Tools for accessing the NCBI's set of databases")
2392 (description
2393 "Entrez Direct (EDirect) is a method for accessing the National Center
2394 for Biotechnology Information's (NCBI) set of interconnected
2395 databases (publication, sequence, structure, gene, variation, expression,
2396 etc.) from a terminal. Functions take search terms from command-line
2397 arguments. Individual operations are combined to build multi-step queries.
2398 Record retrieval and formatting normally complete the process.
2399
2400 EDirect also provides an argument-driven function that simplifies the
2401 extraction of data from document summaries or other results that are returned
2402 in structured XML format. This can eliminate the need for writing custom
2403 software to answer ad hoc questions.")
2404 (license license:public-domain)))
2405
2406 (define-public exonerate
2407 (package
2408 (name "exonerate")
2409 (version "2.4.0")
2410 (source
2411 (origin
2412 (method url-fetch)
2413 (uri
2414 (string-append
2415 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2416 "exonerate-" version ".tar.gz"))
2417 (sha256
2418 (base32
2419 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2420 (build-system gnu-build-system)
2421 (arguments
2422 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2423 (native-inputs
2424 `(("pkg-config" ,pkg-config)))
2425 (inputs
2426 `(("glib" ,glib)))
2427 (home-page
2428 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2429 (synopsis "Generic tool for biological sequence alignment")
2430 (description
2431 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2432 the alignment of sequences using a many alignment models, either exhaustive
2433 dynamic programming or a variety of heuristics.")
2434 (license license:gpl3)))
2435
2436 (define-public express
2437 (package
2438 (name "express")
2439 (version "1.5.1")
2440 (source (origin
2441 (method url-fetch)
2442 (uri
2443 (string-append
2444 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2445 version "/express-" version "-src.tgz"))
2446 (sha256
2447 (base32
2448 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2449 (build-system cmake-build-system)
2450 (arguments
2451 `(#:tests? #f ;no "check" target
2452 #:phases
2453 (modify-phases %standard-phases
2454 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2455 (lambda* (#:key inputs #:allow-other-keys)
2456 (substitute* "CMakeLists.txt"
2457 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2458 "set(Boost_USE_STATIC_LIBS OFF)")
2459 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2460 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2461 (substitute* "src/CMakeLists.txt"
2462 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2463 (string-append (assoc-ref inputs "bamtools") "/lib"))
2464 (("libprotobuf.a") "libprotobuf.so"))
2465 #t)))))
2466 (inputs
2467 `(("boost" ,boost)
2468 ("bamtools" ,bamtools)
2469 ("protobuf" ,protobuf)
2470 ("zlib" ,zlib)))
2471 (home-page "http://bio.math.berkeley.edu/eXpress")
2472 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2473 (description
2474 "eXpress is a streaming tool for quantifying the abundances of a set of
2475 target sequences from sampled subsequences. Example applications include
2476 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2477 analysis (from RNA-Seq), transcription factor binding quantification in
2478 ChIP-Seq, and analysis of metagenomic data.")
2479 (license license:artistic2.0)))
2480
2481 (define-public express-beta-diversity
2482 (package
2483 (name "express-beta-diversity")
2484 (version "1.0.8")
2485 (source (origin
2486 (method git-fetch)
2487 (uri (git-reference
2488 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2489 (commit (string-append "v" version))))
2490 (file-name (git-file-name name version))
2491 (sha256
2492 (base32
2493 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2494 (build-system gnu-build-system)
2495 (arguments
2496 `(#:phases
2497 (modify-phases %standard-phases
2498 (delete 'configure)
2499 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2500 (replace 'check
2501 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2502 (replace 'install
2503 (lambda* (#:key outputs #:allow-other-keys)
2504 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2505 (install-file "../scripts/convertToEBD.py" bin)
2506 (install-file "../bin/ExpressBetaDiversity" bin)
2507 #t))))))
2508 (inputs
2509 `(("python" ,python-2)))
2510 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2511 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2512 (description
2513 "Express Beta Diversity (EBD) calculates ecological beta diversity
2514 (dissimilarity) measures between biological communities. EBD implements a
2515 variety of diversity measures including those that make use of phylogenetic
2516 similarity of community members.")
2517 (license license:gpl3+)))
2518
2519 (define-public fasttree
2520 (package
2521 (name "fasttree")
2522 (version "2.1.10")
2523 (source (origin
2524 (method url-fetch)
2525 (uri (string-append
2526 "http://www.microbesonline.org/fasttree/FastTree-"
2527 version ".c"))
2528 (sha256
2529 (base32
2530 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2531 (build-system gnu-build-system)
2532 (arguments
2533 `(#:tests? #f ; no "check" target
2534 #:phases
2535 (modify-phases %standard-phases
2536 (delete 'unpack)
2537 (delete 'configure)
2538 (replace 'build
2539 (lambda* (#:key source #:allow-other-keys)
2540 (invoke "gcc"
2541 "-O3"
2542 "-finline-functions"
2543 "-funroll-loops"
2544 "-Wall"
2545 "-o"
2546 "FastTree"
2547 source
2548 "-lm")
2549 (invoke "gcc"
2550 "-DOPENMP"
2551 "-fopenmp"
2552 "-O3"
2553 "-finline-functions"
2554 "-funroll-loops"
2555 "-Wall"
2556 "-o"
2557 "FastTreeMP"
2558 source
2559 "-lm")
2560 #t))
2561 (replace 'install
2562 (lambda* (#:key outputs #:allow-other-keys)
2563 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2564 (install-file "FastTree" bin)
2565 (install-file "FastTreeMP" bin)
2566 #t))))))
2567 (home-page "http://www.microbesonline.org/fasttree")
2568 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2569 (description
2570 "FastTree can handle alignments with up to a million of sequences in a
2571 reasonable amount of time and memory. For large alignments, FastTree is
2572 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2573 (license license:gpl2+)))
2574
2575 (define-public fastx-toolkit
2576 (package
2577 (name "fastx-toolkit")
2578 (version "0.0.14")
2579 (source (origin
2580 (method url-fetch)
2581 (uri
2582 (string-append
2583 "https://github.com/agordon/fastx_toolkit/releases/download/"
2584 version "/fastx_toolkit-" version ".tar.bz2"))
2585 (sha256
2586 (base32
2587 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2588 (build-system gnu-build-system)
2589 (inputs
2590 `(("libgtextutils" ,libgtextutils)))
2591 (native-inputs
2592 `(("pkg-config" ,pkg-config)))
2593 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2594 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2595 (description
2596 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2597 FASTA/FASTQ files preprocessing.
2598
2599 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2600 containing multiple short-reads sequences. The main processing of such
2601 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2602 is sometimes more productive to preprocess the files before mapping the
2603 sequences to the genome---manipulating the sequences to produce better mapping
2604 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2605 (license license:agpl3+)))
2606
2607 (define-public flexbar
2608 (package
2609 (name "flexbar")
2610 (version "3.4.0")
2611 (source (origin
2612 (method git-fetch)
2613 (uri (git-reference
2614 (url "https://github.com/seqan/flexbar.git")
2615 (commit (string-append "v" version))))
2616 (file-name (git-file-name name version))
2617 (sha256
2618 (base32
2619 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
2620 (build-system cmake-build-system)
2621 (arguments
2622 `(#:phases
2623 (modify-phases %standard-phases
2624 (replace 'check
2625 (lambda* (#:key outputs #:allow-other-keys)
2626 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
2627 (with-directory-excursion "../source/test"
2628 (invoke "bash" "flexbar_test.sh"))
2629 #t))
2630 (replace 'install
2631 (lambda* (#:key outputs #:allow-other-keys)
2632 (let* ((out (string-append (assoc-ref outputs "out")))
2633 (bin (string-append out "/bin/")))
2634 (install-file "flexbar" bin))
2635 #t)))))
2636 (inputs
2637 `(("tbb" ,tbb)
2638 ("zlib" ,zlib)))
2639 (native-inputs
2640 `(("pkg-config" ,pkg-config)
2641 ("seqan" ,seqan)))
2642 (home-page "https://github.com/seqan/flexbar")
2643 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2644 (description
2645 "Flexbar preprocesses high-throughput nucleotide sequencing data
2646 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2647 Moreover, trimming and filtering features are provided. Flexbar increases
2648 read mapping rates and improves genome and transcriptome assemblies. It
2649 supports next-generation sequencing data in fasta/q and csfasta/q format from
2650 Illumina, Roche 454, and the SOLiD platform.")
2651 (license license:bsd-3)))
2652
2653 (define-public fraggenescan
2654 (package
2655 (name "fraggenescan")
2656 (version "1.30")
2657 (source
2658 (origin
2659 (method url-fetch)
2660 (uri
2661 (string-append "mirror://sourceforge/fraggenescan/"
2662 "FragGeneScan" version ".tar.gz"))
2663 (sha256
2664 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2665 (build-system gnu-build-system)
2666 (arguments
2667 `(#:phases
2668 (modify-phases %standard-phases
2669 (delete 'configure)
2670 (add-before 'build 'patch-paths
2671 (lambda* (#:key outputs #:allow-other-keys)
2672 (let* ((out (string-append (assoc-ref outputs "out")))
2673 (share (string-append out "/share/fraggenescan/")))
2674 (substitute* "run_FragGeneScan.pl"
2675 (("system\\(\"rm")
2676 (string-append "system(\"" (which "rm")))
2677 (("system\\(\"mv")
2678 (string-append "system(\"" (which "mv")))
2679 (("\\\"awk") (string-append "\"" (which "awk")))
2680 ;; This script and other programs expect the training files
2681 ;; to be in the non-standard location bin/train/XXX. Change
2682 ;; this to be share/fraggenescan/train/XXX instead.
2683 (("^\\$train.file = \\$dir.*")
2684 (string-append "$train_file = \""
2685 share
2686 "train/\".$FGS_train_file;")))
2687 (substitute* "run_hmm.c"
2688 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2689 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2690 #t))
2691 (replace 'build
2692 (lambda _ (and (zero? (system* "make" "clean"))
2693 (zero? (system* "make" "fgs")))))
2694 (replace 'install
2695 (lambda* (#:key outputs #:allow-other-keys)
2696 (let* ((out (string-append (assoc-ref outputs "out")))
2697 (bin (string-append out "/bin/"))
2698 (share (string-append out "/share/fraggenescan/train")))
2699 (install-file "run_FragGeneScan.pl" bin)
2700 (install-file "FragGeneScan" bin)
2701 (copy-recursively "train" share))))
2702 (delete 'check)
2703 (add-after 'install 'post-install-check
2704 ;; In lieu of 'make check', run one of the examples and check the
2705 ;; output files gets created.
2706 (lambda* (#:key outputs #:allow-other-keys)
2707 (let* ((out (string-append (assoc-ref outputs "out")))
2708 (bin (string-append out "/bin/"))
2709 (frag (string-append bin "run_FragGeneScan.pl")))
2710 (and (zero? (system* frag ; Test complete genome.
2711 "-genome=./example/NC_000913.fna"
2712 "-out=./test2"
2713 "-complete=1"
2714 "-train=complete"))
2715 (file-exists? "test2.faa")
2716 (file-exists? "test2.ffn")
2717 (file-exists? "test2.gff")
2718 (file-exists? "test2.out")
2719 (zero? (system* ; Test incomplete sequences.
2720 frag
2721 "-genome=./example/NC_000913-fgs.ffn"
2722 "-out=out"
2723 "-complete=0"
2724 "-train=454_30")))))))))
2725 (inputs
2726 `(("perl" ,perl)
2727 ("python" ,python-2))) ;not compatible with python 3.
2728 (home-page "https://sourceforge.net/projects/fraggenescan/")
2729 (synopsis "Finds potentially fragmented genes in short reads")
2730 (description
2731 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2732 short and error-prone DNA sequencing reads. It can also be applied to predict
2733 genes in incomplete assemblies or complete genomes.")
2734 ;; GPL3+ according to private correspondense with the authors.
2735 (license license:gpl3+)))
2736
2737 (define-public fxtract
2738 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2739 (package
2740 (name "fxtract")
2741 (version "2.3")
2742 (source
2743 (origin
2744 (method url-fetch)
2745 (uri (string-append
2746 "https://github.com/ctSkennerton/fxtract/archive/"
2747 version ".tar.gz"))
2748 (file-name (string-append "ctstennerton-util-"
2749 (string-take util-commit 7)
2750 "-checkout"))
2751 (sha256
2752 (base32
2753 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2754 (build-system gnu-build-system)
2755 (arguments
2756 `(#:make-flags (list
2757 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2758 "CC=gcc")
2759 #:test-target "fxtract_test"
2760 #:phases
2761 (modify-phases %standard-phases
2762 (delete 'configure)
2763 (add-before 'build 'copy-util
2764 (lambda* (#:key inputs #:allow-other-keys)
2765 (rmdir "util")
2766 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2767 #t))
2768 ;; Do not use make install as this requires additional dependencies.
2769 (replace 'install
2770 (lambda* (#:key outputs #:allow-other-keys)
2771 (let* ((out (assoc-ref outputs "out"))
2772 (bin (string-append out"/bin")))
2773 (install-file "fxtract" bin)
2774 #t))))))
2775 (inputs
2776 `(("pcre" ,pcre)
2777 ("zlib" ,zlib)))
2778 (native-inputs
2779 ;; ctskennerton-util is licensed under GPL2.
2780 `(("ctskennerton-util"
2781 ,(origin
2782 (method git-fetch)
2783 (uri (git-reference
2784 (url "https://github.com/ctSkennerton/util.git")
2785 (commit util-commit)))
2786 (file-name (string-append
2787 "ctstennerton-util-" util-commit "-checkout"))
2788 (sha256
2789 (base32
2790 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2791 (home-page "https://github.com/ctSkennerton/fxtract")
2792 (synopsis "Extract sequences from FASTA and FASTQ files")
2793 (description
2794 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2795 or FASTQ) file given a subsequence. It uses a simple substring search for
2796 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2797 lookups or multi-pattern searching as required. By default fxtract looks in
2798 the sequence of each record but can also be told to look in the header,
2799 comment or quality sections.")
2800 ;; 'util' requires SSE instructions.
2801 (supported-systems '("x86_64-linux"))
2802 (license license:expat))))
2803
2804 (define-public gemma
2805 (package
2806 (name "gemma")
2807 (version "0.96")
2808 (source (origin
2809 (method url-fetch)
2810 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2811 version ".tar.gz"))
2812 (file-name (string-append name "-" version ".tar.gz"))
2813 (sha256
2814 (base32
2815 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2816 (patches (search-patches "gemma-intel-compat.patch"))))
2817 (inputs
2818 `(("gsl" ,gsl)
2819 ("lapack" ,lapack)
2820 ("zlib" ,zlib)))
2821 (build-system gnu-build-system)
2822 (arguments
2823 `(#:make-flags
2824 '(,@(match (%current-system)
2825 ("x86_64-linux"
2826 '("FORCE_DYNAMIC=1"))
2827 ("i686-linux"
2828 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2829 (_
2830 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2831 #:phases
2832 (modify-phases %standard-phases
2833 (delete 'configure)
2834 (add-before 'build 'bin-mkdir
2835 (lambda _
2836 (mkdir-p "bin")
2837 #t))
2838 (replace 'install
2839 (lambda* (#:key outputs #:allow-other-keys)
2840 (let ((out (assoc-ref outputs "out")))
2841 (install-file "bin/gemma"
2842 (string-append
2843 out "/bin")))
2844 #t)))
2845 #:tests? #f)) ; no tests included yet
2846 (home-page "https://github.com/xiangzhou/GEMMA")
2847 (synopsis "Tool for genome-wide efficient mixed model association")
2848 (description
2849 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2850 standard linear mixed model resolver with application in genome-wide
2851 association studies (GWAS).")
2852 (license license:gpl3)))
2853
2854 (define-public grit
2855 (package
2856 (name "grit")
2857 (version "2.0.2")
2858 (source (origin
2859 (method url-fetch)
2860 (uri (string-append
2861 "https://github.com/nboley/grit/archive/"
2862 version ".tar.gz"))
2863 (file-name (string-append name "-" version ".tar.gz"))
2864 (sha256
2865 (base32
2866 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2867 (build-system python-build-system)
2868 (arguments
2869 `(#:python ,python-2
2870 #:phases
2871 (modify-phases %standard-phases
2872 (add-after 'unpack 'generate-from-cython-sources
2873 (lambda* (#:key inputs outputs #:allow-other-keys)
2874 ;; Delete these C files to force fresh generation from pyx sources.
2875 (delete-file "grit/sparsify_support_fns.c")
2876 (delete-file "grit/call_peaks_support_fns.c")
2877 (substitute* "setup.py"
2878 (("Cython.Setup") "Cython.Build")
2879 ;; Add numpy include path to fix compilation
2880 (("pyx\", \\]")
2881 (string-append "pyx\", ], include_dirs = ['"
2882 (assoc-ref inputs "python-numpy")
2883 "/lib/python2.7/site-packages/numpy/core/include/"
2884 "']")))
2885 #t)))))
2886 (inputs
2887 `(("python-scipy" ,python2-scipy)
2888 ("python-numpy" ,python2-numpy)
2889 ("python-pysam" ,python2-pysam)
2890 ("python-networkx" ,python2-networkx)))
2891 (native-inputs
2892 `(("python-cython" ,python2-cython)))
2893 (home-page "http://grit-bio.org")
2894 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2895 (description
2896 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2897 full length transcript models. When none of these data sources are available,
2898 GRIT can be run by providing a candidate set of TES or TSS sites. In
2899 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2900 also be run in quantification mode, where it uses a provided GTF file and just
2901 estimates transcript expression.")
2902 (license license:gpl3+)))
2903
2904 (define-public hisat
2905 (package
2906 (name "hisat")
2907 (version "0.1.4")
2908 (source (origin
2909 (method url-fetch)
2910 (uri (string-append
2911 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2912 version "-beta-source.zip"))
2913 (sha256
2914 (base32
2915 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2916 (build-system gnu-build-system)
2917 (arguments
2918 `(#:tests? #f ;no check target
2919 #:make-flags '("allall"
2920 ;; Disable unsupported `popcnt' instructions on
2921 ;; architectures other than x86_64
2922 ,@(if (string-prefix? "x86_64"
2923 (or (%current-target-system)
2924 (%current-system)))
2925 '()
2926 '("POPCNT_CAPABILITY=0")))
2927 #:phases
2928 (modify-phases %standard-phases
2929 (add-after 'unpack 'patch-sources
2930 (lambda _
2931 ;; XXX Cannot use snippet because zip files are not supported
2932 (substitute* "Makefile"
2933 (("^CC = .*$") "CC = gcc")
2934 (("^CPP = .*$") "CPP = g++")
2935 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2936 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2937 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2938 (substitute* '("hisat-build" "hisat-inspect")
2939 (("/usr/bin/env") (which "env")))
2940 #t))
2941 (replace 'install
2942 (lambda* (#:key outputs #:allow-other-keys)
2943 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2944 (for-each (lambda (file)
2945 (install-file file bin))
2946 (find-files
2947 "."
2948 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2949 #t))
2950 (delete 'configure))))
2951 (native-inputs
2952 `(("unzip" ,unzip)))
2953 (inputs
2954 `(("perl" ,perl)
2955 ("python" ,python)
2956 ("zlib" ,zlib)))
2957 ;; Non-portable SSE instructions are used so building fails on platforms
2958 ;; other than x86_64.
2959 (supported-systems '("x86_64-linux"))
2960 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2961 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2962 (description
2963 "HISAT is a fast and sensitive spliced alignment program for mapping
2964 RNA-seq reads. In addition to one global FM index that represents a whole
2965 genome, HISAT uses a large set of small FM indexes that collectively cover the
2966 whole genome. These small indexes (called local indexes) combined with
2967 several alignment strategies enable effective alignment of RNA-seq reads, in
2968 particular, reads spanning multiple exons.")
2969 (license license:gpl3+)))
2970
2971 (define-public hisat2
2972 (package
2973 (name "hisat2")
2974 (version "2.0.5")
2975 (source
2976 (origin
2977 (method url-fetch)
2978 ;; FIXME: a better source URL is
2979 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2980 ;; "/downloads/hisat2-" version "-source.zip")
2981 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2982 ;; but it is currently unavailable.
2983 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2984 (file-name (string-append name "-" version ".tar.gz"))
2985 (sha256
2986 (base32
2987 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2988 (build-system gnu-build-system)
2989 (arguments
2990 `(#:tests? #f ; no check target
2991 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2992 #:modules ((guix build gnu-build-system)
2993 (guix build utils)
2994 (srfi srfi-26))
2995 #:phases
2996 (modify-phases %standard-phases
2997 (add-after 'unpack 'make-deterministic
2998 (lambda _
2999 (substitute* "Makefile"
3000 (("`date`") "0"))
3001 #t))
3002 (delete 'configure)
3003 (replace 'install
3004 (lambda* (#:key outputs #:allow-other-keys)
3005 (let* ((out (assoc-ref outputs "out"))
3006 (bin (string-append out "/bin/"))
3007 (doc (string-append out "/share/doc/hisat2/")))
3008 (for-each
3009 (cut install-file <> bin)
3010 (find-files "."
3011 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3012 (mkdir-p doc)
3013 (install-file "doc/manual.inc.html" doc))
3014 #t)))))
3015 (native-inputs
3016 `(("unzip" ,unzip) ; needed for archive from ftp
3017 ("perl" ,perl)
3018 ("pandoc" ,ghc-pandoc))) ; for documentation
3019 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3020 (synopsis "Graph-based alignment of genomic sequencing reads")
3021 (description "HISAT2 is a fast and sensitive alignment program for mapping
3022 next-generation sequencing reads (both DNA and RNA) to a population of human
3023 genomes (as well as to a single reference genome). In addition to using one
3024 global @dfn{graph FM} (GFM) index that represents a population of human
3025 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3026 the whole genome. These small indexes, combined with several alignment
3027 strategies, enable rapid and accurate alignment of sequencing reads. This new
3028 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3029 ;; HISAT2 contains files from Bowtie2, which is released under
3030 ;; GPLv2 or later. The HISAT2 source files are released under
3031 ;; GPLv3 or later.
3032 (license license:gpl3+)))
3033
3034 (define-public hmmer
3035 (package
3036 (name "hmmer")
3037 (version "3.2.1")
3038 (source
3039 (origin
3040 (method url-fetch)
3041 (uri (string-append
3042 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3043 (sha256
3044 (base32
3045 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3046 (build-system gnu-build-system)
3047 (native-inputs `(("perl" ,perl)))
3048 (home-page "http://hmmer.org/")
3049 (synopsis "Biosequence analysis using profile hidden Markov models")
3050 (description
3051 "HMMER is used for searching sequence databases for homologs of protein
3052 sequences, and for making protein sequence alignments. It implements methods
3053 using probabilistic models called profile hidden Markov models (profile
3054 HMMs).")
3055 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3056 ;; platforms.
3057 (supported-systems '("x86_64-linux" "i686-linux"))
3058 (license license:bsd-3)))
3059
3060 (define-public htseq
3061 (package
3062 (name "htseq")
3063 (version "0.9.1")
3064 (source (origin
3065 (method url-fetch)
3066 (uri (pypi-uri "HTSeq" version))
3067 (sha256
3068 (base32
3069 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3070 (build-system python-build-system)
3071 (native-inputs
3072 `(("python-cython" ,python-cython)))
3073 ;; Numpy needs to be propagated when htseq is used as a Python library.
3074 (propagated-inputs
3075 `(("python-numpy" ,python-numpy)))
3076 (inputs
3077 `(("python-pysam" ,python-pysam)
3078 ("python-matplotlib" ,python-matplotlib)))
3079 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3080 (synopsis "Analysing high-throughput sequencing data with Python")
3081 (description
3082 "HTSeq is a Python package that provides infrastructure to process data
3083 from high-throughput sequencing assays.")
3084 (license license:gpl3+)))
3085
3086 (define-public python2-htseq
3087 (package-with-python2 htseq))
3088
3089 (define-public java-htsjdk
3090 (package
3091 (name "java-htsjdk")
3092 (version "2.3.0") ; last version without build dependency on gradle
3093 (source (origin
3094 (method url-fetch)
3095 (uri (string-append
3096 "https://github.com/samtools/htsjdk/archive/"
3097 version ".tar.gz"))
3098 (file-name (string-append name "-" version ".tar.gz"))
3099 (sha256
3100 (base32
3101 "1ibhzzxsfc38nqyk9r8zqj6blfc1kh26iirypd4q6n90hs2m6nyq"))
3102 (modules '((guix build utils)))
3103 (snippet
3104 ;; Delete pre-built binaries
3105 '(begin
3106 (delete-file-recursively "lib")
3107 (mkdir-p "lib")
3108 #t))))
3109 (build-system ant-build-system)
3110 (arguments
3111 `(#:tests? #f ; test require Internet access
3112 #:jdk ,icedtea-8
3113 #:make-flags
3114 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3115 "/share/java/htsjdk/"))
3116 #:build-target "all"
3117 #:phases
3118 (modify-phases %standard-phases
3119 ;; The build phase also installs the jars
3120 (delete 'install))))
3121 (inputs
3122 `(("java-ngs" ,java-ngs)
3123 ("java-snappy-1" ,java-snappy-1)
3124 ("java-commons-compress" ,java-commons-compress)
3125 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3126 ("java-commons-jexl-2" ,java-commons-jexl-2)
3127 ("java-xz" ,java-xz)))
3128 (native-inputs
3129 `(("java-testng" ,java-testng)))
3130 (home-page "http://samtools.github.io/htsjdk/")
3131 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3132 (description
3133 "HTSJDK is an implementation of a unified Java library for accessing
3134 common file formats, such as SAM and VCF, used for high-throughput
3135 sequencing (HTS) data. There are also an number of useful utilities for
3136 manipulating HTS data.")
3137 (license license:expat)))
3138
3139 (define-public java-htsjdk-latest
3140 (package
3141 (name "java-htsjdk")
3142 (version "2.14.3")
3143 (source (origin
3144 (method git-fetch)
3145 (uri (git-reference
3146 (url "https://github.com/samtools/htsjdk.git")
3147 (commit version)))
3148 (file-name (string-append name "-" version "-checkout"))
3149 (sha256
3150 (base32
3151 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3152 (build-system ant-build-system)
3153 (arguments
3154 `(#:tests? #f ; test require Scala
3155 #:jdk ,icedtea-8
3156 #:jar-name "htsjdk.jar"
3157 #:phases
3158 (modify-phases %standard-phases
3159 (add-after 'unpack 'remove-useless-build.xml
3160 (lambda _ (delete-file "build.xml") #t))
3161 ;; The tests require the scalatest package.
3162 (add-after 'unpack 'remove-tests
3163 (lambda _ (delete-file-recursively "src/test") #t)))))
3164 (inputs
3165 `(("java-ngs" ,java-ngs)
3166 ("java-snappy-1" ,java-snappy-1)
3167 ("java-commons-compress" ,java-commons-compress)
3168 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3169 ("java-commons-jexl-2" ,java-commons-jexl-2)
3170 ("java-xz" ,java-xz)))
3171 (native-inputs
3172 `(("java-junit" ,java-junit)))
3173 (home-page "http://samtools.github.io/htsjdk/")
3174 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3175 (description
3176 "HTSJDK is an implementation of a unified Java library for accessing
3177 common file formats, such as SAM and VCF, used for high-throughput
3178 sequencing (HTS) data. There are also an number of useful utilities for
3179 manipulating HTS data.")
3180 (license license:expat)))
3181
3182 ;; This is needed for picard 2.10.3
3183 (define-public java-htsjdk-2.10.1
3184 (package (inherit java-htsjdk-latest)
3185 (name "java-htsjdk")
3186 (version "2.10.1")
3187 (source (origin
3188 (method git-fetch)
3189 (uri (git-reference
3190 (url "https://github.com/samtools/htsjdk.git")
3191 (commit version)))
3192 (file-name (string-append name "-" version "-checkout"))
3193 (sha256
3194 (base32
3195 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3196 (build-system ant-build-system)
3197 (arguments
3198 `(#:tests? #f ; tests require Scala
3199 #:jdk ,icedtea-8
3200 #:jar-name "htsjdk.jar"
3201 #:phases
3202 (modify-phases %standard-phases
3203 (add-after 'unpack 'remove-useless-build.xml
3204 (lambda _ (delete-file "build.xml") #t))
3205 ;; The tests require the scalatest package.
3206 (add-after 'unpack 'remove-tests
3207 (lambda _ (delete-file-recursively "src/test") #t)))))))
3208
3209 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3210 ;; recent version of java-htsjdk, which depends on gradle.
3211 (define-public java-picard
3212 (package
3213 (name "java-picard")
3214 (version "2.3.0")
3215 (source (origin
3216 (method git-fetch)
3217 (uri (git-reference
3218 (url "https://github.com/broadinstitute/picard.git")
3219 (commit version)))
3220 (file-name (string-append "java-picard-" version "-checkout"))
3221 (sha256
3222 (base32
3223 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3224 (modules '((guix build utils)))
3225 (snippet
3226 '(begin
3227 ;; Delete pre-built binaries.
3228 (delete-file-recursively "lib")
3229 (mkdir-p "lib")
3230 (substitute* "build.xml"
3231 ;; Remove build-time dependency on git.
3232 (("failifexecutionfails=\"true\"")
3233 "failifexecutionfails=\"false\"")
3234 ;; Use our htsjdk.
3235 (("depends=\"compile-htsjdk, ")
3236 "depends=\"")
3237 (("depends=\"compile-htsjdk-tests, ")
3238 "depends=\"")
3239 ;; Build picard-lib.jar before building picard.jar
3240 (("name=\"picard-jar\" depends=\"" line)
3241 (string-append line "picard-lib-jar, ")))
3242 #t))))
3243 (build-system ant-build-system)
3244 (arguments
3245 `(#:build-target "picard-jar"
3246 #:test-target "test"
3247 ;; Tests require jacoco:coverage.
3248 #:tests? #f
3249 #:make-flags
3250 (list (string-append "-Dhtsjdk_lib_dir="
3251 (assoc-ref %build-inputs "java-htsjdk")
3252 "/share/java/htsjdk/")
3253 "-Dhtsjdk-classes=dist/tmp"
3254 (string-append "-Dhtsjdk-version="
3255 ,(package-version java-htsjdk)))
3256 #:jdk ,icedtea-8
3257 #:phases
3258 (modify-phases %standard-phases
3259 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3260 (delete 'generate-jar-indices)
3261 (add-after 'unpack 'use-our-htsjdk
3262 (lambda* (#:key inputs #:allow-other-keys)
3263 (substitute* "build.xml"
3264 (("\\$\\{htsjdk\\}/lib")
3265 (string-append (assoc-ref inputs "java-htsjdk")
3266 "/share/java/htsjdk/")))
3267 #t))
3268 (add-after 'unpack 'make-test-target-independent
3269 (lambda* (#:key inputs #:allow-other-keys)
3270 (substitute* "build.xml"
3271 (("name=\"test\" depends=\"compile, ")
3272 "name=\"test\" depends=\""))
3273 #t))
3274 (replace 'install (install-jars "dist")))))
3275 (inputs
3276 `(("java-htsjdk" ,java-htsjdk)
3277 ("java-guava" ,java-guava)))
3278 (native-inputs
3279 `(("java-testng" ,java-testng)))
3280 (home-page "http://broadinstitute.github.io/picard/")
3281 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3282 (description "Picard is a set of Java command line tools for manipulating
3283 high-throughput sequencing (HTS) data and formats. Picard is implemented
3284 using the HTSJDK Java library to support accessing file formats that are
3285 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3286 VCF.")
3287 (license license:expat)))
3288
3289 ;; This is needed for dropseq-tools
3290 (define-public java-picard-2.10.3
3291 (package
3292 (name "java-picard")
3293 (version "2.10.3")
3294 (source (origin
3295 (method git-fetch)
3296 (uri (git-reference
3297 (url "https://github.com/broadinstitute/picard.git")
3298 (commit version)))
3299 (file-name (string-append "java-picard-" version "-checkout"))
3300 (sha256
3301 (base32
3302 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3303 (build-system ant-build-system)
3304 (arguments
3305 `(#:jar-name "picard.jar"
3306 ;; Tests require jacoco:coverage.
3307 #:tests? #f
3308 #:jdk ,icedtea-8
3309 #:main-class "picard.cmdline.PicardCommandLine"
3310 #:modules ((guix build ant-build-system)
3311 (guix build utils)
3312 (guix build java-utils)
3313 (sxml simple)
3314 (sxml transform)
3315 (sxml xpath))
3316 #:phases
3317 (modify-phases %standard-phases
3318 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3319 (delete 'generate-jar-indices)
3320 (add-after 'unpack 'remove-useless-build.xml
3321 (lambda _ (delete-file "build.xml") #t))
3322 ;; This is necessary to ensure that htsjdk is found when using
3323 ;; picard.jar as an executable.
3324 (add-before 'build 'edit-classpath-in-manifest
3325 (lambda* (#:key inputs #:allow-other-keys)
3326 (chmod "build.xml" #o664)
3327 (call-with-output-file "build.xml.new"
3328 (lambda (port)
3329 (sxml->xml
3330 (pre-post-order
3331 (with-input-from-file "build.xml"
3332 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3333 `((target . ,(lambda (tag . kids)
3334 (let ((name ((sxpath '(name *text*))
3335 (car kids)))
3336 ;; FIXME: We're breaking the line
3337 ;; early with a dummy path to
3338 ;; ensure that the store reference
3339 ;; isn't broken apart and can still
3340 ;; be found by the reference
3341 ;; scanner.
3342 (msg (format #f
3343 "\
3344 Class-Path: /~a \
3345 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3346 ;; maximum line length is 70
3347 (string-tabulate (const #\b) 57)
3348 (assoc-ref inputs "java-htsjdk"))))
3349 (if (member "manifest" name)
3350 `(,tag ,@kids
3351 (replaceregexp
3352 (@ (file "${manifest.file}")
3353 (match "\\r\\n\\r\\n")
3354 (replace "${line.separator}")))
3355 (echo
3356 (@ (message ,msg)
3357 (file "${manifest.file}")
3358 (append "true"))))
3359 `(,tag ,@kids)))))
3360 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3361 (*text* . ,(lambda (_ txt) txt))))
3362 port)))
3363 (rename-file "build.xml.new" "build.xml")
3364 #t)))))
3365 (propagated-inputs
3366 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3367 (native-inputs
3368 `(("java-testng" ,java-testng)
3369 ("java-guava" ,java-guava)))
3370 (home-page "http://broadinstitute.github.io/picard/")
3371 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3372 (description "Picard is a set of Java command line tools for manipulating
3373 high-throughput sequencing (HTS) data and formats. Picard is implemented
3374 using the HTSJDK Java library to support accessing file formats that are
3375 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3376 VCF.")
3377 (license license:expat)))
3378
3379 ;; This is the last version of Picard to provide net.sf.samtools
3380 (define-public java-picard-1.113
3381 (package (inherit java-picard)
3382 (name "java-picard")
3383 (version "1.113")
3384 (source (origin
3385 (method git-fetch)
3386 (uri (git-reference
3387 (url "https://github.com/broadinstitute/picard.git")
3388 (commit version)))
3389 (file-name (string-append "java-picard-" version "-checkout"))
3390 (sha256
3391 (base32
3392 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3393 (modules '((guix build utils)))
3394 (snippet
3395 '(begin
3396 ;; Delete pre-built binaries.
3397 (delete-file-recursively "lib")
3398 (mkdir-p "lib")
3399 #t))))
3400 (build-system ant-build-system)
3401 (arguments
3402 `(#:build-target "picard-jar"
3403 #:test-target "test"
3404 ;; FIXME: the class path at test time is wrong.
3405 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3406 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3407 #:tests? #f
3408 #:jdk ,icedtea-8
3409 ;; This is only used for tests.
3410 #:make-flags
3411 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3412 #:phases
3413 (modify-phases %standard-phases
3414 ;; FIXME: This phase fails.
3415 (delete 'generate-jar-indices)
3416 ;; Do not use bundled ant bzip2.
3417 (add-after 'unpack 'use-ant-bzip
3418 (lambda* (#:key inputs #:allow-other-keys)
3419 (substitute* "build.xml"
3420 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3421 (string-append (assoc-ref inputs "ant")
3422 "/lib/ant.jar")))
3423 #t))
3424 (add-after 'unpack 'make-test-target-independent
3425 (lambda* (#:key inputs #:allow-other-keys)
3426 (substitute* "build.xml"
3427 (("name=\"test\" depends=\"compile, ")
3428 "name=\"test\" depends=\"compile-tests, ")
3429 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3430 "name=\"compile\" depends=\"compile-src\""))
3431 #t))
3432 (add-after 'unpack 'fix-deflater-path
3433 (lambda* (#:key outputs #:allow-other-keys)
3434 (substitute* "src/java/net/sf/samtools/Defaults.java"
3435 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3436 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3437 (assoc-ref outputs "out")
3438 "/lib/jni/libIntelDeflater.so"
3439 "\")")))
3440 #t))
3441 ;; Build the deflater library, because we've previously deleted the
3442 ;; pre-built one. This can only be built with access to the JDK
3443 ;; sources.
3444 (add-after 'build 'build-jni
3445 (lambda* (#:key inputs #:allow-other-keys)
3446 (mkdir-p "lib/jni")
3447 (mkdir-p "jdk-src")
3448 (and (zero? (system* "tar" "--strip-components=1" "-C" "jdk-src"
3449 "-xf" (assoc-ref inputs "jdk-src")))
3450 (zero? (system* "javah" "-jni"
3451 "-classpath" "classes"
3452 "-d" "lib/"
3453 "net.sf.samtools.util.zip.IntelDeflater"))
3454 (with-directory-excursion "src/c/inteldeflater"
3455 (zero? (system* "gcc" "-I../../../lib" "-I."
3456 (string-append "-I" (assoc-ref inputs "jdk")
3457 "/include/linux")
3458 "-I../../../jdk-src/src/share/native/common/"
3459 "-I../../../jdk-src/src/solaris/native/common/"
3460 "-c" "-O3" "-fPIC" "IntelDeflater.c"))
3461 (zero? (system* "gcc" "-shared"
3462 "-o" "../../../lib/jni/libIntelDeflater.so"
3463 "IntelDeflater.o" "-lz" "-lstdc++"))))))
3464 ;; We can only build everything else after building the JNI library.
3465 (add-after 'build-jni 'build-rest
3466 (lambda* (#:key make-flags #:allow-other-keys)
3467 (zero? (apply system* `("ant" "all" ,@make-flags)))))
3468 (add-before 'build 'set-JAVA6_HOME
3469 (lambda _
3470 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3471 #t))
3472 (replace 'install (install-jars "dist"))
3473 (add-after 'install 'install-jni-lib
3474 (lambda* (#:key outputs #:allow-other-keys)
3475 (let ((jni (string-append (assoc-ref outputs "out")
3476 "/lib/jni")))
3477 (mkdir-p jni)
3478 (install-file "lib/jni/libIntelDeflater.so" jni)
3479 #t))))))
3480 (inputs
3481 `(("java-snappy-1" ,java-snappy-1)
3482 ("java-commons-jexl-2" ,java-commons-jexl-2)
3483 ("java-cofoja" ,java-cofoja)
3484 ("ant" ,ant) ; for bzip2 support at runtime
3485 ("zlib" ,zlib)))
3486 (native-inputs
3487 `(("ant-apache-bcel" ,ant-apache-bcel)
3488 ("ant-junit" ,ant-junit)
3489 ("java-testng" ,java-testng)
3490 ("java-commons-bcel" ,java-commons-bcel)
3491 ("java-jcommander" ,java-jcommander)
3492 ("jdk" ,icedtea-8 "jdk")
3493 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3494
3495 (define-public fastqc
3496 (package
3497 (name "fastqc")
3498 (version "0.11.5")
3499 (source
3500 (origin
3501 (method url-fetch)
3502 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3503 "projects/fastqc/fastqc_v"
3504 version "_source.zip"))
3505 (sha256
3506 (base32
3507 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3508 (build-system ant-build-system)
3509 (arguments
3510 `(#:tests? #f ; there are no tests
3511 #:build-target "build"
3512 #:phases
3513 (modify-phases %standard-phases
3514 (add-after 'unpack 'fix-dependencies
3515 (lambda* (#:key inputs #:allow-other-keys)
3516 (substitute* "build.xml"
3517 (("jbzip2-0.9.jar")
3518 (string-append (assoc-ref inputs "java-jbzip2")
3519 "/share/java/jbzip2.jar"))
3520 (("sam-1.103.jar")
3521 (string-append (assoc-ref inputs "java-picard-1.113")
3522 "/share/java/sam-1.112.jar"))
3523 (("cisd-jhdf5.jar")
3524 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3525 "/share/java/sis-jhdf5.jar")))
3526 #t))
3527 ;; There is no installation target
3528 (replace 'install
3529 (lambda* (#:key inputs outputs #:allow-other-keys)
3530 (let* ((out (assoc-ref outputs "out"))
3531 (bin (string-append out "/bin"))
3532 (share (string-append out "/share/fastqc/"))
3533 (exe (string-append share "/fastqc")))
3534 (for-each mkdir-p (list bin share))
3535 (copy-recursively "bin" share)
3536 (substitute* exe
3537 (("my \\$java_bin = 'java';")
3538 (string-append "my $java_bin = '"
3539 (assoc-ref inputs "java")
3540 "/bin/java';")))
3541 (chmod exe #o555)
3542 (symlink exe (string-append bin "/fastqc"))
3543 #t))))))
3544 (inputs
3545 `(("java" ,icedtea)
3546 ("perl" ,perl) ; needed for the wrapper script
3547 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3548 ("java-picard-1.113" ,java-picard-1.113)
3549 ("java-jbzip2" ,java-jbzip2)))
3550 (native-inputs
3551 `(("unzip" ,unzip)))
3552 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3553 (synopsis "Quality control tool for high throughput sequence data")
3554 (description
3555 "FastQC aims to provide a simple way to do some quality control
3556 checks on raw sequence data coming from high throughput sequencing
3557 pipelines. It provides a modular set of analyses which you can use to
3558 give a quick impression of whether your data has any problems of which
3559 you should be aware before doing any further analysis.
3560
3561 The main functions of FastQC are:
3562
3563 @itemize
3564 @item Import of data from BAM, SAM or FastQ files (any variant);
3565 @item Providing a quick overview to tell you in which areas there may
3566 be problems;
3567 @item Summary graphs and tables to quickly assess your data;
3568 @item Export of results to an HTML based permanent report;
3569 @item Offline operation to allow automated generation of reports
3570 without running the interactive application.
3571 @end itemize\n")
3572 (license license:gpl3+)))
3573
3574 (define-public fastp
3575 (package
3576 (name "fastp")
3577 (version "0.14.1")
3578 (source
3579 (origin
3580 (method git-fetch)
3581 (uri (git-reference
3582 (url "https://github.com/OpenGene/fastp.git")
3583 (commit (string-append "v" version))))
3584 (file-name (git-file-name name version))
3585 (sha256
3586 (base32
3587 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3588 (build-system gnu-build-system)
3589 (arguments
3590 `(#:tests? #f ; there are none
3591 #:make-flags
3592 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3593 #:phases
3594 (modify-phases %standard-phases
3595 (delete 'configure)
3596 (add-before 'install 'create-target-dir
3597 (lambda* (#:key outputs #:allow-other-keys)
3598 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3599 #t)))))
3600 (inputs
3601 `(("zlib" ,zlib)))
3602 (home-page "https://github.com/OpenGene/fastp/")
3603 (synopsis "All-in-one FastQ preprocessor")
3604 (description
3605 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3606 FastQ files. This tool has multi-threading support to afford high
3607 performance.")
3608 (license license:expat)))
3609
3610 (define-public htslib
3611 (package
3612 (name "htslib")
3613 (version "1.9")
3614 (source (origin
3615 (method url-fetch)
3616 (uri (string-append
3617 "https://github.com/samtools/htslib/releases/download/"
3618 version "/htslib-" version ".tar.bz2"))
3619 (sha256
3620 (base32
3621 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
3622 (build-system gnu-build-system)
3623 (inputs
3624 `(("openssl" ,openssl)
3625 ("curl" ,curl)
3626 ("zlib" ,zlib)))
3627 (native-inputs
3628 `(("perl" ,perl)))
3629 (home-page "http://www.htslib.org")
3630 (synopsis "C library for reading/writing high-throughput sequencing data")
3631 (description
3632 "HTSlib is a C library for reading/writing high-throughput sequencing
3633 data. It also provides the @command{bgzip}, @command{htsfile}, and
3634 @command{tabix} utilities.")
3635 ;; Files under cram/ are released under the modified BSD license;
3636 ;; the rest is released under the Expat license
3637 (license (list license:expat license:bsd-3))))
3638
3639 ;; This package should be removed once no packages rely upon it.
3640 (define htslib-1.3
3641 (package
3642 (inherit htslib)
3643 (version "1.3.1")
3644 (source (origin
3645 (method url-fetch)
3646 (uri (string-append
3647 "https://github.com/samtools/htslib/releases/download/"
3648 version "/htslib-" version ".tar.bz2"))
3649 (sha256
3650 (base32
3651 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3652
3653 (define-public idr
3654 (package
3655 (name "idr")
3656 (version "2.0.3")
3657 (source (origin
3658 (method url-fetch)
3659 (uri (string-append
3660 "https://github.com/nboley/idr/archive/"
3661 version ".tar.gz"))
3662 (file-name (string-append name "-" version ".tar.gz"))
3663 (sha256
3664 (base32
3665 "1rjdly6daslw66r43g9md8znizlscn1sphycqyldzsidkc4vxqv3"))
3666 ;; Delete generated C code.
3667 (snippet
3668 '(begin (delete-file "idr/inv_cdf.c") #t))))
3669 (build-system python-build-system)
3670 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3671 ;; are no longer part of this package. It also asserts False, which
3672 ;; causes the tests to always fail.
3673 (arguments `(#:tests? #f))
3674 (propagated-inputs
3675 `(("python-scipy" ,python-scipy)
3676 ("python-sympy" ,python-sympy)
3677 ("python-numpy" ,python-numpy)
3678 ("python-matplotlib" ,python-matplotlib)))
3679 (native-inputs
3680 `(("python-cython" ,python-cython)))
3681 (home-page "https://github.com/nboley/idr")
3682 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3683 (description
3684 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3685 to measure the reproducibility of findings identified from replicate
3686 experiments and provide highly stable thresholds based on reproducibility.")
3687 (license license:gpl2+)))
3688
3689 (define-public jellyfish
3690 (package
3691 (name "jellyfish")
3692 (version "2.2.10")
3693 (source (origin
3694 (method url-fetch)
3695 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3696 "releases/download/v" version
3697 "/jellyfish-" version ".tar.gz"))
3698 (sha256
3699 (base32
3700 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3701 (build-system gnu-build-system)
3702 (outputs '("out" ;for library
3703 "ruby" ;for Ruby bindings
3704 "python")) ;for Python bindings
3705 (arguments
3706 `(#:configure-flags
3707 (list (string-append "--enable-ruby-binding="
3708 (assoc-ref %outputs "ruby"))
3709 (string-append "--enable-python-binding="
3710 (assoc-ref %outputs "python")))
3711 #:phases
3712 (modify-phases %standard-phases
3713 (add-before 'check 'set-SHELL-variable
3714 (lambda _
3715 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3716 ;; to run tests.
3717 (setenv "SHELL" (which "bash"))
3718 #t)))))
3719 (native-inputs
3720 `(("bc" ,bc)
3721 ("time" ,time)
3722 ("ruby" ,ruby)
3723 ("python" ,python-2)
3724 ("pkg-config" ,pkg-config)))
3725 (inputs
3726 `(("htslib" ,htslib)))
3727 (synopsis "Tool for fast counting of k-mers in DNA")
3728 (description
3729 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3730 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3731 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3732 is a command-line program that reads FASTA and multi-FASTA files containing
3733 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3734 translated into a human-readable text format using the @code{jellyfish dump}
3735 command, or queried for specific k-mers with @code{jellyfish query}.")
3736 (home-page "http://www.genome.umd.edu/jellyfish.html")
3737 ;; JELLYFISH seems to be 64-bit only.
3738 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3739 ;; The combined work is published under the GPLv3 or later. Individual
3740 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3741 (license (list license:gpl3+ license:expat))))
3742
3743 (define-public khmer
3744 (package
3745 (name "khmer")
3746 (version "2.1.2")
3747 (source
3748 (origin
3749 (method git-fetch)
3750 (uri (git-reference
3751 (url "https://github.com/dib-lab/khmer.git")
3752 (commit (string-append "v" version))))
3753 (file-name (git-file-name name version))
3754 (sha256
3755 (base32
3756 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
3757 (patches (search-patches "khmer-use-libraries.patch"))
3758 (modules '((guix build utils)))
3759 (snippet
3760 '(begin
3761 ;; Delete bundled libraries. We do not replace the bundled seqan
3762 ;; as it is a modified subset of the old version 1.4.1.
3763 ;;
3764 ;; We do not replace the bundled MurmurHash as the canonical
3765 ;; repository for this code 'SMHasher' is unsuitable for providing
3766 ;; a library. See
3767 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3768 (delete-file-recursively "third-party/zlib")
3769 (delete-file-recursively "third-party/bzip2")
3770 #t))))
3771 (build-system python-build-system)
3772 (arguments
3773 `(#:phases
3774 (modify-phases %standard-phases
3775 (add-after 'unpack 'set-cc
3776 (lambda _ (setenv "CC" "gcc") #t))
3777 ;; FIXME: This fails with "permission denied".
3778 (delete 'reset-gzip-timestamps))))
3779 (native-inputs
3780 `(("python-cython" ,python-cython)
3781 ("python-pytest" ,python-pytest)
3782 ("python-pytest-runner" ,python-pytest-runner)))
3783 (inputs
3784 `(("zlib" ,zlib)
3785 ("bzip2" ,bzip2)
3786 ("python-screed" ,python-screed)
3787 ("python-bz2file" ,python-bz2file)))
3788 (home-page "https://khmer.readthedocs.org/")
3789 (synopsis "K-mer counting, filtering and graph traversal library")
3790 (description "The khmer software is a set of command-line tools for
3791 working with DNA shotgun sequencing data from genomes, transcriptomes,
3792 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3793 sometimes better. Khmer can also identify and fix problems with shotgun
3794 data.")
3795 ;; When building on i686, armhf and mips64el, we get the following error:
3796 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3797 (supported-systems '("x86_64-linux" "aarch64-linux"))
3798 (license license:bsd-3)))
3799
3800 (define-public kaiju
3801 (package
3802 (name "kaiju")
3803 (version "1.6.2")
3804 (source (origin
3805 (method url-fetch)
3806 (uri (string-append
3807 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3808 version ".tar.gz"))
3809 (file-name (string-append name "-" version ".tar.gz"))
3810 (sha256
3811 (base32
3812 "1kdn4rxs0kr9ibmrgrfcci71aa6j6gr71dbc8pff7731rpab6kj7"))))
3813 (build-system gnu-build-system)
3814 (arguments
3815 `(#:tests? #f ; There are no tests.
3816 #:phases
3817 (modify-phases %standard-phases
3818 (delete 'configure)
3819 (add-before 'build 'move-to-src-dir
3820 (lambda _ (chdir "src") #t))
3821 (replace 'install
3822 (lambda* (#:key inputs outputs #:allow-other-keys)
3823 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3824 (mkdir-p bin)
3825 (chdir "..")
3826 (copy-recursively "bin" bin)
3827 (copy-recursively "util" bin))
3828 #t)))))
3829 (inputs
3830 `(("perl" ,perl)
3831 ("zlib" ,zlib)))
3832 (home-page "http://kaiju.binf.ku.dk/")
3833 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3834 (description "Kaiju is a program for sensitive taxonomic classification
3835 of high-throughput sequencing reads from metagenomic whole genome sequencing
3836 experiments.")
3837 (license license:gpl3+)))
3838
3839 (define-public macs
3840 (package
3841 (name "macs")
3842 (version "2.1.1.20160309")
3843 (source (origin
3844 (method url-fetch)
3845 (uri (pypi-uri "MACS2" version))
3846 (sha256
3847 (base32
3848 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3849 (build-system python-build-system)
3850 (arguments
3851 `(#:python ,python-2 ; only compatible with Python 2.7
3852 #:tests? #f)) ; no test target
3853 (inputs
3854 `(("python-numpy" ,python2-numpy)))
3855 (home-page "https://github.com/taoliu/MACS/")
3856 (synopsis "Model based analysis for ChIP-Seq data")
3857 (description
3858 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3859 identifying transcript factor binding sites named Model-based Analysis of
3860 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3861 the significance of enriched ChIP regions and it improves the spatial
3862 resolution of binding sites through combining the information of both
3863 sequencing tag position and orientation.")
3864 (license license:bsd-3)))
3865
3866 (define-public mafft
3867 (package
3868 (name "mafft")
3869 (version "7.394")
3870 (source (origin
3871 (method url-fetch)
3872 (uri (string-append
3873 "https://mafft.cbrc.jp/alignment/software/mafft-" version
3874 "-without-extensions-src.tgz"))
3875 (file-name (string-append name "-" version ".tgz"))
3876 (sha256
3877 (base32
3878 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
3879 (build-system gnu-build-system)
3880 (arguments
3881 `(#:tests? #f ; no automated tests, though there are tests in the read me
3882 #:make-flags (let ((out (assoc-ref %outputs "out")))
3883 (list (string-append "PREFIX=" out)
3884 (string-append "BINDIR="
3885 (string-append out "/bin"))))
3886 #:phases
3887 (modify-phases %standard-phases
3888 (add-after 'unpack 'enter-dir
3889 (lambda _ (chdir "core") #t))
3890 (add-after 'enter-dir 'patch-makefile
3891 (lambda _
3892 ;; on advice from the MAFFT authors, there is no need to
3893 ;; distribute mafft-profile, mafft-distance, or
3894 ;; mafft-homologs.rb as they are too "specialised".
3895 (substitute* "Makefile"
3896 ;; remove mafft-homologs.rb from SCRIPTS
3897 (("^SCRIPTS = mafft mafft-homologs.rb")
3898 "SCRIPTS = mafft")
3899 ;; remove mafft-homologs from MANPAGES
3900 (("^MANPAGES = mafft.1 mafft-homologs.1")
3901 "MANPAGES = mafft.1")
3902 ;; remove mafft-distance from PROGS
3903 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3904 "PROGS = dvtditr dndfast7 dndblast sextet5")
3905 ;; remove mafft-profile from PROGS
3906 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3907 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3908 (("^rm -f mafft-profile mafft-profile.exe") "#")
3909 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3910 ;; do not install MAN pages in libexec folder
3911 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3912 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3913 #t))
3914 (add-after 'enter-dir 'patch-paths
3915 (lambda* (#:key inputs #:allow-other-keys)
3916 (substitute* '("pairash.c"
3917 "mafft.tmpl")
3918 (("perl") (which "perl"))
3919 (("([\"`| ])awk" _ prefix)
3920 (string-append prefix (which "awk")))
3921 (("grep") (which "grep")))
3922 #t))
3923 (delete 'configure)
3924 (add-after 'install 'wrap-programs
3925 (lambda* (#:key outputs #:allow-other-keys)
3926 (let* ((out (assoc-ref outputs "out"))
3927 (bin (string-append out "/bin"))
3928 (path (string-append
3929 (assoc-ref %build-inputs "coreutils") "/bin:")))
3930 (for-each (lambda (file)
3931 (wrap-program file
3932 `("PATH" ":" prefix (,path))))
3933 (find-files bin)))
3934 #t)))))
3935 (inputs
3936 `(("perl" ,perl)
3937 ("ruby" ,ruby)
3938 ("gawk" ,gawk)
3939 ("grep" ,grep)
3940 ("coreutils" ,coreutils)))
3941 (home-page "http://mafft.cbrc.jp/alignment/software/")
3942 (synopsis "Multiple sequence alignment program")
3943 (description
3944 "MAFFT offers a range of multiple alignment methods for nucleotide and
3945 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3946 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3947 sequences).")
3948 (license (license:non-copyleft
3949 "http://mafft.cbrc.jp/alignment/software/license.txt"
3950 "BSD-3 with different formatting"))))
3951
3952 (define-public mash
3953 (package
3954 (name "mash")
3955 (version "2.0")
3956 (source (origin
3957 (method url-fetch)
3958 (uri (string-append
3959 "https://github.com/marbl/mash/archive/v"
3960 version ".tar.gz"))
3961 (file-name (string-append name "-" version ".tar.gz"))
3962 (sha256
3963 (base32
3964 "00fx14vpmgsijwxd1xql3if934l82v8ckqgjjyyhnr36qb9qrskv"))
3965 (modules '((guix build utils)))
3966 (snippet
3967 '(begin
3968 ;; Delete bundled kseq.
3969 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3970 (delete-file "src/mash/kseq.h")
3971 #t))))
3972 (build-system gnu-build-system)
3973 (arguments
3974 `(#:tests? #f ; No tests.
3975 #:configure-flags
3976 (list
3977 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3978 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3979 #:make-flags (list "CC=gcc")
3980 #:phases
3981 (modify-phases %standard-phases
3982 (add-after 'unpack 'fix-includes
3983 (lambda _
3984 (substitute* '("src/mash/Sketch.cpp"
3985 "src/mash/CommandFind.cpp"
3986 "src/mash/CommandScreen.cpp")
3987 (("^#include \"kseq\\.h\"")
3988 "#include \"htslib/kseq.h\""))
3989 #t))
3990 (add-after 'fix-includes 'autoconf
3991 (lambda _ (zero? (system* "autoconf")))))))
3992 (native-inputs
3993 `(("autoconf" ,autoconf)
3994 ;; Capnproto and htslib are statically embedded in the final
3995 ;; application. Therefore we also list their licenses, below.
3996 ("capnproto" ,capnproto)
3997 ("htslib" ,htslib)))
3998 (inputs
3999 `(("gsl" ,gsl)
4000 ("zlib" ,zlib)))
4001 (supported-systems '("x86_64-linux"))
4002 (home-page "https://mash.readthedocs.io")
4003 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4004 (description "Mash is a fast sequence distance estimator that uses the
4005 MinHash algorithm and is designed to work with genomes and metagenomes in the
4006 form of assemblies or reads.")
4007 (license (list license:bsd-3 ; Mash
4008 license:expat ; HTSlib and capnproto
4009 license:public-domain ; MurmurHash 3
4010 license:cpl1.0)))) ; Open Bloom Filter
4011
4012 (define-public metabat
4013 (package
4014 (name "metabat")
4015 (version "2.12.1")
4016 (source
4017 (origin
4018 (method url-fetch)
4019 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
4020 version ".tar.gz"))
4021 (file-name (string-append name "-" version ".tar.gz"))
4022 (sha256
4023 (base32
4024 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
4025 (patches (search-patches "metabat-fix-compilation.patch"))))
4026 (build-system scons-build-system)
4027 (arguments
4028 `(#:scons ,scons-python2
4029 #:scons-flags
4030 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4031 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4032 #:tests? #f ;; Tests are run during the build phase.
4033 #:phases
4034 (modify-phases %standard-phases
4035 (add-after 'unpack 'fix-includes
4036 (lambda _
4037 (substitute* "src/BamUtils.h"
4038 (("^#include \"bam/bam\\.h\"")
4039 "#include \"samtools/bam.h\"")
4040 (("^#include \"bam/sam\\.h\"")
4041 "#include \"samtools/sam.h\""))
4042 (substitute* "src/KseqReader.h"
4043 (("^#include \"bam/kseq\\.h\"")
4044 "#include \"htslib/kseq.h\""))
4045 #t))
4046 (add-after 'unpack 'fix-scons
4047 (lambda* (#:key inputs #:allow-other-keys)
4048 (substitute* "SConstruct"
4049 (("^htslib_dir += 'samtools'")
4050 (string-append "htslib_dir = '"
4051 (assoc-ref inputs "htslib")
4052 "'"))
4053 (("^samtools_dir = 'samtools'")
4054 (string-append "samtools_dir = '"
4055 (assoc-ref inputs "samtools")
4056 "'"))
4057 (("^findStaticOrShared\\('bam', hts_lib")
4058 (string-append "findStaticOrShared('bam', '"
4059 (assoc-ref inputs "samtools")
4060 "/lib'"))
4061 ;; Do not distribute README.
4062 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4063 #t)))))
4064 (inputs
4065 `(("zlib" ,zlib)
4066 ("perl" ,perl)
4067 ("samtools" ,samtools)
4068 ("htslib" ,htslib)
4069 ("boost" ,boost)))
4070 (home-page "https://bitbucket.org/berkeleylab/metabat")
4071 (synopsis
4072 "Reconstruction of single genomes from complex microbial communities")
4073 (description
4074 "Grouping large genomic fragments assembled from shotgun metagenomic
4075 sequences to deconvolute complex microbial communities, or metagenome binning,
4076 enables the study of individual organisms and their interactions. MetaBAT is
4077 an automated metagenome binning software, which integrates empirical
4078 probabilistic distances of genome abundance and tetranucleotide frequency.")
4079 ;; The source code contains inline assembly.
4080 (supported-systems '("x86_64-linux" "i686-linux"))
4081 (license (license:non-copyleft "file://license.txt"
4082 "See license.txt in the distribution."))))
4083
4084 (define-public minced
4085 (package
4086 (name "minced")
4087 (version "0.2.0")
4088 (source (origin
4089 (method url-fetch)
4090 (uri (string-append
4091 "https://github.com/ctSkennerton/minced/archive/"
4092 version ".tar.gz"))
4093 (file-name (string-append name "-" version ".tar.gz"))
4094 (sha256
4095 (base32
4096 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
4097 (build-system gnu-build-system)
4098 (arguments
4099 `(#:test-target "test"
4100 #:phases
4101 (modify-phases %standard-phases
4102 (delete 'configure)
4103 (add-before 'check 'fix-test
4104 (lambda _
4105 ;; Fix test for latest version.
4106 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4107 (("minced:0.1.6") "minced:0.2.0"))
4108 #t))
4109 (replace 'install ; No install target.
4110 (lambda* (#:key inputs outputs #:allow-other-keys)
4111 (let* ((out (assoc-ref outputs "out"))
4112 (bin (string-append out "/bin"))
4113 (wrapper (string-append bin "/minced")))
4114 ;; Minced comes with a wrapper script that tries to figure out where
4115 ;; it is located before running the JAR. Since these paths are known
4116 ;; to us, we build our own wrapper to avoid coreutils dependency.
4117 (install-file "minced.jar" bin)
4118 (with-output-to-file wrapper
4119 (lambda _
4120 (display
4121 (string-append
4122 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4123 (assoc-ref inputs "jre") "/bin/java -jar "
4124 bin "/minced.jar \"$@\"\n"))))
4125 (chmod wrapper #o555)))))))
4126 (native-inputs
4127 `(("jdk" ,icedtea "jdk")))
4128 (inputs
4129 `(("bash" ,bash)
4130 ("jre" ,icedtea "out")))
4131 (home-page "https://github.com/ctSkennerton/minced")
4132 (synopsis "Mining CRISPRs in Environmental Datasets")
4133 (description
4134 "MinCED is a program to find Clustered Regularly Interspaced Short
4135 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4136 unassembled metagenomic reads, but is mainly designed for full genomes and
4137 assembled metagenomic sequence.")
4138 (license license:gpl3+)))
4139
4140 (define-public miso
4141 (package
4142 (name "miso")
4143 (version "0.5.4")
4144 (source (origin
4145 (method url-fetch)
4146 (uri (pypi-uri "misopy" version))
4147 (sha256
4148 (base32
4149 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4150 (modules '((guix build utils)))
4151 (snippet '(begin
4152 (substitute* "setup.py"
4153 ;; Use setuptools, or else the executables are not
4154 ;; installed.
4155 (("distutils.core") "setuptools")
4156 ;; use "gcc" instead of "cc" for compilation
4157 (("^defines")
4158 "cc.set_executables(
4159 compiler='gcc',
4160 compiler_so='gcc',
4161 linker_exe='gcc',
4162 linker_so='gcc -shared'); defines"))
4163 #t))))
4164 (build-system python-build-system)
4165 (arguments
4166 `(#:python ,python-2 ; only Python 2 is supported
4167 #:tests? #f)) ; no "test" target
4168 (inputs
4169 `(("samtools" ,samtools)
4170 ("python-numpy" ,python2-numpy)
4171 ("python-pysam" ,python2-pysam)
4172 ("python-scipy" ,python2-scipy)
4173 ("python-matplotlib" ,python2-matplotlib)))
4174 (native-inputs
4175 `(("python-mock" ,python2-mock) ;for tests
4176 ("python-pytz" ,python2-pytz))) ;for tests
4177 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4178 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4179 (description
4180 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4181 the expression level of alternatively spliced genes from RNA-Seq data, and
4182 identifies differentially regulated isoforms or exons across samples. By
4183 modeling the generative process by which reads are produced from isoforms in
4184 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4185 that a read originated from a particular isoform.")
4186 (license license:gpl2)))
4187
4188 (define-public muscle
4189 (package
4190 (name "muscle")
4191 (version "3.8.1551")
4192 (source (origin
4193 (method url-fetch/tarbomb)
4194 (uri (string-append
4195 "http://www.drive5.com/muscle/muscle_src_"
4196 version ".tar.gz"))
4197 (sha256
4198 (base32
4199 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4200 (build-system gnu-build-system)
4201 (arguments
4202 `(#:make-flags (list "LDLIBS = -lm")
4203 #:phases
4204 (modify-phases %standard-phases
4205 (delete 'configure)
4206 (replace 'check
4207 ;; There are no tests, so just test if it runs.
4208 (lambda _ (zero? (system* "./muscle" "-version"))))
4209 (replace 'install
4210 (lambda* (#:key outputs #:allow-other-keys)
4211 (let* ((out (assoc-ref outputs "out"))
4212 (bin (string-append out "/bin")))
4213 (install-file "muscle" bin)))))))
4214 (home-page "http://www.drive5.com/muscle")
4215 (synopsis "Multiple sequence alignment program")
4216 (description
4217 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4218 program for nucleotide and protein sequences.")
4219 ;; License information found in 'muscle -h' and usage.cpp.
4220 (license license:public-domain)))
4221
4222 (define-public newick-utils
4223 ;; There are no recent releases so we package from git.
4224 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4225 (package
4226 (name "newick-utils")
4227 (version (string-append "1.6-1." (string-take commit 8)))
4228 (source (origin
4229 (method git-fetch)
4230 (uri (git-reference
4231 (url "https://github.com/tjunier/newick_utils.git")
4232 (commit commit)))
4233 (file-name (string-append name "-" version "-checkout"))
4234 (sha256
4235 (base32
4236 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4237 (build-system gnu-build-system)
4238 (arguments
4239 `(#:phases
4240 (modify-phases %standard-phases
4241 (add-after 'unpack 'autoconf
4242 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4243 (inputs
4244 ;; XXX: TODO: Enable Lua and Guile bindings.
4245 ;; https://github.com/tjunier/newick_utils/issues/13
4246 `(("libxml2" ,libxml2)
4247 ("flex" ,flex)
4248 ("bison" ,bison)))
4249 (native-inputs
4250 `(("autoconf" ,autoconf)
4251 ("automake" ,automake)
4252 ("libtool" ,libtool)))
4253 (synopsis "Programs for working with newick format phylogenetic trees")
4254 (description
4255 "Newick-utils is a suite of utilities for processing phylogenetic trees
4256 in Newick format. Functions include re-rooting, extracting subtrees,
4257 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4258 (home-page "https://github.com/tjunier/newick_utils")
4259 (license license:bsd-3))))
4260
4261 (define-public orfm
4262 (package
4263 (name "orfm")
4264 (version "0.7.1")
4265 (source (origin
4266 (method url-fetch)
4267 (uri (string-append
4268 "https://github.com/wwood/OrfM/releases/download/v"
4269 version "/orfm-" version ".tar.gz"))
4270 (sha256
4271 (base32
4272 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4273 (build-system gnu-build-system)
4274 (inputs `(("zlib" ,zlib)))
4275 (native-inputs
4276 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4277 ("ruby-rspec" ,ruby-rspec)
4278 ("ruby" ,ruby)))
4279 (synopsis "Simple and not slow open reading frame (ORF) caller")
4280 (description
4281 "An ORF caller finds stretches of DNA that, when translated, are not
4282 interrupted by stop codons. OrfM finds and prints these ORFs.")
4283 (home-page "https://github.com/wwood/OrfM")
4284 (license license:lgpl3+)))
4285
4286 (define-public pplacer
4287 (let ((commit "g807f6f3"))
4288 (package
4289 (name "pplacer")
4290 ;; The commit should be updated with each version change.
4291 (version "1.1.alpha19")
4292 (source
4293 (origin
4294 (method url-fetch)
4295 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
4296 version ".tar.gz"))
4297 (file-name (string-append name "-" version ".tar.gz"))
4298 (sha256
4299 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
4300 (build-system ocaml-build-system)
4301 (arguments
4302 `(#:ocaml ,ocaml-4.01
4303 #:findlib ,ocaml4.01-findlib
4304 #:modules ((guix build ocaml-build-system)
4305 (guix build utils)
4306 (ice-9 ftw))
4307 #:phases
4308 (modify-phases %standard-phases
4309 (delete 'configure)
4310 (add-after 'unpack 'replace-bundled-cddlib
4311 (lambda* (#:key inputs #:allow-other-keys)
4312 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
4313 (local-dir "cddlib_guix"))
4314 (mkdir local-dir)
4315 (with-directory-excursion local-dir
4316 (system* "tar" "xvf" cddlib-src))
4317 (let ((cddlib-src-folder
4318 (string-append local-dir "/"
4319 (list-ref (scandir local-dir) 2)
4320 "/lib-src")))
4321 (for-each
4322 (lambda (file)
4323 (copy-file file
4324 (string-append "cdd_src/" (basename file))))
4325 (find-files cddlib-src-folder ".*[ch]$")))
4326 #t)))
4327 (add-after 'unpack 'fix-makefile
4328 (lambda _
4329 ;; Remove system calls to 'git'.
4330 (substitute* "Makefile"
4331 (("^DESCRIPT:=pplacer-.*")
4332 (string-append
4333 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
4334 (substitute* "myocamlbuild.ml"
4335 (("git describe --tags --long .*\\\" with")
4336 (string-append
4337 "echo -n v" ,version "-" ,commit "\" with")))
4338 #t))
4339 (replace 'install
4340 (lambda* (#:key outputs #:allow-other-keys)
4341 (let* ((out (assoc-ref outputs "out"))
4342 (bin (string-append out "/bin")))
4343 (copy-recursively "bin" bin))
4344 #t)))))
4345 (native-inputs
4346 `(("zlib" ,zlib)
4347 ("gsl" ,gsl)
4348 ("ocaml-ounit" ,ocaml4.01-ounit)
4349 ("ocaml-batteries" ,ocaml4.01-batteries)
4350 ("ocaml-camlzip" ,ocaml4.01-camlzip)
4351 ("ocaml-csv" ,ocaml4.01-csv)
4352 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
4353 ("ocaml-xmlm" ,ocaml4.01-xmlm)
4354 ("ocaml-mcl" ,ocaml4.01-mcl)
4355 ("ocaml-gsl" ,ocaml4.01-gsl)
4356 ("cddlib-src" ,(package-source cddlib))))
4357 (propagated-inputs
4358 `(("pplacer-scripts" ,pplacer-scripts)))
4359 (synopsis "Phylogenetic placement of biological sequences")
4360 (description
4361 "Pplacer places query sequences on a fixed reference phylogenetic tree
4362 to maximize phylogenetic likelihood or posterior probability according to a
4363 reference alignment. Pplacer is designed to be fast, to give useful
4364 information about uncertainty, and to offer advanced visualization and
4365 downstream analysis.")
4366 (home-page "http://matsen.fhcrc.org/pplacer")
4367 (license license:gpl3))))
4368
4369 ;; This package is installed alongside 'pplacer'. It is a separate package so
4370 ;; that it can use the python-build-system for the scripts that are
4371 ;; distributed alongside the main OCaml binaries.
4372 (define pplacer-scripts
4373 (package
4374 (inherit pplacer)
4375 (name "pplacer-scripts")
4376 (build-system python-build-system)
4377 (arguments
4378 `(#:python ,python-2
4379 #:phases
4380 (modify-phases %standard-phases
4381 (add-after 'unpack 'enter-scripts-dir
4382 (lambda _ (chdir "scripts")))
4383 (replace 'check
4384 (lambda _
4385 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
4386 (add-after 'install 'wrap-executables
4387 (lambda* (#:key inputs outputs #:allow-other-keys)
4388 (let* ((out (assoc-ref outputs "out"))
4389 (bin (string-append out "/bin")))
4390 (let ((path (string-append
4391 (assoc-ref inputs "hmmer") "/bin:"
4392 (assoc-ref inputs "infernal") "/bin")))
4393 (display path)
4394 (wrap-program (string-append bin "/refpkg_align.py")
4395 `("PATH" ":" prefix (,path))))
4396 (let ((path (string-append
4397 (assoc-ref inputs "hmmer") "/bin")))
4398 (wrap-program (string-append bin "/hrefpkg_query.py")
4399 `("PATH" ":" prefix (,path)))))
4400 #t)))))
4401 (inputs
4402 `(("infernal" ,infernal)
4403 ("hmmer" ,hmmer)))
4404 (propagated-inputs
4405 `(("python-biopython" ,python2-biopython)
4406 ("taxtastic" ,taxtastic)))
4407 (synopsis "Pplacer Python scripts")))
4408
4409 (define-public python2-pbcore
4410 (package
4411 (name "python2-pbcore")
4412 (version "1.2.10")
4413 (source (origin
4414 (method url-fetch)
4415 (uri (pypi-uri "pbcore" version))
4416 (sha256
4417 (base32
4418 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4419 (build-system python-build-system)
4420 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4421 (propagated-inputs
4422 `(("python-cython" ,python2-cython)
4423 ("python-numpy" ,python2-numpy)
4424 ("python-pysam" ,python2-pysam)
4425 ("python-h5py" ,python2-h5py)))
4426 (native-inputs
4427 `(("python-nose" ,python2-nose)
4428 ("python-sphinx" ,python2-sphinx)
4429 ("python-pyxb" ,python2-pyxb)))
4430 (home-page "http://pacificbiosciences.github.io/pbcore/")
4431 (synopsis "Library for reading and writing PacBio data files")
4432 (description
4433 "The pbcore package provides Python APIs for interacting with PacBio data
4434 files and writing bioinformatics applications.")
4435 (license license:bsd-3)))
4436
4437 (define-public python2-warpedlmm
4438 (package
4439 (name "python2-warpedlmm")
4440 (version "0.21")
4441 (source
4442 (origin
4443 (method url-fetch)
4444 (uri (string-append
4445 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
4446 version ".zip"))
4447 (sha256
4448 (base32
4449 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4450 (build-system python-build-system)
4451 (arguments
4452 `(#:python ,python-2)) ; requires Python 2.7
4453 (propagated-inputs
4454 `(("python-scipy" ,python2-scipy)
4455 ("python-numpy" ,python2-numpy)
4456 ("python-matplotlib" ,python2-matplotlib)
4457 ("python-fastlmm" ,python2-fastlmm)
4458 ("python-pandas" ,python2-pandas)
4459 ("python-pysnptools" ,python2-pysnptools)))
4460 (native-inputs
4461 `(("python-mock" ,python2-mock)
4462 ("python-nose" ,python2-nose)
4463 ("unzip" ,unzip)))
4464 (home-page "https://github.com/PMBio/warpedLMM")
4465 (synopsis "Implementation of warped linear mixed models")
4466 (description
4467 "WarpedLMM is a Python implementation of the warped linear mixed model,
4468 which automatically learns an optimal warping function (or transformation) for
4469 the phenotype as it models the data.")
4470 (license license:asl2.0)))
4471
4472 (define-public pbtranscript-tofu
4473 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4474 (package
4475 (name "pbtranscript-tofu")
4476 (version (string-append "2.2.3." (string-take commit 7)))
4477 (source (origin
4478 (method git-fetch)
4479 (uri (git-reference
4480 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4481 (commit commit)))
4482 (file-name (string-append name "-" version "-checkout"))
4483 (sha256
4484 (base32
4485 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4486 (modules '((guix build utils)))
4487 (snippet
4488 '(begin
4489 ;; remove bundled Cython sources
4490 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4491 #t))))
4492 (build-system python-build-system)
4493 (arguments
4494 `(#:python ,python-2
4495 ;; FIXME: Tests fail with "No such file or directory:
4496 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4497 #:tests? #f
4498 #:phases
4499 (modify-phases %standard-phases
4500 (add-after 'unpack 'enter-directory
4501 (lambda _
4502 (chdir "pbtranscript-tofu/pbtranscript/")
4503 #t))
4504 ;; With setuptools version 18.0 and later this setup.py hack causes
4505 ;; a build error, so we disable it.
4506 (add-after 'enter-directory 'patch-setuppy
4507 (lambda _
4508 (substitute* "setup.py"
4509 (("if 'setuptools.extension' in sys.modules:")
4510 "if False:"))
4511 #t)))))
4512 (inputs
4513 `(("python-numpy" ,python2-numpy)
4514 ("python-bx-python" ,python2-bx-python)
4515 ("python-networkx" ,python2-networkx)
4516 ("python-scipy" ,python2-scipy)
4517 ("python-pbcore" ,python2-pbcore)
4518 ("python-h5py" ,python2-h5py)))
4519 (native-inputs
4520 `(("python-cython" ,python2-cython)
4521 ("python-nose" ,python2-nose)))
4522 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4523 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4524 (description
4525 "pbtranscript-tofu contains scripts to analyze transcriptome data
4526 generated using the PacBio Iso-Seq protocol.")
4527 (license license:bsd-3))))
4528
4529 (define-public prank
4530 (package
4531 (name "prank")
4532 (version "150803")
4533 (source (origin
4534 (method url-fetch)
4535 (uri (string-append
4536 "http://wasabiapp.org/download/prank/prank.source."
4537 version ".tgz"))
4538 (sha256
4539 (base32
4540 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4541 (build-system gnu-build-system)
4542 (arguments
4543 `(#:phases
4544 (modify-phases %standard-phases
4545 (add-after 'unpack 'enter-src-dir
4546 (lambda _
4547 (chdir "src")
4548 #t))
4549 (add-after 'unpack 'remove-m64-flag
4550 ;; Prank will build with the correct 'bit-ness' without this flag
4551 ;; and this allows building on 32-bit machines.
4552 (lambda _ (substitute* "src/Makefile"
4553 (("-m64") ""))
4554 #t))
4555 (delete 'configure)
4556 (replace 'install
4557 (lambda* (#:key outputs #:allow-other-keys)
4558 (let* ((out (assoc-ref outputs "out"))
4559 (bin (string-append out "/bin"))
4560 (man (string-append out "/share/man/man1"))
4561 (path (string-append
4562 (assoc-ref %build-inputs "mafft") "/bin:"
4563 (assoc-ref %build-inputs "exonerate") "/bin:"
4564 (assoc-ref %build-inputs "bppsuite") "/bin")))
4565 (install-file "prank" bin)
4566 (wrap-program (string-append bin "/prank")
4567 `("PATH" ":" prefix (,path)))
4568 (install-file "prank.1" man))
4569 #t)))))
4570 (inputs
4571 `(("mafft" ,mafft)
4572 ("exonerate" ,exonerate)
4573 ("bppsuite" ,bppsuite)))
4574 (home-page "http://wasabiapp.org/software/prank/")
4575 (synopsis "Probabilistic multiple sequence alignment program")
4576 (description
4577 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4578 codon and amino-acid sequences. It is based on a novel algorithm that treats
4579 insertions correctly and avoids over-estimation of the number of deletion
4580 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4581 in phylogenetics and correctly takes into account the evolutionary distances
4582 between sequences. Lastly, PRANK allows for defining a potential structure
4583 for sequences to be aligned and then, simultaneously with the alignment,
4584 predicts the locations of structural units in the sequences.")
4585 (license license:gpl2+)))
4586
4587 (define-public proteinortho
4588 (package
4589 (name "proteinortho")
4590 (version "5.16b")
4591 (source
4592 (origin
4593 (method url-fetch)
4594 (uri
4595 (string-append
4596 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4597 version "_src.tar.gz"))
4598 (sha256
4599 (base32
4600 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4601 (build-system gnu-build-system)
4602 (arguments
4603 `(#:test-target "test"
4604 #:phases
4605 (modify-phases %standard-phases
4606 (replace 'configure
4607 ;; There is no configure script, so we modify the Makefile directly.
4608 (lambda* (#:key outputs #:allow-other-keys)
4609 (substitute* "Makefile"
4610 (("INSTALLDIR=.*")
4611 (string-append
4612 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4613 #t))
4614 (add-before 'install 'make-install-directory
4615 ;; The install directory is not created during 'make install'.
4616 (lambda* (#:key outputs #:allow-other-keys)
4617 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4618 #t))
4619 (add-after 'install 'wrap-programs
4620 (lambda* (#:key inputs outputs #:allow-other-keys)
4621 (let* ((path (getenv "PATH"))
4622 (out (assoc-ref outputs "out"))
4623 (binary (string-append out "/bin/proteinortho5.pl")))
4624 (wrap-program binary `("PATH" ":" prefix (,path))))
4625 #t)))))
4626 (inputs
4627 `(("perl" ,perl)
4628 ("python" ,python-2)
4629 ("blast+" ,blast+)))
4630 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4631 (synopsis "Detect orthologous genes across species")
4632 (description
4633 "Proteinortho is a tool to detect orthologous genes across different
4634 species. For doing so, it compares similarities of given gene sequences and
4635 clusters them to find significant groups. The algorithm was designed to handle
4636 large-scale data and can be applied to hundreds of species at once.")
4637 (license license:gpl2+)))
4638
4639 (define-public pyicoteo
4640 (package
4641 (name "pyicoteo")
4642 (version "2.0.7")
4643 (source
4644 (origin
4645 (method url-fetch)
4646 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4647 "pyicoteo/get/v" version ".tar.bz2"))
4648 (file-name (string-append name "-" version ".tar.bz2"))
4649 (sha256
4650 (base32
4651 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4652 (build-system python-build-system)
4653 (arguments
4654 `(#:python ,python-2 ; does not work with Python 3
4655 #:tests? #f)) ; there are no tests
4656 (inputs
4657 `(("python2-matplotlib" ,python2-matplotlib)))
4658 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4659 (synopsis "Analyze high-throughput genetic sequencing data")
4660 (description
4661 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4662 sequencing data. It works with genomic coordinates. There are currently six
4663 different command-line tools:
4664
4665 @enumerate
4666 @item pyicoregion: for generating exploratory regions automatically;
4667 @item pyicoenrich: for differential enrichment between two conditions;
4668 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4669 @item pyicos: for genomic coordinates manipulation;
4670 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4671 @item pyicount: to count how many reads from N experiment files overlap in a
4672 region file;
4673 @item pyicotrocol: to combine operations from pyicoteo.
4674 @end enumerate\n")
4675 (license license:gpl3+)))
4676
4677 (define-public prodigal
4678 (package
4679 (name "prodigal")
4680 (version "2.6.3")
4681 (source (origin
4682 (method git-fetch)
4683 (uri (git-reference
4684 (url "https://github.com/hyattpd/Prodigal.git")
4685 (commit (string-append "v" version))))
4686 (file-name (git-file-name name version))
4687 (sha256
4688 (base32
4689 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4690 (build-system gnu-build-system)
4691 (arguments
4692 `(#:tests? #f ;no check target
4693 #:make-flags (list (string-append "INSTALLDIR="
4694 (assoc-ref %outputs "out")
4695 "/bin"))
4696 #:phases
4697 (modify-phases %standard-phases
4698 (delete 'configure))))
4699 (home-page "http://prodigal.ornl.gov")
4700 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4701 (description
4702 "Prodigal runs smoothly on finished genomes, draft genomes, and
4703 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4704 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4705 partial genes, and identifies translation initiation sites.")
4706 (license license:gpl3+)))
4707
4708 (define-public roary
4709 (package
4710 (name "roary")
4711 (version "3.12.0")
4712 (source
4713 (origin
4714 (method url-fetch)
4715 (uri (string-append
4716 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4717 version ".tar.gz"))
4718 (sha256
4719 (base32
4720 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4721 (build-system perl-build-system)
4722 (arguments
4723 `(#:phases
4724 (modify-phases %standard-phases
4725 (delete 'configure)
4726 (delete 'build)
4727 (replace 'check
4728 (lambda _
4729 ;; The tests are not run by default, so we run each test file
4730 ;; directly.
4731 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4732 (getenv "PATH")))
4733 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4734 (getenv "PERL5LIB")))
4735 (zero? (length (filter (lambda (file)
4736 (display file)(display "\n")
4737 (not (zero? (system* "perl" file))))
4738 (find-files "t" ".*\\.t$"))))))
4739 (replace 'install
4740 ;; There is no 'install' target in the Makefile.
4741 (lambda* (#:key outputs #:allow-other-keys)
4742 (let* ((out (assoc-ref outputs "out"))
4743 (bin (string-append out "/bin"))
4744 (perl (string-append out "/lib/perl5/site_perl"))
4745 (roary-plots "contrib/roary_plots"))
4746 (mkdir-p bin)
4747 (mkdir-p perl)
4748 (copy-recursively "bin" bin)
4749 (copy-recursively "lib" perl)
4750 #t)))
4751 (add-after 'install 'wrap-programs
4752 (lambda* (#:key inputs outputs #:allow-other-keys)
4753 (let* ((out (assoc-ref outputs "out"))
4754 (perl5lib (getenv "PERL5LIB"))
4755 (path (getenv "PATH")))
4756 (for-each (lambda (prog)
4757 (let ((binary (string-append out "/" prog)))
4758 (wrap-program binary
4759 `("PERL5LIB" ":" prefix
4760 (,(string-append perl5lib ":" out
4761 "/lib/perl5/site_perl"))))
4762 (wrap-program binary
4763 `("PATH" ":" prefix
4764 (,(string-append path ":" out "/bin"))))))
4765 (find-files "bin" ".*[^R]$"))
4766 (let ((file
4767 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4768 (r-site-lib (getenv "R_LIBS_SITE"))
4769 (coreutils-path
4770 (string-append (assoc-ref inputs "coreutils") "/bin")))
4771 (wrap-program file
4772 `("R_LIBS_SITE" ":" prefix
4773 (,(string-append r-site-lib ":" out "/site-library/"))))
4774 (wrap-program file
4775 `("PATH" ":" prefix
4776 (,(string-append coreutils-path ":" out "/bin"))))))
4777 #t)))))
4778 (native-inputs
4779 `(("perl-env-path" ,perl-env-path)
4780 ("perl-test-files" ,perl-test-files)
4781 ("perl-test-most" ,perl-test-most)
4782 ("perl-test-output" ,perl-test-output)))
4783 (inputs
4784 `(("perl-array-utils" ,perl-array-utils)
4785 ("bioperl" ,bioperl-minimal)
4786 ("perl-digest-md5-file" ,perl-digest-md5-file)
4787 ("perl-exception-class" ,perl-exception-class)
4788 ("perl-file-find-rule" ,perl-file-find-rule)
4789 ("perl-file-grep" ,perl-file-grep)
4790 ("perl-file-slurper" ,perl-file-slurper)
4791 ("perl-file-which" ,perl-file-which)
4792 ("perl-graph" ,perl-graph)
4793 ("perl-graph-readwrite" ,perl-graph-readwrite)
4794 ("perl-log-log4perl" ,perl-log-log4perl)
4795 ("perl-moose" ,perl-moose)
4796 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4797 ("perl-text-csv" ,perl-text-csv)
4798 ("bedtools" ,bedtools)
4799 ("cd-hit" ,cd-hit)
4800 ("blast+" ,blast+)
4801 ("mcl" ,mcl)
4802 ("parallel" ,parallel)
4803 ("prank" ,prank)
4804 ("mafft" ,mafft)
4805 ("fasttree" ,fasttree)
4806 ("grep" ,grep)
4807 ("sed" ,sed)
4808 ("gawk" ,gawk)
4809 ("r-minimal" ,r-minimal)
4810 ("r-ggplot2" ,r-ggplot2)
4811 ("coreutils" ,coreutils)))
4812 (home-page "http://sanger-pathogens.github.io/Roary")
4813 (synopsis "High speed stand-alone pan genome pipeline")
4814 (description
4815 "Roary is a high speed stand alone pan genome pipeline, which takes
4816 annotated assemblies in GFF3 format (produced by the Prokka program) and
4817 calculates the pan genome. Using a standard desktop PC, it can analyse
4818 datasets with thousands of samples, without compromising the quality of the
4819 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4820 single processor. Roary is not intended for metagenomics or for comparing
4821 extremely diverse sets of genomes.")
4822 (license license:gpl3)))
4823
4824 (define-public raxml
4825 (package
4826 (name "raxml")
4827 (version "8.2.10")
4828 (source
4829 (origin
4830 (method url-fetch)
4831 (uri
4832 (string-append
4833 "https://github.com/stamatak/standard-RAxML/archive/v"
4834 version ".tar.gz"))
4835 (file-name (string-append name "-" version ".tar.gz"))
4836 (sha256
4837 (base32
4838 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4839 (build-system gnu-build-system)
4840 (arguments
4841 `(#:tests? #f ; There are no tests.
4842 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4843 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4844 #:phases
4845 (modify-phases %standard-phases
4846 (delete 'configure)
4847 (replace 'install
4848 (lambda* (#:key outputs #:allow-other-keys)
4849 (let* ((out (assoc-ref outputs "out"))
4850 (bin (string-append out "/bin"))
4851 (executable "raxmlHPC-HYBRID"))
4852 (install-file executable bin)
4853 (symlink (string-append bin "/" executable) "raxml"))
4854 #t)))))
4855 (inputs
4856 `(("openmpi" ,openmpi)))
4857 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4858 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4859 (description
4860 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4861 phylogenies.")
4862 ;; The source includes x86 specific code
4863 (supported-systems '("x86_64-linux" "i686-linux"))
4864 (license license:gpl2+)))
4865
4866 (define-public rsem
4867 (package
4868 (name "rsem")
4869 (version "1.3.1")
4870 (source
4871 (origin
4872 (method git-fetch)
4873 (uri (git-reference
4874 (url "https://github.com/deweylab/RSEM.git")
4875 (commit (string-append "v" version))))
4876 (sha256
4877 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
4878 (file-name (git-file-name name version))
4879 (modules '((guix build utils)))
4880 (snippet
4881 '(begin
4882 ;; remove bundled copy of boost and samtools
4883 (delete-file-recursively "boost")
4884 (delete-file-recursively "samtools-1.3")
4885 #t))))
4886 (build-system gnu-build-system)
4887 (arguments
4888 `(#:tests? #f ;no "check" target
4889 #:make-flags
4890 (list (string-append "BOOST="
4891 (assoc-ref %build-inputs "boost")
4892 "/include/")
4893 (string-append "SAMHEADERS="
4894 (assoc-ref %build-inputs "htslib")
4895 "/include/htslib/sam.h")
4896 (string-append "SAMLIBS="
4897 (assoc-ref %build-inputs "htslib")
4898 "/lib/libhts.a"))
4899 #:phases
4900 (modify-phases %standard-phases
4901 ;; No "configure" script.
4902 ;; Do not build bundled samtools library.
4903 (replace 'configure
4904 (lambda _
4905 (substitute* "Makefile"
4906 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
4907 (("^\\$\\(SAMLIBS\\).*") ""))
4908 #t))
4909 (replace 'install
4910 (lambda* (#:key outputs #:allow-other-keys)
4911 (let* ((out (string-append (assoc-ref outputs "out")))
4912 (bin (string-append out "/bin/"))
4913 (perl (string-append out "/lib/perl5/site_perl")))
4914 (mkdir-p bin)
4915 (mkdir-p perl)
4916 (for-each (lambda (file)
4917 (install-file file bin))
4918 (find-files "." "rsem-.*"))
4919 (install-file "rsem_perl_utils.pm" perl))
4920 #t))
4921 (add-after 'install 'wrap-program
4922 (lambda* (#:key outputs #:allow-other-keys)
4923 (let ((out (assoc-ref outputs "out")))
4924 (for-each (lambda (prog)
4925 (wrap-program (string-append out "/bin/" prog)
4926 `("PERL5LIB" ":" prefix
4927 (,(string-append out "/lib/perl5/site_perl")))))
4928 '("rsem-calculate-expression"
4929 "rsem-control-fdr"
4930 "rsem-generate-data-matrix"
4931 "rsem-generate-ngvector"
4932 "rsem-plot-transcript-wiggles"
4933 "rsem-prepare-reference"
4934 "rsem-run-ebseq"
4935 "rsem-run-prsem-testing-procedure")))
4936 #t)))))
4937 (inputs
4938 `(("boost" ,boost)
4939 ("r-minimal" ,r-minimal)
4940 ("perl" ,perl)
4941 ("htslib" ,htslib-1.3)
4942 ("zlib" ,zlib)))
4943 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4944 (synopsis "Estimate gene expression levels from RNA-Seq data")
4945 (description
4946 "RSEM is a software package for estimating gene and isoform expression
4947 levels from RNA-Seq data. The RSEM package provides a user-friendly
4948 interface, supports threads for parallel computation of the EM algorithm,
4949 single-end and paired-end read data, quality scores, variable-length reads and
4950 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4951 interval estimates for expression levels. For visualization, it can generate
4952 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4953 (license license:gpl3+)))
4954
4955 (define-public rseqc
4956 (package
4957 (name "rseqc")
4958 (version "2.6.1")
4959 (source
4960 (origin
4961 (method url-fetch)
4962 (uri
4963 (string-append "mirror://sourceforge/rseqc/"
4964 "RSeQC-" version ".tar.gz"))
4965 (sha256
4966 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4967 (modules '((guix build utils)))
4968 (snippet
4969 '(begin
4970 ;; remove bundled copy of pysam
4971 (delete-file-recursively "lib/pysam")
4972 (substitute* "setup.py"
4973 ;; remove dependency on outdated "distribute" module
4974 (("^from distribute_setup import use_setuptools") "")
4975 (("^use_setuptools\\(\\)") "")
4976 ;; do not use bundled copy of pysam
4977 (("^have_pysam = False") "have_pysam = True"))
4978 #t))))
4979 (build-system python-build-system)
4980 (arguments `(#:python ,python-2))
4981 (inputs
4982 `(("python-cython" ,python2-cython)
4983 ("python-pysam" ,python2-pysam)
4984 ("python-numpy" ,python2-numpy)
4985 ("zlib" ,zlib)))
4986 (native-inputs
4987 `(("python-nose" ,python2-nose)))
4988 (home-page "http://rseqc.sourceforge.net/")
4989 (synopsis "RNA-seq quality control package")
4990 (description
4991 "RSeQC provides a number of modules that can comprehensively evaluate
4992 high throughput sequence data, especially RNA-seq data. Some basic modules
4993 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4994 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4995 distribution, coverage uniformity, strand specificity, etc.")
4996 (license license:gpl3+)))
4997
4998 (define-public seek
4999 ;; There are no release tarballs. According to the installation
5000 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5001 ;; stable release is identified by this changeset ID.
5002 (let ((changeset "2329130")
5003 (revision "1"))
5004 (package
5005 (name "seek")
5006 (version (string-append "0-" revision "." changeset))
5007 (source (origin
5008 (method hg-fetch)
5009 (uri (hg-reference
5010 (url "https://bitbucket.org/libsleipnir/sleipnir")
5011 (changeset changeset)))
5012 (file-name (string-append name "-" version "-checkout"))
5013 (sha256
5014 (base32
5015 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5016 (build-system gnu-build-system)
5017 (arguments
5018 `(#:modules ((srfi srfi-1)
5019 (guix build gnu-build-system)
5020 (guix build utils))
5021 #:phases
5022 (let ((dirs '("SeekMiner"
5023 "SeekEvaluator"
5024 "SeekPrep"
5025 "Distancer"
5026 "Data2DB"
5027 "PCL2Bin")))
5028 (modify-phases %standard-phases
5029 (replace 'bootstrap
5030 (lambda _
5031 (invoke "bash" "gen_auto")))
5032 (add-after 'build 'build-additional-tools
5033 (lambda* (#:key make-flags #:allow-other-keys)
5034 (every (lambda (dir)
5035 (with-directory-excursion (string-append "tools/" dir)
5036 (zero? (apply system* "make" make-flags))))
5037 dirs)))
5038 (add-after 'install 'install-additional-tools
5039 (lambda* (#:key make-flags #:allow-other-keys)
5040 (fold (lambda (dir result)
5041 (with-directory-excursion (string-append "tools/" dir)
5042 (and result
5043 (zero? (apply system*
5044 `("make" ,@make-flags "install"))))))
5045 #t dirs)))))))
5046 (inputs
5047 `(("gsl" ,gsl)
5048 ("boost" ,boost)
5049 ("libsvm" ,libsvm)
5050 ("readline" ,readline)
5051 ("gengetopt" ,gengetopt)
5052 ("log4cpp" ,log4cpp)))
5053 (native-inputs
5054 `(("autoconf" ,autoconf)
5055 ("automake" ,automake)
5056 ("perl" ,perl)))
5057 (home-page "http://seek.princeton.edu")
5058 (synopsis "Gene co-expression search engine")
5059 (description
5060 "SEEK is a computational gene co-expression search engine. SEEK provides
5061 biologists with a way to navigate the massive human expression compendium that
5062 now contains thousands of expression datasets. SEEK returns a robust ranking
5063 of co-expressed genes in the biological area of interest defined by the user's
5064 query genes. It also prioritizes thousands of expression datasets according
5065 to the user's query of interest.")
5066 (license license:cc-by3.0))))
5067
5068 (define-public samtools
5069 (package
5070 (name "samtools")
5071 (version "1.9")
5072 (source
5073 (origin
5074 (method url-fetch)
5075 (uri
5076 (string-append "mirror://sourceforge/samtools/samtools/"
5077 version "/samtools-" version ".tar.bz2"))
5078 (sha256
5079 (base32
5080 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5081 (modules '((guix build utils)))
5082 (snippet '(begin
5083 ;; Delete bundled htslib.
5084 (delete-file-recursively "htslib-1.9")
5085 #t))))
5086 (build-system gnu-build-system)
5087 (arguments
5088 `(#:modules ((ice-9 ftw)
5089 (ice-9 regex)
5090 (guix build gnu-build-system)
5091 (guix build utils))
5092 #:configure-flags (list "--with-ncurses")
5093 #:phases
5094 (modify-phases %standard-phases
5095 (add-after 'unpack 'patch-tests
5096 (lambda _
5097 (substitute* "test/test.pl"
5098 ;; The test script calls out to /bin/bash
5099 (("/bin/bash") (which "bash")))
5100 #t))
5101 (add-after 'install 'install-library
5102 (lambda* (#:key outputs #:allow-other-keys)
5103 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5104 (install-file "libbam.a" lib)
5105 #t)))
5106 (add-after 'install 'install-headers
5107 (lambda* (#:key outputs #:allow-other-keys)
5108 (let ((include (string-append (assoc-ref outputs "out")
5109 "/include/samtools/")))
5110 (for-each (lambda (file)
5111 (install-file file include))
5112 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5113 #t))))))
5114 (native-inputs `(("pkg-config" ,pkg-config)))
5115 (inputs
5116 `(("htslib" ,htslib)
5117 ("ncurses" ,ncurses)
5118 ("perl" ,perl)
5119 ("python" ,python)
5120 ("zlib" ,zlib)))
5121 (home-page "http://samtools.sourceforge.net")
5122 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5123 (description
5124 "Samtools implements various utilities for post-processing nucleotide
5125 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5126 variant calling (in conjunction with bcftools), and a simple alignment
5127 viewer.")
5128 (license license:expat)))
5129
5130 (define-public samtools-0.1
5131 ;; This is the most recent version of the 0.1 line of samtools. The input
5132 ;; and output formats differ greatly from that used and produced by samtools
5133 ;; 1.x and is still used in many bioinformatics pipelines.
5134 (package (inherit samtools)
5135 (version "0.1.19")
5136 (source
5137 (origin
5138 (method url-fetch)
5139 (uri
5140 (string-append "mirror://sourceforge/samtools/samtools/"
5141 version "/samtools-" version ".tar.bz2"))
5142 (sha256
5143 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5144 (arguments
5145 `(#:tests? #f ;no "check" target
5146 #:make-flags
5147 (list "LIBCURSES=-lncurses")
5148 ,@(substitute-keyword-arguments (package-arguments samtools)
5149 ((#:phases phases)
5150 `(modify-phases ,phases
5151 (replace 'install
5152 (lambda* (#:key outputs #:allow-other-keys)
5153 (let ((bin (string-append
5154 (assoc-ref outputs "out") "/bin")))
5155 (mkdir-p bin)
5156 (install-file "samtools" bin)
5157 #t)))
5158 (delete 'patch-tests)
5159 (delete 'configure))))))))
5160
5161 (define-public mosaik
5162 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5163 (package
5164 (name "mosaik")
5165 (version "2.2.30")
5166 (source (origin
5167 ;; There are no release tarballs nor tags.
5168 (method git-fetch)
5169 (uri (git-reference
5170 (url "https://github.com/wanpinglee/MOSAIK.git")
5171 (commit commit)))
5172 (file-name (string-append name "-" version))
5173 (sha256
5174 (base32
5175 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5176 (build-system gnu-build-system)
5177 (arguments
5178 `(#:tests? #f ; no tests
5179 #:make-flags (list "CC=gcc")
5180 #:phases
5181 (modify-phases %standard-phases
5182 (replace 'configure
5183 (lambda _ (chdir "src") #t))
5184 (replace 'install
5185 (lambda* (#:key outputs #:allow-other-keys)
5186 (let ((bin (string-append (assoc-ref outputs "out")
5187 "/bin")))
5188 (mkdir-p bin)
5189 (copy-recursively "../bin" bin)
5190 #t))))))
5191 (inputs
5192 `(("perl" ,perl)
5193 ("zlib" ,zlib)))
5194 (supported-systems '("x86_64-linux"))
5195 (home-page "https://github.com/wanpinglee/MOSAIK")
5196 (synopsis "Map nucleotide sequence reads to reference genomes")
5197 (description
5198 "MOSAIK is a program for mapping second and third-generation sequencing
5199 reads to a reference genome. MOSAIK can align reads generated by all the
5200 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5201 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5202 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5203 ;; code released into the public domain:
5204 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5205 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5206 (license (list license:gpl2+ license:public-domain)))))
5207
5208 (define-public ngs-sdk
5209 (package
5210 (name "ngs-sdk")
5211 (version "1.3.0")
5212 (source
5213 (origin
5214 (method url-fetch)
5215 (uri
5216 (string-append "https://github.com/ncbi/ngs/archive/"
5217 version ".tar.gz"))
5218 (file-name (string-append name "-" version ".tar.gz"))
5219 (sha256
5220 (base32
5221 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
5222 (build-system gnu-build-system)
5223 (arguments
5224 `(#:parallel-build? #f ; not supported
5225 #:tests? #f ; no "check" target
5226 #:phases
5227 (modify-phases %standard-phases
5228 (replace 'configure
5229 (lambda* (#:key outputs #:allow-other-keys)
5230 (let ((out (assoc-ref outputs "out")))
5231 ;; Allow 'konfigure.perl' to find 'package.prl'.
5232 (setenv "PERL5LIB"
5233 (string-append ".:" (getenv "PERL5LIB")))
5234
5235 ;; The 'configure' script doesn't recognize things like
5236 ;; '--enable-fast-install'.
5237 (zero? (system* "./configure"
5238 (string-append "--build-prefix=" (getcwd) "/build")
5239 (string-append "--prefix=" out))))))
5240 (add-after 'unpack 'enter-dir
5241 (lambda _ (chdir "ngs-sdk") #t)))))
5242 (native-inputs `(("perl" ,perl)))
5243 ;; According to the test
5244 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5245 ;; in ngs-sdk/setup/konfigure.perl
5246 (supported-systems '("i686-linux" "x86_64-linux"))
5247 (home-page "https://github.com/ncbi/ngs")
5248 (synopsis "API for accessing Next Generation Sequencing data")
5249 (description
5250 "NGS is a domain-specific API for accessing reads, alignments and pileups
5251 produced from Next Generation Sequencing. The API itself is independent from
5252 any particular back-end implementation, and supports use of multiple back-ends
5253 simultaneously.")
5254 (license license:public-domain)))
5255
5256 (define-public java-ngs
5257 (package (inherit ngs-sdk)
5258 (name "java-ngs")
5259 (arguments
5260 `(,@(substitute-keyword-arguments
5261 `(#:modules ((guix build gnu-build-system)
5262 (guix build utils)
5263 (srfi srfi-1)
5264 (srfi srfi-26))
5265 ,@(package-arguments ngs-sdk))
5266 ((#:phases phases)
5267 `(modify-phases ,phases
5268 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5269 (inputs
5270 `(("jdk" ,icedtea "jdk")
5271 ("ngs-sdk" ,ngs-sdk)))
5272 (synopsis "Java bindings for NGS SDK")))
5273
5274 (define-public ncbi-vdb
5275 (package
5276 (name "ncbi-vdb")
5277 (version "2.8.2")
5278 (source
5279 (origin
5280 (method url-fetch)
5281 (uri
5282 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
5283 version ".tar.gz"))
5284 (file-name (string-append name "-" version ".tar.gz"))
5285 (sha256
5286 (base32
5287 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
5288 (build-system gnu-build-system)
5289 (arguments
5290 `(#:parallel-build? #f ; not supported
5291 #:tests? #f ; no "check" target
5292 #:phases
5293 (modify-phases %standard-phases
5294 (add-before 'configure 'set-perl-search-path
5295 (lambda _
5296 ;; Work around "dotless @INC" build failure.
5297 (setenv "PERL5LIB"
5298 (string-append (getcwd) "/setup:"
5299 (getenv "PERL5LIB")))
5300 #t))
5301 (replace 'configure
5302 (lambda* (#:key inputs outputs #:allow-other-keys)
5303 (let ((out (assoc-ref outputs "out")))
5304 ;; Override include path for libmagic
5305 (substitute* "setup/package.prl"
5306 (("name => 'magic', Include => '/usr/include'")
5307 (string-append "name=> 'magic', Include => '"
5308 (assoc-ref inputs "libmagic")
5309 "/include" "'")))
5310
5311 ;; Install kdf5 library (needed by sra-tools)
5312 (substitute* "build/Makefile.install"
5313 (("LIBRARIES_TO_INSTALL =")
5314 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5315
5316 (substitute* "build/Makefile.env"
5317 (("CFLAGS =" prefix)
5318 (string-append prefix "-msse2 ")))
5319
5320 ;; Override search path for ngs-java
5321 (substitute* "setup/package.prl"
5322 (("/usr/local/ngs/ngs-java")
5323 (assoc-ref inputs "java-ngs")))
5324
5325 ;; The 'configure' script doesn't recognize things like
5326 ;; '--enable-fast-install'.
5327 (zero? (system*
5328 "./configure"
5329 (string-append "--build-prefix=" (getcwd) "/build")
5330 (string-append "--prefix=" (assoc-ref outputs "out"))
5331 (string-append "--debug")
5332 (string-append "--with-xml2-prefix="
5333 (assoc-ref inputs "libxml2"))
5334 (string-append "--with-ngs-sdk-prefix="
5335 (assoc-ref inputs "ngs-sdk"))
5336 (string-append "--with-hdf5-prefix="
5337 (assoc-ref inputs "hdf5")))))))
5338 (add-after 'install 'install-interfaces
5339 (lambda* (#:key outputs #:allow-other-keys)
5340 ;; Install interface libraries. On i686 the interface libraries
5341 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5342 ;; architecture name ("i386") instead of the target system prefix
5343 ;; ("i686").
5344 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5345 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5346 ,(system->linux-architecture
5347 (or (%current-target-system)
5348 (%current-system)))
5349 "/rel/ilib")
5350 (string-append (assoc-ref outputs "out")
5351 "/ilib"))
5352 ;; Install interface headers
5353 (copy-recursively "interfaces"
5354 (string-append (assoc-ref outputs "out")
5355 "/include"))
5356 #t))
5357 ;; These files are needed by sra-tools.
5358 (add-after 'install 'install-configuration-files
5359 (lambda* (#:key outputs #:allow-other-keys)
5360 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5361 (mkdir target)
5362 (install-file "libs/kfg/default.kfg" target)
5363 (install-file "libs/kfg/certs.kfg" target))
5364 #t)))))
5365 (inputs
5366 `(("libxml2" ,libxml2)
5367 ("ngs-sdk" ,ngs-sdk)
5368 ("java-ngs" ,java-ngs)
5369 ("libmagic" ,file)
5370 ("hdf5" ,hdf5)))
5371 (native-inputs `(("perl" ,perl)))
5372 ;; NCBI-VDB requires SSE capability.
5373 (supported-systems '("i686-linux" "x86_64-linux"))
5374 (home-page "https://github.com/ncbi/ncbi-vdb")
5375 (synopsis "Database engine for genetic information")
5376 (description
5377 "The NCBI-VDB library implements a highly compressed columnar data
5378 warehousing engine that is most often used to store genetic information.
5379 Databases are stored in a portable image within the file system, and can be
5380 accessed/downloaded on demand across HTTP.")
5381 (license license:public-domain)))
5382
5383 (define-public plink
5384 (package
5385 (name "plink")
5386 (version "1.07")
5387 (source
5388 (origin
5389 (method url-fetch)
5390 (uri (string-append
5391 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5392 version "-src.zip"))
5393 (sha256
5394 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5395 (patches (search-patches "plink-1.07-unclobber-i.patch"
5396 "plink-endian-detection.patch"))))
5397 (build-system gnu-build-system)
5398 (arguments
5399 '(#:tests? #f ;no "check" target
5400 #:make-flags (list (string-append "LIB_LAPACK="
5401 (assoc-ref %build-inputs "lapack")
5402 "/lib/liblapack.so")
5403 "WITH_LAPACK=1"
5404 "FORCE_DYNAMIC=1"
5405 ;; disable phoning home
5406 "WITH_WEBCHECK=")
5407 #:phases
5408 (modify-phases %standard-phases
5409 ;; no "configure" script
5410 (delete 'configure)
5411 (replace 'install
5412 (lambda* (#:key outputs #:allow-other-keys)
5413 (let ((bin (string-append (assoc-ref outputs "out")
5414 "/bin/")))
5415 (install-file "plink" bin)
5416 #t))))))
5417 (inputs
5418 `(("zlib" ,zlib)
5419 ("lapack" ,lapack)))
5420 (native-inputs
5421 `(("unzip" ,unzip)))
5422 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5423 (synopsis "Whole genome association analysis toolset")
5424 (description
5425 "PLINK is a whole genome association analysis toolset, designed to
5426 perform a range of basic, large-scale analyses in a computationally efficient
5427 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5428 so there is no support for steps prior to this (e.g. study design and
5429 planning, generating genotype or CNV calls from raw data). Through
5430 integration with gPLINK and Haploview, there is some support for the
5431 subsequent visualization, annotation and storage of results.")
5432 ;; Code is released under GPLv2, except for fisher.h, which is under
5433 ;; LGPLv2.1+
5434 (license (list license:gpl2 license:lgpl2.1+))))
5435
5436 (define-public plink-ng
5437 (package (inherit plink)
5438 (name "plink-ng")
5439 (version "1.90b4")
5440 (source
5441 (origin
5442 (method url-fetch)
5443 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
5444 version ".tar.gz"))
5445 (file-name (string-append name "-" version ".tar.gz"))
5446 (sha256
5447 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
5448 (build-system gnu-build-system)
5449 (arguments
5450 '(#:tests? #f ;no "check" target
5451 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5452 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5453 "ZLIB=-lz"
5454 "-f" "Makefile.std")
5455 #:phases
5456 (modify-phases %standard-phases
5457 (add-after 'unpack 'chdir
5458 (lambda _ (chdir "1.9") #t))
5459 (delete 'configure) ; no "configure" script
5460 (replace 'install
5461 (lambda* (#:key outputs #:allow-other-keys)
5462 (let ((bin (string-append (assoc-ref outputs "out")
5463 "/bin/")))
5464 (install-file "plink" bin)
5465 #t))))))
5466 (inputs
5467 `(("zlib" ,zlib)
5468 ("lapack" ,lapack)
5469 ("openblas" ,openblas)))
5470 (home-page "https://www.cog-genomics.org/plink/")
5471 (license license:gpl3+)))
5472
5473 (define-public smithlab-cpp
5474 (let ((revision "1")
5475 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5476 (package
5477 (name "smithlab-cpp")
5478 (version (string-append "0." revision "." (string-take commit 7)))
5479 (source (origin
5480 (method git-fetch)
5481 (uri (git-reference
5482 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5483 (commit commit)))
5484 (file-name (string-append name "-" version "-checkout"))
5485 (sha256
5486 (base32
5487 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5488 (build-system gnu-build-system)
5489 (arguments
5490 `(#:modules ((guix build gnu-build-system)
5491 (guix build utils)
5492 (srfi srfi-26))
5493 #:tests? #f ;no "check" target
5494 #:phases
5495 (modify-phases %standard-phases
5496 (add-after 'unpack 'use-samtools-headers
5497 (lambda _
5498 (substitute* '("SAM.cpp"
5499 "SAM.hpp")
5500 (("sam.h") "samtools/sam.h"))
5501 #t))
5502 (replace 'install
5503 (lambda* (#:key outputs #:allow-other-keys)
5504 (let* ((out (assoc-ref outputs "out"))
5505 (lib (string-append out "/lib"))
5506 (include (string-append out "/include/smithlab-cpp")))
5507 (mkdir-p lib)
5508 (mkdir-p include)
5509 (for-each (cut install-file <> lib)
5510 (find-files "." "\\.o$"))
5511 (for-each (cut install-file <> include)
5512 (find-files "." "\\.hpp$")))
5513 #t))
5514 (delete 'configure))))
5515 (inputs
5516 `(("samtools" ,samtools-0.1)
5517 ("zlib" ,zlib)))
5518 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5519 (synopsis "C++ helper library for functions used in Smith lab projects")
5520 (description
5521 "Smithlab CPP is a C++ library that includes functions used in many of
5522 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5523 structures, classes for genomic regions, mapped sequencing reads, etc.")
5524 (license license:gpl3+))))
5525
5526 (define-public preseq
5527 (package
5528 (name "preseq")
5529 (version "2.0")
5530 (source (origin
5531 (method url-fetch)
5532 (uri (string-append "https://github.com/smithlabcode/"
5533 "preseq/archive/v" version ".tar.gz"))
5534 (file-name (string-append name "-" version ".tar.gz"))
5535 (sha256
5536 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
5537 (modules '((guix build utils)))
5538 (snippet '(begin
5539 ;; Remove bundled samtools.
5540 (delete-file-recursively "samtools")
5541 #t))))
5542 (build-system gnu-build-system)
5543 (arguments
5544 `(#:tests? #f ;no "check" target
5545 #:phases
5546 (modify-phases %standard-phases
5547 (delete 'configure))
5548 #:make-flags
5549 (list (string-append "PREFIX="
5550 (assoc-ref %outputs "out"))
5551 (string-append "LIBBAM="
5552 (assoc-ref %build-inputs "samtools")
5553 "/lib/libbam.a")
5554 (string-append "SMITHLAB_CPP="
5555 (assoc-ref %build-inputs "smithlab-cpp")
5556 "/lib")
5557 "PROGS=preseq"
5558 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5559 (inputs
5560 `(("gsl" ,gsl)
5561 ("samtools" ,samtools-0.1)
5562 ("smithlab-cpp" ,smithlab-cpp)
5563 ("zlib" ,zlib)))
5564 (home-page "http://smithlabresearch.org/software/preseq/")
5565 (synopsis "Program for analyzing library complexity")
5566 (description
5567 "The preseq package is aimed at predicting and estimating the complexity
5568 of a genomic sequencing library, equivalent to predicting and estimating the
5569 number of redundant reads from a given sequencing depth and how many will be
5570 expected from additional sequencing using an initial sequencing experiment.
5571 The estimates can then be used to examine the utility of further sequencing,
5572 optimize the sequencing depth, or to screen multiple libraries to avoid low
5573 complexity samples.")
5574 (license license:gpl3+)))
5575
5576 (define-public python-screed
5577 (package
5578 (name "python-screed")
5579 (version "1.0")
5580 (source
5581 (origin
5582 (method url-fetch)
5583 (uri (pypi-uri "screed" version))
5584 (sha256
5585 (base32
5586 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5587 (build-system python-build-system)
5588 (arguments
5589 '(#:phases
5590 (modify-phases %standard-phases
5591 ;; Tests must be run after installation, as the "screed" command does
5592 ;; not exist right after building.
5593 (delete 'check)
5594 (add-after 'install 'check
5595 (lambda* (#:key inputs outputs #:allow-other-keys)
5596 (let ((out (assoc-ref outputs "out")))
5597 (setenv "PYTHONPATH"
5598 (string-append out "/lib/python"
5599 (string-take (string-take-right
5600 (assoc-ref inputs "python")
5601 5) 3)
5602 "/site-packages:"
5603 (getenv "PYTHONPATH")))
5604 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5605 (invoke "python" "setup.py" "test")
5606 #t)))))
5607 (native-inputs
5608 `(("python-pytest" ,python-pytest)
5609 ("python-pytest-cov" ,python-pytest-cov)
5610 ("python-pytest-runner" ,python-pytest-runner)))
5611 (inputs
5612 `(("python-bz2file" ,python-bz2file)))
5613 (home-page "https://github.com/dib-lab/screed/")
5614 (synopsis "Short read sequence database utilities")
5615 (description "Screed parses FASTA and FASTQ files and generates databases.
5616 Values such as sequence name, sequence description, sequence quality and the
5617 sequence itself can be retrieved from these databases.")
5618 (license license:bsd-3)))
5619
5620 (define-public python2-screed
5621 (package-with-python2 python-screed))
5622
5623 (define-public sra-tools
5624 (package
5625 (name "sra-tools")
5626 (version "2.8.2-1")
5627 (source
5628 (origin
5629 (method url-fetch)
5630 (uri
5631 (string-append "https://github.com/ncbi/sra-tools/archive/"
5632 version ".tar.gz"))
5633 (file-name (string-append name "-" version ".tar.gz"))
5634 (sha256
5635 (base32
5636 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5637 (build-system gnu-build-system)
5638 (arguments
5639 `(#:parallel-build? #f ; not supported
5640 #:tests? #f ; no "check" target
5641 #:make-flags
5642 (list (string-append "DEFAULT_CRT="
5643 (assoc-ref %build-inputs "ncbi-vdb")
5644 "/kfg/certs.kfg")
5645 (string-append "DEFAULT_KFG="
5646 (assoc-ref %build-inputs "ncbi-vdb")
5647 "/kfg/default.kfg")
5648 (string-append "VDB_LIBDIR="
5649 (assoc-ref %build-inputs "ncbi-vdb")
5650 ,(if (string-prefix? "x86_64"
5651 (or (%current-target-system)
5652 (%current-system)))
5653 "/lib64"
5654 "/lib32")))
5655 #:phases
5656 (modify-phases %standard-phases
5657 (add-before 'configure 'set-perl-search-path
5658 (lambda _
5659 ;; Work around "dotless @INC" build failure.
5660 (setenv "PERL5LIB"
5661 (string-append (getcwd) "/setup:"
5662 (getenv "PERL5LIB")))
5663 #t))
5664 (replace 'configure
5665 (lambda* (#:key inputs outputs #:allow-other-keys)
5666 ;; The build system expects a directory containing the sources and
5667 ;; raw build output of ncbi-vdb, including files that are not
5668 ;; installed. Since we are building against an installed version of
5669 ;; ncbi-vdb, the following modifications are needed.
5670 (substitute* "setup/konfigure.perl"
5671 ;; Make the configure script look for the "ilib" directory of
5672 ;; "ncbi-vdb" without first checking for the existence of a
5673 ;; matching library in its "lib" directory.
5674 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5675 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5676 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5677 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5678 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5679
5680 ;; Dynamic linking
5681 (substitute* "tools/copycat/Makefile"
5682 (("smagic-static") "lmagic"))
5683
5684 ;; The 'configure' script doesn't recognize things like
5685 ;; '--enable-fast-install'.
5686 (zero? (system*
5687 "./configure"
5688 (string-append "--build-prefix=" (getcwd) "/build")
5689 (string-append "--prefix=" (assoc-ref outputs "out"))
5690 (string-append "--debug")
5691 (string-append "--with-fuse-prefix="
5692 (assoc-ref inputs "fuse"))
5693 (string-append "--with-magic-prefix="
5694 (assoc-ref inputs "libmagic"))
5695 ;; TODO: building with libxml2 fails with linker errors
5696 ;; (string-append "--with-xml2-prefix="
5697 ;; (assoc-ref inputs "libxml2"))
5698 (string-append "--with-ncbi-vdb-sources="
5699 (assoc-ref inputs "ncbi-vdb"))
5700 (string-append "--with-ncbi-vdb-build="
5701 (assoc-ref inputs "ncbi-vdb"))
5702 (string-append "--with-ngs-sdk-prefix="
5703 (assoc-ref inputs "ngs-sdk"))
5704 (string-append "--with-hdf5-prefix="
5705 (assoc-ref inputs "hdf5"))))))
5706 ;; This version of sra-tools fails to build with glibc because of a
5707 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5708 ;; contains a definition of "canonicalize", so we rename it.
5709 ;;
5710 ;; See upstream bug report:
5711 ;; https://github.com/ncbi/sra-tools/issues/67
5712 (add-after 'unpack 'patch-away-glibc-conflict
5713 (lambda _
5714 (substitute* "tools/bam-loader/bam.c"
5715 (("canonicalize\\(" line)
5716 (string-append "sra_tools_" line)))
5717 #t)))))
5718 (native-inputs `(("perl" ,perl)))
5719 (inputs
5720 `(("ngs-sdk" ,ngs-sdk)
5721 ("ncbi-vdb" ,ncbi-vdb)
5722 ("libmagic" ,file)
5723 ("fuse" ,fuse)
5724 ("hdf5" ,hdf5)
5725 ("zlib" ,zlib)))
5726 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5727 (synopsis "Tools and libraries for reading and writing sequencing data")
5728 (description
5729 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5730 reading of sequencing files from the Sequence Read Archive (SRA) database and
5731 writing files into the .sra format.")
5732 (license license:public-domain)))
5733
5734 (define-public seqan
5735 (package
5736 (name "seqan")
5737 (version "2.4.0")
5738 (source (origin
5739 (method url-fetch)
5740 (uri (string-append "https://github.com/seqan/seqan/releases/"
5741 "download/seqan-v" version
5742 "/seqan-library-" version ".tar.xz"))
5743 (sha256
5744 (base32
5745 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
5746 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5747 ;; makes sense to split the outputs.
5748 (outputs '("out" "doc"))
5749 (build-system trivial-build-system)
5750 (arguments
5751 `(#:modules ((guix build utils))
5752 #:builder
5753 (begin
5754 (use-modules (guix build utils))
5755 (let ((tar (assoc-ref %build-inputs "tar"))
5756 (xz (assoc-ref %build-inputs "xz"))
5757 (out (assoc-ref %outputs "out"))
5758 (doc (assoc-ref %outputs "doc")))
5759 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
5760 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5761 (chdir (string-append "seqan-library-" ,version))
5762 (copy-recursively "include" (string-append out "/include"))
5763 (copy-recursively "share" (string-append doc "/share"))
5764 #t))))
5765 (native-inputs
5766 `(("source" ,source)
5767 ("tar" ,tar)
5768 ("xz" ,xz)))
5769 (home-page "http://www.seqan.de")
5770 (synopsis "Library for nucleotide sequence analysis")
5771 (description
5772 "SeqAn is a C++ library of efficient algorithms and data structures for
5773 the analysis of sequences with the focus on biological data. It contains
5774 algorithms and data structures for string representation and their
5775 manipulation, online and indexed string search, efficient I/O of
5776 bioinformatics file formats, sequence alignment, and more.")
5777 (license license:bsd-3)))
5778
5779 (define-public seqan-1
5780 (package (inherit seqan)
5781 (name "seqan")
5782 (version "1.4.2")
5783 (source (origin
5784 (method url-fetch)
5785 (uri (string-append "http://packages.seqan.de/seqan-library/"
5786 "seqan-library-" version ".tar.bz2"))
5787 (sha256
5788 (base32
5789 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5790 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5791 ;; makes sense to split the outputs.
5792 (outputs '("out" "doc"))
5793 (build-system trivial-build-system)
5794 (arguments
5795 `(#:modules ((guix build utils))
5796 #:builder
5797 (begin
5798 (use-modules (guix build utils))
5799 (let ((tar (assoc-ref %build-inputs "tar"))
5800 (bzip (assoc-ref %build-inputs "bzip2"))
5801 (out (assoc-ref %outputs "out"))
5802 (doc (assoc-ref %outputs "doc")))
5803 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5804 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5805 (chdir (string-append "seqan-library-" ,version))
5806 (copy-recursively "include" (string-append out "/include"))
5807 (copy-recursively "share" (string-append doc "/share"))
5808 #t))))
5809 (native-inputs
5810 `(("source" ,source)
5811 ("tar" ,tar)
5812 ("bzip2" ,bzip2)))))
5813
5814 (define-public seqmagick
5815 (package
5816 (name "seqmagick")
5817 (version "0.7.0")
5818 (source
5819 (origin
5820 (method url-fetch)
5821 (uri (pypi-uri "seqmagick" version))
5822 (sha256
5823 (base32
5824 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5825 (build-system python-build-system)
5826 (inputs
5827 `(("python-biopython" ,python-biopython)))
5828 (native-inputs
5829 `(("python-nose" ,python-nose)))
5830 (home-page "https://github.com/fhcrc/seqmagick")
5831 (synopsis "Tools for converting and modifying sequence files")
5832 (description
5833 "Bioinformaticians often have to convert sequence files between formats
5834 and do little manipulations on them, and it's not worth writing scripts for
5835 that. Seqmagick is a utility to expose the file format conversion in
5836 BioPython in a convenient way. Instead of having a big mess of scripts, there
5837 is one that takes arguments.")
5838 (license license:gpl3)))
5839
5840 (define-public seqtk
5841 (package
5842 (name "seqtk")
5843 (version "1.2")
5844 (source (origin
5845 (method url-fetch)
5846 (uri (string-append
5847 "https://github.com/lh3/seqtk/archive/v"
5848 version ".tar.gz"))
5849 (file-name (string-append name "-" version ".tar.gz"))
5850 (sha256
5851 (base32
5852 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5853 (modules '((guix build utils)))
5854 (snippet
5855 '(begin
5856 ;; Remove extraneous header files, as is done in the seqtk
5857 ;; master branch.
5858 (for-each (lambda (file) (delete-file file))
5859 (list "ksort.h" "kstring.h" "kvec.h"))
5860 #t))))
5861 (build-system gnu-build-system)
5862 (arguments
5863 `(#:phases
5864 (modify-phases %standard-phases
5865 (delete 'configure)
5866 (replace 'check
5867 ;; There are no tests, so we just run a sanity check.
5868 (lambda _ (zero? (system* "./seqtk" "seq"))))
5869 (replace 'install
5870 (lambda* (#:key outputs #:allow-other-keys)
5871 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5872 (install-file "seqtk" bin)))))))
5873 (inputs
5874 `(("zlib" ,zlib)))
5875 (home-page "https://github.com/lh3/seqtk")
5876 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5877 (description
5878 "Seqtk is a fast and lightweight tool for processing sequences in the
5879 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5880 optionally compressed by gzip.")
5881 (license license:expat)))
5882
5883 (define-public snap-aligner
5884 (package
5885 (name "snap-aligner")
5886 (version "1.0beta.18")
5887 (source (origin
5888 (method url-fetch)
5889 (uri (string-append
5890 "https://github.com/amplab/snap/archive/v"
5891 version ".tar.gz"))
5892 (file-name (string-append name "-" version ".tar.gz"))
5893 (sha256
5894 (base32
5895 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5896 (build-system gnu-build-system)
5897 (arguments
5898 '(#:phases
5899 (modify-phases %standard-phases
5900 (delete 'configure)
5901 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5902 (replace 'install
5903 (lambda* (#:key outputs #:allow-other-keys)
5904 (let* ((out (assoc-ref outputs "out"))
5905 (bin (string-append out "/bin")))
5906 (install-file "snap-aligner" bin)
5907 (install-file "SNAPCommand" bin)
5908 #t))))))
5909 (native-inputs
5910 `(("zlib" ,zlib)))
5911 (home-page "http://snap.cs.berkeley.edu/")
5912 (synopsis "Short read DNA sequence aligner")
5913 (description
5914 "SNAP is a fast and accurate aligner for short DNA reads. It is
5915 optimized for modern read lengths of 100 bases or higher, and takes advantage
5916 of these reads to align data quickly through a hash-based indexing scheme.")
5917 ;; 32-bit systems are not supported by the unpatched code.
5918 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5919 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5920 ;; systems without a lot of memory cannot make good use of this program.
5921 (supported-systems '("x86_64-linux"))
5922 (license license:asl2.0)))
5923
5924 (define-public sortmerna
5925 (package
5926 (name "sortmerna")
5927 (version "2.1b")
5928 (source
5929 (origin
5930 (method url-fetch)
5931 (uri (string-append
5932 "https://github.com/biocore/sortmerna/archive/"
5933 version ".tar.gz"))
5934 (file-name (string-append name "-" version ".tar.gz"))
5935 (sha256
5936 (base32
5937 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5938 (build-system gnu-build-system)
5939 (outputs '("out" ;for binaries
5940 "db")) ;for sequence databases
5941 (arguments
5942 `(#:phases
5943 (modify-phases %standard-phases
5944 (replace 'install
5945 (lambda* (#:key outputs #:allow-other-keys)
5946 (let* ((out (assoc-ref outputs "out"))
5947 (bin (string-append out "/bin"))
5948 (db (assoc-ref outputs "db"))
5949 (share
5950 (string-append db "/share/sortmerna/rRNA_databases")))
5951 (install-file "sortmerna" bin)
5952 (install-file "indexdb_rna" bin)
5953 (for-each (lambda (file)
5954 (install-file file share))
5955 (find-files "rRNA_databases" ".*fasta"))
5956 #t))))))
5957 (inputs
5958 `(("zlib" ,zlib)))
5959 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5960 (synopsis "Biological sequence analysis tool for NGS reads")
5961 (description
5962 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5963 and operational taxonomic unit (OTU) picking of next generation
5964 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5965 allows for fast and sensitive analyses of nucleotide sequences. The main
5966 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5967 ;; The source includes x86 specific code
5968 (supported-systems '("x86_64-linux" "i686-linux"))
5969 (license license:lgpl3)))
5970
5971 (define-public star
5972 (package
5973 (name "star")
5974 (version "2.6.0c")
5975 (source (origin
5976 (method git-fetch)
5977 (uri (git-reference
5978 (url "https://github.com/alexdobin/STAR.git")
5979 (commit version)))
5980 (file-name (string-append name "-" version "-checkout"))
5981 (sha256
5982 (base32
5983 "04cj6jw8d9q6lk9c78wa4fky6jdlicf1d13plq7182h8vqiz8p59"))
5984 (modules '((guix build utils)))
5985 (snippet
5986 '(begin
5987 (substitute* "source/Makefile"
5988 (("/bin/rm") "rm"))
5989 ;; Remove pre-built binaries and bundled htslib sources.
5990 (delete-file-recursively "bin/MacOSX_x86_64")
5991 (delete-file-recursively "bin/Linux_x86_64")
5992 (delete-file-recursively "bin/Linux_x86_64_static")
5993 (delete-file-recursively "source/htslib")
5994 #t))))
5995 (build-system gnu-build-system)
5996 (arguments
5997 '(#:tests? #f ;no check target
5998 #:make-flags '("STAR")
5999 #:phases
6000 (modify-phases %standard-phases
6001 (add-after 'unpack 'enter-source-dir
6002 (lambda _ (chdir "source") #t))
6003 (add-after 'enter-source-dir 'make-reproducible
6004 (lambda _
6005 (substitute* "Makefile"
6006 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6007 (string-append pre "Built with Guix" post)))))
6008 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6009 (lambda _
6010 (substitute* "Makefile"
6011 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6012 _ prefix) prefix))
6013 (substitute* '("BAMfunctions.cpp"
6014 "signalFromBAM.h"
6015 "bam_cat.h"
6016 "bam_cat.c"
6017 "STAR.cpp"
6018 "bamRemoveDuplicates.cpp")
6019 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6020 (string-append "#include <" header ">")))
6021 (substitute* "IncludeDefine.h"
6022 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6023 (string-append "<" header ">")))
6024 #t))
6025 (replace 'install
6026 (lambda* (#:key outputs #:allow-other-keys)
6027 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6028 (install-file "STAR" bin))
6029 #t))
6030 (delete 'configure))))
6031 (native-inputs
6032 `(("xxd" ,xxd)))
6033 (inputs
6034 `(("htslib" ,htslib)
6035 ("zlib" ,zlib)))
6036 (home-page "https://github.com/alexdobin/STAR")
6037 (synopsis "Universal RNA-seq aligner")
6038 (description
6039 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6040 based on a previously undescribed RNA-seq alignment algorithm that uses
6041 sequential maximum mappable seed search in uncompressed suffix arrays followed
6042 by seed clustering and stitching procedure. In addition to unbiased de novo
6043 detection of canonical junctions, STAR can discover non-canonical splices and
6044 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6045 sequences.")
6046 ;; Only 64-bit systems are supported according to the README.
6047 (supported-systems '("x86_64-linux" "mips64el-linux"))
6048 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6049 (license license:gpl3+)))
6050
6051 (define-public subread
6052 (package
6053 (name "subread")
6054 (version "1.6.0")
6055 (source (origin
6056 (method url-fetch)
6057 (uri (string-append "mirror://sourceforge/subread/subread-"
6058 version "/subread-" version "-source.tar.gz"))
6059 (sha256
6060 (base32
6061 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6062 (build-system gnu-build-system)
6063 (arguments
6064 `(#:tests? #f ;no "check" target
6065 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6066 ;; optimizations by default, so we override these flags such that x86_64
6067 ;; flags are only added when the build target is an x86_64 system.
6068 #:make-flags
6069 (list (let ((system ,(or (%current-target-system)
6070 (%current-system)))
6071 (flags '("-ggdb" "-fomit-frame-pointer"
6072 "-ffast-math" "-funroll-loops"
6073 "-fmessage-length=0"
6074 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6075 "-DMAKE_STANDALONE"
6076 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6077 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6078 (if (string-prefix? "x86_64" system)
6079 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6080 (string-append "CCFLAGS=" (string-join flags))))
6081 "-f" "Makefile.Linux"
6082 "CC=gcc ${CCFLAGS}")
6083 #:phases
6084 (modify-phases %standard-phases
6085 (add-after 'unpack 'enter-dir
6086 (lambda _ (chdir "src") #t))
6087 (replace 'install
6088 (lambda* (#:key outputs #:allow-other-keys)
6089 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6090 (mkdir-p bin)
6091 (copy-recursively "../bin" bin))))
6092 ;; no "configure" script
6093 (delete 'configure))))
6094 (inputs `(("zlib" ,zlib)))
6095 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6096 (synopsis "Tool kit for processing next-gen sequencing data")
6097 (description
6098 "The subread package contains the following tools: subread aligner, a
6099 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6100 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6101 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6102 against local background noises.")
6103 (license license:gpl3+)))
6104
6105 (define-public stringtie
6106 (package
6107 (name "stringtie")
6108 (version "1.2.1")
6109 (source (origin
6110 (method url-fetch)
6111 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6112 "stringtie-" version ".tar.gz"))
6113 (sha256
6114 (base32
6115 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6116 (modules '((guix build utils)))
6117 (snippet
6118 '(begin
6119 (delete-file-recursively "samtools-0.1.18")
6120 #t))))
6121 (build-system gnu-build-system)
6122 (arguments
6123 `(#:tests? #f ;no test suite
6124 #:phases
6125 (modify-phases %standard-phases
6126 ;; no configure script
6127 (delete 'configure)
6128 (add-before 'build 'use-system-samtools
6129 (lambda _
6130 (substitute* "Makefile"
6131 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6132 "stringtie: "))
6133 (substitute* '("gclib/GBam.h"
6134 "gclib/GBam.cpp")
6135 (("#include \"(bam|sam|kstring).h\"" _ header)
6136 (string-append "#include <samtools/" header ".h>")))
6137 #t))
6138 (add-after 'unpack 'remove-duplicate-typedef
6139 (lambda _
6140 ;; This typedef conflicts with the typedef in
6141 ;; glibc-2.25/include/bits/types.h
6142 (substitute* "gclib/GThreads.h"
6143 (("typedef long long __intmax_t;") ""))
6144 #t))
6145 (replace 'install
6146 (lambda* (#:key outputs #:allow-other-keys)
6147 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6148 (install-file "stringtie" bin)
6149 #t))))))
6150 (inputs
6151 `(("samtools" ,samtools-0.1)
6152 ("zlib" ,zlib)))
6153 (home-page "http://ccb.jhu.edu/software/stringtie/")
6154 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6155 (description
6156 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6157 alignments into potential transcripts. It uses a novel network flow algorithm
6158 as well as an optional de novo assembly step to assemble and quantitate
6159 full-length transcripts representing multiple splice variants for each gene
6160 locus. Its input can include not only the alignments of raw reads used by
6161 other transcript assemblers, but also alignments of longer sequences that have
6162 been assembled from those reads. To identify differentially expressed genes
6163 between experiments, StringTie's output can be processed either by the
6164 Cuffdiff or Ballgown programs.")
6165 (license license:artistic2.0)))
6166
6167 (define-public taxtastic
6168 (package
6169 (name "taxtastic")
6170 (version "0.8.5")
6171 (source (origin
6172 (method url-fetch)
6173 (uri (pypi-uri "taxtastic" version))
6174 (sha256
6175 (base32
6176 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6177 (build-system python-build-system)
6178 (arguments
6179 `(#:python ,python-2
6180 #:phases
6181 (modify-phases %standard-phases
6182 (replace 'check
6183 (lambda _
6184 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
6185 (propagated-inputs
6186 `(("python-sqlalchemy" ,python2-sqlalchemy)
6187 ("python-decorator" ,python2-decorator)
6188 ("python-biopython" ,python2-biopython)
6189 ("python-pandas" ,python2-pandas)
6190 ("python-psycopg2" ,python2-psycopg2)
6191 ("python-fastalite" ,python2-fastalite)
6192 ("python-pyyaml" ,python2-pyyaml)
6193 ("python-six" ,python2-six)
6194 ("python-jinja2" ,python2-jinja2)
6195 ("python-dendropy" ,python2-dendropy)))
6196 (home-page "https://github.com/fhcrc/taxtastic")
6197 (synopsis "Tools for taxonomic naming and annotation")
6198 (description
6199 "Taxtastic is software written in python used to build and maintain
6200 reference packages i.e. collections of reference trees, reference alignments,
6201 profiles, and associated taxonomic information.")
6202 (license license:gpl3+)))
6203
6204 (define-public vcftools
6205 (package
6206 (name "vcftools")
6207 (version "0.1.15")
6208 (source (origin
6209 (method url-fetch)
6210 (uri (string-append
6211 "https://github.com/vcftools/vcftools/releases/download/v"
6212 version "/vcftools-" version ".tar.gz"))
6213 (sha256
6214 (base32
6215 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6216 (build-system gnu-build-system)
6217 (arguments
6218 `(#:tests? #f ; no "check" target
6219 #:make-flags (list
6220 "CFLAGS=-O2" ; override "-m64" flag
6221 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6222 (string-append "MANDIR=" (assoc-ref %outputs "out")
6223 "/share/man/man1"))))
6224 (native-inputs
6225 `(("pkg-config" ,pkg-config)))
6226 (inputs
6227 `(("perl" ,perl)
6228 ("zlib" ,zlib)))
6229 (home-page "https://vcftools.github.io/")
6230 (synopsis "Tools for working with VCF files")
6231 (description
6232 "VCFtools is a program package designed for working with VCF files, such
6233 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6234 provide easily accessible methods for working with complex genetic variation
6235 data in the form of VCF files.")
6236 ;; The license is declared as LGPLv3 in the README and
6237 ;; at https://vcftools.github.io/license.html
6238 (license license:lgpl3)))
6239
6240 (define-public infernal
6241 (package
6242 (name "infernal")
6243 (version "1.1.2")
6244 (source (origin
6245 (method url-fetch)
6246 (uri (string-append "http://eddylab.org/software/infernal/"
6247 "infernal-" version ".tar.gz"))
6248 (sha256
6249 (base32
6250 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6251 (build-system gnu-build-system)
6252 (native-inputs
6253 `(("perl" ,perl))) ; for tests
6254 (home-page "http://eddylab.org/infernal/")
6255 (synopsis "Inference of RNA alignments")
6256 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6257 searching DNA sequence databases for RNA structure and sequence similarities.
6258 It is an implementation of a special case of profile stochastic context-free
6259 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6260 profile, but it scores a combination of sequence consensus and RNA secondary
6261 structure consensus, so in many cases, it is more capable of identifying RNA
6262 homologs that conserve their secondary structure more than their primary
6263 sequence.")
6264 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6265 (supported-systems '("i686-linux" "x86_64-linux"))
6266 (license license:bsd-3)))
6267
6268 (define-public r-centipede
6269 (package
6270 (name "r-centipede")
6271 (version "1.2")
6272 (source (origin
6273 (method url-fetch)
6274 (uri (string-append "http://download.r-forge.r-project.org/"
6275 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6276 (sha256
6277 (base32
6278 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6279 (build-system r-build-system)
6280 (home-page "http://centipede.uchicago.edu/")
6281 (synopsis "Predict transcription factor binding sites")
6282 (description
6283 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6284 of the genome that are bound by particular transcription factors. It starts
6285 by identifying a set of candidate binding sites, and then aims to classify the
6286 sites according to whether each site is bound or not bound by a transcription
6287 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6288 between two different types of motif instances using as much relevant
6289 information as possible.")
6290 (license (list license:gpl2+ license:gpl3+))))
6291
6292 (define-public r-vegan
6293 (package
6294 (name "r-vegan")
6295 (version "2.5-3")
6296 (source
6297 (origin
6298 (method url-fetch)
6299 (uri (cran-uri "vegan" version))
6300 (sha256
6301 (base32
6302 "023xznh0iy0496icpchadmp7a3rk3nj9s48fvwlvp3dssw58yp3c"))))
6303 (build-system r-build-system)
6304 (native-inputs
6305 `(("gfortran" ,gfortran)))
6306 (propagated-inputs
6307 `(("r-cluster" ,r-cluster)
6308 ("r-knitr" ,r-knitr) ; needed for vignettes
6309 ("r-lattice" ,r-lattice)
6310 ("r-mass" ,r-mass)
6311 ("r-mgcv" ,r-mgcv)
6312 ("r-permute" ,r-permute)))
6313 (home-page "https://cran.r-project.org/web/packages/vegan")
6314 (synopsis "Functions for community ecology")
6315 (description
6316 "The vegan package provides tools for descriptive community ecology. It
6317 has most basic functions of diversity analysis, community ordination and
6318 dissimilarity analysis. Most of its multivariate tools can be used for other
6319 data types as well.")
6320 (license license:gpl2+)))
6321
6322 (define-public r-annotate
6323 (package
6324 (name "r-annotate")
6325 (version "1.60.0")
6326 (source
6327 (origin
6328 (method url-fetch)
6329 (uri (bioconductor-uri "annotate" version))
6330 (sha256
6331 (base32
6332 "0p6c96lay23a67dyirgnwzm2yw22m592z780vy6p4nqwla8ha18n"))))
6333 (build-system r-build-system)
6334 (propagated-inputs
6335 `(("r-annotationdbi" ,r-annotationdbi)
6336 ("r-biobase" ,r-biobase)
6337 ("r-biocgenerics" ,r-biocgenerics)
6338 ("r-dbi" ,r-dbi)
6339 ("r-rcurl" ,r-rcurl)
6340 ("r-xml" ,r-xml)
6341 ("r-xtable" ,r-xtable)))
6342 (home-page
6343 "https://bioconductor.org/packages/annotate")
6344 (synopsis "Annotation for microarrays")
6345 (description "This package provides R environments for the annotation of
6346 microarrays.")
6347 (license license:artistic2.0)))
6348
6349 (define-public r-copynumber
6350 (package
6351 (name "r-copynumber")
6352 (version "1.22.0")
6353 (source (origin
6354 (method url-fetch)
6355 (uri (bioconductor-uri "copynumber" version))
6356 (sha256
6357 (base32
6358 "0ipwj9i5p1bwhg5d80jdjagm02krpj2v0j47qdgw41h8wncdyal3"))))
6359 (build-system r-build-system)
6360 (propagated-inputs
6361 `(("r-s4vectors" ,r-s4vectors)
6362 ("r-iranges" ,r-iranges)
6363 ("r-genomicranges" ,r-genomicranges)
6364 ("r-biocgenerics" ,r-biocgenerics)))
6365 (home-page "https://bioconductor.org/packages/copynumber")
6366 (synopsis "Segmentation of single- and multi-track copy number data")
6367 (description
6368 "This package segments single- and multi-track copy number data by a
6369 penalized least squares regression method.")
6370 (license license:artistic2.0)))
6371
6372 (define-public r-geneplotter
6373 (package
6374 (name "r-geneplotter")
6375 (version "1.60.0")
6376 (source
6377 (origin
6378 (method url-fetch)
6379 (uri (bioconductor-uri "geneplotter" version))
6380 (sha256
6381 (base32
6382 "10khr0pznxf3m0f5gzck9ymljrwcv3vamfmpskd51yjh36lhllqz"))))
6383 (build-system r-build-system)
6384 (propagated-inputs
6385 `(("r-annotate" ,r-annotate)
6386 ("r-annotationdbi" ,r-annotationdbi)
6387 ("r-biobase" ,r-biobase)
6388 ("r-biocgenerics" ,r-biocgenerics)
6389 ("r-lattice" ,r-lattice)
6390 ("r-rcolorbrewer" ,r-rcolorbrewer)))
6391 (home-page "https://bioconductor.org/packages/geneplotter")
6392 (synopsis "Graphics functions for genomic data")
6393 (description
6394 "This package provides functions for plotting genomic data.")
6395 (license license:artistic2.0)))
6396
6397 (define-public r-genefilter
6398 (package
6399 (name "r-genefilter")
6400 (version "1.64.0")
6401 (source
6402 (origin
6403 (method url-fetch)
6404 (uri (bioconductor-uri "genefilter" version))
6405 (sha256
6406 (base32
6407 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6408 (build-system r-build-system)
6409 (native-inputs
6410 `(("gfortran" ,gfortran)))
6411 (propagated-inputs
6412 `(("r-annotate" ,r-annotate)
6413 ("r-annotationdbi" ,r-annotationdbi)
6414 ("r-biobase" ,r-biobase)
6415 ("r-s4vectors" ,r-s4vectors)
6416 ("r-survival" ,r-survival)))
6417 (home-page "https://bioconductor.org/packages/genefilter")
6418 (synopsis "Filter genes from high-throughput experiments")
6419 (description
6420 "This package provides basic functions for filtering genes from
6421 high-throughput sequencing experiments.")
6422 (license license:artistic2.0)))
6423
6424 (define-public r-deseq2
6425 (package
6426 (name "r-deseq2")
6427 (version "1.22.1")
6428 (source
6429 (origin
6430 (method url-fetch)
6431 (uri (bioconductor-uri "DESeq2" version))
6432 (sha256
6433 (base32
6434 "1b2bmvcsfzvks47d7w46zplcwz0kgcdhx5xmx3x9lp2gvx2p84r5"))))
6435 (properties `((upstream-name . "DESeq2")))
6436 (build-system r-build-system)
6437 (propagated-inputs
6438 `(("r-biobase" ,r-biobase)
6439 ("r-biocgenerics" ,r-biocgenerics)
6440 ("r-biocparallel" ,r-biocparallel)
6441 ("r-genefilter" ,r-genefilter)
6442 ("r-geneplotter" ,r-geneplotter)
6443 ("r-genomicranges" ,r-genomicranges)
6444 ("r-ggplot2" ,r-ggplot2)
6445 ("r-hmisc" ,r-hmisc)
6446 ("r-iranges" ,r-iranges)
6447 ("r-locfit" ,r-locfit)
6448 ("r-rcpp" ,r-rcpp)
6449 ("r-rcpparmadillo" ,r-rcpparmadillo)
6450 ("r-s4vectors" ,r-s4vectors)
6451 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6452 (home-page "https://bioconductor.org/packages/DESeq2")
6453 (synopsis "Differential gene expression analysis")
6454 (description
6455 "This package provides functions to estimate variance-mean dependence in
6456 count data from high-throughput nucleotide sequencing assays and test for
6457 differential expression based on a model using the negative binomial
6458 distribution.")
6459 (license license:lgpl3+)))
6460
6461 (define-public r-dexseq
6462 (package
6463 (name "r-dexseq")
6464 (version "1.28.0")
6465 (source
6466 (origin
6467 (method url-fetch)
6468 (uri (bioconductor-uri "DEXSeq" version))
6469 (sha256
6470 (base32
6471 "0jh1640cnzpk8x3155cqc8dvrs1rciw3d6nv2k70baw96bhrynp8"))))
6472 (properties `((upstream-name . "DEXSeq")))
6473 (build-system r-build-system)
6474 (propagated-inputs
6475 `(("r-annotationdbi" ,r-annotationdbi)
6476 ("r-biobase" ,r-biobase)
6477 ("r-biocgenerics" ,r-biocgenerics)
6478 ("r-biocparallel" ,r-biocparallel)
6479 ("r-biomart" ,r-biomart)
6480 ("r-deseq2" ,r-deseq2)
6481 ("r-genefilter" ,r-genefilter)
6482 ("r-geneplotter" ,r-geneplotter)
6483 ("r-genomicranges" ,r-genomicranges)
6484 ("r-hwriter" ,r-hwriter)
6485 ("r-iranges" ,r-iranges)
6486 ("r-rcolorbrewer" ,r-rcolorbrewer)
6487 ("r-rsamtools" ,r-rsamtools)
6488 ("r-s4vectors" ,r-s4vectors)
6489 ("r-statmod" ,r-statmod)
6490 ("r-stringr" ,r-stringr)
6491 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6492 (home-page "https://bioconductor.org/packages/DEXSeq")
6493 (synopsis "Inference of differential exon usage in RNA-Seq")
6494 (description
6495 "This package is focused on finding differential exon usage using RNA-seq
6496 exon counts between samples with different experimental designs. It provides
6497 functions that allows the user to make the necessary statistical tests based
6498 on a model that uses the negative binomial distribution to estimate the
6499 variance between biological replicates and generalized linear models for
6500 testing. The package also provides functions for the visualization and
6501 exploration of the results.")
6502 (license license:gpl3+)))
6503
6504 (define-public r-annotationforge
6505 (package
6506 (name "r-annotationforge")
6507 (version "1.24.0")
6508 (source
6509 (origin
6510 (method url-fetch)
6511 (uri (bioconductor-uri "AnnotationForge" version))
6512 (sha256
6513 (base32
6514 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6515 (properties
6516 `((upstream-name . "AnnotationForge")))
6517 (build-system r-build-system)
6518 (propagated-inputs
6519 `(("r-annotationdbi" ,r-annotationdbi)
6520 ("r-biobase" ,r-biobase)
6521 ("r-biocgenerics" ,r-biocgenerics)
6522 ("r-dbi" ,r-dbi)
6523 ("r-rcurl" ,r-rcurl)
6524 ("r-rsqlite" ,r-rsqlite)
6525 ("r-s4vectors" ,r-s4vectors)
6526 ("r-xml" ,r-xml)))
6527 (home-page "https://bioconductor.org/packages/AnnotationForge")
6528 (synopsis "Code for building annotation database packages")
6529 (description
6530 "This package provides code for generating Annotation packages and their
6531 databases. Packages produced are intended to be used with AnnotationDbi.")
6532 (license license:artistic2.0)))
6533
6534 (define-public r-rbgl
6535 (package
6536 (name "r-rbgl")
6537 (version "1.58.0")
6538 (source
6539 (origin
6540 (method url-fetch)
6541 (uri (bioconductor-uri "RBGL" version))
6542 (sha256
6543 (base32
6544 "0jy95m38c4qp0a12097hhm2gg63k96k6ydhb11dy379h3ziapcar"))))
6545 (properties `((upstream-name . "RBGL")))
6546 (build-system r-build-system)
6547 (propagated-inputs `(("r-graph" ,r-graph)))
6548 (home-page "https://www.bioconductor.org/packages/RBGL")
6549 (synopsis "Interface to the Boost graph library")
6550 (description
6551 "This package provides a fairly extensive and comprehensive interface to
6552 the graph algorithms contained in the Boost library.")
6553 (license license:artistic2.0)))
6554
6555 (define-public r-gseabase
6556 (package
6557 (name "r-gseabase")
6558 (version "1.44.0")
6559 (source
6560 (origin
6561 (method url-fetch)
6562 (uri (bioconductor-uri "GSEABase" version))
6563 (sha256
6564 (base32
6565 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6566 (properties `((upstream-name . "GSEABase")))
6567 (build-system r-build-system)
6568 (propagated-inputs
6569 `(("r-annotate" ,r-annotate)
6570 ("r-annotationdbi" ,r-annotationdbi)
6571 ("r-biobase" ,r-biobase)
6572 ("r-biocgenerics" ,r-biocgenerics)
6573 ("r-graph" ,r-graph)
6574 ("r-xml" ,r-xml)))
6575 (home-page "https://bioconductor.org/packages/GSEABase")
6576 (synopsis "Gene set enrichment data structures and methods")
6577 (description
6578 "This package provides classes and methods to support @dfn{Gene Set
6579 Enrichment Analysis} (GSEA).")
6580 (license license:artistic2.0)))
6581
6582 (define-public r-category
6583 (package
6584 (name "r-category")
6585 (version "2.48.0")
6586 (source
6587 (origin
6588 (method url-fetch)
6589 (uri (bioconductor-uri "Category" version))
6590 (sha256
6591 (base32
6592 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6593 (properties `((upstream-name . "Category")))
6594 (build-system r-build-system)
6595 (propagated-inputs
6596 `(("r-annotate" ,r-annotate)
6597 ("r-annotationdbi" ,r-annotationdbi)
6598 ("r-biobase" ,r-biobase)
6599 ("r-biocgenerics" ,r-biocgenerics)
6600 ("r-genefilter" ,r-genefilter)
6601 ("r-graph" ,r-graph)
6602 ("r-gseabase" ,r-gseabase)
6603 ("r-matrix" ,r-matrix)
6604 ("r-rbgl" ,r-rbgl)
6605 ("r-dbi" ,r-dbi)))
6606 (home-page "https://bioconductor.org/packages/Category")
6607 (synopsis "Category analysis")
6608 (description
6609 "This package provides a collection of tools for performing category
6610 analysis.")
6611 (license license:artistic2.0)))
6612
6613 (define-public r-gostats
6614 (package
6615 (name "r-gostats")
6616 (version "2.48.0")
6617 (source
6618 (origin
6619 (method url-fetch)
6620 (uri (bioconductor-uri "GOstats" version))
6621 (sha256
6622 (base32
6623 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6624 (properties `((upstream-name . "GOstats")))
6625 (build-system r-build-system)
6626 (propagated-inputs
6627 `(("r-annotate" ,r-annotate)
6628 ("r-annotationdbi" ,r-annotationdbi)
6629 ("r-annotationforge" ,r-annotationforge)
6630 ("r-biobase" ,r-biobase)
6631 ("r-category" ,r-category)
6632 ("r-go-db" ,r-go-db)
6633 ("r-graph" ,r-graph)
6634 ("r-rgraphviz" ,r-rgraphviz)
6635 ("r-rbgl" ,r-rbgl)))
6636 (home-page "https://bioconductor.org/packages/GOstats")
6637 (synopsis "Tools for manipulating GO and microarrays")
6638 (description
6639 "This package provides a set of tools for interacting with GO and
6640 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6641 testing and other simple calculations.")
6642 (license license:artistic2.0)))
6643
6644 (define-public r-shortread
6645 (package
6646 (name "r-shortread")
6647 (version "1.40.0")
6648 (source
6649 (origin
6650 (method url-fetch)
6651 (uri (bioconductor-uri "ShortRead" version))
6652 (sha256
6653 (base32
6654 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6655 (properties `((upstream-name . "ShortRead")))
6656 (build-system r-build-system)
6657 (inputs
6658 `(("zlib" ,zlib)))
6659 (propagated-inputs
6660 `(("r-biobase" ,r-biobase)
6661 ("r-biocgenerics" ,r-biocgenerics)
6662 ("r-biocparallel" ,r-biocparallel)
6663 ("r-biostrings" ,r-biostrings)
6664 ("r-genomeinfodb" ,r-genomeinfodb)
6665 ("r-genomicalignments" ,r-genomicalignments)
6666 ("r-genomicranges" ,r-genomicranges)
6667 ("r-hwriter" ,r-hwriter)
6668 ("r-iranges" ,r-iranges)
6669 ("r-lattice" ,r-lattice)
6670 ("r-latticeextra" ,r-latticeextra)
6671 ("r-rsamtools" ,r-rsamtools)
6672 ("r-s4vectors" ,r-s4vectors)
6673 ("r-xvector" ,r-xvector)
6674 ("r-zlibbioc" ,r-zlibbioc)))
6675 (home-page "https://bioconductor.org/packages/ShortRead")
6676 (synopsis "FASTQ input and manipulation tools")
6677 (description
6678 "This package implements sampling, iteration, and input of FASTQ files.
6679 It includes functions for filtering and trimming reads, and for generating a
6680 quality assessment report. Data are represented as
6681 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6682 purposes. The package also contains legacy support for early single-end,
6683 ungapped alignment formats.")
6684 (license license:artistic2.0)))
6685
6686 (define-public r-systempiper
6687 (package
6688 (name "r-systempiper")
6689 (version "1.16.0")
6690 (source
6691 (origin
6692 (method url-fetch)
6693 (uri (bioconductor-uri "systemPipeR" version))
6694 (sha256
6695 (base32
6696 "0l26q8zjdmzg84g7f25gv9z60sykybahlpg5bg9bmpbg5lzcsx04"))))
6697 (properties `((upstream-name . "systemPipeR")))
6698 (build-system r-build-system)
6699 (propagated-inputs
6700 `(("r-annotate" ,r-annotate)
6701 ("r-batchjobs" ,r-batchjobs)
6702 ("r-biocgenerics" ,r-biocgenerics)
6703 ("r-biostrings" ,r-biostrings)
6704 ("r-deseq2" ,r-deseq2)
6705 ("r-edger" ,r-edger)
6706 ("r-genomicfeatures" ,r-genomicfeatures)
6707 ("r-genomicranges" ,r-genomicranges)
6708 ("r-ggplot2" ,r-ggplot2)
6709 ("r-go-db" ,r-go-db)
6710 ("r-gostats" ,r-gostats)
6711 ("r-limma" ,r-limma)
6712 ("r-pheatmap" ,r-pheatmap)
6713 ("r-rjson" ,r-rjson)
6714 ("r-rsamtools" ,r-rsamtools)
6715 ("r-shortread" ,r-shortread)
6716 ("r-summarizedexperiment" ,r-summarizedexperiment)
6717 ("r-variantannotation" ,r-variantannotation)))
6718 (home-page "https://github.com/tgirke/systemPipeR")
6719 (synopsis "Next generation sequencing workflow and reporting environment")
6720 (description
6721 "This R package provides tools for building and running automated
6722 end-to-end analysis workflows for a wide range of @dfn{next generation
6723 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6724 Important features include a uniform workflow interface across different NGS
6725 applications, automated report generation, and support for running both R and
6726 command-line software, such as NGS aligners or peak/variant callers, on local
6727 computers or compute clusters. Efficient handling of complex sample sets and
6728 experimental designs is facilitated by a consistently implemented sample
6729 annotation infrastructure.")
6730 (license license:artistic2.0)))
6731
6732 (define-public r-grohmm
6733 (package
6734 (name "r-grohmm")
6735 (version "1.16.0")
6736 (source
6737 (origin
6738 (method url-fetch)
6739 (uri (bioconductor-uri "groHMM" version))
6740 (sha256
6741 (base32
6742 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6743 (properties `((upstream-name . "groHMM")))
6744 (build-system r-build-system)
6745 (propagated-inputs
6746 `(("r-genomeinfodb" ,r-genomeinfodb)
6747 ("r-genomicalignments" ,r-genomicalignments)
6748 ("r-genomicranges" ,r-genomicranges)
6749 ("r-iranges" ,r-iranges)
6750 ("r-mass" ,r-mass)
6751 ("r-rtracklayer" ,r-rtracklayer)
6752 ("r-s4vectors" ,r-s4vectors)))
6753 (home-page "https://github.com/Kraus-Lab/groHMM")
6754 (synopsis "GRO-seq analysis pipeline")
6755 (description
6756 "This package provides a pipeline for the analysis of GRO-seq data.")
6757 (license license:gpl3+)))
6758
6759 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6760 (package
6761 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6762 (version "3.2.2")
6763 (source (origin
6764 (method url-fetch)
6765 ;; We cannot use bioconductor-uri here because this tarball is
6766 ;; located under "data/annotation/" instead of "bioc/".
6767 (uri (string-append "https://bioconductor.org/packages/"
6768 "release/data/annotation/src/contrib"
6769 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6770 version ".tar.gz"))
6771 (sha256
6772 (base32
6773 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6774 (properties
6775 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6776 (build-system r-build-system)
6777 ;; As this package provides little more than a very large data file it
6778 ;; doesn't make sense to build substitutes.
6779 (arguments `(#:substitutable? #f))
6780 (propagated-inputs
6781 `(("r-genomicfeatures" ,r-genomicfeatures)))
6782 (home-page
6783 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6784 (synopsis "Annotation package for human genome in TxDb format")
6785 (description
6786 "This package provides an annotation database of Homo sapiens genome
6787 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6788 track. The database is exposed as a @code{TxDb} object.")
6789 (license license:artistic2.0)))
6790
6791 (define-public r-sparql
6792 (package
6793 (name "r-sparql")
6794 (version "1.16")
6795 (source (origin
6796 (method url-fetch)
6797 (uri (cran-uri "SPARQL" version))
6798 (sha256
6799 (base32
6800 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6801 (properties `((upstream-name . "SPARQL")))
6802 (build-system r-build-system)
6803 (propagated-inputs
6804 `(("r-rcurl" ,r-rcurl)
6805 ("r-xml" ,r-xml)))
6806 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6807 (synopsis "SPARQL client for R")
6808 (description "This package provides an interface to use SPARQL to pose
6809 SELECT or UPDATE queries to an end-point.")
6810 ;; The only license indication is found in the DESCRIPTION file,
6811 ;; which states GPL-3. So we cannot assume GPLv3+.
6812 (license license:gpl3)))
6813
6814 (define-public vsearch
6815 (package
6816 (name "vsearch")
6817 (version "2.8.0")
6818 (source
6819 (origin
6820 (method url-fetch)
6821 (uri (string-append
6822 "https://github.com/torognes/vsearch/archive/v"
6823 version ".tar.gz"))
6824 (file-name (string-append name "-" version ".tar.gz"))
6825 (sha256
6826 (base32
6827 "15pbirgzhvflj4pi5n82vybbzjy9mlb0lv5l3qhrmdkfzpbyahw3"))
6828 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6829 (snippet
6830 '(begin
6831 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6832 ;; for this in the patch.
6833 (delete-file "src/city.h")
6834 (delete-file "src/citycrc.h")
6835 (delete-file "src/city.cc")
6836 #t))))
6837 (build-system gnu-build-system)
6838 (arguments
6839 `(#:phases
6840 (modify-phases %standard-phases
6841 (add-after 'unpack 'autogen
6842 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6843 (inputs
6844 `(("zlib" ,zlib)
6845 ("bzip2" ,bzip2)
6846 ("cityhash" ,cityhash)))
6847 (native-inputs
6848 `(("autoconf" ,autoconf)
6849 ("automake" ,automake)))
6850 (synopsis "Sequence search tools for metagenomics")
6851 (description
6852 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6853 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6854 masking. The tool takes advantage of parallelism in the form of SIMD
6855 vectorization as well as multiple threads to perform accurate alignments at
6856 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6857 Needleman-Wunsch).")
6858 (home-page "https://github.com/torognes/vsearch")
6859 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6860 ;; platforms.
6861 (supported-systems '("x86_64-linux"))
6862 ;; Dual licensed; also includes public domain source.
6863 (license (list license:gpl3 license:bsd-2))))
6864
6865 (define-public pardre
6866 (package
6867 (name "pardre")
6868 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6869 (version "1.1.5-1")
6870 (source
6871 (origin
6872 (method url-fetch)
6873 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6874 "1.1.5" ".tar.gz"))
6875 (sha256
6876 (base32
6877 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6878 (build-system gnu-build-system)
6879 (arguments
6880 `(#:tests? #f ; no tests included
6881 #:phases
6882 (modify-phases %standard-phases
6883 (delete 'configure)
6884 (replace 'install
6885 (lambda* (#:key outputs #:allow-other-keys)
6886 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6887 (install-file "ParDRe" bin)
6888 #t))))))
6889 (inputs
6890 `(("openmpi" ,openmpi)
6891 ("zlib" ,zlib)))
6892 (synopsis "Parallel tool to remove duplicate DNA reads")
6893 (description
6894 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6895 Duplicate reads can be seen as identical or nearly identical sequences with
6896 some mismatches. This tool lets users avoid the analysis of unnecessary
6897 reads, reducing the time of subsequent procedures with the
6898 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6899 in order to exploit the parallel capabilities of multicore clusters. It is
6900 faster than multithreaded counterparts (end of 2015) for the same number of
6901 cores and, thanks to the message-passing technology, it can be executed on
6902 clusters.")
6903 (home-page "https://sourceforge.net/projects/pardre/")
6904 (license license:gpl3+)))
6905
6906 (define-public ruby-bio-kseq
6907 (package
6908 (name "ruby-bio-kseq")
6909 (version "0.0.2")
6910 (source
6911 (origin
6912 (method url-fetch)
6913 (uri (rubygems-uri "bio-kseq" version))
6914 (sha256
6915 (base32
6916 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6917 (build-system ruby-build-system)
6918 (arguments
6919 `(#:test-target "spec"))
6920 (native-inputs
6921 `(("bundler" ,bundler)
6922 ("ruby-rspec" ,ruby-rspec)
6923 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6924 (inputs
6925 `(("zlib" ,zlib)))
6926 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6927 (description
6928 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6929 FASTQ parsing code. It provides a fast iterator over sequences and their
6930 quality scores.")
6931 (home-page "https://github.com/gusevfe/bio-kseq")
6932 (license license:expat)))
6933
6934 (define-public bio-locus
6935 (package
6936 (name "bio-locus")
6937 (version "0.0.7")
6938 (source
6939 (origin
6940 (method url-fetch)
6941 (uri (rubygems-uri "bio-locus" version))
6942 (sha256
6943 (base32
6944 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6945 (build-system ruby-build-system)
6946 (native-inputs
6947 `(("ruby-rspec" ,ruby-rspec)))
6948 (synopsis "Tool for fast querying of genome locations")
6949 (description
6950 "Bio-locus is a tabix-like tool for fast querying of genome
6951 locations. Many file formats in bioinformatics contain records that
6952 start with a chromosome name and a position for a SNP, or a start-end
6953 position for indels. Bio-locus allows users to store this chr+pos or
6954 chr+pos+alt information in a database.")
6955 (home-page "https://github.com/pjotrp/bio-locus")
6956 (license license:expat)))
6957
6958 (define-public bio-blastxmlparser
6959 (package
6960 (name "bio-blastxmlparser")
6961 (version "2.0.4")
6962 (source (origin
6963 (method url-fetch)
6964 (uri (rubygems-uri "bio-blastxmlparser" version))
6965 (sha256
6966 (base32
6967 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6968 (build-system ruby-build-system)
6969 (propagated-inputs
6970 `(("ruby-bio-logger" ,ruby-bio-logger)
6971 ("ruby-nokogiri" ,ruby-nokogiri)))
6972 (inputs
6973 `(("ruby-rspec" ,ruby-rspec)))
6974 (synopsis "Fast big data BLAST XML parser and library")
6975 (description
6976 "Very fast parallel big-data BLAST XML file parser which can be used as
6977 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6978 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6979 (home-page "https://github.com/pjotrp/blastxmlparser")
6980 (license license:expat)))
6981
6982 (define-public bioruby
6983 (package
6984 (name "bioruby")
6985 (version "1.5.2")
6986 (source
6987 (origin
6988 (method url-fetch)
6989 (uri (rubygems-uri "bio" version))
6990 (sha256
6991 (base32
6992 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
6993 (build-system ruby-build-system)
6994 (propagated-inputs
6995 `(("ruby-libxml" ,ruby-libxml)))
6996 (native-inputs
6997 `(("which" ,which))) ; required for test phase
6998 (arguments
6999 `(#:phases
7000 (modify-phases %standard-phases
7001 (add-before 'build 'patch-test-command
7002 (lambda _
7003 (substitute* '("test/functional/bio/test_command.rb")
7004 (("/bin/sh") (which "sh")))
7005 (substitute* '("test/functional/bio/test_command.rb")
7006 (("/bin/ls") (which "ls")))
7007 (substitute* '("test/functional/bio/test_command.rb")
7008 (("which") (which "which")))
7009 (substitute* '("test/functional/bio/test_command.rb",
7010 "test/data/command/echoarg2.sh")
7011 (("/bin/echo") (which "echo")))
7012 #t)))))
7013 (synopsis "Ruby library, shell and utilities for bioinformatics")
7014 (description "BioRuby comes with a comprehensive set of Ruby development
7015 tools and libraries for bioinformatics and molecular biology. BioRuby has
7016 components for sequence analysis, pathway analysis, protein modelling and
7017 phylogenetic analysis; it supports many widely used data formats and provides
7018 easy access to databases, external programs and public web services, including
7019 BLAST, KEGG, GenBank, MEDLINE and GO.")
7020 (home-page "http://bioruby.org/")
7021 ;; Code is released under Ruby license, except for setup
7022 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7023 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7024
7025 (define-public r-acsnminer
7026 (package
7027 (name "r-acsnminer")
7028 (version "0.16.8.25")
7029 (source (origin
7030 (method url-fetch)
7031 (uri (cran-uri "ACSNMineR" version))
7032 (sha256
7033 (base32
7034 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
7035 (properties `((upstream-name . "ACSNMineR")))
7036 (build-system r-build-system)
7037 (propagated-inputs
7038 `(("r-ggplot2" ,r-ggplot2)
7039 ("r-gridextra" ,r-gridextra)))
7040 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
7041 (synopsis "Gene enrichment analysis")
7042 (description
7043 "This package provides tools to compute and represent gene set enrichment
7044 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
7045 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
7046 enrichment can be run with hypergeometric test or Fisher exact test, and can
7047 use multiple corrections. Visualization of data can be done either by
7048 barplots or heatmaps.")
7049 (license license:gpl2+)))
7050
7051 (define-public r-biocgenerics
7052 (package
7053 (name "r-biocgenerics")
7054 (version "0.28.0")
7055 (source (origin
7056 (method url-fetch)
7057 (uri (bioconductor-uri "BiocGenerics" version))
7058 (sha256
7059 (base32
7060 "0cvpsrhg7sn7lpqgxvqrsagv6j7xj5rafq5xdjfd8zc4gxrs5rb8"))))
7061 (properties
7062 `((upstream-name . "BiocGenerics")))
7063 (build-system r-build-system)
7064 (home-page "https://bioconductor.org/packages/BiocGenerics")
7065 (synopsis "S4 generic functions for Bioconductor")
7066 (description
7067 "This package provides S4 generic functions needed by many Bioconductor
7068 packages.")
7069 (license license:artistic2.0)))
7070
7071 (define-public r-biocinstaller
7072 (package
7073 (name "r-biocinstaller")
7074 (version "1.32.1")
7075 (source (origin
7076 (method url-fetch)
7077 (uri (bioconductor-uri "BiocInstaller" version))
7078 (sha256
7079 (base32
7080 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7081 (properties
7082 `((upstream-name . "BiocInstaller")))
7083 (build-system r-build-system)
7084 (home-page "https://bioconductor.org/packages/BiocInstaller")
7085 (synopsis "Install Bioconductor packages")
7086 (description "This package is used to install and update R packages from
7087 Bioconductor, CRAN, and Github.")
7088 (license license:artistic2.0)))
7089
7090 (define-public r-biocviews
7091 (package
7092 (name "r-biocviews")
7093 (version "1.50.1")
7094 (source (origin
7095 (method url-fetch)
7096 (uri (bioconductor-uri "biocViews" version))
7097 (sha256
7098 (base32
7099 "0hjm3r58i0r9qhyar9pk250cx7sfijg0lnvi12a9s6brmmbip1a3"))))
7100 (properties
7101 `((upstream-name . "biocViews")))
7102 (build-system r-build-system)
7103 (propagated-inputs
7104 `(("r-biobase" ,r-biobase)
7105 ("r-graph" ,r-graph)
7106 ("r-rbgl" ,r-rbgl)
7107 ("r-rcurl" ,r-rcurl)
7108 ("r-xml" ,r-xml)
7109 ("r-runit" ,r-runit)))
7110 (home-page "https://bioconductor.org/packages/biocViews")
7111 (synopsis "Bioconductor package categorization helper")
7112 (description "The purpose of biocViews is to create HTML pages that
7113 categorize packages in a Bioconductor package repository according to keywords,
7114 also known as views, in a controlled vocabulary.")
7115 (license license:artistic2.0)))
7116
7117 (define-public r-bookdown
7118 (package
7119 (name "r-bookdown")
7120 (version "0.7")
7121 (source (origin
7122 (method url-fetch)
7123 (uri (cran-uri "bookdown" version))
7124 (sha256
7125 (base32
7126 "1b3fw1f41zph5yw3kynb47aijq53vhaa6mnnvxly72zamyzdf95q"))))
7127 (build-system r-build-system)
7128 (propagated-inputs
7129 `(("r-htmltools" ,r-htmltools)
7130 ("r-knitr" ,r-knitr)
7131 ("r-rmarkdown" ,r-rmarkdown)
7132 ("r-tinytex" ,r-tinytex)
7133 ("r-yaml" ,r-yaml)
7134 ("r-xfun" ,r-xfun)))
7135 (home-page "https://github.com/rstudio/bookdown")
7136 (synopsis "Authoring books and technical documents with R markdown")
7137 (description "This package provides output formats and utilities for
7138 authoring books and technical documents with R Markdown.")
7139 (license license:gpl3)))
7140
7141 (define-public r-biocstyle
7142 (package
7143 (name "r-biocstyle")
7144 (version "2.10.0")
7145 (source (origin
7146 (method url-fetch)
7147 (uri (bioconductor-uri "BiocStyle" version))
7148 (sha256
7149 (base32
7150 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7151 (properties
7152 `((upstream-name . "BiocStyle")))
7153 (build-system r-build-system)
7154 (propagated-inputs
7155 `(("r-biocmanager" ,r-biocmanager)
7156 ("r-bookdown" ,r-bookdown)
7157 ("r-knitr" ,r-knitr)
7158 ("r-rmarkdown" ,r-rmarkdown)
7159 ("r-yaml" ,r-yaml)))
7160 (home-page "https://bioconductor.org/packages/BiocStyle")
7161 (synopsis "Bioconductor formatting styles")
7162 (description "This package provides standard formatting styles for
7163 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7164 functionality.")
7165 (license license:artistic2.0)))
7166
7167 (define-public r-bioccheck
7168 (package
7169 (name "r-bioccheck")
7170 (version "1.18.0")
7171 (source (origin
7172 (method url-fetch)
7173 (uri (bioconductor-uri "BiocCheck" version))
7174 (sha256
7175 (base32
7176 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7177 (properties
7178 `((upstream-name . "BiocCheck")))
7179 (build-system r-build-system)
7180 (arguments
7181 '(#:phases
7182 (modify-phases %standard-phases
7183 ;; This package can be used by calling BiocCheck(<package>) from
7184 ;; within R, or by running R CMD BiocCheck <package>. This phase
7185 ;; makes sure the latter works. For this to work, the BiocCheck
7186 ;; script must be somewhere on the PATH (not the R bin directory).
7187 (add-after 'install 'install-bioccheck-subcommand
7188 (lambda* (#:key outputs #:allow-other-keys)
7189 (let* ((out (assoc-ref outputs "out"))
7190 (dest-dir (string-append out "/bin"))
7191 (script-dir
7192 (string-append out "/site-library/BiocCheck/script/")))
7193 (mkdir-p dest-dir)
7194 (symlink (string-append script-dir "/checkBadDeps.R")
7195 (string-append dest-dir "/checkBadDeps.R"))
7196 (symlink (string-append script-dir "/BiocCheck")
7197 (string-append dest-dir "/BiocCheck")))
7198 #t)))))
7199 (propagated-inputs
7200 `(("r-codetools" ,r-codetools)
7201 ("r-graph" ,r-graph)
7202 ("r-httr" ,r-httr)
7203 ("r-knitr" ,r-knitr)
7204 ("r-optparse" ,r-optparse)
7205 ("r-biocmanager" ,r-biocmanager)
7206 ("r-biocviews" ,r-biocviews)
7207 ("r-stringdist" ,r-stringdist)))
7208 (home-page "https://bioconductor.org/packages/BiocCheck")
7209 (synopsis "Executes Bioconductor-specific package checks")
7210 (description "This package contains tools to perform additional quality
7211 checks on R packages that are to be submitted to the Bioconductor repository.")
7212 (license license:artistic2.0)))
7213
7214 (define-public r-optparse
7215 (package
7216 (name "r-optparse")
7217 (version "1.6.0")
7218 (source
7219 (origin
7220 (method url-fetch)
7221 (uri (cran-uri "optparse" version))
7222 (sha256
7223 (base32
7224 "1d7v5gl45x4amsfmzn5zyyffyqlc7a82h01szlnda22viyxids0h"))))
7225 (build-system r-build-system)
7226 (propagated-inputs
7227 `(("r-getopt" ,r-getopt)))
7228 (home-page
7229 "https://github.com/trevorld/optparse")
7230 (synopsis "Command line option parser")
7231 (description
7232 "This package provides a command line parser inspired by Python's
7233 @code{optparse} library to be used with Rscript to write shebang scripts
7234 that accept short and long options.")
7235 (license license:gpl2+)))
7236
7237 (define-public r-dnacopy
7238 (package
7239 (name "r-dnacopy")
7240 (version "1.56.0")
7241 (source (origin
7242 (method url-fetch)
7243 (uri (bioconductor-uri "DNAcopy" version))
7244 (sha256
7245 (base32
7246 "04cqdqxhva66xwh1s2vffi56b9fcrqd4slcrvqasj5lp2rkjli82"))))
7247 (properties
7248 `((upstream-name . "DNAcopy")))
7249 (build-system r-build-system)
7250 (inputs
7251 `(("gfortran" ,gfortran)))
7252 (home-page "https://bioconductor.org/packages/DNAcopy")
7253 (synopsis "Implementation of a circular binary segmentation algorithm")
7254 (description "This package implements the circular binary segmentation (CBS)
7255 algorithm to segment DNA copy number data and identify genomic regions with
7256 abnormal copy number.")
7257 (license license:gpl2+)))
7258
7259 (define-public r-s4vectors
7260 (package
7261 (name "r-s4vectors")
7262 (version "0.20.0")
7263 (source (origin
7264 (method url-fetch)
7265 (uri (bioconductor-uri "S4Vectors" version))
7266 (sha256
7267 (base32
7268 "0qgiykjhnsvvpcp3zwmrnpx3bv3msvj0szchyvb1yb0fxw716xc5"))))
7269 (properties
7270 `((upstream-name . "S4Vectors")))
7271 (build-system r-build-system)
7272 (propagated-inputs
7273 `(("r-biocgenerics" ,r-biocgenerics)))
7274 (home-page "https://bioconductor.org/packages/S4Vectors")
7275 (synopsis "S4 implementation of vectors and lists")
7276 (description
7277 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7278 classes and a set of generic functions that extend the semantic of ordinary
7279 vectors and lists in R. Package developers can easily implement vector-like
7280 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7281 In addition, a few low-level concrete subclasses of general interest (e.g.
7282 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7283 S4Vectors package itself.")
7284 (license license:artistic2.0)))
7285
7286 (define-public r-seqinr
7287 (package
7288 (name "r-seqinr")
7289 (version "3.4-5")
7290 (source
7291 (origin
7292 (method url-fetch)
7293 (uri (cran-uri "seqinr" version))
7294 (sha256
7295 (base32
7296 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7297 (build-system r-build-system)
7298 (propagated-inputs
7299 `(("r-ade4" ,r-ade4)
7300 ("r-segmented" ,r-segmented)))
7301 (inputs
7302 `(("zlib" ,zlib)))
7303 (home-page "http://seqinr.r-forge.r-project.org/")
7304 (synopsis "Biological sequences retrieval and analysis")
7305 (description
7306 "This package provides tools for exploratory data analysis and data
7307 visualization of biological sequence (DNA and protein) data. It also includes
7308 utilities for sequence data management under the ACNUC system.")
7309 (license license:gpl2+)))
7310
7311 (define-public r-iranges
7312 (package
7313 (name "r-iranges")
7314 (version "2.16.0")
7315 (source (origin
7316 (method url-fetch)
7317 (uri (bioconductor-uri "IRanges" version))
7318 (sha256
7319 (base32
7320 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7321 (properties
7322 `((upstream-name . "IRanges")))
7323 (build-system r-build-system)
7324 (propagated-inputs
7325 `(("r-biocgenerics" ,r-biocgenerics)
7326 ("r-s4vectors" ,r-s4vectors)))
7327 (home-page "https://bioconductor.org/packages/IRanges")
7328 (synopsis "Infrastructure for manipulating intervals on sequences")
7329 (description
7330 "This package provides efficient low-level and highly reusable S4 classes
7331 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7332 generally, data that can be organized sequentially (formally defined as
7333 @code{Vector} objects), as well as views on these @code{Vector} objects.
7334 Efficient list-like classes are also provided for storing big collections of
7335 instances of the basic classes. All classes in the package use consistent
7336 naming and share the same rich and consistent \"Vector API\" as much as
7337 possible.")
7338 (license license:artistic2.0)))
7339
7340 (define-public r-genomeinfodbdata
7341 (package
7342 (name "r-genomeinfodbdata")
7343 (version "1.1.0")
7344 (source (origin
7345 (method url-fetch)
7346 ;; We cannot use bioconductor-uri here because this tarball is
7347 ;; located under "data/annotation/" instead of "bioc/".
7348 (uri (string-append "https://bioconductor.org/packages/release/"
7349 "data/annotation/src/contrib/GenomeInfoDbData_"
7350 version ".tar.gz"))
7351 (sha256
7352 (base32
7353 "0k1hsjx6n2i1sf14hyrgdhxqxm5mxk0bgnivhiax944whcicmzbf"))))
7354 (properties
7355 `((upstream-name . "GenomeInfoDbData")))
7356 (build-system r-build-system)
7357 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7358 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7359 (description "This package contains data for mapping between NCBI taxonomy
7360 ID and species. It is used by functions in the GenomeInfoDb package.")
7361 (license license:artistic2.0)))
7362
7363 (define-public r-genomeinfodb
7364 (package
7365 (name "r-genomeinfodb")
7366 (version "1.18.0")
7367 (source (origin
7368 (method url-fetch)
7369 (uri (bioconductor-uri "GenomeInfoDb" version))
7370 (sha256
7371 (base32
7372 "1xqpgngd8by0yn627v9kz26a03v5a1lhcfwlnx2i0ivplk9bd40s"))))
7373 (properties
7374 `((upstream-name . "GenomeInfoDb")))
7375 (build-system r-build-system)
7376 (propagated-inputs
7377 `(("r-biocgenerics" ,r-biocgenerics)
7378 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7379 ("r-iranges" ,r-iranges)
7380 ("r-rcurl" ,r-rcurl)
7381 ("r-s4vectors" ,r-s4vectors)))
7382 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7383 (synopsis "Utilities for manipulating chromosome identifiers")
7384 (description
7385 "This package contains data and functions that define and allow
7386 translation between different chromosome sequence naming conventions (e.g.,
7387 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7388 names in their natural, rather than lexicographic, order.")
7389 (license license:artistic2.0)))
7390
7391 (define-public r-edger
7392 (package
7393 (name "r-edger")
7394 (version "3.24.0")
7395 (source (origin
7396 (method url-fetch)
7397 (uri (bioconductor-uri "edgeR" version))
7398 (sha256
7399 (base32
7400 "0ihihgzrgb4q3xc8xkzp1v76ndgihrj4gas00fa25vggfs1v6hvg"))))
7401 (properties `((upstream-name . "edgeR")))
7402 (build-system r-build-system)
7403 (propagated-inputs
7404 `(("r-limma" ,r-limma)
7405 ("r-locfit" ,r-locfit)
7406 ("r-rcpp" ,r-rcpp)
7407 ("r-statmod" ,r-statmod))) ;for estimateDisp
7408 (home-page "http://bioinf.wehi.edu.au/edgeR")
7409 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7410 (description "This package can do differential expression analysis of
7411 RNA-seq expression profiles with biological replication. It implements a range
7412 of statistical methodology based on the negative binomial distributions,
7413 including empirical Bayes estimation, exact tests, generalized linear models
7414 and quasi-likelihood tests. It be applied to differential signal analysis of
7415 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7416 CAGE.")
7417 (license license:gpl2+)))
7418
7419 (define-public r-variantannotation
7420 (package
7421 (name "r-variantannotation")
7422 (version "1.28.1")
7423 (source (origin
7424 (method url-fetch)
7425 (uri (bioconductor-uri "VariantAnnotation" version))
7426 (sha256
7427 (base32
7428 "0gvah258mkaafhbna81zwknx8qr3lidbcx5qvwk39q3yswr9mi49"))))
7429 (properties
7430 `((upstream-name . "VariantAnnotation")))
7431 (inputs
7432 `(("zlib" ,zlib)))
7433 (propagated-inputs
7434 `(("r-annotationdbi" ,r-annotationdbi)
7435 ("r-biobase" ,r-biobase)
7436 ("r-biocgenerics" ,r-biocgenerics)
7437 ("r-biostrings" ,r-biostrings)
7438 ("r-bsgenome" ,r-bsgenome)
7439 ("r-dbi" ,r-dbi)
7440 ("r-genomeinfodb" ,r-genomeinfodb)
7441 ("r-genomicfeatures" ,r-genomicfeatures)
7442 ("r-genomicranges" ,r-genomicranges)
7443 ("r-iranges" ,r-iranges)
7444 ("r-summarizedexperiment" ,r-summarizedexperiment)
7445 ("r-rsamtools" ,r-rsamtools)
7446 ("r-rtracklayer" ,r-rtracklayer)
7447 ("r-s4vectors" ,r-s4vectors)
7448 ("r-xvector" ,r-xvector)
7449 ("r-zlibbioc" ,r-zlibbioc)))
7450 (build-system r-build-system)
7451 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7452 (synopsis "Package for annotation of genetic variants")
7453 (description "This R package can annotate variants, compute amino acid
7454 coding changes and predict coding outcomes.")
7455 (license license:artistic2.0)))
7456
7457 (define-public r-limma
7458 (package
7459 (name "r-limma")
7460 (version "3.38.2")
7461 (source (origin
7462 (method url-fetch)
7463 (uri (bioconductor-uri "limma" version))
7464 (sha256
7465 (base32
7466 "1wkh362rmn24q7bkinb6nx62a31wl3r3myg5l326gx65wpwdnx97"))))
7467 (build-system r-build-system)
7468 (home-page "http://bioinf.wehi.edu.au/limma")
7469 (synopsis "Package for linear models for microarray and RNA-seq data")
7470 (description "This package can be used for the analysis of gene expression
7471 studies, especially the use of linear models for analysing designed experiments
7472 and the assessment of differential expression. The analysis methods apply to
7473 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7474 (license license:gpl2+)))
7475
7476 (define-public r-xvector
7477 (package
7478 (name "r-xvector")
7479 (version "0.22.0")
7480 (source (origin
7481 (method url-fetch)
7482 (uri (bioconductor-uri "XVector" version))
7483 (sha256
7484 (base32
7485 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7486 (properties
7487 `((upstream-name . "XVector")))
7488 (build-system r-build-system)
7489 (arguments
7490 `(#:phases
7491 (modify-phases %standard-phases
7492 (add-after 'unpack 'use-system-zlib
7493 (lambda _
7494 (substitute* "DESCRIPTION"
7495 (("zlibbioc, ") ""))
7496 (substitute* "NAMESPACE"
7497 (("import\\(zlibbioc\\)") ""))
7498 #t)))))
7499 (inputs
7500 `(("zlib" ,zlib)))
7501 (propagated-inputs
7502 `(("r-biocgenerics" ,r-biocgenerics)
7503 ("r-iranges" ,r-iranges)
7504 ("r-s4vectors" ,r-s4vectors)))
7505 (home-page "https://bioconductor.org/packages/XVector")
7506 (synopsis "Representation and manpulation of external sequences")
7507 (description
7508 "This package provides memory efficient S4 classes for storing sequences
7509 \"externally\" (behind an R external pointer, or on disk).")
7510 (license license:artistic2.0)))
7511
7512 (define-public r-genomicranges
7513 (package
7514 (name "r-genomicranges")
7515 (version "1.34.0")
7516 (source (origin
7517 (method url-fetch)
7518 (uri (bioconductor-uri "GenomicRanges" version))
7519 (sha256
7520 (base32
7521 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7522 (properties
7523 `((upstream-name . "GenomicRanges")))
7524 (build-system r-build-system)
7525 (propagated-inputs
7526 `(("r-biocgenerics" ,r-biocgenerics)
7527 ("r-genomeinfodb" ,r-genomeinfodb)
7528 ("r-iranges" ,r-iranges)
7529 ("r-s4vectors" ,r-s4vectors)
7530 ("r-xvector" ,r-xvector)))
7531 (home-page "https://bioconductor.org/packages/GenomicRanges")
7532 (synopsis "Representation and manipulation of genomic intervals")
7533 (description
7534 "This package provides tools to efficiently represent and manipulate
7535 genomic annotations and alignments is playing a central role when it comes to
7536 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7537 GenomicRanges package defines general purpose containers for storing and
7538 manipulating genomic intervals and variables defined along a genome.")
7539 (license license:artistic2.0)))
7540
7541 (define-public r-biobase
7542 (package
7543 (name "r-biobase")
7544 (version "2.42.0")
7545 (source (origin
7546 (method url-fetch)
7547 (uri (bioconductor-uri "Biobase" version))
7548 (sha256
7549 (base32
7550 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7551 (properties
7552 `((upstream-name . "Biobase")))
7553 (build-system r-build-system)
7554 (propagated-inputs
7555 `(("r-biocgenerics" ,r-biocgenerics)))
7556 (home-page "https://bioconductor.org/packages/Biobase")
7557 (synopsis "Base functions for Bioconductor")
7558 (description
7559 "This package provides functions that are needed by many other packages
7560 on Bioconductor or which replace R functions.")
7561 (license license:artistic2.0)))
7562
7563 (define-public r-annotationdbi
7564 (package
7565 (name "r-annotationdbi")
7566 (version "1.44.0")
7567 (source (origin
7568 (method url-fetch)
7569 (uri (bioconductor-uri "AnnotationDbi" version))
7570 (sha256
7571 (base32
7572 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7573 (properties
7574 `((upstream-name . "AnnotationDbi")))
7575 (build-system r-build-system)
7576 (propagated-inputs
7577 `(("r-biobase" ,r-biobase)
7578 ("r-biocgenerics" ,r-biocgenerics)
7579 ("r-dbi" ,r-dbi)
7580 ("r-iranges" ,r-iranges)
7581 ("r-rsqlite" ,r-rsqlite)
7582 ("r-s4vectors" ,r-s4vectors)))
7583 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7584 (synopsis "Annotation database interface")
7585 (description
7586 "This package provides user interface and database connection code for
7587 annotation data packages using SQLite data storage.")
7588 (license license:artistic2.0)))
7589
7590 (define-public r-biomart
7591 (package
7592 (name "r-biomart")
7593 (version "2.38.0")
7594 (source (origin
7595 (method url-fetch)
7596 (uri (bioconductor-uri "biomaRt" version))
7597 (sha256
7598 (base32
7599 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7600 (properties
7601 `((upstream-name . "biomaRt")))
7602 (build-system r-build-system)
7603 (propagated-inputs
7604 `(("r-annotationdbi" ,r-annotationdbi)
7605 ("r-httr" ,r-httr)
7606 ("r-progress" ,r-progress)
7607 ("r-rcurl" ,r-rcurl)
7608 ("r-stringr" ,r-stringr)
7609 ("r-xml" ,r-xml)))
7610 (home-page "https://bioconductor.org/packages/biomaRt")
7611 (synopsis "Interface to BioMart databases")
7612 (description
7613 "biomaRt provides an interface to a growing collection of databases
7614 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7615 package enables retrieval of large amounts of data in a uniform way without
7616 the need to know the underlying database schemas or write complex SQL queries.
7617 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7618 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7619 users direct access to a diverse set of data and enable a wide range of
7620 powerful online queries from gene annotation to database mining.")
7621 (license license:artistic2.0)))
7622
7623 (define-public r-biocparallel
7624 (package
7625 (name "r-biocparallel")
7626 (version "1.16.0")
7627 (source (origin
7628 (method url-fetch)
7629 (uri (bioconductor-uri "BiocParallel" version))
7630 (sha256
7631 (base32
7632 "0g16cy0vjapqkb188z63r1b6y96m9g8vx0a3v2qavzxc177k0cja"))))
7633 (properties
7634 `((upstream-name . "BiocParallel")))
7635 (build-system r-build-system)
7636 (propagated-inputs
7637 `(("r-futile-logger" ,r-futile-logger)
7638 ("r-snow" ,r-snow)
7639 ("r-bh" ,r-bh)))
7640 (home-page "https://bioconductor.org/packages/BiocParallel")
7641 (synopsis "Bioconductor facilities for parallel evaluation")
7642 (description
7643 "This package provides modified versions and novel implementation of
7644 functions for parallel evaluation, tailored to use with Bioconductor
7645 objects.")
7646 (license (list license:gpl2+ license:gpl3+))))
7647
7648 (define-public r-biostrings
7649 (package
7650 (name "r-biostrings")
7651 (version "2.50.0")
7652 (source (origin
7653 (method url-fetch)
7654 (uri (bioconductor-uri "Biostrings" version))
7655 (sha256
7656 (base32
7657 "0zw0dj67fnpbz4iqnam5fxs92c1c8w8d7mzl0rkq4ksx0xl8vgg7"))))
7658 (properties
7659 `((upstream-name . "Biostrings")))
7660 (build-system r-build-system)
7661 (propagated-inputs
7662 `(("r-biocgenerics" ,r-biocgenerics)
7663 ("r-iranges" ,r-iranges)
7664 ("r-s4vectors" ,r-s4vectors)
7665 ("r-xvector" ,r-xvector)))
7666 (home-page "https://bioconductor.org/packages/Biostrings")
7667 (synopsis "String objects and algorithms for biological sequences")
7668 (description
7669 "This package provides memory efficient string containers, string
7670 matching algorithms, and other utilities, for fast manipulation of large
7671 biological sequences or sets of sequences.")
7672 (license license:artistic2.0)))
7673
7674 (define-public r-rsamtools
7675 (package
7676 (name "r-rsamtools")
7677 (version "1.34.0")
7678 (source (origin
7679 (method url-fetch)
7680 (uri (bioconductor-uri "Rsamtools" version))
7681 (sha256
7682 (base32
7683 "01v4bjhj2i126pwyk0v9lvmfp2ih495xsq903k3xa2z24bjxphbi"))))
7684 (properties
7685 `((upstream-name . "Rsamtools")))
7686 (build-system r-build-system)
7687 (arguments
7688 `(#:phases
7689 (modify-phases %standard-phases
7690 (add-after 'unpack 'use-system-zlib
7691 (lambda _
7692 (substitute* "DESCRIPTION"
7693 (("zlibbioc, ") ""))
7694 (substitute* "NAMESPACE"
7695 (("import\\(zlibbioc\\)") ""))
7696 #t)))))
7697 (inputs
7698 `(("zlib" ,zlib)))
7699 (propagated-inputs
7700 `(("r-biocgenerics" ,r-biocgenerics)
7701 ("r-biocparallel" ,r-biocparallel)
7702 ("r-biostrings" ,r-biostrings)
7703 ("r-bitops" ,r-bitops)
7704 ("r-genomeinfodb" ,r-genomeinfodb)
7705 ("r-genomicranges" ,r-genomicranges)
7706 ("r-iranges" ,r-iranges)
7707 ("r-s4vectors" ,r-s4vectors)
7708 ("r-xvector" ,r-xvector)))
7709 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7710 (synopsis "Interface to samtools, bcftools, and tabix")
7711 (description
7712 "This package provides an interface to the 'samtools', 'bcftools', and
7713 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7714 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7715 files.")
7716 (license license:expat)))
7717
7718 (define-public r-delayedarray
7719 (package
7720 (name "r-delayedarray")
7721 (version "0.8.0")
7722 (source (origin
7723 (method url-fetch)
7724 (uri (bioconductor-uri "DelayedArray" version))
7725 (sha256
7726 (base32
7727 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7728 (properties
7729 `((upstream-name . "DelayedArray")))
7730 (build-system r-build-system)
7731 (propagated-inputs
7732 `(("r-biocgenerics" ,r-biocgenerics)
7733 ("r-biocparallel" ,r-biocparallel)
7734 ("r-s4vectors" ,r-s4vectors)
7735 ("r-iranges" ,r-iranges)
7736 ("r-matrixstats" ,r-matrixstats)))
7737 (home-page "https://bioconductor.org/packages/DelayedArray")
7738 (synopsis "Delayed operations on array-like objects")
7739 (description
7740 "Wrapping an array-like object (typically an on-disk object) in a
7741 @code{DelayedArray} object allows one to perform common array operations on it
7742 without loading the object in memory. In order to reduce memory usage and
7743 optimize performance, operations on the object are either delayed or executed
7744 using a block processing mechanism. Note that this also works on in-memory
7745 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7746 @code{Matrix} objects, and ordinary arrays and data frames.")
7747 (license license:artistic2.0)))
7748
7749 (define-public r-summarizedexperiment
7750 (package
7751 (name "r-summarizedexperiment")
7752 (version "1.12.0")
7753 (source (origin
7754 (method url-fetch)
7755 (uri (bioconductor-uri "SummarizedExperiment" version))
7756 (sha256
7757 (base32
7758 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7759 (properties
7760 `((upstream-name . "SummarizedExperiment")))
7761 (build-system r-build-system)
7762 (propagated-inputs
7763 `(("r-biobase" ,r-biobase)
7764 ("r-biocgenerics" ,r-biocgenerics)
7765 ("r-delayedarray" ,r-delayedarray)
7766 ("r-genomeinfodb" ,r-genomeinfodb)
7767 ("r-genomicranges" ,r-genomicranges)
7768 ("r-iranges" ,r-iranges)
7769 ("r-matrix" ,r-matrix)
7770 ("r-s4vectors" ,r-s4vectors)))
7771 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7772 (synopsis "Container for representing genomic ranges by sample")
7773 (description
7774 "The SummarizedExperiment container contains one or more assays, each
7775 represented by a matrix-like object of numeric or other mode. The rows
7776 typically represent genomic ranges of interest and the columns represent
7777 samples.")
7778 (license license:artistic2.0)))
7779
7780 (define-public r-genomicalignments
7781 (package
7782 (name "r-genomicalignments")
7783 (version "1.18.0")
7784 (source (origin
7785 (method url-fetch)
7786 (uri (bioconductor-uri "GenomicAlignments" version))
7787 (sha256
7788 (base32
7789 "0a3zhwripfw2508fvgx3wzqa8nq8vnslg97a911znpwvxh53jl24"))))
7790 (properties
7791 `((upstream-name . "GenomicAlignments")))
7792 (build-system r-build-system)
7793 (propagated-inputs
7794 `(("r-biocgenerics" ,r-biocgenerics)
7795 ("r-biocparallel" ,r-biocparallel)
7796 ("r-biostrings" ,r-biostrings)
7797 ("r-genomeinfodb" ,r-genomeinfodb)
7798 ("r-genomicranges" ,r-genomicranges)
7799 ("r-iranges" ,r-iranges)
7800 ("r-rsamtools" ,r-rsamtools)
7801 ("r-s4vectors" ,r-s4vectors)
7802 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7803 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7804 (synopsis "Representation and manipulation of short genomic alignments")
7805 (description
7806 "This package provides efficient containers for storing and manipulating
7807 short genomic alignments (typically obtained by aligning short reads to a
7808 reference genome). This includes read counting, computing the coverage,
7809 junction detection, and working with the nucleotide content of the
7810 alignments.")
7811 (license license:artistic2.0)))
7812
7813 (define-public r-rtracklayer
7814 (package
7815 (name "r-rtracklayer")
7816 (version "1.42.0")
7817 (source (origin
7818 (method url-fetch)
7819 (uri (bioconductor-uri "rtracklayer" version))
7820 (sha256
7821 (base32
7822 "0a4mhd926w9slkfil5xgngjsfdj024a4w57w2bm3d4r0pj8y5da7"))))
7823 (build-system r-build-system)
7824 (arguments
7825 `(#:phases
7826 (modify-phases %standard-phases
7827 (add-after 'unpack 'use-system-zlib
7828 (lambda _
7829 (substitute* "DESCRIPTION"
7830 ((" zlibbioc,") ""))
7831 (substitute* "NAMESPACE"
7832 (("import\\(zlibbioc\\)") ""))
7833 #t)))))
7834 (native-inputs
7835 `(("pkg-config" ,pkg-config)))
7836 (inputs
7837 `(("zlib" ,zlib)))
7838 (propagated-inputs
7839 `(("r-biocgenerics" ,r-biocgenerics)
7840 ("r-biostrings" ,r-biostrings)
7841 ("r-genomeinfodb" ,r-genomeinfodb)
7842 ("r-genomicalignments" ,r-genomicalignments)
7843 ("r-genomicranges" ,r-genomicranges)
7844 ("r-iranges" ,r-iranges)
7845 ("r-rcurl" ,r-rcurl)
7846 ("r-rsamtools" ,r-rsamtools)
7847 ("r-s4vectors" ,r-s4vectors)
7848 ("r-xml" ,r-xml)
7849 ("r-xvector" ,r-xvector)))
7850 (home-page "https://bioconductor.org/packages/rtracklayer")
7851 (synopsis "R interface to genome browsers and their annotation tracks")
7852 (description
7853 "rtracklayer is an extensible framework for interacting with multiple
7854 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7855 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7856 built-in). The user may export/import tracks to/from the supported browsers,
7857 as well as query and modify the browser state, such as the current viewport.")
7858 (license license:artistic2.0)))
7859
7860 (define-public r-genomicfeatures
7861 (package
7862 (name "r-genomicfeatures")
7863 (version "1.34.1")
7864 (source (origin
7865 (method url-fetch)
7866 (uri (bioconductor-uri "GenomicFeatures" version))
7867 (sha256
7868 (base32
7869 "0slq6hv5bmc3bgrl824jzmr6db3fvaj6b7ihwmdn76pgqqbq2fq6"))))
7870 (properties
7871 `((upstream-name . "GenomicFeatures")))
7872 (build-system r-build-system)
7873 (propagated-inputs
7874 `(("r-annotationdbi" ,r-annotationdbi)
7875 ("r-biobase" ,r-biobase)
7876 ("r-biocgenerics" ,r-biocgenerics)
7877 ("r-biomart" ,r-biomart)
7878 ("r-biostrings" ,r-biostrings)
7879 ("r-dbi" ,r-dbi)
7880 ("r-genomeinfodb" ,r-genomeinfodb)
7881 ("r-genomicranges" ,r-genomicranges)
7882 ("r-iranges" ,r-iranges)
7883 ("r-rcurl" ,r-rcurl)
7884 ("r-rsqlite" ,r-rsqlite)
7885 ("r-rtracklayer" ,r-rtracklayer)
7886 ("r-s4vectors" ,r-s4vectors)
7887 ("r-xvector" ,r-xvector)))
7888 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7889 (synopsis "Tools for working with transcript centric annotations")
7890 (description
7891 "This package provides a set of tools and methods for making and
7892 manipulating transcript centric annotations. With these tools the user can
7893 easily download the genomic locations of the transcripts, exons and cds of a
7894 given organism, from either the UCSC Genome Browser or a BioMart
7895 database (more sources will be supported in the future). This information is
7896 then stored in a local database that keeps track of the relationship between
7897 transcripts, exons, cds and genes. Flexible methods are provided for
7898 extracting the desired features in a convenient format.")
7899 (license license:artistic2.0)))
7900
7901 (define-public r-go-db
7902 (package
7903 (name "r-go-db")
7904 (version "3.6.0")
7905 (source (origin
7906 (method url-fetch)
7907 (uri (string-append "https://www.bioconductor.org/packages/"
7908 "release/data/annotation/src/contrib/GO.db_"
7909 version ".tar.gz"))
7910 (sha256
7911 (base32
7912 "0fi2qywr9apg5lwfqfq9qq6bgrnv4rdhxx25656qn4bsy62i838j"))))
7913 (properties
7914 `((upstream-name . "GO.db")))
7915 (build-system r-build-system)
7916 (propagated-inputs
7917 `(("r-annotationdbi" ,r-annotationdbi)))
7918 (home-page "https://bioconductor.org/packages/GO.db")
7919 (synopsis "Annotation maps describing the entire Gene Ontology")
7920 (description
7921 "The purpose of this GO.db annotation package is to provide detailed
7922 information about the latest version of the Gene Ontologies.")
7923 (license license:artistic2.0)))
7924
7925 (define-public r-topgo
7926 (package
7927 (name "r-topgo")
7928 (version "2.34.0")
7929 (source (origin
7930 (method url-fetch)
7931 (uri (bioconductor-uri "topGO" version))
7932 (sha256
7933 (base32
7934 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
7935 (properties
7936 `((upstream-name . "topGO")))
7937 (build-system r-build-system)
7938 (propagated-inputs
7939 `(("r-annotationdbi" ,r-annotationdbi)
7940 ("r-dbi" ,r-dbi)
7941 ("r-biobase" ,r-biobase)
7942 ("r-biocgenerics" ,r-biocgenerics)
7943 ("r-go-db" ,r-go-db)
7944 ("r-graph" ,r-graph)
7945 ("r-lattice" ,r-lattice)
7946 ("r-matrixstats" ,r-matrixstats)
7947 ("r-sparsem" ,r-sparsem)))
7948 (home-page "https://bioconductor.org/packages/topGO")
7949 (synopsis "Enrichment analysis for gene ontology")
7950 (description
7951 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7952 terms while accounting for the topology of the GO graph. Different test
7953 statistics and different methods for eliminating local similarities and
7954 dependencies between GO terms can be implemented and applied.")
7955 ;; Any version of the LGPL applies.
7956 (license license:lgpl2.1+)))
7957
7958 (define-public r-bsgenome
7959 (package
7960 (name "r-bsgenome")
7961 (version "1.50.0")
7962 (source (origin
7963 (method url-fetch)
7964 (uri (bioconductor-uri "BSgenome" version))
7965 (sha256
7966 (base32
7967 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
7968 (properties
7969 `((upstream-name . "BSgenome")))
7970 (build-system r-build-system)
7971 (propagated-inputs
7972 `(("r-biocgenerics" ,r-biocgenerics)
7973 ("r-biostrings" ,r-biostrings)
7974 ("r-genomeinfodb" ,r-genomeinfodb)
7975 ("r-genomicranges" ,r-genomicranges)
7976 ("r-iranges" ,r-iranges)
7977 ("r-rsamtools" ,r-rsamtools)
7978 ("r-rtracklayer" ,r-rtracklayer)
7979 ("r-s4vectors" ,r-s4vectors)
7980 ("r-xvector" ,r-xvector)))
7981 (home-page "https://bioconductor.org/packages/BSgenome")
7982 (synopsis "Infrastructure for Biostrings-based genome data packages")
7983 (description
7984 "This package provides infrastructure shared by all Biostrings-based
7985 genome data packages and support for efficient SNP representation.")
7986 (license license:artistic2.0)))
7987
7988 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7989 (package
7990 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7991 (version "0.99.1")
7992 (source (origin
7993 (method url-fetch)
7994 ;; We cannot use bioconductor-uri here because this tarball is
7995 ;; located under "data/annotation/" instead of "bioc/".
7996 (uri (string-append "https://www.bioconductor.org/packages/"
7997 "release/data/annotation/src/contrib/"
7998 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7999 version ".tar.gz"))
8000 (sha256
8001 (base32
8002 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
8003 (properties
8004 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
8005 (build-system r-build-system)
8006 ;; As this package provides little more than a very large data file it
8007 ;; doesn't make sense to build substitutes.
8008 (arguments `(#:substitutable? #f))
8009 (propagated-inputs
8010 `(("r-bsgenome" ,r-bsgenome)))
8011 (home-page
8012 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
8013 (synopsis "Full genome sequences for Homo sapiens")
8014 (description
8015 "This package provides full genome sequences for Homo sapiens from
8016 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
8017 (license license:artistic2.0)))
8018
8019 (define-public r-impute
8020 (package
8021 (name "r-impute")
8022 (version "1.56.0")
8023 (source (origin
8024 (method url-fetch)
8025 (uri (bioconductor-uri "impute" version))
8026 (sha256
8027 (base32
8028 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
8029 (inputs
8030 `(("gfortran" ,gfortran)))
8031 (build-system r-build-system)
8032 (home-page "https://bioconductor.org/packages/impute")
8033 (synopsis "Imputation for microarray data")
8034 (description
8035 "This package provides a function to impute missing gene expression
8036 microarray data, using nearest neighbor averaging.")
8037 (license license:gpl2+)))
8038
8039 (define-public r-seqpattern
8040 (package
8041 (name "r-seqpattern")
8042 (version "1.14.0")
8043 (source (origin
8044 (method url-fetch)
8045 (uri (bioconductor-uri "seqPattern" version))
8046 (sha256
8047 (base32
8048 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
8049 (properties
8050 `((upstream-name . "seqPattern")))
8051 (build-system r-build-system)
8052 (propagated-inputs
8053 `(("r-biostrings" ,r-biostrings)
8054 ("r-genomicranges" ,r-genomicranges)
8055 ("r-iranges" ,r-iranges)
8056 ("r-kernsmooth" ,r-kernsmooth)
8057 ("r-plotrix" ,r-plotrix)))
8058 (home-page "https://bioconductor.org/packages/seqPattern")
8059 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8060 (description
8061 "This package provides tools to visualize oligonucleotide patterns and
8062 sequence motif occurrences across a large set of sequences centred at a common
8063 reference point and sorted by a user defined feature.")
8064 (license license:gpl3+)))
8065
8066 (define-public r-genomation
8067 (package
8068 (name "r-genomation")
8069 (version "1.14.0")
8070 (source (origin
8071 (method url-fetch)
8072 (uri (bioconductor-uri "genomation" version))
8073 (sha256
8074 (base32
8075 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
8076 (build-system r-build-system)
8077 (propagated-inputs
8078 `(("r-biostrings" ,r-biostrings)
8079 ("r-bsgenome" ,r-bsgenome)
8080 ("r-data-table" ,r-data-table)
8081 ("r-genomeinfodb" ,r-genomeinfodb)
8082 ("r-genomicalignments" ,r-genomicalignments)
8083 ("r-genomicranges" ,r-genomicranges)
8084 ("r-ggplot2" ,r-ggplot2)
8085 ("r-gridbase" ,r-gridbase)
8086 ("r-impute" ,r-impute)
8087 ("r-iranges" ,r-iranges)
8088 ("r-matrixstats" ,r-matrixstats)
8089 ("r-plotrix" ,r-plotrix)
8090 ("r-plyr" ,r-plyr)
8091 ("r-rcpp" ,r-rcpp)
8092 ("r-readr" ,r-readr)
8093 ("r-reshape2" ,r-reshape2)
8094 ("r-rsamtools" ,r-rsamtools)
8095 ("r-rtracklayer" ,r-rtracklayer)
8096 ("r-runit" ,r-runit)
8097 ("r-s4vectors" ,r-s4vectors)
8098 ("r-seqpattern" ,r-seqpattern)))
8099 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8100 (synopsis "Summary, annotation and visualization of genomic data")
8101 (description
8102 "This package provides a package for summary and annotation of genomic
8103 intervals. Users can visualize and quantify genomic intervals over
8104 pre-defined functional regions, such as promoters, exons, introns, etc. The
8105 genomic intervals represent regions with a defined chromosome position, which
8106 may be associated with a score, such as aligned reads from HT-seq experiments,
8107 TF binding sites, methylation scores, etc. The package can use any tabular
8108 genomic feature data as long as it has minimal information on the locations of
8109 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8110 (license license:artistic2.0)))
8111
8112 (define-public r-genomationdata
8113 (package
8114 (name "r-genomationdata")
8115 (version "1.10.0")
8116 (source (origin
8117 (method url-fetch)
8118 ;; We cannot use bioconductor-uri here because this tarball is
8119 ;; located under "data/annotation/" instead of "bioc/".
8120 (uri (string-append "https://bioconductor.org/packages/"
8121 "release/data/experiment/src/contrib/"
8122 "genomationData_" version ".tar.gz"))
8123 (sha256
8124 (base32
8125 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
8126 (build-system r-build-system)
8127 ;; As this package provides little more than large data files, it doesn't
8128 ;; make sense to build substitutes.
8129 (arguments `(#:substitutable? #f))
8130 (native-inputs
8131 `(("r-knitr" ,r-knitr)))
8132 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8133 (synopsis "Experimental data for use with the genomation package")
8134 (description
8135 "This package contains experimental genetic data for use with the
8136 genomation package. Included are Chip Seq, Methylation and Cage data,
8137 downloaded from Encode.")
8138 (license license:gpl3+)))
8139
8140 (define-public r-org-hs-eg-db
8141 (package
8142 (name "r-org-hs-eg-db")
8143 (version "3.5.0")
8144 (source (origin
8145 (method url-fetch)
8146 ;; We cannot use bioconductor-uri here because this tarball is
8147 ;; located under "data/annotation/" instead of "bioc/".
8148 (uri (string-append "https://www.bioconductor.org/packages/"
8149 "release/data/annotation/src/contrib/"
8150 "org.Hs.eg.db_" version ".tar.gz"))
8151 (sha256
8152 (base32
8153 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
8154 (properties
8155 `((upstream-name . "org.Hs.eg.db")))
8156 (build-system r-build-system)
8157 (propagated-inputs
8158 `(("r-annotationdbi" ,r-annotationdbi)))
8159 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8160 (synopsis "Genome wide annotation for Human")
8161 (description
8162 "This package contains genome-wide annotations for Human, primarily based
8163 on mapping using Entrez Gene identifiers.")
8164 (license license:artistic2.0)))
8165
8166 (define-public r-org-ce-eg-db
8167 (package
8168 (name "r-org-ce-eg-db")
8169 (version "3.5.0")
8170 (source (origin
8171 (method url-fetch)
8172 ;; We cannot use bioconductor-uri here because this tarball is
8173 ;; located under "data/annotation/" instead of "bioc/".
8174 (uri (string-append "https://www.bioconductor.org/packages/"
8175 "release/data/annotation/src/contrib/"
8176 "org.Ce.eg.db_" version ".tar.gz"))
8177 (sha256
8178 (base32
8179 "02ggchixlmzywhsbr0h2ms4dravv7m5964cjxqcjxqs16vjwlbk9"))))
8180 (properties
8181 `((upstream-name . "org.Ce.eg.db")))
8182 (build-system r-build-system)
8183 (propagated-inputs
8184 `(("r-annotationdbi" ,r-annotationdbi)))
8185 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8186 (synopsis "Genome wide annotation for Worm")
8187 (description
8188 "This package provides mappings from Entrez gene identifiers to various
8189 annotations for the genome of the model worm Caenorhabditis elegans.")
8190 (license license:artistic2.0)))
8191
8192 (define-public r-org-dm-eg-db
8193 (package
8194 (name "r-org-dm-eg-db")
8195 (version "3.5.0")
8196 (source (origin
8197 (method url-fetch)
8198 ;; We cannot use bioconductor-uri here because this tarball is
8199 ;; located under "data/annotation/" instead of "bioc/".
8200 (uri (string-append "https://www.bioconductor.org/packages/"
8201 "release/data/annotation/src/contrib/"
8202 "org.Dm.eg.db_" version ".tar.gz"))
8203 (sha256
8204 (base32
8205 "033qak1d3wwz17va0bh8z8p8arx0aw2va6gm1qfwsvdkj9cd9d7d"))))
8206 (properties
8207 `((upstream-name . "org.Dm.eg.db")))
8208 (build-system r-build-system)
8209 (propagated-inputs
8210 `(("r-annotationdbi" ,r-annotationdbi)))
8211 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8212 (synopsis "Genome wide annotation for Fly")
8213 (description
8214 "This package provides mappings from Entrez gene identifiers to various
8215 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8216 (license license:artistic2.0)))
8217
8218 (define-public r-org-mm-eg-db
8219 (package
8220 (name "r-org-mm-eg-db")
8221 (version "3.5.0")
8222 (source (origin
8223 (method url-fetch)
8224 ;; We cannot use bioconductor-uri here because this tarball is
8225 ;; located under "data/annotation/" instead of "bioc/".
8226 (uri (string-append "https://www.bioconductor.org/packages/"
8227 "release/data/annotation/src/contrib/"
8228 "org.Mm.eg.db_" version ".tar.gz"))
8229 (sha256
8230 (base32
8231 "11q21p3ki4bn4hb3aix0g775l45l66jmas6m94nfhqqnpjhv4d6g"))))
8232 (properties
8233 `((upstream-name . "org.Mm.eg.db")))
8234 (build-system r-build-system)
8235 (propagated-inputs
8236 `(("r-annotationdbi" ,r-annotationdbi)))
8237 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8238 (synopsis "Genome wide annotation for Mouse")
8239 (description
8240 "This package provides mappings from Entrez gene identifiers to various
8241 annotations for the genome of the model mouse Mus musculus.")
8242 (license license:artistic2.0)))
8243
8244 (define-public r-seqlogo
8245 (package
8246 (name "r-seqlogo")
8247 (version "1.48.0")
8248 (source
8249 (origin
8250 (method url-fetch)
8251 (uri (bioconductor-uri "seqLogo" version))
8252 (sha256
8253 (base32
8254 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
8255 (properties `((upstream-name . "seqLogo")))
8256 (build-system r-build-system)
8257 (home-page "https://bioconductor.org/packages/seqLogo")
8258 (synopsis "Sequence logos for DNA sequence alignments")
8259 (description
8260 "seqLogo takes the position weight matrix of a DNA sequence motif and
8261 plots the corresponding sequence logo as introduced by Schneider and
8262 Stephens (1990).")
8263 (license license:lgpl2.0+)))
8264
8265 (define-public r-bsgenome-hsapiens-ucsc-hg19
8266 (package
8267 (name "r-bsgenome-hsapiens-ucsc-hg19")
8268 (version "1.4.0")
8269 (source (origin
8270 (method url-fetch)
8271 ;; We cannot use bioconductor-uri here because this tarball is
8272 ;; located under "data/annotation/" instead of "bioc/".
8273 (uri (string-append "https://www.bioconductor.org/packages/"
8274 "release/data/annotation/src/contrib/"
8275 "BSgenome.Hsapiens.UCSC.hg19_"
8276 version ".tar.gz"))
8277 (sha256
8278 (base32
8279 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
8280 (properties
8281 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
8282 (build-system r-build-system)
8283 ;; As this package provides little more than a very large data file it
8284 ;; doesn't make sense to build substitutes.
8285 (arguments `(#:substitutable? #f))
8286 (propagated-inputs
8287 `(("r-bsgenome" ,r-bsgenome)))
8288 (home-page
8289 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
8290 (synopsis "Full genome sequences for Homo sapiens")
8291 (description
8292 "This package provides full genome sequences for Homo sapiens as provided
8293 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
8294 (license license:artistic2.0)))
8295
8296 (define-public r-bsgenome-mmusculus-ucsc-mm9
8297 (package
8298 (name "r-bsgenome-mmusculus-ucsc-mm9")
8299 (version "1.4.0")
8300 (source (origin
8301 (method url-fetch)
8302 ;; We cannot use bioconductor-uri here because this tarball is
8303 ;; located under "data/annotation/" instead of "bioc/".
8304 (uri (string-append "https://www.bioconductor.org/packages/"
8305 "release/data/annotation/src/contrib/"
8306 "BSgenome.Mmusculus.UCSC.mm9_"
8307 version ".tar.gz"))
8308 (sha256
8309 (base32
8310 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
8311 (properties
8312 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
8313 (build-system r-build-system)
8314 ;; As this package provides little more than a very large data file it
8315 ;; doesn't make sense to build substitutes.
8316 (arguments `(#:substitutable? #f))
8317 (propagated-inputs
8318 `(("r-bsgenome" ,r-bsgenome)))
8319 (home-page
8320 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
8321 (synopsis "Full genome sequences for Mouse")
8322 (description
8323 "This package provides full genome sequences for Mus musculus (Mouse) as
8324 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
8325 (license license:artistic2.0)))
8326
8327 (define-public r-bsgenome-mmusculus-ucsc-mm10
8328 (package
8329 (name "r-bsgenome-mmusculus-ucsc-mm10")
8330 (version "1.4.0")
8331 (source (origin
8332 (method url-fetch)
8333 ;; We cannot use bioconductor-uri here because this tarball is
8334 ;; located under "data/annotation/" instead of "bioc/".
8335 (uri (string-append "https://www.bioconductor.org/packages/"
8336 "release/data/annotation/src/contrib/"
8337 "BSgenome.Mmusculus.UCSC.mm10_"
8338 version ".tar.gz"))
8339 (sha256
8340 (base32
8341 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8342 (properties
8343 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8344 (build-system r-build-system)
8345 ;; As this package provides little more than a very large data file it
8346 ;; doesn't make sense to build substitutes.
8347 (arguments `(#:substitutable? #f))
8348 (propagated-inputs
8349 `(("r-bsgenome" ,r-bsgenome)))
8350 (home-page
8351 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8352 (synopsis "Full genome sequences for Mouse")
8353 (description
8354 "This package provides full genome sequences for Mus
8355 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8356 in Biostrings objects.")
8357 (license license:artistic2.0)))
8358
8359 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8360 (package
8361 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8362 (version "3.4.0")
8363 (source (origin
8364 (method url-fetch)
8365 ;; We cannot use bioconductor-uri here because this tarball is
8366 ;; located under "data/annotation/" instead of "bioc/".
8367 (uri (string-append "https://www.bioconductor.org/packages/"
8368 "release/data/annotation/src/contrib/"
8369 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8370 version ".tar.gz"))
8371 (sha256
8372 (base32
8373 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
8374 (properties
8375 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8376 (build-system r-build-system)
8377 ;; As this package provides little more than a very large data file it
8378 ;; doesn't make sense to build substitutes.
8379 (arguments `(#:substitutable? #f))
8380 (propagated-inputs
8381 `(("r-bsgenome" ,r-bsgenome)
8382 ("r-genomicfeatures" ,r-genomicfeatures)
8383 ("r-annotationdbi" ,r-annotationdbi)))
8384 (home-page
8385 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8386 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8387 (description
8388 "This package loads a TxDb object, which is an R interface to
8389 prefabricated databases contained in this package. This package provides
8390 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8391 based on the knownGene track.")
8392 (license license:artistic2.0)))
8393
8394 (define-public r-bsgenome-celegans-ucsc-ce6
8395 (package
8396 (name "r-bsgenome-celegans-ucsc-ce6")
8397 (version "1.4.0")
8398 (source (origin
8399 (method url-fetch)
8400 ;; We cannot use bioconductor-uri here because this tarball is
8401 ;; located under "data/annotation/" instead of "bioc/".
8402 (uri (string-append "https://www.bioconductor.org/packages/"
8403 "release/data/annotation/src/contrib/"
8404 "BSgenome.Celegans.UCSC.ce6_"
8405 version ".tar.gz"))
8406 (sha256
8407 (base32
8408 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8409 (properties
8410 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8411 (build-system r-build-system)
8412 ;; As this package provides little more than a very large data file it
8413 ;; doesn't make sense to build substitutes.
8414 (arguments `(#:substitutable? #f))
8415 (propagated-inputs
8416 `(("r-bsgenome" ,r-bsgenome)))
8417 (home-page
8418 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8419 (synopsis "Full genome sequences for Worm")
8420 (description
8421 "This package provides full genome sequences for Caenorhabditis
8422 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8423 objects.")
8424 (license license:artistic2.0)))
8425
8426 (define-public r-bsgenome-celegans-ucsc-ce10
8427 (package
8428 (name "r-bsgenome-celegans-ucsc-ce10")
8429 (version "1.4.0")
8430 (source (origin
8431 (method url-fetch)
8432 ;; We cannot use bioconductor-uri here because this tarball is
8433 ;; located under "data/annotation/" instead of "bioc/".
8434 (uri (string-append "https://www.bioconductor.org/packages/"
8435 "release/data/annotation/src/contrib/"
8436 "BSgenome.Celegans.UCSC.ce10_"
8437 version ".tar.gz"))
8438 (sha256
8439 (base32
8440 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8441 (properties
8442 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8443 (build-system r-build-system)
8444 ;; As this package provides little more than a very large data file it
8445 ;; doesn't make sense to build substitutes.
8446 (arguments `(#:substitutable? #f))
8447 (propagated-inputs
8448 `(("r-bsgenome" ,r-bsgenome)))
8449 (home-page
8450 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8451 (synopsis "Full genome sequences for Worm")
8452 (description
8453 "This package provides full genome sequences for Caenorhabditis
8454 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8455 objects.")
8456 (license license:artistic2.0)))
8457
8458 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8459 (package
8460 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8461 (version "1.4.0")
8462 (source (origin
8463 (method url-fetch)
8464 ;; We cannot use bioconductor-uri here because this tarball is
8465 ;; located under "data/annotation/" instead of "bioc/".
8466 (uri (string-append "https://www.bioconductor.org/packages/"
8467 "release/data/annotation/src/contrib/"
8468 "BSgenome.Dmelanogaster.UCSC.dm3_"
8469 version ".tar.gz"))
8470 (sha256
8471 (base32
8472 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8473 (properties
8474 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8475 (build-system r-build-system)
8476 ;; As this package provides little more than a very large data file it
8477 ;; doesn't make sense to build substitutes.
8478 (arguments `(#:substitutable? #f))
8479 (propagated-inputs
8480 `(("r-bsgenome" ,r-bsgenome)))
8481 (home-page
8482 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8483 (synopsis "Full genome sequences for Fly")
8484 (description
8485 "This package provides full genome sequences for Drosophila
8486 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8487 Biostrings objects.")
8488 (license license:artistic2.0)))
8489
8490 (define-public r-motifrg
8491 (package
8492 (name "r-motifrg")
8493 (version "1.26.0")
8494 (source
8495 (origin
8496 (method url-fetch)
8497 (uri (bioconductor-uri "motifRG" version))
8498 (sha256
8499 (base32
8500 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8501 (properties `((upstream-name . "motifRG")))
8502 (build-system r-build-system)
8503 (propagated-inputs
8504 `(("r-biostrings" ,r-biostrings)
8505 ("r-bsgenome" ,r-bsgenome)
8506 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8507 ("r-iranges" ,r-iranges)
8508 ("r-seqlogo" ,r-seqlogo)
8509 ("r-xvector" ,r-xvector)))
8510 (home-page "https://bioconductor.org/packages/motifRG")
8511 (synopsis "Discover motifs in high throughput sequencing data")
8512 (description
8513 "This package provides tools for discriminative motif discovery in high
8514 throughput genetic sequencing data sets using regression methods.")
8515 (license license:artistic2.0)))
8516
8517 (define-public r-qtl
8518 (package
8519 (name "r-qtl")
8520 (version "1.42-8")
8521 (source
8522 (origin
8523 (method url-fetch)
8524 (uri (string-append "mirror://cran/src/contrib/qtl_"
8525 version ".tar.gz"))
8526 (sha256
8527 (base32
8528 "1l528dwvfpdlr05imrrm4rq32axp6hld9nqm6mm43kn5n7z2f5k6"))))
8529 (build-system r-build-system)
8530 (home-page "http://rqtl.org/")
8531 (synopsis "R package for analyzing QTL experiments in genetics")
8532 (description "R/qtl is an extension library for the R statistics
8533 system. It is used to analyze experimental crosses for identifying
8534 genes contributing to variation in quantitative traits (so-called
8535 quantitative trait loci, QTLs).
8536
8537 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8538 identify genotyping errors, and to perform single-QTL and two-QTL,
8539 two-dimensional genome scans.")
8540 (license license:gpl3)))
8541
8542 (define-public r-zlibbioc
8543 (package
8544 (name "r-zlibbioc")
8545 (version "1.28.0")
8546 (source (origin
8547 (method url-fetch)
8548 (uri (bioconductor-uri "zlibbioc" version))
8549 (sha256
8550 (base32
8551 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8552 (properties
8553 `((upstream-name . "zlibbioc")))
8554 (build-system r-build-system)
8555 (home-page "https://bioconductor.org/packages/zlibbioc")
8556 (synopsis "Provider for zlib-1.2.5 to R packages")
8557 (description "This package uses the source code of zlib-1.2.5 to create
8558 libraries for systems that do not have these available via other means.")
8559 (license license:artistic2.0)))
8560
8561 (define-public r-r4rna
8562 (package
8563 (name "r-r4rna")
8564 (version "0.1.4")
8565 (source
8566 (origin
8567 (method url-fetch)
8568 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8569 version ".tar.gz"))
8570 (sha256
8571 (base32
8572 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8573 (build-system r-build-system)
8574 (propagated-inputs
8575 `(("r-optparse" ,r-optparse)
8576 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8577 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8578 (synopsis "Analysis framework for RNA secondary structure")
8579 (description
8580 "The R4RNA package aims to be a general framework for the analysis of RNA
8581 secondary structure and comparative analysis in R.")
8582 (license license:gpl3+)))
8583
8584 (define-public r-rhtslib
8585 (package
8586 (name "r-rhtslib")
8587 (version "1.14.0")
8588 (source
8589 (origin
8590 (method url-fetch)
8591 (uri (bioconductor-uri "Rhtslib" version))
8592 (sha256
8593 (base32
8594 "1h4q54f8za3aaxgy186zf2165sar5c3cgxkk44lq5hzx5pxkl5wn"))))
8595 (properties `((upstream-name . "Rhtslib")))
8596 (build-system r-build-system)
8597 (propagated-inputs
8598 `(("r-zlibbioc" ,r-zlibbioc)))
8599 (inputs
8600 `(("zlib" ,zlib)))
8601 (native-inputs
8602 `(("pkg-config" ,pkg-config)))
8603 (home-page "https://github.com/nhayden/Rhtslib")
8604 (synopsis "High-throughput sequencing library as an R package")
8605 (description
8606 "This package provides the HTSlib C library for high-throughput
8607 nucleotide sequence analysis. The package is primarily useful to developers
8608 of other R packages who wish to make use of HTSlib.")
8609 (license license:lgpl2.0+)))
8610
8611 (define-public r-bamsignals
8612 (package
8613 (name "r-bamsignals")
8614 (version "1.14.0")
8615 (source
8616 (origin
8617 (method url-fetch)
8618 (uri (bioconductor-uri "bamsignals" version))
8619 (sha256
8620 (base32
8621 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8622 (build-system r-build-system)
8623 (propagated-inputs
8624 `(("r-biocgenerics" ,r-biocgenerics)
8625 ("r-genomicranges" ,r-genomicranges)
8626 ("r-iranges" ,r-iranges)
8627 ("r-rcpp" ,r-rcpp)
8628 ("r-rhtslib" ,r-rhtslib)
8629 ("r-zlibbioc" ,r-zlibbioc)))
8630 (inputs
8631 `(("zlib" ,zlib)))
8632 (home-page "https://bioconductor.org/packages/bamsignals")
8633 (synopsis "Extract read count signals from bam files")
8634 (description
8635 "This package allows to efficiently obtain count vectors from indexed bam
8636 files. It counts the number of nucleotide sequence reads in given genomic
8637 ranges and it computes reads profiles and coverage profiles. It also handles
8638 paired-end data.")
8639 (license license:gpl2+)))
8640
8641 (define-public r-rcas
8642 (package
8643 (name "r-rcas")
8644 (version "1.8.0")
8645 (source (origin
8646 (method url-fetch)
8647 (uri (bioconductor-uri "RCAS" version))
8648 (sha256
8649 (base32
8650 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8651 (build-system r-build-system)
8652 (propagated-inputs
8653 `(("r-annotationdbi" ,r-annotationdbi)
8654 ("r-biocgenerics" ,r-biocgenerics)
8655 ("r-biomart" ,r-biomart)
8656 ("r-biostrings" ,r-biostrings)
8657 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8658 ("r-cowplot" ,r-cowplot)
8659 ("r-data-table" ,r-data-table)
8660 ("r-dbi" ,r-dbi)
8661 ("r-dt" ,r-dt)
8662 ("r-genomation" ,r-genomation)
8663 ("r-genomeinfodb" ,r-genomeinfodb)
8664 ("r-genomicfeatures" ,r-genomicfeatures)
8665 ("r-genomicranges" ,r-genomicranges)
8666 ("r-ggplot2" ,r-ggplot2)
8667 ("r-ggseqlogo" ,r-ggseqlogo)
8668 ("r-knitr" ,r-knitr)
8669 ("r-motifrg" ,r-motifrg)
8670 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8671 ("r-pbapply" ,r-pbapply)
8672 ("r-pheatmap" ,r-pheatmap)
8673 ("r-plotly" ,r-plotly)
8674 ("r-plotrix" ,r-plotrix)
8675 ("r-proxy" ,r-proxy)
8676 ("r-rsqlite" ,r-rsqlite)
8677 ("r-rtracklayer" ,r-rtracklayer)
8678 ("r-rmarkdown" ,r-rmarkdown)
8679 ("r-s4vectors" ,r-s4vectors)
8680 ("r-topgo" ,r-topgo)))
8681 (synopsis "RNA-centric annotation system")
8682 (description
8683 "RCAS aims to be a standalone RNA-centric annotation system that provides
8684 intuitive reports and publication-ready graphics. This package provides the R
8685 library implementing most of the pipeline's features.")
8686 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8687 (license license:artistic2.0)))
8688
8689 (define-public rcas-web
8690 (package
8691 (name "rcas-web")
8692 (version "0.0.5")
8693 (source
8694 (origin
8695 (method url-fetch)
8696 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8697 "releases/download/v" version
8698 "/rcas-web-" version ".tar.gz"))
8699 (sha256
8700 (base32
8701 "0igz7jpcf7cm9800zcag6p3gd1i649figrhbdba6cjkm8f4gfspr"))))
8702 (build-system gnu-build-system)
8703 (arguments
8704 `(#:phases
8705 (modify-phases %standard-phases
8706 (add-after 'install 'wrap-executable
8707 (lambda* (#:key inputs outputs #:allow-other-keys)
8708 (let* ((out (assoc-ref outputs "out"))
8709 (json (assoc-ref inputs "guile-json"))
8710 (redis (assoc-ref inputs "guile-redis"))
8711 (path (string-append
8712 json "/share/guile/site/2.2:"
8713 redis "/share/guile/site/2.2")))
8714 (wrap-program (string-append out "/bin/rcas-web")
8715 `("GUILE_LOAD_PATH" ":" = (,path))
8716 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8717 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8718 #t)))))
8719 (inputs
8720 `(("r-minimal" ,r-minimal)
8721 ("r-rcas" ,r-rcas)
8722 ("guile-next" ,guile-2.2)
8723 ("guile-json" ,guile-json)
8724 ("guile-redis" ,guile2.2-redis)))
8725 (native-inputs
8726 `(("pkg-config" ,pkg-config)))
8727 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8728 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8729 (description "This package provides a simple web interface for the
8730 @dfn{RNA-centric annotation system} (RCAS).")
8731 (license license:agpl3+)))
8732
8733 (define-public r-mutationalpatterns
8734 (package
8735 (name "r-mutationalpatterns")
8736 (version "1.8.0")
8737 (source
8738 (origin
8739 (method url-fetch)
8740 (uri (bioconductor-uri "MutationalPatterns" version))
8741 (sha256
8742 (base32
8743 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8744 (build-system r-build-system)
8745 (propagated-inputs
8746 `(("r-biocgenerics" ,r-biocgenerics)
8747 ("r-biostrings" ,r-biostrings)
8748 ;; These two packages are suggested packages
8749 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8750 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8751 ("r-genomicranges" ,r-genomicranges)
8752 ("r-genomeinfodb" ,r-genomeinfodb)
8753 ("r-ggplot2" ,r-ggplot2)
8754 ("r-iranges" ,r-iranges)
8755 ("r-nmf" ,r-nmf)
8756 ("r-plyr" ,r-plyr)
8757 ("r-pracma" ,r-pracma)
8758 ("r-reshape2" ,r-reshape2)
8759 ("r-cowplot" ,r-cowplot)
8760 ("r-ggdendro" ,r-ggdendro)
8761 ("r-s4vectors" ,r-s4vectors)
8762 ("r-summarizedexperiment" ,r-summarizedexperiment)
8763 ("r-variantannotation" ,r-variantannotation)))
8764 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8765 (synopsis "Extract and visualize mutational patterns in genomic data")
8766 (description "This package provides an extensive toolset for the
8767 characterization and visualization of a wide range of mutational patterns
8768 in SNV base substitution data.")
8769 (license license:expat)))
8770
8771 (define-public r-wgcna
8772 (package
8773 (name "r-wgcna")
8774 (version "1.66")
8775 (source
8776 (origin
8777 (method url-fetch)
8778 (uri (cran-uri "WGCNA" version))
8779 (sha256
8780 (base32
8781 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8782 (properties `((upstream-name . "WGCNA")))
8783 (build-system r-build-system)
8784 (propagated-inputs
8785 `(("r-annotationdbi" ,r-annotationdbi)
8786 ("r-doparallel" ,r-doparallel)
8787 ("r-dynamictreecut" ,r-dynamictreecut)
8788 ("r-fastcluster" ,r-fastcluster)
8789 ("r-foreach" ,r-foreach)
8790 ("r-go-db" ,r-go-db)
8791 ("r-hmisc" ,r-hmisc)
8792 ("r-impute" ,r-impute)
8793 ("r-rcpp" ,r-rcpp)
8794 ("r-robust" ,r-robust)
8795 ("r-survival" ,r-survival)
8796 ("r-matrixstats" ,r-matrixstats)
8797 ("r-preprocesscore" ,r-preprocesscore)))
8798 (home-page
8799 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8800 (synopsis "Weighted correlation network analysis")
8801 (description
8802 "This package provides functions necessary to perform Weighted
8803 Correlation Network Analysis on high-dimensional data. It includes functions
8804 for rudimentary data cleaning, construction and summarization of correlation
8805 networks, module identification and functions for relating both variables and
8806 modules to sample traits. It also includes a number of utility functions for
8807 data manipulation and visualization.")
8808 (license license:gpl2+)))
8809
8810 (define-public r-chipkernels
8811 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8812 (revision "1"))
8813 (package
8814 (name "r-chipkernels")
8815 (version (string-append "1.1-" revision "." (string-take commit 9)))
8816 (source
8817 (origin
8818 (method git-fetch)
8819 (uri (git-reference
8820 (url "https://github.com/ManuSetty/ChIPKernels.git")
8821 (commit commit)))
8822 (file-name (string-append name "-" version))
8823 (sha256
8824 (base32
8825 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8826 (build-system r-build-system)
8827 (propagated-inputs
8828 `(("r-iranges" ,r-iranges)
8829 ("r-xvector" ,r-xvector)
8830 ("r-biostrings" ,r-biostrings)
8831 ("r-bsgenome" ,r-bsgenome)
8832 ("r-gtools" ,r-gtools)
8833 ("r-genomicranges" ,r-genomicranges)
8834 ("r-sfsmisc" ,r-sfsmisc)
8835 ("r-kernlab" ,r-kernlab)
8836 ("r-s4vectors" ,r-s4vectors)
8837 ("r-biocgenerics" ,r-biocgenerics)))
8838 (home-page "https://github.com/ManuSetty/ChIPKernels")
8839 (synopsis "Build string kernels for DNA Sequence analysis")
8840 (description "ChIPKernels is an R package for building different string
8841 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8842 must be built and this dictionary can be used for determining kernels for DNA
8843 Sequences.")
8844 (license license:gpl2+))))
8845
8846 (define-public r-seqgl
8847 (package
8848 (name "r-seqgl")
8849 (version "1.1.4")
8850 (source
8851 (origin
8852 (method url-fetch)
8853 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8854 "archive/" version ".tar.gz"))
8855 (file-name (string-append name "-" version ".tar.gz"))
8856 (sha256
8857 (base32
8858 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8859 (build-system r-build-system)
8860 (propagated-inputs
8861 `(("r-biostrings" ,r-biostrings)
8862 ("r-chipkernels" ,r-chipkernels)
8863 ("r-genomicranges" ,r-genomicranges)
8864 ("r-spams" ,r-spams)
8865 ("r-wgcna" ,r-wgcna)
8866 ("r-fastcluster" ,r-fastcluster)))
8867 (home-page "https://github.com/ManuSetty/SeqGL")
8868 (synopsis "Group lasso for Dnase/ChIP-seq data")
8869 (description "SeqGL is a group lasso based algorithm to extract
8870 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8871 This package presents a method which uses group lasso to discriminate between
8872 bound and non bound genomic regions to accurately identify transcription
8873 factors bound at the specific regions.")
8874 (license license:gpl2+)))
8875
8876 (define-public r-gkmsvm
8877 (package
8878 (name "r-gkmsvm")
8879 (version "0.79.0")
8880 (source
8881 (origin
8882 (method url-fetch)
8883 (uri (cran-uri "gkmSVM" version))
8884 (sha256
8885 (base32
8886 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8887 (properties `((upstream-name . "gkmSVM")))
8888 (build-system r-build-system)
8889 (propagated-inputs
8890 `(("r-biocgenerics" ,r-biocgenerics)
8891 ("r-biostrings" ,r-biostrings)
8892 ("r-genomeinfodb" ,r-genomeinfodb)
8893 ("r-genomicranges" ,r-genomicranges)
8894 ("r-iranges" ,r-iranges)
8895 ("r-kernlab" ,r-kernlab)
8896 ("r-rcpp" ,r-rcpp)
8897 ("r-rocr" ,r-rocr)
8898 ("r-rtracklayer" ,r-rtracklayer)
8899 ("r-s4vectors" ,r-s4vectors)
8900 ("r-seqinr" ,r-seqinr)))
8901 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8902 (synopsis "Gapped-kmer support vector machine")
8903 (description
8904 "This R package provides tools for training gapped-kmer SVM classifiers
8905 for DNA and protein sequences. This package supports several sequence
8906 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8907 (license license:gpl2+)))
8908
8909 (define-public r-tximport
8910 (package
8911 (name "r-tximport")
8912 (version "1.10.0")
8913 (source (origin
8914 (method url-fetch)
8915 (uri (bioconductor-uri "tximport" version))
8916 (sha256
8917 (base32
8918 "0za2js8hqjgz8ria09cglynffj4w9vrzg85nmn1xgpvmc1xk813h"))))
8919 (build-system r-build-system)
8920 (home-page "https://bioconductor.org/packages/tximport")
8921 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8922 (description
8923 "This package provides tools to import transcript-level abundance,
8924 estimated counts and transcript lengths, and to summarize them into matrices
8925 for use with downstream gene-level analysis packages. Average transcript
8926 length, weighted by sample-specific transcript abundance estimates, is
8927 provided as a matrix which can be used as an offset for different expression
8928 of gene-level counts.")
8929 (license license:gpl2+)))
8930
8931 (define-public r-rhdf5
8932 (package
8933 (name "r-rhdf5")
8934 (version "2.26.0")
8935 (source (origin
8936 (method url-fetch)
8937 (uri (bioconductor-uri "rhdf5" version))
8938 (sha256
8939 (base32
8940 "0xmpkfdsmgl79ffffj7cf9fx3zxki2rk0xn25k778kr3s0sbmhis"))))
8941 (build-system r-build-system)
8942 (propagated-inputs
8943 `(("r-rhdf5lib" ,r-rhdf5lib)))
8944 (inputs
8945 `(("zlib" ,zlib)))
8946 (home-page "https://bioconductor.org/packages/rhdf5")
8947 (synopsis "HDF5 interface to R")
8948 (description
8949 "This R/Bioconductor package provides an interface between HDF5 and R.
8950 HDF5's main features are the ability to store and access very large and/or
8951 complex datasets and a wide variety of metadata on mass storage (disk) through
8952 a completely portable file format. The rhdf5 package is thus suited for the
8953 exchange of large and/or complex datasets between R and other software
8954 package, and for letting R applications work on datasets that are larger than
8955 the available RAM.")
8956 (license license:artistic2.0)))
8957
8958 (define-public r-annotationfilter
8959 (package
8960 (name "r-annotationfilter")
8961 (version "1.6.0")
8962 (source (origin
8963 (method url-fetch)
8964 (uri (bioconductor-uri "AnnotationFilter" version))
8965 (sha256
8966 (base32
8967 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
8968 (properties
8969 `((upstream-name . "AnnotationFilter")))
8970 (build-system r-build-system)
8971 (propagated-inputs
8972 `(("r-genomicranges" ,r-genomicranges)
8973 ("r-lazyeval" ,r-lazyeval)))
8974 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8975 (synopsis "Facilities for filtering Bioconductor annotation resources")
8976 (description
8977 "This package provides classes and other infrastructure to implement
8978 filters for manipulating Bioconductor annotation resources. The filters are
8979 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8980 (license license:artistic2.0)))
8981
8982 (define-public emboss
8983 (package
8984 (name "emboss")
8985 (version "6.5.7")
8986 (source (origin
8987 (method url-fetch)
8988 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8989 (version-major+minor version) ".0/"
8990 "EMBOSS-" version ".tar.gz"))
8991 (sha256
8992 (base32
8993 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8994 (build-system gnu-build-system)
8995 (arguments
8996 `(#:configure-flags
8997 (list (string-append "--with-hpdf="
8998 (assoc-ref %build-inputs "libharu")))
8999 #:phases
9000 (modify-phases %standard-phases
9001 (add-after 'unpack 'fix-checks
9002 (lambda _
9003 ;; The PNGDRIVER tests check for the presence of libgd, libpng
9004 ;; and zlib, but assume that they are all found at the same
9005 ;; prefix.
9006 (substitute* "configure.in"
9007 (("CHECK_PNGDRIVER")
9008 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
9009 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
9010 AM_CONDITIONAL(AMPNG, true)"))
9011 #t))
9012 (add-after 'fix-checks 'disable-update-check
9013 (lambda _
9014 ;; At build time there is no connection to the Internet, so
9015 ;; looking for updates will not work.
9016 (substitute* "Makefile.am"
9017 (("\\$\\(bindir\\)/embossupdate") ""))
9018 #t))
9019 (add-after 'disable-update-check 'autogen
9020 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
9021 (inputs
9022 `(("perl" ,perl)
9023 ("libpng" ,libpng)
9024 ("gd" ,gd)
9025 ("libx11" ,libx11)
9026 ("libharu" ,libharu)
9027 ("zlib" ,zlib)))
9028 (native-inputs
9029 `(("autoconf" ,autoconf)
9030 ("automake" ,automake)
9031 ("libtool" ,libtool)
9032 ("pkg-config" ,pkg-config)))
9033 (home-page "http://emboss.sourceforge.net")
9034 (synopsis "Molecular biology analysis suite")
9035 (description "EMBOSS is the \"European Molecular Biology Open Software
9036 Suite\". EMBOSS is an analysis package specially developed for the needs of
9037 the molecular biology (e.g. EMBnet) user community. The software
9038 automatically copes with data in a variety of formats and even allows
9039 transparent retrieval of sequence data from the web. It also provides a
9040 number of libraries for the development of software in the field of molecular
9041 biology. EMBOSS also integrates a range of currently available packages and
9042 tools for sequence analysis into a seamless whole.")
9043 (license license:gpl2+)))
9044
9045 (define-public bits
9046 (let ((revision "1")
9047 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9048 (package
9049 (name "bits")
9050 ;; The version is 2.13.0 even though no release archives have been
9051 ;; published as yet.
9052 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9053 (source (origin
9054 (method git-fetch)
9055 (uri (git-reference
9056 (url "https://github.com/arq5x/bits.git")
9057 (commit commit)))
9058 (file-name (string-append name "-" version "-checkout"))
9059 (sha256
9060 (base32
9061 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9062 (build-system gnu-build-system)
9063 (arguments
9064 `(#:tests? #f ;no tests included
9065 #:phases
9066 (modify-phases %standard-phases
9067 (delete 'configure)
9068 (add-after 'unpack 'remove-cuda
9069 (lambda _
9070 (substitute* "Makefile"
9071 ((".*_cuda") "")
9072 (("(bits_test_intersections) \\\\" _ match) match))
9073 #t))
9074 (replace 'install
9075 (lambda* (#:key outputs #:allow-other-keys)
9076 (copy-recursively
9077 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9078 #t)))))
9079 (inputs
9080 `(("gsl" ,gsl)
9081 ("zlib" ,zlib)))
9082 (home-page "https://github.com/arq5x/bits")
9083 (synopsis "Implementation of binary interval search algorithm")
9084 (description "This package provides an implementation of the
9085 BITS (Binary Interval Search) algorithm, an approach to interval set
9086 intersection. It is especially suited for the comparison of diverse genomic
9087 datasets and the exploration of large datasets of genome
9088 intervals (e.g. genes, sequence alignments).")
9089 (license license:gpl2))))
9090
9091 (define-public piranha
9092 ;; There is no release tarball for the latest version. The latest commit is
9093 ;; older than one year at the time of this writing.
9094 (let ((revision "1")
9095 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9096 (package
9097 (name "piranha")
9098 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9099 (source (origin
9100 (method git-fetch)
9101 (uri (git-reference
9102 (url "https://github.com/smithlabcode/piranha.git")
9103 (commit commit)))
9104 (file-name (git-file-name name version))
9105 (sha256
9106 (base32
9107 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9108 (build-system gnu-build-system)
9109 (arguments
9110 `(#:test-target "test"
9111 #:phases
9112 (modify-phases %standard-phases
9113 (add-after 'unpack 'copy-smithlab-cpp
9114 (lambda* (#:key inputs #:allow-other-keys)
9115 (for-each (lambda (file)
9116 (install-file file "./src/smithlab_cpp/"))
9117 (find-files (assoc-ref inputs "smithlab-cpp")))
9118 #t))
9119 (add-after 'install 'install-to-store
9120 (lambda* (#:key outputs #:allow-other-keys)
9121 (let* ((out (assoc-ref outputs "out"))
9122 (bin (string-append out "/bin")))
9123 (for-each (lambda (file)
9124 (install-file file bin))
9125 (find-files "bin" ".*")))
9126 #t)))
9127 #:configure-flags
9128 (list (string-append "--with-bam_tools_headers="
9129 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9130 (string-append "--with-bam_tools_library="
9131 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9132 (inputs
9133 `(("bamtools" ,bamtools)
9134 ("samtools" ,samtools-0.1)
9135 ("gsl" ,gsl)
9136 ("smithlab-cpp"
9137 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9138 (origin
9139 (method git-fetch)
9140 (uri (git-reference
9141 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9142 (commit commit)))
9143 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9144 (sha256
9145 (base32
9146 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9147 (native-inputs
9148 `(("python" ,python-2)))
9149 (home-page "https://github.com/smithlabcode/piranha")
9150 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9151 (description
9152 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9153 RIP-seq experiments. It takes input in BED or BAM format and identifies
9154 regions of statistically significant read enrichment. Additional covariates
9155 may optionally be provided to further inform the peak-calling process.")
9156 (license license:gpl3+))))
9157
9158 (define-public pepr
9159 (package
9160 (name "pepr")
9161 (version "1.0.9")
9162 (source (origin
9163 (method url-fetch)
9164 (uri (string-append "https://pypi.python.org/packages/source/P"
9165 "/PePr/PePr-" version ".tar.gz"))
9166 (sha256
9167 (base32
9168 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9169 (build-system python-build-system)
9170 (arguments
9171 `(#:python ,python-2 ; python2 only
9172 #:tests? #f)) ; no tests included
9173 (propagated-inputs
9174 `(("python2-numpy" ,python2-numpy)
9175 ("python2-scipy" ,python2-scipy)
9176 ("python2-pysam" ,python2-pysam)))
9177 (home-page "https://github.com/shawnzhangyx/PePr")
9178 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9179 (description
9180 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9181 that is primarily designed for data with biological replicates. It uses a
9182 negative binomial distribution to model the read counts among the samples in
9183 the same group, and look for consistent differences between ChIP and control
9184 group or two ChIP groups run under different conditions.")
9185 (license license:gpl3+)))
9186
9187 (define-public filevercmp
9188 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9189 (package
9190 (name "filevercmp")
9191 (version (string-append "0-1." (string-take commit 7)))
9192 (source (origin
9193 (method url-fetch)
9194 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
9195 commit ".tar.gz"))
9196 (file-name (string-append name "-" version ".tar.gz"))
9197 (sha256
9198 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
9199 (build-system gnu-build-system)
9200 (arguments
9201 `(#:tests? #f ; There are no tests to run.
9202 #:phases
9203 (modify-phases %standard-phases
9204 (delete 'configure) ; There is no configure phase.
9205 (replace 'install
9206 (lambda* (#:key outputs #:allow-other-keys)
9207 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9208 (install-file "filevercmp" bin)))))))
9209 (home-page "https://github.com/ekg/filevercmp")
9210 (synopsis "This program compares version strings")
9211 (description "This program compares version strings. It intends to be a
9212 replacement for strverscmp.")
9213 (license license:gpl3+))))
9214
9215 (define-public multiqc
9216 (package
9217 (name "multiqc")
9218 (version "1.5")
9219 (source
9220 (origin
9221 (method url-fetch)
9222 (uri (pypi-uri "multiqc" version))
9223 (sha256
9224 (base32
9225 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9226 (build-system python-build-system)
9227 (propagated-inputs
9228 `(("python-jinja2" ,python-jinja2)
9229 ("python-simplejson" ,python-simplejson)
9230 ("python-pyyaml" ,python-pyyaml)
9231 ("python-click" ,python-click)
9232 ("python-spectra" ,python-spectra)
9233 ("python-requests" ,python-requests)
9234 ("python-markdown" ,python-markdown)
9235 ("python-lzstring" ,python-lzstring)
9236 ("python-matplotlib" ,python-matplotlib)
9237 ("python-numpy" ,python-numpy)
9238 ;; MultQC checks for the presence of nose at runtime.
9239 ("python-nose" ,python-nose)))
9240 (arguments
9241 `(#:phases
9242 (modify-phases %standard-phases
9243 (add-after 'unpack 'relax-requirements
9244 (lambda _
9245 (substitute* "setup.py"
9246 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9247 ;; than the one in Guix, but should work fine with 2.2.2.
9248 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9249 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9250 (("['\"]matplotlib.*?['\"]")
9251 "'matplotlib'"))
9252 #t)))))
9253 (home-page "http://multiqc.info")
9254 (synopsis "Aggregate bioinformatics analysis reports")
9255 (description
9256 "MultiQC is a tool to aggregate bioinformatics results across many
9257 samples into a single report. It contains modules for a large number of
9258 common bioinformatics tools.")
9259 (license license:gpl3+)))
9260
9261 (define-public r-chipseq
9262 (package
9263 (name "r-chipseq")
9264 (version "1.32.0")
9265 (source
9266 (origin
9267 (method url-fetch)
9268 (uri (bioconductor-uri "chipseq" version))
9269 (sha256
9270 (base32
9271 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
9272 (build-system r-build-system)
9273 (propagated-inputs
9274 `(("r-biocgenerics" ,r-biocgenerics)
9275 ("r-genomicranges" ,r-genomicranges)
9276 ("r-iranges" ,r-iranges)
9277 ("r-lattice" ,r-lattice)
9278 ("r-s4vectors" ,r-s4vectors)
9279 ("r-shortread" ,r-shortread)))
9280 (home-page "https://bioconductor.org/packages/chipseq")
9281 (synopsis "Package for analyzing ChIPseq data")
9282 (description
9283 "This package provides tools for processing short read data from ChIPseq
9284 experiments.")
9285 (license license:artistic2.0)))
9286
9287 (define-public r-copyhelper
9288 (package
9289 (name "r-copyhelper")
9290 (version "1.6.0")
9291 (source
9292 (origin
9293 (method url-fetch)
9294 (uri (string-append "https://bioconductor.org/packages/release/"
9295 "data/experiment/src/contrib/CopyhelpeR_"
9296 version ".tar.gz"))
9297 (sha256
9298 (base32
9299 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9300 (properties `((upstream-name . "CopyhelpeR")))
9301 (build-system r-build-system)
9302 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9303 (synopsis "Helper files for CopywriteR")
9304 (description
9305 "This package contains the helper files that are required to run the
9306 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9307 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9308 mm10. In addition, it contains a blacklist filter to remove regions that
9309 display copy number variation. Files are stored as GRanges objects from the
9310 GenomicRanges Bioconductor package.")
9311 (license license:gpl2)))
9312
9313 (define-public r-copywriter
9314 (package
9315 (name "r-copywriter")
9316 (version "2.14.0")
9317 (source
9318 (origin
9319 (method url-fetch)
9320 (uri (bioconductor-uri "CopywriteR" version))
9321 (sha256
9322 (base32
9323 "0aamxafdk98n7s92jyqs65d6ljpnc2463vanvsw80p44qn6l6awn"))))
9324 (properties `((upstream-name . "CopywriteR")))
9325 (build-system r-build-system)
9326 (propagated-inputs
9327 `(("r-biocparallel" ,r-biocparallel)
9328 ("r-chipseq" ,r-chipseq)
9329 ("r-copyhelper" ,r-copyhelper)
9330 ("r-data-table" ,r-data-table)
9331 ("r-dnacopy" ,r-dnacopy)
9332 ("r-futile-logger" ,r-futile-logger)
9333 ("r-genomeinfodb" ,r-genomeinfodb)
9334 ("r-genomicalignments" ,r-genomicalignments)
9335 ("r-genomicranges" ,r-genomicranges)
9336 ("r-gtools" ,r-gtools)
9337 ("r-iranges" ,r-iranges)
9338 ("r-matrixstats" ,r-matrixstats)
9339 ("r-rsamtools" ,r-rsamtools)
9340 ("r-s4vectors" ,r-s4vectors)))
9341 (home-page "https://github.com/PeeperLab/CopywriteR")
9342 (synopsis "Copy number information from targeted sequencing")
9343 (description
9344 "CopywriteR extracts DNA copy number information from targeted sequencing
9345 by utilizing off-target reads. It allows for extracting uniformly distributed
9346 copy number information, can be used without reference, and can be applied to
9347 sequencing data obtained from various techniques including chromatin
9348 immunoprecipitation and target enrichment on small gene panels. Thereby,
9349 CopywriteR constitutes a widely applicable alternative to available copy
9350 number detection tools.")
9351 (license license:gpl2)))
9352
9353 (define-public r-methylkit
9354 (package
9355 (name "r-methylkit")
9356 (version "1.8.0")
9357 (source (origin
9358 (method url-fetch)
9359 (uri (bioconductor-uri "methylKit" version))
9360 (sha256
9361 (base32
9362 "0mz6lil1wax931incnw5byx0v9i8ryhwq9mv0nv8s48ai33ch3x6"))))
9363 (properties `((upstream-name . "methylKit")))
9364 (build-system r-build-system)
9365 (propagated-inputs
9366 `(("r-data-table" ,r-data-table)
9367 ("r-emdbook" ,r-emdbook)
9368 ("r-fastseg" ,r-fastseg)
9369 ("r-genomeinfodb" ,r-genomeinfodb)
9370 ("r-genomicranges" ,r-genomicranges)
9371 ("r-gtools" ,r-gtools)
9372 ("r-iranges" ,r-iranges)
9373 ("r-kernsmooth" ,r-kernsmooth)
9374 ("r-limma" ,r-limma)
9375 ("r-mclust" ,r-mclust)
9376 ("r-qvalue" ,r-qvalue)
9377 ("r-r-utils" ,r-r-utils)
9378 ("r-rcpp" ,r-rcpp)
9379 ("r-rhtslib" ,r-rhtslib)
9380 ("r-rsamtools" ,r-rsamtools)
9381 ("r-rtracklayer" ,r-rtracklayer)
9382 ("r-s4vectors" ,r-s4vectors)
9383 ("r-zlibbioc" ,r-zlibbioc)))
9384 (inputs
9385 `(("zlib" ,zlib)))
9386 (home-page "https://github.com/al2na/methylKit")
9387 (synopsis
9388 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9389 (description
9390 "MethylKit is an R package for DNA methylation analysis and annotation
9391 from high-throughput bisulfite sequencing. The package is designed to deal
9392 with sequencing data from @dfn{Reduced representation bisulfite
9393 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9394 genome bisulfite sequencing. It also has functions to analyze base-pair
9395 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9396 TAB-Seq.")
9397 (license license:artistic2.0)))
9398
9399 (define-public r-sva
9400 (package
9401 (name "r-sva")
9402 (version "3.30.0")
9403 (source
9404 (origin
9405 (method url-fetch)
9406 (uri (bioconductor-uri "sva" version))
9407 (sha256
9408 (base32
9409 "1xf0hlrqjxl0y3x13mrkxghiv39fd9v2g8gq3qzbf1wj7il6bph3"))))
9410 (build-system r-build-system)
9411 (propagated-inputs
9412 `(("r-genefilter" ,r-genefilter)
9413 ("r-mgcv" ,r-mgcv)
9414 ("r-biocparallel" ,r-biocparallel)
9415 ("r-matrixstats" ,r-matrixstats)
9416 ("r-limma" ,r-limma)))
9417 (home-page "https://bioconductor.org/packages/sva")
9418 (synopsis "Surrogate variable analysis")
9419 (description
9420 "This package contains functions for removing batch effects and other
9421 unwanted variation in high-throughput experiment. It also contains functions
9422 for identifying and building surrogate variables for high-dimensional data
9423 sets. Surrogate variables are covariates constructed directly from
9424 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9425 imaging data that can be used in subsequent analyses to adjust for unknown,
9426 unmodeled, or latent sources of noise.")
9427 (license license:artistic2.0)))
9428
9429 (define-public r-seqminer
9430 (package
9431 (name "r-seqminer")
9432 (version "6.1")
9433 (source
9434 (origin
9435 (method url-fetch)
9436 (uri (cran-uri "seqminer" version))
9437 (sha256
9438 (base32
9439 "15yhg4vfc7jg1jnqb3371j00pgbmbyc9l1xx63hq1l3p34lazq2l"))))
9440 (build-system r-build-system)
9441 (inputs
9442 `(("zlib" ,zlib)))
9443 (home-page "http://seqminer.genomic.codes")
9444 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9445 (description
9446 "This package provides tools to integrate nucleotide sequencing
9447 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9448 ;; Any version of the GPL is acceptable
9449 (license (list license:gpl2+ license:gpl3+))))
9450
9451 (define-public r-raremetals2
9452 (package
9453 (name "r-raremetals2")
9454 (version "0.1")
9455 (source
9456 (origin
9457 (method url-fetch)
9458 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9459 "b/b7/RareMETALS2_" version ".tar.gz"))
9460 (sha256
9461 (base32
9462 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9463 (properties `((upstream-name . "RareMETALS2")))
9464 (build-system r-build-system)
9465 (propagated-inputs
9466 `(("r-seqminer" ,r-seqminer)
9467 ("r-mvtnorm" ,r-mvtnorm)
9468 ("r-mass" ,r-mass)
9469 ("r-compquadform" ,r-compquadform)
9470 ("r-getopt" ,r-getopt)))
9471 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9472 (synopsis "Analyze gene-level association tests for binary trait")
9473 (description
9474 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9475 It was designed to meta-analyze gene-level association tests for binary trait.
9476 While rareMETALS offers a near-complete solution for meta-analysis of
9477 gene-level tests for quantitative trait, it does not offer the optimal
9478 solution for binary trait. The package rareMETALS2 offers improved features
9479 for analyzing gene-level association tests in meta-analyses for binary
9480 trait.")
9481 (license license:gpl3)))
9482
9483 (define-public r-maldiquant
9484 (package
9485 (name "r-maldiquant")
9486 (version "1.18")
9487 (source
9488 (origin
9489 (method url-fetch)
9490 (uri (cran-uri "MALDIquant" version))
9491 (sha256
9492 (base32
9493 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9494 (properties `((upstream-name . "MALDIquant")))
9495 (build-system r-build-system)
9496 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9497 (synopsis "Quantitative analysis of mass spectrometry data")
9498 (description
9499 "This package provides a complete analysis pipeline for matrix-assisted
9500 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9501 two-dimensional mass spectrometry data. In addition to commonly used plotting
9502 and processing methods it includes distinctive features, namely baseline
9503 subtraction methods such as morphological filters (TopHat) or the
9504 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9505 alignment using warping functions, handling of replicated measurements as well
9506 as allowing spectra with different resolutions.")
9507 (license license:gpl3+)))
9508
9509 (define-public r-protgenerics
9510 (package
9511 (name "r-protgenerics")
9512 (version "1.14.0")
9513 (source
9514 (origin
9515 (method url-fetch)
9516 (uri (bioconductor-uri "ProtGenerics" version))
9517 (sha256
9518 (base32
9519 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9520 (properties `((upstream-name . "ProtGenerics")))
9521 (build-system r-build-system)
9522 (home-page "https://github.com/lgatto/ProtGenerics")
9523 (synopsis "S4 generic functions for proteomics infrastructure")
9524 (description
9525 "This package provides S4 generic functions needed by Bioconductor
9526 proteomics packages.")
9527 (license license:artistic2.0)))
9528
9529 (define-public r-mzr
9530 (package
9531 (name "r-mzr")
9532 (version "2.16.0")
9533 (source
9534 (origin
9535 (method url-fetch)
9536 (uri (bioconductor-uri "mzR" version))
9537 (sha256
9538 (base32
9539 "0li1y6p95ljiva4lvfmql9sipn4dq42sknbh60b36ycjppnf8lj5"))
9540 (modules '((guix build utils)))
9541 (snippet
9542 '(begin
9543 (delete-file-recursively "src/boost")
9544 #t))))
9545 (properties `((upstream-name . "mzR")))
9546 (build-system r-build-system)
9547 (arguments
9548 `(#:phases
9549 (modify-phases %standard-phases
9550 (add-after 'unpack 'use-system-boost
9551 (lambda _
9552 (substitute* "src/Makevars"
9553 (("\\./boost/libs.*") "")
9554 (("ARCH_OBJS=" line)
9555 (string-append line
9556 "\nARCH_LIBS=-lboost_system -lboost_regex \
9557 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9558 #t)))))
9559 (inputs
9560 `(("boost" ,boost) ; use this instead of the bundled boost sources
9561 ("zlib" ,zlib)))
9562 (propagated-inputs
9563 `(("r-biobase" ,r-biobase)
9564 ("r-biocgenerics" ,r-biocgenerics)
9565 ("r-ncdf4" ,r-ncdf4)
9566 ("r-protgenerics" ,r-protgenerics)
9567 ("r-rcpp" ,r-rcpp)
9568 ("r-rhdf5lib" ,r-rhdf5lib)
9569 ("r-zlibbioc" ,r-zlibbioc)))
9570 (home-page "https://github.com/sneumann/mzR/")
9571 (synopsis "Parser for mass spectrometry data files")
9572 (description
9573 "The mzR package provides a unified API to the common file formats and
9574 parsers available for mass spectrometry data. It comes with a wrapper for the
9575 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9576 The package contains the original code written by the ISB, and a subset of the
9577 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9578 previously been used in XCMS.")
9579 (license license:artistic2.0)))
9580
9581 (define-public r-affyio
9582 (package
9583 (name "r-affyio")
9584 (version "1.52.0")
9585 (source
9586 (origin
9587 (method url-fetch)
9588 (uri (bioconductor-uri "affyio" version))
9589 (sha256
9590 (base32
9591 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9592 (build-system r-build-system)
9593 (propagated-inputs
9594 `(("r-zlibbioc" ,r-zlibbioc)))
9595 (inputs
9596 `(("zlib" ,zlib)))
9597 (home-page "https://github.com/bmbolstad/affyio")
9598 (synopsis "Tools for parsing Affymetrix data files")
9599 (description
9600 "This package provides routines for parsing Affymetrix data files based
9601 upon file format information. The primary focus is on accessing the CEL and
9602 CDF file formats.")
9603 (license license:lgpl2.0+)))
9604
9605 (define-public r-affy
9606 (package
9607 (name "r-affy")
9608 (version "1.60.0")
9609 (source
9610 (origin
9611 (method url-fetch)
9612 (uri (bioconductor-uri "affy" version))
9613 (sha256
9614 (base32
9615 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9616 (build-system r-build-system)
9617 (propagated-inputs
9618 `(("r-affyio" ,r-affyio)
9619 ("r-biobase" ,r-biobase)
9620 ("r-biocgenerics" ,r-biocgenerics)
9621 ("r-biocmanager" ,r-biocmanager)
9622 ("r-preprocesscore" ,r-preprocesscore)
9623 ("r-zlibbioc" ,r-zlibbioc)))
9624 (inputs
9625 `(("zlib" ,zlib)))
9626 (home-page "https://bioconductor.org/packages/affy")
9627 (synopsis "Methods for affymetrix oligonucleotide arrays")
9628 (description
9629 "This package contains functions for exploratory oligonucleotide array
9630 analysis.")
9631 (license license:lgpl2.0+)))
9632
9633 (define-public r-vsn
9634 (package
9635 (name "r-vsn")
9636 (version "3.50.0")
9637 (source
9638 (origin
9639 (method url-fetch)
9640 (uri (bioconductor-uri "vsn" version))
9641 (sha256
9642 (base32
9643 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9644 (build-system r-build-system)
9645 (propagated-inputs
9646 `(("r-affy" ,r-affy)
9647 ("r-biobase" ,r-biobase)
9648 ("r-ggplot2" ,r-ggplot2)
9649 ("r-lattice" ,r-lattice)
9650 ("r-limma" ,r-limma)))
9651 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9652 (synopsis "Variance stabilization and calibration for microarray data")
9653 (description
9654 "The package implements a method for normalising microarray intensities,
9655 and works for single- and multiple-color arrays. It can also be used for data
9656 from other technologies, as long as they have similar format. The method uses
9657 a robust variant of the maximum-likelihood estimator for an
9658 additive-multiplicative error model and affine calibration. The model
9659 incorporates data calibration step (a.k.a. normalization), a model for the
9660 dependence of the variance on the mean intensity and a variance stabilizing
9661 data transformation. Differences between transformed intensities are
9662 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9663 their variance is independent of the mean, and they are usually more sensitive
9664 and specific in detecting differential transcription.")
9665 (license license:artistic2.0)))
9666
9667 (define-public r-mzid
9668 (package
9669 (name "r-mzid")
9670 (version "1.20.0")
9671 (source
9672 (origin
9673 (method url-fetch)
9674 (uri (bioconductor-uri "mzID" version))
9675 (sha256
9676 (base32
9677 "08jbq223viwknsmsi30hyxyxslvmb0l4wx3vmqlkl6qk4vfmxzjz"))))
9678 (properties `((upstream-name . "mzID")))
9679 (build-system r-build-system)
9680 (propagated-inputs
9681 `(("r-doparallel" ,r-doparallel)
9682 ("r-foreach" ,r-foreach)
9683 ("r-iterators" ,r-iterators)
9684 ("r-plyr" ,r-plyr)
9685 ("r-protgenerics" ,r-protgenerics)
9686 ("r-rcpp" ,r-rcpp)
9687 ("r-xml" ,r-xml)))
9688 (home-page "https://bioconductor.org/packages/mzID")
9689 (synopsis "Parser for mzIdentML files")
9690 (description
9691 "This package provides a parser for mzIdentML files implemented using the
9692 XML package. The parser tries to be general and able to handle all types of
9693 mzIdentML files with the drawback of having less pretty output than a vendor
9694 specific parser.")
9695 (license license:gpl2+)))
9696
9697 (define-public r-pcamethods
9698 (package
9699 (name "r-pcamethods")
9700 (version "1.74.0")
9701 (source
9702 (origin
9703 (method url-fetch)
9704 (uri (bioconductor-uri "pcaMethods" version))
9705 (sha256
9706 (base32
9707 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9708 (properties `((upstream-name . "pcaMethods")))
9709 (build-system r-build-system)
9710 (propagated-inputs
9711 `(("r-biobase" ,r-biobase)
9712 ("r-biocgenerics" ,r-biocgenerics)
9713 ("r-mass" ,r-mass)
9714 ("r-rcpp" ,r-rcpp)))
9715 (home-page "https://github.com/hredestig/pcamethods")
9716 (synopsis "Collection of PCA methods")
9717 (description
9718 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9719 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9720 for missing value estimation is included for comparison. BPCA, PPCA and
9721 NipalsPCA may be used to perform PCA on incomplete data as well as for
9722 accurate missing value estimation. A set of methods for printing and plotting
9723 the results is also provided. All PCA methods make use of the same data
9724 structure (pcaRes) to provide a common interface to the PCA results.")
9725 (license license:gpl3+)))
9726
9727 (define-public r-msnbase
9728 (package
9729 (name "r-msnbase")
9730 (version "2.8.0")
9731 (source
9732 (origin
9733 (method url-fetch)
9734 (uri (bioconductor-uri "MSnbase" version))
9735 (sha256
9736 (base32
9737 "0nnlydpklmv9kwlk3gkjgabx7l6y4gav3imq98w8wskb1fhm50c0"))))
9738 (properties `((upstream-name . "MSnbase")))
9739 (build-system r-build-system)
9740 (propagated-inputs
9741 `(("r-affy" ,r-affy)
9742 ("r-biobase" ,r-biobase)
9743 ("r-biocgenerics" ,r-biocgenerics)
9744 ("r-biocparallel" ,r-biocparallel)
9745 ("r-digest" ,r-digest)
9746 ("r-ggplot2" ,r-ggplot2)
9747 ("r-impute" ,r-impute)
9748 ("r-iranges" ,r-iranges)
9749 ("r-lattice" ,r-lattice)
9750 ("r-maldiquant" ,r-maldiquant)
9751 ("r-mass" ,r-mass)
9752 ("r-mzid" ,r-mzid)
9753 ("r-mzr" ,r-mzr)
9754 ("r-pcamethods" ,r-pcamethods)
9755 ("r-plyr" ,r-plyr)
9756 ("r-preprocesscore" ,r-preprocesscore)
9757 ("r-protgenerics" ,r-protgenerics)
9758 ("r-rcpp" ,r-rcpp)
9759 ("r-s4vectors" ,r-s4vectors)
9760 ("r-scales" ,r-scales)
9761 ("r-vsn" ,r-vsn)
9762 ("r-xml" ,r-xml)))
9763 (home-page "https://github.com/lgatto/MSnbase")
9764 (synopsis "Base functions and classes for MS-based proteomics")
9765 (description
9766 "This package provides basic plotting, data manipulation and processing
9767 of mass spectrometry based proteomics data.")
9768 (license license:artistic2.0)))
9769
9770 (define-public r-msnid
9771 (package
9772 (name "r-msnid")
9773 (version "1.16.0")
9774 (source
9775 (origin
9776 (method url-fetch)
9777 (uri (bioconductor-uri "MSnID" version))
9778 (sha256
9779 (base32
9780 "0hgq4argllhh5hvxqi8vkf1blc3nibsslhx4zsv2mcv4yj75bv4n"))))
9781 (properties `((upstream-name . "MSnID")))
9782 (build-system r-build-system)
9783 (propagated-inputs
9784 `(("r-biobase" ,r-biobase)
9785 ("r-data-table" ,r-data-table)
9786 ("r-doparallel" ,r-doparallel)
9787 ("r-dplyr" ,r-dplyr)
9788 ("r-foreach" ,r-foreach)
9789 ("r-iterators" ,r-iterators)
9790 ("r-msnbase" ,r-msnbase)
9791 ("r-mzid" ,r-mzid)
9792 ("r-mzr" ,r-mzr)
9793 ("r-protgenerics" ,r-protgenerics)
9794 ("r-r-cache" ,r-r-cache)
9795 ("r-rcpp" ,r-rcpp)
9796 ("r-reshape2" ,r-reshape2)))
9797 (home-page "https://bioconductor.org/packages/MSnID")
9798 (synopsis "Utilities for LC-MSn proteomics identifications")
9799 (description
9800 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9801 from mzIdentML (leveraging the mzID package) or text files. After collating
9802 the search results from multiple datasets it assesses their identification
9803 quality and optimize filtering criteria to achieve the maximum number of
9804 identifications while not exceeding a specified false discovery rate. It also
9805 contains a number of utilities to explore the MS/MS results and assess missed
9806 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9807 (license license:artistic2.0)))
9808
9809 (define-public r-seurat
9810 (package
9811 (name "r-seurat")
9812 (version "2.3.4")
9813 (source (origin
9814 (method url-fetch)
9815 (uri (cran-uri "Seurat" version))
9816 (sha256
9817 (base32
9818 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9819 (properties `((upstream-name . "Seurat")))
9820 (build-system r-build-system)
9821 (propagated-inputs
9822 `(("r-ape" ,r-ape)
9823 ("r-cluster" ,r-cluster)
9824 ("r-cowplot" ,r-cowplot)
9825 ("r-dosnow" ,r-dosnow)
9826 ("r-dplyr" ,r-dplyr)
9827 ("r-dtw" ,r-dtw)
9828 ("r-fitdistrplus" ,r-fitdistrplus)
9829 ("r-foreach" ,r-foreach)
9830 ("r-fpc" ,r-fpc)
9831 ("r-ggplot2" ,r-ggplot2)
9832 ("r-ggridges" ,r-ggridges)
9833 ("r-gplots" ,r-gplots)
9834 ("r-hdf5r" ,r-hdf5r)
9835 ("r-hmisc" ,r-hmisc)
9836 ("r-httr" ,r-httr)
9837 ("r-ica" ,r-ica)
9838 ("r-igraph" ,r-igraph)
9839 ("r-irlba" ,r-irlba)
9840 ("r-lars" ,r-lars)
9841 ("r-lmtest" ,r-lmtest)
9842 ("r-mass" ,r-mass)
9843 ("r-matrix" ,r-matrix)
9844 ("r-metap" ,r-metap)
9845 ("r-mixtools" ,r-mixtools)
9846 ("r-pbapply" ,r-pbapply)
9847 ("r-plotly" ,r-plotly)
9848 ("r-png" ,r-png)
9849 ("r-rann" ,r-rann)
9850 ("r-rcolorbrewer" ,r-rcolorbrewer)
9851 ("r-rcpp" ,r-rcpp)
9852 ("r-rcppeigen" ,r-rcppeigen)
9853 ("r-rcppprogress" ,r-rcppprogress)
9854 ("r-reshape2" ,r-reshape2)
9855 ("r-reticulate" ,r-reticulate)
9856 ("r-rocr" ,r-rocr)
9857 ("r-rtsne" ,r-rtsne)
9858 ("r-sdmtools" ,r-sdmtools)
9859 ("r-tidyr" ,r-tidyr)
9860 ("r-tsne" ,r-tsne)))
9861 (home-page "http://www.satijalab.org/seurat")
9862 (synopsis "Seurat is an R toolkit for single cell genomics")
9863 (description
9864 "This package is an R package designed for QC, analysis, and
9865 exploration of single cell RNA-seq data. It easily enables widely-used
9866 analytical techniques, including the identification of highly variable genes,
9867 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9868 algorithms; density clustering, hierarchical clustering, k-means, and the
9869 discovery of differentially expressed genes and markers.")
9870 (license license:gpl3)))
9871
9872 (define-public r-aroma-light
9873 (package
9874 (name "r-aroma-light")
9875 (version "3.12.0")
9876 (source
9877 (origin
9878 (method url-fetch)
9879 (uri (bioconductor-uri "aroma.light" version))
9880 (sha256
9881 (base32
9882 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9883 (properties `((upstream-name . "aroma.light")))
9884 (build-system r-build-system)
9885 (propagated-inputs
9886 `(("r-matrixstats" ,r-matrixstats)
9887 ("r-r-methodss3" ,r-r-methodss3)
9888 ("r-r-oo" ,r-r-oo)
9889 ("r-r-utils" ,r-r-utils)))
9890 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9891 (synopsis "Methods for normalization and visualization of microarray data")
9892 (description
9893 "This package provides methods for microarray analysis that take basic
9894 data types such as matrices and lists of vectors. These methods can be used
9895 standalone, be utilized in other packages, or be wrapped up in higher-level
9896 classes.")
9897 (license license:gpl2+)))
9898
9899 (define-public r-deseq
9900 (package
9901 (name "r-deseq")
9902 (version "1.34.0")
9903 (source
9904 (origin
9905 (method url-fetch)
9906 (uri (bioconductor-uri "DESeq" version))
9907 (sha256
9908 (base32
9909 "1klv1xrh3173srywr6dnq6i7m9djn4gc9aflr1p3a6yjlqcq6fya"))))
9910 (properties `((upstream-name . "DESeq")))
9911 (build-system r-build-system)
9912 (propagated-inputs
9913 `(("r-biobase" ,r-biobase)
9914 ("r-biocgenerics" ,r-biocgenerics)
9915 ("r-genefilter" ,r-genefilter)
9916 ("r-geneplotter" ,r-geneplotter)
9917 ("r-lattice" ,r-lattice)
9918 ("r-locfit" ,r-locfit)
9919 ("r-mass" ,r-mass)
9920 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9921 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9922 (synopsis "Differential gene expression analysis")
9923 (description
9924 "This package provides tools for estimating variance-mean dependence in
9925 count data from high-throughput genetic sequencing assays and for testing for
9926 differential expression based on a model using the negative binomial
9927 distribution.")
9928 (license license:gpl3+)))
9929
9930 (define-public r-edaseq
9931 (package
9932 (name "r-edaseq")
9933 (version "2.16.0")
9934 (source
9935 (origin
9936 (method url-fetch)
9937 (uri (bioconductor-uri "EDASeq" version))
9938 (sha256
9939 (base32
9940 "1gjqzn1kg9qwyz2gwjyy9xzzr1lnc7xd5zwdyvzkadz97gckzxwf"))))
9941 (properties `((upstream-name . "EDASeq")))
9942 (build-system r-build-system)
9943 (propagated-inputs
9944 `(("r-annotationdbi" ,r-annotationdbi)
9945 ("r-aroma-light" ,r-aroma-light)
9946 ("r-biobase" ,r-biobase)
9947 ("r-biocgenerics" ,r-biocgenerics)
9948 ("r-biomart" ,r-biomart)
9949 ("r-biostrings" ,r-biostrings)
9950 ("r-deseq" ,r-deseq)
9951 ("r-genomicfeatures" ,r-genomicfeatures)
9952 ("r-genomicranges" ,r-genomicranges)
9953 ("r-iranges" ,r-iranges)
9954 ("r-rsamtools" ,r-rsamtools)
9955 ("r-shortread" ,r-shortread)))
9956 (home-page "https://github.com/drisso/EDASeq")
9957 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9958 (description
9959 "This package provides support for numerical and graphical summaries of
9960 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9961 adjust for GC-content effect (or other gene-level effects) on read counts:
9962 loess robust local regression, global-scaling, and full-quantile
9963 normalization. Between-lane normalization procedures to adjust for
9964 distributional differences between lanes (e.g., sequencing depth):
9965 global-scaling and full-quantile normalization.")
9966 (license license:artistic2.0)))
9967
9968 (define-public r-interactivedisplaybase
9969 (package
9970 (name "r-interactivedisplaybase")
9971 (version "1.20.0")
9972 (source
9973 (origin
9974 (method url-fetch)
9975 (uri (bioconductor-uri "interactiveDisplayBase" version))
9976 (sha256
9977 (base32
9978 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
9979 (properties
9980 `((upstream-name . "interactiveDisplayBase")))
9981 (build-system r-build-system)
9982 (propagated-inputs
9983 `(("r-biocgenerics" ,r-biocgenerics)
9984 ("r-shiny" ,r-shiny)))
9985 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9986 (synopsis "Base package for web displays of Bioconductor objects")
9987 (description
9988 "This package contains the basic methods needed to generate interactive
9989 Shiny-based display methods for Bioconductor objects.")
9990 (license license:artistic2.0)))
9991
9992 (define-public r-annotationhub
9993 (package
9994 (name "r-annotationhub")
9995 (version "2.14.1")
9996 (source
9997 (origin
9998 (method url-fetch)
9999 (uri (bioconductor-uri "AnnotationHub" version))
10000 (sha256
10001 (base32
10002 "00288x3na0izpmbcvsqac1br1qwry86vwc2slj1l47crdfb7za6c"))))
10003 (properties `((upstream-name . "AnnotationHub")))
10004 (build-system r-build-system)
10005 (propagated-inputs
10006 `(("r-annotationdbi" ,r-annotationdbi)
10007 ("r-biocgenerics" ,r-biocgenerics)
10008 ("r-biocmanager" ,r-biocmanager)
10009 ("r-curl" ,r-curl)
10010 ("r-httr" ,r-httr)
10011 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
10012 ("r-rsqlite" ,r-rsqlite)
10013 ("r-s4vectors" ,r-s4vectors)
10014 ("r-yaml" ,r-yaml)))
10015 (home-page "https://bioconductor.org/packages/AnnotationHub")
10016 (synopsis "Client to access AnnotationHub resources")
10017 (description
10018 "This package provides a client for the Bioconductor AnnotationHub web
10019 resource. The AnnotationHub web resource provides a central location where
10020 genomic files (e.g. VCF, bed, wig) and other resources from standard
10021 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10022 metadata about each resource, e.g., a textual description, tags, and date of
10023 modification. The client creates and manages a local cache of files retrieved
10024 by the user, helping with quick and reproducible access.")
10025 (license license:artistic2.0)))
10026
10027 (define-public r-fastseg
10028 (package
10029 (name "r-fastseg")
10030 (version "1.28.0")
10031 (source
10032 (origin
10033 (method url-fetch)
10034 (uri (bioconductor-uri "fastseg" version))
10035 (sha256
10036 (base32
10037 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
10038 (build-system r-build-system)
10039 (propagated-inputs
10040 `(("r-biobase" ,r-biobase)
10041 ("r-biocgenerics" ,r-biocgenerics)
10042 ("r-genomicranges" ,r-genomicranges)
10043 ("r-iranges" ,r-iranges)
10044 ("r-s4vectors" ,r-s4vectors)))
10045 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
10046 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10047 (description
10048 "Fastseg implements a very fast and efficient segmentation algorithm.
10049 It can segment data from DNA microarrays and data from next generation
10050 sequencing for example to detect copy number segments. Further it can segment
10051 data from RNA microarrays like tiling arrays to identify transcripts. Most
10052 generally, it can segment data given as a matrix or as a vector. Various data
10053 formats can be used as input to fastseg like expression set objects for
10054 microarrays or GRanges for sequencing data.")
10055 (license license:lgpl2.0+)))
10056
10057 (define-public r-keggrest
10058 (package
10059 (name "r-keggrest")
10060 (version "1.22.0")
10061 (source
10062 (origin
10063 (method url-fetch)
10064 (uri (bioconductor-uri "KEGGREST" version))
10065 (sha256
10066 (base32
10067 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
10068 (properties `((upstream-name . "KEGGREST")))
10069 (build-system r-build-system)
10070 (propagated-inputs
10071 `(("r-biostrings" ,r-biostrings)
10072 ("r-httr" ,r-httr)
10073 ("r-png" ,r-png)))
10074 (home-page "https://bioconductor.org/packages/KEGGREST")
10075 (synopsis "Client-side REST access to KEGG")
10076 (description
10077 "This package provides a package that provides a client interface to the
10078 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10079 (license license:artistic2.0)))
10080
10081 (define-public r-gage
10082 (package
10083 (name "r-gage")
10084 (version "2.32.0")
10085 (source
10086 (origin
10087 (method url-fetch)
10088 (uri (bioconductor-uri "gage" version))
10089 (sha256
10090 (base32
10091 "07b098wvryxf0zd423nk6h52s3gyngwjcx2vplqybpbpgl8h2931"))))
10092 (build-system r-build-system)
10093 (propagated-inputs
10094 `(("r-annotationdbi" ,r-annotationdbi)
10095 ("r-graph" ,r-graph)
10096 ("r-keggrest" ,r-keggrest)))
10097 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
10098 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10099 (description
10100 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10101 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10102 data attributes including sample sizes, experimental designs, assay platforms,
10103 and other types of heterogeneity. The gage package provides functions for
10104 basic GAGE analysis, result processing and presentation. In addition, it
10105 provides demo microarray data and commonly used gene set data based on KEGG
10106 pathways and GO terms. These funtions and data are also useful for gene set
10107 analysis using other methods.")
10108 (license license:gpl2+)))
10109
10110 (define-public r-genomicfiles
10111 (package
10112 (name "r-genomicfiles")
10113 (version "1.18.0")
10114 (source
10115 (origin
10116 (method url-fetch)
10117 (uri (bioconductor-uri "GenomicFiles" version))
10118 (sha256
10119 (base32
10120 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
10121 (properties `((upstream-name . "GenomicFiles")))
10122 (build-system r-build-system)
10123 (propagated-inputs
10124 `(("r-biocgenerics" ,r-biocgenerics)
10125 ("r-biocparallel" ,r-biocparallel)
10126 ("r-genomeinfodb" ,r-genomeinfodb)
10127 ("r-genomicalignments" ,r-genomicalignments)
10128 ("r-genomicranges" ,r-genomicranges)
10129 ("r-iranges" ,r-iranges)
10130 ("r-rsamtools" ,r-rsamtools)
10131 ("r-rtracklayer" ,r-rtracklayer)
10132 ("r-s4vectors" ,r-s4vectors)
10133 ("r-summarizedexperiment" ,r-summarizedexperiment)
10134 ("r-variantannotation" ,r-variantannotation)))
10135 (home-page "https://bioconductor.org/packages/GenomicFiles")
10136 (synopsis "Distributed computing by file or by range")
10137 (description
10138 "This package provides infrastructure for parallel computations
10139 distributed by file or by range. User defined mapper and reducer functions
10140 provide added flexibility for data combination and manipulation.")
10141 (license license:artistic2.0)))
10142
10143 (define-public r-complexheatmap
10144 (package
10145 (name "r-complexheatmap")
10146 (version "1.20.0")
10147 (source
10148 (origin
10149 (method url-fetch)
10150 (uri (bioconductor-uri "ComplexHeatmap" version))
10151 (sha256
10152 (base32
10153 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
10154 (properties
10155 `((upstream-name . "ComplexHeatmap")))
10156 (build-system r-build-system)
10157 (propagated-inputs
10158 `(("r-circlize" ,r-circlize)
10159 ("r-colorspace" ,r-colorspace)
10160 ("r-getoptlong" ,r-getoptlong)
10161 ("r-globaloptions" ,r-globaloptions)
10162 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10163 (home-page
10164 "https://github.com/jokergoo/ComplexHeatmap")
10165 (synopsis "Making Complex Heatmaps")
10166 (description
10167 "Complex heatmaps are efficient to visualize associations between
10168 different sources of data sets and reveal potential structures. This package
10169 provides a highly flexible way to arrange multiple heatmaps and supports
10170 self-defined annotation graphics.")
10171 (license license:gpl2+)))
10172
10173 (define-public r-dirichletmultinomial
10174 (package
10175 (name "r-dirichletmultinomial")
10176 (version "1.24.0")
10177 (source
10178 (origin
10179 (method url-fetch)
10180 (uri (bioconductor-uri "DirichletMultinomial" version))
10181 (sha256
10182 (base32
10183 "19bzn0a5jal1xv0ad6wikxc7wrk582hczqamlln0vb2ffwkj1z3f"))))
10184 (properties
10185 `((upstream-name . "DirichletMultinomial")))
10186 (build-system r-build-system)
10187 (inputs
10188 `(("gsl" ,gsl)))
10189 (propagated-inputs
10190 `(("r-biocgenerics" ,r-biocgenerics)
10191 ("r-iranges" ,r-iranges)
10192 ("r-s4vectors" ,r-s4vectors)))
10193 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10194 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10195 (description
10196 "Dirichlet-multinomial mixture models can be used to describe variability
10197 in microbial metagenomic data. This package is an interface to code
10198 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10199 1-15.")
10200 (license license:lgpl3)))
10201
10202 (define-public r-ensembldb
10203 (package
10204 (name "r-ensembldb")
10205 (version "2.6.0")
10206 (source
10207 (origin
10208 (method url-fetch)
10209 (uri (bioconductor-uri "ensembldb" version))
10210 (sha256
10211 (base32
10212 "12jqz9h6w4mxyfr43w5qbwmacn512aw0mnl0zvhsg5i7p4qj45ks"))))
10213 (build-system r-build-system)
10214 (propagated-inputs
10215 `(("r-annotationdbi" ,r-annotationdbi)
10216 ("r-annotationfilter" ,r-annotationfilter)
10217 ("r-biobase" ,r-biobase)
10218 ("r-biocgenerics" ,r-biocgenerics)
10219 ("r-biostrings" ,r-biostrings)
10220 ("r-curl" ,r-curl)
10221 ("r-dbi" ,r-dbi)
10222 ("r-genomeinfodb" ,r-genomeinfodb)
10223 ("r-genomicfeatures" ,r-genomicfeatures)
10224 ("r-genomicranges" ,r-genomicranges)
10225 ("r-iranges" ,r-iranges)
10226 ("r-protgenerics" ,r-protgenerics)
10227 ("r-rsamtools" ,r-rsamtools)
10228 ("r-rsqlite" ,r-rsqlite)
10229 ("r-rtracklayer" ,r-rtracklayer)
10230 ("r-s4vectors" ,r-s4vectors)))
10231 (home-page "https://github.com/jotsetung/ensembldb")
10232 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10233 (description
10234 "The package provides functions to create and use transcript-centric
10235 annotation databases/packages. The annotation for the databases are directly
10236 fetched from Ensembl using their Perl API. The functionality and data is
10237 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10238 but, in addition to retrieve all gene/transcript models and annotations from
10239 the database, the @code{ensembldb} package also provides a filter framework
10240 allowing to retrieve annotations for specific entries like genes encoded on a
10241 chromosome region or transcript models of lincRNA genes.")
10242 ;; No version specified
10243 (license license:lgpl3+)))
10244
10245 (define-public r-organismdbi
10246 (package
10247 (name "r-organismdbi")
10248 (version "1.24.0")
10249 (source
10250 (origin
10251 (method url-fetch)
10252 (uri (bioconductor-uri "OrganismDbi" version))
10253 (sha256
10254 (base32
10255 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
10256 (properties `((upstream-name . "OrganismDbi")))
10257 (build-system r-build-system)
10258 (propagated-inputs
10259 `(("r-annotationdbi" ,r-annotationdbi)
10260 ("r-biobase" ,r-biobase)
10261 ("r-biocgenerics" ,r-biocgenerics)
10262 ("r-biocmanager" ,r-biocmanager)
10263 ("r-dbi" ,r-dbi)
10264 ("r-genomicfeatures" ,r-genomicfeatures)
10265 ("r-genomicranges" ,r-genomicranges)
10266 ("r-graph" ,r-graph)
10267 ("r-iranges" ,r-iranges)
10268 ("r-rbgl" ,r-rbgl)
10269 ("r-s4vectors" ,r-s4vectors)))
10270 (home-page "https://bioconductor.org/packages/OrganismDbi")
10271 (synopsis "Software to enable the smooth interfacing of database packages")
10272 (description "The package enables a simple unified interface to several
10273 annotation packages each of which has its own schema by taking advantage of
10274 the fact that each of these packages implements a select methods.")
10275 (license license:artistic2.0)))
10276
10277 (define-public r-biovizbase
10278 (package
10279 (name "r-biovizbase")
10280 (version "1.30.0")
10281 (source
10282 (origin
10283 (method url-fetch)
10284 (uri (bioconductor-uri "biovizBase" version))
10285 (sha256
10286 (base32
10287 "0v54mcn3rnnfx8dmcrms5z3rgq19n3hp4r23azlgzwq6hjw7cccx"))))
10288 (properties `((upstream-name . "biovizBase")))
10289 (build-system r-build-system)
10290 (propagated-inputs
10291 `(("r-annotationdbi" ,r-annotationdbi)
10292 ("r-annotationfilter" ,r-annotationfilter)
10293 ("r-biocgenerics" ,r-biocgenerics)
10294 ("r-biostrings" ,r-biostrings)
10295 ("r-dichromat" ,r-dichromat)
10296 ("r-ensembldb" ,r-ensembldb)
10297 ("r-genomeinfodb" ,r-genomeinfodb)
10298 ("r-genomicalignments" ,r-genomicalignments)
10299 ("r-genomicfeatures" ,r-genomicfeatures)
10300 ("r-genomicranges" ,r-genomicranges)
10301 ("r-hmisc" ,r-hmisc)
10302 ("r-iranges" ,r-iranges)
10303 ("r-rcolorbrewer" ,r-rcolorbrewer)
10304 ("r-rlang" ,r-rlang)
10305 ("r-rsamtools" ,r-rsamtools)
10306 ("r-s4vectors" ,r-s4vectors)
10307 ("r-scales" ,r-scales)
10308 ("r-summarizedexperiment" ,r-summarizedexperiment)
10309 ("r-variantannotation" ,r-variantannotation)))
10310 (home-page "https://bioconductor.org/packages/biovizBase")
10311 (synopsis "Basic graphic utilities for visualization of genomic data")
10312 (description
10313 "The biovizBase package is designed to provide a set of utilities, color
10314 schemes and conventions for genomic data. It serves as the base for various
10315 high-level packages for biological data visualization. This saves development
10316 effort and encourages consistency.")
10317 (license license:artistic2.0)))
10318
10319 (define-public r-ggbio
10320 (package
10321 (name "r-ggbio")
10322 (version "1.30.0")
10323 (source
10324 (origin
10325 (method url-fetch)
10326 (uri (bioconductor-uri "ggbio" version))
10327 (sha256
10328 (base32
10329 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
10330 (build-system r-build-system)
10331 (propagated-inputs
10332 `(("r-annotationdbi" ,r-annotationdbi)
10333 ("r-annotationfilter" ,r-annotationfilter)
10334 ("r-biobase" ,r-biobase)
10335 ("r-biocgenerics" ,r-biocgenerics)
10336 ("r-biostrings" ,r-biostrings)
10337 ("r-biovizbase" ,r-biovizbase)
10338 ("r-bsgenome" ,r-bsgenome)
10339 ("r-ensembldb" ,r-ensembldb)
10340 ("r-genomeinfodb" ,r-genomeinfodb)
10341 ("r-genomicalignments" ,r-genomicalignments)
10342 ("r-genomicfeatures" ,r-genomicfeatures)
10343 ("r-genomicranges" ,r-genomicranges)
10344 ("r-ggally" ,r-ggally)
10345 ("r-ggplot2" ,r-ggplot2)
10346 ("r-gridextra" ,r-gridextra)
10347 ("r-gtable" ,r-gtable)
10348 ("r-hmisc" ,r-hmisc)
10349 ("r-iranges" ,r-iranges)
10350 ("r-organismdbi" ,r-organismdbi)
10351 ("r-reshape2" ,r-reshape2)
10352 ("r-rlang" ,r-rlang)
10353 ("r-rsamtools" ,r-rsamtools)
10354 ("r-rtracklayer" ,r-rtracklayer)
10355 ("r-s4vectors" ,r-s4vectors)
10356 ("r-scales" ,r-scales)
10357 ("r-summarizedexperiment" ,r-summarizedexperiment)
10358 ("r-variantannotation" ,r-variantannotation)))
10359 (home-page "http://www.tengfei.name/ggbio/")
10360 (synopsis "Visualization tools for genomic data")
10361 (description
10362 "The ggbio package extends and specializes the grammar of graphics for
10363 biological data. The graphics are designed to answer common scientific
10364 questions, in particular those often asked of high throughput genomics data.
10365 All core Bioconductor data structures are supported, where appropriate. The
10366 package supports detailed views of particular genomic regions, as well as
10367 genome-wide overviews. Supported overviews include ideograms and grand linear
10368 views. High-level plots include sequence fragment length, edge-linked
10369 interval to data view, mismatch pileup, and several splicing summaries.")
10370 (license license:artistic2.0)))
10371
10372 (define-public r-gprofiler
10373 (package
10374 (name "r-gprofiler")
10375 (version "0.6.7")
10376 (source
10377 (origin
10378 (method url-fetch)
10379 (uri (cran-uri "gProfileR" version))
10380 (sha256
10381 (base32
10382 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10383 (properties `((upstream-name . "gProfileR")))
10384 (build-system r-build-system)
10385 (propagated-inputs
10386 `(("r-plyr" ,r-plyr)
10387 ("r-rcurl" ,r-rcurl)))
10388 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10389 (synopsis "Interface to the g:Profiler toolkit")
10390 (description
10391 "This package provides tools for functional enrichment analysis,
10392 gene identifier conversion and mapping homologous genes across related
10393 organisms via the @code{g:Profiler} toolkit.")
10394 (license license:gpl2+)))
10395
10396 (define-public r-gqtlbase
10397 (package
10398 (name "r-gqtlbase")
10399 (version "1.14.0")
10400 (source
10401 (origin
10402 (method url-fetch)
10403 (uri (bioconductor-uri "gQTLBase" version))
10404 (sha256
10405 (base32
10406 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10407 (properties `((upstream-name . "gQTLBase")))
10408 (build-system r-build-system)
10409 (propagated-inputs
10410 `(("r-batchjobs" ,r-batchjobs)
10411 ("r-bbmisc" ,r-bbmisc)
10412 ("r-biocgenerics" ,r-biocgenerics)
10413 ("r-bit" ,r-bit)
10414 ("r-doparallel" ,r-doparallel)
10415 ("r-ff" ,r-ff)
10416 ("r-ffbase" ,r-ffbase)
10417 ("r-foreach" ,r-foreach)
10418 ("r-genomicfiles" ,r-genomicfiles)
10419 ("r-genomicranges" ,r-genomicranges)
10420 ("r-rtracklayer" ,r-rtracklayer)
10421 ("r-s4vectors" ,r-s4vectors)
10422 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10423 (home-page "https://bioconductor.org/packages/gQTLBase")
10424 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10425 (description
10426 "The purpose of this package is to simplify the storage and interrogation
10427 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10428 and more.")
10429 (license license:artistic2.0)))
10430
10431 (define-public r-snpstats
10432 (package
10433 (name "r-snpstats")
10434 (version "1.32.0")
10435 (source
10436 (origin
10437 (method url-fetch)
10438 (uri (bioconductor-uri "snpStats" version))
10439 (sha256
10440 (base32
10441 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10442 (properties `((upstream-name . "snpStats")))
10443 (build-system r-build-system)
10444 (inputs `(("zlib" ,zlib)))
10445 (propagated-inputs
10446 `(("r-biocgenerics" ,r-biocgenerics)
10447 ("r-matrix" ,r-matrix)
10448 ("r-survival" ,r-survival)
10449 ("r-zlibbioc" ,r-zlibbioc)))
10450 (home-page "https://bioconductor.org/packages/snpStats")
10451 (synopsis "Methods for SNP association studies")
10452 (description
10453 "This package provides classes and statistical methods for large
10454 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10455 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10456 (license license:gpl3)))
10457
10458 (define-public r-homo-sapiens
10459 (package
10460 (name "r-homo-sapiens")
10461 (version "1.3.1")
10462 (source (origin
10463 (method url-fetch)
10464 ;; We cannot use bioconductor-uri here because this tarball is
10465 ;; located under "data/annotation/" instead of "bioc/".
10466 (uri (string-append "http://www.bioconductor.org/packages/"
10467 "release/data/annotation/src/contrib/"
10468 "Homo.sapiens_"
10469 version ".tar.gz"))
10470 (sha256
10471 (base32
10472 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10473 (properties
10474 `((upstream-name . "Homo.sapiens")))
10475 (build-system r-build-system)
10476 (propagated-inputs
10477 `(("r-genomicfeatures" ,r-genomicfeatures)
10478 ("r-go-db" ,r-go-db)
10479 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10480 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10481 ("r-organismdbi" ,r-organismdbi)
10482 ("r-annotationdbi" ,r-annotationdbi)))
10483 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10484 (synopsis "Annotation package for the Homo.sapiens object")
10485 (description
10486 "This package contains the Homo.sapiens object to access data from
10487 several related annotation packages.")
10488 (license license:artistic2.0)))
10489
10490 (define-public r-erma
10491 (package
10492 (name "r-erma")
10493 (version "0.14.0")
10494 (source
10495 (origin
10496 (method url-fetch)
10497 (uri (bioconductor-uri "erma" version))
10498 (sha256
10499 (base32
10500 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10501 (build-system r-build-system)
10502 (propagated-inputs
10503 `(("r-annotationdbi" ,r-annotationdbi)
10504 ("r-biobase" ,r-biobase)
10505 ("r-biocgenerics" ,r-biocgenerics)
10506 ("r-biocparallel" ,r-biocparallel)
10507 ("r-genomeinfodb" ,r-genomeinfodb)
10508 ("r-genomicfiles" ,r-genomicfiles)
10509 ("r-genomicranges" ,r-genomicranges)
10510 ("r-ggplot2" ,r-ggplot2)
10511 ("r-homo-sapiens" ,r-homo-sapiens)
10512 ("r-iranges" ,r-iranges)
10513 ("r-rtracklayer" ,r-rtracklayer)
10514 ("r-s4vectors" ,r-s4vectors)
10515 ("r-shiny" ,r-shiny)
10516 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10517 (home-page "https://bioconductor.org/packages/erma")
10518 (synopsis "Epigenomic road map adventures")
10519 (description
10520 "The epigenomics road map describes locations of epigenetic marks in DNA
10521 from a variety of cell types. Of interest are locations of histone
10522 modifications, sites of DNA methylation, and regions of accessible chromatin.
10523 This package presents a selection of elements of the road map including
10524 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10525 by Ernst and Kellis.")
10526 (license license:artistic2.0)))
10527
10528 (define-public r-ldblock
10529 (package
10530 (name "r-ldblock")
10531 (version "1.12.0")
10532 (source
10533 (origin
10534 (method url-fetch)
10535 (uri (bioconductor-uri "ldblock" version))
10536 (sha256
10537 (base32
10538 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10539 (build-system r-build-system)
10540 (propagated-inputs
10541 `(("r-biocgenerics" ,r-biocgenerics)
10542 ("r-erma" ,r-erma)
10543 ("r-genomeinfodb" ,r-genomeinfodb)
10544 ("r-genomicfiles" ,r-genomicfiles)
10545 ("r-go-db" ,r-go-db)
10546 ("r-homo-sapiens" ,r-homo-sapiens)
10547 ("r-matrix" ,r-matrix)
10548 ("r-rsamtools" ,r-rsamtools)
10549 ("r-snpstats" ,r-snpstats)
10550 ("r-variantannotation" ,r-variantannotation)))
10551 (home-page "https://bioconductor.org/packages/ldblock")
10552 (synopsis "Data structures for linkage disequilibrium measures in populations")
10553 (description
10554 "This package defines data structures for @dfn{linkage
10555 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10556 handling of existing population-level data for the purpose of flexibly
10557 defining LD blocks.")
10558 (license license:artistic2.0)))
10559
10560 (define-public r-gqtlstats
10561 (package
10562 (name "r-gqtlstats")
10563 (version "1.14.0")
10564 (source
10565 (origin
10566 (method url-fetch)
10567 (uri (bioconductor-uri "gQTLstats" version))
10568 (sha256
10569 (base32
10570 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10571 (properties `((upstream-name . "gQTLstats")))
10572 (build-system r-build-system)
10573 (propagated-inputs
10574 `(("r-annotationdbi" ,r-annotationdbi)
10575 ("r-batchjobs" ,r-batchjobs)
10576 ("r-bbmisc" ,r-bbmisc)
10577 ("r-beeswarm" ,r-beeswarm)
10578 ("r-biobase" ,r-biobase)
10579 ("r-biocgenerics" ,r-biocgenerics)
10580 ("r-doparallel" ,r-doparallel)
10581 ("r-dplyr" ,r-dplyr)
10582 ("r-erma" ,r-erma)
10583 ("r-ffbase" ,r-ffbase)
10584 ("r-foreach" ,r-foreach)
10585 ("r-genomeinfodb" ,r-genomeinfodb)
10586 ("r-genomicfeatures" ,r-genomicfeatures)
10587 ("r-genomicfiles" ,r-genomicfiles)
10588 ("r-genomicranges" ,r-genomicranges)
10589 ("r-ggbeeswarm" ,r-ggbeeswarm)
10590 ("r-ggplot2" ,r-ggplot2)
10591 ("r-gqtlbase" ,r-gqtlbase)
10592 ("r-hardyweinberg" ,r-hardyweinberg)
10593 ("r-homo-sapiens" ,r-homo-sapiens)
10594 ("r-iranges" ,r-iranges)
10595 ("r-limma" ,r-limma)
10596 ("r-mgcv" ,r-mgcv)
10597 ("r-plotly" ,r-plotly)
10598 ("r-reshape2" ,r-reshape2)
10599 ("r-s4vectors" ,r-s4vectors)
10600 ("r-shiny" ,r-shiny)
10601 ("r-snpstats" ,r-snpstats)
10602 ("r-summarizedexperiment" ,r-summarizedexperiment)
10603 ("r-variantannotation" ,r-variantannotation)))
10604 (home-page "https://bioconductor.org/packages/gQTLstats")
10605 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10606 (description
10607 "This package provides tools for the computationally efficient analysis
10608 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10609 The software in this package aims to support refinements and functional
10610 interpretation of members of a collection of association statistics on a
10611 family of feature/genome hypotheses.")
10612 (license license:artistic2.0)))
10613
10614 (define-public r-gviz
10615 (package
10616 (name "r-gviz")
10617 (version "1.26.0")
10618 (source
10619 (origin
10620 (method url-fetch)
10621 (uri (bioconductor-uri "Gviz" version))
10622 (sha256
10623 (base32
10624 "05zk9hf30afg6rjg97lzn5v8xij90v8zm09y9vcz0asmc3c8xs0a"))))
10625 (properties `((upstream-name . "Gviz")))
10626 (build-system r-build-system)
10627 (propagated-inputs
10628 `(("r-annotationdbi" ,r-annotationdbi)
10629 ("r-biobase" ,r-biobase)
10630 ("r-biocgenerics" ,r-biocgenerics)
10631 ("r-biomart" ,r-biomart)
10632 ("r-biostrings" ,r-biostrings)
10633 ("r-biovizbase" ,r-biovizbase)
10634 ("r-bsgenome" ,r-bsgenome)
10635 ("r-digest" ,r-digest)
10636 ("r-genomeinfodb" ,r-genomeinfodb)
10637 ("r-genomicalignments" ,r-genomicalignments)
10638 ("r-genomicfeatures" ,r-genomicfeatures)
10639 ("r-genomicranges" ,r-genomicranges)
10640 ("r-iranges" ,r-iranges)
10641 ("r-lattice" ,r-lattice)
10642 ("r-latticeextra" ,r-latticeextra)
10643 ("r-matrixstats" ,r-matrixstats)
10644 ("r-rcolorbrewer" ,r-rcolorbrewer)
10645 ("r-rsamtools" ,r-rsamtools)
10646 ("r-rtracklayer" ,r-rtracklayer)
10647 ("r-s4vectors" ,r-s4vectors)
10648 ("r-xvector" ,r-xvector)))
10649 (home-page "https://bioconductor.org/packages/Gviz")
10650 (synopsis "Plotting data and annotation information along genomic coordinates")
10651 (description
10652 "Genomic data analyses requires integrated visualization of known genomic
10653 information and new experimental data. Gviz uses the biomaRt and the
10654 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10655 and translates this to e.g. gene/transcript structures in viewports of the
10656 grid graphics package. This results in genomic information plotted together
10657 with your data.")
10658 (license license:artistic2.0)))
10659
10660 (define-public r-gwascat
10661 (package
10662 (name "r-gwascat")
10663 (version "2.14.0")
10664 (source
10665 (origin
10666 (method url-fetch)
10667 (uri (bioconductor-uri "gwascat" version))
10668 (sha256
10669 (base32
10670 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10671 (build-system r-build-system)
10672 (propagated-inputs
10673 `(("r-annotationdbi" ,r-annotationdbi)
10674 ("r-annotationhub" ,r-annotationhub)
10675 ("r-biocgenerics" ,r-biocgenerics)
10676 ("r-biostrings" ,r-biostrings)
10677 ("r-genomeinfodb" ,r-genomeinfodb)
10678 ("r-genomicfeatures" ,r-genomicfeatures)
10679 ("r-genomicranges" ,r-genomicranges)
10680 ("r-ggbio" ,r-ggbio)
10681 ("r-ggplot2" ,r-ggplot2)
10682 ("r-gqtlstats" ,r-gqtlstats)
10683 ("r-graph" ,r-graph)
10684 ("r-gviz" ,r-gviz)
10685 ("r-homo-sapiens" ,r-homo-sapiens)
10686 ("r-iranges" ,r-iranges)
10687 ("r-rsamtools" ,r-rsamtools)
10688 ("r-rtracklayer" ,r-rtracklayer)
10689 ("r-s4vectors" ,r-s4vectors)
10690 ("r-snpstats" ,r-snpstats)
10691 ("r-summarizedexperiment" ,r-summarizedexperiment)
10692 ("r-variantannotation" ,r-variantannotation)))
10693 (home-page "https://bioconductor.org/packages/gwascat")
10694 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10695 (description
10696 "This package provides tools for representing and modeling data in the
10697 EMBL-EBI GWAS catalog.")
10698 (license license:artistic2.0)))
10699
10700 (define-public r-sushi
10701 (package
10702 (name "r-sushi")
10703 (version "1.20.0")
10704 (source (origin
10705 (method url-fetch)
10706 (uri (bioconductor-uri "Sushi" version))
10707 (sha256
10708 (base32
10709 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10710 (properties `((upstream-name . "Sushi")))
10711 (build-system r-build-system)
10712 (propagated-inputs
10713 `(("r-biomart" ,r-biomart)
10714 ("r-zoo" ,r-zoo)))
10715 (home-page "https://bioconductor.org/packages/Sushi")
10716 (synopsis "Tools for visualizing genomics data")
10717 (description
10718 "This package provides flexible, quantitative, and integrative genomic
10719 visualizations for publication-quality multi-panel figures.")
10720 (license license:gpl2+)))
10721
10722 (define-public r-fithic
10723 (package
10724 (name "r-fithic")
10725 (version "1.8.0")
10726 (source (origin
10727 (method url-fetch)
10728 (uri (bioconductor-uri "FitHiC" version))
10729 (sha256
10730 (base32
10731 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10732 (properties `((upstream-name . "FitHiC")))
10733 (build-system r-build-system)
10734 (propagated-inputs
10735 `(("r-data-table" ,r-data-table)
10736 ("r-fdrtool" ,r-fdrtool)
10737 ("r-rcpp" ,r-rcpp)))
10738 (home-page "https://bioconductor.org/packages/FitHiC")
10739 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10740 (description
10741 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10742 intra-chromosomal contact maps produced by genome-wide genome architecture
10743 assays such as Hi-C.")
10744 (license license:gpl2+)))
10745
10746 (define-public r-hitc
10747 (package
10748 (name "r-hitc")
10749 (version "1.26.0")
10750 (source (origin
10751 (method url-fetch)
10752 (uri (bioconductor-uri "HiTC" version))
10753 (sha256
10754 (base32
10755 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10756 (properties `((upstream-name . "HiTC")))
10757 (build-system r-build-system)
10758 (propagated-inputs
10759 `(("r-biostrings" ,r-biostrings)
10760 ("r-genomeinfodb" ,r-genomeinfodb)
10761 ("r-genomicranges" ,r-genomicranges)
10762 ("r-iranges" ,r-iranges)
10763 ("r-matrix" ,r-matrix)
10764 ("r-rcolorbrewer" ,r-rcolorbrewer)
10765 ("r-rtracklayer" ,r-rtracklayer)))
10766 (home-page "https://bioconductor.org/packages/HiTC")
10767 (synopsis "High throughput chromosome conformation capture analysis")
10768 (description
10769 "The HiTC package was developed to explore high-throughput \"C\" data
10770 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10771 quality controls, normalization, visualization, and further analysis are also
10772 provided.")
10773 (license license:artistic2.0)))
10774
10775 (define-public r-qvalue
10776 (package
10777 (name "r-qvalue")
10778 (version "2.14.0")
10779 (source
10780 (origin
10781 (method url-fetch)
10782 (uri (bioconductor-uri "qvalue" version))
10783 (sha256
10784 (base32
10785 "03qxshqwwq1rj23p6pjrz08jm3ziikvy9badi4mz2rcwy2nz783a"))))
10786 (build-system r-build-system)
10787 (propagated-inputs
10788 `(("r-ggplot2" ,r-ggplot2)
10789 ("r-reshape2" ,r-reshape2)))
10790 (home-page "http://github.com/jdstorey/qvalue")
10791 (synopsis "Q-value estimation for false discovery rate control")
10792 (description
10793 "This package takes a list of p-values resulting from the simultaneous
10794 testing of many hypotheses and estimates their q-values and local @dfn{false
10795 discovery rate} (FDR) values. The q-value of a test measures the proportion
10796 of false positives incurred when that particular test is called significant.
10797 The local FDR measures the posterior probability the null hypothesis is true
10798 given the test's p-value. Various plots are automatically generated, allowing
10799 one to make sensible significance cut-offs. The software can be applied to
10800 problems in genomics, brain imaging, astrophysics, and data mining.")
10801 ;; Any version of the LGPL.
10802 (license license:lgpl3+)))
10803
10804 (define-public r-hdf5array
10805 (package
10806 (name "r-hdf5array")
10807 (version "1.10.0")
10808 (source
10809 (origin
10810 (method url-fetch)
10811 (uri (bioconductor-uri "HDF5Array" version))
10812 (sha256
10813 (base32
10814 "1w7ad8cfsbh5xx82m3l4lc0vbmj9lcsqxxpiy3ana2ycgn1bqv3g"))))
10815 (properties `((upstream-name . "HDF5Array")))
10816 (build-system r-build-system)
10817 (propagated-inputs
10818 `(("r-biocgenerics" ,r-biocgenerics)
10819 ("r-delayedarray" ,r-delayedarray)
10820 ("r-iranges" ,r-iranges)
10821 ("r-rhdf5" ,r-rhdf5)
10822 ("r-s4vectors" ,r-s4vectors)))
10823 (home-page "https://bioconductor.org/packages/HDF5Array")
10824 (synopsis "HDF5 back end for DelayedArray objects")
10825 (description "This package provides an array-like container for convenient
10826 access and manipulation of HDF5 datasets. It supports delayed operations and
10827 block processing.")
10828 (license license:artistic2.0)))
10829
10830 (define-public r-rhdf5lib
10831 (package
10832 (name "r-rhdf5lib")
10833 (version "1.4.0")
10834 (source
10835 (origin
10836 (method url-fetch)
10837 (uri (bioconductor-uri "Rhdf5lib" version))
10838 (sha256
10839 (base32
10840 "01gpz780g850ql20b2ql6pvr678ydk4nq4sn5iiih94a4crb9lz1"))
10841 (modules '((guix build utils)))
10842 (snippet
10843 '(begin
10844 ;; Delete bundled binaries
10845 (delete-file-recursively "src/winlib/")
10846 #t))))
10847 (properties `((upstream-name . "Rhdf5lib")))
10848 (build-system r-build-system)
10849 (arguments
10850 `(#:phases
10851 (modify-phases %standard-phases
10852 (add-after 'unpack 'do-not-use-bundled-hdf5
10853 (lambda* (#:key inputs #:allow-other-keys)
10854 (for-each delete-file '("configure" "configure.ac"))
10855 ;; Do not make other packages link with the proprietary libsz.
10856 (substitute* "R/zzz.R"
10857 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10858 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10859 (("'%s/libhdf5.a %s/libsz.a -lz'")
10860 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10861 (with-directory-excursion "src"
10862 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10863 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10864 "hdf5")
10865 ;; Remove timestamp and host system information to make
10866 ;; the build reproducible.
10867 (substitute* "hdf5/src/libhdf5.settings.in"
10868 (("Configured on: @CONFIG_DATE@")
10869 "Configured on: Guix")
10870 (("Uname information:.*")
10871 "Uname information: Linux\n")
10872 ;; Remove unnecessary store reference.
10873 (("C Compiler:.*")
10874 "C Compiler: GCC\n"))
10875 (rename-file "Makevars.in" "Makevars")
10876 (substitute* "Makevars"
10877 (("HDF5_CXX_LIB=.*")
10878 (string-append "HDF5_CXX_LIB="
10879 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10880 (("HDF5_LIB=.*")
10881 (string-append "HDF5_LIB="
10882 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10883 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10884 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10885 ;; szip is non-free software
10886 (("cp \\$\\{SZIP_LIB\\}.*") "")
10887 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10888 #t)))))
10889 (inputs
10890 `(("zlib" ,zlib)))
10891 (propagated-inputs
10892 `(("hdf5" ,hdf5-1.10)))
10893 (native-inputs
10894 `(("hdf5-source" ,(package-source hdf5-1.10))))
10895 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10896 (synopsis "HDF5 library as an R package")
10897 (description "This package provides C and C++ HDF5 libraries for use in R
10898 packages.")
10899 (license license:artistic2.0)))
10900
10901 (define-public r-beachmat
10902 (package
10903 (name "r-beachmat")
10904 (version "1.4.0")
10905 (source
10906 (origin
10907 (method url-fetch)
10908 (uri (bioconductor-uri "beachmat" version))
10909 (sha256
10910 (base32
10911 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10912 (build-system r-build-system)
10913 (inputs
10914 `(("hdf5" ,hdf5)
10915 ("zlib" ,zlib)))
10916 (propagated-inputs
10917 `(("r-biocgenerics" ,r-biocgenerics)
10918 ("r-delayedarray" ,r-delayedarray)
10919 ("r-hdf5array" ,r-hdf5array)
10920 ("r-rcpp" ,r-rcpp)
10921 ("r-rhdf5" ,r-rhdf5)
10922 ("r-rhdf5lib" ,r-rhdf5lib)))
10923 (home-page "https://bioconductor.org/packages/beachmat")
10924 (synopsis "Compiling Bioconductor to handle each matrix type")
10925 (description "This package provides a consistent C++ class interface for a
10926 variety of commonly used matrix types, including sparse and HDF5-backed
10927 matrices.")
10928 (license license:gpl3)))
10929
10930 (define-public r-singlecellexperiment
10931 (package
10932 (name "r-singlecellexperiment")
10933 (version "1.4.0")
10934 (source
10935 (origin
10936 (method url-fetch)
10937 (uri (bioconductor-uri "SingleCellExperiment" version))
10938 (sha256
10939 (base32
10940 "19r4r7djrn46qlijkj1g926vcklxzcrxjlxv6cg43m9j9jgfs3dj"))))
10941 (properties
10942 `((upstream-name . "SingleCellExperiment")))
10943 (build-system r-build-system)
10944 (propagated-inputs
10945 `(("r-biocgenerics" ,r-biocgenerics)
10946 ("r-s4vectors" ,r-s4vectors)
10947 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10948 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10949 (synopsis "S4 classes for single cell data")
10950 (description "This package defines an S4 class for storing data from
10951 single-cell experiments. This includes specialized methods to store and
10952 retrieve spike-in information, dimensionality reduction coordinates and size
10953 factors for each cell, along with the usual metadata for genes and
10954 libraries.")
10955 (license license:gpl3)))
10956
10957 (define-public r-scater
10958 (package
10959 (name "r-scater")
10960 (version "1.10.0")
10961 (source (origin
10962 (method url-fetch)
10963 (uri (bioconductor-uri "scater" version))
10964 (sha256
10965 (base32
10966 "1kwa9n70c5j0xcj6nkmlkzjr63cnj78mp8nhg58n07fq1ijm4ns3"))))
10967 (build-system r-build-system)
10968 (propagated-inputs
10969 `(("r-beachmat" ,r-beachmat)
10970 ("r-biocgenerics" ,r-biocgenerics)
10971 ("r-biocparallel" ,r-biocparallel)
10972 ("r-delayedarray" ,r-delayedarray)
10973 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10974 ("r-dplyr" ,r-dplyr)
10975 ("r-ggbeeswarm" ,r-ggbeeswarm)
10976 ("r-ggplot2" ,r-ggplot2)
10977 ("r-matrix" ,r-matrix)
10978 ("r-plyr" ,r-plyr)
10979 ("r-rcpp" ,r-rcpp)
10980 ("r-reshape2" ,r-reshape2)
10981 ("r-rhdf5lib" ,r-rhdf5lib)
10982 ("r-s4vectors" ,r-s4vectors)
10983 ("r-singlecellexperiment" ,r-singlecellexperiment)
10984 ("r-summarizedexperiment" ,r-summarizedexperiment)
10985 ("r-viridis" ,r-viridis)))
10986 (home-page "https://github.com/davismcc/scater")
10987 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10988 (description "This package provides a collection of tools for doing
10989 various analyses of single-cell RNA-seq gene expression data, with a focus on
10990 quality control.")
10991 (license license:gpl2+)))
10992
10993 (define-public r-scran
10994 (package
10995 (name "r-scran")
10996 (version "1.10.1")
10997 (source
10998 (origin
10999 (method url-fetch)
11000 (uri (bioconductor-uri "scran" version))
11001 (sha256
11002 (base32
11003 "1viyzrwfm9vccsf54c6g7k1dn7skkfx4ml1jy12q67wa20sx8l03"))))
11004 (build-system r-build-system)
11005 (propagated-inputs
11006 `(("r-beachmat" ,r-beachmat)
11007 ("r-biocgenerics" ,r-biocgenerics)
11008 ("r-biocneighbors" ,r-biocneighbors)
11009 ("r-biocparallel" ,r-biocparallel)
11010 ("r-delayedarray" ,r-delayedarray)
11011 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11012 ("r-dynamictreecut" ,r-dynamictreecut)
11013 ("r-edger" ,r-edger)
11014 ("r-igraph" ,r-igraph)
11015 ("r-limma" ,r-limma)
11016 ("r-matrix" ,r-matrix)
11017 ("r-rcpp" ,r-rcpp)
11018 ("r-rhdf5lib" ,r-rhdf5lib)
11019 ("r-s4vectors" ,r-s4vectors)
11020 ("r-scater" ,r-scater)
11021 ("r-singlecellexperiment" ,r-singlecellexperiment)
11022 ("r-statmod" ,r-statmod)
11023 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11024 (home-page "https://bioconductor.org/packages/scran")
11025 (synopsis "Methods for single-cell RNA-Seq data analysis")
11026 (description "This package implements a variety of low-level analyses of
11027 single-cell RNA-seq data. Methods are provided for normalization of
11028 cell-specific biases, assignment of cell cycle phase, and detection of highly
11029 variable and significantly correlated genes.")
11030 (license license:gpl3)))
11031
11032 (define-public r-delayedmatrixstats
11033 (package
11034 (name "r-delayedmatrixstats")
11035 (version "1.4.0")
11036 (source
11037 (origin
11038 (method url-fetch)
11039 (uri (bioconductor-uri "DelayedMatrixStats" version))
11040 (sha256
11041 (base32
11042 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
11043 (properties
11044 `((upstream-name . "DelayedMatrixStats")))
11045 (build-system r-build-system)
11046 (propagated-inputs
11047 `(("r-biocparallel" ,r-biocparallel)
11048 ("r-delayedarray" ,r-delayedarray)
11049 ("r-hdf5array" ,r-hdf5array)
11050 ("r-iranges" ,r-iranges)
11051 ("r-matrix" ,r-matrix)
11052 ("r-matrixstats" ,r-matrixstats)
11053 ("r-s4vectors" ,r-s4vectors)))
11054 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11055 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11056 (description
11057 "This package provides a port of the @code{matrixStats} API for use with
11058 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11059 contains high-performing functions operating on rows and columns of
11060 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11061 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11062 are optimized per data type and for subsetted calculations such that both
11063 memory usage and processing time is minimized.")
11064 (license license:expat)))
11065
11066 (define-public r-phangorn
11067 (package
11068 (name "r-phangorn")
11069 (version "2.4.0")
11070 (source
11071 (origin
11072 (method url-fetch)
11073 (uri (cran-uri "phangorn" version))
11074 (sha256
11075 (base32
11076 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
11077 (build-system r-build-system)
11078 (propagated-inputs
11079 `(("r-ape" ,r-ape)
11080 ("r-fastmatch" ,r-fastmatch)
11081 ("r-igraph" ,r-igraph)
11082 ("r-magrittr" ,r-magrittr)
11083 ("r-matrix" ,r-matrix)
11084 ("r-quadprog" ,r-quadprog)
11085 ("r-rcpp" ,r-rcpp)))
11086 (home-page "https://github.com/KlausVigo/phangorn")
11087 (synopsis "Phylogenetic analysis in R")
11088 (description
11089 "Phangorn is a package for phylogenetic analysis in R. It supports
11090 estimation of phylogenetic trees and networks using Maximum Likelihood,
11091 Maximum Parsimony, distance methods and Hadamard conjugation.")
11092 (license license:gpl2+)))
11093
11094 (define-public r-dropbead
11095 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11096 (revision "2"))
11097 (package
11098 (name "r-dropbead")
11099 (version (string-append "0-" revision "." (string-take commit 7)))
11100 (source
11101 (origin
11102 (method git-fetch)
11103 (uri (git-reference
11104 (url "https://github.com/rajewsky-lab/dropbead.git")
11105 (commit commit)))
11106 (file-name (git-file-name name version))
11107 (sha256
11108 (base32
11109 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11110 (build-system r-build-system)
11111 (propagated-inputs
11112 `(("r-ggplot2" ,r-ggplot2)
11113 ("r-rcolorbrewer" ,r-rcolorbrewer)
11114 ("r-gridextra" ,r-gridextra)
11115 ("r-gplots" ,r-gplots)
11116 ("r-plyr" ,r-plyr)))
11117 (home-page "https://github.com/rajewsky-lab/dropbead")
11118 (synopsis "Basic exploration and analysis of Drop-seq data")
11119 (description "This package offers a quick and straight-forward way to
11120 explore and perform basic analysis of single cell sequencing data coming from
11121 droplet sequencing. It has been particularly tailored for Drop-seq.")
11122 (license license:gpl3))))
11123
11124 (define htslib-for-sambamba
11125 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11126 (package
11127 (inherit htslib)
11128 (name "htslib-for-sambamba")
11129 (version (string-append "1.3.1-1." (string-take commit 9)))
11130 (source
11131 (origin
11132 (method git-fetch)
11133 (uri (git-reference
11134 (url "https://github.com/lomereiter/htslib.git")
11135 (commit commit)))
11136 (file-name (string-append "htslib-" version "-checkout"))
11137 (sha256
11138 (base32
11139 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11140 (native-inputs
11141 `(("autoconf" ,autoconf)
11142 ("automake" ,automake)
11143 ,@(package-native-inputs htslib))))))
11144
11145 (define-public sambamba
11146 (package
11147 (name "sambamba")
11148 (version "0.6.7-10-g223fa20")
11149 (source
11150 (origin
11151 (method git-fetch)
11152 (uri (git-reference
11153 (url "https://github.com/lomereiter/sambamba.git")
11154 (commit (string-append "v" version))))
11155 (file-name (string-append name "-" version "-checkout"))
11156 (sha256
11157 (base32
11158 "1zb9hrxglxqh13ava9wwri30cvf85hjnbn8ccnr8l60a3k5avczn"))))
11159 (build-system gnu-build-system)
11160 (arguments
11161 `(#:tests? #f ; there is no test target
11162 #:parallel-build? #f ; not supported
11163 #:phases
11164 (modify-phases %standard-phases
11165 (delete 'configure)
11166 (add-after 'unpack 'fix-ldc-version
11167 (lambda _
11168 (substitute* "gen_ldc_version_info.py"
11169 (("/usr/bin/env.*") (which "python")))
11170 (substitute* "Makefile"
11171 (("\\$\\(shell which ldmd2\\)") (which "ldmd2")))
11172 #t))
11173 (add-after 'unpack 'place-biod-and-undead
11174 (lambda* (#:key inputs #:allow-other-keys)
11175 (copy-recursively (assoc-ref inputs "biod") "BioD")
11176 (copy-recursively (assoc-ref inputs "undead") "undeaD")
11177 #t))
11178 (add-after 'unpack 'unbundle-prerequisites
11179 (lambda _
11180 (substitute* "Makefile"
11181 (("htslib/libhts.a lz4/lib/liblz4.a")
11182 "-L-lhts -L-llz4")
11183 ((" htslib-static lz4-static") ""))
11184 #t))
11185 (replace 'install
11186 (lambda* (#:key outputs #:allow-other-keys)
11187 (let* ((out (assoc-ref outputs "out"))
11188 (bin (string-append out "/bin")))
11189 (mkdir-p bin)
11190 (install-file "build/sambamba" bin)
11191 #t))))))
11192 (native-inputs
11193 `(("ldc" ,ldc)
11194 ("rdmd" ,rdmd)
11195 ("python" ,python2-minimal)
11196 ("biod"
11197 ,(let ((commit "c778e4f2d8bacea7499283ce39f5577b232732c6"))
11198 (origin
11199 (method git-fetch)
11200 (uri (git-reference
11201 (url "https://github.com/biod/BioD.git")
11202 (commit commit)))
11203 (file-name (string-append "biod-"
11204 (string-take commit 9)
11205 "-checkout"))
11206 (sha256
11207 (base32
11208 "1z90562hg47i63gx042wb3ak2vqjg5z7hwgn9bp2pdxfg3nxrw37")))))
11209 ("undead"
11210 ,(let ((commit "92803d25c88657e945511f0976a0c79d8da46e89"))
11211 (origin
11212 (method git-fetch)
11213 (uri (git-reference
11214 (url "https://github.com/dlang/undeaD.git")
11215 (commit commit)))
11216 (file-name (string-append "undead-"
11217 (string-take commit 9)
11218 "-checkout"))
11219 (sha256
11220 (base32
11221 "0vq6n81vzqvgphjw54lz2isc1j8lcxwjdbrhqz1h5gwrvw9w5138")))))))
11222 (inputs
11223 `(("lz4" ,lz4)
11224 ("htslib" ,htslib-for-sambamba)))
11225 (home-page "http://lomereiter.github.io/sambamba")
11226 (synopsis "Tools for working with SAM/BAM data")
11227 (description "Sambamba is a high performance modern robust and
11228 fast tool (and library), written in the D programming language, for
11229 working with SAM and BAM files. Current parallelised functionality is
11230 an important subset of samtools functionality, including view, index,
11231 sort, markdup, and depth.")
11232 (license license:gpl2+)))
11233
11234 (define-public ritornello
11235 (package
11236 (name "ritornello")
11237 (version "1.0.0")
11238 (source (origin
11239 (method url-fetch)
11240 (uri (string-append "https://github.com/KlugerLab/"
11241 "Ritornello/archive/v"
11242 version ".tar.gz"))
11243 (file-name (string-append name "-" version ".tar.gz"))
11244 (sha256
11245 (base32
11246 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
11247 (build-system gnu-build-system)
11248 (arguments
11249 `(#:tests? #f ; there are no tests
11250 #:phases
11251 (modify-phases %standard-phases
11252 (add-after 'unpack 'patch-samtools-references
11253 (lambda* (#:key inputs #:allow-other-keys)
11254 (substitute* '("src/SamStream.h"
11255 "src/BufferedGenomeReader.h")
11256 (("<sam.h>") "<samtools/sam.h>"))
11257 #t))
11258 (delete 'configure)
11259 (replace 'install
11260 (lambda* (#:key inputs outputs #:allow-other-keys)
11261 (let* ((out (assoc-ref outputs "out"))
11262 (bin (string-append out "/bin/")))
11263 (mkdir-p bin)
11264 (install-file "bin/Ritornello" bin)
11265 #t))))))
11266 (inputs
11267 `(("samtools" ,samtools-0.1)
11268 ("fftw" ,fftw)
11269 ("boost" ,boost)
11270 ("zlib" ,zlib)))
11271 (home-page "https://github.com/KlugerLab/Ritornello")
11272 (synopsis "Control-free peak caller for ChIP-seq data")
11273 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11274 signal processing that can accurately call binding events without the need to
11275 do a pair total DNA input or IgG control sample. It has been tested for use
11276 with narrow binding events such as transcription factor ChIP-seq.")
11277 (license license:gpl3+)))
11278
11279 (define-public trim-galore
11280 (package
11281 (name "trim-galore")
11282 (version "0.4.5")
11283 (source
11284 (origin
11285 (method git-fetch)
11286 (uri (git-reference
11287 (url "https://github.com/FelixKrueger/TrimGalore.git")
11288 (commit version)))
11289 (file-name (string-append name "-" version "-checkout"))
11290 (sha256
11291 (base32
11292 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11293 (build-system gnu-build-system)
11294 (arguments
11295 `(#:tests? #f ; no tests
11296 #:phases
11297 (modify-phases %standard-phases
11298 (delete 'configure)
11299 (delete 'build)
11300 (add-after 'unpack 'hardcode-tool-references
11301 (lambda* (#:key inputs #:allow-other-keys)
11302 (substitute* "trim_galore"
11303 (("\\$path_to_cutadapt = 'cutadapt'")
11304 (string-append "$path_to_cutadapt = '"
11305 (assoc-ref inputs "cutadapt")
11306 "/bin/cutadapt'"))
11307 (("\\| gzip")
11308 (string-append "| "
11309 (assoc-ref inputs "gzip")
11310 "/bin/gzip"))
11311 (("\"gunzip")
11312 (string-append "\""
11313 (assoc-ref inputs "gzip")
11314 "/bin/gunzip")))
11315 #t))
11316 (replace 'install
11317 (lambda* (#:key outputs #:allow-other-keys)
11318 (let ((bin (string-append (assoc-ref outputs "out")
11319 "/bin")))
11320 (mkdir-p bin)
11321 (install-file "trim_galore" bin)
11322 #t))))))
11323 (inputs
11324 `(("gzip" ,gzip)
11325 ("perl" ,perl)
11326 ("cutadapt" ,cutadapt)))
11327 (native-inputs
11328 `(("unzip" ,unzip)))
11329 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11330 (synopsis "Wrapper around Cutadapt and FastQC")
11331 (description "Trim Galore! is a wrapper script to automate quality and
11332 adapter trimming as well as quality control, with some added functionality to
11333 remove biased methylation positions for RRBS sequence files.")
11334 (license license:gpl3+)))
11335
11336 (define-public gess
11337 (package
11338 (name "gess")
11339 (version "1.0")
11340 (source (origin
11341 (method url-fetch)
11342 (uri (string-append "http://compbio.uthscsa.edu/"
11343 "GESS_Web/files/"
11344 "gess-" version ".src.tar.gz"))
11345 (sha256
11346 (base32
11347 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11348 (build-system gnu-build-system)
11349 (arguments
11350 `(#:tests? #f ; no tests
11351 #:phases
11352 (modify-phases %standard-phases
11353 (delete 'configure)
11354 (delete 'build)
11355 (replace 'install
11356 (lambda* (#:key inputs outputs #:allow-other-keys)
11357 (let* ((python (assoc-ref inputs "python"))
11358 (out (assoc-ref outputs "out"))
11359 (bin (string-append out "/bin/"))
11360 (target (string-append
11361 out "/lib/python2.7/site-packages/gess/")))
11362 (mkdir-p target)
11363 (copy-recursively "." target)
11364 ;; Make GESS.py executable
11365 (chmod (string-append target "GESS.py") #o555)
11366 ;; Add Python shebang to the top and make Matplotlib
11367 ;; usable.
11368 (substitute* (string-append target "GESS.py")
11369 (("\"\"\"Description:" line)
11370 (string-append "#!" (which "python") "
11371 import matplotlib
11372 matplotlib.use('Agg')
11373 " line)))
11374 ;; Make sure GESS has all modules in its path
11375 (wrap-program (string-append target "GESS.py")
11376 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11377 (mkdir-p bin)
11378 (symlink (string-append target "GESS.py")
11379 (string-append bin "GESS.py"))
11380 #t))))))
11381 (inputs
11382 `(("python" ,python-2)
11383 ("python2-pysam" ,python2-pysam)
11384 ("python2-scipy" ,python2-scipy)
11385 ("python2-numpy" ,python2-numpy)
11386 ("python2-networkx" ,python2-networkx)
11387 ("python2-biopython" ,python2-biopython)))
11388 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11389 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11390 (description
11391 "GESS is an implementation of a novel computational method to detect de
11392 novo exon-skipping events directly from raw RNA-seq data without the prior
11393 knowledge of gene annotation information. GESS stands for the graph-based
11394 exon-skipping scanner detection scheme.")
11395 (license license:bsd-3)))
11396
11397 (define-public phylip
11398 (package
11399 (name "phylip")
11400 (version "3.696")
11401 (source
11402 (origin
11403 (method url-fetch)
11404 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11405 "download/phylip-" version ".tar.gz"))
11406 (sha256
11407 (base32
11408 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11409 (build-system gnu-build-system)
11410 (arguments
11411 `(#:tests? #f ; no check target
11412 #:make-flags (list "-f" "Makefile.unx" "install")
11413 #:parallel-build? #f ; not supported
11414 #:phases
11415 (modify-phases %standard-phases
11416 (add-after 'unpack 'enter-dir
11417 (lambda _ (chdir "src") #t))
11418 (delete 'configure)
11419 (replace 'install
11420 (lambda* (#:key inputs outputs #:allow-other-keys)
11421 (let ((target (string-append (assoc-ref outputs "out")
11422 "/bin")))
11423 (mkdir-p target)
11424 (for-each (lambda (file)
11425 (install-file file target))
11426 (find-files "../exe" ".*")))
11427 #t)))))
11428 (home-page "http://evolution.genetics.washington.edu/phylip/")
11429 (synopsis "Tools for inferring phylogenies")
11430 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11431 programs for inferring phylogenies (evolutionary trees).")
11432 (license license:bsd-2)))
11433
11434 (define-public imp
11435 (package
11436 (name "imp")
11437 (version "2.6.2")
11438 (source
11439 (origin
11440 (method url-fetch)
11441 (uri (string-append "https://integrativemodeling.org/"
11442 version "/download/imp-" version ".tar.gz"))
11443 (sha256
11444 (base32
11445 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11446 (build-system cmake-build-system)
11447 (arguments
11448 `(;; FIXME: Some tests fail because they produce warnings, others fail
11449 ;; because the PYTHONPATH does not include the modeller's directory.
11450 #:tests? #f))
11451 (inputs
11452 `(("boost" ,boost)
11453 ("gsl" ,gsl)
11454 ("swig" ,swig)
11455 ("hdf5" ,hdf5)
11456 ("fftw" ,fftw)
11457 ("python" ,python-2)))
11458 (propagated-inputs
11459 `(("python2-numpy" ,python2-numpy)
11460 ("python2-scipy" ,python2-scipy)
11461 ("python2-pandas" ,python2-pandas)
11462 ("python2-scikit-learn" ,python2-scikit-learn)
11463 ("python2-networkx" ,python2-networkx)))
11464 (home-page "https://integrativemodeling.org")
11465 (synopsis "Integrative modeling platform")
11466 (description "IMP's broad goal is to contribute to a comprehensive
11467 structural characterization of biomolecules ranging in size and complexity
11468 from small peptides to large macromolecular assemblies, by integrating data
11469 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11470 Python toolbox for solving complex modeling problems, and a number of
11471 applications for tackling some common problems in a user-friendly way.")
11472 ;; IMP is largely available under the GNU Lesser GPL; see the file
11473 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11474 ;; available under the GNU GPL (see the file COPYING.GPL).
11475 (license (list license:lgpl2.1+
11476 license:gpl3+))))
11477
11478 (define-public tadbit
11479 (package
11480 (name "tadbit")
11481 (version "0.2")
11482 (source (origin
11483 (method url-fetch)
11484 (uri (string-append "https://github.com/3DGenomes/TADbit/"
11485 "archive/v" version ".tar.gz"))
11486 (file-name (string-append name "-" version ".tar.gz"))
11487 (sha256
11488 (base32
11489 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
11490 (build-system python-build-system)
11491 (arguments
11492 `(;; Tests are included and must be run after installation, but
11493 ;; they are incomplete and thus cannot be run.
11494 #:tests? #f
11495 #:python ,python-2
11496 #:phases
11497 (modify-phases %standard-phases
11498 (add-after 'unpack 'fix-problems-with-setup.py
11499 (lambda* (#:key outputs #:allow-other-keys)
11500 ;; setup.py opens these files for writing
11501 (chmod "_pytadbit/_version.py" #o664)
11502 (chmod "README.rst" #o664)
11503
11504 ;; Don't attempt to install the bash completions to
11505 ;; the home directory.
11506 (rename-file "extras/.bash_completion"
11507 "extras/tadbit")
11508 (substitute* "setup.py"
11509 (("\\(path.expanduser\\('~'\\)")
11510 (string-append "(\""
11511 (assoc-ref outputs "out")
11512 "/etc/bash_completion.d\""))
11513 (("extras/\\.bash_completion")
11514 "extras/tadbit"))
11515 #t)))))
11516 (inputs
11517 ;; TODO: add Chimera for visualization
11518 `(("imp" ,imp)
11519 ("mcl" ,mcl)
11520 ("python2-scipy" ,python2-scipy)
11521 ("python2-numpy" ,python2-numpy)
11522 ("python2-matplotlib" ,python2-matplotlib)
11523 ("python2-pysam" ,python2-pysam)))
11524 (home-page "https://3dgenomes.github.io/TADbit/")
11525 (synopsis "Analyze, model, and explore 3C-based data")
11526 (description
11527 "TADbit is a complete Python library to deal with all steps to analyze,
11528 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11529 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11530 correct interaction matrices, identify and compare the so-called
11531 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11532 interaction matrices, and finally, extract structural properties from the
11533 models. TADbit is complemented by TADkit for visualizing 3D models.")
11534 (license license:gpl3+)))
11535
11536 (define-public kentutils
11537 (package
11538 (name "kentutils")
11539 ;; 302.1.0 is out, but the only difference is the inclusion of
11540 ;; pre-built binaries.
11541 (version "302.0.0")
11542 (source
11543 (origin
11544 (method url-fetch)
11545 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
11546 "archive/v" version ".tar.gz"))
11547 (file-name (string-append name "-" version ".tar.gz"))
11548 (sha256
11549 (base32
11550 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
11551 (modules '((guix build utils)
11552 (srfi srfi-26)
11553 (ice-9 ftw)))
11554 (snippet
11555 '(begin
11556 ;; Only the contents of the specified directories are free
11557 ;; for all uses, so we remove the rest. "hg/autoSql" and
11558 ;; "hg/autoXml" are nominally free, but they depend on a
11559 ;; library that is built from the sources in "hg/lib",
11560 ;; which is nonfree.
11561 (let ((free (list "." ".."
11562 "utils" "lib" "inc" "tagStorm"
11563 "parasol" "htslib"))
11564 (directory? (lambda (file)
11565 (eq? 'directory (stat:type (stat file))))))
11566 (for-each (lambda (file)
11567 (and (directory? file)
11568 (delete-file-recursively file)))
11569 (map (cut string-append "src/" <>)
11570 (scandir "src"
11571 (lambda (file)
11572 (not (member file free)))))))
11573 ;; Only make the utils target, not the userApps target,
11574 ;; because that requires libraries we won't build.
11575 (substitute* "Makefile"
11576 ((" userApps") " utils"))
11577 ;; Only build libraries that are free.
11578 (substitute* "src/makefile"
11579 (("DIRS =.*") "DIRS =\n")
11580 (("cd jkOwnLib.*") "")
11581 ((" hgLib") "")
11582 (("cd hg.*") ""))
11583 (substitute* "src/utils/makefile"
11584 ;; These tools depend on "jkhgap.a", which is part of the
11585 ;; nonfree "src/hg/lib" directory.
11586 (("raSqlQuery") "")
11587 (("pslLiftSubrangeBlat") "")
11588
11589 ;; Do not build UCSC tools, which may require nonfree
11590 ;; components.
11591 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11592 #t))))
11593 (build-system gnu-build-system)
11594 (arguments
11595 `( ;; There is no global test target and the test target for
11596 ;; individual tools depends on input files that are not
11597 ;; included.
11598 #:tests? #f
11599 #:phases
11600 (modify-phases %standard-phases
11601 (add-after 'unpack 'fix-paths
11602 (lambda _
11603 (substitute* "Makefile"
11604 (("/bin/echo") (which "echo")))
11605 #t))
11606 (add-after 'unpack 'prepare-samtabix
11607 (lambda* (#:key inputs #:allow-other-keys)
11608 (copy-recursively (assoc-ref inputs "samtabix")
11609 "samtabix")
11610 #t))
11611 (delete 'configure)
11612 (replace 'install
11613 (lambda* (#:key outputs #:allow-other-keys)
11614 (let ((bin (string-append (assoc-ref outputs "out")
11615 "/bin")))
11616 (copy-recursively "bin" bin))
11617 #t)))))
11618 (native-inputs
11619 `(("samtabix"
11620 ,(origin
11621 (method git-fetch)
11622 (uri (git-reference
11623 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11624 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11625 (sha256
11626 (base32
11627 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11628 (inputs
11629 `(("zlib" ,zlib)
11630 ("tcsh" ,tcsh)
11631 ("perl" ,perl)
11632 ("libpng" ,libpng)
11633 ("mariadb" ,mariadb)
11634 ("openssl" ,openssl)))
11635 (home-page "http://genome.cse.ucsc.edu/index.html")
11636 (synopsis "Assorted bioinformatics utilities")
11637 (description "This package provides the kentUtils, a selection of
11638 bioinformatics utilities used in combination with the UCSC genome
11639 browser.")
11640 ;; Only a subset of the sources are released under a non-copyleft
11641 ;; free software license. All other sources are removed in a
11642 ;; snippet. See this bug report for an explanation of how the
11643 ;; license statements apply:
11644 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11645 (license (license:non-copyleft
11646 "http://genome.ucsc.edu/license/"
11647 "The contents of this package are free for all uses."))))
11648
11649 (define-public f-seq
11650 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11651 (revision "1"))
11652 (package
11653 (name "f-seq")
11654 (version (string-append "1.1-" revision "." (string-take commit 7)))
11655 (source (origin
11656 (method git-fetch)
11657 (uri (git-reference
11658 (url "https://github.com/aboyle/F-seq.git")
11659 (commit commit)))
11660 (file-name (string-append name "-" version))
11661 (sha256
11662 (base32
11663 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11664 (modules '((guix build utils)))
11665 ;; Remove bundled Java library archives.
11666 (snippet
11667 '(begin
11668 (for-each delete-file (find-files "lib" ".*"))
11669 #t))))
11670 (build-system ant-build-system)
11671 (arguments
11672 `(#:tests? #f ; no tests included
11673 #:phases
11674 (modify-phases %standard-phases
11675 (replace 'install
11676 (lambda* (#:key inputs outputs #:allow-other-keys)
11677 (let* ((target (assoc-ref outputs "out"))
11678 (bin (string-append target "/bin"))
11679 (doc (string-append target "/share/doc/f-seq"))
11680 (lib (string-append target "/lib")))
11681 (mkdir-p target)
11682 (mkdir-p doc)
11683 (substitute* "bin/linux/fseq"
11684 (("java") (which "java"))
11685 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11686 (string-append (assoc-ref inputs "java-commons-cli")
11687 "/share/java/commons-cli.jar"))
11688 (("REALDIR=.*")
11689 (string-append "REALDIR=" bin "\n")))
11690 (install-file "README.txt" doc)
11691 (install-file "bin/linux/fseq" bin)
11692 (install-file "build~/fseq.jar" lib)
11693 (copy-recursively "lib" lib)
11694 #t))))))
11695 (inputs
11696 `(("perl" ,perl)
11697 ("java-commons-cli" ,java-commons-cli)))
11698 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11699 (synopsis "Feature density estimator for high-throughput sequence tags")
11700 (description
11701 "F-Seq is a software package that generates a continuous tag sequence
11702 density estimation allowing identification of biologically meaningful sites
11703 such as transcription factor binding sites (ChIP-seq) or regions of open
11704 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11705 Browser.")
11706 (license license:gpl3+))))
11707
11708 (define-public bismark
11709 (package
11710 (name "bismark")
11711 (version "0.19.1")
11712 (source
11713 (origin
11714 (method git-fetch)
11715 (uri (git-reference
11716 (url "https://github.com/FelixKrueger/Bismark.git")
11717 (commit version)))
11718 (file-name (string-append name "-" version "-checkout"))
11719 (sha256
11720 (base32
11721 "0yb5l36slwg02fp4b1jdlplgljcsxgqfzvzihzdnphd87dghcc84"))
11722 (snippet
11723 '(begin
11724 ;; highcharts.js is non-free software. The code is available under
11725 ;; CC-BY-NC or proprietary licenses only.
11726 (delete-file "bismark_sitrep/highcharts.js")
11727 #t))))
11728 (build-system perl-build-system)
11729 (arguments
11730 `(#:tests? #f ; there are no tests
11731 #:phases
11732 (modify-phases %standard-phases
11733 (delete 'configure)
11734 (delete 'build)
11735 (replace 'install
11736 (lambda* (#:key inputs outputs #:allow-other-keys)
11737 (let* ((out (assoc-ref outputs "out"))
11738 (bin (string-append out "/bin"))
11739 (share (string-append out "/share/bismark"))
11740 (docdir (string-append out "/share/doc/bismark"))
11741 (docs '("Docs/Bismark_User_Guide.html"))
11742 (scripts '("bismark"
11743 "bismark_genome_preparation"
11744 "bismark_methylation_extractor"
11745 "bismark2bedGraph"
11746 "bismark2report"
11747 "coverage2cytosine"
11748 "deduplicate_bismark"
11749 "filter_non_conversion"
11750 "bam2nuc"
11751 "bismark2summary")))
11752 (substitute* "bismark2report"
11753 (("\\$RealBin/bismark_sitrep")
11754 (string-append share "/bismark_sitrep")))
11755 (mkdir-p share)
11756 (mkdir-p docdir)
11757 (mkdir-p bin)
11758 (for-each (lambda (file) (install-file file bin))
11759 scripts)
11760 (for-each (lambda (file) (install-file file docdir))
11761 docs)
11762 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11763 (copy-recursively "bismark_sitrep"
11764 (string-append share "/bismark_sitrep"))
11765
11766 ;; Fix references to gunzip
11767 (substitute* (map (lambda (file)
11768 (string-append bin "/" file))
11769 scripts)
11770 (("\"gunzip -c")
11771 (string-append "\"" (assoc-ref inputs "gzip")
11772 "/bin/gunzip -c")))
11773 #t))))))
11774 (inputs
11775 `(("gzip" ,gzip)))
11776 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11777 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11778 (description "Bismark is a program to map bisulfite treated sequencing
11779 reads to a genome of interest and perform methylation calls in a single step.
11780 The output can be easily imported into a genome viewer, such as SeqMonk, and
11781 enables a researcher to analyse the methylation levels of their samples
11782 straight away. Its main features are:
11783
11784 @itemize
11785 @item Bisulfite mapping and methylation calling in one single step
11786 @item Supports single-end and paired-end read alignments
11787 @item Supports ungapped and gapped alignments
11788 @item Alignment seed length, number of mismatches etc are adjustable
11789 @item Output discriminates between cytosine methylation in CpG, CHG
11790 and CHH context
11791 @end itemize\n")
11792 (license license:gpl3+)))
11793
11794 (define-public paml
11795 (package
11796 (name "paml")
11797 (version "4.9e")
11798 (source (origin
11799 (method url-fetch)
11800 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11801 "paml" version ".tgz"))
11802 (sha256
11803 (base32
11804 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11805 (modules '((guix build utils)))
11806 ;; Remove Windows binaries
11807 (snippet
11808 '(begin
11809 (for-each delete-file (find-files "." "\\.exe$"))
11810 #t))))
11811 (build-system gnu-build-system)
11812 (arguments
11813 `(#:tests? #f ; there are no tests
11814 #:make-flags '("CC=gcc")
11815 #:phases
11816 (modify-phases %standard-phases
11817 (replace 'configure
11818 (lambda _
11819 (substitute* "src/BFdriver.c"
11820 (("/bin/bash") (which "bash")))
11821 (chdir "src")
11822 #t))
11823 (replace 'install
11824 (lambda* (#:key outputs #:allow-other-keys)
11825 (let ((tools '("baseml" "basemlg" "codeml"
11826 "pamp" "evolver" "yn00" "chi2"))
11827 (bin (string-append (assoc-ref outputs "out") "/bin"))
11828 (docdir (string-append (assoc-ref outputs "out")
11829 "/share/doc/paml")))
11830 (mkdir-p bin)
11831 (for-each (lambda (file) (install-file file bin)) tools)
11832 (copy-recursively "../doc" docdir)
11833 #t))))))
11834 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11835 (synopsis "Phylogentic analysis by maximum likelihood")
11836 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11837 contains a few programs for model fitting and phylogenetic tree reconstruction
11838 using nucleotide or amino-acid sequence data.")
11839 ;; GPLv3 only
11840 (license license:gpl3)))
11841
11842 (define-public kallisto
11843 (package
11844 (name "kallisto")
11845 (version "0.44.0")
11846 (source (origin
11847 (method git-fetch)
11848 (uri (git-reference
11849 (url "https://github.com/pachterlab/kallisto.git")
11850 (commit (string-append "v" version))))
11851 (file-name (git-file-name name version))
11852 (sha256
11853 (base32
11854 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11855 (build-system cmake-build-system)
11856 (arguments
11857 `(#:tests? #f ; no "check" target
11858 #:phases
11859 (modify-phases %standard-phases
11860 (add-after 'unpack 'do-not-use-bundled-htslib
11861 (lambda _
11862 (substitute* "CMakeLists.txt"
11863 (("^ExternalProject_Add" m)
11864 (string-append "if (NEVER)\n" m))
11865 (("^\\)")
11866 (string-append ")\nendif(NEVER)"))
11867 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11868 (string-append "# " m)))
11869 (substitute* "src/CMakeLists.txt"
11870 (("target_link_libraries\\(kallisto kallisto_core pthread \
11871 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11872 "target_link_libraries(kallisto kallisto_core pthread hts)")
11873 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11874 #t)))))
11875 (inputs
11876 `(("hdf5" ,hdf5)
11877 ("htslib" ,htslib)
11878 ("zlib" ,zlib)))
11879 (home-page "http://pachterlab.github.io/kallisto/")
11880 (synopsis "Near-optimal RNA-Seq quantification")
11881 (description
11882 "Kallisto is a program for quantifying abundances of transcripts from
11883 RNA-Seq data, or more generally of target sequences using high-throughput
11884 sequencing reads. It is based on the novel idea of pseudoalignment for
11885 rapidly determining the compatibility of reads with targets, without the need
11886 for alignment. Pseudoalignment of reads preserves the key information needed
11887 for quantification, and kallisto is therefore not only fast, but also as
11888 accurate as existing quantification tools.")
11889 (license license:bsd-2)))
11890
11891 (define-public libgff
11892 (package
11893 (name "libgff")
11894 (version "1.0")
11895 (source (origin
11896 (method url-fetch)
11897 (uri (string-append
11898 "https://github.com/Kingsford-Group/"
11899 "libgff/archive/v" version ".tar.gz"))
11900 (file-name (string-append name "-" version ".tar.gz"))
11901 (sha256
11902 (base32
11903 "0vc4nxyhlm6g9vvmx5l4lfs5pnvixsv1hiiy4kddf2y3p6jna8ls"))))
11904 (build-system cmake-build-system)
11905 (arguments `(#:tests? #f)) ; no tests included
11906 (home-page "https://github.com/Kingsford-Group/libgff")
11907 (synopsis "Parser library for reading/writing GFF files")
11908 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11909 code that is used in the Cufflinks codebase. The goal of this library is to
11910 provide this functionality without the necessity of drawing in a heavy-weight
11911 dependency like SeqAn.")
11912 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11913
11914 (define-public libdivsufsort
11915 (package
11916 (name "libdivsufsort")
11917 (version "2.0.1")
11918 (source (origin
11919 (method git-fetch)
11920 (uri (git-reference
11921 (url "https://github.com/y-256/libdivsufsort.git")
11922 (commit version)))
11923 (file-name (git-file-name name version))
11924 (sha256
11925 (base32
11926 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11927 (build-system cmake-build-system)
11928 (arguments
11929 '(#:tests? #f ; there are no tests
11930 #:configure-flags
11931 ;; Needed for rapmap and sailfish.
11932 '("-DBUILD_DIVSUFSORT64=ON")))
11933 (home-page "https://github.com/y-256/libdivsufsort")
11934 (synopsis "Lightweight suffix-sorting library")
11935 (description "libdivsufsort is a software library that implements a
11936 lightweight suffix array construction algorithm. This library provides a
11937 simple and an efficient C API to construct a suffix array and a
11938 Burrows-Wheeler transformed string from a given string over a constant-size
11939 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11940 bytes of memory space, where n is the length of the string.")
11941 (license license:expat)))
11942
11943 (define-public sailfish
11944 (package
11945 (name "sailfish")
11946 (version "0.10.1")
11947 (source (origin
11948 (method url-fetch)
11949 (uri
11950 (string-append "https://github.com/kingsfordgroup/"
11951 "sailfish/archive/v" version ".tar.gz"))
11952 (file-name (string-append name "-" version ".tar.gz"))
11953 (sha256
11954 (base32
11955 "1inn60dxiwsz8g9w7kvfhjxj4bwfb0r12dyhpzzhfbig712dkmm0"))
11956 (modules '((guix build utils)))
11957 (snippet
11958 '(begin
11959 ;; Delete bundled headers for eigen3.
11960 (delete-file-recursively "include/eigen3/")
11961 #t))))
11962 (build-system cmake-build-system)
11963 (arguments
11964 `(#:configure-flags
11965 (list (string-append "-DBOOST_INCLUDEDIR="
11966 (assoc-ref %build-inputs "boost")
11967 "/include/")
11968 (string-append "-DBOOST_LIBRARYDIR="
11969 (assoc-ref %build-inputs "boost")
11970 "/lib/")
11971 (string-append "-DBoost_LIBRARIES="
11972 "-lboost_iostreams "
11973 "-lboost_filesystem "
11974 "-lboost_system "
11975 "-lboost_thread "
11976 "-lboost_timer "
11977 "-lboost_chrono "
11978 "-lboost_program_options")
11979 "-DBoost_FOUND=TRUE"
11980 ;; Don't download RapMap---we already have it!
11981 "-DFETCHED_RAPMAP=1")
11982 ;; Tests must be run after installation and the location of the test
11983 ;; data file must be overridden. But the tests fail. It looks like
11984 ;; they are not really meant to be run.
11985 #:tests? #f
11986 #:phases
11987 (modify-phases %standard-phases
11988 ;; Boost cannot be found, even though it's right there.
11989 (add-after 'unpack 'do-not-look-for-boost
11990 (lambda* (#:key inputs #:allow-other-keys)
11991 (substitute* "CMakeLists.txt"
11992 (("find_package\\(Boost 1\\.53\\.0") "#"))))
11993 (add-after 'unpack 'do-not-assign-to-macro
11994 (lambda _
11995 (substitute* "include/spdlog/details/format.cc"
11996 (("const unsigned CHAR_WIDTH = 1;") ""))))
11997 (add-after 'unpack 'prepare-rapmap
11998 (lambda* (#:key inputs #:allow-other-keys)
11999 (let ((src "external/install/src/rapmap/")
12000 (include "external/install/include/rapmap/")
12001 (rapmap (assoc-ref inputs "rapmap")))
12002 (mkdir-p "/tmp/rapmap")
12003 (system* "tar" "xf"
12004 (assoc-ref inputs "rapmap")
12005 "-C" "/tmp/rapmap"
12006 "--strip-components=1")
12007 (mkdir-p src)
12008 (mkdir-p include)
12009 (for-each (lambda (file)
12010 (install-file file src))
12011 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
12012 (copy-recursively "/tmp/rapmap/include" include))))
12013 (add-after 'unpack 'use-system-libraries
12014 (lambda* (#:key inputs #:allow-other-keys)
12015 (substitute* '("src/SailfishIndexer.cpp"
12016 "src/SailfishUtils.cpp"
12017 "src/SailfishQuantify.cpp"
12018 "src/FASTAParser.cpp"
12019 "include/PCA.hpp"
12020 "include/SailfishUtils.hpp"
12021 "include/SailfishIndex.hpp"
12022 "include/CollapsedEMOptimizer.hpp"
12023 "src/CollapsedEMOptimizer.cpp")
12024 (("#include \"jellyfish/config.h\"") ""))
12025 (substitute* "src/CMakeLists.txt"
12026 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12027 (string-append (assoc-ref inputs "jellyfish")
12028 "/include/jellyfish-" ,(package-version jellyfish)))
12029 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12030 (string-append (assoc-ref inputs "jellyfish")
12031 "/lib/libjellyfish-2.0.a"))
12032 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12033 (string-append (assoc-ref inputs "libdivsufsort")
12034 "/lib/libdivsufsort.so"))
12035 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12036 (string-append (assoc-ref inputs "libdivsufsort")
12037 "/lib/libdivsufsort64.so")))
12038 (substitute* "CMakeLists.txt"
12039 ;; Don't prefer static libs
12040 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12041 (("find_package\\(Jellyfish.*") "")
12042 (("ExternalProject_Add\\(libjellyfish") "message(")
12043 (("ExternalProject_Add\\(libgff") "message(")
12044 (("ExternalProject_Add\\(libsparsehash") "message(")
12045 (("ExternalProject_Add\\(libdivsufsort") "message("))
12046
12047 ;; Ensure that Eigen headers can be found
12048 (setenv "CPLUS_INCLUDE_PATH"
12049 (string-append (getenv "CPLUS_INCLUDE_PATH")
12050 ":"
12051 (assoc-ref inputs "eigen")
12052 "/include/eigen3")))))))
12053 (inputs
12054 `(("boost" ,boost)
12055 ("eigen" ,eigen)
12056 ("jemalloc" ,jemalloc)
12057 ("jellyfish" ,jellyfish)
12058 ("sparsehash" ,sparsehash)
12059 ("rapmap" ,(origin
12060 (method git-fetch)
12061 (uri (git-reference
12062 (url "https://github.com/COMBINE-lab/RapMap.git")
12063 (commit (string-append "sf-v" version))))
12064 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12065 (sha256
12066 (base32
12067 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12068 (modules '((guix build utils)))
12069 ;; These files are expected to be excluded.
12070 (snippet
12071 '(begin (delete-file-recursively "include/spdlog")
12072 (for-each delete-file '("include/xxhash.h"
12073 "src/xxhash.c"))
12074 #t))))
12075 ("libdivsufsort" ,libdivsufsort)
12076 ("libgff" ,libgff)
12077 ("tbb" ,tbb)
12078 ("zlib" ,zlib)))
12079 (native-inputs
12080 `(("pkg-config" ,pkg-config)))
12081 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
12082 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12083 (description "Sailfish is a tool for genomic transcript quantification
12084 from RNA-seq data. It requires a set of target transcripts (either from a
12085 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12086 fasta file containing your reference transcripts and a (set of) fasta/fastq
12087 file(s) containing your reads.")
12088 (license license:gpl3+)))
12089
12090 (define libstadenio-for-salmon
12091 (package
12092 (name "libstadenio")
12093 (version "1.14.8")
12094 (source (origin
12095 (method git-fetch)
12096 (uri (git-reference
12097 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12098 (commit (string-append "v" version))))
12099 (file-name (string-append name "-" version "-checkout"))
12100 (sha256
12101 (base32
12102 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12103 (build-system gnu-build-system)
12104 (arguments '(#:parallel-tests? #f)) ; not supported
12105 (inputs
12106 `(("zlib" ,zlib)))
12107 (native-inputs
12108 `(("perl" ,perl))) ; for tests
12109 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12110 (synopsis "General purpose trace and experiment file library")
12111 (description "This package provides a library of file reading and writing
12112 code to provide a general purpose Trace file (and Experiment File) reading
12113 interface.
12114
12115 The following file formats are supported:
12116
12117 @enumerate
12118 @item SCF trace files
12119 @item ABI trace files
12120 @item ALF trace files
12121 @item ZTR trace files
12122 @item SFF trace archives
12123 @item SRF trace archives
12124 @item Experiment files
12125 @item Plain text files
12126 @item SAM/BAM sequence files
12127 @item CRAM sequence files
12128 @end enumerate\n")
12129 (license license:bsd-3)))
12130
12131 (define spdlog-for-salmon
12132 (package
12133 (name "spdlog")
12134 (version "0.14.0")
12135 (source (origin
12136 (method git-fetch)
12137 (uri (git-reference
12138 (url "https://github.com/COMBINE-lab/spdlog.git")
12139 (commit (string-append "v" version))))
12140 (file-name (string-append name "-" version "-checkout"))
12141 (sha256
12142 (base32
12143 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
12144 (build-system cmake-build-system)
12145 (home-page "https://github.com/COMBINE-lab/spdlog")
12146 (synopsis "Very fast C++ logging library")
12147 (description "Spdlog is a very fast header-only C++ logging library with
12148 performance as its primary goal.")
12149 (license license:expat)))
12150
12151 ;; This is a modified variant of bwa for use with Salmon. It installs a
12152 ;; library to avoid having to build this as part of Salmon.
12153 (define bwa-for-salmon
12154 (package (inherit bwa)
12155 (name "bwa")
12156 (version "0.7.12.5")
12157 (source (origin
12158 (method git-fetch)
12159 (uri (git-reference
12160 (url "https://github.com/COMBINE-lab/bwa.git")
12161 (commit (string-append "v" version))))
12162 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
12163 (sha256
12164 (base32
12165 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
12166 (build-system gnu-build-system)
12167 (arguments
12168 '(#:tests? #f ;no "check" target
12169 #:phases
12170 (modify-phases %standard-phases
12171 (replace 'install
12172 (lambda* (#:key outputs #:allow-other-keys)
12173 (let* ((out (assoc-ref outputs "out"))
12174 (bin (string-append out "/bin"))
12175 (lib (string-append out "/lib"))
12176 (doc (string-append out "/share/doc/bwa"))
12177 (man (string-append out "/share/man/man1"))
12178 (inc (string-append out "/include/bwa")))
12179 (install-file "bwa" bin)
12180 (install-file "README.md" doc)
12181 (install-file "bwa.1" man)
12182 (install-file "libbwa.a" lib)
12183 (mkdir-p lib)
12184 (mkdir-p inc)
12185 (for-each (lambda (file)
12186 (install-file file inc))
12187 (find-files "." "\\.h$")))
12188 #t))
12189 ;; no "configure" script
12190 (delete 'configure))))))
12191
12192 (define-public salmon
12193 (package
12194 (name "salmon")
12195 (version "0.9.1")
12196 (source (origin
12197 (method git-fetch)
12198 (uri (git-reference
12199 (url "https://github.com/COMBINE-lab/salmon.git")
12200 (commit (string-append "v" version))))
12201 (file-name (string-append name "-" version "-checkout"))
12202 (sha256
12203 (base32
12204 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12205 (modules '((guix build utils)))
12206 (snippet
12207 '(begin
12208 ;; Delete bundled headers for eigen3.
12209 (delete-file-recursively "include/eigen3/")
12210 #t))))
12211 (build-system cmake-build-system)
12212 (arguments
12213 `(#:configure-flags
12214 (list (string-append "-DBOOST_INCLUDEDIR="
12215 (assoc-ref %build-inputs "boost")
12216 "/include/")
12217 (string-append "-DBOOST_LIBRARYDIR="
12218 (assoc-ref %build-inputs "boost")
12219 "/lib/")
12220 (string-append "-DBoost_LIBRARIES="
12221 "-lboost_iostreams "
12222 "-lboost_filesystem "
12223 "-lboost_system "
12224 "-lboost_thread "
12225 "-lboost_timer "
12226 "-lboost_chrono "
12227 "-lboost_program_options")
12228 "-DBoost_FOUND=TRUE"
12229 "-DTBB_LIBRARIES=tbb tbbmalloc"
12230 ;; Don't download RapMap---we already have it!
12231 "-DFETCHED_RAPMAP=1")
12232 #:phases
12233 (modify-phases %standard-phases
12234 ;; Boost cannot be found, even though it's right there.
12235 (add-after 'unpack 'do-not-look-for-boost
12236 (lambda* (#:key inputs #:allow-other-keys)
12237 (substitute* "CMakeLists.txt"
12238 (("find_package\\(Boost 1\\.53\\.0") "#"))))
12239 (add-after 'unpack 'do-not-phone-home
12240 (lambda _
12241 (substitute* "src/Salmon.cpp"
12242 (("getVersionMessage\\(\\)") "\"\""))))
12243 (add-after 'unpack 'prepare-rapmap
12244 (lambda* (#:key inputs #:allow-other-keys)
12245 (let ((src "external/install/src/rapmap/")
12246 (include "external/install/include/rapmap/")
12247 (rapmap (assoc-ref inputs "rapmap")))
12248 (mkdir-p src)
12249 (mkdir-p include)
12250 (for-each (lambda (file)
12251 (install-file file src))
12252 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12253 (copy-recursively (string-append rapmap "/include") include)
12254 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12255 "external/install/include/rapmap/FastxParser.hpp"
12256 "external/install/include/rapmap/concurrentqueue.h"
12257 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12258 "external/install/src/rapmap/FastxParser.cpp"
12259 "external/install/src/rapmap/xxhash.c")))))
12260 (add-after 'unpack 'use-system-libraries
12261 (lambda* (#:key inputs #:allow-other-keys)
12262 (substitute* "src/CMakeLists.txt"
12263 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12264 (string-append (assoc-ref inputs "jellyfish")
12265 "/include/jellyfish-" ,(package-version jellyfish)))
12266 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12267 (string-append (assoc-ref inputs "jellyfish")
12268 "/lib/libjellyfish-2.0.a"))
12269 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12270 (string-append (assoc-ref inputs "libdivsufsort")
12271 "/lib/libdivsufsort.so"))
12272 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12273 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12274 "/lib/libstaden-read.a"))
12275 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12276 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12277 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12278 (string-append (assoc-ref inputs "libdivsufsort")
12279 "/lib/libdivsufsort64.so")))
12280 (substitute* "CMakeLists.txt"
12281 ;; Don't prefer static libs
12282 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12283 (("set\\(TBB_LIBRARIES") "message(")
12284 (("find_package\\(Jellyfish.*") "")
12285 (("ExternalProject_Add\\(libcereal") "message(")
12286 (("ExternalProject_Add\\(libbwa") "message(")
12287 (("ExternalProject_Add\\(libjellyfish") "message(")
12288 (("ExternalProject_Add\\(libgff") "message(")
12289 (("ExternalProject_Add\\(libtbb") "message(")
12290 (("ExternalProject_Add\\(libspdlog") "message(")
12291 (("ExternalProject_Add\\(libdivsufsort") "message(")
12292 (("ExternalProject_Add\\(libstadenio") "message(")
12293 (("ExternalProject_Add_Step\\(") "message("))
12294
12295 ;; Ensure that all headers can be found
12296 (setenv "CPLUS_INCLUDE_PATH"
12297 (string-append (getenv "CPLUS_INCLUDE_PATH")
12298 ":"
12299 (assoc-ref inputs "bwa")
12300 "/include/bwa"
12301 ":"
12302 (assoc-ref inputs "eigen")
12303 "/include/eigen3"))
12304 (setenv "CPATH"
12305 (string-append (assoc-ref inputs "bwa")
12306 "/include/bwa"
12307 ":"
12308 (assoc-ref inputs "eigen")
12309 "/include/eigen3"))
12310 #t))
12311 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12312 ;; run. It only exists after the install phase.
12313 (add-after 'unpack 'fix-tests
12314 (lambda _
12315 (substitute* "src/CMakeLists.txt"
12316 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12317 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12318 #t)))))
12319 (inputs
12320 `(("boost" ,boost)
12321 ("bwa" ,bwa-for-salmon)
12322 ("bzip2" ,bzip2)
12323 ("cereal" ,cereal)
12324 ("eigen" ,eigen)
12325 ("rapmap" ,(origin
12326 (method git-fetch)
12327 (uri (git-reference
12328 (url "https://github.com/COMBINE-lab/RapMap.git")
12329 (commit (string-append "salmon-v" version))))
12330 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12331 (sha256
12332 (base32
12333 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12334 ("jemalloc" ,jemalloc)
12335 ("jellyfish" ,jellyfish)
12336 ("libgff" ,libgff)
12337 ("tbb" ,tbb)
12338 ("libdivsufsort" ,libdivsufsort)
12339 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12340 ("spdlog-for-salmon" ,spdlog-for-salmon)
12341 ("xz" ,xz)
12342 ("zlib" ,zlib)))
12343 (home-page "https://github.com/COMBINE-lab/salmon")
12344 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12345 (description "Salmon is a program to produce highly-accurate,
12346 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12347 its accuracy and speed via a number of different innovations, including the
12348 use of lightweight alignments (accurate but fast-to-compute proxies for
12349 traditional read alignments) and massively-parallel stochastic collapsed
12350 variational inference.")
12351 (license license:gpl3+)))
12352
12353 (define-public python-loompy
12354 (package
12355 (name "python-loompy")
12356 (version "2.0.2")
12357 (source
12358 (origin
12359 (method url-fetch)
12360 (uri (pypi-uri "loompy" version))
12361 (sha256
12362 (base32
12363 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12364 (build-system python-build-system)
12365 ;; There are no tests
12366 (arguments '(#:tests? #f))
12367 (propagated-inputs
12368 `(("python-h5py" ,python-h5py)
12369 ("python-numpy" ,python-numpy)
12370 ("python-scipy" ,python-scipy)
12371 ("python-typing" ,python-typing)))
12372 (home-page "https://github.com/linnarsson-lab/loompy")
12373 (synopsis "Work with .loom files for single-cell RNA-seq data")
12374 (description "The loom file format is an efficient format for very large
12375 omics datasets, consisting of a main matrix, optional additional layers, a
12376 variable number of row and column annotations. Loom also supports sparse
12377 graphs. This library makes it easy to work with @file{.loom} files for
12378 single-cell RNA-seq data.")
12379 (license license:bsd-3)))
12380
12381 ;; We cannot use the latest commit because it requires Java 9.
12382 (define-public java-forester
12383 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12384 (revision "1"))
12385 (package
12386 (name "java-forester")
12387 (version (string-append "0-" revision "." (string-take commit 7)))
12388 (source (origin
12389 (method git-fetch)
12390 (uri (git-reference
12391 (url "https://github.com/cmzmasek/forester.git")
12392 (commit commit)))
12393 (file-name (string-append name "-" version "-checkout"))
12394 (sha256
12395 (base32
12396 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12397 (modules '((guix build utils)))
12398 (snippet
12399 '(begin
12400 ;; Delete bundled jars and pre-built classes
12401 (delete-file-recursively "forester/java/resources")
12402 (delete-file-recursively "forester/java/classes")
12403 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12404 ;; Delete bundled applications
12405 (delete-file-recursively "forester_applications")
12406 #t))))
12407 (build-system ant-build-system)
12408 (arguments
12409 `(#:tests? #f ; there are none
12410 #:jdk ,icedtea-8
12411 #:modules ((guix build ant-build-system)
12412 (guix build utils)
12413 (guix build java-utils)
12414 (sxml simple)
12415 (sxml transform))
12416 #:phases
12417 (modify-phases %standard-phases
12418 (add-after 'unpack 'chdir
12419 (lambda _ (chdir "forester/java") #t))
12420 (add-after 'chdir 'fix-dependencies
12421 (lambda _
12422 (chmod "build.xml" #o664)
12423 (call-with-output-file "build.xml.new"
12424 (lambda (port)
12425 (sxml->xml
12426 (pre-post-order
12427 (with-input-from-file "build.xml"
12428 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12429 `(;; Remove all unjar tags to avoid repacking classes.
12430 (unjar . ,(lambda _ '()))
12431 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12432 (*text* . ,(lambda (_ txt) txt))))
12433 port)))
12434 (rename-file "build.xml.new" "build.xml")
12435 #t))
12436 ;; FIXME: itext is difficult to package as it depends on a few
12437 ;; unpackaged libraries.
12438 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12439 (lambda _
12440 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12441 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12442 (("pdf_written_to = PdfExporter.*")
12443 "throw new IOException(\"PDF export is not available.\");"))
12444 #t))
12445 ;; There is no install target
12446 (replace 'install (install-jars ".")))))
12447 (propagated-inputs
12448 `(("java-commons-codec" ,java-commons-codec)
12449 ("java-openchart2" ,java-openchart2)))
12450 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12451 (synopsis "Phylogenomics libraries for Java")
12452 (description "Forester is a collection of Java libraries for
12453 phylogenomics and evolutionary biology research. It includes support for
12454 reading, writing, and exporting phylogenetic trees.")
12455 (license license:lgpl2.1+))))
12456
12457 (define-public java-forester-1.005
12458 (package
12459 (name "java-forester")
12460 (version "1.005")
12461 (source (origin
12462 (method url-fetch)
12463 (uri (string-append "http://search.maven.org/remotecontent?"
12464 "filepath=org/biojava/thirdparty/forester/"
12465 version "/forester-" version "-sources.jar"))
12466 (file-name (string-append name "-" version ".jar"))
12467 (sha256
12468 (base32
12469 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12470 (build-system ant-build-system)
12471 (arguments
12472 `(#:tests? #f ; there are none
12473 #:jdk ,icedtea-8
12474 #:modules ((guix build ant-build-system)
12475 (guix build utils)
12476 (guix build java-utils)
12477 (sxml simple)
12478 (sxml transform))
12479 #:phases
12480 (modify-phases %standard-phases
12481 (add-after 'unpack 'fix-dependencies
12482 (lambda* (#:key inputs #:allow-other-keys)
12483 (call-with-output-file "build.xml"
12484 (lambda (port)
12485 (sxml->xml
12486 (pre-post-order
12487 (with-input-from-file "src/build.xml"
12488 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12489 `(;; Remove all unjar tags to avoid repacking classes.
12490 (unjar . ,(lambda _ '()))
12491 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12492 (*text* . ,(lambda (_ txt) txt))))
12493 port)))
12494 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12495 "synth_look_and_feel_1.xml")
12496 (copy-file (assoc-ref inputs "phyloxml.xsd")
12497 "phyloxml.xsd")
12498 (substitute* "build.xml"
12499 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12500 "synth_look_and_feel_1.xml")
12501 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12502 "phyloxml.xsd"))
12503 #t))
12504 ;; FIXME: itext is difficult to package as it depends on a few
12505 ;; unpackaged libraries.
12506 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12507 (lambda _
12508 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12509 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12510 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12511 (("pdf_written_to = PdfExporter.*")
12512 "throw new IOException(\"PDF export is not available.\"); /*")
12513 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12514 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12515 #t))
12516 (add-after 'unpack 'delete-pre-built-classes
12517 (lambda _ (delete-file-recursively "src/classes") #t))
12518 ;; There is no install target
12519 (replace 'install (install-jars ".")))))
12520 (propagated-inputs
12521 `(("java-commons-codec" ,java-commons-codec)
12522 ("java-openchart2" ,java-openchart2)))
12523 ;; The source archive does not contain the resources.
12524 (native-inputs
12525 `(("phyloxml.xsd"
12526 ,(origin
12527 (method url-fetch)
12528 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12529 "b61cc2dcede0bede317db362472333115756b8c6/"
12530 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12531 (file-name (string-append name "-phyloxml-" version ".xsd"))
12532 (sha256
12533 (base32
12534 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12535 ("synth_look_and_feel_1.xml"
12536 ,(origin
12537 (method url-fetch)
12538 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12539 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12540 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12541 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12542 (sha256
12543 (base32
12544 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12545 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12546 (synopsis "Phylogenomics libraries for Java")
12547 (description "Forester is a collection of Java libraries for
12548 phylogenomics and evolutionary biology research. It includes support for
12549 reading, writing, and exporting phylogenetic trees.")
12550 (license license:lgpl2.1+)))
12551
12552 (define-public java-biojava-core
12553 (package
12554 (name "java-biojava-core")
12555 (version "4.2.11")
12556 (source (origin
12557 (method git-fetch)
12558 (uri (git-reference
12559 (url "https://github.com/biojava/biojava")
12560 (commit (string-append "biojava-" version))))
12561 (file-name (string-append name "-" version "-checkout"))
12562 (sha256
12563 (base32
12564 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12565 (build-system ant-build-system)
12566 (arguments
12567 `(#:jdk ,icedtea-8
12568 #:jar-name "biojava-core.jar"
12569 #:source-dir "biojava-core/src/main/java/"
12570 #:test-dir "biojava-core/src/test"
12571 ;; These tests seem to require internet access.
12572 #:test-exclude (list "**/SearchIOTest.java"
12573 "**/BlastXMLParserTest.java"
12574 "**/GenbankCookbookTest.java"
12575 "**/GenbankProxySequenceReaderTest.java")
12576 #:phases
12577 (modify-phases %standard-phases
12578 (add-before 'build 'copy-resources
12579 (lambda _
12580 (copy-recursively "biojava-core/src/main/resources"
12581 "build/classes")
12582 #t))
12583 (add-before 'check 'copy-test-resources
12584 (lambda _
12585 (copy-recursively "biojava-core/src/test/resources"
12586 "build/test-classes")
12587 #t)))))
12588 (propagated-inputs
12589 `(("java-log4j-api" ,java-log4j-api)
12590 ("java-log4j-core" ,java-log4j-core)
12591 ("java-slf4j-api" ,java-slf4j-api)
12592 ("java-slf4j-simple" ,java-slf4j-simple)))
12593 (native-inputs
12594 `(("java-junit" ,java-junit)
12595 ("java-hamcrest-core" ,java-hamcrest-core)))
12596 (home-page "http://biojava.org")
12597 (synopsis "Core libraries of Java framework for processing biological data")
12598 (description "BioJava is a project dedicated to providing a Java framework
12599 for processing biological data. It provides analytical and statistical
12600 routines, parsers for common file formats, reference implementations of
12601 popular algorithms, and allows the manipulation of sequences and 3D
12602 structures. The goal of the biojava project is to facilitate rapid
12603 application development for bioinformatics.
12604
12605 This package provides the core libraries.")
12606 (license license:lgpl2.1+)))
12607
12608 (define-public java-biojava-phylo
12609 (package (inherit java-biojava-core)
12610 (name "java-biojava-phylo")
12611 (build-system ant-build-system)
12612 (arguments
12613 `(#:jdk ,icedtea-8
12614 #:jar-name "biojava-phylo.jar"
12615 #:source-dir "biojava-phylo/src/main/java/"
12616 #:test-dir "biojava-phylo/src/test"
12617 #:phases
12618 (modify-phases %standard-phases
12619 (add-before 'build 'copy-resources
12620 (lambda _
12621 (copy-recursively "biojava-phylo/src/main/resources"
12622 "build/classes")
12623 #t))
12624 (add-before 'check 'copy-test-resources
12625 (lambda _
12626 (copy-recursively "biojava-phylo/src/test/resources"
12627 "build/test-classes")
12628 #t)))))
12629 (propagated-inputs
12630 `(("java-log4j-api" ,java-log4j-api)
12631 ("java-log4j-core" ,java-log4j-core)
12632 ("java-slf4j-api" ,java-slf4j-api)
12633 ("java-slf4j-simple" ,java-slf4j-simple)
12634 ("java-biojava-core" ,java-biojava-core)
12635 ("java-forester" ,java-forester)))
12636 (native-inputs
12637 `(("java-junit" ,java-junit)
12638 ("java-hamcrest-core" ,java-hamcrest-core)))
12639 (home-page "http://biojava.org")
12640 (synopsis "Biojava interface to the forester phylogenomics library")
12641 (description "The phylo module provides a biojava interface layer to the
12642 forester phylogenomics library for constructing phylogenetic trees.")))
12643
12644 (define-public java-biojava-alignment
12645 (package (inherit java-biojava-core)
12646 (name "java-biojava-alignment")
12647 (build-system ant-build-system)
12648 (arguments
12649 `(#:jdk ,icedtea-8
12650 #:jar-name "biojava-alignment.jar"
12651 #:source-dir "biojava-alignment/src/main/java/"
12652 #:test-dir "biojava-alignment/src/test"
12653 #:phases
12654 (modify-phases %standard-phases
12655 (add-before 'build 'copy-resources
12656 (lambda _
12657 (copy-recursively "biojava-alignment/src/main/resources"
12658 "build/classes")
12659 #t))
12660 (add-before 'check 'copy-test-resources
12661 (lambda _
12662 (copy-recursively "biojava-alignment/src/test/resources"
12663 "build/test-classes")
12664 #t)))))
12665 (propagated-inputs
12666 `(("java-log4j-api" ,java-log4j-api)
12667 ("java-log4j-core" ,java-log4j-core)
12668 ("java-slf4j-api" ,java-slf4j-api)
12669 ("java-slf4j-simple" ,java-slf4j-simple)
12670 ("java-biojava-core" ,java-biojava-core)
12671 ("java-biojava-phylo" ,java-biojava-phylo)
12672 ("java-forester" ,java-forester)))
12673 (native-inputs
12674 `(("java-junit" ,java-junit)
12675 ("java-hamcrest-core" ,java-hamcrest-core)))
12676 (home-page "http://biojava.org")
12677 (synopsis "Biojava API for genetic sequence alignment")
12678 (description "The alignment module of BioJava provides an API that
12679 contains
12680
12681 @itemize
12682 @item implementations of dynamic programming algorithms for sequence
12683 alignment;
12684 @item reading and writing of popular alignment file formats;
12685 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12686 @end itemize\n")))
12687
12688 (define-public java-biojava-core-4.0
12689 (package (inherit java-biojava-core)
12690 (name "java-biojava-core")
12691 (version "4.0.0")
12692 (source (origin
12693 (method git-fetch)
12694 (uri (git-reference
12695 (url "https://github.com/biojava/biojava")
12696 (commit (string-append "biojava-" version))))
12697 (file-name (string-append name "-" version "-checkout"))
12698 (sha256
12699 (base32
12700 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12701
12702 (define-public java-biojava-phylo-4.0
12703 (package (inherit java-biojava-core-4.0)
12704 (name "java-biojava-phylo")
12705 (build-system ant-build-system)
12706 (arguments
12707 `(#:jdk ,icedtea-8
12708 #:jar-name "biojava-phylo.jar"
12709 #:source-dir "biojava-phylo/src/main/java/"
12710 #:test-dir "biojava-phylo/src/test"
12711 #:phases
12712 (modify-phases %standard-phases
12713 (add-before 'build 'copy-resources
12714 (lambda _
12715 (copy-recursively "biojava-phylo/src/main/resources"
12716 "build/classes")
12717 #t))
12718 (add-before 'check 'copy-test-resources
12719 (lambda _
12720 (copy-recursively "biojava-phylo/src/test/resources"
12721 "build/test-classes")
12722 #t)))))
12723 (propagated-inputs
12724 `(("java-log4j-api" ,java-log4j-api)
12725 ("java-log4j-core" ,java-log4j-core)
12726 ("java-slf4j-api" ,java-slf4j-api)
12727 ("java-slf4j-simple" ,java-slf4j-simple)
12728 ("java-biojava-core" ,java-biojava-core-4.0)
12729 ("java-forester" ,java-forester-1.005)))
12730 (native-inputs
12731 `(("java-junit" ,java-junit)
12732 ("java-hamcrest-core" ,java-hamcrest-core)))
12733 (home-page "http://biojava.org")
12734 (synopsis "Biojava interface to the forester phylogenomics library")
12735 (description "The phylo module provides a biojava interface layer to the
12736 forester phylogenomics library for constructing phylogenetic trees.")))
12737
12738 (define-public java-biojava-alignment-4.0
12739 (package (inherit java-biojava-core-4.0)
12740 (name "java-biojava-alignment")
12741 (build-system ant-build-system)
12742 (arguments
12743 `(#:jdk ,icedtea-8
12744 #:jar-name "biojava-alignment.jar"
12745 #:source-dir "biojava-alignment/src/main/java/"
12746 #:test-dir "biojava-alignment/src/test"
12747 #:phases
12748 (modify-phases %standard-phases
12749 (add-before 'build 'copy-resources
12750 (lambda _
12751 (copy-recursively "biojava-alignment/src/main/resources"
12752 "build/classes")
12753 #t))
12754 (add-before 'check 'copy-test-resources
12755 (lambda _
12756 (copy-recursively "biojava-alignment/src/test/resources"
12757 "build/test-classes")
12758 #t)))))
12759 (propagated-inputs
12760 `(("java-log4j-api" ,java-log4j-api)
12761 ("java-log4j-core" ,java-log4j-core)
12762 ("java-slf4j-api" ,java-slf4j-api)
12763 ("java-slf4j-simple" ,java-slf4j-simple)
12764 ("java-biojava-core" ,java-biojava-core-4.0)
12765 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12766 ("java-forester" ,java-forester-1.005)))
12767 (native-inputs
12768 `(("java-junit" ,java-junit)
12769 ("java-hamcrest-core" ,java-hamcrest-core)))
12770 (home-page "http://biojava.org")
12771 (synopsis "Biojava API for genetic sequence alignment")
12772 (description "The alignment module of BioJava provides an API that
12773 contains
12774
12775 @itemize
12776 @item implementations of dynamic programming algorithms for sequence
12777 alignment;
12778 @item reading and writing of popular alignment file formats;
12779 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12780 @end itemize\n")))
12781
12782 (define-public dropseq-tools
12783 (package
12784 (name "dropseq-tools")
12785 (version "1.13")
12786 (source
12787 (origin
12788 (method url-fetch)
12789 (uri "http://mccarrolllab.com/download/1276/")
12790 (file-name (string-append "dropseq-tools-" version ".zip"))
12791 (sha256
12792 (base32
12793 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12794 ;; Delete bundled libraries
12795 (modules '((guix build utils)))
12796 (snippet
12797 '(begin
12798 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12799 (delete-file-recursively "3rdParty")
12800 #t))))
12801 (build-system ant-build-system)
12802 (arguments
12803 `(#:tests? #f ; test data are not included
12804 #:test-target "test"
12805 #:build-target "all"
12806 #:source-dir "public/src/"
12807 #:jdk ,icedtea-8
12808 #:make-flags
12809 (list (string-append "-Dpicard.executable.dir="
12810 (assoc-ref %build-inputs "java-picard")
12811 "/share/java/"))
12812 #:modules ((ice-9 match)
12813 (srfi srfi-1)
12814 (guix build utils)
12815 (guix build java-utils)
12816 (guix build ant-build-system))
12817 #:phases
12818 (modify-phases %standard-phases
12819 ;; FIXME: fails with "java.io.FileNotFoundException:
12820 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12821 (delete 'generate-jar-indices)
12822 ;; All dependencies must be linked to "lib", because that's where
12823 ;; they will be searched for when the Class-Path property of the
12824 ;; manifest is computed.
12825 (add-after 'unpack 'record-references
12826 (lambda* (#:key inputs #:allow-other-keys)
12827 (mkdir-p "jar/lib")
12828 (let ((dirs (filter-map (match-lambda
12829 ((name . dir)
12830 (if (and (string-prefix? "java-" name)
12831 (not (string=? name "java-testng")))
12832 dir #f)))
12833 inputs)))
12834 (for-each (lambda (jar)
12835 (symlink jar (string-append "jar/lib/" (basename jar))))
12836 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12837 dirs)))
12838 #t))
12839 ;; There is no installation target
12840 (replace 'install
12841 (lambda* (#:key inputs outputs #:allow-other-keys)
12842 (let* ((out (assoc-ref outputs "out"))
12843 (bin (string-append out "/bin"))
12844 (share (string-append out "/share/java/"))
12845 (lib (string-append share "/lib/"))
12846 (scripts (list "BAMTagHistogram"
12847 "BAMTagofTagCounts"
12848 "BaseDistributionAtReadPosition"
12849 "CollapseBarcodesInPlace"
12850 "CollapseTagWithContext"
12851 "ConvertToRefFlat"
12852 "CreateIntervalsFiles"
12853 "DetectBeadSynthesisErrors"
12854 "DigitalExpression"
12855 "Drop-seq_alignment.sh"
12856 "FilterBAM"
12857 "FilterBAMByTag"
12858 "GatherGeneGCLength"
12859 "GatherMolecularBarcodeDistributionByGene"
12860 "GatherReadQualityMetrics"
12861 "PolyATrimmer"
12862 "ReduceGTF"
12863 "SelectCellsByNumTranscripts"
12864 "SingleCellRnaSeqMetricsCollector"
12865 "TagBamWithReadSequenceExtended"
12866 "TagReadWithGeneExon"
12867 "TagReadWithInterval"
12868 "TrimStartingSequence"
12869 "ValidateReference")))
12870 (for-each mkdir-p (list bin share lib))
12871 (install-file "dist/dropseq.jar" share)
12872 (for-each (lambda (script)
12873 (chmod script #o555)
12874 (install-file script bin))
12875 scripts)
12876 (substitute* (map (lambda (script)
12877 (string-append bin "/" script))
12878 scripts)
12879 (("^java") (which "java"))
12880 (("jar_deploy_dir=.*")
12881 (string-append "jar_deploy_dir=" share "\n"))))
12882 #t))
12883 ;; FIXME: We do this after stripping jars because we don't want it to
12884 ;; copy all these jars and strip them. We only want to install
12885 ;; links. Arguably, this is a problem with the ant-build-system.
12886 (add-after 'strip-jar-timestamps 'install-links
12887 (lambda* (#:key outputs #:allow-other-keys)
12888 (let* ((out (assoc-ref outputs "out"))
12889 (share (string-append out "/share/java/"))
12890 (lib (string-append share "/lib/")))
12891 (for-each (lambda (jar)
12892 (symlink (readlink jar)
12893 (string-append lib (basename jar))))
12894 (find-files "jar/lib" "\\.jar$")))
12895 #t)))))
12896 (inputs
12897 `(("jdk" ,icedtea-8)
12898 ("java-picard" ,java-picard-2.10.3)
12899 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12900 ("java-commons-math3" ,java-commons-math3)
12901 ("java-commons-jexl2" ,java-commons-jexl-2)
12902 ("java-commons-collections4" ,java-commons-collections4)
12903 ("java-commons-lang2" ,java-commons-lang)
12904 ("java-commons-io" ,java-commons-io)
12905 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12906 ("java-guava" ,java-guava)
12907 ("java-la4j" ,java-la4j)
12908 ("java-biojava-core" ,java-biojava-core-4.0)
12909 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12910 ("java-jdistlib" ,java-jdistlib)
12911 ("java-simple-xml" ,java-simple-xml)
12912 ("java-snakeyaml" ,java-snakeyaml)))
12913 (native-inputs
12914 `(("unzip" ,unzip)
12915 ("java-testng" ,java-testng)))
12916 (home-page "http://mccarrolllab.com/dropseq/")
12917 (synopsis "Tools for Drop-seq analyses")
12918 (description "Drop-seq is a technology to enable biologists to
12919 analyze RNA expression genome-wide in thousands of individual cells at
12920 once. This package provides tools to perform Drop-seq analyses.")
12921 (license license:expat)))
12922
12923 (define-public pigx-rnaseq
12924 (package
12925 (name "pigx-rnaseq")
12926 (version "0.0.4")
12927 (source (origin
12928 (method url-fetch)
12929 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12930 "releases/download/v" version
12931 "/pigx_rnaseq-" version ".tar.gz"))
12932 (sha256
12933 (base32
12934 "16gla23rmziimqan7w494q0nr7vfbp42zzkrl9fracmr4k7b1kzr"))))
12935 (build-system gnu-build-system)
12936 (arguments
12937 `(#:parallel-tests? #f ; not supported
12938 #:phases
12939 (modify-phases %standard-phases
12940 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12941 (add-after 'unpack 'disable-resource-intensive-test
12942 (lambda _
12943 (substitute* "Makefile.in"
12944 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12945 (("^ tests/test_multiqc/test.sh") "")
12946 (("^ test.sh") ""))
12947 #t)))))
12948 (inputs
12949 `(("gzip" ,gzip)
12950 ("snakemake" ,snakemake-4)
12951 ("fastqc" ,fastqc)
12952 ("multiqc" ,multiqc)
12953 ("star" ,star)
12954 ("trim-galore" ,trim-galore)
12955 ("htseq" ,htseq)
12956 ("samtools" ,samtools)
12957 ("bedtools" ,bedtools)
12958 ("r-minimal" ,r-minimal)
12959 ("r-rmarkdown" ,r-rmarkdown)
12960 ("r-ggplot2" ,r-ggplot2)
12961 ("r-ggrepel" ,r-ggrepel)
12962 ("r-gprofiler" ,r-gprofiler)
12963 ("r-deseq2" ,r-deseq2)
12964 ("r-dt" ,r-dt)
12965 ("r-knitr" ,r-knitr)
12966 ("r-pheatmap" ,r-pheatmap)
12967 ("r-corrplot" ,r-corrplot)
12968 ("r-reshape2" ,r-reshape2)
12969 ("r-plotly" ,r-plotly)
12970 ("r-scales" ,r-scales)
12971 ("r-summarizedexperiment" ,r-summarizedexperiment)
12972 ("r-crosstalk" ,r-crosstalk)
12973 ("r-tximport" ,r-tximport)
12974 ("r-rtracklayer" ,r-rtracklayer)
12975 ("r-rjson" ,r-rjson)
12976 ("salmon" ,salmon)
12977 ("ghc-pandoc" ,ghc-pandoc)
12978 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12979 ("python-wrapper" ,python-wrapper)
12980 ("python-pyyaml" ,python-pyyaml)))
12981 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12982 (synopsis "Analysis pipeline for RNA sequencing experiments")
12983 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12984 reporting for RNA sequencing experiments. It is easy to use and produces high
12985 quality reports. The inputs are reads files from the sequencing experiment,
12986 and a configuration file which describes the experiment. In addition to
12987 quality control of the experiment, the pipeline produces a differential
12988 expression report comparing samples in an easily configurable manner.")
12989 (license license:gpl3+)))
12990
12991 (define-public pigx-chipseq
12992 (package
12993 (name "pigx-chipseq")
12994 (version "0.0.20")
12995 (source (origin
12996 (method url-fetch)
12997 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12998 "releases/download/v" version
12999 "/pigx_chipseq-" version ".tar.gz"))
13000 (sha256
13001 (base32
13002 "19a7dclqq0b4kqg3phiz4d4arlwfp34nm3z0rf1gkqdpsy7gghp3"))))
13003 (build-system gnu-build-system)
13004 ;; parts of the tests rely on access to the network
13005 (arguments '(#:tests? #f))
13006 (inputs
13007 `(("grep" ,grep)
13008 ("coreutils" ,coreutils)
13009 ("r-minimal" ,r-minimal)
13010 ("r-argparser" ,r-argparser)
13011 ("r-biocparallel" ,r-biocparallel)
13012 ("r-biostrings" ,r-biostrings)
13013 ("r-chipseq" ,r-chipseq)
13014 ("r-data-table" ,r-data-table)
13015 ("r-dplyr" ,r-dplyr)
13016 ("r-genomation" ,r-genomation)
13017 ("r-genomicalignments" ,r-genomicalignments)
13018 ("r-genomicranges" ,r-genomicranges)
13019 ("r-rsamtools" ,r-rsamtools)
13020 ("r-rtracklayer" ,r-rtracklayer)
13021 ("r-s4vectors" ,r-s4vectors)
13022 ("r-stringr" ,r-stringr)
13023 ("r-tibble" ,r-tibble)
13024 ("r-tidyr" ,r-tidyr)
13025 ("r-jsonlite" ,r-jsonlite)
13026 ("r-heatmaply" ,r-heatmaply)
13027 ("r-htmlwidgets" ,r-htmlwidgets)
13028 ("r-ggplot2" ,r-ggplot2)
13029 ("r-plotly" ,r-plotly)
13030 ("r-rmarkdown" ,r-rmarkdown)
13031 ("python-wrapper" ,python-wrapper)
13032 ("python-pyyaml" ,python-pyyaml)
13033 ("python-magic" ,python-magic)
13034 ("python-xlrd" ,python-xlrd)
13035 ("trim-galore" ,trim-galore)
13036 ("macs" ,macs)
13037 ("multiqc" ,multiqc)
13038 ("perl" ,perl)
13039 ("ghc-pandoc" ,ghc-pandoc)
13040 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13041 ("fastqc" ,fastqc)
13042 ("bowtie" ,bowtie)
13043 ("idr" ,idr)
13044 ("snakemake" ,snakemake-4)
13045 ("samtools" ,samtools)
13046 ("bedtools" ,bedtools)
13047 ("kentutils" ,kentutils)))
13048 (native-inputs
13049 `(("python-pytest" ,python-pytest)))
13050 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13051 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13052 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13053 calling and reporting for ChIP sequencing experiments. It is easy to use and
13054 produces high quality reports. The inputs are reads files from the sequencing
13055 experiment, and a configuration file which describes the experiment. In
13056 addition to quality control of the experiment, the pipeline enables to set up
13057 multiple peak calling analysis and allows the generation of a UCSC track hub
13058 in an easily configurable manner.")
13059 (license license:gpl3+)))
13060
13061 (define-public pigx-bsseq
13062 (package
13063 (name "pigx-bsseq")
13064 (version "0.0.10")
13065 (source (origin
13066 (method url-fetch)
13067 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13068 "releases/download/v" version
13069 "/pigx_bsseq-" version ".tar.gz"))
13070 (sha256
13071 (base32
13072 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
13073 (build-system gnu-build-system)
13074 (arguments
13075 `(#:phases
13076 (modify-phases %standard-phases
13077 (add-before 'check 'set-timezone
13078 ;; The readr package is picky about timezones.
13079 (lambda* (#:key inputs #:allow-other-keys)
13080 (setenv "TZ" "UTC+1")
13081 (setenv "TZDIR"
13082 (string-append (assoc-ref inputs "tzdata")
13083 "/share/zoneinfo"))
13084 #t)))))
13085 (native-inputs
13086 `(("tzdata" ,tzdata)))
13087 (inputs
13088 `(("coreutils" ,coreutils)
13089 ("sed" ,sed)
13090 ("grep" ,grep)
13091 ("r-minimal" ,r-minimal)
13092 ("r-annotationhub" ,r-annotationhub)
13093 ("r-dt" ,r-dt)
13094 ("r-genomation" ,r-genomation)
13095 ("r-methylkit" ,r-methylkit)
13096 ("r-rtracklayer" ,r-rtracklayer)
13097 ("r-rmarkdown" ,r-rmarkdown)
13098 ("r-bookdown" ,r-bookdown)
13099 ("r-ggplot2" ,r-ggplot2)
13100 ("r-ggbio" ,r-ggbio)
13101 ("ghc-pandoc" ,ghc-pandoc)
13102 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13103 ("python-wrapper" ,python-wrapper)
13104 ("python-pyyaml" ,python-pyyaml)
13105 ("snakemake" ,snakemake-4)
13106 ("bismark" ,bismark)
13107 ("fastqc" ,fastqc)
13108 ("bowtie" ,bowtie)
13109 ("trim-galore" ,trim-galore)
13110 ("cutadapt" ,cutadapt)
13111 ("samtools" ,samtools)))
13112 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13113 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13114 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13115 data of bisulfite experiments; it produces reports on aggregate methylation
13116 and coverage and can be used to produce information on differential
13117 methylation and segmentation.")
13118 (license license:gpl3+)))
13119
13120 (define-public pigx-scrnaseq
13121 (package
13122 (name "pigx-scrnaseq")
13123 (version "0.0.7")
13124 (source (origin
13125 (method url-fetch)
13126 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13127 "releases/download/v" version
13128 "/pigx_scrnaseq-" version ".tar.gz"))
13129 (sha256
13130 (base32
13131 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
13132 (build-system gnu-build-system)
13133 (arguments
13134 `(#:configure-flags
13135 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
13136 "/share/java/picard.jar")
13137 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
13138 "/share/java/dropseq.jar"))))
13139 (inputs
13140 `(("coreutils" ,coreutils)
13141 ("perl" ,perl)
13142 ("dropseq-tools" ,dropseq-tools)
13143 ("fastqc" ,fastqc)
13144 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
13145 ("java" ,icedtea-8)
13146 ("python-wrapper" ,python-wrapper)
13147 ("python-pyyaml" ,python-pyyaml)
13148 ("python-pandas" ,python-pandas)
13149 ("python-magic" ,python-magic)
13150 ("python-numpy" ,python-numpy)
13151 ("python-loompy" ,python-loompy)
13152 ("ghc-pandoc" ,ghc-pandoc)
13153 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13154 ("samtools" ,samtools)
13155 ("snakemake" ,snakemake-4)
13156 ("star" ,star)
13157 ("r-minimal" ,r-minimal)
13158 ("r-argparser" ,r-argparser)
13159 ("r-cowplot" ,r-cowplot)
13160 ("r-data-table" ,r-data-table)
13161 ("r-delayedarray" ,r-delayedarray)
13162 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13163 ("r-dplyr" ,r-dplyr)
13164 ("r-dropbead" ,r-dropbead)
13165 ("r-dt" ,r-dt)
13166 ("r-genomicalignments" ,r-genomicalignments)
13167 ("r-genomicfiles" ,r-genomicfiles)
13168 ("r-genomicranges" ,r-genomicranges)
13169 ("r-ggplot2" ,r-ggplot2)
13170 ("r-hdf5array" ,r-hdf5array)
13171 ("r-pheatmap" ,r-pheatmap)
13172 ("r-rmarkdown" ,r-rmarkdown)
13173 ("r-rsamtools" ,r-rsamtools)
13174 ("r-rtracklayer" ,r-rtracklayer)
13175 ("r-rtsne" ,r-rtsne)
13176 ("r-scater" ,r-scater)
13177 ("r-scran" ,r-scran)
13178 ("r-singlecellexperiment" ,r-singlecellexperiment)
13179 ("r-stringr" ,r-stringr)
13180 ("r-yaml" ,r-yaml)))
13181 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13182 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13183 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13184 quality control for single cell RNA sequencing experiments. The inputs are
13185 read files from the sequencing experiment, and a configuration file which
13186 describes the experiment. It produces processed files for downstream analysis
13187 and interactive quality reports. The pipeline is designed to work with UMI
13188 based methods.")
13189 (license license:gpl3+)))
13190
13191 (define-public pigx
13192 (package
13193 (name "pigx")
13194 (version "0.0.3")
13195 (source (origin
13196 (method url-fetch)
13197 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13198 "releases/download/v" version
13199 "/pigx-" version ".tar.gz"))
13200 (sha256
13201 (base32
13202 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13203 (build-system gnu-build-system)
13204 (inputs
13205 `(("python" ,python)
13206 ("pigx-bsseq" ,pigx-bsseq)
13207 ("pigx-chipseq" ,pigx-chipseq)
13208 ("pigx-rnaseq" ,pigx-rnaseq)
13209 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13210 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13211 (synopsis "Analysis pipelines for genomics")
13212 (description "PiGx is a collection of genomics pipelines. It includes the
13213 following pipelines:
13214
13215 @itemize
13216 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13217 @item PiGx RNAseq for RNAseq samples
13218 @item PiGx scRNAseq for single cell dropseq analysis
13219 @item PiGx ChIPseq for reads from ChIPseq experiments
13220 @end itemize
13221
13222 All pipelines are easily configured with a simple sample sheet and a
13223 descriptive settings file. The result is a set of comprehensive, interactive
13224 HTML reports with interesting findings about your samples.")
13225 (license license:gpl3+)))
13226
13227 (define-public r-diversitree
13228 (package
13229 (name "r-diversitree")
13230 (version "0.9-10")
13231 (source
13232 (origin
13233 (method url-fetch)
13234 (uri (cran-uri "diversitree" version))
13235 (sha256
13236 (base32
13237 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13238 (build-system r-build-system)
13239 (native-inputs
13240 `(("gfortran" ,gfortran)))
13241 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13242 (propagated-inputs
13243 `(("r-ape" ,r-ape)
13244 ("r-desolve" ,r-desolve)
13245 ("r-rcpp" ,r-rcpp)
13246 ("r-suplex" ,r-subplex)))
13247 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13248 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13249 (description "This package contains a number of comparative \"phylogenetic\"
13250 methods, mostly focusing on analysing diversification and character evolution.
13251 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13252 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13253 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13254 include Markov models of discrete and continuous trait evolution and constant
13255 rate speciation and extinction.")
13256 (license license:gpl2+)))
13257
13258 (define-public sjcount
13259 ;; There is no tag for version 3.2, nor is there a release archive.
13260 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13261 (revision "1"))
13262 (package
13263 (name "sjcount")
13264 (version (git-version "3.2" revision commit))
13265 (source (origin
13266 (method git-fetch)
13267 (uri (git-reference
13268 (url "https://github.com/pervouchine/sjcount-full.git")
13269 (commit commit)))
13270 (file-name (string-append name "-" version "-checkout"))
13271 (sha256
13272 (base32
13273 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13274 (build-system gnu-build-system)
13275 (arguments
13276 `(#:tests? #f ; requires a 1.4G test file
13277 #:make-flags
13278 (list (string-append "SAMTOOLS_DIR="
13279 (assoc-ref %build-inputs "samtools")
13280 "/lib/"))
13281 #:phases
13282 (modify-phases %standard-phases
13283 (replace 'configure
13284 (lambda* (#:key inputs #:allow-other-keys)
13285 (substitute* "makefile"
13286 (("-I \\$\\{SAMTOOLS_DIR\\}")
13287 (string-append "-I" (assoc-ref inputs "samtools")
13288 "/include/samtools"))
13289 (("-lz ") "-lz -lpthread "))
13290 #t))
13291 (replace 'install
13292 (lambda* (#:key outputs #:allow-other-keys)
13293 (for-each (lambda (tool)
13294 (install-file tool
13295 (string-append (assoc-ref outputs "out")
13296 "/bin")))
13297 '("j_count" "b_count" "sjcount"))
13298 #t)))))
13299 (inputs
13300 `(("samtools" ,samtools-0.1)
13301 ("zlib" ,zlib)))
13302 (home-page "https://github.com/pervouchine/sjcount-full/")
13303 (synopsis "Annotation-agnostic splice junction counting pipeline")
13304 (description "Sjcount is a utility for fast quantification of splice
13305 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13306 version does count multisplits.")
13307 (license license:gpl3+))))
13308
13309 (define-public minimap2
13310 (package
13311 (name "minimap2")
13312 (version "2.10")
13313 (source
13314 (origin
13315 (method url-fetch)
13316 (uri (string-append "https://github.com/lh3/minimap2/"
13317 "releases/download/v" version "/"
13318 "minimap2-" version ".tar.bz2"))
13319 (sha256
13320 (base32
13321 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13322 (build-system gnu-build-system)
13323 (arguments
13324 `(#:tests? #f ; there are none
13325 #:make-flags
13326 (list "CC=gcc"
13327 (let ((system ,(or (%current-target-system)
13328 (%current-system))))
13329 (cond
13330 ((string-prefix? "x86_64" system)
13331 "all")
13332 ((or (string-prefix? "armhf" system)
13333 (string-prefix? "aarch64" system))
13334 "arm_neon=1")
13335 (_ "sse2only=1"))))
13336 #:phases
13337 (modify-phases %standard-phases
13338 (delete 'configure)
13339 (replace 'install
13340 (lambda* (#:key outputs #:allow-other-keys)
13341 (let* ((out (assoc-ref outputs "out"))
13342 (bin (string-append out "/bin"))
13343 (man (string-append out "/share/man/man1")))
13344 (install-file "minimap2" bin)
13345 (mkdir-p man)
13346 (install-file "minimap2.1" man))
13347 #t)))))
13348 (inputs
13349 `(("zlib" ,zlib)))
13350 (home-page "https://lh3.github.io/minimap2/")
13351 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13352 (description "Minimap2 is a versatile sequence alignment program that
13353 aligns DNA or mRNA sequences against a large reference database. Typical use
13354 cases include:
13355
13356 @enumerate
13357 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13358 @item finding overlaps between long reads with error rate up to ~15%;
13359 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13360 reads against a reference genome;
13361 @item aligning Illumina single- or paired-end reads;
13362 @item assembly-to-assembly alignment;
13363 @item full-genome alignment between two closely related species with
13364 divergence below ~15%.
13365 @end enumerate\n")
13366 (license license:expat)))
13367
13368 (define-public r-circus
13369 (package
13370 (name "r-circus")
13371 (version "0.1.5")
13372 (source
13373 (origin
13374 (method git-fetch)
13375 (uri (git-reference
13376 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13377 (commit (string-append "v" version))))
13378 (file-name (git-file-name name version))
13379 (sha256
13380 (base32
13381 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13382 (build-system r-build-system)
13383 (propagated-inputs
13384 `(("r-annotationdbi" ,r-annotationdbi)
13385 ("r-annotationhub" ,r-annotationhub)
13386 ("r-biomart" ,r-biomart)
13387 ("r-data-table" ,r-data-table)
13388 ("r-dbi" ,r-dbi)
13389 ("r-genomicfeatures" ,r-genomicfeatures)
13390 ("r-genomicranges" ,r-genomicranges)
13391 ("r-ggplot2" ,r-ggplot2)
13392 ("r-hash" ,r-hash)
13393 ("r-iranges" ,r-iranges)
13394 ("r-rcolorbrewer" ,r-rcolorbrewer)
13395 ("r-rmysql" ,r-rmysql)
13396 ("r-s4vectors" ,r-s4vectors)
13397 ("r-stringr" ,r-stringr)
13398 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13399 (native-inputs
13400 `(("r-knitr" ,r-knitr)))
13401 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13402 (synopsis "Annotation, analysis and visualization of circRNA data")
13403 (description "Circus is an R package for annotation, analysis and
13404 visualization of circRNA data. Users can annotate their circRNA candidates
13405 with host genes, gene featrues they are spliced from, and discriminate between
13406 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13407 can be calculated, and a number of descriptive plots easily generated.")
13408 (license license:artistic2.0)))
13409
13410 (define-public r-loomr
13411 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13412 (revision "1"))
13413 (package
13414 (name "r-loomr")
13415 (version (git-version "0.2.0" revision commit))
13416 (source
13417 (origin
13418 (method git-fetch)
13419 (uri (git-reference
13420 (url "https://github.com/mojaveazure/loomR.git")
13421 (commit commit)))
13422 (file-name (git-file-name name version))
13423 (sha256
13424 (base32
13425 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13426 (build-system r-build-system)
13427 (propagated-inputs
13428 `(("r-r6" ,r-r6)
13429 ("r-hdf5r" ,r-hdf5r)
13430 ("r-iterators" ,r-iterators)
13431 ("r-itertools" ,r-itertools)
13432 ("r-matrix" ,r-matrix)))
13433 (home-page "https://github.com/mojaveazure/loomR")
13434 (synopsis "R interface for loom files")
13435 (description "This package provides an R interface to access, create,
13436 and modify loom files. loomR aims to be completely compatible with loompy.")
13437 (license license:gpl3))))
13438
13439 (define-public gffread
13440 ;; We cannot use the tagged release because it is not in sync with gclib.
13441 ;; See https://github.com/gpertea/gffread/issues/26
13442 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13443 (revision "1"))
13444 (package
13445 (name "gffread")
13446 (version (git-version "0.9.12" revision commit))
13447 (source
13448 (origin
13449 (method git-fetch)
13450 (uri (git-reference
13451 (url "https://github.com/gpertea/gffread.git")
13452 (commit commit)))
13453 (file-name (git-file-name name version))
13454 (sha256
13455 (base32
13456 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13457 (build-system gnu-build-system)
13458 (arguments
13459 `(#:tests? #f ; no check target
13460 #:make-flags
13461 (list "GCLDIR=gclib")
13462 #:phases
13463 (modify-phases %standard-phases
13464 (delete 'configure)
13465 (add-after 'unpack 'copy-gclib-source
13466 (lambda* (#:key inputs #:allow-other-keys)
13467 (mkdir-p "gclib")
13468 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13469 #t))
13470 ;; There is no install target
13471 (replace 'install
13472 (lambda* (#:key outputs #:allow-other-keys)
13473 (let* ((out (assoc-ref outputs "out"))
13474 (bin (string-append out "/bin")))
13475 (install-file "gffread" bin))
13476 #t)))))
13477 (native-inputs
13478 `(("gclib-source"
13479 ,(let ((version "0.10.3")
13480 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13481 (revision "1"))
13482 (origin
13483 (method git-fetch)
13484 (uri (git-reference
13485 (url "https://github.com/gpertea/gclib.git")
13486 (commit commit)))
13487 (file-name (git-file-name "gclib" version))
13488 (sha256
13489 (base32
13490 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13491 (home-page "https://github.com/gpertea/gffread/")
13492 (synopsis "Parse and convert GFF/GTF files")
13493 (description
13494 "This package provides a GFF/GTF file parsing utility providing format
13495 conversions, region filtering, FASTA sequence extraction and more.")
13496 ;; gffread is under Expat, but gclib is under Artistic 2.0
13497 (license (list license:expat
13498 license:artistic2.0)))))
13499
13500 (define-public find-circ
13501 ;; The last release was in 2015. The license was clarified in 2017, so we
13502 ;; take the latest commit.
13503 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13504 (revision "1"))
13505 (package
13506 (name "find-circ")
13507 (version (git-version "1.2" revision commit))
13508 (source
13509 (origin
13510 (method git-fetch)
13511 (uri (git-reference
13512 (url "https://github.com/marvin-jens/find_circ.git")
13513 (commit commit)))
13514 (file-name (git-file-name name version))
13515 (sha256
13516 (base32
13517 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13518 (build-system gnu-build-system)
13519 (arguments
13520 `(#:tests? #f ; there are none
13521 #:phases
13522 ;; There is no actual build system.
13523 (modify-phases %standard-phases
13524 (delete 'configure)
13525 (delete 'build)
13526 (replace 'install
13527 (lambda* (#:key outputs #:allow-other-keys)
13528 (let* ((out (assoc-ref outputs "out"))
13529 (bin (string-append out "/bin"))
13530 (path (getenv "PYTHONPATH")))
13531 (for-each (lambda (script)
13532 (install-file script bin)
13533 (wrap-program (string-append bin "/" script)
13534 `("PYTHONPATH" ":" prefix (,path))))
13535 '("cmp_bed.py"
13536 "find_circ.py"
13537 "maxlength.py"
13538 "merge_bed.py"
13539 "unmapped2anchors.py")))
13540 #t)))))
13541 (inputs
13542 `(("python2" ,python-2)
13543 ("python2-pysam" ,python2-pysam)
13544 ("python2-numpy" ,python2-numpy)))
13545 (home-page "https://github.com/marvin-jens/find_circ")
13546 (synopsis "circRNA detection from RNA-seq reads")
13547 (description "This package provides tools to detect head-to-tail
13548 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13549 in RNA-seq data.")
13550 (license license:gpl3))))
13551
13552 (define-public python-scanpy
13553 (package
13554 (name "python-scanpy")
13555 (version "1.2.2")
13556 (source
13557 (origin
13558 (method url-fetch)
13559 (uri (pypi-uri "scanpy" version))
13560 (sha256
13561 (base32
13562 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13563 (build-system python-build-system)
13564 (propagated-inputs
13565 `(("python-anndata" ,python-anndata)
13566 ("python-igraph" ,python-igraph)
13567 ("python-numba" ,python-numba)
13568 ("python-joblib" ,python-joblib)
13569 ("python-natsort" ,python-natsort)
13570 ("python-networkx" ,python-networkx)
13571 ("python-statsmodels" ,python-statsmodels)
13572 ("python-scikit-learn" ,python-scikit-learn)
13573 ("python-matplotlib" ,python-matplotlib)
13574 ("python-pandas" ,python-pandas)
13575 ("python-scipy" ,python-scipy)
13576 ("python-seaborn" ,python-seaborn)
13577 ("python-h5py" ,python-h5py)
13578 ("python-tables" ,python-tables)))
13579 (home-page "http://github.com/theislab/scanpy")
13580 (synopsis "Single-Cell Analysis in Python.")
13581 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13582 expression data. It includes preprocessing, visualization, clustering,
13583 pseudotime and trajectory inference and differential expression testing. The
13584 Python-based implementation efficiently deals with datasets of more than one
13585 million cells.")
13586 (license license:bsd-3)))
13587
13588 (define-public gffcompare
13589 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13590 (revision "1"))
13591 (package
13592 (name "gffcompare")
13593 (version (git-version "0.10.15" revision commit))
13594 (source
13595 (origin
13596 (method git-fetch)
13597 (uri (git-reference
13598 (url "https://github.com/gpertea/gffcompare/")
13599 (commit commit)))
13600 (file-name (git-file-name name version))
13601 (sha256
13602 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13603 (build-system gnu-build-system)
13604 (arguments
13605 `(#:tests? #f ; no check target
13606 #:phases
13607 (modify-phases %standard-phases
13608 (delete 'configure)
13609 (add-before 'build 'copy-gclib-source
13610 (lambda* (#:key inputs #:allow-other-keys)
13611 (mkdir "../gclib")
13612 (copy-recursively
13613 (assoc-ref inputs "gclib-source") "../gclib")
13614 #t))
13615 (replace 'install
13616 (lambda* (#:key outputs #:allow-other-keys)
13617 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13618 (install-file "gffcompare" bin)
13619 #t))))))
13620 (native-inputs
13621 `(("gclib-source" ; see 'README.md' of gffcompare
13622 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13623 (revision "1")
13624 (name "gclib")
13625 (version (git-version "0.10.3" revision commit)))
13626 (origin
13627 (method git-fetch)
13628 (uri (git-reference
13629 (url "https://github.com/gpertea/gclib/")
13630 (commit commit)))
13631 (file-name (git-file-name name version))
13632 (sha256
13633 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13634 (home-page "https://github.com/gpertea/gffcompare/")
13635 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13636 (description
13637 "@code{gffcompare} is a tool that can:
13638 @enumerate
13639 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13640 (Cufflinks, Stringtie);
13641 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13642 resulted from assembly of different samples);
13643 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13644 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13645 @end enumerate")
13646 (license
13647 (list
13648 license:expat ;license for gffcompare
13649 license:artistic2.0))))) ;license for gclib
13650
13651 (define-public python-intervaltree
13652 (package
13653 (name "python-intervaltree")
13654 (version "2.1.0")
13655 (source
13656 (origin
13657 (method url-fetch)
13658 (uri (pypi-uri "intervaltree" version))
13659 (sha256
13660 (base32
13661 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13662 (build-system python-build-system)
13663 ;; FIXME: error when collecting tests
13664 (arguments '(#:tests? #f))
13665 (propagated-inputs
13666 `(("python-sortedcontainers" ,python-sortedcontainers)))
13667 (native-inputs
13668 `(("python-pytest" ,python-pytest)))
13669 (home-page "https://github.com/chaimleib/intervaltree")
13670 (synopsis "Editable interval tree data structure")
13671 (description
13672 "This package provides a mutable, self-balancing interval tree
13673 implementation for Python. Queries may be by point, by range overlap, or by
13674 range envelopment. This library was designed to allow tagging text and time
13675 intervals, where the intervals include the lower bound but not the upper
13676 bound.")
13677 (license license:asl2.0)))
13678
13679 (define-public python-pypairix
13680 (package
13681 (name "python-pypairix")
13682 (version "0.3.6")
13683 (source
13684 (origin
13685 (method url-fetch)
13686 (uri (pypi-uri "pypairix" version))
13687 (sha256
13688 (base32
13689 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13690 (build-system python-build-system)
13691 ;; FIXME: the tests fail because test.support cannot be loaded:
13692 ;; ImportError: cannot import name 'support'
13693 (arguments '(#:tests? #f))
13694 (inputs
13695 `(("zlib" ,zlib)))
13696 (home-page "https://github.com/4dn-dcic/pairix")
13697 (synopsis "Support for querying pairix-indexed bgzipped text files")
13698 (description
13699 "Pypairix is a Python module for fast querying on a pairix-indexed
13700 bgzipped text file that contains a pair of genomic coordinates per line.")
13701 (license license:expat)))
13702
13703 (define-public python-pyfaidx
13704 (package
13705 (name "python-pyfaidx")
13706 (version "0.5.4.2")
13707 (source
13708 (origin
13709 (method url-fetch)
13710 (uri (pypi-uri "pyfaidx" version))
13711 (sha256
13712 (base32
13713 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13714 (build-system python-build-system)
13715 (propagated-inputs
13716 `(("python-setuptools" ,python-setuptools)
13717 ("python-six" ,python-six)))
13718 (home-page "http://mattshirley.com")
13719 (synopsis "Random access to fasta subsequences")
13720 (description
13721 "This package provides procedures for efficient pythonic random access to
13722 fasta subsequences.")
13723 (license license:bsd-3)))
13724
13725 (define-public python-cooler
13726 (package
13727 (name "python-cooler")
13728 (version "0.7.11")
13729 (source
13730 (origin
13731 (method url-fetch)
13732 (uri (pypi-uri "cooler" version))
13733 (sha256
13734 (base32
13735 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13736 (build-system python-build-system)
13737 (propagated-inputs
13738 `(("python-biopython" ,python-biopython)
13739 ("python-click" ,python-click)
13740 ("python-cytoolz" ,python-cytoolz)
13741 ("python-dask" ,python-dask)
13742 ("python-h5py" ,python-h5py)
13743 ("python-multiprocess" ,python-multiprocess)
13744 ("python-pandas" ,python-pandas)
13745 ("python-pyfaidx" ,python-pyfaidx)
13746 ("python-pypairix" ,python-pypairix)
13747 ("python-pysam" ,python-pysam)
13748 ("python-scipy" ,python-scipy)))
13749 (native-inputs
13750 `(("python-mock" ,python-mock)
13751 ("python-nose" ,python-nose)
13752 ("python-numpydoc" ,python-numpydoc)
13753 ("python-sphinx" ,python-sphinx)))
13754 (home-page "https://github.com/mirnylab/cooler")
13755 (synopsis "Sparse binary format for genomic interaction matrices")
13756 (description
13757 "Cooler is a support library for a sparse, compressed, binary persistent
13758 storage format, called @code{cool}, used to store genomic interaction data,
13759 such as Hi-C contact matrices.")
13760 (license license:bsd-3)))
13761
13762 (define-public python-hicexplorer
13763 (package
13764 (name "python-hicexplorer")
13765 (version "2.1.4")
13766 (source
13767 (origin
13768 ;; The latest version is not available on Pypi.
13769 (method git-fetch)
13770 (uri (git-reference
13771 (url "https://github.com/deeptools/HiCExplorer.git")
13772 (commit version)))
13773 (file-name (git-file-name name version))
13774 (sha256
13775 (base32
13776 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13777 (build-system python-build-system)
13778 (arguments
13779 `(#:phases
13780 (modify-phases %standard-phases
13781 (add-after 'unpack 'loosen-up-requirements
13782 (lambda _
13783 (substitute* "setup.py"
13784 (("==") ">="))
13785 #t)))))
13786 (propagated-inputs
13787 `(("python-biopython" ,python-biopython)
13788 ("python-configparser" ,python-configparser)
13789 ("python-cooler" ,python-cooler)
13790 ("python-future" ,python-future)
13791 ("python-intervaltree" ,python-intervaltree)
13792 ("python-jinja2" ,python-jinja2)
13793 ("python-matplotlib" ,python-matplotlib)
13794 ("python-numpy" ,python-numpy)
13795 ("python-pandas" ,python-pandas)
13796 ("python-pybigwig" ,python-pybigwig)
13797 ("python-pysam" ,python-pysam)
13798 ("python-scipy" ,python-scipy)
13799 ("python-six" ,python-six)
13800 ("python-tables" ,python-tables)
13801 ("python-unidecode" ,python-unidecode)))
13802 (home-page "http://hicexplorer.readthedocs.io")
13803 (synopsis "Process, analyze and visualize Hi-C data")
13804 (description
13805 "HiCExplorer is a powerful and easy to use set of tools to process,
13806 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13807 contact matrices, correction of contacts, TAD detection, A/B compartments,
13808 merging, reordering or chromosomes, conversion from different formats
13809 including cooler and detection of long-range contacts. Moreover, it allows
13810 the visualization of multiple contact matrices along with other types of data
13811 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13812 genomic scores), long range contacts and the visualization of viewpoints.")
13813 (license license:gpl3)))
13814
13815 (define-public python-pygenometracks
13816 (package
13817 (name "python-pygenometracks")
13818 (version "2.0")
13819 (source
13820 (origin
13821 (method url-fetch)
13822 (uri (pypi-uri "pyGenomeTracks" version))
13823 (sha256
13824 (base32
13825 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13826 (build-system python-build-system)
13827 (propagated-inputs
13828 `(("python-configparser" ,python-configparser)
13829 ("python-future" ,python-future)
13830 ("python-hicexplorer" ,python-hicexplorer)
13831 ("python-intervaltree" ,python-intervaltree)
13832 ("python-matplotlib" ,python-matplotlib)
13833 ("python-numpy" ,python-numpy)
13834 ("python-pybigwig" ,python-pybigwig)))
13835 (native-inputs
13836 `(("python-pytest" ,python-pytest)))
13837 (home-page "https://pygenometracks.readthedocs.io")
13838 (synopsis "Program and library to plot beautiful genome browser tracks")
13839 (description
13840 "This package aims to produce high-quality genome browser tracks that
13841 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13842 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13843 pyGenomeTracks can make plots with or without Hi-C data.")
13844 (license license:gpl3+)))
13845
13846 (define-public python-hic2cool
13847 (package
13848 (name "python-hic2cool")
13849 (version "0.4.2")
13850 (source
13851 (origin
13852 (method url-fetch)
13853 (uri (pypi-uri "hic2cool" version))
13854 (sha256
13855 (base32
13856 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13857 (build-system python-build-system)
13858 (arguments '(#:tests? #f)) ; no tests included
13859 (propagated-inputs
13860 `(("python-cooler" ,python-cooler)))
13861 (home-page "https://github.com/4dn-dcic/hic2cool")
13862 (synopsis "Converter for .hic and .cool files")
13863 (description
13864 "This package provides a converter between @code{.hic} files (from
13865 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13866 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13867 matrices.")
13868 (license license:expat)))
13869
13870 (define-public r-pore
13871 (package
13872 (name "r-pore")
13873 (version "0.24")
13874 (source
13875 (origin
13876 (method url-fetch)
13877 (uri
13878 (string-append "mirror://sourceforge/rpore/" version
13879 "/poRe_" version ".tar.gz"))
13880 (sha256
13881 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13882 (properties `((upstream-name . "poRe")))
13883 (build-system r-build-system)
13884 (propagated-inputs
13885 `(("r-bit64" ,r-bit64)
13886 ("r-data-table" ,r-data-table)
13887 ("r-rhdf5" ,r-rhdf5)
13888 ("r-shiny" ,r-shiny)
13889 ("r-svdialogs" ,r-svdialogs)))
13890 (home-page "https://sourceforge.net/projects/rpore/")
13891 (synopsis "Visualize Nanopore sequencing data")
13892 (description
13893 "This package provides graphical user interfaces to organize and visualize Nanopore
13894 sequencing data.")
13895 ;; This is free software but the license variant is unclear:
13896 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13897 (license license:bsd-3)))
13898
13899 (define-public r-xbioc
13900 (let ((revision "1")
13901 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13902 (package
13903 (name "r-xbioc")
13904 (version (git-version "0.1.15" revision commit))
13905 (source (origin
13906 (method git-fetch)
13907 (uri (git-reference
13908 (url "https://github.com/renozao/xbioc.git")
13909 (commit commit)))
13910 (file-name (git-file-name name version))
13911 (sha256
13912 (base32
13913 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13914 (build-system r-build-system)
13915 (propagated-inputs
13916 `(("r-annotationdbi" ,r-annotationdbi)
13917 ("r-assertthat" ,r-assertthat)
13918 ("r-biobase" ,r-biobase)
13919 ("r-biocinstaller" ,r-biocinstaller)
13920 ("r-digest" ,r-digest)
13921 ("r-pkgmaker" ,r-pkgmaker)
13922 ("r-plyr" ,r-plyr)
13923 ("r-reshape2" ,r-reshape2)
13924 ("r-stringr" ,r-stringr)))
13925 (home-page "https://github.com/renozao/xbioc/")
13926 (synopsis "Extra base functions for Bioconductor")
13927 (description "This package provides extra utility functions to perform
13928 common tasks in the analysis of omics data, leveraging and enhancing features
13929 provided by Bioconductor packages.")
13930 (license license:gpl3+))))
13931
13932 (define-public r-cssam
13933 (let ((revision "1")
13934 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13935 (package
13936 (name "r-cssam")
13937 (version (git-version "1.4" revision commit))
13938 (source (origin
13939 (method git-fetch)
13940 (uri (git-reference
13941 (url "https://github.com/shenorrLab/csSAM.git")
13942 (commit commit)))
13943 (file-name (git-file-name name version))
13944 (sha256
13945 (base32
13946 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13947 (build-system r-build-system)
13948 (propagated-inputs
13949 `(("r-formula" ,r-formula)
13950 ("r-ggplot2" ,r-ggplot2)
13951 ("r-pkgmaker" ,r-pkgmaker)
13952 ("r-plyr" ,r-plyr)
13953 ("r-rngtools" ,r-rngtools)
13954 ("r-scales" ,r-scales)))
13955 (home-page "https://github.com/shenorrLab/csSAM/")
13956 (synopsis "Cell type-specific statistical analysis of microarray")
13957 (description "This package implements the method csSAM that computes
13958 cell-specific differential expression from measured cell proportions using
13959 SAM.")
13960 ;; Any version
13961 (license license:lgpl2.1+))))
13962
13963 (define-public r-bseqsc
13964 (let ((revision "1")
13965 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13966 (package
13967 (name "r-bseqsc")
13968 (version (git-version "1.0" revision commit))
13969 (source (origin
13970 (method git-fetch)
13971 (uri (git-reference
13972 (url "https://github.com/shenorrLab/bseqsc.git")
13973 (commit commit)))
13974 (file-name (git-file-name name version))
13975 (sha256
13976 (base32
13977 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13978 (build-system r-build-system)
13979 (propagated-inputs
13980 `(("r-abind" ,r-abind)
13981 ("r-annotationdbi" ,r-annotationdbi)
13982 ("r-biobase" ,r-biobase)
13983 ("r-cssam" ,r-cssam)
13984 ("r-dplyr" ,r-dplyr)
13985 ("r-e1071" ,r-e1071)
13986 ("r-edger" ,r-edger)
13987 ("r-ggplot2" ,r-ggplot2)
13988 ("r-nmf" ,r-nmf)
13989 ("r-openxlsx" ,r-openxlsx)
13990 ("r-pkgmaker" ,r-pkgmaker)
13991 ("r-plyr" ,r-plyr)
13992 ("r-preprocesscore" ,r-preprocesscore)
13993 ("r-rngtools" ,r-rngtools)
13994 ("r-scales" ,r-scales)
13995 ("r-stringr" ,r-stringr)
13996 ("r-xbioc" ,r-xbioc)))
13997 (home-page "https://github.com/shenorrLab/bseqsc")
13998 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13999 (description "BSeq-sc is a bioinformatics analysis pipeline that
14000 leverages single-cell sequencing data to estimate cell type proportion and
14001 cell type-specific gene expression differences from RNA-seq data from bulk
14002 tissue samples. This is a companion package to the publication \"A
14003 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14004 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14005 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14006 (license license:gpl2+))))
14007
14008 (define-public porechop
14009 ;; The recommended way to install is to clone the git repository
14010 ;; https://github.com/rrwick/Porechop#installation
14011 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14012 (revision "1"))
14013 (package
14014 (name "porechop")
14015 (version (git-version "0.2.3" revision commit))
14016 (source
14017 (origin
14018 (method git-fetch)
14019 (uri (git-reference
14020 (url "https://github.com/rrwick/Porechop.git")
14021 (commit commit)))
14022 (file-name (git-file-name name version))
14023 (sha256
14024 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14025 (build-system python-build-system)
14026 (home-page "https://github.com/rrwick/porechop")
14027 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14028 (description
14029 "The porechop package is a tool for finding and removing adapters from Oxford
14030 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14031 has an adapter in its middle, it is treated as chimeric and chopped into
14032 separate reads. Porechop performs thorough alignments to effectively find
14033 adapters, even at low sequence identity. Porechop also supports demultiplexing
14034 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14035 Barcoding Kit or Rapid Barcoding Kit.")
14036 (license license:gpl3+))))
14037
14038 (define-public poretools
14039 ;; The latest release was in 2016 and the latest commit is from 2017
14040 ;; the recommended way to install is to clone the git repository
14041 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14042 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14043 (revision "1"))
14044 (package
14045 (name "poretools")
14046 (version (git-version "0.6.0" revision commit))
14047 (source
14048 (origin
14049 (method git-fetch)
14050 (uri (git-reference
14051 (url "https://github.com/arq5x/poretools.git")
14052 (commit commit)))
14053 (file-name (git-file-name name version))
14054 (sha256
14055 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14056 (build-system python-build-system)
14057 ;; requires python >=2.7, <3.0, and the same for python dependencies
14058 (arguments `(#:python ,python-2))
14059 (inputs
14060 `(("hdf5" ,hdf5)))
14061 (propagated-inputs
14062 `(("python-dateutil" ,python2-dateutil)
14063 ("python-h5py" ,python2-h5py)
14064 ("python-matplotlib" ,python2-matplotlib)
14065 ("python-pandas" ,python2-pandas)
14066 ("python-seaborn" ,python2-seaborn)))
14067 (home-page "https://poretools.readthedocs.io")
14068 (synopsis "Toolkit for working with nanopore sequencing data")
14069 (description
14070 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14071 This @code{poretools} package is a flexible toolkit for exploring datasets
14072 generated by nanopore sequencing devices for the purposes of quality control and
14073 downstream analysis. Poretools operates directly on the native FAST5, a variant
14074 of the Hierarchical Data Format (HDF5) standard.")
14075 (license license:expat))))
14076
14077 (define-public r-absfiltergsea
14078 (package
14079 (name "r-absfiltergsea")
14080 (version "1.5.1")
14081 (source
14082 (origin
14083 (method url-fetch)
14084 (uri (cran-uri "AbsFilterGSEA" version))
14085 (sha256
14086 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14087 (properties `((upstream-name . "AbsFilterGSEA")))
14088 (build-system r-build-system)
14089 (propagated-inputs
14090 `(("r-biobase" ,r-biobase)
14091 ("r-deseq" ,r-deseq)
14092 ("r-limma" ,r-limma)
14093 ("r-rcpp" ,r-rcpp)
14094 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14095 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14096 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14097 (description
14098 "This package provides a function that performs gene-permuting of a gene-set
14099 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14100 Without filtering, users can perform (original) two-tailed or one-tailed
14101 absolute GSEA.")
14102 (license license:gpl2)))
14103
14104 (define-public ngless
14105 (package
14106 (name "ngless")
14107 (version "0.9.1")
14108 (source
14109 (origin
14110 (method git-fetch)
14111 (uri (git-reference
14112 (url "https://gitlab.com/ngless/ngless.git")
14113 (commit (string-append "v" version))))
14114 (file-name (git-file-name name version))
14115 (sha256
14116 (base32
14117 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14118 (build-system haskell-build-system)
14119 (arguments
14120 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14121 ; error: parse error on input import
14122 ; import Options.Applicative
14123 #:phases
14124 (modify-phases %standard-phases
14125 (add-after 'unpack 'create-cabal-file
14126 (lambda _ (invoke "hpack") #t))
14127 ;; These tools are expected to be installed alongside ngless.
14128 (add-after 'install 'link-tools
14129 (lambda* (#:key inputs outputs #:allow-other-keys)
14130 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14131 (symlink (string-append (assoc-ref inputs "prodigal")
14132 "/bin/prodigal")
14133 (string-append bin "ngless-" ,version "-prodigal"))
14134 (symlink (string-append (assoc-ref inputs "minimap2")
14135 "/bin/minimap2")
14136 (string-append bin "ngless-" ,version "-minimap2"))
14137 (symlink (string-append (assoc-ref inputs "samtools")
14138 "/bin/samtools")
14139 (string-append bin "ngless-" ,version "-samtools"))
14140 (symlink (string-append (assoc-ref inputs "bwa")
14141 "/bin/bwa")
14142 (string-append bin "ngless-" ,version "-bwa"))
14143 #t))))))
14144 (inputs
14145 `(("prodigal" ,prodigal)
14146 ("bwa" ,bwa)
14147 ("samtools" ,samtools)
14148 ("minimap2" ,minimap2)
14149 ("ghc-aeson" ,ghc-aeson)
14150 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14151 ("ghc-async" ,ghc-async)
14152 ("ghc-atomic-write" ,ghc-atomic-write)
14153 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14154 ("ghc-chart" ,ghc-chart)
14155 ("ghc-chart-cairo" ,ghc-chart-cairo)
14156 ("ghc-conduit" ,ghc-conduit)
14157 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14158 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14159 ("ghc-conduit-extra" ,ghc-conduit-extra)
14160 ("ghc-configurator" ,ghc-configurator)
14161 ("ghc-convertible" ,ghc-convertible)
14162 ("ghc-data-default" ,ghc-data-default)
14163 ("ghc-double-conversion" ,ghc-double-conversion)
14164 ("ghc-edit-distance" ,ghc-edit-distance)
14165 ("ghc-either" ,ghc-either)
14166 ("ghc-errors" ,ghc-errors)
14167 ("ghc-extra" ,ghc-extra)
14168 ("ghc-filemanip" ,ghc-filemanip)
14169 ("ghc-file-embed" ,ghc-file-embed)
14170 ("ghc-gitrev" ,ghc-gitrev)
14171 ("ghc-hashtables" ,ghc-hashtables)
14172 ("ghc-http-conduit" ,ghc-http-conduit)
14173 ("ghc-inline-c" ,ghc-inline-c)
14174 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14175 ("ghc-intervalmap" ,ghc-intervalmap)
14176 ("ghc-missingh" ,ghc-missingh)
14177 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14178 ("ghc-parsec" ,ghc-parsec)
14179 ("ghc-regex" ,ghc-regex)
14180 ("ghc-safe" ,ghc-safe)
14181 ("ghc-safeio" ,ghc-safeio)
14182 ("ghc-strict" ,ghc-strict)
14183 ("ghc-tar" ,ghc-tar)
14184 ("ghc-text" ,ghc-text)
14185 ("ghc-unliftio" ,ghc-unliftio)
14186 ("ghc-unliftio-core" ,ghc-unliftio-core)
14187 ("ghc-vector" ,ghc-vector)
14188 ("ghc-yaml" ,ghc-yaml)
14189 ("ghc-zlib" ,ghc-zlib)))
14190 (propagated-inputs
14191 `(("r-r6" ,r-r6)
14192 ("r-hdf5r" ,r-hdf5r)
14193 ("r-iterators" ,r-iterators)
14194 ("r-itertools" ,r-itertools)
14195 ("r-matrix" ,r-matrix)))
14196 (native-inputs
14197 `(("ghc-hpack" ,ghc-hpack)
14198 ("ghc-quickcheck" ,ghc-quickcheck)
14199 ("ghc-test-framework" ,ghc-test-framework)
14200 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14201 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14202 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14203 (home-page "https://gitlab.com/ngless/ngless")
14204 (synopsis "DSL for processing next-generation sequencing data")
14205 (description "Ngless is a domain-specific language for
14206 @dfn{next-generation sequencing} (NGS) data processing.")
14207 (license license:expat)))
14208
14209 (define-public filtlong
14210 ;; The recommended way to install is to clone the git repository
14211 ;; https://github.com/rrwick/Filtlong#installation
14212 ;; and the lastest release is more than nine months old
14213 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14214 (revision "1"))
14215 (package
14216 (name "filtlong")
14217 (version (git-version "0.2.0" revision commit))
14218 (source
14219 (origin
14220 (method git-fetch)
14221 (uri (git-reference
14222 (url "https://github.com/rrwick/Filtlong.git")
14223 (commit commit)))
14224 (file-name (git-file-name name version))
14225 (sha256
14226 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14227 (build-system gnu-build-system)
14228 (arguments
14229 `(#:tests? #f ; no check target
14230 #:phases
14231 (modify-phases %standard-phases
14232 (delete 'configure)
14233 (replace 'install
14234 (lambda* (#:key outputs #:allow-other-keys)
14235 (let* ((out (assoc-ref outputs "out"))
14236 (bin (string-append out "/bin"))
14237 (scripts (string-append out "/share/filtlong/scripts")))
14238 (install-file "bin/filtlong" bin)
14239 (install-file "scripts/histogram.py" scripts)
14240 (install-file "scripts/read_info_histograms.sh" scripts))
14241 #t))
14242 (add-after 'install 'wrap-program
14243 (lambda* (#:key inputs outputs #:allow-other-keys)
14244 (let* ((out (assoc-ref outputs "out"))
14245 (path (getenv "PYTHONPATH")))
14246 (wrap-program (string-append out
14247 "/share/filtlong/scripts/histogram.py")
14248 `("PYTHONPATH" ":" prefix (,path))))
14249 #t))
14250 (add-before 'check 'patch-tests
14251 (lambda _
14252 (substitute* "scripts/read_info_histograms.sh"
14253 (("awk") (which "gawk")))
14254 #t)))))
14255 (inputs
14256 `(("gawk" ,gawk) ;for read_info_histograms.sh
14257 ("python" ,python-2) ;required for histogram.py
14258 ("zlib" ,zlib)))
14259 (home-page "https://github.com/rrwick/Filtlong/")
14260 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14261 (description
14262 "The Filtlong package is a tool for filtering long reads by quality.
14263 It can take a set of long reads and produce a smaller, better subset. It uses
14264 both read length (longer is better) and read identity (higher is better) when
14265 choosing which reads pass the filter.")
14266 (license (list license:gpl3 ;filtlong
14267 license:asl2.0))))) ;histogram.py