gnu: Use 'modify-phases' syntax.
[jackhill/guix/guix.git] / gnu / packages / bioinformatics.scm
1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;;
11 ;;; This file is part of GNU Guix.
12 ;;;
13 ;;; GNU Guix is free software; you can redistribute it and/or modify it
14 ;;; under the terms of the GNU General Public License as published by
15 ;;; the Free Software Foundation; either version 3 of the License, or (at
16 ;;; your option) any later version.
17 ;;;
18 ;;; GNU Guix is distributed in the hope that it will be useful, but
19 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
20 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21 ;;; GNU General Public License for more details.
22 ;;;
23 ;;; You should have received a copy of the GNU General Public License
24 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
25
26 (define-module (gnu packages bioinformatics)
27 #:use-module ((guix licenses) #:prefix license:)
28 #:use-module (guix packages)
29 #:use-module (guix utils)
30 #:use-module (guix download)
31 #:use-module (guix git-download)
32 #:use-module (guix hg-download)
33 #:use-module (guix build-system ant)
34 #:use-module (guix build-system gnu)
35 #:use-module (guix build-system cmake)
36 #:use-module (guix build-system ocaml)
37 #:use-module (guix build-system perl)
38 #:use-module (guix build-system python)
39 #:use-module (guix build-system r)
40 #:use-module (guix build-system ruby)
41 #:use-module (guix build-system trivial)
42 #:use-module (gnu packages)
43 #:use-module (gnu packages autotools)
44 #:use-module (gnu packages algebra)
45 #:use-module (gnu packages base)
46 #:use-module (gnu packages bash)
47 #:use-module (gnu packages bison)
48 #:use-module (gnu packages boost)
49 #:use-module (gnu packages compression)
50 #:use-module (gnu packages cpio)
51 #:use-module (gnu packages cran)
52 #:use-module (gnu packages curl)
53 #:use-module (gnu packages documentation)
54 #:use-module (gnu packages databases)
55 #:use-module (gnu packages datastructures)
56 #:use-module (gnu packages file)
57 #:use-module (gnu packages flex)
58 #:use-module (gnu packages gawk)
59 #:use-module (gnu packages gcc)
60 #:use-module (gnu packages gd)
61 #:use-module (gnu packages gtk)
62 #:use-module (gnu packages glib)
63 #:use-module (gnu packages graph)
64 #:use-module (gnu packages groff)
65 #:use-module (gnu packages guile)
66 #:use-module (gnu packages haskell)
67 #:use-module (gnu packages image)
68 #:use-module (gnu packages imagemagick)
69 #:use-module (gnu packages java)
70 #:use-module (gnu packages ldc)
71 #:use-module (gnu packages linux)
72 #:use-module (gnu packages logging)
73 #:use-module (gnu packages machine-learning)
74 #:use-module (gnu packages man)
75 #:use-module (gnu packages maths)
76 #:use-module (gnu packages mpi)
77 #:use-module (gnu packages ncurses)
78 #:use-module (gnu packages ocaml)
79 #:use-module (gnu packages pcre)
80 #:use-module (gnu packages parallel)
81 #:use-module (gnu packages pdf)
82 #:use-module (gnu packages perl)
83 #:use-module (gnu packages pkg-config)
84 #:use-module (gnu packages popt)
85 #:use-module (gnu packages protobuf)
86 #:use-module (gnu packages python)
87 #:use-module (gnu packages readline)
88 #:use-module (gnu packages ruby)
89 #:use-module (gnu packages serialization)
90 #:use-module (gnu packages shells)
91 #:use-module (gnu packages statistics)
92 #:use-module (gnu packages swig)
93 #:use-module (gnu packages tbb)
94 #:use-module (gnu packages tex)
95 #:use-module (gnu packages texinfo)
96 #:use-module (gnu packages textutils)
97 #:use-module (gnu packages time)
98 #:use-module (gnu packages tls)
99 #:use-module (gnu packages vim)
100 #:use-module (gnu packages web)
101 #:use-module (gnu packages xml)
102 #:use-module (gnu packages xorg)
103 #:use-module (srfi srfi-1)
104 #:use-module (ice-9 match))
105
106 (define-public r-ape
107 (package
108 (name "r-ape")
109 (version "4.1")
110 (source
111 (origin
112 (method url-fetch)
113 (uri (cran-uri "ape" version))
114 (sha256
115 (base32
116 "0959fiiy11rzfzrzaknmgrx64bhszj02l0ycz79k5a6bmpfzanlk"))))
117 (build-system r-build-system)
118 (propagated-inputs
119 `(("r-lattice" ,r-lattice)
120 ("r-nlme" ,r-nlme)))
121 (home-page "http://ape-package.ird.fr/")
122 (synopsis "Analyses of phylogenetics and evolution")
123 (description
124 "This package provides functions for reading, writing, plotting, and
125 manipulating phylogenetic trees, analyses of comparative data in a
126 phylogenetic framework, ancestral character analyses, analyses of
127 diversification and macroevolution, computing distances from DNA sequences,
128 and several other tools.")
129 (license license:gpl2+)))
130
131 (define-public aragorn
132 (package
133 (name "aragorn")
134 (version "1.2.38")
135 (source (origin
136 (method url-fetch)
137 (uri (string-append
138 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
139 version ".tgz"))
140 (sha256
141 (base32
142 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
143 (build-system gnu-build-system)
144 (arguments
145 `(#:tests? #f ; there are no tests
146 #:phases
147 (modify-phases %standard-phases
148 (delete 'configure)
149 (replace 'build
150 (lambda _
151 (zero? (system* "gcc"
152 "-O3"
153 "-ffast-math"
154 "-finline-functions"
155 "-o"
156 "aragorn"
157 (string-append "aragorn" ,version ".c")))))
158 (replace 'install
159 (lambda* (#:key outputs #:allow-other-keys)
160 (let* ((out (assoc-ref outputs "out"))
161 (bin (string-append out "/bin"))
162 (man (string-append out "/share/man/man1")))
163 (mkdir-p bin)
164 (install-file "aragorn" bin)
165 (mkdir-p man)
166 (install-file "aragorn.1" man))
167 #t)))))
168 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
169 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
170 (description
171 "Aragorn identifies transfer RNA, mitochondrial RNA and
172 transfer-messenger RNA from nucleotide sequences, based on homology to known
173 tRNA consensus sequences and RNA structure. It also outputs the secondary
174 structure of the predicted RNA.")
175 (license license:gpl2)))
176
177 (define-public bamm
178 (package
179 (name "bamm")
180 (version "1.7.3")
181 (source (origin
182 (method url-fetch)
183 ;; BamM is not available on pypi.
184 (uri (string-append
185 "https://github.com/Ecogenomics/BamM/archive/"
186 version ".tar.gz"))
187 (file-name (string-append name "-" version ".tar.gz"))
188 (sha256
189 (base32
190 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
191 (modules '((guix build utils)))
192 (snippet
193 `(begin
194 ;; Delete bundled htslib.
195 (delete-file-recursively "c/htslib-1.3.1")
196 #t))))
197 (build-system python-build-system)
198 (arguments
199 `(#:python ,python-2 ; BamM is Python 2 only.
200 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
201 ;; been modified from its original form.
202 #:configure-flags
203 (let ((htslib (assoc-ref %build-inputs "htslib")))
204 (list "--with-libhts-lib" (string-append htslib "/lib")
205 "--with-libhts-inc" (string-append htslib "/include/htslib")))
206 #:phases
207 (modify-phases %standard-phases
208 (add-after 'unpack 'autogen
209 (lambda _
210 (with-directory-excursion "c"
211 (let ((sh (which "sh")))
212 ;; Use autogen so that 'configure' works.
213 (substitute* "autogen.sh" (("/bin/sh") sh))
214 (setenv "CONFIG_SHELL" sh)
215 (substitute* "configure" (("/bin/sh") sh))
216 (zero? (system* "./autogen.sh"))))))
217 (delete 'build)
218 ;; Run tests after installation so compilation only happens once.
219 (delete 'check)
220 (add-after 'install 'wrap-executable
221 (lambda* (#:key outputs #:allow-other-keys)
222 (let* ((out (assoc-ref outputs "out"))
223 (path (getenv "PATH")))
224 (wrap-program (string-append out "/bin/bamm")
225 `("PATH" ":" prefix (,path))))
226 #t))
227 (add-after 'wrap-executable 'post-install-check
228 (lambda* (#:key inputs outputs #:allow-other-keys)
229 (setenv "PATH"
230 (string-append (assoc-ref outputs "out")
231 "/bin:"
232 (getenv "PATH")))
233 (setenv "PYTHONPATH"
234 (string-append
235 (assoc-ref outputs "out")
236 "/lib/python"
237 (string-take (string-take-right
238 (assoc-ref inputs "python") 5) 3)
239 "/site-packages:"
240 (getenv "PYTHONPATH")))
241 ;; There are 2 errors printed, but they are safe to ignore:
242 ;; 1) [E::hts_open_format] fail to open file ...
243 ;; 2) samtools view: failed to open ...
244 (zero? (system* "nosetests")))))))
245 (native-inputs
246 `(("autoconf" ,autoconf)
247 ("automake" ,automake)
248 ("libtool" ,libtool)
249 ("zlib" ,zlib)
250 ("python-nose" ,python2-nose)
251 ("python-pysam" ,python2-pysam)))
252 (inputs
253 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
254 ("samtools" ,samtools)
255 ("bwa" ,bwa)
256 ("grep" ,grep)
257 ("sed" ,sed)
258 ("coreutils" ,coreutils)))
259 (propagated-inputs
260 `(("python-numpy" ,python2-numpy)))
261 (home-page "http://ecogenomics.github.io/BamM/")
262 (synopsis "Metagenomics-focused BAM file manipulator")
263 (description
264 "BamM is a C library, wrapped in python, to efficiently generate and
265 parse BAM files, specifically for the analysis of metagenomic data. For
266 instance, it implements several methods to assess contig-wise read coverage.")
267 (license license:lgpl3+)))
268
269 (define-public bamtools
270 (package
271 (name "bamtools")
272 (version "2.4.1")
273 (source (origin
274 (method url-fetch)
275 (uri (string-append
276 "https://github.com/pezmaster31/bamtools/archive/v"
277 version ".tar.gz"))
278 (file-name (string-append name "-" version ".tar.gz"))
279 (sha256
280 (base32
281 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
282 (build-system cmake-build-system)
283 (arguments
284 `(#:tests? #f ;no "check" target
285 #:phases
286 (modify-phases %standard-phases
287 (add-before
288 'configure 'set-ldflags
289 (lambda* (#:key outputs #:allow-other-keys)
290 (setenv "LDFLAGS"
291 (string-append
292 "-Wl,-rpath="
293 (assoc-ref outputs "out") "/lib/bamtools")))))))
294 (inputs `(("zlib" ,zlib)))
295 (home-page "https://github.com/pezmaster31/bamtools")
296 (synopsis "C++ API and command-line toolkit for working with BAM data")
297 (description
298 "BamTools provides both a C++ API and a command-line toolkit for handling
299 BAM files.")
300 (license license:expat)))
301
302 (define-public bcftools
303 (package
304 (name "bcftools")
305 (version "1.5")
306 (source (origin
307 (method url-fetch)
308 (uri (string-append
309 "https://github.com/samtools/bcftools/releases/download/"
310 version "/bcftools-" version ".tar.bz2"))
311 (sha256
312 (base32
313 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
314 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
315 (modules '((guix build utils)))
316 (snippet
317 ;; Delete bundled htslib.
318 '(delete-file-recursively "htslib-1.5"))))
319 (build-system gnu-build-system)
320 (arguments
321 `(#:test-target "test"
322 #:configure-flags (list "--with-htslib=system")
323 #:make-flags
324 (list
325 "USE_GPL=1"
326 "LIBS=-lgsl -lgslcblas"
327 (string-append "prefix=" (assoc-ref %outputs "out"))
328 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
329 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
330 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
331 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
332 (string-append "PACKAGE_VERSION=" ,version))
333 #:phases
334 (modify-phases %standard-phases
335 (add-before 'check 'patch-tests
336 (lambda _
337 (substitute* "test/test.pl"
338 (("/bin/bash") (which "bash")))
339 #t)))))
340 (native-inputs
341 `(("htslib" ,htslib)
342 ("perl" ,perl)))
343 (inputs
344 `(("gsl" ,gsl)
345 ("zlib" ,zlib)))
346 (home-page "https://samtools.github.io/bcftools/")
347 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
348 (description
349 "BCFtools is a set of utilities that manipulate variant calls in the
350 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
351 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
352 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
353 (license (list license:gpl3+ license:expat))))
354
355 (define-public bedops
356 (package
357 (name "bedops")
358 (version "2.4.14")
359 (source (origin
360 (method url-fetch)
361 (uri (string-append "https://github.com/bedops/bedops/archive/v"
362 version ".tar.gz"))
363 (file-name (string-append name "-" version ".tar.gz"))
364 (sha256
365 (base32
366 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
367 (build-system gnu-build-system)
368 (arguments
369 '(#:tests? #f
370 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
371 #:phases
372 (modify-phases %standard-phases
373 (add-after 'unpack 'unpack-tarballs
374 (lambda _
375 ;; FIXME: Bedops includes tarballs of minimally patched upstream
376 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
377 ;; libraries because at least one of the libraries (zlib) is
378 ;; patched to add a C++ function definition (deflateInit2cpp).
379 ;; Until the Bedops developers offer a way to link against system
380 ;; libraries we have to build the in-tree copies of these three
381 ;; libraries.
382
383 ;; See upstream discussion:
384 ;; https://github.com/bedops/bedops/issues/124
385
386 ;; Unpack the tarballs to benefit from shebang patching.
387 (with-directory-excursion "third-party"
388 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
389 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
390 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
391 ;; Disable unpacking of tarballs in Makefile.
392 (substitute* "system.mk/Makefile.linux"
393 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
394 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
395 (substitute* "third-party/zlib-1.2.7/Makefile.in"
396 (("^SHELL=.*$") "SHELL=bash\n"))
397 #t))
398 (delete 'configure))))
399 (home-page "https://github.com/bedops/bedops")
400 (synopsis "Tools for high-performance genomic feature operations")
401 (description
402 "BEDOPS is a suite of tools to address common questions raised in genomic
403 studies---mostly with regard to overlap and proximity relationships between
404 data sets. It aims to be scalable and flexible, facilitating the efficient
405 and accurate analysis and management of large-scale genomic data.
406
407 BEDOPS provides tools that perform highly efficient and scalable Boolean and
408 other set operations, statistical calculations, archiving, conversion and
409 other management of genomic data of arbitrary scale. Tasks can be easily
410 split by chromosome for distributing whole-genome analyses across a
411 computational cluster.")
412 (license license:gpl2+)))
413
414 (define-public bedtools
415 (package
416 (name "bedtools")
417 (version "2.26.0")
418 (source (origin
419 (method url-fetch)
420 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
421 version ".tar.gz"))
422 (file-name (string-append name "-" version ".tar.gz"))
423 (sha256
424 (base32
425 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
426 (build-system gnu-build-system)
427 (native-inputs `(("python" ,python-2)))
428 (inputs `(("samtools" ,samtools)
429 ("zlib" ,zlib)))
430 (arguments
431 '(#:test-target "test"
432 #:phases
433 (modify-phases %standard-phases
434 (delete 'configure)
435 (replace 'install
436 (lambda* (#:key outputs #:allow-other-keys)
437 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
438 (for-each (lambda (file)
439 (install-file file bin))
440 (find-files "bin" ".*")))
441 #t)))))
442 (home-page "https://github.com/arq5x/bedtools2")
443 (synopsis "Tools for genome analysis and arithmetic")
444 (description
445 "Collectively, the bedtools utilities are a swiss-army knife of tools for
446 a wide-range of genomics analysis tasks. The most widely-used tools enable
447 genome arithmetic: that is, set theory on the genome. For example, bedtools
448 allows one to intersect, merge, count, complement, and shuffle genomic
449 intervals from multiple files in widely-used genomic file formats such as BAM,
450 BED, GFF/GTF, VCF.")
451 (license license:gpl2)))
452
453 ;; Later releases of bedtools produce files with more columns than
454 ;; what Ribotaper expects.
455 (define-public bedtools-2.18
456 (package (inherit bedtools)
457 (name "bedtools")
458 (version "2.18.0")
459 (source (origin
460 (method url-fetch)
461 (uri (string-append "https://github.com/arq5x/bedtools2/"
462 "archive/v" version ".tar.gz"))
463 (file-name (string-append name "-" version ".tar.gz"))
464 (sha256
465 (base32
466 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
467
468 (define-public ribotaper
469 (package
470 (name "ribotaper")
471 (version "1.3.1")
472 (source (origin
473 (method url-fetch)
474 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
475 "files/RiboTaper/RiboTaper_Version_"
476 version ".tar.gz"))
477 (sha256
478 (base32
479 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
480 (build-system gnu-build-system)
481 (inputs
482 `(("bedtools" ,bedtools-2.18)
483 ("samtools" ,samtools-0.1)
484 ("r-minimal" ,r-minimal)
485 ("r-foreach" ,r-foreach)
486 ("r-xnomial" ,r-xnomial)
487 ("r-domc" ,r-domc)
488 ("r-multitaper" ,r-multitaper)
489 ("r-seqinr" ,r-seqinr)))
490 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
491 (synopsis "Define translated ORFs using ribosome profiling data")
492 (description
493 "Ribotaper is a method for defining translated @dfn{open reading
494 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
495 provides the Ribotaper pipeline.")
496 (license license:gpl3+)))
497
498 (define-public ribodiff
499 (package
500 (name "ribodiff")
501 (version "0.2.2")
502 (source
503 (origin
504 (method url-fetch)
505 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
506 "archive/v" version ".tar.gz"))
507 (file-name (string-append name "-" version ".tar.gz"))
508 (sha256
509 (base32
510 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
511 (build-system python-build-system)
512 (arguments
513 `(#:python ,python-2
514 #:phases
515 (modify-phases %standard-phases
516 ;; Generate an installable executable script wrapper.
517 (add-after 'unpack 'patch-setup.py
518 (lambda _
519 (substitute* "setup.py"
520 (("^(.*)packages=.*" line prefix)
521 (string-append line "\n"
522 prefix "scripts=['scripts/TE.py'],\n")))
523 #t)))))
524 (inputs
525 `(("python-numpy" ,python2-numpy)
526 ("python-matplotlib" ,python2-matplotlib)
527 ("python-scipy" ,python2-scipy)
528 ("python-statsmodels" ,python2-statsmodels)))
529 (native-inputs
530 `(("python-mock" ,python2-mock)
531 ("python-nose" ,python2-nose)))
532 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
533 (synopsis "Detect translation efficiency changes from ribosome footprints")
534 (description "RiboDiff is a statistical tool that detects the protein
535 translational efficiency change from Ribo-Seq (ribosome footprinting) and
536 RNA-Seq data. It uses a generalized linear model to detect genes showing
537 difference in translational profile taking mRNA abundance into account. It
538 facilitates us to decipher the translational regulation that behave
539 independently with transcriptional regulation.")
540 (license license:gpl3+)))
541
542 (define-public bioawk
543 (package
544 (name "bioawk")
545 (version "1.0")
546 (source (origin
547 (method url-fetch)
548 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
549 version ".tar.gz"))
550 (file-name (string-append name "-" version ".tar.gz"))
551 (sha256
552 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
553 (build-system gnu-build-system)
554 (inputs
555 `(("zlib" ,zlib)))
556 (native-inputs
557 `(("bison" ,bison)))
558 (arguments
559 `(#:tests? #f ; There are no tests to run.
560 ;; Bison must generate files, before other targets can build.
561 #:parallel-build? #f
562 #:phases
563 (modify-phases %standard-phases
564 (delete 'configure) ; There is no configure phase.
565 (replace 'install
566 (lambda* (#:key outputs #:allow-other-keys)
567 (let* ((out (assoc-ref outputs "out"))
568 (bin (string-append out "/bin"))
569 (man (string-append out "/share/man/man1")))
570 (mkdir-p man)
571 (copy-file "awk.1" (string-append man "/bioawk.1"))
572 (install-file "bioawk" bin)))))))
573 (home-page "https://github.com/lh3/bioawk")
574 (synopsis "AWK with bioinformatics extensions")
575 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
576 support of several common biological data formats, including optionally gzip'ed
577 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
578 also adds a few built-in functions and a command line option to use TAB as the
579 input/output delimiter. When the new functionality is not used, bioawk is
580 intended to behave exactly the same as the original BWK awk.")
581 (license license:x11)))
582
583 (define-public python2-pybedtools
584 (package
585 (name "python2-pybedtools")
586 (version "0.6.9")
587 (source (origin
588 (method url-fetch)
589 (uri (string-append
590 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
591 version ".tar.gz"))
592 (sha256
593 (base32
594 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
595 (build-system python-build-system)
596 (arguments `(#:python ,python-2)) ; no Python 3 support
597 (inputs
598 `(("python-matplotlib" ,python2-matplotlib)))
599 (propagated-inputs
600 `(("bedtools" ,bedtools)
601 ("samtools" ,samtools)))
602 (native-inputs
603 `(("python-cython" ,python2-cython)
604 ("python-pyyaml" ,python2-pyyaml)
605 ("python-nose" ,python2-nose)))
606 (home-page "https://pythonhosted.org/pybedtools/")
607 (synopsis "Python wrapper for BEDtools programs")
608 (description
609 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
610 which are widely used for genomic interval manipulation or \"genome algebra\".
611 pybedtools extends BEDTools by offering feature-level manipulations from with
612 Python.")
613 (license license:gpl2+)))
614
615 (define-public python-biom-format
616 (package
617 (name "python-biom-format")
618 (version "2.1.6")
619 (source
620 (origin
621 (method url-fetch)
622 ;; Use GitHub as source because PyPI distribution does not contain
623 ;; test data: https://github.com/biocore/biom-format/issues/693
624 (uri (string-append "https://github.com/biocore/biom-format/archive/"
625 version ".tar.gz"))
626 (file-name (string-append name "-" version ".tar.gz"))
627 (sha256
628 (base32
629 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
630 (build-system python-build-system)
631 (propagated-inputs
632 `(("python-numpy" ,python-numpy)
633 ("python-scipy" ,python-scipy)
634 ("python-future" ,python-future)
635 ("python-click" ,python-click)
636 ("python-h5py" ,python-h5py)
637 ("python-pandas" ,python-pandas)))
638 (native-inputs
639 `(("python-nose" ,python-nose)))
640 (home-page "http://www.biom-format.org")
641 (synopsis "Biological Observation Matrix (BIOM) format utilities")
642 (description
643 "The BIOM file format is designed to be a general-use format for
644 representing counts of observations e.g. operational taxonomic units, KEGG
645 orthology groups or lipid types, in one or more biological samples
646 e.g. microbiome samples, genomes, metagenomes.")
647 (license license:bsd-3)
648 (properties `((python2-variant . ,(delay python2-biom-format))))))
649
650 (define-public python2-biom-format
651 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
652 (package
653 (inherit base)
654 (arguments
655 `(#:phases
656 (modify-phases %standard-phases
657 ;; Do not require the unmaintained pyqi library.
658 (add-after 'unpack 'remove-pyqi
659 (lambda _
660 (substitute* "setup.py"
661 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
662 #t)))
663 ,@(package-arguments base))))))
664
665 (define-public bioperl-minimal
666 (let* ((inputs `(("perl-module-build" ,perl-module-build)
667 ("perl-data-stag" ,perl-data-stag)
668 ("perl-libwww" ,perl-libwww)
669 ("perl-uri" ,perl-uri)))
670 (transitive-inputs
671 (map (compose package-name cadr)
672 (delete-duplicates
673 (concatenate
674 (map (compose package-transitive-target-inputs cadr) inputs))))))
675 (package
676 (name "bioperl-minimal")
677 (version "1.7.0")
678 (source
679 (origin
680 (method url-fetch)
681 (uri (string-append "https://github.com/bioperl/bioperl-live/"
682 "archive/release-"
683 (string-map (lambda (c)
684 (if (char=? c #\.)
685 #\- c)) version)
686 ".tar.gz"))
687 (sha256
688 (base32
689 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
690 (build-system perl-build-system)
691 (arguments
692 `(#:phases
693 (modify-phases %standard-phases
694 (add-after
695 'install 'wrap-programs
696 (lambda* (#:key outputs #:allow-other-keys)
697 ;; Make sure all executables in "bin" find the required Perl
698 ;; modules at runtime. As the PERL5LIB variable contains also
699 ;; the paths of native inputs, we pick the transitive target
700 ;; inputs from %build-inputs.
701 (let* ((out (assoc-ref outputs "out"))
702 (bin (string-append out "/bin/"))
703 (path (string-join
704 (cons (string-append out "/lib/perl5/site_perl")
705 (map (lambda (name)
706 (assoc-ref %build-inputs name))
707 ',transitive-inputs))
708 ":")))
709 (for-each (lambda (file)
710 (wrap-program file
711 `("PERL5LIB" ":" prefix (,path))))
712 (find-files bin "\\.pl$"))
713 #t))))))
714 (inputs inputs)
715 (native-inputs
716 `(("perl-test-most" ,perl-test-most)))
717 (home-page "http://search.cpan.org/dist/BioPerl")
718 (synopsis "Bioinformatics toolkit")
719 (description
720 "BioPerl is the product of a community effort to produce Perl code which
721 is useful in biology. Examples include Sequence objects, Alignment objects
722 and database searching objects. These objects not only do what they are
723 advertised to do in the documentation, but they also interact - Alignment
724 objects are made from the Sequence objects, Sequence objects have access to
725 Annotation and SeqFeature objects and databases, Blast objects can be
726 converted to Alignment objects, and so on. This means that the objects
727 provide a coordinated and extensible framework to do computational biology.")
728 (license license:perl-license))))
729
730 (define-public python-biopython
731 (package
732 (name "python-biopython")
733 (version "1.68")
734 (source (origin
735 (method url-fetch)
736 ;; use PyPi rather than biopython.org to ease updating
737 (uri (pypi-uri "biopython" version))
738 (sha256
739 (base32
740 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
741 (build-system python-build-system)
742 (arguments
743 `(#:phases
744 (modify-phases %standard-phases
745 (add-before 'check 'set-home
746 ;; Some tests require a home directory to be set.
747 (lambda _ (setenv "HOME" "/tmp") #t)))))
748 (propagated-inputs
749 `(("python-numpy" ,python-numpy)))
750 (home-page "http://biopython.org/")
751 (synopsis "Tools for biological computation in Python")
752 (description
753 "Biopython is a set of tools for biological computation including parsers
754 for bioinformatics files into Python data structures; interfaces to common
755 bioinformatics programs; a standard sequence class and tools for performing
756 common operations on them; code to perform data classification; code for
757 dealing with alignments; code making it easy to split up parallelizable tasks
758 into separate processes; and more.")
759 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
760
761 (define-public python2-biopython
762 (package-with-python2 python-biopython))
763
764 ;; An outdated version of biopython is required for seqmagick, see
765 ;; https://github.com/fhcrc/seqmagick/issues/59
766 ;; When that issue has been resolved this package should be removed.
767 (define python2-biopython-1.66
768 (package
769 (inherit python2-biopython)
770 (version "1.66")
771 (source (origin
772 (method url-fetch)
773 (uri (pypi-uri "biopython" version))
774 (sha256
775 (base32
776 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
777
778 (define-public bpp-core
779 ;; The last release was in 2014 and the recommended way to install from source
780 ;; is to clone the git repository, so we do this.
781 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
782 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
783 (package
784 (name "bpp-core")
785 (version (string-append "2.2.0-1." (string-take commit 7)))
786 (source (origin
787 (method git-fetch)
788 (uri (git-reference
789 (url "http://biopp.univ-montp2.fr/git/bpp-core")
790 (commit commit)))
791 (file-name (string-append name "-" version "-checkout"))
792 (sha256
793 (base32
794 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
795 (build-system cmake-build-system)
796 (arguments
797 `(#:parallel-build? #f))
798 (inputs
799 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
800 ; compile all of the bpp packages with GCC 5.
801 (home-page "http://biopp.univ-montp2.fr")
802 (synopsis "C++ libraries for Bioinformatics")
803 (description
804 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
805 analysis, phylogenetics, molecular evolution and population genetics. It is
806 Object Oriented and is designed to be both easy to use and computer efficient.
807 Bio++ intends to help programmers to write computer expensive programs, by
808 providing them a set of re-usable tools.")
809 (license license:cecill-c))))
810
811 (define-public bpp-phyl
812 ;; The last release was in 2014 and the recommended way to install from source
813 ;; is to clone the git repository, so we do this.
814 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
815 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
816 (package
817 (name "bpp-phyl")
818 (version (string-append "2.2.0-1." (string-take commit 7)))
819 (source (origin
820 (method git-fetch)
821 (uri (git-reference
822 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
823 (commit commit)))
824 (file-name (string-append name "-" version "-checkout"))
825 (sha256
826 (base32
827 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
828 (build-system cmake-build-system)
829 (arguments
830 `(#:parallel-build? #f
831 ;; If out-of-source, test data is not copied into the build directory
832 ;; so the tests fail.
833 #:out-of-source? #f))
834 (inputs
835 `(("bpp-core" ,bpp-core)
836 ("bpp-seq" ,bpp-seq)
837 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
838 ;; modern GCC.
839 ("gcc" ,gcc-5)))
840 (home-page "http://biopp.univ-montp2.fr")
841 (synopsis "Bio++ phylogenetic Library")
842 (description
843 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
844 analysis, phylogenetics, molecular evolution and population genetics. This
845 library provides phylogenetics-related modules.")
846 (license license:cecill-c))))
847
848 (define-public bpp-popgen
849 ;; The last release was in 2014 and the recommended way to install from source
850 ;; is to clone the git repository, so we do this.
851 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
852 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
853 (package
854 (name "bpp-popgen")
855 (version (string-append "2.2.0-1." (string-take commit 7)))
856 (source (origin
857 (method git-fetch)
858 (uri (git-reference
859 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
860 (commit commit)))
861 (file-name (string-append name "-" version "-checkout"))
862 (sha256
863 (base32
864 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
865 (build-system cmake-build-system)
866 (arguments
867 `(#:parallel-build? #f
868 #:tests? #f)) ; There are no tests.
869 (inputs
870 `(("bpp-core" ,bpp-core)
871 ("bpp-seq" ,bpp-seq)
872 ("gcc" ,gcc-5)))
873 (home-page "http://biopp.univ-montp2.fr")
874 (synopsis "Bio++ population genetics library")
875 (description
876 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
877 analysis, phylogenetics, molecular evolution and population genetics. This
878 library provides population genetics-related modules.")
879 (license license:cecill-c))))
880
881 (define-public bpp-seq
882 ;; The last release was in 2014 and the recommended way to install from source
883 ;; is to clone the git repository, so we do this.
884 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
885 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
886 (package
887 (name "bpp-seq")
888 (version (string-append "2.2.0-1." (string-take commit 7)))
889 (source (origin
890 (method git-fetch)
891 (uri (git-reference
892 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
893 (commit commit)))
894 (file-name (string-append name "-" version "-checkout"))
895 (sha256
896 (base32
897 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
898 (build-system cmake-build-system)
899 (arguments
900 `(#:parallel-build? #f
901 ;; If out-of-source, test data is not copied into the build directory
902 ;; so the tests fail.
903 #:out-of-source? #f))
904 (inputs
905 `(("bpp-core" ,bpp-core)
906 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
907 (home-page "http://biopp.univ-montp2.fr")
908 (synopsis "Bio++ sequence library")
909 (description
910 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
911 analysis, phylogenetics, molecular evolution and population genetics. This
912 library provides sequence-related modules.")
913 (license license:cecill-c))))
914
915 (define-public bppsuite
916 ;; The last release was in 2014 and the recommended way to install from source
917 ;; is to clone the git repository, so we do this.
918 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
919 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
920 (package
921 (name "bppsuite")
922 (version (string-append "2.2.0-1." (string-take commit 7)))
923 (source (origin
924 (method git-fetch)
925 (uri (git-reference
926 (url "http://biopp.univ-montp2.fr/git/bppsuite")
927 (commit commit)))
928 (file-name (string-append name "-" version "-checkout"))
929 (sha256
930 (base32
931 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
932 (build-system cmake-build-system)
933 (arguments
934 `(#:parallel-build? #f
935 #:tests? #f)) ; There are no tests.
936 (native-inputs
937 `(("groff" ,groff)
938 ("man-db" ,man-db)
939 ("texinfo" ,texinfo)))
940 (inputs
941 `(("bpp-core" ,bpp-core)
942 ("bpp-seq" ,bpp-seq)
943 ("bpp-phyl" ,bpp-phyl)
944 ("bpp-phyl" ,bpp-popgen)
945 ("gcc" ,gcc-5)))
946 (home-page "http://biopp.univ-montp2.fr")
947 (synopsis "Bioinformatics tools written with the Bio++ libraries")
948 (description
949 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
950 analysis, phylogenetics, molecular evolution and population genetics. This
951 package provides command line tools using the Bio++ library.")
952 (license license:cecill-c))))
953
954 (define-public blast+
955 (package
956 (name "blast+")
957 (version "2.6.0")
958 (source (origin
959 (method url-fetch)
960 (uri (string-append
961 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
962 version "/ncbi-blast-" version "+-src.tar.gz"))
963 (sha256
964 (base32
965 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
966 (patches (search-patches "blast+-fix-makefile.patch"))
967 (modules '((guix build utils)))
968 (snippet
969 '(begin
970 ;; Remove bundled bzip2, zlib and pcre.
971 (delete-file-recursively "c++/src/util/compress/bzip2")
972 (delete-file-recursively "c++/src/util/compress/zlib")
973 (delete-file-recursively "c++/src/util/regexp")
974 (substitute* "c++/src/util/compress/Makefile.in"
975 (("bzip2 zlib api") "api"))
976 ;; Remove useless msbuild directory
977 (delete-file-recursively
978 "c++/src/build-system/project_tree_builder/msbuild")
979 #t))))
980 (build-system gnu-build-system)
981 (arguments
982 `(;; There are two(!) tests for this massive library, and both fail with
983 ;; "unparsable timing stats".
984 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
985 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
986 #:tests? #f
987 #:out-of-source? #t
988 #:parallel-build? #f ; not supported
989 #:phases
990 (modify-phases %standard-phases
991 (add-before
992 'configure 'set-HOME
993 ;; $HOME needs to be set at some point during the configure phase
994 (lambda _ (setenv "HOME" "/tmp") #t))
995 (add-after
996 'unpack 'enter-dir
997 (lambda _ (chdir "c++") #t))
998 (add-after
999 'enter-dir 'fix-build-system
1000 (lambda _
1001 (define (which* cmd)
1002 (cond ((string=? cmd "date")
1003 ;; make call to "date" deterministic
1004 "date -d @0")
1005 ((which cmd)
1006 => identity)
1007 (else
1008 (format (current-error-port)
1009 "WARNING: Unable to find absolute path for ~s~%"
1010 cmd)
1011 #f)))
1012
1013 ;; Rewrite hardcoded paths to various tools
1014 (substitute* (append '("src/build-system/configure.ac"
1015 "src/build-system/configure"
1016 "src/build-system/helpers/run_with_lock.c"
1017 "scripts/common/impl/if_diff.sh"
1018 "scripts/common/impl/run_with_lock.sh"
1019 "src/build-system/Makefile.configurables.real"
1020 "src/build-system/Makefile.in.top"
1021 "src/build-system/Makefile.meta.gmake=no"
1022 "src/build-system/Makefile.meta.in"
1023 "src/build-system/Makefile.meta_l"
1024 "src/build-system/Makefile.meta_p"
1025 "src/build-system/Makefile.meta_r"
1026 "src/build-system/Makefile.mk.in"
1027 "src/build-system/Makefile.requirements"
1028 "src/build-system/Makefile.rules_with_autodep.in")
1029 (find-files "scripts/common/check" "\\.sh$"))
1030 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1031 (or (which* cmd) all)))
1032
1033 (substitute* (find-files "src/build-system" "^config.*")
1034 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1035 (("^PATH=.*") ""))
1036
1037 ;; rewrite "/var/tmp" in check script
1038 (substitute* "scripts/common/check/check_make_unix.sh"
1039 (("/var/tmp") "/tmp"))
1040
1041 ;; do not reset PATH
1042 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1043 (("^ *PATH=.*") "")
1044 (("action=/bin/") "action=")
1045 (("export PATH") ":"))
1046 #t))
1047 (replace
1048 'configure
1049 (lambda* (#:key inputs outputs #:allow-other-keys)
1050 (let ((out (assoc-ref outputs "out"))
1051 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1052 (include (string-append (assoc-ref outputs "include")
1053 "/include/ncbi-tools++")))
1054 ;; The 'configure' script doesn't recognize things like
1055 ;; '--enable-fast-install'.
1056 (zero? (system* "./configure.orig"
1057 (string-append "--with-build-root=" (getcwd) "/build")
1058 (string-append "--prefix=" out)
1059 (string-append "--libdir=" lib)
1060 (string-append "--includedir=" include)
1061 (string-append "--with-bz2="
1062 (assoc-ref inputs "bzip2"))
1063 (string-append "--with-z="
1064 (assoc-ref inputs "zlib"))
1065 (string-append "--with-pcre="
1066 (assoc-ref inputs "pcre"))
1067 ;; Each library is built twice by default, once
1068 ;; with "-static" in its name, and again
1069 ;; without.
1070 "--without-static"
1071 "--with-dll"))))))))
1072 (outputs '("out" ; 21 MB
1073 "lib" ; 226 MB
1074 "include")) ; 33 MB
1075 (inputs
1076 `(("bzip2" ,bzip2)
1077 ("zlib" ,zlib)
1078 ("pcre" ,pcre)
1079 ("perl" ,perl)
1080 ("python" ,python-wrapper)))
1081 (native-inputs
1082 `(("cpio" ,cpio)))
1083 (home-page "http://blast.ncbi.nlm.nih.gov")
1084 (synopsis "Basic local alignment search tool")
1085 (description
1086 "BLAST is a popular method of performing a DNA or protein sequence
1087 similarity search, using heuristics to produce results quickly. It also
1088 calculates an “expect value” that estimates how many matches would have
1089 occurred at a given score by chance, which can aid a user in judging how much
1090 confidence to have in an alignment.")
1091 ;; Most of the sources are in the public domain, with the following
1092 ;; exceptions:
1093 ;; * Expat:
1094 ;; * ./c++/include/util/bitset/
1095 ;; * ./c++/src/html/ncbi_menu*.js
1096 ;; * Boost license:
1097 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1098 ;; * LGPL 2+:
1099 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1100 ;; * ASL 2.0:
1101 ;; * ./c++/src/corelib/teamcity_*
1102 (license (list license:public-domain
1103 license:expat
1104 license:boost1.0
1105 license:lgpl2.0+
1106 license:asl2.0))))
1107
1108 (define-public bless
1109 (package
1110 (name "bless")
1111 (version "1p02")
1112 (source (origin
1113 (method url-fetch)
1114 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1115 version ".tgz"))
1116 (sha256
1117 (base32
1118 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1119 (modules '((guix build utils)))
1120 (snippet
1121 `(begin
1122 ;; Remove bundled boost, pigz, zlib, and .git directory
1123 ;; FIXME: also remove bundled sources for murmurhash3 and
1124 ;; kmc once packaged.
1125 (delete-file-recursively "boost")
1126 (delete-file-recursively "pigz")
1127 (delete-file-recursively "google-sparsehash")
1128 (delete-file-recursively "zlib")
1129 (delete-file-recursively ".git")
1130 #t))))
1131 (build-system gnu-build-system)
1132 (arguments
1133 '(#:tests? #f ;no "check" target
1134 #:make-flags
1135 (list (string-append "ZLIB="
1136 (assoc-ref %build-inputs "zlib")
1137 "/lib/libz.a")
1138 (string-append "LDFLAGS="
1139 (string-join '("-lboost_filesystem"
1140 "-lboost_system"
1141 "-lboost_iostreams"
1142 "-lz"
1143 "-fopenmp"
1144 "-std=c++11"))))
1145 #:phases
1146 (modify-phases %standard-phases
1147 (add-after 'unpack 'do-not-build-bundled-pigz
1148 (lambda* (#:key inputs outputs #:allow-other-keys)
1149 (substitute* "Makefile"
1150 (("cd pigz/pigz-2.3.3; make") ""))
1151 #t))
1152 (add-after 'unpack 'patch-paths-to-executables
1153 (lambda* (#:key inputs outputs #:allow-other-keys)
1154 (substitute* "parse_args.cpp"
1155 (("kmc_binary = .*")
1156 (string-append "kmc_binary = \""
1157 (assoc-ref outputs "out")
1158 "/bin/kmc\";"))
1159 (("pigz_binary = .*")
1160 (string-append "pigz_binary = \""
1161 (assoc-ref inputs "pigz")
1162 "/bin/pigz\";")))
1163 #t))
1164 (replace 'install
1165 (lambda* (#:key outputs #:allow-other-keys)
1166 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1167 (for-each (lambda (file)
1168 (install-file file bin))
1169 '("bless" "kmc/bin/kmc"))
1170 #t)))
1171 (delete 'configure))))
1172 (native-inputs
1173 `(("perl" ,perl)))
1174 (inputs
1175 `(("openmpi" ,openmpi)
1176 ("boost" ,boost)
1177 ("sparsehash" ,sparsehash)
1178 ("pigz" ,pigz)
1179 ("zlib" ,zlib)))
1180 (supported-systems '("x86_64-linux"))
1181 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1182 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1183 (description
1184 "@dfn{Bloom-filter-based error correction solution for high-throughput
1185 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1186 correction tool for genomic reads produced by @dfn{Next-generation
1187 sequencing} (NGS). BLESS produces accurate correction results with much less
1188 memory compared with previous solutions and is also able to tolerate a higher
1189 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1190 errors at the end of reads.")
1191 (license license:gpl3+)))
1192
1193 (define-public bowtie
1194 (package
1195 (name "bowtie")
1196 (version "2.3.2")
1197 (source (origin
1198 (method url-fetch)
1199 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1200 version ".tar.gz"))
1201 (file-name (string-append name "-" version ".tar.gz"))
1202 (sha256
1203 (base32
1204 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1205 (modules '((guix build utils)))
1206 (snippet
1207 '(substitute* "Makefile"
1208 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1209 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1210 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1211 (build-system gnu-build-system)
1212 (inputs
1213 `(("perl" ,perl)
1214 ("perl-clone" ,perl-clone)
1215 ("perl-test-deep" ,perl-test-deep)
1216 ("perl-test-simple" ,perl-test-simple)
1217 ("python" ,python-2)
1218 ("tbb" ,tbb)
1219 ("zlib" ,zlib)))
1220 (arguments
1221 '(#:make-flags
1222 (list "allall"
1223 "WITH_TBB=1"
1224 (string-append "prefix=" (assoc-ref %outputs "out")))
1225 #:phases
1226 (modify-phases %standard-phases
1227 (delete 'configure)
1228 (replace 'check
1229 (lambda* (#:key outputs #:allow-other-keys)
1230 (zero? (system* "perl"
1231 "scripts/test/simple_tests.pl"
1232 "--bowtie2=./bowtie2"
1233 "--bowtie2-build=./bowtie2-build")))))))
1234 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1235 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1236 (description
1237 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1238 reads to long reference sequences. It is particularly good at aligning reads
1239 of about 50 up to 100s or 1,000s of characters, and particularly good at
1240 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1241 genome with an FM Index to keep its memory footprint small: for the human
1242 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1243 gapped, local, and paired-end alignment modes.")
1244 (supported-systems '("x86_64-linux"))
1245 (license license:gpl3+)))
1246
1247 (define-public tophat
1248 (package
1249 (name "tophat")
1250 (version "2.1.0")
1251 (source (origin
1252 (method url-fetch)
1253 (uri (string-append
1254 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1255 version ".tar.gz"))
1256 (sha256
1257 (base32
1258 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1259 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1260 (modules '((guix build utils)))
1261 (snippet
1262 '(begin
1263 ;; Remove bundled SeqAn and samtools
1264 (delete-file-recursively "src/SeqAn-1.3")
1265 (delete-file-recursively "src/samtools-0.1.18")
1266 #t))))
1267 (build-system gnu-build-system)
1268 (arguments
1269 '(#:parallel-build? #f ; not supported
1270 #:phases
1271 (modify-phases %standard-phases
1272 (add-after 'unpack 'use-system-samtools
1273 (lambda* (#:key inputs #:allow-other-keys)
1274 (substitute* "src/Makefile.in"
1275 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1276 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1277 (("SAMPROG = samtools_0\\.1\\.18") "")
1278 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1279 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1280 (substitute* '("src/common.cpp"
1281 "src/tophat.py")
1282 (("samtools_0.1.18") (which "samtools")))
1283 (substitute* '("src/common.h"
1284 "src/bam2fastx.cpp")
1285 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1286 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1287 (substitute* '("src/bwt_map.h"
1288 "src/map2gtf.h"
1289 "src/align_status.h")
1290 (("#include <bam.h>") "#include <samtools/bam.h>")
1291 (("#include <sam.h>") "#include <samtools/sam.h>"))
1292 #t)))))
1293 (inputs
1294 `(("boost" ,boost)
1295 ("bowtie" ,bowtie)
1296 ("samtools" ,samtools-0.1)
1297 ("ncurses" ,ncurses)
1298 ("python" ,python-2)
1299 ("perl" ,perl)
1300 ("zlib" ,zlib)
1301 ("seqan" ,seqan)))
1302 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1303 (synopsis "Spliced read mapper for RNA-Seq data")
1304 (description
1305 "TopHat is a fast splice junction mapper for nucleotide sequence
1306 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1307 mammalian-sized genomes using the ultra high-throughput short read
1308 aligner Bowtie, and then analyzes the mapping results to identify
1309 splice junctions between exons.")
1310 ;; TopHat is released under the Boost Software License, Version 1.0
1311 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1312 (license license:boost1.0)))
1313
1314 (define-public bwa
1315 (package
1316 (name "bwa")
1317 (version "0.7.15")
1318 (source (origin
1319 (method url-fetch)
1320 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1321 version ".tar.bz2"))
1322 (sha256
1323 (base32
1324 "0585ikg0gv0mpyw9iq0bq9n0hr95867bbv8jbzs9pk4slkpsymig"))))
1325 (build-system gnu-build-system)
1326 (arguments
1327 '(#:tests? #f ;no "check" target
1328 #:phases
1329 (modify-phases %standard-phases
1330 (replace 'install
1331 (lambda* (#:key outputs #:allow-other-keys)
1332 (let ((bin (string-append
1333 (assoc-ref outputs "out") "/bin"))
1334 (doc (string-append
1335 (assoc-ref outputs "out") "/share/doc/bwa"))
1336 (man (string-append
1337 (assoc-ref outputs "out") "/share/man/man1")))
1338 (install-file "bwa" bin)
1339 (install-file "README.md" doc)
1340 (install-file "bwa.1" man))
1341 #t))
1342 ;; no "configure" script
1343 (delete 'configure))))
1344 (inputs `(("zlib" ,zlib)))
1345 ;; Non-portable SSE instructions are used so building fails on platforms
1346 ;; other than x86_64.
1347 (supported-systems '("x86_64-linux"))
1348 (home-page "http://bio-bwa.sourceforge.net/")
1349 (synopsis "Burrows-Wheeler sequence aligner")
1350 (description
1351 "BWA is a software package for mapping low-divergent sequences against a
1352 large reference genome, such as the human genome. It consists of three
1353 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1354 designed for Illumina sequence reads up to 100bp, while the rest two for
1355 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1356 features such as long-read support and split alignment, but BWA-MEM, which is
1357 the latest, is generally recommended for high-quality queries as it is faster
1358 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1359 70-100bp Illumina reads.")
1360 (license license:gpl3+)))
1361
1362 (define-public bwa-pssm
1363 (package (inherit bwa)
1364 (name "bwa-pssm")
1365 (version "0.5.11")
1366 (source (origin
1367 (method url-fetch)
1368 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1369 "archive/" version ".tar.gz"))
1370 (file-name (string-append name "-" version ".tar.gz"))
1371 (sha256
1372 (base32
1373 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1374 (build-system gnu-build-system)
1375 (inputs
1376 `(("gdsl" ,gdsl)
1377 ("zlib" ,zlib)
1378 ("perl" ,perl)))
1379 (home-page "http://bwa-pssm.binf.ku.dk/")
1380 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1381 (description
1382 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1383 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1384 existing aligners it is fast and sensitive. Unlike most other aligners,
1385 however, it is also adaptible in the sense that one can direct the alignment
1386 based on known biases within the data set. It is coded as a modification of
1387 the original BWA alignment program and shares the genome index structure as
1388 well as many of the command line options.")
1389 (license license:gpl3+)))
1390
1391 (define-public python2-bx-python
1392 (package
1393 (name "python2-bx-python")
1394 (version "0.7.3")
1395 (source (origin
1396 (method url-fetch)
1397 (uri (pypi-uri "bx-python" version))
1398 (sha256
1399 (base32
1400 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1401 (modules '((guix build utils)))
1402 (snippet
1403 '(substitute* "setup.py"
1404 ;; remove dependency on outdated "distribute" module
1405 (("^from distribute_setup import use_setuptools") "")
1406 (("^use_setuptools\\(\\)") "")))))
1407 (build-system python-build-system)
1408 (arguments
1409 `(#:tests? #f ;tests fail because test data are not included
1410 #:python ,python-2))
1411 (inputs
1412 `(("python-numpy" ,python2-numpy)
1413 ("zlib" ,zlib)))
1414 (native-inputs
1415 `(("python-nose" ,python2-nose)))
1416 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1417 (synopsis "Tools for manipulating biological data")
1418 (description
1419 "bx-python provides tools for manipulating biological data, particularly
1420 multiple sequence alignments.")
1421 (license license:expat)))
1422
1423 (define-public python-pysam
1424 (package
1425 (name "python-pysam")
1426 (version "0.11.2.2")
1427 (source (origin
1428 (method url-fetch)
1429 ;; Test data is missing on PyPi.
1430 (uri (string-append
1431 "https://github.com/pysam-developers/pysam/archive/v"
1432 version ".tar.gz"))
1433 (file-name (string-append name "-" version ".tar.gz"))
1434 (sha256
1435 (base32
1436 "1cfqdxsqs3xhacns9n0271ck6wkc76px66ddjm91wfw2jxxfklvc"))
1437 (modules '((guix build utils)))
1438 (snippet
1439 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1440 '(delete-file-recursively "htslib"))))
1441 (build-system python-build-system)
1442 (arguments
1443 `(#:modules ((ice-9 ftw)
1444 (srfi srfi-26)
1445 (guix build python-build-system)
1446 (guix build utils))
1447 #:phases
1448 (modify-phases %standard-phases
1449 (add-before 'build 'set-flags
1450 (lambda* (#:key inputs #:allow-other-keys)
1451 (setenv "HTSLIB_MODE" "external")
1452 (setenv "HTSLIB_LIBRARY_DIR"
1453 (string-append (assoc-ref inputs "htslib") "/lib"))
1454 (setenv "HTSLIB_INCLUDE_DIR"
1455 (string-append (assoc-ref inputs "htslib") "/include"))
1456 (setenv "LDFLAGS" "-lncurses")
1457 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1458 #t))
1459 (replace 'check
1460 (lambda* (#:key inputs outputs #:allow-other-keys)
1461 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1462 (setenv "PYTHONPATH"
1463 (string-append
1464 (getenv "PYTHONPATH")
1465 ":" (getcwd) "/build/"
1466 (car (scandir "build"
1467 (negate (cut string-prefix? "." <>))))))
1468 ;; Step out of source dir so python does not import from CWD.
1469 (with-directory-excursion "tests"
1470 (setenv "HOME" "/tmp")
1471 (and (zero? (system* "make" "-C" "pysam_data"))
1472 (zero? (system* "make" "-C" "cbcf_data"))
1473 ;; Running nosetests without explicitly asking for a
1474 ;; single process leads to a crash. Running with multiple
1475 ;; processes fails because the tests are not designed to
1476 ;; run in parallel.
1477
1478 ;; FIXME: tests keep timing out on some systems.
1479 ;; (zero? (system* "nosetests" "-v"
1480 ;; "--processes" "1"))
1481 )))))))
1482 (propagated-inputs
1483 `(("htslib" ,htslib))) ; Included from installed header files.
1484 (inputs
1485 `(("ncurses" ,ncurses)
1486 ("zlib" ,zlib)))
1487 (native-inputs
1488 `(("python-cython" ,python-cython)
1489 ;; Dependencies below are are for tests only.
1490 ("samtools" ,samtools)
1491 ("bcftools" ,bcftools)
1492 ("python-nose" ,python-nose)))
1493 (home-page "https://github.com/pysam-developers/pysam")
1494 (synopsis "Python bindings to the SAMtools C API")
1495 (description
1496 "Pysam is a Python module for reading and manipulating files in the
1497 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1498 also includes an interface for tabix.")
1499 (license license:expat)))
1500
1501 (define-public python2-pysam
1502 (package-with-python2 python-pysam))
1503
1504 (define-public python-twobitreader
1505 (package
1506 (name "python-twobitreader")
1507 (version "3.1.4")
1508 (source (origin
1509 (method url-fetch)
1510 (uri (pypi-uri "twobitreader" version))
1511 (sha256
1512 (base32
1513 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1514 (build-system python-build-system)
1515 (arguments
1516 '(;; Tests are not distributed in the PyPi release.
1517 ;; TODO Try building from the Git repo or asking the upstream maintainer
1518 ;; to distribute the tests on PyPi.
1519 #:tests? #f))
1520 (native-inputs
1521 `(("python-sphinx" ,python-sphinx)))
1522 (home-page "https://github.com/benjschiller/twobitreader")
1523 (synopsis "Python library for reading .2bit files")
1524 (description
1525 "twobitreader is a Python library for reading .2bit files as used by the
1526 UCSC genome browser.")
1527 (license license:artistic2.0)))
1528
1529 (define-public python2-twobitreader
1530 (package-with-python2 python-twobitreader))
1531
1532 (define-public python-plastid
1533 (package
1534 (name "python-plastid")
1535 (version "0.4.8")
1536 (source (origin
1537 (method url-fetch)
1538 (uri (pypi-uri "plastid" version))
1539 (sha256
1540 (base32
1541 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1542 (build-system python-build-system)
1543 (arguments
1544 ;; Some test files are not included.
1545 `(#:tests? #f))
1546 (propagated-inputs
1547 `(("python-numpy" ,python-numpy)
1548 ("python-scipy" ,python-scipy)
1549 ("python-pandas" ,python-pandas)
1550 ("python-pysam" ,python-pysam)
1551 ("python-matplotlib" ,python-matplotlib)
1552 ("python-biopython" ,python-biopython)
1553 ("python-twobitreader" ,python-twobitreader)
1554 ("python-termcolor" ,python-termcolor)))
1555 (native-inputs
1556 `(("python-cython" ,python-cython)
1557 ("python-nose" ,python-nose)))
1558 (home-page "https://github.com/joshuagryphon/plastid")
1559 (synopsis "Python library for genomic analysis")
1560 (description
1561 "plastid is a Python library for genomic analysis – in particular,
1562 high-throughput sequencing data – with an emphasis on simplicity.")
1563 (license license:bsd-3)))
1564
1565 (define-public python2-plastid
1566 (package-with-python2 python-plastid))
1567
1568 (define-public cd-hit
1569 (package
1570 (name "cd-hit")
1571 (version "4.6.8")
1572 (source (origin
1573 (method url-fetch)
1574 (uri (string-append "https://github.com/weizhongli/cdhit"
1575 "/releases/download/V" version
1576 "/cd-hit-v" version
1577 "-2017-0621-source.tar.gz"))
1578 (sha256
1579 (base32
1580 "1386dg2npx8p62wmv08mjzsd2z3waknb9j1gg3gkvblcy57hymnn"))))
1581 (build-system gnu-build-system)
1582 (arguments
1583 `(#:tests? #f ; there are no tests
1584 #:make-flags
1585 ;; Executables are copied directly to the PREFIX.
1586 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1587 #:phases
1588 (modify-phases %standard-phases
1589 ;; No "configure" script
1590 (delete 'configure)
1591 ;; Remove sources of non-determinism
1592 (add-after 'unpack 'be-timeless
1593 (lambda _
1594 (substitute* "cdhit-utility.c++"
1595 ((" \\(built on \" __DATE__ \"\\)") ""))
1596 (substitute* "cdhit-common.c++"
1597 (("__DATE__") "\"0\"")
1598 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1599 #t))
1600 ;; The "install" target does not create the target directory.
1601 (add-before 'install 'create-target-dir
1602 (lambda* (#:key outputs #:allow-other-keys)
1603 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1604 #t)))))
1605 (inputs
1606 `(("perl" ,perl)))
1607 (home-page "http://weizhongli-lab.org/cd-hit/")
1608 (synopsis "Cluster and compare protein or nucleotide sequences")
1609 (description
1610 "CD-HIT is a program for clustering and comparing protein or nucleotide
1611 sequences. CD-HIT is designed to be fast and handle extremely large
1612 databases.")
1613 ;; The manual says: "It can be copied under the GNU General Public License
1614 ;; version 2 (GPLv2)."
1615 (license license:gpl2)))
1616
1617 (define-public clipper
1618 (package
1619 (name "clipper")
1620 (version "1.1")
1621 (source (origin
1622 (method url-fetch)
1623 (uri (string-append
1624 "https://github.com/YeoLab/clipper/archive/"
1625 version ".tar.gz"))
1626 (file-name (string-append name "-" version ".tar.gz"))
1627 (sha256
1628 (base32
1629 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1630 (modules '((guix build utils)))
1631 (snippet
1632 '(begin
1633 ;; remove unnecessary setup dependency
1634 (substitute* "setup.py"
1635 (("setup_requires = .*") ""))
1636 (for-each delete-file
1637 '("clipper/src/peaks.so"
1638 "clipper/src/readsToWiggle.so"))
1639 (delete-file-recursively "dist/")
1640 #t))))
1641 (build-system python-build-system)
1642 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1643 (inputs
1644 `(("htseq" ,python2-htseq)
1645 ("python-pybedtools" ,python2-pybedtools)
1646 ("python-cython" ,python2-cython)
1647 ("python-scikit-learn" ,python2-scikit-learn)
1648 ("python-matplotlib" ,python2-matplotlib)
1649 ("python-pandas" ,python2-pandas)
1650 ("python-pysam" ,python2-pysam)
1651 ("python-numpy" ,python2-numpy)
1652 ("python-scipy" ,python2-scipy)))
1653 (native-inputs
1654 `(("python-mock" ,python2-mock) ; for tests
1655 ("python-nose" ,python2-nose) ; for tests
1656 ("python-pytz" ,python2-pytz))) ; for tests
1657 (home-page "https://github.com/YeoLab/clipper")
1658 (synopsis "CLIP peak enrichment recognition")
1659 (description
1660 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1661 (license license:gpl2)))
1662
1663 (define-public codingquarry
1664 (package
1665 (name "codingquarry")
1666 (version "2.0")
1667 (source (origin
1668 (method url-fetch)
1669 (uri (string-append
1670 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1671 version ".tar.gz"))
1672 (sha256
1673 (base32
1674 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1675 (build-system gnu-build-system)
1676 (arguments
1677 '(#:tests? #f ; no "check" target
1678 #:phases
1679 (modify-phases %standard-phases
1680 (delete 'configure)
1681 (replace 'install
1682 (lambda* (#:key outputs #:allow-other-keys)
1683 (let* ((out (assoc-ref outputs "out"))
1684 (bin (string-append out "/bin"))
1685 (doc (string-append out "/share/doc/codingquarry")))
1686 (install-file "INSTRUCTIONS.pdf" doc)
1687 (copy-recursively "QuarryFiles"
1688 (string-append out "/QuarryFiles"))
1689 (install-file "CodingQuarry" bin)
1690 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1691 (inputs `(("openmpi" ,openmpi)))
1692 (native-search-paths
1693 (list (search-path-specification
1694 (variable "QUARRY_PATH")
1695 (files '("QuarryFiles")))))
1696 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1697 (synopsis "Fungal gene predictor")
1698 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1699 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1700 (home-page "https://sourceforge.net/projects/codingquarry/")
1701 (license license:gpl3+)))
1702
1703 (define-public couger
1704 (package
1705 (name "couger")
1706 (version "1.8.2")
1707 (source (origin
1708 (method url-fetch)
1709 (uri (string-append
1710 "http://couger.oit.duke.edu/static/assets/COUGER"
1711 version ".zip"))
1712 (sha256
1713 (base32
1714 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1715 (build-system gnu-build-system)
1716 (arguments
1717 `(#:tests? #f
1718 #:phases
1719 (modify-phases %standard-phases
1720 (delete 'configure)
1721 (delete 'build)
1722 (replace
1723 'install
1724 (lambda* (#:key outputs #:allow-other-keys)
1725 (let* ((out (assoc-ref outputs "out"))
1726 (bin (string-append out "/bin")))
1727 (copy-recursively "src" (string-append out "/src"))
1728 (mkdir bin)
1729 ;; Add "src" directory to module lookup path.
1730 (substitute* "couger"
1731 (("from argparse")
1732 (string-append "import sys\nsys.path.append(\""
1733 out "\")\nfrom argparse")))
1734 (install-file "couger" bin))
1735 #t))
1736 (add-after
1737 'install 'wrap-program
1738 (lambda* (#:key inputs outputs #:allow-other-keys)
1739 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1740 (let* ((out (assoc-ref outputs "out"))
1741 (path (getenv "PYTHONPATH")))
1742 (wrap-program (string-append out "/bin/couger")
1743 `("PYTHONPATH" ":" prefix (,path))))
1744 #t)))))
1745 (inputs
1746 `(("python" ,python-2)
1747 ("python2-pillow" ,python2-pillow)
1748 ("python2-numpy" ,python2-numpy)
1749 ("python2-scipy" ,python2-scipy)
1750 ("python2-matplotlib" ,python2-matplotlib)))
1751 (propagated-inputs
1752 `(("r-minimal" ,r-minimal)
1753 ("libsvm" ,libsvm)
1754 ("randomjungle" ,randomjungle)))
1755 (native-inputs
1756 `(("unzip" ,unzip)))
1757 (home-page "http://couger.oit.duke.edu")
1758 (synopsis "Identify co-factors in sets of genomic regions")
1759 (description
1760 "COUGER can be applied to any two sets of genomic regions bound by
1761 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1762 putative co-factors that provide specificity to each TF. The framework
1763 determines the genomic targets uniquely-bound by each TF, and identifies a
1764 small set of co-factors that best explain the in vivo binding differences
1765 between the two TFs.
1766
1767 COUGER uses classification algorithms (support vector machines and random
1768 forests) with features that reflect the DNA binding specificities of putative
1769 co-factors. The features are generated either from high-throughput TF-DNA
1770 binding data (from protein binding microarray experiments), or from large
1771 collections of DNA motifs.")
1772 (license license:gpl3+)))
1773
1774 (define-public clustal-omega
1775 (package
1776 (name "clustal-omega")
1777 (version "1.2.1")
1778 (source (origin
1779 (method url-fetch)
1780 (uri (string-append
1781 "http://www.clustal.org/omega/clustal-omega-"
1782 version ".tar.gz"))
1783 (sha256
1784 (base32
1785 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1786 (build-system gnu-build-system)
1787 (inputs
1788 `(("argtable" ,argtable)))
1789 (home-page "http://www.clustal.org/omega/")
1790 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1791 (description
1792 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1793 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1794 of handling data-sets of hundreds of thousands of sequences in reasonable
1795 time.")
1796 (license license:gpl2+)))
1797
1798 (define-public crossmap
1799 (package
1800 (name "crossmap")
1801 (version "0.2.1")
1802 (source (origin
1803 (method url-fetch)
1804 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1805 version ".tar.gz"))
1806 (sha256
1807 (base32
1808 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1809 ;; This patch has been sent upstream already and is available
1810 ;; for download from Sourceforge, but it has not been merged.
1811 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1812 (modules '((guix build utils)))
1813 ;; remove bundled copy of pysam
1814 (snippet
1815 '(delete-file-recursively "lib/pysam"))))
1816 (build-system python-build-system)
1817 (arguments
1818 `(#:python ,python-2
1819 #:phases
1820 (modify-phases %standard-phases
1821 (add-after 'unpack 'set-env
1822 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1823 (inputs
1824 `(("python-numpy" ,python2-numpy)
1825 ("python-pysam" ,python2-pysam)
1826 ("zlib" ,zlib)))
1827 (native-inputs
1828 `(("python-cython" ,python2-cython)
1829 ("python-nose" ,python2-nose)))
1830 (home-page "http://crossmap.sourceforge.net/")
1831 (synopsis "Convert genome coordinates between assemblies")
1832 (description
1833 "CrossMap is a program for conversion of genome coordinates or annotation
1834 files between different genome assemblies. It supports most commonly used
1835 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1836 (license license:gpl2+)))
1837
1838 (define-public cufflinks
1839 (package
1840 (name "cufflinks")
1841 (version "2.2.1")
1842 (source (origin
1843 (method url-fetch)
1844 (uri (string-append "http://cole-trapnell-lab.github.io/"
1845 "cufflinks/assets/downloads/cufflinks-"
1846 version ".tar.gz"))
1847 (sha256
1848 (base32
1849 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1850 (build-system gnu-build-system)
1851 (arguments
1852 `(#:make-flags
1853 (list
1854 ;; The includes for "eigen" are located in a subdirectory.
1855 (string-append "EIGEN_CPPFLAGS="
1856 "-I" (assoc-ref %build-inputs "eigen")
1857 "/include/eigen3/")
1858 ;; Cufflinks must be linked with various boost libraries.
1859 (string-append "LDFLAGS="
1860 (string-join '("-lboost_system"
1861 "-lboost_serialization"
1862 "-lboost_thread"))))
1863 #:phases
1864 (modify-phases %standard-phases
1865 (add-after 'unpack 'fix-search-for-bam
1866 (lambda _
1867 (substitute* '("ax_bam.m4"
1868 "configure"
1869 "src/hits.h")
1870 (("<bam/sam\\.h>") "<samtools/sam.h>")
1871 (("<bam/bam\\.h>") "<samtools/bam.h>")
1872 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1873 #t)))
1874 #:configure-flags
1875 (list (string-append "--with-bam="
1876 (assoc-ref %build-inputs "samtools")))))
1877 (inputs
1878 `(("eigen" ,eigen)
1879 ("samtools" ,samtools-0.1)
1880 ("htslib" ,htslib)
1881 ("boost" ,boost)
1882 ("python" ,python-2)
1883 ("zlib" ,zlib)))
1884 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1885 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1886 (description
1887 "Cufflinks assembles RNA transcripts, estimates their abundances,
1888 and tests for differential expression and regulation in RNA-Seq
1889 samples. It accepts aligned RNA-Seq reads and assembles the
1890 alignments into a parsimonious set of transcripts. Cufflinks then
1891 estimates the relative abundances of these transcripts based on how
1892 many reads support each one, taking into account biases in library
1893 preparation protocols.")
1894 (license license:boost1.0)))
1895
1896 (define-public cutadapt
1897 (package
1898 (name "cutadapt")
1899 (version "1.12")
1900 (source (origin
1901 (method url-fetch)
1902 (uri (string-append
1903 "https://github.com/marcelm/cutadapt/archive/v"
1904 version ".tar.gz"))
1905 (file-name (string-append name "-" version ".tar.gz"))
1906 (sha256
1907 (base32
1908 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1909 (build-system python-build-system)
1910 (arguments
1911 `(#:phases
1912 (modify-phases %standard-phases
1913 ;; The tests must be run after installation.
1914 (delete 'check)
1915 (add-after 'install 'check
1916 (lambda* (#:key inputs outputs #:allow-other-keys)
1917 (setenv "PYTHONPATH"
1918 (string-append
1919 (getenv "PYTHONPATH")
1920 ":" (assoc-ref outputs "out")
1921 "/lib/python"
1922 (string-take (string-take-right
1923 (assoc-ref inputs "python") 5) 3)
1924 "/site-packages"))
1925 (zero? (system* "nosetests" "-P" "tests")))))))
1926 (inputs
1927 `(("python-xopen" ,python-xopen)))
1928 (native-inputs
1929 `(("python-cython" ,python-cython)
1930 ("python-nose" ,python-nose)))
1931 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1932 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1933 (description
1934 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1935 other types of unwanted sequence from high-throughput sequencing reads.")
1936 (license license:expat)))
1937
1938 (define-public libbigwig
1939 (package
1940 (name "libbigwig")
1941 (version "0.1.4")
1942 (source (origin
1943 (method url-fetch)
1944 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1945 "archive/" version ".tar.gz"))
1946 (file-name (string-append name "-" version ".tar.gz"))
1947 (sha256
1948 (base32
1949 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1950 (build-system gnu-build-system)
1951 (arguments
1952 `(#:test-target "test"
1953 #:make-flags
1954 (list "CC=gcc"
1955 (string-append "prefix=" (assoc-ref %outputs "out")))
1956 #:phases
1957 (modify-phases %standard-phases
1958 (delete 'configure)
1959 (add-before 'check 'disable-curl-test
1960 (lambda _
1961 (substitute* "Makefile"
1962 (("./test/testRemote.*") ""))
1963 #t))
1964 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1965 ;; there has not yet been a release containing this change.
1966 (add-before 'install 'create-target-dirs
1967 (lambda* (#:key outputs #:allow-other-keys)
1968 (let ((out (assoc-ref outputs "out")))
1969 (mkdir-p (string-append out "/lib"))
1970 (mkdir-p (string-append out "/include"))
1971 #t))))))
1972 (inputs
1973 `(("zlib" ,zlib)
1974 ("curl" ,curl)))
1975 (native-inputs
1976 `(("doxygen" ,doxygen)))
1977 (home-page "https://github.com/dpryan79/libBigWig")
1978 (synopsis "C library for handling bigWig files")
1979 (description
1980 "This package provides a C library for parsing local and remote BigWig
1981 files.")
1982 (license license:expat)))
1983
1984 (define-public python-pybigwig
1985 (package
1986 (name "python-pybigwig")
1987 (version "0.2.5")
1988 (source (origin
1989 (method url-fetch)
1990 (uri (pypi-uri "pyBigWig" version))
1991 (sha256
1992 (base32
1993 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1994 (modules '((guix build utils)))
1995 (snippet
1996 '(begin
1997 ;; Delete bundled libBigWig sources
1998 (delete-file-recursively "libBigWig")))))
1999 (build-system python-build-system)
2000 (arguments
2001 `(#:phases
2002 (modify-phases %standard-phases
2003 (add-after 'unpack 'link-with-libBigWig
2004 (lambda* (#:key inputs #:allow-other-keys)
2005 (substitute* "setup.py"
2006 (("libs=\\[") "libs=[\"BigWig\", "))
2007 #t)))))
2008 (inputs
2009 `(("libbigwig" ,libbigwig)
2010 ("zlib" ,zlib)
2011 ("curl" ,curl)))
2012 (home-page "https://github.com/dpryan79/pyBigWig")
2013 (synopsis "Access bigWig files in Python using libBigWig")
2014 (description
2015 "This package provides Python bindings to the libBigWig library for
2016 accessing bigWig files.")
2017 (license license:expat)))
2018
2019 (define-public python2-pybigwig
2020 (package-with-python2 python-pybigwig))
2021
2022 (define-public python-dendropy
2023 (package
2024 (name "python-dendropy")
2025 (version "4.2.0")
2026 (source
2027 (origin
2028 (method url-fetch)
2029 (uri (pypi-uri "DendroPy" version))
2030 (sha256
2031 (base32
2032 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
2033 (patches (search-patches "python-dendropy-fix-tests.patch"))))
2034 (build-system python-build-system)
2035 (home-page "http://packages.python.org/DendroPy/")
2036 (synopsis "Library for phylogenetics and phylogenetic computing")
2037 (description
2038 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2039 writing, simulation, processing and manipulation of phylogenetic
2040 trees (phylogenies) and characters.")
2041 (license license:bsd-3)
2042 (properties `((python2-variant . ,(delay python2-dendropy))))))
2043
2044 (define-public python2-dendropy
2045 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2046 (package
2047 (inherit base)
2048 (arguments
2049 `(#:python ,python-2
2050 #:phases
2051 (modify-phases %standard-phases
2052 (replace 'check
2053 ;; There is currently a test failure that only happens on some
2054 ;; systems, and only using "setup.py test"
2055 (lambda _ (zero? (system* "nosetests")))))))
2056 (native-inputs `(("python2-nose" ,python2-nose)
2057 ,@(package-native-inputs base))))))
2058
2059 (define-public python-py2bit
2060 (package
2061 (name "python-py2bit")
2062 (version "0.2.1")
2063 (source
2064 (origin
2065 (method url-fetch)
2066 (uri (pypi-uri "py2bit" version))
2067 (sha256
2068 (base32
2069 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2070 (build-system python-build-system)
2071 (home-page "https://github.com/dpryan79/py2bit")
2072 (synopsis "Access 2bit files using lib2bit")
2073 (description
2074 "This package provides Python bindings for lib2bit to access 2bit files
2075 with Python.")
2076 (license license:expat)))
2077
2078 (define-public deeptools
2079 (package
2080 (name "deeptools")
2081 (version "2.5.1")
2082 (source (origin
2083 (method url-fetch)
2084 (uri (string-append "https://github.com/fidelram/deepTools/"
2085 "archive/" version ".tar.gz"))
2086 (file-name (string-append name "-" version ".tar.gz"))
2087 (sha256
2088 (base32
2089 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2090 (build-system python-build-system)
2091 (inputs
2092 `(("python-scipy" ,python-scipy)
2093 ("python-numpy" ,python-numpy)
2094 ("python-numpydoc" ,python-numpydoc)
2095 ("python-matplotlib" ,python-matplotlib)
2096 ("python-pysam" ,python-pysam)
2097 ("python-py2bit" ,python-py2bit)
2098 ("python-pybigwig" ,python-pybigwig)))
2099 (native-inputs
2100 `(("python-mock" ,python-mock) ;for tests
2101 ("python-nose" ,python-nose) ;for tests
2102 ("python-pytz" ,python-pytz))) ;for tests
2103 (home-page "https://github.com/fidelram/deepTools")
2104 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2105 (description
2106 "DeepTools addresses the challenge of handling the large amounts of data
2107 that are now routinely generated from DNA sequencing centers. To do so,
2108 deepTools contains useful modules to process the mapped reads data to create
2109 coverage files in standard bedGraph and bigWig file formats. By doing so,
2110 deepTools allows the creation of normalized coverage files or the comparison
2111 between two files (for example, treatment and control). Finally, using such
2112 normalized and standardized files, multiple visualizations can be created to
2113 identify enrichments with functional annotations of the genome.")
2114 (license license:gpl3+)))
2115
2116 (define-public diamond
2117 (package
2118 (name "diamond")
2119 (version "0.9.10")
2120 (source (origin
2121 (method url-fetch)
2122 (uri (string-append
2123 "https://github.com/bbuchfink/diamond/archive/v"
2124 version ".tar.gz"))
2125 (file-name (string-append name "-" version ".tar.gz"))
2126 (sha256
2127 (base32
2128 "13qqzwg54n5dqh8pm5n3v8x6gqbczzakphwwjix63qv60hcd5bqd"))))
2129 (build-system cmake-build-system)
2130 (arguments
2131 '(#:tests? #f ; no "check" target
2132 #:phases
2133 (modify-phases %standard-phases
2134 (add-after 'unpack 'remove-native-compilation
2135 (lambda _
2136 (substitute* "CMakeLists.txt" (("-march=native") ""))
2137 #t)))))
2138 (inputs
2139 `(("zlib" ,zlib)))
2140 (home-page "https://github.com/bbuchfink/diamond")
2141 (synopsis "Accelerated BLAST compatible local sequence aligner")
2142 (description
2143 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2144 translated DNA query sequences against a protein reference database (BLASTP
2145 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2146 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2147 data and settings.")
2148 (license license:agpl3+)))
2149
2150 (define-public discrover
2151 (package
2152 (name "discrover")
2153 (version "1.6.0")
2154 (source
2155 (origin
2156 (method url-fetch)
2157 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2158 version ".tar.gz"))
2159 (file-name (string-append name "-" version ".tar.gz"))
2160 (sha256
2161 (base32
2162 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2163 (build-system cmake-build-system)
2164 (arguments
2165 `(#:tests? #f ; there are no tests
2166 #:phases
2167 (modify-phases %standard-phases
2168 (add-after 'unpack 'add-missing-includes
2169 (lambda _
2170 (substitute* "src/executioninformation.hpp"
2171 (("#define EXECUTIONINFORMATION_HPP" line)
2172 (string-append line "\n#include <random>")))
2173 (substitute* "src/plasma/fasta.hpp"
2174 (("#define FASTA_HPP" line)
2175 (string-append line "\n#include <random>")))
2176 #t)))))
2177 (inputs
2178 `(("boost" ,boost)
2179 ("cairo" ,cairo)))
2180 (native-inputs
2181 `(("texlive" ,texlive)
2182 ("imagemagick" ,imagemagick)))
2183 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2184 (synopsis "Discover discriminative nucleotide sequence motifs")
2185 (description "Discrover is a motif discovery method to find binding sites
2186 of nucleic acid binding proteins.")
2187 (license license:gpl3+)))
2188
2189 (define-public eigensoft
2190 (let ((revision "1")
2191 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2192 (package
2193 (name "eigensoft")
2194 (version (string-append "6.1.2-"
2195 revision "."
2196 (string-take commit 9)))
2197 (source
2198 (origin
2199 (method git-fetch)
2200 (uri (git-reference
2201 (url "https://github.com/DReichLab/EIG.git")
2202 (commit commit)))
2203 (file-name (string-append "eigensoft-" commit "-checkout"))
2204 (sha256
2205 (base32
2206 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2207 (modules '((guix build utils)))
2208 ;; Remove pre-built binaries.
2209 (snippet '(begin
2210 (delete-file-recursively "bin")
2211 (mkdir "bin")
2212 #t))))
2213 (build-system gnu-build-system)
2214 (arguments
2215 `(#:tests? #f ; There are no tests.
2216 #:make-flags '("CC=gcc")
2217 #:phases
2218 (modify-phases %standard-phases
2219 ;; There is no configure phase, but the Makefile is in a
2220 ;; sub-directory.
2221 (replace 'configure
2222 (lambda _
2223 (chdir "src")
2224 ;; The link flags are incomplete.
2225 (substitute* "Makefile"
2226 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2227 #t))
2228 ;; The provided install target only copies executables to
2229 ;; the "bin" directory in the build root.
2230 (add-after 'install 'actually-install
2231 (lambda* (#:key outputs #:allow-other-keys)
2232 (let* ((out (assoc-ref outputs "out"))
2233 (bin (string-append out "/bin")))
2234 (for-each (lambda (file)
2235 (install-file file bin))
2236 (find-files "../bin" ".*"))
2237 #t))))))
2238 (inputs
2239 `(("gsl" ,gsl)
2240 ("lapack" ,lapack)
2241 ("openblas" ,openblas)
2242 ("perl" ,perl)
2243 ("gfortran" ,gfortran "lib")))
2244 (home-page "https://github.com/DReichLab/EIG")
2245 (synopsis "Tools for population genetics")
2246 (description "The EIGENSOFT package provides tools for population
2247 genetics and stratification correction. EIGENSOFT implements methods commonly
2248 used in population genetics analyses such as PCA, computation of Tracy-Widom
2249 statistics, and finding related individuals in structured populations. It
2250 comes with a built-in plotting script and supports multiple file formats and
2251 quantitative phenotypes.")
2252 ;; The license of the eigensoft tools is Expat, but since it's
2253 ;; linking with the GNU Scientific Library (GSL) the effective
2254 ;; license is the GPL.
2255 (license license:gpl3+))))
2256
2257 (define-public edirect
2258 (package
2259 (name "edirect")
2260 (version "4.10")
2261 (source (origin
2262 (method url-fetch)
2263 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2264 "versions/2016-05-03/edirect.tar.gz"))
2265 (sha256
2266 (base32
2267 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2268 (build-system perl-build-system)
2269 (arguments
2270 `(#:tests? #f ;no "check" target
2271 #:phases
2272 (modify-phases %standard-phases
2273 (delete 'configure)
2274 (delete 'build)
2275 (replace 'install
2276 (lambda* (#:key outputs #:allow-other-keys)
2277 (let ((target (string-append (assoc-ref outputs "out")
2278 "/bin")))
2279 (mkdir-p target)
2280 (install-file "edirect.pl" target)
2281 #t)))
2282 (add-after
2283 'install 'wrap-program
2284 (lambda* (#:key inputs outputs #:allow-other-keys)
2285 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2286 (let* ((out (assoc-ref outputs "out"))
2287 (path (getenv "PERL5LIB")))
2288 (wrap-program (string-append out "/bin/edirect.pl")
2289 `("PERL5LIB" ":" prefix (,path)))))))))
2290 (inputs
2291 `(("perl-html-parser" ,perl-html-parser)
2292 ("perl-encode-locale" ,perl-encode-locale)
2293 ("perl-file-listing" ,perl-file-listing)
2294 ("perl-html-tagset" ,perl-html-tagset)
2295 ("perl-html-tree" ,perl-html-tree)
2296 ("perl-http-cookies" ,perl-http-cookies)
2297 ("perl-http-date" ,perl-http-date)
2298 ("perl-http-message" ,perl-http-message)
2299 ("perl-http-negotiate" ,perl-http-negotiate)
2300 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2301 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2302 ("perl-net-http" ,perl-net-http)
2303 ("perl-uri" ,perl-uri)
2304 ("perl-www-robotrules" ,perl-www-robotrules)
2305 ("perl" ,perl)))
2306 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2307 (synopsis "Tools for accessing the NCBI's set of databases")
2308 (description
2309 "Entrez Direct (EDirect) is a method for accessing the National Center
2310 for Biotechnology Information's (NCBI) set of interconnected
2311 databases (publication, sequence, structure, gene, variation, expression,
2312 etc.) from a terminal. Functions take search terms from command-line
2313 arguments. Individual operations are combined to build multi-step queries.
2314 Record retrieval and formatting normally complete the process.
2315
2316 EDirect also provides an argument-driven function that simplifies the
2317 extraction of data from document summaries or other results that are returned
2318 in structured XML format. This can eliminate the need for writing custom
2319 software to answer ad hoc questions.")
2320 (license license:public-domain)))
2321
2322 (define-public exonerate
2323 (package
2324 (name "exonerate")
2325 (version "2.4.0")
2326 (source
2327 (origin
2328 (method url-fetch)
2329 (uri
2330 (string-append
2331 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2332 "exonerate-" version ".tar.gz"))
2333 (sha256
2334 (base32
2335 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2336 (build-system gnu-build-system)
2337 (arguments
2338 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2339 (native-inputs
2340 `(("pkg-config" ,pkg-config)))
2341 (inputs
2342 `(("glib" ,glib)))
2343 (home-page
2344 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2345 (synopsis "Generic tool for biological sequence alignment")
2346 (description
2347 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2348 the alignment of sequences using a many alignment models, either exhaustive
2349 dynamic programming or a variety of heuristics.")
2350 (license license:gpl3)))
2351
2352 (define-public express
2353 (package
2354 (name "express")
2355 (version "1.5.1")
2356 (source (origin
2357 (method url-fetch)
2358 (uri
2359 (string-append
2360 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2361 version "/express-" version "-src.tgz"))
2362 (sha256
2363 (base32
2364 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2365 (build-system cmake-build-system)
2366 (arguments
2367 `(#:tests? #f ;no "check" target
2368 #:phases
2369 (modify-phases %standard-phases
2370 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2371 (lambda* (#:key inputs #:allow-other-keys)
2372 (substitute* "CMakeLists.txt"
2373 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2374 "set(Boost_USE_STATIC_LIBS OFF)")
2375 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2376 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2377 (substitute* "src/CMakeLists.txt"
2378 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2379 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2380 #t)))))
2381 (inputs
2382 `(("boost" ,boost)
2383 ("bamtools" ,bamtools)
2384 ("protobuf" ,protobuf)
2385 ("zlib" ,zlib)))
2386 (home-page "http://bio.math.berkeley.edu/eXpress")
2387 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2388 (description
2389 "eXpress is a streaming tool for quantifying the abundances of a set of
2390 target sequences from sampled subsequences. Example applications include
2391 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2392 analysis (from RNA-Seq), transcription factor binding quantification in
2393 ChIP-Seq, and analysis of metagenomic data.")
2394 (license license:artistic2.0)))
2395
2396 (define-public express-beta-diversity
2397 (package
2398 (name "express-beta-diversity")
2399 (version "1.0.7")
2400 (source (origin
2401 (method url-fetch)
2402 (uri
2403 (string-append
2404 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2405 version ".tar.gz"))
2406 (file-name (string-append name "-" version ".tar.gz"))
2407 (sha256
2408 (base32
2409 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2410 (build-system gnu-build-system)
2411 (arguments
2412 `(#:phases
2413 (modify-phases %standard-phases
2414 (delete 'configure)
2415 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2416 (replace 'check
2417 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2418 "-u"))))
2419 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2420 (replace 'install
2421 (lambda* (#:key outputs #:allow-other-keys)
2422 (let ((bin (string-append (assoc-ref outputs "out")
2423 "/bin")))
2424 (mkdir-p bin)
2425 (install-file "scripts/convertToEBD.py" bin)
2426 (install-file "bin/ExpressBetaDiversity" bin)
2427 #t))))))
2428 (inputs
2429 `(("python" ,python-2)))
2430 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2431 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2432 (description
2433 "Express Beta Diversity (EBD) calculates ecological beta diversity
2434 (dissimilarity) measures between biological communities. EBD implements a
2435 variety of diversity measures including those that make use of phylogenetic
2436 similarity of community members.")
2437 (license license:gpl3+)))
2438
2439 (define-public fasttree
2440 (package
2441 (name "fasttree")
2442 (version "2.1.10")
2443 (source (origin
2444 (method url-fetch)
2445 (uri (string-append
2446 "http://www.microbesonline.org/fasttree/FastTree-"
2447 version ".c"))
2448 (sha256
2449 (base32
2450 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2451 (build-system gnu-build-system)
2452 (arguments
2453 `(#:tests? #f ; no "check" target
2454 #:phases
2455 (modify-phases %standard-phases
2456 (delete 'unpack)
2457 (delete 'configure)
2458 (replace 'build
2459 (lambda* (#:key source #:allow-other-keys)
2460 (and (zero? (system* "gcc"
2461 "-O3"
2462 "-finline-functions"
2463 "-funroll-loops"
2464 "-Wall"
2465 "-o"
2466 "FastTree"
2467 source
2468 "-lm"))
2469 (zero? (system* "gcc"
2470 "-DOPENMP"
2471 "-fopenmp"
2472 "-O3"
2473 "-finline-functions"
2474 "-funroll-loops"
2475 "-Wall"
2476 "-o"
2477 "FastTreeMP"
2478 source
2479 "-lm")))))
2480 (replace 'install
2481 (lambda* (#:key outputs #:allow-other-keys)
2482 (let ((bin (string-append (assoc-ref outputs "out")
2483 "/bin")))
2484 (mkdir-p bin)
2485 (install-file "FastTree" bin)
2486 (install-file "FastTreeMP" bin)
2487 #t))))))
2488 (home-page "http://www.microbesonline.org/fasttree")
2489 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2490 (description
2491 "FastTree can handle alignments with up to a million of sequences in a
2492 reasonable amount of time and memory. For large alignments, FastTree is
2493 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2494 (license license:gpl2+)))
2495
2496 (define-public fastx-toolkit
2497 (package
2498 (name "fastx-toolkit")
2499 (version "0.0.14")
2500 (source (origin
2501 (method url-fetch)
2502 (uri
2503 (string-append
2504 "https://github.com/agordon/fastx_toolkit/releases/download/"
2505 version "/fastx_toolkit-" version ".tar.bz2"))
2506 (sha256
2507 (base32
2508 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2509 (build-system gnu-build-system)
2510 (inputs
2511 `(("libgtextutils" ,libgtextutils)))
2512 (native-inputs
2513 `(("pkg-config" ,pkg-config)))
2514 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2515 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2516 (description
2517 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2518 FASTA/FASTQ files preprocessing.
2519
2520 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2521 containing multiple short-reads sequences. The main processing of such
2522 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2523 is sometimes more productive to preprocess the files before mapping the
2524 sequences to the genome---manipulating the sequences to produce better mapping
2525 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2526 (license license:agpl3+)))
2527
2528 (define-public flexbar
2529 (package
2530 (name "flexbar")
2531 (version "2.5")
2532 (source (origin
2533 (method url-fetch)
2534 (uri
2535 (string-append "mirror://sourceforge/flexbar/"
2536 version "/flexbar_v" version "_src.tgz"))
2537 (sha256
2538 (base32
2539 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2540 (build-system cmake-build-system)
2541 (arguments
2542 `(#:configure-flags (list
2543 (string-append "-DFLEXBAR_BINARY_DIR="
2544 (assoc-ref %outputs "out")
2545 "/bin/"))
2546 #:phases
2547 (modify-phases %standard-phases
2548 (replace 'check
2549 (lambda* (#:key outputs #:allow-other-keys)
2550 (setenv "PATH" (string-append
2551 (assoc-ref outputs "out") "/bin:"
2552 (getenv "PATH")))
2553 (chdir "../flexbar_v2.5_src/test")
2554 (zero? (system* "bash" "flexbar_validate.sh"))))
2555 (delete 'install))))
2556 (inputs
2557 `(("tbb" ,tbb)
2558 ("zlib" ,zlib)))
2559 (native-inputs
2560 `(("pkg-config" ,pkg-config)
2561 ("seqan" ,seqan)))
2562 (home-page "http://flexbar.sourceforge.net")
2563 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2564 (description
2565 "Flexbar preprocesses high-throughput nucleotide sequencing data
2566 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2567 Moreover, trimming and filtering features are provided. Flexbar increases
2568 read mapping rates and improves genome and transcriptome assemblies. It
2569 supports next-generation sequencing data in fasta/q and csfasta/q format from
2570 Illumina, Roche 454, and the SOLiD platform.")
2571 (license license:gpl3)))
2572
2573 (define-public fraggenescan
2574 (package
2575 (name "fraggenescan")
2576 (version "1.30")
2577 (source
2578 (origin
2579 (method url-fetch)
2580 (uri
2581 (string-append "mirror://sourceforge/fraggenescan/"
2582 "FragGeneScan" version ".tar.gz"))
2583 (sha256
2584 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2585 (build-system gnu-build-system)
2586 (arguments
2587 `(#:phases
2588 (modify-phases %standard-phases
2589 (delete 'configure)
2590 (add-before 'build 'patch-paths
2591 (lambda* (#:key outputs #:allow-other-keys)
2592 (let* ((out (string-append (assoc-ref outputs "out")))
2593 (share (string-append out "/share/fraggenescan/")))
2594 (substitute* "run_FragGeneScan.pl"
2595 (("system\\(\"rm")
2596 (string-append "system(\"" (which "rm")))
2597 (("system\\(\"mv")
2598 (string-append "system(\"" (which "mv")))
2599 (("\\\"awk") (string-append "\"" (which "awk")))
2600 ;; This script and other programs expect the training files
2601 ;; to be in the non-standard location bin/train/XXX. Change
2602 ;; this to be share/fraggenescan/train/XXX instead.
2603 (("^\\$train.file = \\$dir.*")
2604 (string-append "$train_file = \""
2605 share
2606 "train/\".$FGS_train_file;")))
2607 (substitute* "run_hmm.c"
2608 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2609 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2610 #t))
2611 (replace 'build
2612 (lambda _ (and (zero? (system* "make" "clean"))
2613 (zero? (system* "make" "fgs")))))
2614 (replace 'install
2615 (lambda* (#:key outputs #:allow-other-keys)
2616 (let* ((out (string-append (assoc-ref outputs "out")))
2617 (bin (string-append out "/bin/"))
2618 (share (string-append out "/share/fraggenescan/train")))
2619 (install-file "run_FragGeneScan.pl" bin)
2620 (install-file "FragGeneScan" bin)
2621 (copy-recursively "train" share))))
2622 (delete 'check)
2623 (add-after 'install 'post-install-check
2624 ;; In lieu of 'make check', run one of the examples and check the
2625 ;; output files gets created.
2626 (lambda* (#:key outputs #:allow-other-keys)
2627 (let* ((out (string-append (assoc-ref outputs "out")))
2628 (bin (string-append out "/bin/"))
2629 (frag (string-append bin "run_FragGeneScan.pl")))
2630 (and (zero? (system* frag ; Test complete genome.
2631 "-genome=./example/NC_000913.fna"
2632 "-out=./test2"
2633 "-complete=1"
2634 "-train=complete"))
2635 (file-exists? "test2.faa")
2636 (file-exists? "test2.ffn")
2637 (file-exists? "test2.gff")
2638 (file-exists? "test2.out")
2639 (zero? (system* ; Test incomplete sequences.
2640 frag
2641 "-genome=./example/NC_000913-fgs.ffn"
2642 "-out=out"
2643 "-complete=0"
2644 "-train=454_30")))))))))
2645 (inputs
2646 `(("perl" ,perl)
2647 ("python" ,python-2))) ;not compatible with python 3.
2648 (home-page "https://sourceforge.net/projects/fraggenescan/")
2649 (synopsis "Finds potentially fragmented genes in short reads")
2650 (description
2651 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2652 short and error-prone DNA sequencing reads. It can also be applied to predict
2653 genes in incomplete assemblies or complete genomes.")
2654 ;; GPL3+ according to private correspondense with the authors.
2655 (license license:gpl3+)))
2656
2657 (define-public fxtract
2658 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2659 (package
2660 (name "fxtract")
2661 (version "2.3")
2662 (source
2663 (origin
2664 (method url-fetch)
2665 (uri (string-append
2666 "https://github.com/ctSkennerton/fxtract/archive/"
2667 version ".tar.gz"))
2668 (file-name (string-append "ctstennerton-util-"
2669 (string-take util-commit 7)
2670 "-checkout"))
2671 (sha256
2672 (base32
2673 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2674 (build-system gnu-build-system)
2675 (arguments
2676 `(#:make-flags (list
2677 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2678 "CC=gcc")
2679 #:test-target "fxtract_test"
2680 #:phases
2681 (modify-phases %standard-phases
2682 (delete 'configure)
2683 (add-before 'build 'copy-util
2684 (lambda* (#:key inputs #:allow-other-keys)
2685 (rmdir "util")
2686 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2687 #t))
2688 ;; Do not use make install as this requires additional dependencies.
2689 (replace 'install
2690 (lambda* (#:key outputs #:allow-other-keys)
2691 (let* ((out (assoc-ref outputs "out"))
2692 (bin (string-append out"/bin")))
2693 (install-file "fxtract" bin)
2694 #t))))))
2695 (inputs
2696 `(("pcre" ,pcre)
2697 ("zlib" ,zlib)))
2698 (native-inputs
2699 ;; ctskennerton-util is licensed under GPL2.
2700 `(("ctskennerton-util"
2701 ,(origin
2702 (method git-fetch)
2703 (uri (git-reference
2704 (url "https://github.com/ctSkennerton/util.git")
2705 (commit util-commit)))
2706 (file-name (string-append
2707 "ctstennerton-util-" util-commit "-checkout"))
2708 (sha256
2709 (base32
2710 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2711 (home-page "https://github.com/ctSkennerton/fxtract")
2712 (synopsis "Extract sequences from FASTA and FASTQ files")
2713 (description
2714 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2715 or FASTQ) file given a subsequence. It uses a simple substring search for
2716 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2717 lookups or multi-pattern searching as required. By default fxtract looks in
2718 the sequence of each record but can also be told to look in the header,
2719 comment or quality sections.")
2720 ;; 'util' requires SSE instructions.
2721 (supported-systems '("x86_64-linux"))
2722 (license license:expat))))
2723
2724 (define-public gemma
2725 (package
2726 (name "gemma")
2727 (version "0.96")
2728 (source (origin
2729 (method url-fetch)
2730 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2731 version ".tar.gz"))
2732 (file-name (string-append name "-" version ".tar.gz"))
2733 (sha256
2734 (base32
2735 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2736 (patches (search-patches "gemma-intel-compat.patch"))))
2737 (inputs
2738 `(("gsl" ,gsl)
2739 ("lapack" ,lapack)
2740 ("zlib" ,zlib)))
2741 (build-system gnu-build-system)
2742 (arguments
2743 `(#:make-flags
2744 '(,@(match (%current-system)
2745 ("x86_64-linux"
2746 '("FORCE_DYNAMIC=1"))
2747 ("i686-linux"
2748 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2749 (_
2750 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2751 #:phases
2752 (modify-phases %standard-phases
2753 (delete 'configure)
2754 (add-before 'build 'bin-mkdir
2755 (lambda _
2756 (mkdir-p "bin")
2757 #t))
2758 (replace 'install
2759 (lambda* (#:key outputs #:allow-other-keys)
2760 (let ((out (assoc-ref outputs "out")))
2761 (install-file "bin/gemma"
2762 (string-append
2763 out "/bin")))
2764 #t)))
2765 #:tests? #f)) ; no tests included yet
2766 (home-page "https://github.com/xiangzhou/GEMMA")
2767 (synopsis "Tool for genome-wide efficient mixed model association")
2768 (description
2769 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2770 standard linear mixed model resolver with application in genome-wide
2771 association studies (GWAS).")
2772 (license license:gpl3)))
2773
2774 (define-public grit
2775 (package
2776 (name "grit")
2777 (version "2.0.2")
2778 (source (origin
2779 (method url-fetch)
2780 (uri (string-append
2781 "https://github.com/nboley/grit/archive/"
2782 version ".tar.gz"))
2783 (file-name (string-append name "-" version ".tar.gz"))
2784 (sha256
2785 (base32
2786 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2787 (build-system python-build-system)
2788 (arguments
2789 `(#:python ,python-2
2790 #:phases
2791 (modify-phases %standard-phases
2792 (add-after 'unpack 'generate-from-cython-sources
2793 (lambda* (#:key inputs outputs #:allow-other-keys)
2794 ;; Delete these C files to force fresh generation from pyx sources.
2795 (delete-file "grit/sparsify_support_fns.c")
2796 (delete-file "grit/call_peaks_support_fns.c")
2797 (substitute* "setup.py"
2798 (("Cython.Setup") "Cython.Build")
2799 ;; Add numpy include path to fix compilation
2800 (("pyx\", \\]")
2801 (string-append "pyx\", ], include_dirs = ['"
2802 (assoc-ref inputs "python-numpy")
2803 "/lib/python2.7/site-packages/numpy/core/include/"
2804 "']")))
2805 #t)))))
2806 (inputs
2807 `(("python-scipy" ,python2-scipy)
2808 ("python-numpy" ,python2-numpy)
2809 ("python-pysam" ,python2-pysam)
2810 ("python-networkx" ,python2-networkx)))
2811 (native-inputs
2812 `(("python-cython" ,python2-cython)))
2813 (home-page "http://grit-bio.org")
2814 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2815 (description
2816 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2817 full length transcript models. When none of these data sources are available,
2818 GRIT can be run by providing a candidate set of TES or TSS sites. In
2819 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2820 also be run in quantification mode, where it uses a provided GTF file and just
2821 estimates transcript expression.")
2822 (license license:gpl3+)))
2823
2824 (define-public hisat
2825 (package
2826 (name "hisat")
2827 (version "0.1.4")
2828 (source (origin
2829 (method url-fetch)
2830 (uri (string-append
2831 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2832 version "-beta-source.zip"))
2833 (sha256
2834 (base32
2835 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2836 (build-system gnu-build-system)
2837 (arguments
2838 `(#:tests? #f ;no check target
2839 #:make-flags '("allall"
2840 ;; Disable unsupported `popcnt' instructions on
2841 ;; architectures other than x86_64
2842 ,@(if (string-prefix? "x86_64"
2843 (or (%current-target-system)
2844 (%current-system)))
2845 '()
2846 '("POPCNT_CAPABILITY=0")))
2847 #:phases
2848 (modify-phases %standard-phases
2849 (add-after 'unpack 'patch-sources
2850 (lambda _
2851 ;; XXX Cannot use snippet because zip files are not supported
2852 (substitute* "Makefile"
2853 (("^CC = .*$") "CC = gcc")
2854 (("^CPP = .*$") "CPP = g++")
2855 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2856 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2857 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2858 (substitute* '("hisat-build" "hisat-inspect")
2859 (("/usr/bin/env") (which "env")))
2860 #t))
2861 (replace 'install
2862 (lambda* (#:key outputs #:allow-other-keys)
2863 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2864 (for-each (lambda (file)
2865 (install-file file bin))
2866 (find-files
2867 "."
2868 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2869 #t))
2870 (delete 'configure))))
2871 (native-inputs
2872 `(("unzip" ,unzip)))
2873 (inputs
2874 `(("perl" ,perl)
2875 ("python" ,python)
2876 ("zlib" ,zlib)))
2877 ;; Non-portable SSE instructions are used so building fails on platforms
2878 ;; other than x86_64.
2879 (supported-systems '("x86_64-linux"))
2880 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2881 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2882 (description
2883 "HISAT is a fast and sensitive spliced alignment program for mapping
2884 RNA-seq reads. In addition to one global FM index that represents a whole
2885 genome, HISAT uses a large set of small FM indexes that collectively cover the
2886 whole genome. These small indexes (called local indexes) combined with
2887 several alignment strategies enable effective alignment of RNA-seq reads, in
2888 particular, reads spanning multiple exons.")
2889 (license license:gpl3+)))
2890
2891 (define-public hisat2
2892 (package
2893 (name "hisat2")
2894 (version "2.0.5")
2895 (source
2896 (origin
2897 (method url-fetch)
2898 ;; FIXME: a better source URL is
2899 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2900 ;; "/downloads/hisat2-" version "-source.zip")
2901 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2902 ;; but it is currently unavailable.
2903 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2904 (file-name (string-append name "-" version ".tar.gz"))
2905 (sha256
2906 (base32
2907 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2908 (build-system gnu-build-system)
2909 (arguments
2910 `(#:tests? #f ; no check target
2911 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2912 #:modules ((guix build gnu-build-system)
2913 (guix build utils)
2914 (srfi srfi-26))
2915 #:phases
2916 (modify-phases %standard-phases
2917 (add-after 'unpack 'make-deterministic
2918 (lambda _
2919 (substitute* "Makefile"
2920 (("`date`") "0"))
2921 #t))
2922 (delete 'configure)
2923 (replace 'install
2924 (lambda* (#:key outputs #:allow-other-keys)
2925 (let* ((out (assoc-ref outputs "out"))
2926 (bin (string-append out "/bin/"))
2927 (doc (string-append out "/share/doc/hisat2/")))
2928 (for-each
2929 (cut install-file <> bin)
2930 (find-files "."
2931 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2932 (mkdir-p doc)
2933 (install-file "doc/manual.inc.html" doc))
2934 #t)))))
2935 (native-inputs
2936 `(("unzip" ,unzip) ; needed for archive from ftp
2937 ("perl" ,perl)
2938 ("pandoc" ,ghc-pandoc))) ; for documentation
2939 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2940 (synopsis "Graph-based alignment of genomic sequencing reads")
2941 (description "HISAT2 is a fast and sensitive alignment program for mapping
2942 next-generation sequencing reads (both DNA and RNA) to a population of human
2943 genomes (as well as to a single reference genome). In addition to using one
2944 global @dfn{graph FM} (GFM) index that represents a population of human
2945 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2946 the whole genome. These small indexes, combined with several alignment
2947 strategies, enable rapid and accurate alignment of sequencing reads. This new
2948 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2949 ;; HISAT2 contains files from Bowtie2, which is released under
2950 ;; GPLv2 or later. The HISAT2 source files are released under
2951 ;; GPLv3 or later.
2952 (license license:gpl3+)))
2953
2954 (define-public hmmer
2955 (package
2956 (name "hmmer")
2957 (version "3.1b2")
2958 (source
2959 (origin
2960 (method url-fetch)
2961 (uri (string-append
2962 "http://eddylab.org/software/hmmer"
2963 (version-prefix version 1) "/"
2964 version "/hmmer-" version ".tar.gz"))
2965 (sha256
2966 (base32
2967 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2968 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2969 (build-system gnu-build-system)
2970 (native-inputs `(("perl" ,perl)))
2971 (home-page "http://hmmer.org/")
2972 (synopsis "Biosequence analysis using profile hidden Markov models")
2973 (description
2974 "HMMER is used for searching sequence databases for homologs of protein
2975 sequences, and for making protein sequence alignments. It implements methods
2976 using probabilistic models called profile hidden Markov models (profile
2977 HMMs).")
2978 (license (list license:gpl3+
2979 ;; The bundled library 'easel' is distributed
2980 ;; under The Janelia Farm Software License.
2981 (license:non-copyleft
2982 "file://easel/LICENSE"
2983 "See easel/LICENSE in the distribution.")))))
2984
2985 (define-public htseq
2986 (package
2987 (name "htseq")
2988 (version "0.9.1")
2989 (source (origin
2990 (method url-fetch)
2991 (uri (pypi-uri "HTSeq" version))
2992 (sha256
2993 (base32
2994 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2995 (build-system python-build-system)
2996 (native-inputs
2997 `(("python-cython" ,python-cython)))
2998 ;; Numpy needs to be propagated when htseq is used as a Python library.
2999 (propagated-inputs
3000 `(("python-numpy" ,python-numpy)))
3001 (inputs
3002 `(("python-pysam" ,python-pysam)
3003 ("python-matplotlib" ,python-matplotlib)))
3004 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3005 (synopsis "Analysing high-throughput sequencing data with Python")
3006 (description
3007 "HTSeq is a Python package that provides infrastructure to process data
3008 from high-throughput sequencing assays.")
3009 (license license:gpl3+)))
3010
3011 (define-public python2-htseq
3012 (package-with-python2 htseq))
3013
3014 (define-public java-htsjdk
3015 (package
3016 (name "java-htsjdk")
3017 (version "1.129")
3018 (source (origin
3019 (method url-fetch)
3020 (uri (string-append
3021 "https://github.com/samtools/htsjdk/archive/"
3022 version ".tar.gz"))
3023 (file-name (string-append name "-" version ".tar.gz"))
3024 (sha256
3025 (base32
3026 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
3027 (modules '((guix build utils)))
3028 ;; remove build dependency on git
3029 (snippet '(substitute* "build.xml"
3030 (("failifexecutionfails=\"true\"")
3031 "failifexecutionfails=\"false\"")))))
3032 (build-system ant-build-system)
3033 (arguments
3034 `(#:tests? #f ; test require Internet access
3035 #:make-flags
3036 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3037 "/share/java/htsjdk/"))
3038 #:build-target "all"
3039 #:phases
3040 (modify-phases %standard-phases
3041 ;; The build phase also installs the jars
3042 (delete 'install))))
3043 (home-page "http://samtools.github.io/htsjdk/")
3044 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3045 (description
3046 "HTSJDK is an implementation of a unified Java library for accessing
3047 common file formats, such as SAM and VCF, used for high-throughput
3048 sequencing (HTS) data. There are also an number of useful utilities for
3049 manipulating HTS data.")
3050 (license license:expat)))
3051
3052 (define-public htslib
3053 (package
3054 (name "htslib")
3055 (version "1.5")
3056 (source (origin
3057 (method url-fetch)
3058 (uri (string-append
3059 "https://github.com/samtools/htslib/releases/download/"
3060 version "/htslib-" version ".tar.bz2"))
3061 (sha256
3062 (base32
3063 "0bcjmnbwp2bib1z1bkrp95w9v2syzdwdfqww10mkb1hxlmg52ax0"))))
3064 (build-system gnu-build-system)
3065 (arguments
3066 `(#:phases
3067 (modify-phases %standard-phases
3068 (add-after
3069 'unpack 'patch-tests
3070 (lambda _
3071 (substitute* "test/test.pl"
3072 (("/bin/bash") (which "bash")))
3073 #t)))))
3074 (inputs
3075 `(("openssl" ,openssl)
3076 ("curl" ,curl)
3077 ("zlib" ,zlib)))
3078 (native-inputs
3079 `(("perl" ,perl)))
3080 (home-page "http://www.htslib.org")
3081 (synopsis "C library for reading/writing high-throughput sequencing data")
3082 (description
3083 "HTSlib is a C library for reading/writing high-throughput sequencing
3084 data. It also provides the bgzip, htsfile, and tabix utilities.")
3085 ;; Files under cram/ are released under the modified BSD license;
3086 ;; the rest is released under the Expat license
3087 (license (list license:expat license:bsd-3))))
3088
3089 ;; This package should be removed once no packages rely upon it.
3090 (define htslib-1.3
3091 (package
3092 (inherit htslib)
3093 (version "1.3.1")
3094 (source (origin
3095 (method url-fetch)
3096 (uri (string-append
3097 "https://github.com/samtools/htslib/releases/download/"
3098 version "/htslib-" version ".tar.bz2"))
3099 (sha256
3100 (base32
3101 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3102
3103 (define-public idr
3104 (package
3105 (name "idr")
3106 (version "2.0.0")
3107 (source (origin
3108 (method url-fetch)
3109 (uri (string-append
3110 "https://github.com/nboley/idr/archive/"
3111 version ".tar.gz"))
3112 (file-name (string-append name "-" version ".tar.gz"))
3113 (sha256
3114 (base32
3115 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3116 (build-system python-build-system)
3117 (arguments
3118 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3119 (propagated-inputs
3120 `(("python-scipy" ,python-scipy)
3121 ("python-sympy" ,python-sympy)
3122 ("python-numpy" ,python-numpy)
3123 ("python-matplotlib" ,python-matplotlib)))
3124 (native-inputs
3125 `(("python-cython" ,python-cython)))
3126 (home-page "https://github.com/nboley/idr")
3127 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3128 (description
3129 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3130 to measure the reproducibility of findings identified from replicate
3131 experiments and provide highly stable thresholds based on reproducibility.")
3132 (license license:gpl3+)))
3133
3134 (define-public jellyfish
3135 (package
3136 (name "jellyfish")
3137 (version "2.2.4")
3138 (source (origin
3139 (method url-fetch)
3140 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3141 "releases/download/v" version
3142 "/jellyfish-" version ".tar.gz"))
3143 (sha256
3144 (base32
3145 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3146 (build-system gnu-build-system)
3147 (outputs '("out" ;for library
3148 "ruby" ;for Ruby bindings
3149 "python")) ;for Python bindings
3150 (arguments
3151 `(#:configure-flags
3152 (list (string-append "--enable-ruby-binding="
3153 (assoc-ref %outputs "ruby"))
3154 (string-append "--enable-python-binding="
3155 (assoc-ref %outputs "python")))
3156 #:phases
3157 (modify-phases %standard-phases
3158 (add-before 'check 'set-SHELL-variable
3159 (lambda _
3160 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3161 ;; to run tests.
3162 (setenv "SHELL" (which "bash"))
3163 #t)))))
3164 (native-inputs
3165 `(("bc" ,bc)
3166 ("time" ,time)
3167 ("ruby" ,ruby)
3168 ("python" ,python-2)))
3169 (synopsis "Tool for fast counting of k-mers in DNA")
3170 (description
3171 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3172 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3173 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3174 is a command-line program that reads FASTA and multi-FASTA files containing
3175 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3176 translated into a human-readable text format using the @code{jellyfish dump}
3177 command, or queried for specific k-mers with @code{jellyfish query}.")
3178 (home-page "http://www.genome.umd.edu/jellyfish.html")
3179 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3180 (supported-systems '("x86_64-linux"))
3181 ;; The combined work is published under the GPLv3 or later. Individual
3182 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3183 (license (list license:gpl3+ license:expat))))
3184
3185 (define-public khmer
3186 (package
3187 (name "khmer")
3188 (version "2.0")
3189 (source
3190 (origin
3191 (method url-fetch)
3192 (uri (pypi-uri "khmer" version))
3193 (sha256
3194 (base32
3195 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3196 (patches (search-patches "khmer-use-libraries.patch"))))
3197 (build-system python-build-system)
3198 (arguments
3199 `(#:phases
3200 (modify-phases %standard-phases
3201 (add-after 'unpack 'set-paths
3202 (lambda* (#:key inputs outputs #:allow-other-keys)
3203 ;; Delete bundled libraries.
3204 (delete-file-recursively "third-party/zlib")
3205 (delete-file-recursively "third-party/bzip2")
3206 ;; Replace bundled seqan.
3207 (let* ((seqan-all "third-party/seqan")
3208 (seqan-include (string-append
3209 seqan-all "/core/include")))
3210 (delete-file-recursively seqan-all)
3211 (copy-recursively (string-append (assoc-ref inputs "seqan")
3212 "/include/seqan")
3213 (string-append seqan-include "/seqan")))
3214 ;; We do not replace the bundled MurmurHash as the canonical
3215 ;; repository for this code 'SMHasher' is unsuitable for
3216 ;; providing a library. See
3217 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3218 #t))
3219 (add-after 'unpack 'set-cc
3220 (lambda _
3221 (setenv "CC" "gcc")
3222 #t))
3223 ;; It is simpler to test after installation.
3224 (delete 'check)
3225 (add-after 'install 'post-install-check
3226 (lambda* (#:key inputs outputs #:allow-other-keys)
3227 (let ((out (assoc-ref outputs "out")))
3228 (setenv "PATH"
3229 (string-append
3230 (getenv "PATH")
3231 ":"
3232 (assoc-ref outputs "out")
3233 "/bin"))
3234 (setenv "PYTHONPATH"
3235 (string-append
3236 (getenv "PYTHONPATH")
3237 ":"
3238 out
3239 "/lib/python"
3240 (string-take (string-take-right
3241 (assoc-ref inputs "python") 5) 3)
3242 "/site-packages"))
3243 (with-directory-excursion "build"
3244 (zero? (system* "nosetests" "khmer" "--attr"
3245 "!known_failing")))))))))
3246 (native-inputs
3247 `(("seqan" ,seqan)
3248 ("python-nose" ,python-nose)))
3249 (inputs
3250 `(("zlib" ,zlib)
3251 ("bzip2" ,bzip2)
3252 ("python-screed" ,python-screed)
3253 ("python-bz2file" ,python-bz2file)
3254 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3255 ;; until the next version of khmer (likely 2.1) is released.
3256 ("gcc" ,gcc-4.9)))
3257 (home-page "https://khmer.readthedocs.org/")
3258 (synopsis "K-mer counting, filtering and graph traversal library")
3259 (description "The khmer software is a set of command-line tools for
3260 working with DNA shotgun sequencing data from genomes, transcriptomes,
3261 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3262 sometimes better. Khmer can also identify and fix problems with shotgun
3263 data.")
3264 ;; When building on i686, armhf and mips64el, we get the following error:
3265 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3266 (supported-systems '("x86_64-linux"))
3267 (license license:bsd-3)))
3268
3269 (define-public kaiju
3270 (package
3271 (name "kaiju")
3272 (version "1.5.0")
3273 (source (origin
3274 (method url-fetch)
3275 (uri (string-append
3276 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3277 version ".tar.gz"))
3278 (file-name (string-append name "-" version ".tar.gz"))
3279 (sha256
3280 (base32
3281 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3282 (build-system gnu-build-system)
3283 (arguments
3284 `(#:tests? #f ; There are no tests.
3285 #:phases
3286 (modify-phases %standard-phases
3287 (delete 'configure)
3288 (add-before 'build 'move-to-src-dir
3289 (lambda _ (chdir "src") #t))
3290 (replace 'install
3291 (lambda* (#:key inputs outputs #:allow-other-keys)
3292 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3293 (mkdir-p bin)
3294 (chdir "..")
3295 (copy-recursively "bin" bin)
3296 (copy-recursively "util" bin))
3297 #t)))))
3298 (inputs
3299 `(("perl" ,perl)))
3300 (home-page "http://kaiju.binf.ku.dk/")
3301 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3302 (description "Kaiju is a program for sensitive taxonomic classification
3303 of high-throughput sequencing reads from metagenomic whole genome sequencing
3304 experiments.")
3305 (license license:gpl3+)))
3306
3307 (define-public macs
3308 (package
3309 (name "macs")
3310 (version "2.1.0.20151222")
3311 (source (origin
3312 (method url-fetch)
3313 (uri (pypi-uri "MACS2" version))
3314 (sha256
3315 (base32
3316 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3317 (build-system python-build-system)
3318 (arguments
3319 `(#:python ,python-2 ; only compatible with Python 2.7
3320 #:tests? #f)) ; no test target
3321 (inputs
3322 `(("python-numpy" ,python2-numpy)))
3323 (home-page "https://github.com/taoliu/MACS/")
3324 (synopsis "Model based analysis for ChIP-Seq data")
3325 (description
3326 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3327 identifying transcript factor binding sites named Model-based Analysis of
3328 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3329 the significance of enriched ChIP regions and it improves the spatial
3330 resolution of binding sites through combining the information of both
3331 sequencing tag position and orientation.")
3332 (license license:bsd-3)))
3333
3334 (define-public mafft
3335 (package
3336 (name "mafft")
3337 (version "7.310")
3338 (source (origin
3339 (method url-fetch)
3340 (uri (string-append
3341 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3342 "-without-extensions-src.tgz"))
3343 (file-name (string-append name "-" version ".tgz"))
3344 (sha256
3345 (base32
3346 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3347 (build-system gnu-build-system)
3348 (arguments
3349 `(#:tests? #f ; no automated tests, though there are tests in the read me
3350 #:make-flags (let ((out (assoc-ref %outputs "out")))
3351 (list (string-append "PREFIX=" out)
3352 (string-append "BINDIR="
3353 (string-append out "/bin"))))
3354 #:phases
3355 (modify-phases %standard-phases
3356 (add-after 'unpack 'enter-dir
3357 (lambda _ (chdir "core") #t))
3358 (add-after 'enter-dir 'patch-makefile
3359 (lambda _
3360 ;; on advice from the MAFFT authors, there is no need to
3361 ;; distribute mafft-profile, mafft-distance, or
3362 ;; mafft-homologs.rb as they are too "specialised".
3363 (substitute* "Makefile"
3364 ;; remove mafft-homologs.rb from SCRIPTS
3365 (("^SCRIPTS = mafft mafft-homologs.rb")
3366 "SCRIPTS = mafft")
3367 ;; remove mafft-homologs from MANPAGES
3368 (("^MANPAGES = mafft.1 mafft-homologs.1")
3369 "MANPAGES = mafft.1")
3370 ;; remove mafft-distance from PROGS
3371 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3372 "PROGS = dvtditr dndfast7 dndblast sextet5")
3373 ;; remove mafft-profile from PROGS
3374 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3375 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3376 (("^rm -f mafft-profile mafft-profile.exe") "#")
3377 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3378 ;; do not install MAN pages in libexec folder
3379 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3380 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3381 #t))
3382 (add-after 'enter-dir 'patch-paths
3383 (lambda* (#:key inputs #:allow-other-keys)
3384 (substitute* '("pairash.c"
3385 "mafft.tmpl")
3386 (("perl") (which "perl"))
3387 (("([\"`| ])awk" _ prefix)
3388 (string-append prefix (which "awk")))
3389 (("grep") (which "grep")))
3390 #t))
3391 (delete 'configure)
3392 (add-after 'install 'wrap-programs
3393 (lambda* (#:key outputs #:allow-other-keys)
3394 (let* ((out (assoc-ref outputs "out"))
3395 (bin (string-append out "/bin"))
3396 (path (string-append
3397 (assoc-ref %build-inputs "coreutils") "/bin:")))
3398 (for-each (lambda (file)
3399 (wrap-program file
3400 `("PATH" ":" prefix (,path))))
3401 (find-files bin)))
3402 #t)))))
3403 (inputs
3404 `(("perl" ,perl)
3405 ("ruby" ,ruby)
3406 ("gawk" ,gawk)
3407 ("grep" ,grep)
3408 ("coreutils" ,coreutils)))
3409 (home-page "http://mafft.cbrc.jp/alignment/software/")
3410 (synopsis "Multiple sequence alignment program")
3411 (description
3412 "MAFFT offers a range of multiple alignment methods for nucleotide and
3413 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3414 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3415 sequences).")
3416 (license (license:non-copyleft
3417 "http://mafft.cbrc.jp/alignment/software/license.txt"
3418 "BSD-3 with different formatting"))))
3419
3420 (define-public mash
3421 (package
3422 (name "mash")
3423 (version "1.1.1")
3424 (source (origin
3425 (method url-fetch)
3426 (uri (string-append
3427 "https://github.com/marbl/mash/archive/v"
3428 version ".tar.gz"))
3429 (file-name (string-append name "-" version ".tar.gz"))
3430 (sha256
3431 (base32
3432 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3433 (modules '((guix build utils)))
3434 (snippet
3435 ;; Delete bundled kseq.
3436 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3437 '(delete-file "src/mash/kseq.h"))))
3438 (build-system gnu-build-system)
3439 (arguments
3440 `(#:tests? #f ; No tests.
3441 #:configure-flags
3442 (list
3443 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3444 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3445 #:make-flags (list "CC=gcc")
3446 #:phases
3447 (modify-phases %standard-phases
3448 (add-after 'unpack 'fix-includes
3449 (lambda _
3450 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3451 (("^#include \"kseq\\.h\"")
3452 "#include \"htslib/kseq.h\""))
3453 #t))
3454 (add-after 'fix-includes 'autoconf
3455 (lambda _ (zero? (system* "autoconf")))))))
3456 (native-inputs
3457 `(("autoconf" ,autoconf)
3458 ;; Capnproto and htslib are statically embedded in the final
3459 ;; application. Therefore we also list their licenses, below.
3460 ("capnproto" ,capnproto)
3461 ("htslib" ,htslib)))
3462 (inputs
3463 `(("gsl" ,gsl)
3464 ("zlib" ,zlib)))
3465 (supported-systems '("x86_64-linux"))
3466 (home-page "https://mash.readthedocs.io")
3467 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3468 (description "Mash is a fast sequence distance estimator that uses the
3469 MinHash algorithm and is designed to work with genomes and metagenomes in the
3470 form of assemblies or reads.")
3471 (license (list license:bsd-3 ; Mash
3472 license:expat ; HTSlib and capnproto
3473 license:public-domain ; MurmurHash 3
3474 license:cpl1.0)))) ; Open Bloom Filter
3475
3476 (define-public metabat
3477 (package
3478 (name "metabat")
3479 (version "2.12.1")
3480 (source
3481 (origin
3482 (method url-fetch)
3483 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3484 version ".tar.gz"))
3485 (file-name (string-append name "-" version ".tar.gz"))
3486 (sha256
3487 (base32
3488 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3489 (patches (search-patches "metabat-fix-compilation.patch"))))
3490 (build-system gnu-build-system)
3491 (arguments
3492 `(#:phases
3493 (modify-phases %standard-phases
3494 (add-after 'unpack 'fix-includes
3495 (lambda _
3496 (substitute* "src/BamUtils.h"
3497 (("^#include \"bam/bam\\.h\"")
3498 "#include \"samtools/bam.h\"")
3499 (("^#include \"bam/sam\\.h\"")
3500 "#include \"samtools/sam.h\""))
3501 (substitute* "src/KseqReader.h"
3502 (("^#include \"bam/kseq\\.h\"")
3503 "#include \"htslib/kseq.h\""))
3504 #t))
3505 (add-after 'unpack 'fix-scons
3506 (lambda* (#:key inputs #:allow-other-keys)
3507 (substitute* "SConstruct"
3508 (("^htslib_dir += 'samtools'")
3509 (string-append "htslib_dir = '"
3510 (assoc-ref inputs "htslib")
3511 "'"))
3512 (("^samtools_dir = 'samtools'")
3513 (string-append "samtools_dir = '"
3514 (assoc-ref inputs "samtools")
3515 "'"))
3516 (("^findStaticOrShared\\('bam', hts_lib")
3517 (string-append "findStaticOrShared('bam', '"
3518 (assoc-ref inputs "samtools")
3519 "/lib'"))
3520 ;; Do not distribute README.
3521 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3522 #t))
3523 (delete 'configure)
3524 (replace 'build
3525 (lambda* (#:key inputs outputs #:allow-other-keys)
3526 (mkdir (assoc-ref outputs "out"))
3527 (zero? (system* "scons"
3528 (string-append
3529 "PREFIX="
3530 (assoc-ref outputs "out"))
3531 (string-append
3532 "BOOST_ROOT="
3533 (assoc-ref inputs "boost"))
3534 "install"))))
3535 ;; Check and install are carried out during build phase.
3536 (delete 'check)
3537 (delete 'install))))
3538 (inputs
3539 `(("zlib" ,zlib)
3540 ("perl" ,perl)
3541 ("samtools" ,samtools)
3542 ("htslib" ,htslib)
3543 ("boost" ,boost)))
3544 (native-inputs
3545 `(("scons" ,scons)))
3546 (home-page "https://bitbucket.org/berkeleylab/metabat")
3547 (synopsis
3548 "Reconstruction of single genomes from complex microbial communities")
3549 (description
3550 "Grouping large genomic fragments assembled from shotgun metagenomic
3551 sequences to deconvolute complex microbial communities, or metagenome binning,
3552 enables the study of individual organisms and their interactions. MetaBAT is
3553 an automated metagenome binning software, which integrates empirical
3554 probabilistic distances of genome abundance and tetranucleotide frequency.")
3555 ;; The source code contains inline assembly.
3556 (supported-systems '("x86_64-linux" "i686-linux"))
3557 (license (license:non-copyleft "file://license.txt"
3558 "See license.txt in the distribution."))))
3559
3560 (define-public minced
3561 (package
3562 (name "minced")
3563 (version "0.2.0")
3564 (source (origin
3565 (method url-fetch)
3566 (uri (string-append
3567 "https://github.com/ctSkennerton/minced/archive/"
3568 version ".tar.gz"))
3569 (file-name (string-append name "-" version ".tar.gz"))
3570 (sha256
3571 (base32
3572 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3573 (build-system gnu-build-system)
3574 (arguments
3575 `(#:test-target "test"
3576 #:phases
3577 (modify-phases %standard-phases
3578 (delete 'configure)
3579 (add-before 'check 'fix-test
3580 (lambda _
3581 ;; Fix test for latest version.
3582 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3583 (("minced:0.1.6") "minced:0.2.0"))
3584 #t))
3585 (replace 'install ; No install target.
3586 (lambda* (#:key inputs outputs #:allow-other-keys)
3587 (let* ((out (assoc-ref outputs "out"))
3588 (bin (string-append out "/bin"))
3589 (wrapper (string-append bin "/minced")))
3590 ;; Minced comes with a wrapper script that tries to figure out where
3591 ;; it is located before running the JAR. Since these paths are known
3592 ;; to us, we build our own wrapper to avoid coreutils dependency.
3593 (install-file "minced.jar" bin)
3594 (with-output-to-file wrapper
3595 (lambda _
3596 (display
3597 (string-append
3598 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3599 (assoc-ref inputs "jre") "/bin/java -jar "
3600 bin "/minced.jar \"$@\"\n"))))
3601 (chmod wrapper #o555)))))))
3602 (native-inputs
3603 `(("jdk" ,icedtea "jdk")))
3604 (inputs
3605 `(("bash" ,bash)
3606 ("jre" ,icedtea "out")))
3607 (home-page "https://github.com/ctSkennerton/minced")
3608 (synopsis "Mining CRISPRs in Environmental Datasets")
3609 (description
3610 "MinCED is a program to find Clustered Regularly Interspaced Short
3611 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3612 unassembled metagenomic reads, but is mainly designed for full genomes and
3613 assembled metagenomic sequence.")
3614 (license license:gpl3+)))
3615
3616 (define-public miso
3617 (package
3618 (name "miso")
3619 (version "0.5.3")
3620 (source (origin
3621 (method url-fetch)
3622 (uri (string-append
3623 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3624 version ".tar.gz"))
3625 (sha256
3626 (base32
3627 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3628 (modules '((guix build utils)))
3629 (snippet
3630 '(substitute* "setup.py"
3631 ;; Use setuptools, or else the executables are not
3632 ;; installed.
3633 (("distutils.core") "setuptools")
3634 ;; use "gcc" instead of "cc" for compilation
3635 (("^defines")
3636 "cc.set_executables(
3637 compiler='gcc',
3638 compiler_so='gcc',
3639 linker_exe='gcc',
3640 linker_so='gcc -shared'); defines")))))
3641 (build-system python-build-system)
3642 (arguments
3643 `(#:python ,python-2 ; only Python 2 is supported
3644 #:tests? #f)) ; no "test" target
3645 (inputs
3646 `(("samtools" ,samtools)
3647 ("python-numpy" ,python2-numpy)
3648 ("python-pysam" ,python2-pysam)
3649 ("python-scipy" ,python2-scipy)
3650 ("python-matplotlib" ,python2-matplotlib)))
3651 (native-inputs
3652 `(("python-mock" ,python2-mock) ;for tests
3653 ("python-pytz" ,python2-pytz))) ;for tests
3654 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3655 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3656 (description
3657 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3658 the expression level of alternatively spliced genes from RNA-Seq data, and
3659 identifies differentially regulated isoforms or exons across samples. By
3660 modeling the generative process by which reads are produced from isoforms in
3661 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3662 that a read originated from a particular isoform.")
3663 (license license:gpl2)))
3664
3665 (define-public muscle
3666 (package
3667 (name "muscle")
3668 (version "3.8.1551")
3669 (source (origin
3670 (method url-fetch/tarbomb)
3671 (uri (string-append
3672 "http://www.drive5.com/muscle/muscle_src_"
3673 version ".tar.gz"))
3674 (sha256
3675 (base32
3676 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3677 (build-system gnu-build-system)
3678 (arguments
3679 `(#:make-flags (list "LDLIBS = -lm")
3680 #:phases
3681 (modify-phases %standard-phases
3682 (delete 'configure)
3683 (replace 'check
3684 ;; There are no tests, so just test if it runs.
3685 (lambda _ (zero? (system* "./muscle" "-version"))))
3686 (replace 'install
3687 (lambda* (#:key outputs #:allow-other-keys)
3688 (let* ((out (assoc-ref outputs "out"))
3689 (bin (string-append out "/bin")))
3690 (install-file "muscle" bin)))))))
3691 (home-page "http://www.drive5.com/muscle")
3692 (synopsis "Multiple sequence alignment program")
3693 (description
3694 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3695 program for nucleotide and protein sequences.")
3696 ;; License information found in 'muscle -h' and usage.cpp.
3697 (license license:public-domain)))
3698
3699 (define-public newick-utils
3700 ;; There are no recent releases so we package from git.
3701 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3702 (package
3703 (name "newick-utils")
3704 (version (string-append "1.6-1." (string-take commit 8)))
3705 (source (origin
3706 (method git-fetch)
3707 (uri (git-reference
3708 (url "https://github.com/tjunier/newick_utils.git")
3709 (commit commit)))
3710 (file-name (string-append name "-" version "-checkout"))
3711 (sha256
3712 (base32
3713 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3714 (build-system gnu-build-system)
3715 (arguments
3716 `(#:phases
3717 (modify-phases %standard-phases
3718 (add-after 'unpack 'autoconf
3719 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3720 (inputs
3721 ;; XXX: TODO: Enable Lua and Guile bindings.
3722 ;; https://github.com/tjunier/newick_utils/issues/13
3723 `(("libxml2" ,libxml2)
3724 ("flex" ,flex)
3725 ("bison" ,bison)))
3726 (native-inputs
3727 `(("autoconf" ,autoconf)
3728 ("automake" ,automake)
3729 ("libtool" ,libtool)))
3730 (synopsis "Programs for working with newick format phylogenetic trees")
3731 (description
3732 "Newick-utils is a suite of utilities for processing phylogenetic trees
3733 in Newick format. Functions include re-rooting, extracting subtrees,
3734 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3735 (home-page "https://github.com/tjunier/newick_utils")
3736 (license license:bsd-3))))
3737
3738 (define-public orfm
3739 (package
3740 (name "orfm")
3741 (version "0.7.1")
3742 (source (origin
3743 (method url-fetch)
3744 (uri (string-append
3745 "https://github.com/wwood/OrfM/releases/download/v"
3746 version "/orfm-" version ".tar.gz"))
3747 (sha256
3748 (base32
3749 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
3750 (build-system gnu-build-system)
3751 (inputs `(("zlib" ,zlib)))
3752 (native-inputs
3753 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3754 ("ruby-rspec" ,ruby-rspec)
3755 ("ruby" ,ruby)))
3756 (synopsis "Simple and not slow open reading frame (ORF) caller")
3757 (description
3758 "An ORF caller finds stretches of DNA that, when translated, are not
3759 interrupted by stop codons. OrfM finds and prints these ORFs.")
3760 (home-page "https://github.com/wwood/OrfM")
3761 (license license:lgpl3+)))
3762
3763 (define-public pplacer
3764 (let ((commit "g807f6f3"))
3765 (package
3766 (name "pplacer")
3767 ;; The commit should be updated with each version change.
3768 (version "1.1.alpha19")
3769 (source
3770 (origin
3771 (method url-fetch)
3772 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3773 version ".tar.gz"))
3774 (file-name (string-append name "-" version ".tar.gz"))
3775 (sha256
3776 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3777 (build-system ocaml-build-system)
3778 (arguments
3779 `(#:ocaml ,ocaml-4.01
3780 #:findlib ,ocaml4.01-findlib
3781 #:modules ((guix build ocaml-build-system)
3782 (guix build utils)
3783 (ice-9 ftw))
3784 #:phases
3785 (modify-phases %standard-phases
3786 (delete 'configure)
3787 (add-after 'unpack 'replace-bundled-cddlib
3788 (lambda* (#:key inputs #:allow-other-keys)
3789 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3790 (local-dir "cddlib_guix"))
3791 (mkdir local-dir)
3792 (with-directory-excursion local-dir
3793 (system* "tar" "xvf" cddlib-src))
3794 (let ((cddlib-src-folder
3795 (string-append local-dir "/"
3796 (list-ref (scandir local-dir) 2)
3797 "/lib-src")))
3798 (for-each
3799 (lambda (file)
3800 (copy-file file
3801 (string-append "cdd_src/" (basename file))))
3802 (find-files cddlib-src-folder ".*[ch]$")))
3803 #t)))
3804 (add-after 'unpack 'fix-makefile
3805 (lambda _
3806 ;; Remove system calls to 'git'.
3807 (substitute* "Makefile"
3808 (("^DESCRIPT:=pplacer-.*")
3809 (string-append
3810 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3811 (substitute* "myocamlbuild.ml"
3812 (("git describe --tags --long .*\\\" with")
3813 (string-append
3814 "echo -n v" ,version "-" ,commit "\" with")))
3815 #t))
3816 (replace 'install
3817 (lambda* (#:key outputs #:allow-other-keys)
3818 (let* ((out (assoc-ref outputs "out"))
3819 (bin (string-append out "/bin")))
3820 (copy-recursively "bin" bin))
3821 #t)))))
3822 (native-inputs
3823 `(("zlib" ,zlib)
3824 ("gsl" ,gsl)
3825 ("ocaml-ounit" ,ocaml4.01-ounit)
3826 ("ocaml-batteries" ,ocaml4.01-batteries)
3827 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3828 ("ocaml-csv" ,ocaml4.01-csv)
3829 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3830 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3831 ("ocaml-mcl" ,ocaml4.01-mcl)
3832 ("ocaml-gsl" ,ocaml4.01-gsl)
3833 ("cddlib-src" ,(package-source cddlib))))
3834 (propagated-inputs
3835 `(("pplacer-scripts" ,pplacer-scripts)))
3836 (synopsis "Phylogenetic placement of biological sequences")
3837 (description
3838 "Pplacer places query sequences on a fixed reference phylogenetic tree
3839 to maximize phylogenetic likelihood or posterior probability according to a
3840 reference alignment. Pplacer is designed to be fast, to give useful
3841 information about uncertainty, and to offer advanced visualization and
3842 downstream analysis.")
3843 (home-page "http://matsen.fhcrc.org/pplacer")
3844 (license license:gpl3))))
3845
3846 ;; This package is installed alongside 'pplacer'. It is a separate package so
3847 ;; that it can use the python-build-system for the scripts that are
3848 ;; distributed alongside the main OCaml binaries.
3849 (define pplacer-scripts
3850 (package
3851 (inherit pplacer)
3852 (name "pplacer-scripts")
3853 (build-system python-build-system)
3854 (arguments
3855 `(#:python ,python-2
3856 #:phases
3857 (modify-phases %standard-phases
3858 (add-after 'unpack 'enter-scripts-dir
3859 (lambda _ (chdir "scripts")))
3860 (replace 'check
3861 (lambda _
3862 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
3863 (add-after 'install 'wrap-executables
3864 (lambda* (#:key inputs outputs #:allow-other-keys)
3865 (let* ((out (assoc-ref outputs "out"))
3866 (bin (string-append out "/bin")))
3867 (let ((path (string-append
3868 (assoc-ref inputs "hmmer") "/bin:"
3869 (assoc-ref inputs "infernal") "/bin")))
3870 (display path)
3871 (wrap-program (string-append bin "/refpkg_align.py")
3872 `("PATH" ":" prefix (,path))))
3873 (let ((path (string-append
3874 (assoc-ref inputs "hmmer") "/bin")))
3875 (wrap-program (string-append bin "/hrefpkg_query.py")
3876 `("PATH" ":" prefix (,path)))))
3877 #t)))))
3878 (inputs
3879 `(("infernal" ,infernal)
3880 ("hmmer" ,hmmer)))
3881 (propagated-inputs
3882 `(("python-biopython" ,python2-biopython)
3883 ("taxtastic" ,taxtastic)))
3884 (synopsis "Pplacer Python scripts")))
3885
3886 (define-public python2-pbcore
3887 (package
3888 (name "python2-pbcore")
3889 (version "1.2.10")
3890 (source (origin
3891 (method url-fetch)
3892 (uri (pypi-uri "pbcore" version))
3893 (sha256
3894 (base32
3895 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3896 (build-system python-build-system)
3897 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3898 (propagated-inputs
3899 `(("python-cython" ,python2-cython)
3900 ("python-numpy" ,python2-numpy)
3901 ("python-pysam" ,python2-pysam)
3902 ("python-h5py" ,python2-h5py)))
3903 (native-inputs
3904 `(("python-nose" ,python2-nose)
3905 ("python-sphinx" ,python2-sphinx)
3906 ("python-pyxb" ,python2-pyxb)))
3907 (home-page "http://pacificbiosciences.github.io/pbcore/")
3908 (synopsis "Library for reading and writing PacBio data files")
3909 (description
3910 "The pbcore package provides Python APIs for interacting with PacBio data
3911 files and writing bioinformatics applications.")
3912 (license license:bsd-3)))
3913
3914 (define-public python2-warpedlmm
3915 (package
3916 (name "python2-warpedlmm")
3917 (version "0.21")
3918 (source
3919 (origin
3920 (method url-fetch)
3921 (uri (string-append
3922 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3923 version ".zip"))
3924 (sha256
3925 (base32
3926 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3927 (build-system python-build-system)
3928 (arguments
3929 `(#:python ,python-2)) ; requires Python 2.7
3930 (propagated-inputs
3931 `(("python-scipy" ,python2-scipy)
3932 ("python-numpy" ,python2-numpy)
3933 ("python-matplotlib" ,python2-matplotlib)
3934 ("python-fastlmm" ,python2-fastlmm)
3935 ("python-pandas" ,python2-pandas)
3936 ("python-pysnptools" ,python2-pysnptools)))
3937 (native-inputs
3938 `(("python-mock" ,python2-mock)
3939 ("python-nose" ,python2-nose)
3940 ("unzip" ,unzip)))
3941 (home-page "https://github.com/PMBio/warpedLMM")
3942 (synopsis "Implementation of warped linear mixed models")
3943 (description
3944 "WarpedLMM is a Python implementation of the warped linear mixed model,
3945 which automatically learns an optimal warping function (or transformation) for
3946 the phenotype as it models the data.")
3947 (license license:asl2.0)))
3948
3949 (define-public pbtranscript-tofu
3950 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3951 (package
3952 (name "pbtranscript-tofu")
3953 (version (string-append "2.2.3." (string-take commit 7)))
3954 (source (origin
3955 (method git-fetch)
3956 (uri (git-reference
3957 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3958 (commit commit)))
3959 (file-name (string-append name "-" version "-checkout"))
3960 (sha256
3961 (base32
3962 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3963 (modules '((guix build utils)))
3964 (snippet
3965 '(begin
3966 ;; remove bundled Cython sources
3967 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3968 #t))))
3969 (build-system python-build-system)
3970 (arguments
3971 `(#:python ,python-2
3972 ;; FIXME: Tests fail with "No such file or directory:
3973 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3974 #:tests? #f
3975 #:phases
3976 (modify-phases %standard-phases
3977 (add-after 'unpack 'enter-directory
3978 (lambda _
3979 (chdir "pbtranscript-tofu/pbtranscript/")
3980 #t))
3981 ;; With setuptools version 18.0 and later this setup.py hack causes
3982 ;; a build error, so we disable it.
3983 (add-after 'enter-directory 'patch-setuppy
3984 (lambda _
3985 (substitute* "setup.py"
3986 (("if 'setuptools.extension' in sys.modules:")
3987 "if False:"))
3988 #t)))))
3989 (inputs
3990 `(("python-numpy" ,python2-numpy)
3991 ("python-bx-python" ,python2-bx-python)
3992 ("python-networkx" ,python2-networkx)
3993 ("python-scipy" ,python2-scipy)
3994 ("python-pbcore" ,python2-pbcore)
3995 ("python-h5py" ,python2-h5py)))
3996 (native-inputs
3997 `(("python-cython" ,python2-cython)
3998 ("python-nose" ,python2-nose)))
3999 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4000 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4001 (description
4002 "pbtranscript-tofu contains scripts to analyze transcriptome data
4003 generated using the PacBio Iso-Seq protocol.")
4004 (license license:bsd-3))))
4005
4006 (define-public prank
4007 (package
4008 (name "prank")
4009 (version "150803")
4010 (source (origin
4011 (method url-fetch)
4012 (uri (string-append
4013 "http://wasabiapp.org/download/prank/prank.source."
4014 version ".tgz"))
4015 (sha256
4016 (base32
4017 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4018 (build-system gnu-build-system)
4019 (arguments
4020 `(#:phases
4021 (modify-phases %standard-phases
4022 (add-after 'unpack 'enter-src-dir
4023 (lambda _
4024 (chdir "src")
4025 #t))
4026 (add-after 'unpack 'remove-m64-flag
4027 ;; Prank will build with the correct 'bit-ness' without this flag
4028 ;; and this allows building on 32-bit machines.
4029 (lambda _ (substitute* "src/Makefile"
4030 (("-m64") ""))
4031 #t))
4032 (delete 'configure)
4033 (replace 'install
4034 (lambda* (#:key outputs #:allow-other-keys)
4035 (let* ((out (assoc-ref outputs "out"))
4036 (bin (string-append out "/bin"))
4037 (man (string-append out "/share/man/man1"))
4038 (path (string-append
4039 (assoc-ref %build-inputs "mafft") "/bin:"
4040 (assoc-ref %build-inputs "exonerate") "/bin:"
4041 (assoc-ref %build-inputs "bppsuite") "/bin")))
4042 (install-file "prank" bin)
4043 (wrap-program (string-append bin "/prank")
4044 `("PATH" ":" prefix (,path)))
4045 (install-file "prank.1" man))
4046 #t)))))
4047 (inputs
4048 `(("mafft" ,mafft)
4049 ("exonerate" ,exonerate)
4050 ("bppsuite" ,bppsuite)))
4051 (home-page "http://wasabiapp.org/software/prank/")
4052 (synopsis "Probabilistic multiple sequence alignment program")
4053 (description
4054 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4055 codon and amino-acid sequences. It is based on a novel algorithm that treats
4056 insertions correctly and avoids over-estimation of the number of deletion
4057 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4058 in phylogenetics and correctly takes into account the evolutionary distances
4059 between sequences. Lastly, PRANK allows for defining a potential structure
4060 for sequences to be aligned and then, simultaneously with the alignment,
4061 predicts the locations of structural units in the sequences.")
4062 (license license:gpl2+)))
4063
4064 (define-public proteinortho
4065 (package
4066 (name "proteinortho")
4067 (version "5.16")
4068 (source
4069 (origin
4070 (method url-fetch)
4071 (uri
4072 (string-append
4073 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4074 version "_src.tar.gz"))
4075 (sha256
4076 (base32
4077 "0z4f5cg0cs8ai62hfvp4q6w66q2phcc55nhs4xj5cyhxxivjv2ai"))))
4078 (build-system gnu-build-system)
4079 (arguments
4080 `(#:test-target "test"
4081 #:phases
4082 (modify-phases %standard-phases
4083 (replace 'configure
4084 ;; There is no configure script, so we modify the Makefile directly.
4085 (lambda* (#:key outputs #:allow-other-keys)
4086 (substitute* "Makefile"
4087 (("INSTALLDIR=.*")
4088 (string-append
4089 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4090 #t))
4091 (add-before 'install 'make-install-directory
4092 ;; The install directory is not created during 'make install'.
4093 (lambda* (#:key outputs #:allow-other-keys)
4094 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4095 #t))
4096 (add-after 'install 'wrap-programs
4097 (lambda* (#:key inputs outputs #:allow-other-keys)
4098 (let* ((path (getenv "PATH"))
4099 (out (assoc-ref outputs "out"))
4100 (binary (string-append out "/bin/proteinortho5.pl")))
4101 (wrap-program binary `("PATH" ":" prefix (,path))))
4102 #t)))))
4103 (inputs
4104 `(("perl" ,perl)
4105 ("python" ,python-2)
4106 ("blast+" ,blast+)))
4107 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4108 (synopsis "Detect orthologous genes across species")
4109 (description
4110 "Proteinortho is a tool to detect orthologous genes across different
4111 species. For doing so, it compares similarities of given gene sequences and
4112 clusters them to find significant groups. The algorithm was designed to handle
4113 large-scale data and can be applied to hundreds of species at once.")
4114 (license license:gpl2+)))
4115
4116 (define-public pyicoteo
4117 (package
4118 (name "pyicoteo")
4119 (version "2.0.7")
4120 (source
4121 (origin
4122 (method url-fetch)
4123 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4124 "pyicoteo/get/v" version ".tar.bz2"))
4125 (file-name (string-append name "-" version ".tar.bz2"))
4126 (sha256
4127 (base32
4128 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4129 (build-system python-build-system)
4130 (arguments
4131 `(#:python ,python-2 ; does not work with Python 3
4132 #:tests? #f)) ; there are no tests
4133 (inputs
4134 `(("python2-matplotlib" ,python2-matplotlib)))
4135 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4136 (synopsis "Analyze high-throughput genetic sequencing data")
4137 (description
4138 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4139 sequencing data. It works with genomic coordinates. There are currently six
4140 different command-line tools:
4141
4142 @enumerate
4143 @item pyicoregion: for generating exploratory regions automatically;
4144 @item pyicoenrich: for differential enrichment between two conditions;
4145 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4146 @item pyicos: for genomic coordinates manipulation;
4147 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4148 @item pyicount: to count how many reads from N experiment files overlap in a
4149 region file;
4150 @item pyicotrocol: to combine operations from pyicoteo.
4151 @end enumerate\n")
4152 (license license:gpl3+)))
4153
4154 (define-public prodigal
4155 (package
4156 (name "prodigal")
4157 (version "2.6.3")
4158 (source (origin
4159 (method url-fetch)
4160 (uri (string-append
4161 "https://github.com/hyattpd/Prodigal/archive/v"
4162 version ".tar.gz"))
4163 (file-name (string-append name "-" version ".tar.gz"))
4164 (sha256
4165 (base32
4166 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4167 (build-system gnu-build-system)
4168 (arguments
4169 `(#:tests? #f ;no check target
4170 #:make-flags (list (string-append "INSTALLDIR="
4171 (assoc-ref %outputs "out")
4172 "/bin"))
4173 #:phases
4174 (modify-phases %standard-phases
4175 (delete 'configure))))
4176 (home-page "http://prodigal.ornl.gov")
4177 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4178 (description
4179 "Prodigal runs smoothly on finished genomes, draft genomes, and
4180 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4181 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4182 partial genes, and identifies translation initiation sites.")
4183 (license license:gpl3+)))
4184
4185 (define-public roary
4186 (package
4187 (name "roary")
4188 (version "3.8.2")
4189 (source
4190 (origin
4191 (method url-fetch)
4192 (uri (string-append
4193 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4194 version ".tar.gz"))
4195 (sha256
4196 (base32
4197 "03dfr2cd5fp80bcr65923zpdzrasvcxl7c2vgh8373v25a1yfap7"))))
4198 (build-system perl-build-system)
4199 (arguments
4200 `(#:phases
4201 (modify-phases %standard-phases
4202 (delete 'configure)
4203 (delete 'build)
4204 (replace 'check
4205 (lambda _
4206 ;; The tests are not run by default, so we run each test file
4207 ;; directly.
4208 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4209 (getenv "PATH")))
4210 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4211 (getenv "PERL5LIB")))
4212 (zero? (length (filter (lambda (file)
4213 (display file)(display "\n")
4214 (not (zero? (system* "perl" file))))
4215 (find-files "t" ".*\\.t$"))))))
4216 (replace 'install
4217 ;; There is no 'install' target in the Makefile.
4218 (lambda* (#:key outputs #:allow-other-keys)
4219 (let* ((out (assoc-ref outputs "out"))
4220 (bin (string-append out "/bin"))
4221 (perl (string-append out "/lib/perl5/site_perl"))
4222 (roary-plots "contrib/roary_plots"))
4223 (mkdir-p bin)
4224 (mkdir-p perl)
4225 (copy-recursively "bin" bin)
4226 (copy-recursively "lib" perl)
4227 #t)))
4228 (add-after 'install 'wrap-programs
4229 (lambda* (#:key inputs outputs #:allow-other-keys)
4230 (let* ((out (assoc-ref outputs "out"))
4231 (perl5lib (getenv "PERL5LIB"))
4232 (path (getenv "PATH")))
4233 (for-each (lambda (prog)
4234 (let ((binary (string-append out "/" prog)))
4235 (wrap-program binary
4236 `("PERL5LIB" ":" prefix
4237 (,(string-append perl5lib ":" out
4238 "/lib/perl5/site_perl"))))
4239 (wrap-program binary
4240 `("PATH" ":" prefix
4241 (,(string-append path ":" out "/bin"))))))
4242 (find-files "bin" ".*[^R]$"))
4243 (let ((file
4244 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4245 (r-site-lib (getenv "R_LIBS_SITE"))
4246 (coreutils-path
4247 (string-append (assoc-ref inputs "coreutils") "/bin")))
4248 (wrap-program file
4249 `("R_LIBS_SITE" ":" prefix
4250 (,(string-append r-site-lib ":" out "/site-library/"))))
4251 (wrap-program file
4252 `("PATH" ":" prefix
4253 (,(string-append coreutils-path ":" out "/bin"))))))
4254 #t)))))
4255 (native-inputs
4256 `(("perl-env-path" ,perl-env-path)
4257 ("perl-test-files" ,perl-test-files)
4258 ("perl-test-most" ,perl-test-most)
4259 ("perl-test-output" ,perl-test-output)))
4260 (inputs
4261 `(("perl-array-utils" ,perl-array-utils)
4262 ("bioperl" ,bioperl-minimal)
4263 ("perl-exception-class" ,perl-exception-class)
4264 ("perl-file-find-rule" ,perl-file-find-rule)
4265 ("perl-file-grep" ,perl-file-grep)
4266 ("perl-file-slurper" ,perl-file-slurper)
4267 ("perl-file-which" ,perl-file-which)
4268 ("perl-graph" ,perl-graph)
4269 ("perl-graph-readwrite" ,perl-graph-readwrite)
4270 ("perl-log-log4perl" ,perl-log-log4perl)
4271 ("perl-moose" ,perl-moose)
4272 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4273 ("perl-text-csv" ,perl-text-csv)
4274 ("bedtools" ,bedtools)
4275 ("cd-hit" ,cd-hit)
4276 ("blast+" ,blast+)
4277 ("mcl" ,mcl)
4278 ("parallel" ,parallel)
4279 ("prank" ,prank)
4280 ("mafft" ,mafft)
4281 ("fasttree" ,fasttree)
4282 ("grep" ,grep)
4283 ("sed" ,sed)
4284 ("gawk" ,gawk)
4285 ("r-minimal" ,r-minimal)
4286 ("r-ggplot2" ,r-ggplot2)
4287 ("coreutils" ,coreutils)))
4288 (home-page "http://sanger-pathogens.github.io/Roary")
4289 (synopsis "High speed stand-alone pan genome pipeline")
4290 (description
4291 "Roary is a high speed stand alone pan genome pipeline, which takes
4292 annotated assemblies in GFF3 format (produced by the Prokka program) and
4293 calculates the pan genome. Using a standard desktop PC, it can analyse
4294 datasets with thousands of samples, without compromising the quality of the
4295 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4296 single processor. Roary is not intended for metagenomics or for comparing
4297 extremely diverse sets of genomes.")
4298 (license license:gpl3)))
4299
4300 (define-public raxml
4301 (package
4302 (name "raxml")
4303 (version "8.2.10")
4304 (source
4305 (origin
4306 (method url-fetch)
4307 (uri
4308 (string-append
4309 "https://github.com/stamatak/standard-RAxML/archive/v"
4310 version ".tar.gz"))
4311 (file-name (string-append name "-" version ".tar.gz"))
4312 (sha256
4313 (base32
4314 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4315 (build-system gnu-build-system)
4316 (arguments
4317 `(#:tests? #f ; There are no tests.
4318 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4319 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4320 #:phases
4321 (modify-phases %standard-phases
4322 (delete 'configure)
4323 (replace 'install
4324 (lambda* (#:key outputs #:allow-other-keys)
4325 (let* ((out (assoc-ref outputs "out"))
4326 (bin (string-append out "/bin"))
4327 (executable "raxmlHPC-HYBRID"))
4328 (install-file executable bin)
4329 (symlink (string-append bin "/" executable) "raxml"))
4330 #t)))))
4331 (inputs
4332 `(("openmpi" ,openmpi)))
4333 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4334 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4335 (description
4336 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4337 phylogenies.")
4338 ;; The source includes x86 specific code
4339 (supported-systems '("x86_64-linux" "i686-linux"))
4340 (license license:gpl2+)))
4341
4342 (define-public rsem
4343 (package
4344 (name "rsem")
4345 (version "1.2.20")
4346 (source
4347 (origin
4348 (method url-fetch)
4349 (uri
4350 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4351 version ".tar.gz"))
4352 (sha256
4353 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4354 (patches (search-patches "rsem-makefile.patch"))
4355 (modules '((guix build utils)))
4356 (snippet
4357 '(begin
4358 ;; remove bundled copy of boost
4359 (delete-file-recursively "boost")
4360 #t))))
4361 (build-system gnu-build-system)
4362 (arguments
4363 `(#:tests? #f ;no "check" target
4364 #:phases
4365 (modify-phases %standard-phases
4366 ;; No "configure" script.
4367 ;; Do not build bundled samtools library.
4368 (replace 'configure
4369 (lambda _
4370 (substitute* "Makefile"
4371 (("^all : sam/libbam.a") "all : "))
4372 #t))
4373 (replace 'install
4374 (lambda* (#:key outputs #:allow-other-keys)
4375 (let* ((out (string-append (assoc-ref outputs "out")))
4376 (bin (string-append out "/bin/"))
4377 (perl (string-append out "/lib/perl5/site_perl")))
4378 (mkdir-p bin)
4379 (mkdir-p perl)
4380 (for-each (lambda (file)
4381 (install-file file bin))
4382 (find-files "." "rsem-.*"))
4383 (install-file "rsem_perl_utils.pm" perl))
4384 #t))
4385 (add-after
4386 'install 'wrap-program
4387 (lambda* (#:key outputs #:allow-other-keys)
4388 (let ((out (assoc-ref outputs "out")))
4389 (for-each (lambda (prog)
4390 (wrap-program (string-append out "/bin/" prog)
4391 `("PERL5LIB" ":" prefix
4392 (,(string-append out "/lib/perl5/site_perl")))))
4393 '("rsem-plot-transcript-wiggles"
4394 "rsem-calculate-expression"
4395 "rsem-generate-ngvector"
4396 "rsem-run-ebseq"
4397 "rsem-prepare-reference")))
4398 #t)))))
4399 (inputs
4400 `(("boost" ,boost)
4401 ("ncurses" ,ncurses)
4402 ("r-minimal" ,r-minimal)
4403 ("perl" ,perl)
4404 ("samtools" ,samtools-0.1)
4405 ("zlib" ,zlib)))
4406 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4407 (synopsis "Estimate gene expression levels from RNA-Seq data")
4408 (description
4409 "RSEM is a software package for estimating gene and isoform expression
4410 levels from RNA-Seq data. The RSEM package provides a user-friendly
4411 interface, supports threads for parallel computation of the EM algorithm,
4412 single-end and paired-end read data, quality scores, variable-length reads and
4413 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4414 interval estimates for expression levels. For visualization, it can generate
4415 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4416 (license license:gpl3+)))
4417
4418 (define-public rseqc
4419 (package
4420 (name "rseqc")
4421 (version "2.6.1")
4422 (source
4423 (origin
4424 (method url-fetch)
4425 (uri
4426 (string-append "mirror://sourceforge/rseqc/"
4427 "RSeQC-" version ".tar.gz"))
4428 (sha256
4429 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4430 (modules '((guix build utils)))
4431 (snippet
4432 '(begin
4433 ;; remove bundled copy of pysam
4434 (delete-file-recursively "lib/pysam")
4435 (substitute* "setup.py"
4436 ;; remove dependency on outdated "distribute" module
4437 (("^from distribute_setup import use_setuptools") "")
4438 (("^use_setuptools\\(\\)") "")
4439 ;; do not use bundled copy of pysam
4440 (("^have_pysam = False") "have_pysam = True"))))))
4441 (build-system python-build-system)
4442 (arguments `(#:python ,python-2))
4443 (inputs
4444 `(("python-cython" ,python2-cython)
4445 ("python-pysam" ,python2-pysam)
4446 ("python-numpy" ,python2-numpy)
4447 ("zlib" ,zlib)))
4448 (native-inputs
4449 `(("python-nose" ,python2-nose)))
4450 (home-page "http://rseqc.sourceforge.net/")
4451 (synopsis "RNA-seq quality control package")
4452 (description
4453 "RSeQC provides a number of modules that can comprehensively evaluate
4454 high throughput sequence data, especially RNA-seq data. Some basic modules
4455 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4456 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4457 distribution, coverage uniformity, strand specificity, etc.")
4458 (license license:gpl3+)))
4459
4460 (define-public seek
4461 ;; There are no release tarballs. According to the installation
4462 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4463 ;; stable release is identified by this changeset ID.
4464 (let ((changeset "2329130")
4465 (revision "1"))
4466 (package
4467 (name "seek")
4468 (version (string-append "0-" revision "." changeset))
4469 (source (origin
4470 (method hg-fetch)
4471 (uri (hg-reference
4472 (url "https://bitbucket.org/libsleipnir/sleipnir")
4473 (changeset changeset)))
4474 (sha256
4475 (base32
4476 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4477 (build-system gnu-build-system)
4478 (arguments
4479 `(#:modules ((srfi srfi-1)
4480 (guix build gnu-build-system)
4481 (guix build utils))
4482 #:phases
4483 (let ((dirs '("SeekMiner"
4484 "SeekEvaluator"
4485 "SeekPrep"
4486 "Distancer"
4487 "Data2DB"
4488 "PCL2Bin")))
4489 (modify-phases %standard-phases
4490 (add-before 'configure 'bootstrap
4491 (lambda _
4492 (zero? (system* "bash" "gen_auto"))))
4493 (add-after 'build 'build-additional-tools
4494 (lambda* (#:key make-flags #:allow-other-keys)
4495 (every (lambda (dir)
4496 (with-directory-excursion (string-append "tools/" dir)
4497 (zero? (apply system* "make" make-flags))))
4498 dirs)))
4499 (add-after 'install 'install-additional-tools
4500 (lambda* (#:key make-flags #:allow-other-keys)
4501 (fold (lambda (dir result)
4502 (with-directory-excursion (string-append "tools/" dir)
4503 (and result
4504 (zero? (apply system*
4505 `("make" ,@make-flags "install"))))))
4506 #t dirs)))))))
4507 (inputs
4508 `(("gsl" ,gsl)
4509 ("boost" ,boost)
4510 ("libsvm" ,libsvm)
4511 ("readline" ,readline)
4512 ("gengetopt" ,gengetopt)
4513 ("log4cpp" ,log4cpp)))
4514 (native-inputs
4515 `(("autoconf" ,autoconf)
4516 ("automake" ,automake)
4517 ("perl" ,perl)))
4518 (home-page "http://seek.princeton.edu")
4519 (synopsis "Gene co-expression search engine")
4520 (description
4521 "SEEK is a computational gene co-expression search engine. SEEK provides
4522 biologists with a way to navigate the massive human expression compendium that
4523 now contains thousands of expression datasets. SEEK returns a robust ranking
4524 of co-expressed genes in the biological area of interest defined by the user's
4525 query genes. It also prioritizes thousands of expression datasets according
4526 to the user's query of interest.")
4527 (license license:cc-by3.0))))
4528
4529 (define-public samtools
4530 (package
4531 (name "samtools")
4532 (version "1.5")
4533 (source
4534 (origin
4535 (method url-fetch)
4536 (uri
4537 (string-append "mirror://sourceforge/samtools/samtools/"
4538 version "/samtools-" version ".tar.bz2"))
4539 (sha256
4540 (base32
4541 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4542 (build-system gnu-build-system)
4543 (arguments
4544 `(#:modules ((ice-9 ftw)
4545 (ice-9 regex)
4546 (guix build gnu-build-system)
4547 (guix build utils))
4548 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4549 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4550 #:phases
4551 (modify-phases %standard-phases
4552 (add-after 'unpack 'patch-tests
4553 (lambda _
4554 (substitute* "test/test.pl"
4555 ;; The test script calls out to /bin/bash
4556 (("/bin/bash") (which "bash")))
4557 #t))
4558 (add-after 'install 'install-library
4559 (lambda* (#:key outputs #:allow-other-keys)
4560 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4561 (install-file "libbam.a" lib)
4562 #t)))
4563 (add-after 'install 'install-headers
4564 (lambda* (#:key outputs #:allow-other-keys)
4565 (let ((include (string-append (assoc-ref outputs "out")
4566 "/include/samtools/")))
4567 (for-each (lambda (file)
4568 (install-file file include))
4569 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4570 #t))))))
4571 (native-inputs `(("pkg-config" ,pkg-config)))
4572 (inputs
4573 `(("htslib" ,htslib)
4574 ("ncurses" ,ncurses)
4575 ("perl" ,perl)
4576 ("python" ,python)
4577 ("zlib" ,zlib)))
4578 (home-page "http://samtools.sourceforge.net")
4579 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4580 (description
4581 "Samtools implements various utilities for post-processing nucleotide
4582 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4583 variant calling (in conjunction with bcftools), and a simple alignment
4584 viewer.")
4585 (license license:expat)))
4586
4587 (define-public samtools-0.1
4588 ;; This is the most recent version of the 0.1 line of samtools. The input
4589 ;; and output formats differ greatly from that used and produced by samtools
4590 ;; 1.x and is still used in many bioinformatics pipelines.
4591 (package (inherit samtools)
4592 (version "0.1.19")
4593 (source
4594 (origin
4595 (method url-fetch)
4596 (uri
4597 (string-append "mirror://sourceforge/samtools/samtools/"
4598 version "/samtools-" version ".tar.bz2"))
4599 (sha256
4600 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4601 (arguments
4602 `(#:tests? #f ;no "check" target
4603 ,@(substitute-keyword-arguments (package-arguments samtools)
4604 ((#:make-flags flags)
4605 `(cons "LIBCURSES=-lncurses" ,flags))
4606 ((#:phases phases)
4607 `(modify-phases ,phases
4608 (replace 'install
4609 (lambda* (#:key outputs #:allow-other-keys)
4610 (let ((bin (string-append
4611 (assoc-ref outputs "out") "/bin")))
4612 (mkdir-p bin)
4613 (install-file "samtools" bin)
4614 #t)))
4615 (delete 'patch-tests)
4616 (delete 'configure))))))))
4617
4618 (define-public mosaik
4619 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4620 (package
4621 (name "mosaik")
4622 (version "2.2.30")
4623 (source (origin
4624 ;; There are no release tarballs nor tags.
4625 (method git-fetch)
4626 (uri (git-reference
4627 (url "https://github.com/wanpinglee/MOSAIK.git")
4628 (commit commit)))
4629 (file-name (string-append name "-" version))
4630 (sha256
4631 (base32
4632 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4633 (build-system gnu-build-system)
4634 (arguments
4635 `(#:tests? #f ; no tests
4636 #:make-flags (list "CC=gcc")
4637 #:phases
4638 (modify-phases %standard-phases
4639 (replace 'configure
4640 (lambda _ (chdir "src") #t))
4641 (replace 'install
4642 (lambda* (#:key outputs #:allow-other-keys)
4643 (let ((bin (string-append (assoc-ref outputs "out")
4644 "/bin")))
4645 (mkdir-p bin)
4646 (copy-recursively "../bin" bin)
4647 #t))))))
4648 (inputs
4649 `(("perl" ,perl)
4650 ("zlib" ,zlib)))
4651 (supported-systems '("x86_64-linux"))
4652 (home-page "https://github.com/wanpinglee/MOSAIK")
4653 (synopsis "Map nucleotide sequence reads to reference genomes")
4654 (description
4655 "MOSAIK is a program for mapping second and third-generation sequencing
4656 reads to a reference genome. MOSAIK can align reads generated by all the
4657 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4658 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4659 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4660 ;; code released into the public domain:
4661 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4662 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4663 (license (list license:gpl2+ license:public-domain)))))
4664
4665 (define-public ngs-sdk
4666 (package
4667 (name "ngs-sdk")
4668 (version "1.3.0")
4669 (source
4670 (origin
4671 (method url-fetch)
4672 (uri
4673 (string-append "https://github.com/ncbi/ngs/archive/"
4674 version ".tar.gz"))
4675 (file-name (string-append name "-" version ".tar.gz"))
4676 (sha256
4677 (base32
4678 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4679 (build-system gnu-build-system)
4680 (arguments
4681 `(#:parallel-build? #f ; not supported
4682 #:tests? #f ; no "check" target
4683 #:phases
4684 (modify-phases %standard-phases
4685 (replace 'configure
4686 (lambda* (#:key outputs #:allow-other-keys)
4687 (let ((out (assoc-ref outputs "out")))
4688 ;; Allow 'konfigure.perl' to find 'package.prl'.
4689 (setenv "PERL5LIB"
4690 (string-append ".:" (getenv "PERL5LIB")))
4691
4692 ;; The 'configure' script doesn't recognize things like
4693 ;; '--enable-fast-install'.
4694 (zero? (system* "./configure"
4695 (string-append "--build-prefix=" (getcwd) "/build")
4696 (string-append "--prefix=" out))))))
4697 (add-after 'unpack 'enter-dir
4698 (lambda _ (chdir "ngs-sdk") #t)))))
4699 (native-inputs `(("perl" ,perl)))
4700 ;; According to the test
4701 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4702 ;; in ngs-sdk/setup/konfigure.perl
4703 (supported-systems '("i686-linux" "x86_64-linux"))
4704 (home-page "https://github.com/ncbi/ngs")
4705 (synopsis "API for accessing Next Generation Sequencing data")
4706 (description
4707 "NGS is a domain-specific API for accessing reads, alignments and pileups
4708 produced from Next Generation Sequencing. The API itself is independent from
4709 any particular back-end implementation, and supports use of multiple back-ends
4710 simultaneously.")
4711 (license license:public-domain)))
4712
4713 (define-public java-ngs
4714 (package (inherit ngs-sdk)
4715 (name "java-ngs")
4716 (arguments
4717 `(,@(substitute-keyword-arguments
4718 `(#:modules ((guix build gnu-build-system)
4719 (guix build utils)
4720 (srfi srfi-1)
4721 (srfi srfi-26))
4722 ,@(package-arguments ngs-sdk))
4723 ((#:phases phases)
4724 `(modify-phases ,phases
4725 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4726 (inputs
4727 `(("jdk" ,icedtea "jdk")
4728 ("ngs-sdk" ,ngs-sdk)))
4729 (synopsis "Java bindings for NGS SDK")))
4730
4731 (define-public ncbi-vdb
4732 (package
4733 (name "ncbi-vdb")
4734 (version "2.8.2")
4735 (source
4736 (origin
4737 (method url-fetch)
4738 (uri
4739 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4740 version ".tar.gz"))
4741 (file-name (string-append name "-" version ".tar.gz"))
4742 (sha256
4743 (base32
4744 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4745 (build-system gnu-build-system)
4746 (arguments
4747 `(#:parallel-build? #f ; not supported
4748 #:tests? #f ; no "check" target
4749 #:phases
4750 (modify-phases %standard-phases
4751 (add-before 'configure 'set-perl-search-path
4752 (lambda _
4753 ;; Work around "dotless @INC" build failure.
4754 (setenv "PERL5LIB"
4755 (string-append (getcwd) "/setup:"
4756 (getenv "PERL5LIB")))
4757 #t))
4758 (replace 'configure
4759 (lambda* (#:key inputs outputs #:allow-other-keys)
4760 (let ((out (assoc-ref outputs "out")))
4761 ;; Override include path for libmagic
4762 (substitute* "setup/package.prl"
4763 (("name => 'magic', Include => '/usr/include'")
4764 (string-append "name=> 'magic', Include => '"
4765 (assoc-ref inputs "libmagic")
4766 "/include" "'")))
4767
4768 ;; Install kdf5 library (needed by sra-tools)
4769 (substitute* "build/Makefile.install"
4770 (("LIBRARIES_TO_INSTALL =")
4771 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4772
4773 (substitute* "build/Makefile.env"
4774 (("CFLAGS =" prefix)
4775 (string-append prefix "-msse2 ")))
4776
4777 ;; Override search path for ngs-java
4778 (substitute* "setup/package.prl"
4779 (("/usr/local/ngs/ngs-java")
4780 (assoc-ref inputs "java-ngs")))
4781
4782 ;; The 'configure' script doesn't recognize things like
4783 ;; '--enable-fast-install'.
4784 (zero? (system*
4785 "./configure"
4786 (string-append "--build-prefix=" (getcwd) "/build")
4787 (string-append "--prefix=" (assoc-ref outputs "out"))
4788 (string-append "--debug")
4789 (string-append "--with-xml2-prefix="
4790 (assoc-ref inputs "libxml2"))
4791 (string-append "--with-ngs-sdk-prefix="
4792 (assoc-ref inputs "ngs-sdk"))
4793 (string-append "--with-hdf5-prefix="
4794 (assoc-ref inputs "hdf5")))))))
4795 (add-after 'install 'install-interfaces
4796 (lambda* (#:key outputs #:allow-other-keys)
4797 ;; Install interface libraries. On i686 the interface libraries
4798 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4799 ;; architecture name ("i386") instead of the target system prefix
4800 ;; ("i686").
4801 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4802 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4803 ,(system->linux-architecture
4804 (or (%current-target-system)
4805 (%current-system)))
4806 "/rel/ilib")
4807 (string-append (assoc-ref outputs "out")
4808 "/ilib"))
4809 ;; Install interface headers
4810 (copy-recursively "interfaces"
4811 (string-append (assoc-ref outputs "out")
4812 "/include"))
4813 #t))
4814 ;; These files are needed by sra-tools.
4815 (add-after 'install 'install-configuration-files
4816 (lambda* (#:key outputs #:allow-other-keys)
4817 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4818 (mkdir target)
4819 (install-file "libs/kfg/default.kfg" target)
4820 (install-file "libs/kfg/certs.kfg" target))
4821 #t)))))
4822 (inputs
4823 `(("libxml2" ,libxml2)
4824 ("ngs-sdk" ,ngs-sdk)
4825 ("java-ngs" ,java-ngs)
4826 ("libmagic" ,file)
4827 ("hdf5" ,hdf5)))
4828 (native-inputs `(("perl" ,perl)))
4829 ;; NCBI-VDB requires SSE capability.
4830 (supported-systems '("i686-linux" "x86_64-linux"))
4831 (home-page "https://github.com/ncbi/ncbi-vdb")
4832 (synopsis "Database engine for genetic information")
4833 (description
4834 "The NCBI-VDB library implements a highly compressed columnar data
4835 warehousing engine that is most often used to store genetic information.
4836 Databases are stored in a portable image within the file system, and can be
4837 accessed/downloaded on demand across HTTP.")
4838 (license license:public-domain)))
4839
4840 (define-public plink
4841 (package
4842 (name "plink")
4843 (version "1.07")
4844 (source
4845 (origin
4846 (method url-fetch)
4847 (uri (string-append
4848 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4849 version "-src.zip"))
4850 (sha256
4851 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4852 (patches (search-patches "plink-1.07-unclobber-i.patch"
4853 "plink-endian-detection.patch"))))
4854 (build-system gnu-build-system)
4855 (arguments
4856 '(#:tests? #f ;no "check" target
4857 #:make-flags (list (string-append "LIB_LAPACK="
4858 (assoc-ref %build-inputs "lapack")
4859 "/lib/liblapack.so")
4860 "WITH_LAPACK=1"
4861 "FORCE_DYNAMIC=1"
4862 ;; disable phoning home
4863 "WITH_WEBCHECK=")
4864 #:phases
4865 (modify-phases %standard-phases
4866 ;; no "configure" script
4867 (delete 'configure)
4868 (replace 'install
4869 (lambda* (#:key outputs #:allow-other-keys)
4870 (let ((bin (string-append (assoc-ref outputs "out")
4871 "/bin/")))
4872 (install-file "plink" bin)
4873 #t))))))
4874 (inputs
4875 `(("zlib" ,zlib)
4876 ("lapack" ,lapack)))
4877 (native-inputs
4878 `(("unzip" ,unzip)))
4879 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4880 (synopsis "Whole genome association analysis toolset")
4881 (description
4882 "PLINK is a whole genome association analysis toolset, designed to
4883 perform a range of basic, large-scale analyses in a computationally efficient
4884 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4885 so there is no support for steps prior to this (e.g. study design and
4886 planning, generating genotype or CNV calls from raw data). Through
4887 integration with gPLINK and Haploview, there is some support for the
4888 subsequent visualization, annotation and storage of results.")
4889 ;; Code is released under GPLv2, except for fisher.h, which is under
4890 ;; LGPLv2.1+
4891 (license (list license:gpl2 license:lgpl2.1+))))
4892
4893 (define-public smithlab-cpp
4894 (let ((revision "1")
4895 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4896 (package
4897 (name "smithlab-cpp")
4898 (version (string-append "0." revision "." (string-take commit 7)))
4899 (source (origin
4900 (method git-fetch)
4901 (uri (git-reference
4902 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4903 (commit commit)))
4904 (file-name (string-append name "-" version "-checkout"))
4905 (sha256
4906 (base32
4907 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4908 (build-system gnu-build-system)
4909 (arguments
4910 `(#:modules ((guix build gnu-build-system)
4911 (guix build utils)
4912 (srfi srfi-26))
4913 #:tests? #f ;no "check" target
4914 #:phases
4915 (modify-phases %standard-phases
4916 (add-after 'unpack 'use-samtools-headers
4917 (lambda _
4918 (substitute* '("SAM.cpp"
4919 "SAM.hpp")
4920 (("sam.h") "samtools/sam.h"))
4921 #t))
4922 (replace 'install
4923 (lambda* (#:key outputs #:allow-other-keys)
4924 (let* ((out (assoc-ref outputs "out"))
4925 (lib (string-append out "/lib"))
4926 (include (string-append out "/include/smithlab-cpp")))
4927 (mkdir-p lib)
4928 (mkdir-p include)
4929 (for-each (cut install-file <> lib)
4930 (find-files "." "\\.o$"))
4931 (for-each (cut install-file <> include)
4932 (find-files "." "\\.hpp$")))
4933 #t))
4934 (delete 'configure))))
4935 (inputs
4936 `(("samtools" ,samtools-0.1)
4937 ("zlib" ,zlib)))
4938 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4939 (synopsis "C++ helper library for functions used in Smith lab projects")
4940 (description
4941 "Smithlab CPP is a C++ library that includes functions used in many of
4942 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4943 structures, classes for genomic regions, mapped sequencing reads, etc.")
4944 (license license:gpl3+))))
4945
4946 (define-public preseq
4947 (package
4948 (name "preseq")
4949 (version "2.0")
4950 (source (origin
4951 (method url-fetch)
4952 (uri (string-append "https://github.com/smithlabcode/"
4953 "preseq/archive/v" version ".tar.gz"))
4954 (file-name (string-append name "-" version ".tar.gz"))
4955 (sha256
4956 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4957 (modules '((guix build utils)))
4958 (snippet
4959 ;; Remove bundled samtools.
4960 '(delete-file-recursively "samtools"))))
4961 (build-system gnu-build-system)
4962 (arguments
4963 `(#:tests? #f ;no "check" target
4964 #:phases
4965 (modify-phases %standard-phases
4966 (delete 'configure))
4967 #:make-flags
4968 (list (string-append "PREFIX="
4969 (assoc-ref %outputs "out"))
4970 (string-append "LIBBAM="
4971 (assoc-ref %build-inputs "samtools")
4972 "/lib/libbam.a")
4973 (string-append "SMITHLAB_CPP="
4974 (assoc-ref %build-inputs "smithlab-cpp")
4975 "/lib")
4976 "PROGS=preseq"
4977 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4978 (inputs
4979 `(("gsl" ,gsl)
4980 ("samtools" ,samtools-0.1)
4981 ("smithlab-cpp" ,smithlab-cpp)
4982 ("zlib" ,zlib)))
4983 (home-page "http://smithlabresearch.org/software/preseq/")
4984 (synopsis "Program for analyzing library complexity")
4985 (description
4986 "The preseq package is aimed at predicting and estimating the complexity
4987 of a genomic sequencing library, equivalent to predicting and estimating the
4988 number of redundant reads from a given sequencing depth and how many will be
4989 expected from additional sequencing using an initial sequencing experiment.
4990 The estimates can then be used to examine the utility of further sequencing,
4991 optimize the sequencing depth, or to screen multiple libraries to avoid low
4992 complexity samples.")
4993 (license license:gpl3+)))
4994
4995 (define-public python-screed
4996 (package
4997 (name "python-screed")
4998 (version "0.9")
4999 (source
5000 (origin
5001 (method url-fetch)
5002 (uri (pypi-uri "screed" version))
5003 (sha256
5004 (base32
5005 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
5006 (build-system python-build-system)
5007 (arguments
5008 `(#:phases
5009 (modify-phases %standard-phases
5010 (replace 'check
5011 (lambda _
5012 (setenv "PYTHONPATH"
5013 (string-append (getenv "PYTHONPATH") ":."))
5014 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
5015 (native-inputs
5016 `(("python-nose" ,python-nose)))
5017 (inputs
5018 `(("python-bz2file" ,python-bz2file)))
5019 (home-page "https://github.com/dib-lab/screed/")
5020 (synopsis "Short read sequence database utilities")
5021 (description "Screed parses FASTA and FASTQ files and generates databases.
5022 Values such as sequence name, sequence description, sequence quality and the
5023 sequence itself can be retrieved from these databases.")
5024 (license license:bsd-3)))
5025
5026 (define-public python2-screed
5027 (package-with-python2 python-screed))
5028
5029 (define-public sra-tools
5030 (package
5031 (name "sra-tools")
5032 (version "2.8.2-1")
5033 (source
5034 (origin
5035 (method url-fetch)
5036 (uri
5037 (string-append "https://github.com/ncbi/sra-tools/archive/"
5038 version ".tar.gz"))
5039 (file-name (string-append name "-" version ".tar.gz"))
5040 (sha256
5041 (base32
5042 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5043 (build-system gnu-build-system)
5044 (arguments
5045 `(#:parallel-build? #f ; not supported
5046 #:tests? #f ; no "check" target
5047 #:make-flags
5048 (list (string-append "DEFAULT_CRT="
5049 (assoc-ref %build-inputs "ncbi-vdb")
5050 "/kfg/certs.kfg")
5051 (string-append "DEFAULT_KFG="
5052 (assoc-ref %build-inputs "ncbi-vdb")
5053 "/kfg/default.kfg")
5054 (string-append "VDB_LIBDIR="
5055 (assoc-ref %build-inputs "ncbi-vdb")
5056 ,(if (string-prefix? "x86_64"
5057 (or (%current-target-system)
5058 (%current-system)))
5059 "/lib64"
5060 "/lib32")))
5061 #:phases
5062 (modify-phases %standard-phases
5063 (add-before 'configure 'set-perl-search-path
5064 (lambda _
5065 ;; Work around "dotless @INC" build failure.
5066 (setenv "PERL5LIB"
5067 (string-append (getcwd) "/setup:"
5068 (getenv "PERL5LIB")))
5069 #t))
5070 (replace 'configure
5071 (lambda* (#:key inputs outputs #:allow-other-keys)
5072 ;; The build system expects a directory containing the sources and
5073 ;; raw build output of ncbi-vdb, including files that are not
5074 ;; installed. Since we are building against an installed version of
5075 ;; ncbi-vdb, the following modifications are needed.
5076 (substitute* "setup/konfigure.perl"
5077 ;; Make the configure script look for the "ilib" directory of
5078 ;; "ncbi-vdb" without first checking for the existence of a
5079 ;; matching library in its "lib" directory.
5080 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5081 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5082 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5083 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5084 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5085
5086 ;; Dynamic linking
5087 (substitute* "tools/copycat/Makefile"
5088 (("smagic-static") "lmagic"))
5089
5090 ;; The 'configure' script doesn't recognize things like
5091 ;; '--enable-fast-install'.
5092 (zero? (system*
5093 "./configure"
5094 (string-append "--build-prefix=" (getcwd) "/build")
5095 (string-append "--prefix=" (assoc-ref outputs "out"))
5096 (string-append "--debug")
5097 (string-append "--with-fuse-prefix="
5098 (assoc-ref inputs "fuse"))
5099 (string-append "--with-magic-prefix="
5100 (assoc-ref inputs "libmagic"))
5101 ;; TODO: building with libxml2 fails with linker errors
5102 ;; (string-append "--with-xml2-prefix="
5103 ;; (assoc-ref inputs "libxml2"))
5104 (string-append "--with-ncbi-vdb-sources="
5105 (assoc-ref inputs "ncbi-vdb"))
5106 (string-append "--with-ncbi-vdb-build="
5107 (assoc-ref inputs "ncbi-vdb"))
5108 (string-append "--with-ngs-sdk-prefix="
5109 (assoc-ref inputs "ngs-sdk"))
5110 (string-append "--with-hdf5-prefix="
5111 (assoc-ref inputs "hdf5"))))))
5112 ;; This version of sra-tools fails to build with glibc because of a
5113 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5114 ;; contains a definition of "canonicalize", so we rename it.
5115 ;;
5116 ;; See upstream bug report:
5117 ;; https://github.com/ncbi/sra-tools/issues/67
5118 (add-after 'unpack 'patch-away-glibc-conflict
5119 (lambda _
5120 (substitute* "tools/bam-loader/bam.c"
5121 (("canonicalize\\(" line)
5122 (string-append "sra_tools_" line)))
5123 #t)))))
5124 (native-inputs `(("perl" ,perl)))
5125 (inputs
5126 `(("ngs-sdk" ,ngs-sdk)
5127 ("ncbi-vdb" ,ncbi-vdb)
5128 ("libmagic" ,file)
5129 ("fuse" ,fuse)
5130 ("hdf5" ,hdf5)
5131 ("zlib" ,zlib)))
5132 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5133 (synopsis "Tools and libraries for reading and writing sequencing data")
5134 (description
5135 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5136 reading of sequencing files from the Sequence Read Archive (SRA) database and
5137 writing files into the .sra format.")
5138 (license license:public-domain)))
5139
5140 (define-public seqan
5141 (package
5142 (name "seqan")
5143 (version "1.4.2")
5144 (source (origin
5145 (method url-fetch)
5146 (uri (string-append "http://packages.seqan.de/seqan-library/"
5147 "seqan-library-" version ".tar.bz2"))
5148 (sha256
5149 (base32
5150 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5151 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5152 ;; makes sense to split the outputs.
5153 (outputs '("out" "doc"))
5154 (build-system trivial-build-system)
5155 (arguments
5156 `(#:modules ((guix build utils))
5157 #:builder
5158 (begin
5159 (use-modules (guix build utils))
5160 (let ((tar (assoc-ref %build-inputs "tar"))
5161 (bzip (assoc-ref %build-inputs "bzip2"))
5162 (out (assoc-ref %outputs "out"))
5163 (doc (assoc-ref %outputs "doc")))
5164 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5165 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5166 (chdir (string-append "seqan-library-" ,version))
5167 (copy-recursively "include" (string-append out "/include"))
5168 (copy-recursively "share" (string-append doc "/share"))))))
5169 (native-inputs
5170 `(("source" ,source)
5171 ("tar" ,tar)
5172 ("bzip2" ,bzip2)))
5173 (home-page "http://www.seqan.de")
5174 (synopsis "Library for nucleotide sequence analysis")
5175 (description
5176 "SeqAn is a C++ library of efficient algorithms and data structures for
5177 the analysis of sequences with the focus on biological data. It contains
5178 algorithms and data structures for string representation and their
5179 manipulation, online and indexed string search, efficient I/O of
5180 bioinformatics file formats, sequence alignment, and more.")
5181 (license license:bsd-3)))
5182
5183 (define-public seqmagick
5184 (package
5185 (name "seqmagick")
5186 (version "0.6.1")
5187 (source
5188 (origin
5189 (method url-fetch)
5190 (uri (string-append
5191 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5192 version ".tar.gz"))
5193 (sha256
5194 (base32
5195 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5196 (build-system python-build-system)
5197 (arguments
5198 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5199 `(#:python ,python-2
5200 #:phases
5201 (modify-phases %standard-phases
5202 ;; Current test in setup.py does not work as of 0.6.1,
5203 ;; so use nose to run tests instead for now. See
5204 ;; https://github.com/fhcrc/seqmagick/issues/55
5205 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5206 (inputs
5207 ;; biopython-1.66 is required due to
5208 ;; https://github.com/fhcrc/seqmagick/issues/59
5209 ;; When that issue is resolved the 'python2-biopython-1.66' package
5210 ;; should be removed.
5211 `(("python-biopython" ,python2-biopython-1.66)))
5212 (native-inputs
5213 `(("python-nose" ,python2-nose)))
5214 (home-page "https://github.com/fhcrc/seqmagick")
5215 (synopsis "Tools for converting and modifying sequence files")
5216 (description
5217 "Bioinformaticians often have to convert sequence files between formats
5218 and do little manipulations on them, and it's not worth writing scripts for
5219 that. Seqmagick is a utility to expose the file format conversion in
5220 BioPython in a convenient way. Instead of having a big mess of scripts, there
5221 is one that takes arguments.")
5222 (license license:gpl3)))
5223
5224 (define-public seqtk
5225 (package
5226 (name "seqtk")
5227 (version "1.2")
5228 (source (origin
5229 (method url-fetch)
5230 (uri (string-append
5231 "https://github.com/lh3/seqtk/archive/v"
5232 version ".tar.gz"))
5233 (file-name (string-append name "-" version ".tar.gz"))
5234 (sha256
5235 (base32
5236 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5237 (modules '((guix build utils)))
5238 (snippet
5239 '(begin
5240 ;; Remove extraneous header files, as is done in the seqtk
5241 ;; master branch.
5242 (for-each (lambda (file) (delete-file file))
5243 (list "ksort.h" "kstring.h" "kvec.h"))
5244 #t))))
5245 (build-system gnu-build-system)
5246 (arguments
5247 `(#:phases
5248 (modify-phases %standard-phases
5249 (delete 'configure)
5250 (replace 'check
5251 ;; There are no tests, so we just run a sanity check.
5252 (lambda _ (zero? (system* "./seqtk" "seq"))))
5253 (replace 'install
5254 (lambda* (#:key outputs #:allow-other-keys)
5255 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5256 (install-file "seqtk" bin)))))))
5257 (inputs
5258 `(("zlib" ,zlib)))
5259 (home-page "https://github.com/lh3/seqtk")
5260 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5261 (description
5262 "Seqtk is a fast and lightweight tool for processing sequences in the
5263 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5264 optionally compressed by gzip.")
5265 (license license:expat)))
5266
5267 (define-public snap-aligner
5268 (package
5269 (name "snap-aligner")
5270 (version "1.0beta.18")
5271 (source (origin
5272 (method url-fetch)
5273 (uri (string-append
5274 "https://github.com/amplab/snap/archive/v"
5275 version ".tar.gz"))
5276 (file-name (string-append name "-" version ".tar.gz"))
5277 (sha256
5278 (base32
5279 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5280 (build-system gnu-build-system)
5281 (arguments
5282 '(#:phases
5283 (modify-phases %standard-phases
5284 (delete 'configure)
5285 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5286 (replace 'install
5287 (lambda* (#:key outputs #:allow-other-keys)
5288 (let* ((out (assoc-ref outputs "out"))
5289 (bin (string-append out "/bin")))
5290 (install-file "snap-aligner" bin)
5291 (install-file "SNAPCommand" bin)
5292 #t))))))
5293 (native-inputs
5294 `(("zlib" ,zlib)))
5295 (home-page "http://snap.cs.berkeley.edu/")
5296 (synopsis "Short read DNA sequence aligner")
5297 (description
5298 "SNAP is a fast and accurate aligner for short DNA reads. It is
5299 optimized for modern read lengths of 100 bases or higher, and takes advantage
5300 of these reads to align data quickly through a hash-based indexing scheme.")
5301 ;; 32-bit systems are not supported by the unpatched code.
5302 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5303 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5304 ;; systems without a lot of memory cannot make good use of this program.
5305 (supported-systems '("x86_64-linux"))
5306 (license license:asl2.0)))
5307
5308 (define-public sortmerna
5309 (package
5310 (name "sortmerna")
5311 (version "2.1b")
5312 (source
5313 (origin
5314 (method url-fetch)
5315 (uri (string-append
5316 "https://github.com/biocore/sortmerna/archive/"
5317 version ".tar.gz"))
5318 (file-name (string-append name "-" version ".tar.gz"))
5319 (sha256
5320 (base32
5321 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5322 (build-system gnu-build-system)
5323 (outputs '("out" ;for binaries
5324 "db")) ;for sequence databases
5325 (arguments
5326 `(#:phases
5327 (modify-phases %standard-phases
5328 (replace 'install
5329 (lambda* (#:key outputs #:allow-other-keys)
5330 (let* ((out (assoc-ref outputs "out"))
5331 (bin (string-append out "/bin"))
5332 (db (assoc-ref outputs "db"))
5333 (share
5334 (string-append db "/share/sortmerna/rRNA_databases")))
5335 (install-file "sortmerna" bin)
5336 (install-file "indexdb_rna" bin)
5337 (for-each (lambda (file)
5338 (install-file file share))
5339 (find-files "rRNA_databases" ".*fasta"))
5340 #t))))))
5341 (inputs
5342 `(("zlib" ,zlib)))
5343 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5344 (synopsis "Biological sequence analysis tool for NGS reads")
5345 (description
5346 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5347 and operational taxonomic unit (OTU) picking of next generation
5348 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5349 allows for fast and sensitive analyses of nucleotide sequences. The main
5350 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5351 ;; The source includes x86 specific code
5352 (supported-systems '("x86_64-linux" "i686-linux"))
5353 (license license:lgpl3)))
5354
5355 (define-public star
5356 (package
5357 (name "star")
5358 (version "2.5.3a")
5359 (source (origin
5360 (method url-fetch)
5361 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5362 version ".tar.gz"))
5363 (file-name (string-append name "-" version ".tar.gz"))
5364 (sha256
5365 (base32
5366 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5367 (modules '((guix build utils)))
5368 (snippet
5369 '(begin
5370 (substitute* "source/Makefile"
5371 (("/bin/rm") "rm"))
5372 ;; Remove pre-built binaries and bundled htslib sources.
5373 (delete-file-recursively "bin/MacOSX_x86_64")
5374 (delete-file-recursively "bin/Linux_x86_64")
5375 (delete-file-recursively "bin/Linux_x86_64_static")
5376 (delete-file-recursively "source/htslib")
5377 #t))))
5378 (build-system gnu-build-system)
5379 (arguments
5380 '(#:tests? #f ;no check target
5381 #:make-flags '("STAR")
5382 #:phases
5383 (modify-phases %standard-phases
5384 (add-after 'unpack 'enter-source-dir
5385 (lambda _ (chdir "source") #t))
5386 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5387 (lambda _
5388 (substitute* "Makefile"
5389 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5390 _ prefix) prefix))
5391 (substitute* '("BAMfunctions.cpp"
5392 "signalFromBAM.h"
5393 "bam_cat.h"
5394 "bam_cat.c"
5395 "STAR.cpp"
5396 "bamRemoveDuplicates.cpp")
5397 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5398 (string-append "#include <" header ">")))
5399 (substitute* "IncludeDefine.h"
5400 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5401 (string-append "<" header ">")))
5402 #t))
5403 (replace 'install
5404 (lambda* (#:key outputs #:allow-other-keys)
5405 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5406 (install-file "STAR" bin))
5407 #t))
5408 (delete 'configure))))
5409 (native-inputs
5410 `(("vim" ,vim))) ; for xxd
5411 (inputs
5412 `(("htslib" ,htslib)
5413 ("zlib" ,zlib)))
5414 (home-page "https://github.com/alexdobin/STAR")
5415 (synopsis "Universal RNA-seq aligner")
5416 (description
5417 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5418 based on a previously undescribed RNA-seq alignment algorithm that uses
5419 sequential maximum mappable seed search in uncompressed suffix arrays followed
5420 by seed clustering and stitching procedure. In addition to unbiased de novo
5421 detection of canonical junctions, STAR can discover non-canonical splices and
5422 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5423 sequences.")
5424 ;; Only 64-bit systems are supported according to the README.
5425 (supported-systems '("x86_64-linux" "mips64el-linux"))
5426 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5427 (license license:gpl3+)))
5428
5429 (define-public subread
5430 (package
5431 (name "subread")
5432 (version "1.5.1")
5433 (source (origin
5434 (method url-fetch)
5435 (uri (string-append "mirror://sourceforge/subread/subread-"
5436 version "/subread-" version "-source.tar.gz"))
5437 (sha256
5438 (base32
5439 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5440 (build-system gnu-build-system)
5441 (arguments
5442 `(#:tests? #f ;no "check" target
5443 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5444 ;; optimizations by default, so we override these flags such that x86_64
5445 ;; flags are only added when the build target is an x86_64 system.
5446 #:make-flags
5447 (list (let ((system ,(or (%current-target-system)
5448 (%current-system)))
5449 (flags '("-ggdb" "-fomit-frame-pointer"
5450 "-ffast-math" "-funroll-loops"
5451 "-fmessage-length=0"
5452 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5453 "-DMAKE_STANDALONE"
5454 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5455 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5456 (if (string-prefix? "x86_64" system)
5457 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5458 (string-append "CCFLAGS=" (string-join flags))))
5459 "-f" "Makefile.Linux"
5460 "CC=gcc ${CCFLAGS}")
5461 #:phases
5462 (modify-phases %standard-phases
5463 (add-after 'unpack 'enter-dir
5464 (lambda _ (chdir "src") #t))
5465 (replace 'install
5466 (lambda* (#:key outputs #:allow-other-keys)
5467 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5468 (mkdir-p bin)
5469 (copy-recursively "../bin" bin))))
5470 ;; no "configure" script
5471 (delete 'configure))))
5472 (inputs `(("zlib" ,zlib)))
5473 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5474 (synopsis "Tool kit for processing next-gen sequencing data")
5475 (description
5476 "The subread package contains the following tools: subread aligner, a
5477 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5478 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5479 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5480 against local background noises.")
5481 (license license:gpl3+)))
5482
5483 (define-public stringtie
5484 (package
5485 (name "stringtie")
5486 (version "1.2.1")
5487 (source (origin
5488 (method url-fetch)
5489 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5490 "stringtie-" version ".tar.gz"))
5491 (sha256
5492 (base32
5493 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5494 (modules '((guix build utils)))
5495 (snippet
5496 '(begin
5497 (delete-file-recursively "samtools-0.1.18")
5498 #t))))
5499 (build-system gnu-build-system)
5500 (arguments
5501 `(#:tests? #f ;no test suite
5502 #:phases
5503 (modify-phases %standard-phases
5504 ;; no configure script
5505 (delete 'configure)
5506 (add-before 'build 'use-system-samtools
5507 (lambda _
5508 (substitute* "Makefile"
5509 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5510 "stringtie: "))
5511 (substitute* '("gclib/GBam.h"
5512 "gclib/GBam.cpp")
5513 (("#include \"(bam|sam|kstring).h\"" _ header)
5514 (string-append "#include <samtools/" header ".h>")))
5515 #t))
5516 (add-after 'unpack 'remove-duplicate-typedef
5517 (lambda _
5518 ;; This typedef conflicts with the typedef in
5519 ;; glibc-2.25/include/bits/types.h
5520 (substitute* "gclib/GThreads.h"
5521 (("typedef long long __intmax_t;") ""))
5522 #t))
5523 (replace 'install
5524 (lambda* (#:key outputs #:allow-other-keys)
5525 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5526 (install-file "stringtie" bin)
5527 #t))))))
5528 (inputs
5529 `(("samtools" ,samtools-0.1)
5530 ("zlib" ,zlib)))
5531 (home-page "http://ccb.jhu.edu/software/stringtie/")
5532 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5533 (description
5534 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5535 alignments into potential transcripts. It uses a novel network flow algorithm
5536 as well as an optional de novo assembly step to assemble and quantitate
5537 full-length transcripts representing multiple splice variants for each gene
5538 locus. Its input can include not only the alignments of raw reads used by
5539 other transcript assemblers, but also alignments of longer sequences that have
5540 been assembled from those reads. To identify differentially expressed genes
5541 between experiments, StringTie's output can be processed either by the
5542 Cuffdiff or Ballgown programs.")
5543 (license license:artistic2.0)))
5544
5545 (define-public taxtastic
5546 (package
5547 (name "taxtastic")
5548 (version "0.6.4")
5549 (source (origin
5550 (method url-fetch)
5551 (uri (pypi-uri "taxtastic" version))
5552 (sha256
5553 (base32
5554 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5555 (build-system python-build-system)
5556 (arguments
5557 `(#:python ,python-2
5558 #:phases
5559 (modify-phases %standard-phases
5560 (replace 'check
5561 (lambda _
5562 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5563 (propagated-inputs
5564 `(("python-sqlalchemy" ,python2-sqlalchemy)
5565 ("python-decorator" ,python2-decorator)
5566 ("python-biopython" ,python2-biopython)
5567 ("python-pandas" ,python2-pandas)))
5568 (home-page "https://github.com/fhcrc/taxtastic")
5569 (synopsis "Tools for taxonomic naming and annotation")
5570 (description
5571 "Taxtastic is software written in python used to build and maintain
5572 reference packages i.e. collections of reference trees, reference alignments,
5573 profiles, and associated taxonomic information.")
5574 (license license:gpl3+)))
5575
5576 (define-public vcftools
5577 (package
5578 (name "vcftools")
5579 (version "0.1.15")
5580 (source (origin
5581 (method url-fetch)
5582 (uri (string-append
5583 "https://github.com/vcftools/vcftools/releases/download/v"
5584 version "/vcftools-" version ".tar.gz"))
5585 (sha256
5586 (base32
5587 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5588 (build-system gnu-build-system)
5589 (arguments
5590 `(#:tests? #f ; no "check" target
5591 #:make-flags (list
5592 "CFLAGS=-O2" ; override "-m64" flag
5593 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5594 (string-append "MANDIR=" (assoc-ref %outputs "out")
5595 "/share/man/man1"))))
5596 (native-inputs
5597 `(("pkg-config" ,pkg-config)))
5598 (inputs
5599 `(("perl" ,perl)
5600 ("zlib" ,zlib)))
5601 (home-page "https://vcftools.github.io/")
5602 (synopsis "Tools for working with VCF files")
5603 (description
5604 "VCFtools is a program package designed for working with VCF files, such
5605 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5606 provide easily accessible methods for working with complex genetic variation
5607 data in the form of VCF files.")
5608 ;; The license is declared as LGPLv3 in the README and
5609 ;; at https://vcftools.github.io/license.html
5610 (license license:lgpl3)))
5611
5612 (define-public infernal
5613 (package
5614 (name "infernal")
5615 (version "1.1.2")
5616 (source (origin
5617 (method url-fetch)
5618 (uri (string-append "http://eddylab.org/software/infernal/"
5619 "infernal-" version ".tar.gz"))
5620 (sha256
5621 (base32
5622 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5623 (build-system gnu-build-system)
5624 (native-inputs
5625 `(("perl" ,perl))) ; for tests
5626 (home-page "http://eddylab.org/infernal/")
5627 (synopsis "Inference of RNA alignments")
5628 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5629 searching DNA sequence databases for RNA structure and sequence similarities.
5630 It is an implementation of a special case of profile stochastic context-free
5631 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5632 profile, but it scores a combination of sequence consensus and RNA secondary
5633 structure consensus, so in many cases, it is more capable of identifying RNA
5634 homologs that conserve their secondary structure more than their primary
5635 sequence.")
5636 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5637 (supported-systems '("i686-linux" "x86_64-linux"))
5638 (license license:bsd-3)))
5639
5640 (define-public r-centipede
5641 (package
5642 (name "r-centipede")
5643 (version "1.2")
5644 (source (origin
5645 (method url-fetch)
5646 (uri (string-append "http://download.r-forge.r-project.org/"
5647 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5648 (sha256
5649 (base32
5650 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5651 (build-system r-build-system)
5652 (home-page "http://centipede.uchicago.edu/")
5653 (synopsis "Predict transcription factor binding sites")
5654 (description
5655 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5656 of the genome that are bound by particular transcription factors. It starts
5657 by identifying a set of candidate binding sites, and then aims to classify the
5658 sites according to whether each site is bound or not bound by a transcription
5659 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5660 between two different types of motif instances using as much relevant
5661 information as possible.")
5662 (license (list license:gpl2+ license:gpl3+))))
5663
5664 (define-public r-vegan
5665 (package
5666 (name "r-vegan")
5667 (version "2.4-4")
5668 (source
5669 (origin
5670 (method url-fetch)
5671 (uri (cran-uri "vegan" version))
5672 (sha256
5673 (base32
5674 "1n57dzv2aid6iqd9fkqik401sidqanhzsawyak94qbiyh6dbd1x9"))))
5675 (build-system r-build-system)
5676 (native-inputs
5677 `(("gfortran" ,gfortran)))
5678 (propagated-inputs
5679 `(("r-cluster" ,r-cluster)
5680 ("r-lattice" ,r-lattice)
5681 ("r-mass" ,r-mass)
5682 ("r-mgcv" ,r-mgcv)
5683 ("r-permute" ,r-permute)))
5684 (home-page "https://cran.r-project.org/web/packages/vegan")
5685 (synopsis "Functions for community ecology")
5686 (description
5687 "The vegan package provides tools for descriptive community ecology. It
5688 has most basic functions of diversity analysis, community ordination and
5689 dissimilarity analysis. Most of its multivariate tools can be used for other
5690 data types as well.")
5691 (license license:gpl2+)))
5692
5693 (define-public r-annotate
5694 (package
5695 (name "r-annotate")
5696 (version "1.54.0")
5697 (source
5698 (origin
5699 (method url-fetch)
5700 (uri (bioconductor-uri "annotate" version))
5701 (sha256
5702 (base32
5703 "03hmbvp3i6lvd307fqdg7akxi2qp322rlky3bzw0zccgm0i0221g"))))
5704 (build-system r-build-system)
5705 (propagated-inputs
5706 `(("r-annotationdbi" ,r-annotationdbi)
5707 ("r-biobase" ,r-biobase)
5708 ("r-biocgenerics" ,r-biocgenerics)
5709 ("r-dbi" ,r-dbi)
5710 ("r-rcurl" ,r-rcurl)
5711 ("r-xml" ,r-xml)
5712 ("r-xtable" ,r-xtable)))
5713 (home-page
5714 "http://bioconductor.org/packages/annotate")
5715 (synopsis "Annotation for microarrays")
5716 (description "This package provides R environments for the annotation of
5717 microarrays.")
5718 (license license:artistic2.0)))
5719
5720 (define-public r-geneplotter
5721 (package
5722 (name "r-geneplotter")
5723 (version "1.54.0")
5724 (source
5725 (origin
5726 (method url-fetch)
5727 (uri (bioconductor-uri "geneplotter" version))
5728 (sha256
5729 (base32
5730 "0a0ajns21db5rrjl16bq6wawggsnxr00fg184pc38nmfghv4z4b6"))))
5731 (build-system r-build-system)
5732 (propagated-inputs
5733 `(("r-annotate" ,r-annotate)
5734 ("r-annotationdbi" ,r-annotationdbi)
5735 ("r-biobase" ,r-biobase)
5736 ("r-biocgenerics" ,r-biocgenerics)
5737 ("r-lattice" ,r-lattice)
5738 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5739 (home-page "http://bioconductor.org/packages/geneplotter")
5740 (synopsis "Graphics functions for genomic data")
5741 (description
5742 "This package provides functions for plotting genomic data.")
5743 (license license:artistic2.0)))
5744
5745 (define-public r-genefilter
5746 (package
5747 (name "r-genefilter")
5748 (version "1.58.0")
5749 (source
5750 (origin
5751 (method url-fetch)
5752 (uri (bioconductor-uri "genefilter" version))
5753 (sha256
5754 (base32
5755 "0sf2hdi9nv6r83vn1y65m4jiba8pffddpj46d6yjn5rlsixplmqg"))))
5756 (build-system r-build-system)
5757 (native-inputs
5758 `(("gfortran" ,gfortran)))
5759 (propagated-inputs
5760 `(("r-annotate" ,r-annotate)
5761 ("r-annotationdbi" ,r-annotationdbi)
5762 ("r-biobase" ,r-biobase)
5763 ("r-s4vectors" ,r-s4vectors)
5764 ("r-survival" ,r-survival)))
5765 (home-page "http://bioconductor.org/packages/genefilter")
5766 (synopsis "Filter genes from high-throughput experiments")
5767 (description
5768 "This package provides basic functions for filtering genes from
5769 high-throughput sequencing experiments.")
5770 (license license:artistic2.0)))
5771
5772 (define-public r-deseq2
5773 (package
5774 (name "r-deseq2")
5775 (version "1.16.1")
5776 (source
5777 (origin
5778 (method url-fetch)
5779 (uri (bioconductor-uri "DESeq2" version))
5780 (sha256
5781 (base32
5782 "01pvyljxkwazxl510v7h0971nx65iqd2bdkbdhw3xzind0n9pdvq"))))
5783 (properties `((upstream-name . "DESeq2")))
5784 (build-system r-build-system)
5785 (propagated-inputs
5786 `(("r-biobase" ,r-biobase)
5787 ("r-biocgenerics" ,r-biocgenerics)
5788 ("r-biocparallel" ,r-biocparallel)
5789 ("r-genefilter" ,r-genefilter)
5790 ("r-geneplotter" ,r-geneplotter)
5791 ("r-genomicranges" ,r-genomicranges)
5792 ("r-ggplot2" ,r-ggplot2)
5793 ("r-hmisc" ,r-hmisc)
5794 ("r-iranges" ,r-iranges)
5795 ("r-locfit" ,r-locfit)
5796 ("r-rcpp" ,r-rcpp)
5797 ("r-rcpparmadillo" ,r-rcpparmadillo)
5798 ("r-s4vectors" ,r-s4vectors)
5799 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5800 (home-page "http://bioconductor.org/packages/DESeq2")
5801 (synopsis "Differential gene expression analysis")
5802 (description
5803 "This package provides functions to estimate variance-mean dependence in
5804 count data from high-throughput nucleotide sequencing assays and test for
5805 differential expression based on a model using the negative binomial
5806 distribution.")
5807 (license license:lgpl3+)))
5808
5809 (define-public r-dexseq
5810 (package
5811 (name "r-dexseq")
5812 (version "1.22.0")
5813 (source
5814 (origin
5815 (method url-fetch)
5816 (uri (bioconductor-uri "DEXSeq" version))
5817 (sha256
5818 (base32
5819 "085aqk1wlzzqcqcqhvz74y099kr2ln5dwdxd3rl6zan806mgwahg"))))
5820 (properties `((upstream-name . "DEXSeq")))
5821 (build-system r-build-system)
5822 (propagated-inputs
5823 `(("r-annotationdbi" ,r-annotationdbi)
5824 ("r-biobase" ,r-biobase)
5825 ("r-biocgenerics" ,r-biocgenerics)
5826 ("r-biocparallel" ,r-biocparallel)
5827 ("r-biomart" ,r-biomart)
5828 ("r-deseq2" ,r-deseq2)
5829 ("r-genefilter" ,r-genefilter)
5830 ("r-geneplotter" ,r-geneplotter)
5831 ("r-genomicranges" ,r-genomicranges)
5832 ("r-hwriter" ,r-hwriter)
5833 ("r-iranges" ,r-iranges)
5834 ("r-rcolorbrewer" ,r-rcolorbrewer)
5835 ("r-rsamtools" ,r-rsamtools)
5836 ("r-s4vectors" ,r-s4vectors)
5837 ("r-statmod" ,r-statmod)
5838 ("r-stringr" ,r-stringr)
5839 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5840 (home-page "http://bioconductor.org/packages/DEXSeq")
5841 (synopsis "Inference of differential exon usage in RNA-Seq")
5842 (description
5843 "This package is focused on finding differential exon usage using RNA-seq
5844 exon counts between samples with different experimental designs. It provides
5845 functions that allows the user to make the necessary statistical tests based
5846 on a model that uses the negative binomial distribution to estimate the
5847 variance between biological replicates and generalized linear models for
5848 testing. The package also provides functions for the visualization and
5849 exploration of the results.")
5850 (license license:gpl3+)))
5851
5852 (define-public r-annotationforge
5853 (package
5854 (name "r-annotationforge")
5855 (version "1.18.1")
5856 (source
5857 (origin
5858 (method url-fetch)
5859 (uri (bioconductor-uri "AnnotationForge" version))
5860 (sha256
5861 (base32
5862 "1366qvykd9cpcvwgc5g9mm9adw9rxw6p4814dd6l5fyb0pwpmysx"))))
5863 (properties
5864 `((upstream-name . "AnnotationForge")))
5865 (build-system r-build-system)
5866 (propagated-inputs
5867 `(("r-annotationdbi" ,r-annotationdbi)
5868 ("r-biobase" ,r-biobase)
5869 ("r-biocgenerics" ,r-biocgenerics)
5870 ("r-dbi" ,r-dbi)
5871 ("r-rcurl" ,r-rcurl)
5872 ("r-rsqlite" ,r-rsqlite)
5873 ("r-s4vectors" ,r-s4vectors)
5874 ("r-xml" ,r-xml)))
5875 (home-page "http://bioconductor.org/packages/AnnotationForge")
5876 (synopsis "Code for building annotation database packages")
5877 (description
5878 "This package provides code for generating Annotation packages and their
5879 databases. Packages produced are intended to be used with AnnotationDbi.")
5880 (license license:artistic2.0)))
5881
5882 (define-public r-rbgl
5883 (package
5884 (name "r-rbgl")
5885 (version "1.52.0")
5886 (source
5887 (origin
5888 (method url-fetch)
5889 (uri (bioconductor-uri "RBGL" version))
5890 (sha256
5891 (base32
5892 "11db6kvz453ypj9ds3xpjqzwrrjck84ijn4wlhkfyz2dzdgd5ryv"))))
5893 (properties `((upstream-name . "RBGL")))
5894 (build-system r-build-system)
5895 (propagated-inputs `(("r-graph" ,r-graph)))
5896 (home-page "http://www.bioconductor.org/packages/RBGL")
5897 (synopsis "Interface to the Boost graph library")
5898 (description
5899 "This package provides a fairly extensive and comprehensive interface to
5900 the graph algorithms contained in the Boost library.")
5901 (license license:artistic2.0)))
5902
5903 (define-public r-gseabase
5904 (package
5905 (name "r-gseabase")
5906 (version "1.38.0")
5907 (source
5908 (origin
5909 (method url-fetch)
5910 (uri (bioconductor-uri "GSEABase" version))
5911 (sha256
5912 (base32
5913 "1c6i6g4fj3b8wjyxyygr7i3v8sxrq1ffb2bbicya5ah2gdaclfad"))))
5914 (properties `((upstream-name . "GSEABase")))
5915 (build-system r-build-system)
5916 (propagated-inputs
5917 `(("r-annotate" ,r-annotate)
5918 ("r-annotationdbi" ,r-annotationdbi)
5919 ("r-biobase" ,r-biobase)
5920 ("r-biocgenerics" ,r-biocgenerics)
5921 ("r-graph" ,r-graph)
5922 ("r-xml" ,r-xml)))
5923 (home-page "http://bioconductor.org/packages/GSEABase")
5924 (synopsis "Gene set enrichment data structures and methods")
5925 (description
5926 "This package provides classes and methods to support @dfn{Gene Set
5927 Enrichment Analysis} (GSEA).")
5928 (license license:artistic2.0)))
5929
5930 (define-public r-category
5931 (package
5932 (name "r-category")
5933 (version "2.42.1")
5934 (source
5935 (origin
5936 (method url-fetch)
5937 (uri (bioconductor-uri "Category" version))
5938 (sha256
5939 (base32
5940 "1w186nhc85bglcgmbcrsdbb8l6rph21pl5kdwjqwkp0jnr9z0ifn"))))
5941 (properties `((upstream-name . "Category")))
5942 (build-system r-build-system)
5943 (propagated-inputs
5944 `(("r-annotate" ,r-annotate)
5945 ("r-annotationdbi" ,r-annotationdbi)
5946 ("r-biobase" ,r-biobase)
5947 ("r-biocgenerics" ,r-biocgenerics)
5948 ("r-genefilter" ,r-genefilter)
5949 ("r-graph" ,r-graph)
5950 ("r-gseabase" ,r-gseabase)
5951 ("r-matrix" ,r-matrix)
5952 ("r-rbgl" ,r-rbgl)
5953 ("r-rsqlite" ,r-rsqlite)))
5954 (home-page "http://bioconductor.org/packages/Category")
5955 (synopsis "Category analysis")
5956 (description
5957 "This package provides a collection of tools for performing category
5958 analysis.")
5959 (license license:artistic2.0)))
5960
5961 (define-public r-gostats
5962 (package
5963 (name "r-gostats")
5964 (version "2.42.0")
5965 (source
5966 (origin
5967 (method url-fetch)
5968 (uri (bioconductor-uri "GOstats" version))
5969 (sha256
5970 (base32
5971 "0qvqjgfnd9ap4rikvyxa9p4dhcnccvkw8phzv88vghh6pq463d62"))))
5972 (properties `((upstream-name . "GOstats")))
5973 (build-system r-build-system)
5974 (propagated-inputs
5975 `(("r-annotate" ,r-annotate)
5976 ("r-annotationdbi" ,r-annotationdbi)
5977 ("r-annotationforge" ,r-annotationforge)
5978 ("r-biobase" ,r-biobase)
5979 ("r-category" ,r-category)
5980 ("r-go-db" ,r-go-db)
5981 ("r-graph" ,r-graph)
5982 ("r-rbgl" ,r-rbgl)))
5983 (home-page "http://bioconductor.org/packages/GOstats")
5984 (synopsis "Tools for manipulating GO and microarrays")
5985 (description
5986 "This package provides a set of tools for interacting with GO and
5987 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5988 testing and other simple calculations.")
5989 (license license:artistic2.0)))
5990
5991 (define-public r-shortread
5992 (package
5993 (name "r-shortread")
5994 (version "1.34.0")
5995 (source
5996 (origin
5997 (method url-fetch)
5998 (uri (bioconductor-uri "ShortRead" version))
5999 (sha256
6000 (base32
6001 "0ayk3d5625ymb5g2gycq6banzqmyd642xrwjzhdshz2dwid7kly8"))))
6002 (properties `((upstream-name . "ShortRead")))
6003 (build-system r-build-system)
6004 (inputs
6005 `(("zlib" ,zlib)))
6006 (propagated-inputs
6007 `(("r-biobase" ,r-biobase)
6008 ("r-biocgenerics" ,r-biocgenerics)
6009 ("r-biocparallel" ,r-biocparallel)
6010 ("r-biostrings" ,r-biostrings)
6011 ("r-genomeinfodb" ,r-genomeinfodb)
6012 ("r-genomicalignments" ,r-genomicalignments)
6013 ("r-genomicranges" ,r-genomicranges)
6014 ("r-hwriter" ,r-hwriter)
6015 ("r-iranges" ,r-iranges)
6016 ("r-lattice" ,r-lattice)
6017 ("r-latticeextra" ,r-latticeextra)
6018 ("r-rsamtools" ,r-rsamtools)
6019 ("r-s4vectors" ,r-s4vectors)
6020 ("r-xvector" ,r-xvector)
6021 ("r-zlibbioc" ,r-zlibbioc)))
6022 (home-page "http://bioconductor.org/packages/ShortRead")
6023 (synopsis "FASTQ input and manipulation tools")
6024 (description
6025 "This package implements sampling, iteration, and input of FASTQ files.
6026 It includes functions for filtering and trimming reads, and for generating a
6027 quality assessment report. Data are represented as
6028 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6029 purposes. The package also contains legacy support for early single-end,
6030 ungapped alignment formats.")
6031 (license license:artistic2.0)))
6032
6033 (define-public r-systempiper
6034 (package
6035 (name "r-systempiper")
6036 (version "1.10.0")
6037 (source
6038 (origin
6039 (method url-fetch)
6040 (uri (bioconductor-uri "systemPipeR" version))
6041 (sha256
6042 (base32
6043 "0c3m5rq63ypv15yca97yag5d4vgd7xj9by2a4sd8z0pcmpajz0hw"))))
6044 (properties `((upstream-name . "systemPipeR")))
6045 (build-system r-build-system)
6046 (propagated-inputs
6047 `(("r-annotate" ,r-annotate)
6048 ("r-batchjobs" ,r-batchjobs)
6049 ("r-biocgenerics" ,r-biocgenerics)
6050 ("r-biostrings" ,r-biostrings)
6051 ("r-deseq2" ,r-deseq2)
6052 ("r-edger" ,r-edger)
6053 ("r-genomicfeatures" ,r-genomicfeatures)
6054 ("r-genomicranges" ,r-genomicranges)
6055 ("r-ggplot2" ,r-ggplot2)
6056 ("r-go-db" ,r-go-db)
6057 ("r-gostats" ,r-gostats)
6058 ("r-limma" ,r-limma)
6059 ("r-pheatmap" ,r-pheatmap)
6060 ("r-rjson" ,r-rjson)
6061 ("r-rsamtools" ,r-rsamtools)
6062 ("r-shortread" ,r-shortread)
6063 ("r-summarizedexperiment" ,r-summarizedexperiment)
6064 ("r-variantannotation" ,r-variantannotation)))
6065 (home-page "https://github.com/tgirke/systemPipeR")
6066 (synopsis "Next generation sequencing workflow and reporting environment")
6067 (description
6068 "This R package provides tools for building and running automated
6069 end-to-end analysis workflows for a wide range of @dfn{next generation
6070 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6071 Important features include a uniform workflow interface across different NGS
6072 applications, automated report generation, and support for running both R and
6073 command-line software, such as NGS aligners or peak/variant callers, on local
6074 computers or compute clusters. Efficient handling of complex sample sets and
6075 experimental designs is facilitated by a consistently implemented sample
6076 annotation infrastructure.")
6077 (license license:artistic2.0)))
6078
6079 (define-public r-grohmm
6080 (package
6081 (name "r-grohmm")
6082 (version "1.10.0")
6083 (source
6084 (origin
6085 (method url-fetch)
6086 (uri (bioconductor-uri "groHMM" version))
6087 (sha256
6088 (base32
6089 "16k1kp4sbhh0vp7dzywafq52csq42ksqfrqfy4bdv1qbd7536dpd"))))
6090 (properties `((upstream-name . "groHMM")))
6091 (build-system r-build-system)
6092 (propagated-inputs
6093 `(("r-genomeinfodb" ,r-genomeinfodb)
6094 ("r-genomicalignments" ,r-genomicalignments)
6095 ("r-genomicranges" ,r-genomicranges)
6096 ("r-iranges" ,r-iranges)
6097 ("r-mass" ,r-mass)
6098 ("r-rtracklayer" ,r-rtracklayer)
6099 ("r-s4vectors" ,r-s4vectors)))
6100 (home-page "https://github.com/Kraus-Lab/groHMM")
6101 (synopsis "GRO-seq analysis pipeline")
6102 (description
6103 "This package provides a pipeline for the analysis of GRO-seq data.")
6104 (license license:gpl3+)))
6105
6106 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6107 (package
6108 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6109 (version "3.2.2")
6110 (source (origin
6111 (method url-fetch)
6112 ;; We cannot use bioconductor-uri here because this tarball is
6113 ;; located under "data/annotation/" instead of "bioc/".
6114 (uri (string-append "http://bioconductor.org/packages/"
6115 "release/data/annotation/src/contrib"
6116 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6117 version ".tar.gz"))
6118 (sha256
6119 (base32
6120 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6121 (properties
6122 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6123 (build-system r-build-system)
6124 ;; As this package provides little more than a very large data file it
6125 ;; doesn't make sense to build substitutes.
6126 (arguments `(#:substitutable? #f))
6127 (propagated-inputs
6128 `(("r-genomicfeatures" ,r-genomicfeatures)))
6129 (home-page
6130 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6131 (synopsis "Annotation package for human genome in TxDb format")
6132 (description
6133 "This package provides an annotation database of Homo sapiens genome
6134 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6135 track. The database is exposed as a @code{TxDb} object.")
6136 (license license:artistic2.0)))
6137
6138 (define-public r-sparql
6139 (package
6140 (name "r-sparql")
6141 (version "1.16")
6142 (source (origin
6143 (method url-fetch)
6144 (uri (cran-uri "SPARQL" version))
6145 (sha256
6146 (base32
6147 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6148 (properties `((upstream-name . "SPARQL")))
6149 (build-system r-build-system)
6150 (propagated-inputs
6151 `(("r-rcurl" ,r-rcurl)
6152 ("r-xml" ,r-xml)))
6153 (home-page "http://cran.r-project.org/web/packages/SPARQL")
6154 (synopsis "SPARQL client for R")
6155 (description "This package provides an interface to use SPARQL to pose
6156 SELECT or UPDATE queries to an end-point.")
6157 ;; The only license indication is found in the DESCRIPTION file,
6158 ;; which states GPL-3. So we cannot assume GPLv3+.
6159 (license license:gpl3)))
6160
6161 (define-public vsearch
6162 (package
6163 (name "vsearch")
6164 (version "2.4.4")
6165 (source
6166 (origin
6167 (method url-fetch)
6168 (uri (string-append
6169 "https://github.com/torognes/vsearch/archive/v"
6170 version ".tar.gz"))
6171 (file-name (string-append name "-" version ".tar.gz"))
6172 (sha256
6173 (base32
6174 "1d8a4gjwaqdv57krlr80x18mg5py1bbdiqs5m0jdn38filc9z40k"))
6175 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6176 (snippet
6177 '(begin
6178 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6179 ;; for this in the patch.
6180 (delete-file "src/city.h")
6181 (delete-file "src/citycrc.h")
6182 (delete-file "src/city.cc")
6183 #t))))
6184 (build-system gnu-build-system)
6185 (arguments
6186 `(#:phases
6187 (modify-phases %standard-phases
6188 (add-after 'unpack 'autogen
6189 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6190 (inputs
6191 `(("zlib" ,zlib)
6192 ("bzip2" ,bzip2)
6193 ("cityhash" ,cityhash)))
6194 (native-inputs
6195 `(("autoconf" ,autoconf)
6196 ("automake" ,automake)))
6197 (synopsis "Sequence search tools for metagenomics")
6198 (description
6199 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6200 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6201 masking. The tool takes advantage of parallelism in the form of SIMD
6202 vectorization as well as multiple threads to perform accurate alignments at
6203 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6204 Needleman-Wunsch).")
6205 (home-page "https://github.com/torognes/vsearch")
6206 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6207 ;; platforms.
6208 (supported-systems '("x86_64-linux"))
6209 ;; Dual licensed; also includes public domain source.
6210 (license (list license:gpl3 license:bsd-2))))
6211
6212 (define-public pardre
6213 (package
6214 (name "pardre")
6215 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6216 (version "1.1.5-1")
6217 (source
6218 (origin
6219 (method url-fetch)
6220 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6221 "1.1.5" ".tar.gz"))
6222 (sha256
6223 (base32
6224 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6225 (build-system gnu-build-system)
6226 (arguments
6227 `(#:tests? #f ; no tests included
6228 #:phases
6229 (modify-phases %standard-phases
6230 (delete 'configure)
6231 (replace 'install
6232 (lambda* (#:key outputs #:allow-other-keys)
6233 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6234 (install-file "ParDRe" bin)
6235 #t))))))
6236 (inputs
6237 `(("openmpi" ,openmpi)
6238 ("zlib" ,zlib)))
6239 (synopsis "Parallel tool to remove duplicate DNA reads")
6240 (description
6241 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6242 Duplicate reads can be seen as identical or nearly identical sequences with
6243 some mismatches. This tool lets users avoid the analysis of unnecessary
6244 reads, reducing the time of subsequent procedures with the
6245 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6246 in order to exploit the parallel capabilities of multicore clusters. It is
6247 faster than multithreaded counterparts (end of 2015) for the same number of
6248 cores and, thanks to the message-passing technology, it can be executed on
6249 clusters.")
6250 (home-page "https://sourceforge.net/projects/pardre/")
6251 (license license:gpl3+)))
6252
6253 (define-public ruby-bio-kseq
6254 (package
6255 (name "ruby-bio-kseq")
6256 (version "0.0.2")
6257 (source
6258 (origin
6259 (method url-fetch)
6260 (uri (rubygems-uri "bio-kseq" version))
6261 (sha256
6262 (base32
6263 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6264 (build-system ruby-build-system)
6265 (arguments
6266 `(#:test-target "spec"))
6267 (native-inputs
6268 `(("bundler" ,bundler)
6269 ("ruby-rspec" ,ruby-rspec)
6270 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6271 (inputs
6272 `(("zlib" ,zlib)))
6273 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6274 (description
6275 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6276 FASTQ parsing code. It provides a fast iterator over sequences and their
6277 quality scores.")
6278 (home-page "https://github.com/gusevfe/bio-kseq")
6279 (license license:expat)))
6280
6281 (define-public bio-locus
6282 (package
6283 (name "bio-locus")
6284 (version "0.0.7")
6285 (source
6286 (origin
6287 (method url-fetch)
6288 (uri (rubygems-uri "bio-locus" version))
6289 (sha256
6290 (base32
6291 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6292 (build-system ruby-build-system)
6293 (native-inputs
6294 `(("ruby-rspec" ,ruby-rspec)))
6295 (synopsis "Tool for fast querying of genome locations")
6296 (description
6297 "Bio-locus is a tabix-like tool for fast querying of genome
6298 locations. Many file formats in bioinformatics contain records that
6299 start with a chromosome name and a position for a SNP, or a start-end
6300 position for indels. Bio-locus allows users to store this chr+pos or
6301 chr+pos+alt information in a database.")
6302 (home-page "https://github.com/pjotrp/bio-locus")
6303 (license license:expat)))
6304
6305 (define-public bio-blastxmlparser
6306 (package
6307 (name "bio-blastxmlparser")
6308 (version "2.0.4")
6309 (source (origin
6310 (method url-fetch)
6311 (uri (rubygems-uri "bio-blastxmlparser" version))
6312 (sha256
6313 (base32
6314 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6315 (build-system ruby-build-system)
6316 (propagated-inputs
6317 `(("ruby-bio-logger" ,ruby-bio-logger)
6318 ("ruby-nokogiri" ,ruby-nokogiri)))
6319 (inputs
6320 `(("ruby-rspec" ,ruby-rspec)))
6321 (synopsis "Fast big data BLAST XML parser and library")
6322 (description
6323 "Very fast parallel big-data BLAST XML file parser which can be used as
6324 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6325 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6326 (home-page "https://github.com/pjotrp/blastxmlparser")
6327 (license license:expat)))
6328
6329 (define-public bioruby
6330 (package
6331 (name "bioruby")
6332 (version "1.5.1")
6333 (source
6334 (origin
6335 (method url-fetch)
6336 (uri (rubygems-uri "bio" version))
6337 (sha256
6338 (base32
6339 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6340 (build-system ruby-build-system)
6341 (propagated-inputs
6342 `(("ruby-libxml" ,ruby-libxml)))
6343 (native-inputs
6344 `(("which" ,which))) ; required for test phase
6345 (arguments
6346 `(#:phases
6347 (modify-phases %standard-phases
6348 (add-before 'build 'patch-test-command
6349 (lambda _
6350 (substitute* '("test/functional/bio/test_command.rb")
6351 (("/bin/sh") (which "sh")))
6352 (substitute* '("test/functional/bio/test_command.rb")
6353 (("/bin/ls") (which "ls")))
6354 (substitute* '("test/functional/bio/test_command.rb")
6355 (("which") (which "which")))
6356 (substitute* '("test/functional/bio/test_command.rb",
6357 "test/data/command/echoarg2.sh")
6358 (("/bin/echo") (which "echo")))
6359 #t)))))
6360 (synopsis "Ruby library, shell and utilities for bioinformatics")
6361 (description "BioRuby comes with a comprehensive set of Ruby development
6362 tools and libraries for bioinformatics and molecular biology. BioRuby has
6363 components for sequence analysis, pathway analysis, protein modelling and
6364 phylogenetic analysis; it supports many widely used data formats and provides
6365 easy access to databases, external programs and public web services, including
6366 BLAST, KEGG, GenBank, MEDLINE and GO.")
6367 (home-page "http://bioruby.org/")
6368 ;; Code is released under Ruby license, except for setup
6369 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6370 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6371
6372 (define-public r-acsnminer
6373 (package
6374 (name "r-acsnminer")
6375 (version "0.16.8.25")
6376 (source (origin
6377 (method url-fetch)
6378 (uri (cran-uri "ACSNMineR" version))
6379 (sha256
6380 (base32
6381 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6382 (properties `((upstream-name . "ACSNMineR")))
6383 (build-system r-build-system)
6384 (propagated-inputs
6385 `(("r-ggplot2" ,r-ggplot2)
6386 ("r-gridextra" ,r-gridextra)))
6387 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6388 (synopsis "Gene enrichment analysis")
6389 (description
6390 "This package provides tools to compute and represent gene set enrichment
6391 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6392 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6393 enrichment can be run with hypergeometric test or Fisher exact test, and can
6394 use multiple corrections. Visualization of data can be done either by
6395 barplots or heatmaps.")
6396 (license license:gpl2+)))
6397
6398 (define-public r-biocgenerics
6399 (package
6400 (name "r-biocgenerics")
6401 (version "0.22.0")
6402 (source (origin
6403 (method url-fetch)
6404 (uri (bioconductor-uri "BiocGenerics" version))
6405 (sha256
6406 (base32
6407 "0qbmz2qxwwi30xpxpvp2h1h7l494rbbz5d9pls5cfhqdv3wnpzsv"))))
6408 (properties
6409 `((upstream-name . "BiocGenerics")))
6410 (build-system r-build-system)
6411 (home-page "http://bioconductor.org/packages/BiocGenerics")
6412 (synopsis "S4 generic functions for Bioconductor")
6413 (description
6414 "This package provides S4 generic functions needed by many Bioconductor
6415 packages.")
6416 (license license:artistic2.0)))
6417
6418 (define-public r-biocinstaller
6419 (package
6420 (name "r-biocinstaller")
6421 (version "1.26.0")
6422 (source (origin
6423 (method url-fetch)
6424 (uri (bioconductor-uri "BiocInstaller" version))
6425 (sha256
6426 (base32
6427 "0njw2q3lq1rrjx8qzw5d2130l72bmd3g2z8qlxqmkdcbmmgliyj2"))))
6428 (properties
6429 `((upstream-name . "BiocInstaller")))
6430 (build-system r-build-system)
6431 (home-page "http://bioconductor.org/packages/BiocInstaller")
6432 (synopsis "Install Bioconductor packages")
6433 (description "This package is used to install and update R packages from
6434 Bioconductor, CRAN, and Github.")
6435 (license license:artistic2.0)))
6436
6437 (define-public r-biocviews
6438 (package
6439 (name "r-biocviews")
6440 (version "1.44.0")
6441 (source (origin
6442 (method url-fetch)
6443 (uri (bioconductor-uri "biocViews" version))
6444 (sha256
6445 (base32
6446 "17hi8w0w63f5yc43kid5pbld3ca78sj6n8x9dmkbl8h48818xbga"))))
6447 (properties
6448 `((upstream-name . "biocViews")))
6449 (build-system r-build-system)
6450 (propagated-inputs
6451 `(("r-biobase" ,r-biobase)
6452 ("r-graph" ,r-graph)
6453 ("r-rbgl" ,r-rbgl)
6454 ("r-rcurl" ,r-rcurl)
6455 ("r-xml" ,r-xml)
6456 ("r-knitr" ,r-knitr)
6457 ("r-runit" ,r-runit)))
6458 (home-page "http://bioconductor.org/packages/biocViews")
6459 (synopsis "Bioconductor package categorization helper")
6460 (description "The purpose of biocViews is to create HTML pages that
6461 categorize packages in a Bioconductor package repository according to keywords,
6462 also known as views, in a controlled vocabulary.")
6463 (license license:artistic2.0)))
6464
6465 (define-public r-bookdown
6466 (package
6467 (name "r-bookdown")
6468 (version "0.5")
6469 (source (origin
6470 (method url-fetch)
6471 (uri (cran-uri "bookdown" version))
6472 (sha256
6473 (base32
6474 "0zm63kr4f4kja4qpwkzl119zzyciqj7ihajfqgfjpgb4dzaiycxp"))))
6475 (build-system r-build-system)
6476 (propagated-inputs
6477 `(("r-htmltools" ,r-htmltools)
6478 ("r-knitr" ,r-knitr)
6479 ("r-rmarkdown" ,r-rmarkdown)
6480 ("r-yaml" ,r-yaml)))
6481 (home-page "https://github.com/rstudio/bookdown")
6482 (synopsis "Authoring books and technical documents with R markdown")
6483 (description "This package provides output formats and utilities for
6484 authoring books and technical documents with R Markdown.")
6485 (license license:gpl3)))
6486
6487 (define-public r-biocstyle
6488 (package
6489 (name "r-biocstyle")
6490 (version "2.4.1")
6491 (source (origin
6492 (method url-fetch)
6493 (uri (bioconductor-uri "BiocStyle" version))
6494 (sha256
6495 (base32
6496 "0bmgmsfll923v573g0kyzlmjd7gly5jwgd8vkrcwvbam1gz75f2c"))))
6497 (properties
6498 `((upstream-name . "BiocStyle")))
6499 (build-system r-build-system)
6500 (propagated-inputs
6501 `(("r-bookdown" ,r-bookdown)
6502 ("r-knitr" ,r-knitr)
6503 ("r-rmarkdown" ,r-rmarkdown)
6504 ("r-yaml" ,r-yaml)))
6505 (home-page "http://bioconductor.org/packages/BiocStyle")
6506 (synopsis "Bioconductor formatting styles")
6507 (description "This package provides standard formatting styles for
6508 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6509 functionality.")
6510 (license license:artistic2.0)))
6511
6512 (define-public r-bioccheck
6513 (package
6514 (name "r-bioccheck")
6515 (version "1.12.0")
6516 (source (origin
6517 (method url-fetch)
6518 (uri (bioconductor-uri "BiocCheck" version))
6519 (sha256
6520 (base32
6521 "01zkw5hggzvn0wj4msac71k1mknq4h2inn1c2hwqgw4cy1675wl0"))))
6522 (properties
6523 `((upstream-name . "BiocCheck")))
6524 (build-system r-build-system)
6525 (arguments
6526 '(#:phases
6527 (modify-phases %standard-phases
6528 ;; This package can be used by calling BiocCheck(<package>) from
6529 ;; within R, or by running R CMD BiocCheck <package>. This phase
6530 ;; makes sure the latter works. For this to work, the BiocCheck
6531 ;; script must be somewhere on the PATH (not the R bin directory).
6532 (add-after 'install 'install-bioccheck-subcommand
6533 (lambda* (#:key outputs #:allow-other-keys)
6534 (let* ((out (assoc-ref outputs "out"))
6535 (dest-dir (string-append out "/bin"))
6536 (script-dir
6537 (string-append out "/site-library/BiocCheck/script/")))
6538 (mkdir-p dest-dir)
6539 (symlink (string-append script-dir "/checkBadDeps.R")
6540 (string-append dest-dir "/checkBadDeps.R"))
6541 (symlink (string-append script-dir "/BiocCheck")
6542 (string-append dest-dir "/BiocCheck")))
6543 #t)))))
6544 (native-inputs
6545 `(("which" ,which)))
6546 (propagated-inputs
6547 `(("r-codetools" ,r-codetools)
6548 ("r-graph" ,r-graph)
6549 ("r-httr" ,r-httr)
6550 ("r-optparse" ,r-optparse)
6551 ("r-biocinstaller" ,r-biocinstaller)
6552 ("r-biocviews" ,r-biocviews)))
6553 (home-page "http://bioconductor.org/packages/BiocCheck")
6554 (synopsis "Executes Bioconductor-specific package checks")
6555 (description "This package contains tools to perform additional quality
6556 checks on R packages that are to be submitted to the Bioconductor repository.")
6557 (license license:artistic2.0)))
6558
6559 (define-public r-getopt
6560 (package
6561 (name "r-getopt")
6562 (version "1.20.0")
6563 (source
6564 (origin
6565 (method url-fetch)
6566 (uri (cran-uri "getopt" version))
6567 (sha256
6568 (base32
6569 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6570 (build-system r-build-system)
6571 (home-page "https://github.com/trevorld/getopt")
6572 (synopsis "Command-line option processor for R")
6573 (description
6574 "This package is designed to be used with Rscript to write shebang
6575 scripts that accept short and long options. Many users will prefer to
6576 use the packages @code{optparse} or @code{argparse} which add extra
6577 features like automatically generated help options and usage texts,
6578 support for default values, positional argument support, etc.")
6579 (license license:gpl2+)))
6580
6581 (define-public r-optparse
6582 (package
6583 (name "r-optparse")
6584 (version "1.4.4")
6585 (source
6586 (origin
6587 (method url-fetch)
6588 (uri (cran-uri "optparse" version))
6589 (sha256
6590 (base32
6591 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6592 (build-system r-build-system)
6593 (propagated-inputs
6594 `(("r-getopt" ,r-getopt)))
6595 (home-page
6596 "https://github.com/trevorld/optparse")
6597 (synopsis "Command line option parser")
6598 (description
6599 "This package provides a command line parser inspired by Python's
6600 @code{optparse} library to be used with Rscript to write shebang scripts
6601 that accept short and long options.")
6602 (license license:gpl2+)))
6603
6604 (define-public r-dnacopy
6605 (package
6606 (name "r-dnacopy")
6607 (version "1.50.1")
6608 (source (origin
6609 (method url-fetch)
6610 (uri (bioconductor-uri "DNAcopy" version))
6611 (sha256
6612 (base32
6613 "0f0x83db7rm5xf9fg5pjhvs4i165qqaf01lbwb8kj13fsqpwx15p"))))
6614 (properties
6615 `((upstream-name . "DNAcopy")))
6616 (build-system r-build-system)
6617 (inputs
6618 `(("gfortran" ,gfortran)))
6619 (home-page "https://bioconductor.org/packages/DNAcopy")
6620 (synopsis "Implementation of a circular binary segmentation algorithm")
6621 (description "This package implements the circular binary segmentation (CBS)
6622 algorithm to segment DNA copy number data and identify genomic regions with
6623 abnormal copy number.")
6624 (license license:gpl2+)))
6625
6626 (define-public r-s4vectors
6627 (package
6628 (name "r-s4vectors")
6629 (version "0.14.3")
6630 (source (origin
6631 (method url-fetch)
6632 (uri (bioconductor-uri "S4Vectors" version))
6633 (sha256
6634 (base32
6635 "1r7s4pfw026qazzic090mhk8d9m39j2nwl87dyqcpdylyq7gq5qs"))))
6636 (properties
6637 `((upstream-name . "S4Vectors")))
6638 (build-system r-build-system)
6639 (propagated-inputs
6640 `(("r-biocgenerics" ,r-biocgenerics)))
6641 (home-page "http://bioconductor.org/packages/S4Vectors")
6642 (synopsis "S4 implementation of vectors and lists")
6643 (description
6644 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6645 classes and a set of generic functions that extend the semantic of ordinary
6646 vectors and lists in R. Package developers can easily implement vector-like
6647 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6648 In addition, a few low-level concrete subclasses of general interest (e.g.
6649 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6650 S4Vectors package itself.")
6651 (license license:artistic2.0)))
6652
6653 (define-public r-seqinr
6654 (package
6655 (name "r-seqinr")
6656 (version "3.4-5")
6657 (source
6658 (origin
6659 (method url-fetch)
6660 (uri (cran-uri "seqinr" version))
6661 (sha256
6662 (base32
6663 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
6664 (build-system r-build-system)
6665 (propagated-inputs
6666 `(("r-ade4" ,r-ade4)
6667 ("r-segmented" ,r-segmented)))
6668 (inputs
6669 `(("zlib" ,zlib)))
6670 (home-page "http://seqinr.r-forge.r-project.org/")
6671 (synopsis "Biological sequences retrieval and analysis")
6672 (description
6673 "This package provides tools for exploratory data analysis and data
6674 visualization of biological sequence (DNA and protein) data. It also includes
6675 utilities for sequence data management under the ACNUC system.")
6676 (license license:gpl2+)))
6677
6678 (define-public r-iranges
6679 (package
6680 (name "r-iranges")
6681 (version "2.10.2")
6682 (source (origin
6683 (method url-fetch)
6684 (uri (bioconductor-uri "IRanges" version))
6685 (sha256
6686 (base32
6687 "1brmzs3rsf97gymridrh9c9r3vws8b3rpghaanxnniw36lmcajfy"))))
6688 (properties
6689 `((upstream-name . "IRanges")))
6690 (build-system r-build-system)
6691 (propagated-inputs
6692 `(("r-biocgenerics" ,r-biocgenerics)
6693 ("r-s4vectors" ,r-s4vectors)))
6694 (home-page "http://bioconductor.org/packages/IRanges")
6695 (synopsis "Infrastructure for manipulating intervals on sequences")
6696 (description
6697 "This package provides efficient low-level and highly reusable S4 classes
6698 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6699 generally, data that can be organized sequentially (formally defined as
6700 @code{Vector} objects), as well as views on these @code{Vector} objects.
6701 Efficient list-like classes are also provided for storing big collections of
6702 instances of the basic classes. All classes in the package use consistent
6703 naming and share the same rich and consistent \"Vector API\" as much as
6704 possible.")
6705 (license license:artistic2.0)))
6706
6707 (define-public r-genomeinfodbdata
6708 (package
6709 (name "r-genomeinfodbdata")
6710 (version "0.99.0")
6711 (source (origin
6712 (method url-fetch)
6713 ;; We cannot use bioconductor-uri here because this tarball is
6714 ;; located under "data/annotation/" instead of "bioc/".
6715 (uri (string-append "https://bioconductor.org/packages/release/"
6716 "data/annotation/src/contrib/GenomeInfoDbData_"
6717 version ".tar.gz"))
6718 (sha256
6719 (base32
6720 "120qvhb0pvkzd65lsgja62vyrgc37si6fh68q4cg4w5x9f04jw25"))))
6721 (properties
6722 `((upstream-name . "GenomeInfoDbData")))
6723 (build-system r-build-system)
6724 (home-page "http://bioconductor.org/packages/GenomeInfoDbData")
6725 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6726 (description "This package contains data for mapping between NCBI taxonomy
6727 ID and species. It is used by functions in the GenomeInfoDb package.")
6728 (license license:artistic2.0)))
6729
6730 (define-public r-genomeinfodb
6731 (package
6732 (name "r-genomeinfodb")
6733 (version "1.12.2")
6734 (source (origin
6735 (method url-fetch)
6736 (uri (bioconductor-uri "GenomeInfoDb" version))
6737 (sha256
6738 (base32
6739 "1hjxgmcnrngp1307ipqaq9hgxz4j0ldn7d46knhzs30k2r4qnrfp"))))
6740 (properties
6741 `((upstream-name . "GenomeInfoDb")))
6742 (build-system r-build-system)
6743 (propagated-inputs
6744 `(("r-biocgenerics" ,r-biocgenerics)
6745 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6746 ("r-iranges" ,r-iranges)
6747 ("r-rcurl" ,r-rcurl)
6748 ("r-s4vectors" ,r-s4vectors)))
6749 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6750 (synopsis "Utilities for manipulating chromosome identifiers")
6751 (description
6752 "This package contains data and functions that define and allow
6753 translation between different chromosome sequence naming conventions (e.g.,
6754 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6755 names in their natural, rather than lexicographic, order.")
6756 (license license:artistic2.0)))
6757
6758 (define-public r-edger
6759 (package
6760 (name "r-edger")
6761 (version "3.18.0")
6762 (source (origin
6763 (method url-fetch)
6764 (uri (bioconductor-uri "edgeR" version))
6765 (sha256
6766 (base32
6767 "02l17i6xh33dv10swwvyfxrmv5kp23iv278iwvkfq2mnipasfnb9"))))
6768 (properties `((upstream-name . "edgeR")))
6769 (build-system r-build-system)
6770 (propagated-inputs
6771 `(("r-limma" ,r-limma)
6772 ("r-locfit" ,r-locfit)
6773 ("r-statmod" ,r-statmod))) ;for estimateDisp
6774 (home-page "http://bioinf.wehi.edu.au/edgeR")
6775 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6776 (description "This package can do differential expression analysis of
6777 RNA-seq expression profiles with biological replication. It implements a range
6778 of statistical methodology based on the negative binomial distributions,
6779 including empirical Bayes estimation, exact tests, generalized linear models
6780 and quasi-likelihood tests. It be applied to differential signal analysis of
6781 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6782 CAGE.")
6783 (license license:gpl2+)))
6784
6785 (define-public r-variantannotation
6786 (package
6787 (name "r-variantannotation")
6788 (version "1.22.3")
6789 (source (origin
6790 (method url-fetch)
6791 (uri (bioconductor-uri "VariantAnnotation" version))
6792 (sha256
6793 (base32
6794 "0sr3vdn85x5zdxh80cfwlpfdpi2hmjy3fwi00ac3jya4v145vawr"))))
6795 (properties
6796 `((upstream-name . "VariantAnnotation")))
6797 (inputs
6798 `(("zlib" ,zlib)))
6799 (propagated-inputs
6800 `(("r-annotationdbi" ,r-annotationdbi)
6801 ("r-biobase" ,r-biobase)
6802 ("r-biocgenerics" ,r-biocgenerics)
6803 ("r-biostrings" ,r-biostrings)
6804 ("r-bsgenome" ,r-bsgenome)
6805 ("r-dbi" ,r-dbi)
6806 ("r-genomeinfodb" ,r-genomeinfodb)
6807 ("r-genomicfeatures" ,r-genomicfeatures)
6808 ("r-genomicranges" ,r-genomicranges)
6809 ("r-iranges" ,r-iranges)
6810 ("r-summarizedexperiment" ,r-summarizedexperiment)
6811 ("r-rsamtools" ,r-rsamtools)
6812 ("r-rtracklayer" ,r-rtracklayer)
6813 ("r-s4vectors" ,r-s4vectors)
6814 ("r-xvector" ,r-xvector)
6815 ("r-zlibbioc" ,r-zlibbioc)))
6816 (build-system r-build-system)
6817 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6818 (synopsis "Package for annotation of genetic variants")
6819 (description "This R package can annotate variants, compute amino acid
6820 coding changes and predict coding outcomes.")
6821 (license license:artistic2.0)))
6822
6823 (define-public r-limma
6824 (package
6825 (name "r-limma")
6826 (version "3.32.5")
6827 (source (origin
6828 (method url-fetch)
6829 (uri (bioconductor-uri "limma" version))
6830 (sha256
6831 (base32
6832 "0p2ayha9g9w5r8s7pgdf16mkmdbqwh6f35jh07g3b8gyra48gwiw"))))
6833 (build-system r-build-system)
6834 (home-page "http://bioinf.wehi.edu.au/limma")
6835 (synopsis "Package for linear models for microarray and RNA-seq data")
6836 (description "This package can be used for the analysis of gene expression
6837 studies, especially the use of linear models for analysing designed experiments
6838 and the assessment of differential expression. The analysis methods apply to
6839 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6840 (license license:gpl2+)))
6841
6842 (define-public r-xvector
6843 (package
6844 (name "r-xvector")
6845 (version "0.16.0")
6846 (source (origin
6847 (method url-fetch)
6848 (uri (bioconductor-uri "XVector" version))
6849 (sha256
6850 (base32
6851 "01n09f4jdm60684lzikp02zf9gjan8bdrjx740vggr21q9fa69wn"))))
6852 (properties
6853 `((upstream-name . "XVector")))
6854 (build-system r-build-system)
6855 (arguments
6856 `(#:phases
6857 (modify-phases %standard-phases
6858 (add-after 'unpack 'use-system-zlib
6859 (lambda _
6860 (substitute* "DESCRIPTION"
6861 (("zlibbioc, ") ""))
6862 (substitute* "NAMESPACE"
6863 (("import\\(zlibbioc\\)") ""))
6864 #t)))))
6865 (inputs
6866 `(("zlib" ,zlib)))
6867 (propagated-inputs
6868 `(("r-biocgenerics" ,r-biocgenerics)
6869 ("r-iranges" ,r-iranges)
6870 ("r-s4vectors" ,r-s4vectors)))
6871 (home-page "http://bioconductor.org/packages/XVector")
6872 (synopsis "Representation and manpulation of external sequences")
6873 (description
6874 "This package provides memory efficient S4 classes for storing sequences
6875 \"externally\" (behind an R external pointer, or on disk).")
6876 (license license:artistic2.0)))
6877
6878 (define-public r-genomicranges
6879 (package
6880 (name "r-genomicranges")
6881 (version "1.28.4")
6882 (source (origin
6883 (method url-fetch)
6884 (uri (bioconductor-uri "GenomicRanges" version))
6885 (sha256
6886 (base32
6887 "1y15kg1q81h8rmga83ljiwr8whkajcargfjiljr212d6if17ys1z"))))
6888 (properties
6889 `((upstream-name . "GenomicRanges")))
6890 (build-system r-build-system)
6891 (propagated-inputs
6892 `(("r-biocgenerics" ,r-biocgenerics)
6893 ("r-genomeinfodb" ,r-genomeinfodb)
6894 ("r-iranges" ,r-iranges)
6895 ("r-s4vectors" ,r-s4vectors)
6896 ("r-xvector" ,r-xvector)))
6897 (home-page "http://bioconductor.org/packages/GenomicRanges")
6898 (synopsis "Representation and manipulation of genomic intervals")
6899 (description
6900 "This package provides tools to efficiently represent and manipulate
6901 genomic annotations and alignments is playing a central role when it comes to
6902 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6903 GenomicRanges package defines general purpose containers for storing and
6904 manipulating genomic intervals and variables defined along a genome.")
6905 (license license:artistic2.0)))
6906
6907 (define-public r-biobase
6908 (package
6909 (name "r-biobase")
6910 (version "2.36.2")
6911 (source (origin
6912 (method url-fetch)
6913 (uri (bioconductor-uri "Biobase" version))
6914 (sha256
6915 (base32
6916 "0sr48nqx5bqid4g6lr9zr9286xh842w717yvmssvddb5xxynib6f"))))
6917 (properties
6918 `((upstream-name . "Biobase")))
6919 (build-system r-build-system)
6920 (propagated-inputs
6921 `(("r-biocgenerics" ,r-biocgenerics)))
6922 (home-page "http://bioconductor.org/packages/Biobase")
6923 (synopsis "Base functions for Bioconductor")
6924 (description
6925 "This package provides functions that are needed by many other packages
6926 on Bioconductor or which replace R functions.")
6927 (license license:artistic2.0)))
6928
6929 (define-public r-annotationdbi
6930 (package
6931 (name "r-annotationdbi")
6932 (version "1.38.2")
6933 (source (origin
6934 (method url-fetch)
6935 (uri (bioconductor-uri "AnnotationDbi" version))
6936 (sha256
6937 (base32
6938 "1lsamnbf07zzsy5asy5hn97n2a4layv58w2bzd90ikcdx0gmzarj"))))
6939 (properties
6940 `((upstream-name . "AnnotationDbi")))
6941 (build-system r-build-system)
6942 (propagated-inputs
6943 `(("r-biobase" ,r-biobase)
6944 ("r-biocgenerics" ,r-biocgenerics)
6945 ("r-dbi" ,r-dbi)
6946 ("r-iranges" ,r-iranges)
6947 ("r-rsqlite" ,r-rsqlite)
6948 ("r-s4vectors" ,r-s4vectors)))
6949 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6950 (synopsis "Annotation database interface")
6951 (description
6952 "This package provides user interface and database connection code for
6953 annotation data packages using SQLite data storage.")
6954 (license license:artistic2.0)))
6955
6956 (define-public r-biomart
6957 (package
6958 (name "r-biomart")
6959 (version "2.32.1")
6960 (source (origin
6961 (method url-fetch)
6962 (uri (bioconductor-uri "biomaRt" version))
6963 (sha256
6964 (base32
6965 "0fhpbjlsgbqxrpj6nzhhk9q3ph81n5x4p7mmd097xjjn6b05w1d8"))))
6966 (properties
6967 `((upstream-name . "biomaRt")))
6968 (build-system r-build-system)
6969 (propagated-inputs
6970 `(("r-annotationdbi" ,r-annotationdbi)
6971 ("r-rcurl" ,r-rcurl)
6972 ("r-xml" ,r-xml)))
6973 (home-page "http://bioconductor.org/packages/biomaRt")
6974 (synopsis "Interface to BioMart databases")
6975 (description
6976 "biomaRt provides an interface to a growing collection of databases
6977 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6978 package enables retrieval of large amounts of data in a uniform way without
6979 the need to know the underlying database schemas or write complex SQL queries.
6980 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6981 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6982 users direct access to a diverse set of data and enable a wide range of
6983 powerful online queries from gene annotation to database mining.")
6984 (license license:artistic2.0)))
6985
6986 (define-public r-biocparallel
6987 (package
6988 (name "r-biocparallel")
6989 (version "1.10.1")
6990 (source (origin
6991 (method url-fetch)
6992 (uri (bioconductor-uri "BiocParallel" version))
6993 (sha256
6994 (base32
6995 "08mdfxyk9nwz77v0xhlvs19p2wj0phgm5c5b25vm0xh3749njsp0"))))
6996 (properties
6997 `((upstream-name . "BiocParallel")))
6998 (build-system r-build-system)
6999 (propagated-inputs
7000 `(("r-futile-logger" ,r-futile-logger)
7001 ("r-snow" ,r-snow)))
7002 (home-page "http://bioconductor.org/packages/BiocParallel")
7003 (synopsis "Bioconductor facilities for parallel evaluation")
7004 (description
7005 "This package provides modified versions and novel implementation of
7006 functions for parallel evaluation, tailored to use with Bioconductor
7007 objects.")
7008 (license (list license:gpl2+ license:gpl3+))))
7009
7010 (define-public r-biostrings
7011 (package
7012 (name "r-biostrings")
7013 (version "2.44.2")
7014 (source (origin
7015 (method url-fetch)
7016 (uri (bioconductor-uri "Biostrings" version))
7017 (sha256
7018 (base32
7019 "12c5abgshwq86357jr0r9039y6vl4d6ngysy89rsnr23ldnsirjp"))))
7020 (properties
7021 `((upstream-name . "Biostrings")))
7022 (build-system r-build-system)
7023 (propagated-inputs
7024 `(("r-biocgenerics" ,r-biocgenerics)
7025 ("r-iranges" ,r-iranges)
7026 ("r-s4vectors" ,r-s4vectors)
7027 ("r-xvector" ,r-xvector)))
7028 (home-page "http://bioconductor.org/packages/Biostrings")
7029 (synopsis "String objects and algorithms for biological sequences")
7030 (description
7031 "This package provides memory efficient string containers, string
7032 matching algorithms, and other utilities, for fast manipulation of large
7033 biological sequences or sets of sequences.")
7034 (license license:artistic2.0)))
7035
7036 (define-public r-rsamtools
7037 (package
7038 (name "r-rsamtools")
7039 (version "1.28.0")
7040 (source (origin
7041 (method url-fetch)
7042 (uri (bioconductor-uri "Rsamtools" version))
7043 (sha256
7044 (base32
7045 "1zx6vhdz3lksbfy98jj3qzl7cxgspigm2pbsd5835b12r6mc5w6d"))))
7046 (properties
7047 `((upstream-name . "Rsamtools")))
7048 (build-system r-build-system)
7049 (arguments
7050 `(#:phases
7051 (modify-phases %standard-phases
7052 (add-after 'unpack 'use-system-zlib
7053 (lambda _
7054 (substitute* "DESCRIPTION"
7055 (("zlibbioc, ") ""))
7056 (substitute* "NAMESPACE"
7057 (("import\\(zlibbioc\\)") ""))
7058 #t)))))
7059 (inputs
7060 `(("zlib" ,zlib)))
7061 (propagated-inputs
7062 `(("r-biocgenerics" ,r-biocgenerics)
7063 ("r-biocparallel" ,r-biocparallel)
7064 ("r-biostrings" ,r-biostrings)
7065 ("r-bitops" ,r-bitops)
7066 ("r-genomeinfodb" ,r-genomeinfodb)
7067 ("r-genomicranges" ,r-genomicranges)
7068 ("r-iranges" ,r-iranges)
7069 ("r-s4vectors" ,r-s4vectors)
7070 ("r-xvector" ,r-xvector)))
7071 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7072 (synopsis "Interface to samtools, bcftools, and tabix")
7073 (description
7074 "This package provides an interface to the 'samtools', 'bcftools', and
7075 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7076 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7077 files.")
7078 (license license:expat)))
7079
7080 (define-public r-delayedarray
7081 (package
7082 (name "r-delayedarray")
7083 (version "0.2.7")
7084 (source (origin
7085 (method url-fetch)
7086 (uri (bioconductor-uri "DelayedArray" version))
7087 (sha256
7088 (base32
7089 "02dfqp4md9xaqjj712ijc3jswghmipr5hwkd5hr0x1xi6l2fb69g"))))
7090 (properties
7091 `((upstream-name . "DelayedArray")))
7092 (build-system r-build-system)
7093 (propagated-inputs
7094 `(("r-biocgenerics" ,r-biocgenerics)
7095 ("r-s4vectors" ,r-s4vectors)
7096 ("r-iranges" ,r-iranges)
7097 ("r-matrixstats" ,r-matrixstats)))
7098 (home-page "http://bioconductor.org/packages/DelayedArray")
7099 (synopsis "Delayed operations on array-like objects")
7100 (description
7101 "Wrapping an array-like object (typically an on-disk object) in a
7102 @code{DelayedArray} object allows one to perform common array operations on it
7103 without loading the object in memory. In order to reduce memory usage and
7104 optimize performance, operations on the object are either delayed or executed
7105 using a block processing mechanism. Note that this also works on in-memory
7106 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7107 @code{Matrix} objects, and ordinary arrays and data frames.")
7108 (license license:artistic2.0)))
7109
7110 (define-public r-summarizedexperiment
7111 (package
7112 (name "r-summarizedexperiment")
7113 (version "1.6.3")
7114 (source (origin
7115 (method url-fetch)
7116 (uri (bioconductor-uri "SummarizedExperiment" version))
7117 (sha256
7118 (base32
7119 "0j7xn7pk52d383fb1wplcggacl2586c4zi0alkgfc3wz7qq9w13s"))))
7120 (properties
7121 `((upstream-name . "SummarizedExperiment")))
7122 (build-system r-build-system)
7123 (propagated-inputs
7124 `(("r-biobase" ,r-biobase)
7125 ("r-biocgenerics" ,r-biocgenerics)
7126 ("r-delayedarray" ,r-delayedarray)
7127 ("r-genomeinfodb" ,r-genomeinfodb)
7128 ("r-genomicranges" ,r-genomicranges)
7129 ("r-iranges" ,r-iranges)
7130 ("r-matrix" ,r-matrix)
7131 ("r-s4vectors" ,r-s4vectors)))
7132 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
7133 (synopsis "Container for representing genomic ranges by sample")
7134 (description
7135 "The SummarizedExperiment container contains one or more assays, each
7136 represented by a matrix-like object of numeric or other mode. The rows
7137 typically represent genomic ranges of interest and the columns represent
7138 samples.")
7139 (license license:artistic2.0)))
7140
7141 (define-public r-genomicalignments
7142 (package
7143 (name "r-genomicalignments")
7144 (version "1.12.2")
7145 (source (origin
7146 (method url-fetch)
7147 (uri (bioconductor-uri "GenomicAlignments" version))
7148 (sha256
7149 (base32
7150 "03ysxi9fdd3bcfj05iaysya9knn2aa2irwpypb5srg0xwv92bdb9"))))
7151 (properties
7152 `((upstream-name . "GenomicAlignments")))
7153 (build-system r-build-system)
7154 (propagated-inputs
7155 `(("r-biocgenerics" ,r-biocgenerics)
7156 ("r-biocparallel" ,r-biocparallel)
7157 ("r-biostrings" ,r-biostrings)
7158 ("r-genomeinfodb" ,r-genomeinfodb)
7159 ("r-genomicranges" ,r-genomicranges)
7160 ("r-iranges" ,r-iranges)
7161 ("r-rsamtools" ,r-rsamtools)
7162 ("r-s4vectors" ,r-s4vectors)
7163 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7164 (home-page "http://bioconductor.org/packages/GenomicAlignments")
7165 (synopsis "Representation and manipulation of short genomic alignments")
7166 (description
7167 "This package provides efficient containers for storing and manipulating
7168 short genomic alignments (typically obtained by aligning short reads to a
7169 reference genome). This includes read counting, computing the coverage,
7170 junction detection, and working with the nucleotide content of the
7171 alignments.")
7172 (license license:artistic2.0)))
7173
7174 (define-public r-rtracklayer
7175 (package
7176 (name "r-rtracklayer")
7177 (version "1.36.4")
7178 (source (origin
7179 (method url-fetch)
7180 (uri (bioconductor-uri "rtracklayer" version))
7181 (sha256
7182 (base32
7183 "050q1rv04w31168ljr975vxva31n9lqdx84rnmsk6zcr6p640ffp"))))
7184 (build-system r-build-system)
7185 (arguments
7186 `(#:phases
7187 (modify-phases %standard-phases
7188 (add-after 'unpack 'use-system-zlib
7189 (lambda _
7190 (substitute* "DESCRIPTION"
7191 (("zlibbioc, ") ""))
7192 (substitute* "NAMESPACE"
7193 (("import\\(zlibbioc\\)") ""))
7194 #t)))))
7195 (inputs
7196 `(("zlib" ,zlib)))
7197 (propagated-inputs
7198 `(("r-biocgenerics" ,r-biocgenerics)
7199 ("r-biostrings" ,r-biostrings)
7200 ("r-genomeinfodb" ,r-genomeinfodb)
7201 ("r-genomicalignments" ,r-genomicalignments)
7202 ("r-genomicranges" ,r-genomicranges)
7203 ("r-iranges" ,r-iranges)
7204 ("r-rcurl" ,r-rcurl)
7205 ("r-rsamtools" ,r-rsamtools)
7206 ("r-s4vectors" ,r-s4vectors)
7207 ("r-xml" ,r-xml)
7208 ("r-xvector" ,r-xvector)))
7209 (home-page "http://bioconductor.org/packages/rtracklayer")
7210 (synopsis "R interface to genome browsers and their annotation tracks")
7211 (description
7212 "rtracklayer is an extensible framework for interacting with multiple
7213 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7214 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7215 built-in). The user may export/import tracks to/from the supported browsers,
7216 as well as query and modify the browser state, such as the current viewport.")
7217 (license license:artistic2.0)))
7218
7219 (define-public r-genomicfeatures
7220 (package
7221 (name "r-genomicfeatures")
7222 (version "1.28.4")
7223 (source (origin
7224 (method url-fetch)
7225 (uri (bioconductor-uri "GenomicFeatures" version))
7226 (sha256
7227 (base32
7228 "01ylvg275iy0cvsbxkbfxcf9pi9al597v5wnlqi2xdpmrcxyc3q0"))))
7229 (properties
7230 `((upstream-name . "GenomicFeatures")))
7231 (build-system r-build-system)
7232 (propagated-inputs
7233 `(("r-annotationdbi" ,r-annotationdbi)
7234 ("r-biobase" ,r-biobase)
7235 ("r-biocgenerics" ,r-biocgenerics)
7236 ("r-biomart" ,r-biomart)
7237 ("r-biostrings" ,r-biostrings)
7238 ("r-dbi" ,r-dbi)
7239 ("r-genomeinfodb" ,r-genomeinfodb)
7240 ("r-genomicranges" ,r-genomicranges)
7241 ("r-iranges" ,r-iranges)
7242 ("r-rcurl" ,r-rcurl)
7243 ("r-rsqlite" ,r-rsqlite)
7244 ("r-rtracklayer" ,r-rtracklayer)
7245 ("r-s4vectors" ,r-s4vectors)
7246 ("r-xvector" ,r-xvector)))
7247 (home-page "http://bioconductor.org/packages/GenomicFeatures")
7248 (synopsis "Tools for working with transcript centric annotations")
7249 (description
7250 "This package provides a set of tools and methods for making and
7251 manipulating transcript centric annotations. With these tools the user can
7252 easily download the genomic locations of the transcripts, exons and cds of a
7253 given organism, from either the UCSC Genome Browser or a BioMart
7254 database (more sources will be supported in the future). This information is
7255 then stored in a local database that keeps track of the relationship between
7256 transcripts, exons, cds and genes. Flexible methods are provided for
7257 extracting the desired features in a convenient format.")
7258 (license license:artistic2.0)))
7259
7260 (define-public r-go-db
7261 (package
7262 (name "r-go-db")
7263 (version "3.4.0")
7264 (source (origin
7265 (method url-fetch)
7266 (uri (string-append "http://www.bioconductor.org/packages/"
7267 "release/data/annotation/src/contrib/GO.db_"
7268 version ".tar.gz"))
7269 (sha256
7270 (base32
7271 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
7272 (properties
7273 `((upstream-name . "GO.db")))
7274 (build-system r-build-system)
7275 (propagated-inputs
7276 `(("r-annotationdbi" ,r-annotationdbi)))
7277 (home-page "http://bioconductor.org/packages/GO.db")
7278 (synopsis "Annotation maps describing the entire Gene Ontology")
7279 (description
7280 "The purpose of this GO.db annotation package is to provide detailed
7281 information about the latest version of the Gene Ontologies.")
7282 (license license:artistic2.0)))
7283
7284 (define-public r-graph
7285 (package
7286 (name "r-graph")
7287 (version "1.54.0")
7288 (source (origin
7289 (method url-fetch)
7290 (uri (bioconductor-uri "graph" version))
7291 (sha256
7292 (base32
7293 "0hx9wslnrci7c5i1gd1zlpjmgrkdnx9gabfgmzzwfnykk1mdvvna"))))
7294 (build-system r-build-system)
7295 (propagated-inputs
7296 `(("r-biocgenerics" ,r-biocgenerics)))
7297 (home-page "http://bioconductor.org/packages/graph")
7298 (synopsis "Handle graph data structures in R")
7299 (description
7300 "This package implements some simple graph handling capabilities for R.")
7301 (license license:artistic2.0)))
7302
7303 (define-public r-topgo
7304 (package
7305 (name "r-topgo")
7306 (version "2.28.0")
7307 (source (origin
7308 (method url-fetch)
7309 (uri (bioconductor-uri "topGO" version))
7310 (sha256
7311 (base32
7312 "04kvxz9qsxfz0np7wlrzp4r95nykz94x7mqpyyk76f90g6m66vcc"))))
7313 (properties
7314 `((upstream-name . "topGO")))
7315 (build-system r-build-system)
7316 (propagated-inputs
7317 `(("r-annotationdbi" ,r-annotationdbi)
7318 ("r-dbi" ,r-dbi)
7319 ("r-biobase" ,r-biobase)
7320 ("r-biocgenerics" ,r-biocgenerics)
7321 ("r-go-db" ,r-go-db)
7322 ("r-graph" ,r-graph)
7323 ("r-lattice" ,r-lattice)
7324 ("r-matrixstats" ,r-matrixstats)
7325 ("r-sparsem" ,r-sparsem)))
7326 (home-page "http://bioconductor.org/packages/topGO")
7327 (synopsis "Enrichment analysis for gene ontology")
7328 (description
7329 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7330 terms while accounting for the topology of the GO graph. Different test
7331 statistics and different methods for eliminating local similarities and
7332 dependencies between GO terms can be implemented and applied.")
7333 ;; Any version of the LGPL applies.
7334 (license license:lgpl2.1+)))
7335
7336 (define-public r-bsgenome
7337 (package
7338 (name "r-bsgenome")
7339 (version "1.44.0")
7340 (source (origin
7341 (method url-fetch)
7342 (uri (bioconductor-uri "BSgenome" version))
7343 (sha256
7344 (base32
7345 "18dlknwk3xvi52hamxf9pl5bjc5806mpw98xwvx5xajn8mrxiy5h"))))
7346 (properties
7347 `((upstream-name . "BSgenome")))
7348 (build-system r-build-system)
7349 (propagated-inputs
7350 `(("r-biocgenerics" ,r-biocgenerics)
7351 ("r-biostrings" ,r-biostrings)
7352 ("r-genomeinfodb" ,r-genomeinfodb)
7353 ("r-genomicranges" ,r-genomicranges)
7354 ("r-iranges" ,r-iranges)
7355 ("r-rsamtools" ,r-rsamtools)
7356 ("r-rtracklayer" ,r-rtracklayer)
7357 ("r-s4vectors" ,r-s4vectors)
7358 ("r-xvector" ,r-xvector)))
7359 (home-page "http://bioconductor.org/packages/BSgenome")
7360 (synopsis "Infrastructure for Biostrings-based genome data packages")
7361 (description
7362 "This package provides infrastructure shared by all Biostrings-based
7363 genome data packages and support for efficient SNP representation.")
7364 (license license:artistic2.0)))
7365
7366 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7367 (package
7368 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7369 (version "0.99.1")
7370 (source (origin
7371 (method url-fetch)
7372 ;; We cannot use bioconductor-uri here because this tarball is
7373 ;; located under "data/annotation/" instead of "bioc/".
7374 (uri (string-append "http://www.bioconductor.org/packages/"
7375 "release/data/annotation/src/contrib/"
7376 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7377 version ".tar.gz"))
7378 (sha256
7379 (base32
7380 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7381 (properties
7382 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7383 (build-system r-build-system)
7384 ;; As this package provides little more than a very large data file it
7385 ;; doesn't make sense to build substitutes.
7386 (arguments `(#:substitutable? #f))
7387 (propagated-inputs
7388 `(("r-bsgenome" ,r-bsgenome)))
7389 (home-page
7390 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7391 (synopsis "Full genome sequences for Homo sapiens")
7392 (description
7393 "This package provides full genome sequences for Homo sapiens from
7394 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7395 (license license:artistic2.0)))
7396
7397 (define-public r-impute
7398 (package
7399 (name "r-impute")
7400 (version "1.50.0")
7401 (source (origin
7402 (method url-fetch)
7403 (uri (bioconductor-uri "impute" version))
7404 (sha256
7405 (base32
7406 "0va45vfixy3np549md87h3b3rbavm54gfnmnjhpr9hf02lll6zxs"))))
7407 (inputs
7408 `(("gfortran" ,gfortran)))
7409 (build-system r-build-system)
7410 (home-page "http://bioconductor.org/packages/impute")
7411 (synopsis "Imputation for microarray data")
7412 (description
7413 "This package provides a function to impute missing gene expression
7414 microarray data, using nearest neighbor averaging.")
7415 (license license:gpl2+)))
7416
7417 (define-public r-seqpattern
7418 (package
7419 (name "r-seqpattern")
7420 (version "1.8.0")
7421 (source (origin
7422 (method url-fetch)
7423 (uri (bioconductor-uri "seqPattern" version))
7424 (sha256
7425 (base32
7426 "0yw5251sirv3283xgmfmfbf900xp8dwvqfk88mr945s3by5hx99v"))))
7427 (properties
7428 `((upstream-name . "seqPattern")))
7429 (build-system r-build-system)
7430 (propagated-inputs
7431 `(("r-biostrings" ,r-biostrings)
7432 ("r-genomicranges" ,r-genomicranges)
7433 ("r-iranges" ,r-iranges)
7434 ("r-kernsmooth" ,r-kernsmooth)
7435 ("r-plotrix" ,r-plotrix)))
7436 (home-page "http://bioconductor.org/packages/seqPattern")
7437 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7438 (description
7439 "This package provides tools to visualize oligonucleotide patterns and
7440 sequence motif occurrences across a large set of sequences centred at a common
7441 reference point and sorted by a user defined feature.")
7442 (license license:gpl3+)))
7443
7444 (define-public r-genomation
7445 (package
7446 (name "r-genomation")
7447 (version "1.8.0")
7448 (source (origin
7449 (method url-fetch)
7450 (uri (bioconductor-uri "genomation" version))
7451 (sha256
7452 (base32
7453 "0r71nf8p3aq3yffqxg4yir1zmm7rar5a57nmy1kpqpn8kaf2svjl"))))
7454 (build-system r-build-system)
7455 (propagated-inputs
7456 `(("r-biostrings" ,r-biostrings)
7457 ("r-bsgenome" ,r-bsgenome)
7458 ("r-data-table" ,r-data-table)
7459 ("r-genomeinfodb" ,r-genomeinfodb)
7460 ("r-genomicalignments" ,r-genomicalignments)
7461 ("r-genomicranges" ,r-genomicranges)
7462 ("r-ggplot2" ,r-ggplot2)
7463 ("r-gridbase" ,r-gridbase)
7464 ("r-impute" ,r-impute)
7465 ("r-iranges" ,r-iranges)
7466 ("r-matrixstats" ,r-matrixstats)
7467 ("r-plotrix" ,r-plotrix)
7468 ("r-plyr" ,r-plyr)
7469 ("r-rcpp" ,r-rcpp)
7470 ("r-readr" ,r-readr)
7471 ("r-reshape2" ,r-reshape2)
7472 ("r-rhtslib" ,r-rhtslib)
7473 ("r-rsamtools" ,r-rsamtools)
7474 ("r-rtracklayer" ,r-rtracklayer)
7475 ("r-runit" ,r-runit)
7476 ("r-s4vectors" ,r-s4vectors)
7477 ("r-seqpattern" ,r-seqpattern)))
7478 (inputs
7479 `(("zlib" ,zlib)))
7480 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7481 (synopsis "Summary, annotation and visualization of genomic data")
7482 (description
7483 "This package provides a package for summary and annotation of genomic
7484 intervals. Users can visualize and quantify genomic intervals over
7485 pre-defined functional regions, such as promoters, exons, introns, etc. The
7486 genomic intervals represent regions with a defined chromosome position, which
7487 may be associated with a score, such as aligned reads from HT-seq experiments,
7488 TF binding sites, methylation scores, etc. The package can use any tabular
7489 genomic feature data as long as it has minimal information on the locations of
7490 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7491 (license license:artistic2.0)))
7492
7493 (define-public r-genomationdata
7494 (package
7495 (name "r-genomationdata")
7496 (version "1.6.0")
7497 (source (origin
7498 (method url-fetch)
7499 ;; We cannot use bioconductor-uri here because this tarball is
7500 ;; located under "data/annotation/" instead of "bioc/".
7501 (uri (string-append "https://bioconductor.org/packages/"
7502 "release/data/experiment/src/contrib/"
7503 "genomationData_" version ".tar.gz"))
7504 (sha256
7505 (base32
7506 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7507 (build-system r-build-system)
7508 ;; As this package provides little more than large data files, it doesn't
7509 ;; make sense to build substitutes.
7510 (arguments `(#:substitutable? #f))
7511 (native-inputs
7512 `(("r-knitr" ,r-knitr)))
7513 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7514 (synopsis "Experimental data for use with the genomation package")
7515 (description
7516 "This package contains experimental genetic data for use with the
7517 genomation package. Included are Chip Seq, Methylation and Cage data,
7518 downloaded from Encode.")
7519 (license license:gpl3+)))
7520
7521 (define-public r-org-hs-eg-db
7522 (package
7523 (name "r-org-hs-eg-db")
7524 (version "3.4.0")
7525 (source (origin
7526 (method url-fetch)
7527 ;; We cannot use bioconductor-uri here because this tarball is
7528 ;; located under "data/annotation/" instead of "bioc/".
7529 (uri (string-append "http://www.bioconductor.org/packages/"
7530 "release/data/annotation/src/contrib/"
7531 "org.Hs.eg.db_" version ".tar.gz"))
7532 (sha256
7533 (base32
7534 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7535 (properties
7536 `((upstream-name . "org.Hs.eg.db")))
7537 (build-system r-build-system)
7538 (propagated-inputs
7539 `(("r-annotationdbi" ,r-annotationdbi)))
7540 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
7541 (synopsis "Genome wide annotation for Human")
7542 (description
7543 "This package provides mappings from Entrez gene identifiers to various
7544 annotations for the human genome.")
7545 (license license:artistic2.0)))
7546
7547 (define-public r-org-ce-eg-db
7548 (package
7549 (name "r-org-ce-eg-db")
7550 (version "3.4.0")
7551 (source (origin
7552 (method url-fetch)
7553 ;; We cannot use bioconductor-uri here because this tarball is
7554 ;; located under "data/annotation/" instead of "bioc/".
7555 (uri (string-append "http://www.bioconductor.org/packages/"
7556 "release/data/annotation/src/contrib/"
7557 "org.Ce.eg.db_" version ".tar.gz"))
7558 (sha256
7559 (base32
7560 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7561 (properties
7562 `((upstream-name . "org.Ce.eg.db")))
7563 (build-system r-build-system)
7564 (propagated-inputs
7565 `(("r-annotationdbi" ,r-annotationdbi)))
7566 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
7567 (synopsis "Genome wide annotation for Worm")
7568 (description
7569 "This package provides mappings from Entrez gene identifiers to various
7570 annotations for the genome of the model worm Caenorhabditis elegans.")
7571 (license license:artistic2.0)))
7572
7573 (define-public r-org-dm-eg-db
7574 (package
7575 (name "r-org-dm-eg-db")
7576 (version "3.4.0")
7577 (source (origin
7578 (method url-fetch)
7579 ;; We cannot use bioconductor-uri here because this tarball is
7580 ;; located under "data/annotation/" instead of "bioc/".
7581 (uri (string-append "http://www.bioconductor.org/packages/"
7582 "release/data/annotation/src/contrib/"
7583 "org.Dm.eg.db_" version ".tar.gz"))
7584 (sha256
7585 (base32
7586 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7587 (properties
7588 `((upstream-name . "org.Dm.eg.db")))
7589 (build-system r-build-system)
7590 (propagated-inputs
7591 `(("r-annotationdbi" ,r-annotationdbi)))
7592 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
7593 (synopsis "Genome wide annotation for Fly")
7594 (description
7595 "This package provides mappings from Entrez gene identifiers to various
7596 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7597 (license license:artistic2.0)))
7598
7599 (define-public r-org-mm-eg-db
7600 (package
7601 (name "r-org-mm-eg-db")
7602 (version "3.4.0")
7603 (source (origin
7604 (method url-fetch)
7605 ;; We cannot use bioconductor-uri here because this tarball is
7606 ;; located under "data/annotation/" instead of "bioc/".
7607 (uri (string-append "http://www.bioconductor.org/packages/"
7608 "release/data/annotation/src/contrib/"
7609 "org.Mm.eg.db_" version ".tar.gz"))
7610 (sha256
7611 (base32
7612 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7613 (properties
7614 `((upstream-name . "org.Mm.eg.db")))
7615 (build-system r-build-system)
7616 (propagated-inputs
7617 `(("r-annotationdbi" ,r-annotationdbi)))
7618 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
7619 (synopsis "Genome wide annotation for Mouse")
7620 (description
7621 "This package provides mappings from Entrez gene identifiers to various
7622 annotations for the genome of the model mouse Mus musculus.")
7623 (license license:artistic2.0)))
7624
7625 (define-public r-seqlogo
7626 (package
7627 (name "r-seqlogo")
7628 (version "1.42.0")
7629 (source
7630 (origin
7631 (method url-fetch)
7632 (uri (bioconductor-uri "seqLogo" version))
7633 (sha256
7634 (base32
7635 "19d5zmy7m8svljwgbmrb4vxkq18slq0f3all6k2ayv42b8w44h6q"))))
7636 (properties `((upstream-name . "seqLogo")))
7637 (build-system r-build-system)
7638 (home-page "http://bioconductor.org/packages/seqLogo")
7639 (synopsis "Sequence logos for DNA sequence alignments")
7640 (description
7641 "seqLogo takes the position weight matrix of a DNA sequence motif and
7642 plots the corresponding sequence logo as introduced by Schneider and
7643 Stephens (1990).")
7644 (license license:lgpl2.0+)))
7645
7646 (define-public r-bsgenome-hsapiens-ucsc-hg19
7647 (package
7648 (name "r-bsgenome-hsapiens-ucsc-hg19")
7649 (version "1.4.0")
7650 (source (origin
7651 (method url-fetch)
7652 ;; We cannot use bioconductor-uri here because this tarball is
7653 ;; located under "data/annotation/" instead of "bioc/".
7654 (uri (string-append "http://www.bioconductor.org/packages/"
7655 "release/data/annotation/src/contrib/"
7656 "BSgenome.Hsapiens.UCSC.hg19_"
7657 version ".tar.gz"))
7658 (sha256
7659 (base32
7660 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7661 (properties
7662 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7663 (build-system r-build-system)
7664 ;; As this package provides little more than a very large data file it
7665 ;; doesn't make sense to build substitutes.
7666 (arguments `(#:substitutable? #f))
7667 (propagated-inputs
7668 `(("r-bsgenome" ,r-bsgenome)))
7669 (home-page
7670 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7671 (synopsis "Full genome sequences for Homo sapiens")
7672 (description
7673 "This package provides full genome sequences for Homo sapiens as provided
7674 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7675 (license license:artistic2.0)))
7676
7677 (define-public r-bsgenome-mmusculus-ucsc-mm9
7678 (package
7679 (name "r-bsgenome-mmusculus-ucsc-mm9")
7680 (version "1.4.0")
7681 (source (origin
7682 (method url-fetch)
7683 ;; We cannot use bioconductor-uri here because this tarball is
7684 ;; located under "data/annotation/" instead of "bioc/".
7685 (uri (string-append "http://www.bioconductor.org/packages/"
7686 "release/data/annotation/src/contrib/"
7687 "BSgenome.Mmusculus.UCSC.mm9_"
7688 version ".tar.gz"))
7689 (sha256
7690 (base32
7691 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7692 (properties
7693 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7694 (build-system r-build-system)
7695 ;; As this package provides little more than a very large data file it
7696 ;; doesn't make sense to build substitutes.
7697 (arguments `(#:substitutable? #f))
7698 (propagated-inputs
7699 `(("r-bsgenome" ,r-bsgenome)))
7700 (home-page
7701 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7702 (synopsis "Full genome sequences for Mouse")
7703 (description
7704 "This package provides full genome sequences for Mus musculus (Mouse) as
7705 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7706 (license license:artistic2.0)))
7707
7708 (define-public r-bsgenome-mmusculus-ucsc-mm10
7709 (package
7710 (name "r-bsgenome-mmusculus-ucsc-mm10")
7711 (version "1.4.0")
7712 (source (origin
7713 (method url-fetch)
7714 ;; We cannot use bioconductor-uri here because this tarball is
7715 ;; located under "data/annotation/" instead of "bioc/".
7716 (uri (string-append "http://www.bioconductor.org/packages/"
7717 "release/data/annotation/src/contrib/"
7718 "BSgenome.Mmusculus.UCSC.mm10_"
7719 version ".tar.gz"))
7720 (sha256
7721 (base32
7722 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7723 (properties
7724 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7725 (build-system r-build-system)
7726 ;; As this package provides little more than a very large data file it
7727 ;; doesn't make sense to build substitutes.
7728 (arguments `(#:substitutable? #f))
7729 (propagated-inputs
7730 `(("r-bsgenome" ,r-bsgenome)))
7731 (home-page
7732 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7733 (synopsis "Full genome sequences for Mouse")
7734 (description
7735 "This package provides full genome sequences for Mus
7736 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7737 in Biostrings objects.")
7738 (license license:artistic2.0)))
7739
7740 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7741 (package
7742 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7743 (version "3.4.0")
7744 (source (origin
7745 (method url-fetch)
7746 ;; We cannot use bioconductor-uri here because this tarball is
7747 ;; located under "data/annotation/" instead of "bioc/".
7748 (uri (string-append "http://www.bioconductor.org/packages/"
7749 "release/data/annotation/src/contrib/"
7750 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7751 version ".tar.gz"))
7752 (sha256
7753 (base32
7754 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7755 (properties
7756 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7757 (build-system r-build-system)
7758 ;; As this package provides little more than a very large data file it
7759 ;; doesn't make sense to build substitutes.
7760 (arguments `(#:substitutable? #f))
7761 (propagated-inputs
7762 `(("r-bsgenome" ,r-bsgenome)
7763 ("r-genomicfeatures" ,r-genomicfeatures)
7764 ("r-annotationdbi" ,r-annotationdbi)))
7765 (home-page
7766 "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7767 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7768 (description
7769 "This package loads a TxDb object, which is an R interface to
7770 prefabricated databases contained in this package. This package provides
7771 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7772 based on the knownGene track.")
7773 (license license:artistic2.0)))
7774
7775 (define-public r-bsgenome-celegans-ucsc-ce6
7776 (package
7777 (name "r-bsgenome-celegans-ucsc-ce6")
7778 (version "1.4.0")
7779 (source (origin
7780 (method url-fetch)
7781 ;; We cannot use bioconductor-uri here because this tarball is
7782 ;; located under "data/annotation/" instead of "bioc/".
7783 (uri (string-append "http://www.bioconductor.org/packages/"
7784 "release/data/annotation/src/contrib/"
7785 "BSgenome.Celegans.UCSC.ce6_"
7786 version ".tar.gz"))
7787 (sha256
7788 (base32
7789 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7790 (properties
7791 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7792 (build-system r-build-system)
7793 ;; As this package provides little more than a very large data file it
7794 ;; doesn't make sense to build substitutes.
7795 (arguments `(#:substitutable? #f))
7796 (propagated-inputs
7797 `(("r-bsgenome" ,r-bsgenome)))
7798 (home-page
7799 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7800 (synopsis "Full genome sequences for Worm")
7801 (description
7802 "This package provides full genome sequences for Caenorhabditis
7803 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7804 objects.")
7805 (license license:artistic2.0)))
7806
7807 (define-public r-bsgenome-celegans-ucsc-ce10
7808 (package
7809 (name "r-bsgenome-celegans-ucsc-ce10")
7810 (version "1.4.0")
7811 (source (origin
7812 (method url-fetch)
7813 ;; We cannot use bioconductor-uri here because this tarball is
7814 ;; located under "data/annotation/" instead of "bioc/".
7815 (uri (string-append "http://www.bioconductor.org/packages/"
7816 "release/data/annotation/src/contrib/"
7817 "BSgenome.Celegans.UCSC.ce10_"
7818 version ".tar.gz"))
7819 (sha256
7820 (base32
7821 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7822 (properties
7823 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7824 (build-system r-build-system)
7825 ;; As this package provides little more than a very large data file it
7826 ;; doesn't make sense to build substitutes.
7827 (arguments `(#:substitutable? #f))
7828 (propagated-inputs
7829 `(("r-bsgenome" ,r-bsgenome)))
7830 (home-page
7831 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7832 (synopsis "Full genome sequences for Worm")
7833 (description
7834 "This package provides full genome sequences for Caenorhabditis
7835 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7836 objects.")
7837 (license license:artistic2.0)))
7838
7839 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7840 (package
7841 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7842 (version "1.4.0")
7843 (source (origin
7844 (method url-fetch)
7845 ;; We cannot use bioconductor-uri here because this tarball is
7846 ;; located under "data/annotation/" instead of "bioc/".
7847 (uri (string-append "http://www.bioconductor.org/packages/"
7848 "release/data/annotation/src/contrib/"
7849 "BSgenome.Dmelanogaster.UCSC.dm3_"
7850 version ".tar.gz"))
7851 (sha256
7852 (base32
7853 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7854 (properties
7855 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7856 (build-system r-build-system)
7857 ;; As this package provides little more than a very large data file it
7858 ;; doesn't make sense to build substitutes.
7859 (arguments `(#:substitutable? #f))
7860 (propagated-inputs
7861 `(("r-bsgenome" ,r-bsgenome)))
7862 (home-page
7863 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7864 (synopsis "Full genome sequences for Fly")
7865 (description
7866 "This package provides full genome sequences for Drosophila
7867 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7868 Biostrings objects.")
7869 (license license:artistic2.0)))
7870
7871 (define-public r-motifrg
7872 (package
7873 (name "r-motifrg")
7874 (version "1.20.0")
7875 (source
7876 (origin
7877 (method url-fetch)
7878 (uri (bioconductor-uri "motifRG" version))
7879 (sha256
7880 (base32
7881 "0lxxpqyljiyk73vyq6ss46q13g81pm24q87mkzdsqlr5zx427ch6"))))
7882 (properties `((upstream-name . "motifRG")))
7883 (build-system r-build-system)
7884 (propagated-inputs
7885 `(("r-biostrings" ,r-biostrings)
7886 ("r-bsgenome" ,r-bsgenome)
7887 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7888 ("r-iranges" ,r-iranges)
7889 ("r-seqlogo" ,r-seqlogo)
7890 ("r-xvector" ,r-xvector)))
7891 (home-page "http://bioconductor.org/packages/motifRG")
7892 (synopsis "Discover motifs in high throughput sequencing data")
7893 (description
7894 "This package provides tools for discriminative motif discovery in high
7895 throughput genetic sequencing data sets using regression methods.")
7896 (license license:artistic2.0)))
7897
7898 (define-public r-qtl
7899 (package
7900 (name "r-qtl")
7901 (version "1.41-6")
7902 (source
7903 (origin
7904 (method url-fetch)
7905 (uri (string-append "mirror://cran/src/contrib/qtl_"
7906 version ".tar.gz"))
7907 (sha256
7908 (base32
7909 "067az4v432zxp6lxck8d7vlh9w4r13r0mvw5zsglyaqwsh3d9sad"))))
7910 (build-system r-build-system)
7911 (home-page "http://rqtl.org/")
7912 (synopsis "R package for analyzing QTL experiments in genetics")
7913 (description "R/qtl is an extension library for the R statistics
7914 system. It is used to analyze experimental crosses for identifying
7915 genes contributing to variation in quantitative traits (so-called
7916 quantitative trait loci, QTLs).
7917
7918 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7919 identify genotyping errors, and to perform single-QTL and two-QTL,
7920 two-dimensional genome scans.")
7921 (license license:gpl3)))
7922
7923 (define-public r-zlibbioc
7924 (package
7925 (name "r-zlibbioc")
7926 (version "1.22.0")
7927 (source (origin
7928 (method url-fetch)
7929 (uri (bioconductor-uri "zlibbioc" version))
7930 (sha256
7931 (base32
7932 "1kdgwwlh39mgwzj3zq71za4iv40sq625ghnyrndv5wrivrcr2igv"))))
7933 (properties
7934 `((upstream-name . "zlibbioc")))
7935 (build-system r-build-system)
7936 (home-page "https://bioconductor.org/packages/zlibbioc")
7937 (synopsis "Provider for zlib-1.2.5 to R packages")
7938 (description "This package uses the source code of zlib-1.2.5 to create
7939 libraries for systems that do not have these available via other means.")
7940 (license license:artistic2.0)))
7941
7942 (define-public r-r4rna
7943 (package
7944 (name "r-r4rna")
7945 (version "0.1.4")
7946 (source
7947 (origin
7948 (method url-fetch)
7949 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7950 version ".tar.gz"))
7951 (sha256
7952 (base32
7953 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7954 (build-system r-build-system)
7955 (propagated-inputs
7956 `(("r-optparse" ,r-optparse)
7957 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7958 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7959 (synopsis "Analysis framework for RNA secondary structure")
7960 (description
7961 "The R4RNA package aims to be a general framework for the analysis of RNA
7962 secondary structure and comparative analysis in R.")
7963 (license license:gpl3+)))
7964
7965 (define-public r-rhtslib
7966 (package
7967 (name "r-rhtslib")
7968 (version "1.8.0")
7969 (source
7970 (origin
7971 (method url-fetch)
7972 (uri (bioconductor-uri "Rhtslib" version))
7973 (sha256
7974 (base32
7975 "0jj5h81z5gyf4j3lp2l3zsm6pgbmalgrngr8qdpygc20phndpp0b"))))
7976 (properties `((upstream-name . "Rhtslib")))
7977 (build-system r-build-system)
7978 (propagated-inputs
7979 `(("r-zlibbioc" ,r-zlibbioc)))
7980 (inputs
7981 `(("zlib" ,zlib)))
7982 (native-inputs
7983 `(("autoconf" ,autoconf)))
7984 (home-page "https://github.com/nhayden/Rhtslib")
7985 (synopsis "High-throughput sequencing library as an R package")
7986 (description
7987 "This package provides the HTSlib C library for high-throughput
7988 nucleotide sequence analysis. The package is primarily useful to developers
7989 of other R packages who wish to make use of HTSlib.")
7990 (license license:lgpl2.0+)))
7991
7992 (define-public r-bamsignals
7993 (package
7994 (name "r-bamsignals")
7995 (version "1.8.0")
7996 (source
7997 (origin
7998 (method url-fetch)
7999 (uri (bioconductor-uri "bamsignals" version))
8000 (sha256
8001 (base32
8002 "0knx69zzdaak2sjim8k9mygmcjxpa705m8013ld5zwpgi8dag9mc"))))
8003 (build-system r-build-system)
8004 (propagated-inputs
8005 `(("r-biocgenerics" ,r-biocgenerics)
8006 ("r-genomicranges" ,r-genomicranges)
8007 ("r-iranges" ,r-iranges)
8008 ("r-rcpp" ,r-rcpp)
8009 ("r-rhtslib" ,r-rhtslib)
8010 ("r-zlibbioc" ,r-zlibbioc)))
8011 (inputs
8012 `(("zlib" ,zlib)))
8013 (home-page "http://bioconductor.org/packages/bamsignals")
8014 (synopsis "Extract read count signals from bam files")
8015 (description
8016 "This package allows to efficiently obtain count vectors from indexed bam
8017 files. It counts the number of nucleotide sequence reads in given genomic
8018 ranges and it computes reads profiles and coverage profiles. It also handles
8019 paired-end data.")
8020 (license license:gpl2+)))
8021
8022 (define-public r-rcas
8023 (package
8024 (name "r-rcas")
8025 (version "1.3.4")
8026 (source (origin
8027 (method url-fetch)
8028 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8029 version ".tar.gz"))
8030 (file-name (string-append name "-" version ".tar.gz"))
8031 (sha256
8032 (base32
8033 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8034 (build-system r-build-system)
8035 (native-inputs
8036 `(("r-knitr" ,r-knitr)
8037 ("r-testthat" ,r-testthat)
8038 ;; During vignette building knitr checks that "pandoc-citeproc"
8039 ;; is in the PATH.
8040 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8041 (propagated-inputs
8042 `(("r-data-table" ,r-data-table)
8043 ("r-biomart" ,r-biomart)
8044 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8045 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8046 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8047 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8048 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8049 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8050 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8051 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8052 ("r-topgo" ,r-topgo)
8053 ("r-dt" ,r-dt)
8054 ("r-pbapply" ,r-pbapply)
8055 ("r-plotly" ,r-plotly)
8056 ("r-plotrix" ,r-plotrix)
8057 ("r-motifrg" ,r-motifrg)
8058 ("r-genomation" ,r-genomation)
8059 ("r-genomicfeatures" ,r-genomicfeatures)
8060 ("r-rtracklayer" ,r-rtracklayer)
8061 ("r-rmarkdown" ,r-rmarkdown)))
8062 (synopsis "RNA-centric annotation system")
8063 (description
8064 "RCAS aims to be a standalone RNA-centric annotation system that provides
8065 intuitive reports and publication-ready graphics. This package provides the R
8066 library implementing most of the pipeline's features.")
8067 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8068 (license license:artistic2.0)))
8069
8070 (define-public rcas-web
8071 (package
8072 (name "rcas-web")
8073 (version "0.0.3")
8074 (source
8075 (origin
8076 (method url-fetch)
8077 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8078 "releases/download/v" version
8079 "/rcas-web-" version ".tar.gz"))
8080 (sha256
8081 (base32
8082 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
8083 (build-system gnu-build-system)
8084 (arguments
8085 `(#:phases
8086 (modify-phases %standard-phases
8087 (add-after 'install 'wrap-executable
8088 (lambda* (#:key inputs outputs #:allow-other-keys)
8089 (let* ((out (assoc-ref outputs "out"))
8090 (json (assoc-ref inputs "guile-json"))
8091 (redis (assoc-ref inputs "guile-redis"))
8092 (path (string-append
8093 json "/share/guile/site/2.2:"
8094 redis "/share/guile/site/2.2")))
8095 (wrap-program (string-append out "/bin/rcas-web")
8096 `("GUILE_LOAD_PATH" ":" = (,path))
8097 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8098 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8099 #t)))))
8100 (inputs
8101 `(("r-minimal" ,r-minimal)
8102 ("r-rcas" ,r-rcas)
8103 ("guile-next" ,guile-2.2)
8104 ("guile-json" ,guile-json)
8105 ("guile-redis" ,guile2.2-redis)))
8106 (native-inputs
8107 `(("pkg-config" ,pkg-config)))
8108 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8109 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8110 (description "This package provides a simple web interface for the
8111 @dfn{RNA-centric annotation system} (RCAS).")
8112 (license license:agpl3+)))
8113
8114 (define-public r-mutationalpatterns
8115 (package
8116 (name "r-mutationalpatterns")
8117 (version "1.2.1")
8118 (source
8119 (origin
8120 (method url-fetch)
8121 (uri (bioconductor-uri "MutationalPatterns" version))
8122 (sha256
8123 (base32
8124 "1s50diwh1j6vg3mgahh6bczvq74mfdbmwjrad4d5lh723gnc5pjg"))))
8125 (build-system r-build-system)
8126 (propagated-inputs
8127 `(("r-biocgenerics" ,r-biocgenerics)
8128 ("r-biostrings" ,r-biostrings)
8129 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8130 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8131 ("r-genomicranges" ,r-genomicranges)
8132 ("r-genomeinfodb" ,r-genomeinfodb)
8133 ("r-ggplot2" ,r-ggplot2)
8134 ("r-gridextra" ,r-gridextra)
8135 ("r-iranges" ,r-iranges)
8136 ("r-nmf" ,r-nmf)
8137 ("r-plyr" ,r-plyr)
8138 ("r-pracma" ,r-pracma)
8139 ("r-reshape2" ,r-reshape2)
8140 ("r-summarizedexperiment" ,r-summarizedexperiment)
8141 ("r-variantannotation" ,r-variantannotation)))
8142 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
8143 (synopsis "Extract and visualize mutational patterns in genomic data")
8144 (description "This package provides an extensive toolset for the
8145 characterization and visualization of a wide range of mutational patterns
8146 in SNV base substitution data.")
8147 (license license:expat)))
8148
8149 (define-public r-wgcna
8150 (package
8151 (name "r-wgcna")
8152 (version "1.61")
8153 (source
8154 (origin
8155 (method url-fetch)
8156 (uri (cran-uri "WGCNA" version))
8157 (sha256
8158 (base32
8159 "1vrc2k33a196hrrl7k0z534fp96vv0shmigcr65ny1q0v6lq0h6i"))))
8160 (properties `((upstream-name . "WGCNA")))
8161 (build-system r-build-system)
8162 (propagated-inputs
8163 `(("r-annotationdbi" ,r-annotationdbi)
8164 ("r-doparallel" ,r-doparallel)
8165 ("r-dynamictreecut" ,r-dynamictreecut)
8166 ("r-fastcluster" ,r-fastcluster)
8167 ("r-foreach" ,r-foreach)
8168 ("r-go-db" ,r-go-db)
8169 ("r-hmisc" ,r-hmisc)
8170 ("r-impute" ,r-impute)
8171 ("r-rcpp" ,r-rcpp)
8172 ("r-robust" ,r-robust)
8173 ("r-survival" ,r-survival)
8174 ("r-matrixstats" ,r-matrixstats)
8175 ("r-preprocesscore" ,r-preprocesscore)))
8176 (home-page
8177 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8178 (synopsis "Weighted correlation network analysis")
8179 (description
8180 "This package provides functions necessary to perform Weighted
8181 Correlation Network Analysis on high-dimensional data. It includes functions
8182 for rudimentary data cleaning, construction and summarization of correlation
8183 networks, module identification and functions for relating both variables and
8184 modules to sample traits. It also includes a number of utility functions for
8185 data manipulation and visualization.")
8186 (license license:gpl2+)))
8187
8188 (define-public r-chipkernels
8189 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8190 (revision "1"))
8191 (package
8192 (name "r-chipkernels")
8193 (version (string-append "1.1-" revision "." (string-take commit 9)))
8194 (source
8195 (origin
8196 (method git-fetch)
8197 (uri (git-reference
8198 (url "https://github.com/ManuSetty/ChIPKernels.git")
8199 (commit commit)))
8200 (file-name (string-append name "-" version))
8201 (sha256
8202 (base32
8203 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8204 (build-system r-build-system)
8205 (propagated-inputs
8206 `(("r-iranges" ,r-iranges)
8207 ("r-xvector" ,r-xvector)
8208 ("r-biostrings" ,r-biostrings)
8209 ("r-bsgenome" ,r-bsgenome)
8210 ("r-gtools" ,r-gtools)
8211 ("r-genomicranges" ,r-genomicranges)
8212 ("r-sfsmisc" ,r-sfsmisc)
8213 ("r-kernlab" ,r-kernlab)
8214 ("r-s4vectors" ,r-s4vectors)
8215 ("r-biocgenerics" ,r-biocgenerics)))
8216 (home-page "https://github.com/ManuSetty/ChIPKernels")
8217 (synopsis "Build string kernels for DNA Sequence analysis")
8218 (description "ChIPKernels is an R package for building different string
8219 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8220 must be built and this dictionary can be used for determining kernels for DNA
8221 Sequences.")
8222 (license license:gpl2+))))
8223
8224 (define-public r-seqgl
8225 (package
8226 (name "r-seqgl")
8227 (version "1.1.4")
8228 (source
8229 (origin
8230 (method url-fetch)
8231 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8232 "archive/" version ".tar.gz"))
8233 (file-name (string-append name "-" version ".tar.gz"))
8234 (sha256
8235 (base32
8236 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8237 (build-system r-build-system)
8238 (propagated-inputs
8239 `(("r-biostrings" ,r-biostrings)
8240 ("r-chipkernels" ,r-chipkernels)
8241 ("r-genomicranges" ,r-genomicranges)
8242 ("r-spams" ,r-spams)
8243 ("r-wgcna" ,r-wgcna)
8244 ("r-fastcluster" ,r-fastcluster)))
8245 (home-page "https://github.com/ManuSetty/SeqGL")
8246 (synopsis "Group lasso for Dnase/ChIP-seq data")
8247 (description "SeqGL is a group lasso based algorithm to extract
8248 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8249 This package presents a method which uses group lasso to discriminate between
8250 bound and non bound genomic regions to accurately identify transcription
8251 factors bound at the specific regions.")
8252 (license license:gpl2+)))
8253
8254 (define-public r-gkmsvm
8255 (package
8256 (name "r-gkmsvm")
8257 (version "0.71.0")
8258 (source
8259 (origin
8260 (method url-fetch)
8261 (uri (cran-uri "gkmSVM" version))
8262 (sha256
8263 (base32
8264 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8265 (properties `((upstream-name . "gkmSVM")))
8266 (build-system r-build-system)
8267 (propagated-inputs
8268 `(("r-biocgenerics" ,r-biocgenerics)
8269 ("r-biostrings" ,r-biostrings)
8270 ("r-genomeinfodb" ,r-genomeinfodb)
8271 ("r-genomicranges" ,r-genomicranges)
8272 ("r-iranges" ,r-iranges)
8273 ("r-kernlab" ,r-kernlab)
8274 ("r-rcpp" ,r-rcpp)
8275 ("r-rocr" ,r-rocr)
8276 ("r-rtracklayer" ,r-rtracklayer)
8277 ("r-s4vectors" ,r-s4vectors)
8278 ("r-seqinr" ,r-seqinr)))
8279 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8280 (synopsis "Gapped-kmer support vector machine")
8281 (description
8282 "This R package provides tools for training gapped-kmer SVM classifiers
8283 for DNA and protein sequences. This package supports several sequence
8284 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8285 (license license:gpl2+)))
8286
8287 (define-public r-tximport
8288 (package
8289 (name "r-tximport")
8290 (version "1.4.0")
8291 (source (origin
8292 (method url-fetch)
8293 (uri (bioconductor-uri "tximport" version))
8294 (sha256
8295 (base32
8296 "1mklb02bj4gnbjlmb7vv6k4lr3w9fp3pzli9rddbrwd0y5n8fcpx"))))
8297 (build-system r-build-system)
8298 (home-page "http://bioconductor.org/packages/tximport")
8299 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8300 (description
8301 "This package provides tools to import transcript-level abundance,
8302 estimated counts and transcript lengths, and to summarize them into matrices
8303 for use with downstream gene-level analysis packages. Average transcript
8304 length, weighted by sample-specific transcript abundance estimates, is
8305 provided as a matrix which can be used as an offset for different expression
8306 of gene-level counts.")
8307 (license license:gpl2+)))
8308
8309 (define-public r-rhdf5
8310 (package
8311 (name "r-rhdf5")
8312 (version "2.20.0")
8313 (source (origin
8314 (method url-fetch)
8315 (uri (bioconductor-uri "rhdf5" version))
8316 (sha256
8317 (base32
8318 "1p6f5i6l44phl772a38x9cav2sya37bkqbkjzdc4pmyfzkv1j6hy"))))
8319 (build-system r-build-system)
8320 (arguments
8321 `(#:phases
8322 (modify-phases %standard-phases
8323 (add-after 'unpack 'unpack-smallhdf5
8324 (lambda* (#:key outputs #:allow-other-keys)
8325 (system* "tar" "-xzvf"
8326 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8327 (substitute* "src/Makevars"
8328 (("^.*cd hdf5source &&.*$") "")
8329 (("^.*gunzip -dc hdf5small.tgz.*$") "")
8330 (("^.*rm -rf hdf5.*$") "")
8331 (("^.*mv hdf5source/hdf5 ..*$") ""))
8332 (substitute* "src/hdf5/configure"
8333 (("/bin/mv") "mv"))
8334 #t)))))
8335 (propagated-inputs
8336 `(("r-zlibbioc" ,r-zlibbioc)))
8337 (inputs
8338 `(("perl" ,perl)
8339 ("zlib" ,zlib)))
8340 (home-page "http://bioconductor.org/packages/rhdf5")
8341 (synopsis "HDF5 interface to R")
8342 (description
8343 "This R/Bioconductor package provides an interface between HDF5 and R.
8344 HDF5's main features are the ability to store and access very large and/or
8345 complex datasets and a wide variety of metadata on mass storage (disk) through
8346 a completely portable file format. The rhdf5 package is thus suited for the
8347 exchange of large and/or complex datasets between R and other software
8348 package, and for letting R applications work on datasets that are larger than
8349 the available RAM.")
8350 (license license:artistic2.0)))
8351
8352 (define-public r-annotationfilter
8353 (package
8354 (name "r-annotationfilter")
8355 (version "1.0.0")
8356 (source (origin
8357 (method url-fetch)
8358 (uri (bioconductor-uri "AnnotationFilter" version))
8359 (sha256
8360 (base32
8361 "0pxvswjzwibdfmrkdragxmzcl844z73pmkn82z92wahwa6gjfyi7"))))
8362 (properties
8363 `((upstream-name . "AnnotationFilter")))
8364 (build-system r-build-system)
8365 (propagated-inputs
8366 `(("r-genomicranges" ,r-genomicranges)
8367 ("r-lazyeval" ,r-lazyeval)))
8368 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8369 (synopsis "Facilities for filtering Bioconductor annotation resources")
8370 (description
8371 "This package provides classes and other infrastructure to implement
8372 filters for manipulating Bioconductor annotation resources. The filters are
8373 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8374 (license license:artistic2.0)))
8375
8376 (define-public emboss
8377 (package
8378 (name "emboss")
8379 (version "6.5.7")
8380 (source (origin
8381 (method url-fetch)
8382 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8383 (version-major+minor version) ".0/"
8384 "EMBOSS-" version ".tar.gz"))
8385 (sha256
8386 (base32
8387 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8388 (build-system gnu-build-system)
8389 (arguments
8390 `(#:configure-flags
8391 (list (string-append "--with-hpdf="
8392 (assoc-ref %build-inputs "libharu")))
8393 #:phases
8394 (modify-phases %standard-phases
8395 (add-after 'unpack 'fix-checks
8396 (lambda _
8397 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8398 ;; and zlib, but assume that they are all found at the same
8399 ;; prefix.
8400 (substitute* "configure.in"
8401 (("CHECK_PNGDRIVER")
8402 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8403 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8404 AM_CONDITIONAL(AMPNG, true)"))
8405 #t))
8406 (add-after 'fix-checks 'disable-update-check
8407 (lambda _
8408 ;; At build time there is no connection to the Internet, so
8409 ;; looking for updates will not work.
8410 (substitute* "Makefile.am"
8411 (("\\$\\(bindir\\)/embossupdate") ""))
8412 #t))
8413 (add-after 'disable-update-check 'autogen
8414 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8415 (inputs
8416 `(("perl" ,perl)
8417 ("libpng" ,libpng)
8418 ("gd" ,gd)
8419 ("libx11" ,libx11)
8420 ("libharu" ,libharu)
8421 ("zlib" ,zlib)))
8422 (native-inputs
8423 `(("autoconf" ,autoconf)
8424 ("automake" ,automake)
8425 ("libtool" ,libtool)
8426 ("pkg-config" ,pkg-config)))
8427 (home-page "http://emboss.sourceforge.net")
8428 (synopsis "Molecular biology analysis suite")
8429 (description "EMBOSS is the \"European Molecular Biology Open Software
8430 Suite\". EMBOSS is an analysis package specially developed for the needs of
8431 the molecular biology (e.g. EMBnet) user community. The software
8432 automatically copes with data in a variety of formats and even allows
8433 transparent retrieval of sequence data from the web. It also provides a
8434 number of libraries for the development of software in the field of molecular
8435 biology. EMBOSS also integrates a range of currently available packages and
8436 tools for sequence analysis into a seamless whole.")
8437 (license license:gpl2+)))
8438
8439 (define-public bits
8440 (let ((revision "1")
8441 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8442 (package
8443 (name "bits")
8444 ;; The version is 2.13.0 even though no release archives have been
8445 ;; published as yet.
8446 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8447 (source (origin
8448 (method git-fetch)
8449 (uri (git-reference
8450 (url "https://github.com/arq5x/bits.git")
8451 (commit commit)))
8452 (file-name (string-append name "-" version "-checkout"))
8453 (sha256
8454 (base32
8455 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8456 (build-system gnu-build-system)
8457 (arguments
8458 `(#:tests? #f ;no tests included
8459 #:phases
8460 (modify-phases %standard-phases
8461 (delete 'configure)
8462 (add-after 'unpack 'remove-cuda
8463 (lambda _
8464 (substitute* "Makefile"
8465 ((".*_cuda") "")
8466 (("(bits_test_intersections) \\\\" _ match) match))
8467 #t))
8468 (replace 'install
8469 (lambda* (#:key outputs #:allow-other-keys)
8470 (copy-recursively
8471 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8472 #t)))))
8473 (inputs
8474 `(("gsl" ,gsl)
8475 ("zlib" ,zlib)))
8476 (home-page "https://github.com/arq5x/bits")
8477 (synopsis "Implementation of binary interval search algorithm")
8478 (description "This package provides an implementation of the
8479 BITS (Binary Interval Search) algorithm, an approach to interval set
8480 intersection. It is especially suited for the comparison of diverse genomic
8481 datasets and the exploration of large datasets of genome
8482 intervals (e.g. genes, sequence alignments).")
8483 (license license:gpl2))))
8484
8485 (define-public piranha
8486 ;; There is no release tarball for the latest version. The latest commit is
8487 ;; older than one year at the time of this writing.
8488 (let ((revision "1")
8489 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8490 (package
8491 (name "piranha")
8492 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8493 (source (origin
8494 (method git-fetch)
8495 (uri (git-reference
8496 (url "https://github.com/smithlabcode/piranha.git")
8497 (commit commit)))
8498 (sha256
8499 (base32
8500 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8501 (build-system gnu-build-system)
8502 (arguments
8503 `(#:test-target "test"
8504 #:phases
8505 (modify-phases %standard-phases
8506 (add-after 'unpack 'copy-smithlab-cpp
8507 (lambda* (#:key inputs #:allow-other-keys)
8508 (for-each (lambda (file)
8509 (install-file file "./src/smithlab_cpp/"))
8510 (find-files (assoc-ref inputs "smithlab-cpp")))
8511 #t))
8512 (add-after 'install 'install-to-store
8513 (lambda* (#:key outputs #:allow-other-keys)
8514 (let* ((out (assoc-ref outputs "out"))
8515 (bin (string-append out "/bin")))
8516 (for-each (lambda (file)
8517 (install-file file bin))
8518 (find-files "bin" ".*")))
8519 #t)))
8520 #:configure-flags
8521 (list (string-append "--with-bam_tools_headers="
8522 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8523 (string-append "--with-bam_tools_library="
8524 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8525 (inputs
8526 `(("bamtools" ,bamtools)
8527 ("samtools" ,samtools-0.1)
8528 ("gsl" ,gsl)
8529 ("smithlab-cpp"
8530 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8531 (origin
8532 (method git-fetch)
8533 (uri (git-reference
8534 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8535 (commit commit)))
8536 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8537 (sha256
8538 (base32
8539 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8540 (native-inputs
8541 `(("python" ,python-2)))
8542 (home-page "https://github.com/smithlabcode/piranha")
8543 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8544 (description
8545 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8546 RIP-seq experiments. It takes input in BED or BAM format and identifies
8547 regions of statistically significant read enrichment. Additional covariates
8548 may optionally be provided to further inform the peak-calling process.")
8549 (license license:gpl3+))))
8550
8551 (define-public pepr
8552 (package
8553 (name "pepr")
8554 (version "1.0.9")
8555 (source (origin
8556 (method url-fetch)
8557 (uri (string-append "https://pypi.python.org/packages/source/P"
8558 "/PePr/PePr-" version ".tar.gz"))
8559 (sha256
8560 (base32
8561 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8562 (build-system python-build-system)
8563 (arguments
8564 `(#:python ,python-2 ; python2 only
8565 #:tests? #f)) ; no tests included
8566 (propagated-inputs
8567 `(("python2-numpy" ,python2-numpy)
8568 ("python2-scipy" ,python2-scipy)
8569 ("python2-pysam" ,python2-pysam)))
8570 (home-page "https://github.com/shawnzhangyx/PePr")
8571 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8572 (description
8573 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8574 that is primarily designed for data with biological replicates. It uses a
8575 negative binomial distribution to model the read counts among the samples in
8576 the same group, and look for consistent differences between ChIP and control
8577 group or two ChIP groups run under different conditions.")
8578 (license license:gpl3+)))
8579
8580 (define-public filevercmp
8581 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8582 (package
8583 (name "filevercmp")
8584 (version (string-append "0-1." (string-take commit 7)))
8585 (source (origin
8586 (method url-fetch)
8587 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8588 commit ".tar.gz"))
8589 (file-name (string-append name "-" version ".tar.gz"))
8590 (sha256
8591 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8592 (build-system gnu-build-system)
8593 (arguments
8594 `(#:tests? #f ; There are no tests to run.
8595 #:phases
8596 (modify-phases %standard-phases
8597 (delete 'configure) ; There is no configure phase.
8598 (replace 'install
8599 (lambda* (#:key outputs #:allow-other-keys)
8600 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8601 (install-file "filevercmp" bin)))))))
8602 (home-page "https://github.com/ekg/filevercmp")
8603 (synopsis "This program compares version strings")
8604 (description "This program compares version strings. It intends to be a
8605 replacement for strverscmp.")
8606 (license license:gpl3+))))
8607
8608 (define-public multiqc
8609 (package
8610 (name "multiqc")
8611 (version "1.2")
8612 (source
8613 (origin
8614 (method url-fetch)
8615 (uri (pypi-uri "multiqc" version))
8616 (sha256
8617 (base32
8618 "032svgym67k2ds7wp0cxzv79gi30yrdl45zbqn74lni3dk04qm33"))))
8619 (build-system python-build-system)
8620 (propagated-inputs
8621 `(("python-jinja2" ,python-jinja2)
8622 ("python-simplejson" ,python-simplejson)
8623 ("python-pyyaml" ,python-pyyaml)
8624 ("python-click" ,python-click)
8625 ("python-spectra" ,python-spectra)
8626 ("python-requests" ,python-requests)
8627 ("python-markdown" ,python-markdown)
8628 ("python-lzstring" ,python-lzstring)
8629 ("python-matplotlib" ,python-matplotlib)
8630 ("python-numpy" ,python-numpy)
8631 ;; MultQC checks for the presence of nose at runtime.
8632 ("python-nose" ,python-nose)))
8633 (home-page "http://multiqc.info")
8634 (synopsis "Aggregate bioinformatics analysis reports")
8635 (description
8636 "MultiQC is a tool to aggregate bioinformatics results across many
8637 samples into a single report. It contains modules for a large number of
8638 common bioinformatics tools.")
8639 (license license:gpl3)))
8640
8641 (define-public r-chipseq
8642 (package
8643 (name "r-chipseq")
8644 (version "1.26.0")
8645 (source
8646 (origin
8647 (method url-fetch)
8648 (uri (bioconductor-uri "chipseq" version))
8649 (sha256
8650 (base32
8651 "1hahyqiwb2ch8214xqpw0c3jpiwkmyf3dwz0xc87jx6cdnzipj3i"))))
8652 (build-system r-build-system)
8653 (propagated-inputs
8654 `(("r-biocgenerics" ,r-biocgenerics)
8655 ("r-genomicranges" ,r-genomicranges)
8656 ("r-iranges" ,r-iranges)
8657 ("r-s4vectors" ,r-s4vectors)
8658 ("r-shortread" ,r-shortread)))
8659 (home-page "http://bioconductor.org/packages/chipseq")
8660 (synopsis "Package for analyzing ChIPseq data")
8661 (description
8662 "This package provides tools for processing short read data from ChIPseq
8663 experiments.")
8664 (license license:artistic2.0)))
8665
8666 (define-public r-copyhelper
8667 (package
8668 (name "r-copyhelper")
8669 (version "1.6.0")
8670 (source
8671 (origin
8672 (method url-fetch)
8673 (uri (string-append "http://bioconductor.org/packages/release/"
8674 "data/experiment/src/contrib/CopyhelpeR_"
8675 version ".tar.gz"))
8676 (sha256
8677 (base32
8678 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8679 (properties `((upstream-name . "CopyhelpeR")))
8680 (build-system r-build-system)
8681 (home-page "http://bioconductor.org/packages/CopyhelpeR/")
8682 (synopsis "Helper files for CopywriteR")
8683 (description
8684 "This package contains the helper files that are required to run the
8685 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8686 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8687 mm10. In addition, it contains a blacklist filter to remove regions that
8688 display copy number variation. Files are stored as GRanges objects from the
8689 GenomicRanges Bioconductor package.")
8690 (license license:gpl2)))
8691
8692 (define-public r-copywriter
8693 (package
8694 (name "r-copywriter")
8695 (version "2.8.1")
8696 (source
8697 (origin
8698 (method url-fetch)
8699 (uri (bioconductor-uri "CopywriteR" version))
8700 (sha256
8701 (base32
8702 "0xgqnq5v5213b3nzvlmjysjb7w1bc0iblqpmzbjqn7n0ib0qyhbm"))))
8703 (properties `((upstream-name . "CopywriteR")))
8704 (build-system r-build-system)
8705 (propagated-inputs
8706 `(("r-biocparallel" ,r-biocparallel)
8707 ("r-chipseq" ,r-chipseq)
8708 ("r-copyhelper" ,r-copyhelper)
8709 ("r-data-table" ,r-data-table)
8710 ("r-dnacopy" ,r-dnacopy)
8711 ("r-futile-logger" ,r-futile-logger)
8712 ("r-genomeinfodb" ,r-genomeinfodb)
8713 ("r-genomicalignments" ,r-genomicalignments)
8714 ("r-genomicranges" ,r-genomicranges)
8715 ("r-gtools" ,r-gtools)
8716 ("r-iranges" ,r-iranges)
8717 ("r-matrixstats" ,r-matrixstats)
8718 ("r-rsamtools" ,r-rsamtools)
8719 ("r-s4vectors" ,r-s4vectors)))
8720 (home-page "https://github.com/PeeperLab/CopywriteR")
8721 (synopsis "Copy number information from targeted sequencing")
8722 (description
8723 "CopywriteR extracts DNA copy number information from targeted sequencing
8724 by utilizing off-target reads. It allows for extracting uniformly distributed
8725 copy number information, can be used without reference, and can be applied to
8726 sequencing data obtained from various techniques including chromatin
8727 immunoprecipitation and target enrichment on small gene panels. Thereby,
8728 CopywriteR constitutes a widely applicable alternative to available copy
8729 number detection tools.")
8730 (license license:gpl2)))
8731
8732 (define-public r-methylkit
8733 (package
8734 (name "r-methylkit")
8735 (version "1.2.0")
8736 (source (origin
8737 (method url-fetch)
8738 (uri (bioconductor-uri "methylKit" version))
8739 (sha256
8740 (base32
8741 "02acdjf6jl0c1glymin84pdna4farn4vv0gb6107d9iqz3y3gkmm"))))
8742 (properties `((upstream-name . "methylKit")))
8743 (build-system r-build-system)
8744 (propagated-inputs
8745 `(("r-data-table" ,r-data-table)
8746 ("r-emdbook" ,r-emdbook)
8747 ("r-fastseg" ,r-fastseg)
8748 ("r-genomeinfodb" ,r-genomeinfodb)
8749 ("r-genomicranges" ,r-genomicranges)
8750 ("r-gtools" ,r-gtools)
8751 ("r-iranges" ,r-iranges)
8752 ("r-kernsmooth" ,r-kernsmooth)
8753 ("r-limma" ,r-limma)
8754 ("r-mclust" ,r-mclust)
8755 ("r-qvalue" ,r-qvalue)
8756 ("r-r-utils" ,r-r-utils)
8757 ("r-rcpp" ,r-rcpp)
8758 ("r-rhtslib" ,r-rhtslib)
8759 ("r-rsamtools" ,r-rsamtools)
8760 ("r-rtracklayer" ,r-rtracklayer)
8761 ("r-s4vectors" ,r-s4vectors)
8762 ("r-zlibbioc" ,r-zlibbioc)))
8763 (inputs
8764 `(("zlib" ,zlib)))
8765 (home-page "http://code.google.com/p/methylkit/")
8766 (synopsis
8767 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8768 (description
8769 "MethylKit is an R package for DNA methylation analysis and annotation
8770 from high-throughput bisulfite sequencing. The package is designed to deal
8771 with sequencing data from @dfn{Reduced representation bisulfite
8772 sequencing} (RRBS) and its variants, but also target-capture methods and whole
8773 genome bisulfite sequencing. It also has functions to analyze base-pair
8774 resolution 5hmC data from experimental protocols such as oxBS-Seq and
8775 TAB-Seq.")
8776 (license license:artistic2.0)))
8777
8778 (define-public r-sva
8779 (package
8780 (name "r-sva")
8781 (version "3.24.4")
8782 (source
8783 (origin
8784 (method url-fetch)
8785 (uri (bioconductor-uri "sva" version))
8786 (sha256
8787 (base32
8788 "0wcway4ai9im81xnrzb1vij2iidq5pw24qhjfgacmhxvx3dzhbsc"))))
8789 (build-system r-build-system)
8790 (propagated-inputs
8791 `(("r-genefilter" ,r-genefilter)
8792 ("r-mgcv" ,r-mgcv)
8793 ("r-biocparallel" ,r-biocparallel)
8794 ("r-matrixstats" ,r-matrixstats)
8795 ("r-limma" ,r-limma)))
8796 (home-page "http://bioconductor.org/packages/sva")
8797 (synopsis "Surrogate variable analysis")
8798 (description
8799 "This package contains functions for removing batch effects and other
8800 unwanted variation in high-throughput experiment. It also contains functions
8801 for identifying and building surrogate variables for high-dimensional data
8802 sets. Surrogate variables are covariates constructed directly from
8803 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8804 imaging data that can be used in subsequent analyses to adjust for unknown,
8805 unmodeled, or latent sources of noise.")
8806 (license license:artistic2.0)))
8807
8808 (define-public r-seqminer
8809 (package
8810 (name "r-seqminer")
8811 (version "6.0")
8812 (source
8813 (origin
8814 (method url-fetch)
8815 (uri (cran-uri "seqminer" version))
8816 (sha256
8817 (base32
8818 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
8819 (build-system r-build-system)
8820 (inputs
8821 `(("zlib" ,zlib)))
8822 (home-page "http://seqminer.genomic.codes")
8823 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8824 (description
8825 "This package provides tools to integrate nucleotide sequencing
8826 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8827 ;; Any version of the GPL is acceptable
8828 (license (list license:gpl2+ license:gpl3+))))
8829
8830 (define-public r-raremetals2
8831 (package
8832 (name "r-raremetals2")
8833 (version "0.1")
8834 (source
8835 (origin
8836 (method url-fetch)
8837 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8838 "b/b7/RareMETALS2_" version ".tar.gz"))
8839 (sha256
8840 (base32
8841 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8842 (properties `((upstream-name . "RareMETALS2")))
8843 (build-system r-build-system)
8844 (propagated-inputs
8845 `(("r-seqminer" ,r-seqminer)
8846 ("r-mvtnorm" ,r-mvtnorm)
8847 ("r-mass" ,r-mass)
8848 ("r-compquadform" ,r-compquadform)
8849 ("r-getopt" ,r-getopt)))
8850 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8851 (synopsis "Analyze gene-level association tests for binary trait")
8852 (description
8853 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8854 It was designed to meta-analyze gene-level association tests for binary trait.
8855 While rareMETALS offers a near-complete solution for meta-analysis of
8856 gene-level tests for quantitative trait, it does not offer the optimal
8857 solution for binary trait. The package rareMETALS2 offers improved features
8858 for analyzing gene-level association tests in meta-analyses for binary
8859 trait.")
8860 (license license:gpl3)))
8861
8862 (define-public r-maldiquant
8863 (package
8864 (name "r-maldiquant")
8865 (version "1.16.4")
8866 (source
8867 (origin
8868 (method url-fetch)
8869 (uri (cran-uri "MALDIquant" version))
8870 (sha256
8871 (base32
8872 "1pmhsfvd45a44xdiml4zx3zd5fhygqyziqvygahkk9yibnyhv4cv"))))
8873 (properties `((upstream-name . "MALDIquant")))
8874 (build-system r-build-system)
8875 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8876 (synopsis "Quantitative analysis of mass spectrometry data")
8877 (description
8878 "This package provides a complete analysis pipeline for matrix-assisted
8879 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8880 two-dimensional mass spectrometry data. In addition to commonly used plotting
8881 and processing methods it includes distinctive features, namely baseline
8882 subtraction methods such as morphological filters (TopHat) or the
8883 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8884 alignment using warping functions, handling of replicated measurements as well
8885 as allowing spectra with different resolutions.")
8886 (license license:gpl3+)))
8887
8888 (define-public r-protgenerics
8889 (package
8890 (name "r-protgenerics")
8891 (version "1.8.0")
8892 (source
8893 (origin
8894 (method url-fetch)
8895 (uri (bioconductor-uri "ProtGenerics" version))
8896 (sha256
8897 (base32
8898 "08idb3rvxn4fl7rd66jasyqz47cb76dbc3968r1g26jr2ci3w1pl"))))
8899 (properties `((upstream-name . "ProtGenerics")))
8900 (build-system r-build-system)
8901 (home-page "https://github.com/lgatto/ProtGenerics")
8902 (synopsis "S4 generic functions for proteomics infrastructure")
8903 (description
8904 "This package provides S4 generic functions needed by Bioconductor
8905 proteomics packages.")
8906 (license license:artistic2.0)))
8907
8908 (define-public r-mzr
8909 (package
8910 (name "r-mzr")
8911 (version "2.10.0")
8912 (source
8913 (origin
8914 (method url-fetch)
8915 (uri (bioconductor-uri "mzR" version))
8916 (sha256
8917 (base32
8918 "1zir46h320n2vbrky6q3m8l221f3wdjlfsnx4ak9xca5min24xm7"))))
8919 (properties `((upstream-name . "mzR")))
8920 (build-system r-build-system)
8921 (inputs
8922 `(("boost" ,boost)
8923 ("netcdf" ,netcdf)))
8924 (propagated-inputs
8925 `(("r-biobase" ,r-biobase)
8926 ("r-biocgenerics" ,r-biocgenerics)
8927 ("r-protgenerics" ,r-protgenerics)
8928 ("r-rcpp" ,r-rcpp)
8929 ("r-zlibbioc" ,r-zlibbioc)))
8930 (home-page "https://github.com/sneumann/mzR/")
8931 (synopsis "Parser for mass spectrometry data files")
8932 (description
8933 "The mzR package provides a unified API to the common file formats and
8934 parsers available for mass spectrometry data. It comes with a wrapper for the
8935 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8936 The package contains the original code written by the ISB, and a subset of the
8937 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8938 previously been used in XCMS.")
8939 (license license:artistic2.0)))
8940
8941 (define-public r-affyio
8942 (package
8943 (name "r-affyio")
8944 (version "1.46.0")
8945 (source
8946 (origin
8947 (method url-fetch)
8948 (uri (bioconductor-uri "affyio" version))
8949 (sha256
8950 (base32
8951 "13w6al9296q916w0w6ngbsk25b21ahla1b6n40fcqhbvhyfii6sj"))))
8952 (build-system r-build-system)
8953 (propagated-inputs
8954 `(("r-zlibbioc" ,r-zlibbioc)))
8955 (inputs
8956 `(("zlib" ,zlib)))
8957 (home-page "https://github.com/bmbolstad/affyio")
8958 (synopsis "Tools for parsing Affymetrix data files")
8959 (description
8960 "This package provides routines for parsing Affymetrix data files based
8961 upon file format information. The primary focus is on accessing the CEL and
8962 CDF file formats.")
8963 (license license:lgpl2.0+)))
8964
8965 (define-public r-affy
8966 (package
8967 (name "r-affy")
8968 (version "1.54.0")
8969 (source
8970 (origin
8971 (method url-fetch)
8972 (uri (bioconductor-uri "affy" version))
8973 (sha256
8974 (base32
8975 "0azwg2qxzgflr1rjvbdln5i5rbcr9gs36kqlacd9cwl1szb9ad3m"))))
8976 (build-system r-build-system)
8977 (propagated-inputs
8978 `(("r-affyio" ,r-affyio)
8979 ("r-biobase" ,r-biobase)
8980 ("r-biocgenerics" ,r-biocgenerics)
8981 ("r-biocinstaller" ,r-biocinstaller)
8982 ("r-preprocesscore" ,r-preprocesscore)
8983 ("r-zlibbioc" ,r-zlibbioc)))
8984 (home-page "http://bioconductor.org/packages/affy")
8985 (synopsis "Methods for affymetrix oligonucleotide arrays")
8986 (description
8987 "This package contains functions for exploratory oligonucleotide array
8988 analysis.")
8989 (license license:lgpl2.0+)))
8990
8991 (define-public r-vsn
8992 (package
8993 (name "r-vsn")
8994 (version "3.44.0")
8995 (source
8996 (origin
8997 (method url-fetch)
8998 (uri (bioconductor-uri "vsn" version))
8999 (sha256
9000 (base32
9001 "0qhg3a4sc62pfdxcpvmk831rk138xh4zx4f1s39jhxpqqhmr7jvk"))))
9002 (build-system r-build-system)
9003 (propagated-inputs
9004 `(("r-affy" ,r-affy)
9005 ("r-biobase" ,r-biobase)
9006 ("r-ggplot2" ,r-ggplot2)
9007 ("r-hexbin" ,r-hexbin)
9008 ("r-lattice" ,r-lattice)
9009 ("r-limma" ,r-limma)))
9010 (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
9011 (synopsis "Variance stabilization and calibration for microarray data")
9012 (description
9013 "The package implements a method for normalising microarray intensities,
9014 and works for single- and multiple-color arrays. It can also be used for data
9015 from other technologies, as long as they have similar format. The method uses
9016 a robust variant of the maximum-likelihood estimator for an
9017 additive-multiplicative error model and affine calibration. The model
9018 incorporates data calibration step (a.k.a. normalization), a model for the
9019 dependence of the variance on the mean intensity and a variance stabilizing
9020 data transformation. Differences between transformed intensities are
9021 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9022 their variance is independent of the mean, and they are usually more sensitive
9023 and specific in detecting differential transcription.")
9024 (license license:artistic2.0)))
9025
9026 (define-public r-mzid
9027 (package
9028 (name "r-mzid")
9029 (version "1.14.0")
9030 (source
9031 (origin
9032 (method url-fetch)
9033 (uri (bioconductor-uri "mzID" version))
9034 (sha256
9035 (base32
9036 "11xnild02jz24vbsfy92lb7jlqqwnrswg66a7r4rsw8d2ibrbk33"))))
9037 (properties `((upstream-name . "mzID")))
9038 (build-system r-build-system)
9039 (propagated-inputs
9040 `(("r-doparallel" ,r-doparallel)
9041 ("r-foreach" ,r-foreach)
9042 ("r-iterators" ,r-iterators)
9043 ("r-plyr" ,r-plyr)
9044 ("r-protgenerics" ,r-protgenerics)
9045 ("r-rcpp" ,r-rcpp)
9046 ("r-xml" ,r-xml)))
9047 (home-page "http://bioconductor.org/packages/mzID")
9048 (synopsis "Parser for mzIdentML files")
9049 (description
9050 "This package provides a parser for mzIdentML files implemented using the
9051 XML package. The parser tries to be general and able to handle all types of
9052 mzIdentML files with the drawback of having less pretty output than a vendor
9053 specific parser.")
9054 (license license:gpl2+)))
9055
9056 (define-public r-pcamethods
9057 (package
9058 (name "r-pcamethods")
9059 (version "1.68.0")
9060 (source
9061 (origin
9062 (method url-fetch)
9063 (uri (bioconductor-uri "pcaMethods" version))
9064 (sha256
9065 (base32
9066 "0c4lphqyzj577ws4s172391cgv00s5nhy152zp18k2k4diyhq6n0"))))
9067 (properties `((upstream-name . "pcaMethods")))
9068 (build-system r-build-system)
9069 (propagated-inputs
9070 `(("r-biobase" ,r-biobase)
9071 ("r-biocgenerics" ,r-biocgenerics)
9072 ("r-mass" ,r-mass)
9073 ("r-rcpp" ,r-rcpp)))
9074 (home-page "https://github.com/hredestig/pcamethods")
9075 (synopsis "Collection of PCA methods")
9076 (description
9077 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9078 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9079 for missing value estimation is included for comparison. BPCA, PPCA and
9080 NipalsPCA may be used to perform PCA on incomplete data as well as for
9081 accurate missing value estimation. A set of methods for printing and plotting
9082 the results is also provided. All PCA methods make use of the same data
9083 structure (pcaRes) to provide a common interface to the PCA results.")
9084 (license license:gpl3+)))
9085
9086 (define-public r-msnbase
9087 (package
9088 (name "r-msnbase")
9089 (version "2.2.0")
9090 (source
9091 (origin
9092 (method url-fetch)
9093 (uri (bioconductor-uri "MSnbase" version))
9094 (sha256
9095 (base32
9096 "1n9bbdlp8d8bx2mqby0c4yylz1yil42scbkxqgyrfr9s5sn6dqff"))))
9097 (properties `((upstream-name . "MSnbase")))
9098 (build-system r-build-system)
9099 (propagated-inputs
9100 `(("r-affy" ,r-affy)
9101 ("r-biobase" ,r-biobase)
9102 ("r-biocgenerics" ,r-biocgenerics)
9103 ("r-biocparallel" ,r-biocparallel)
9104 ("r-digest" ,r-digest)
9105 ("r-ggplot2" ,r-ggplot2)
9106 ("r-impute" ,r-impute)
9107 ("r-iranges" ,r-iranges)
9108 ("r-maldiquant" ,r-maldiquant)
9109 ("r-mzid" ,r-mzid)
9110 ("r-mzr" ,r-mzr)
9111 ("r-pcamethods" ,r-pcamethods)
9112 ("r-plyr" ,r-plyr)
9113 ("r-preprocesscore" ,r-preprocesscore)
9114 ("r-protgenerics" ,r-protgenerics)
9115 ("r-rcpp" ,r-rcpp)
9116 ("r-reshape2" ,r-reshape2)
9117 ("r-s4vectors" ,r-s4vectors)
9118 ("r-vsn" ,r-vsn)
9119 ("r-xml" ,r-xml)))
9120 (home-page "https://github.com/lgatto/MSnbase")
9121 (synopsis "Base functions and classes for MS-based proteomics")
9122 (description
9123 "This package provides basic plotting, data manipulation and processing
9124 of mass spectrometry based proteomics data.")
9125 (license license:artistic2.0)))
9126
9127 (define-public r-msnid
9128 (package
9129 (name "r-msnid")
9130 (version "1.10.0")
9131 (source
9132 (origin
9133 (method url-fetch)
9134 (uri (bioconductor-uri "MSnID" version))
9135 (sha256
9136 (base32
9137 "0pjwargi5lif8q53fd43ql67p3yk9w10jychafd9qgbaw5k3f68k"))))
9138 (properties `((upstream-name . "MSnID")))
9139 (build-system r-build-system)
9140 (propagated-inputs
9141 `(("r-biobase" ,r-biobase)
9142 ("r-data-table" ,r-data-table)
9143 ("r-doparallel" ,r-doparallel)
9144 ("r-dplyr" ,r-dplyr)
9145 ("r-foreach" ,r-foreach)
9146 ("r-iterators" ,r-iterators)
9147 ("r-msnbase" ,r-msnbase)
9148 ("r-mzid" ,r-mzid)
9149 ("r-mzr" ,r-mzr)
9150 ("r-protgenerics" ,r-protgenerics)
9151 ("r-r-cache" ,r-r-cache)
9152 ("r-rcpp" ,r-rcpp)
9153 ("r-reshape2" ,r-reshape2)))
9154 (home-page "http://bioconductor.org/packages/MSnID")
9155 (synopsis "Utilities for LC-MSn proteomics identifications")
9156 (description
9157 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9158 from mzIdentML (leveraging the mzID package) or text files. After collating
9159 the search results from multiple datasets it assesses their identification
9160 quality and optimize filtering criteria to achieve the maximum number of
9161 identifications while not exceeding a specified false discovery rate. It also
9162 contains a number of utilities to explore the MS/MS results and assess missed
9163 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9164 (license license:artistic2.0)))
9165
9166 (define-public r-seurat
9167 ;; Source releases are only made for new x.0 versions. All newer versions
9168 ;; are only released as pre-built binaries. At the time of this writing the
9169 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
9170 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
9171 (revision "1"))
9172 (package
9173 (name "r-seurat")
9174 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
9175 (source (origin
9176 (method git-fetch)
9177 (uri (git-reference
9178 (url "https://github.com/satijalab/seurat")
9179 (commit commit)))
9180 (file-name (string-append name "-" version "-checkout"))
9181 (sha256
9182 (base32
9183 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
9184 ;; Delete pre-built jar.
9185 (snippet
9186 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9187 #t))))
9188 (build-system r-build-system)
9189 (arguments
9190 `(#:phases
9191 (modify-phases %standard-phases
9192 (add-after 'unpack 'build-jar
9193 (lambda* (#:key inputs #:allow-other-keys)
9194 (let ((classesdir "tmp-classes"))
9195 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9196 (mkdir classesdir)
9197 (and (zero? (apply system* `("javac" "-d" ,classesdir
9198 ,@(find-files "java" "\\.java$"))))
9199 (zero? (system* "jar"
9200 "-cf" "inst/java/ModularityOptimizer.jar"
9201 "-C" classesdir ".")))))))))
9202 (native-inputs
9203 `(("jdk" ,icedtea "jdk")))
9204 (propagated-inputs
9205 `(("r-ape" ,r-ape)
9206 ("r-caret" ,r-caret)
9207 ("r-cowplot" ,r-cowplot)
9208 ("r-dplyr" ,r-dplyr)
9209 ("r-fastica" ,r-fastica)
9210 ("r-fnn" ,r-fnn)
9211 ("r-fpc" ,r-fpc)
9212 ("r-gdata" ,r-gdata)
9213 ("r-ggplot2" ,r-ggplot2)
9214 ("r-gplots" ,r-gplots)
9215 ("r-gridextra" ,r-gridextra)
9216 ("r-igraph" ,r-igraph)
9217 ("r-irlba" ,r-irlba)
9218 ("r-lars" ,r-lars)
9219 ("r-mixtools" ,r-mixtools)
9220 ("r-pbapply" ,r-pbapply)
9221 ("r-plyr" ,r-plyr)
9222 ("r-ranger" ,r-ranger)
9223 ("r-rcolorbrewer" ,r-rcolorbrewer)
9224 ("r-rcpp" ,r-rcpp)
9225 ("r-rcppeigen" ,r-rcppeigen)
9226 ("r-rcppprogress" ,r-rcppprogress)
9227 ("r-reshape2" ,r-reshape2)
9228 ("r-rocr" ,r-rocr)
9229 ("r-rtsne" ,r-rtsne)
9230 ("r-stringr" ,r-stringr)
9231 ("r-tclust" ,r-tclust)
9232 ("r-tsne" ,r-tsne)
9233 ("r-vgam" ,r-vgam)))
9234 (home-page "http://www.satijalab.org/seurat")
9235 (synopsis "Seurat is an R toolkit for single cell genomics")
9236 (description
9237 "This package is an R package designed for QC, analysis, and
9238 exploration of single cell RNA-seq data. It easily enables widely-used
9239 analytical techniques, including the identification of highly variable genes,
9240 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9241 algorithms; density clustering, hierarchical clustering, k-means, and the
9242 discovery of differentially expressed genes and markers.")
9243 (license license:gpl3))))
9244
9245 (define-public r-aroma-light
9246 (package
9247 (name "r-aroma-light")
9248 (version "3.6.0")
9249 (source
9250 (origin
9251 (method url-fetch)
9252 (uri (bioconductor-uri "aroma.light" version))
9253 (sha256
9254 (base32
9255 "10snykmmx36qaymyf5s1n1km8hsscyzpykcpf0mzsrcv8ml9rp8a"))))
9256 (properties `((upstream-name . "aroma.light")))
9257 (build-system r-build-system)
9258 (propagated-inputs
9259 `(("r-matrixstats" ,r-matrixstats)
9260 ("r-r-methodss3" ,r-r-methodss3)
9261 ("r-r-oo" ,r-r-oo)
9262 ("r-r-utils" ,r-r-utils)))
9263 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9264 (synopsis "Methods for normalization and visualization of microarray data")
9265 (description
9266 "This package provides methods for microarray analysis that take basic
9267 data types such as matrices and lists of vectors. These methods can be used
9268 standalone, be utilized in other packages, or be wrapped up in higher-level
9269 classes.")
9270 (license license:gpl2+)))
9271
9272 (define-public r-deseq
9273 (package
9274 (name "r-deseq")
9275 (version "1.28.0")
9276 (source
9277 (origin
9278 (method url-fetch)
9279 (uri (bioconductor-uri "DESeq" version))
9280 (sha256
9281 (base32
9282 "0j3dgcxd64m9qknmlcbdzvg4xhp981xd6nbwsvnqjfn6yypslgyw"))))
9283 (properties `((upstream-name . "DESeq")))
9284 (build-system r-build-system)
9285 (propagated-inputs
9286 `(("r-biobase" ,r-biobase)
9287 ("r-biocgenerics" ,r-biocgenerics)
9288 ("r-genefilter" ,r-genefilter)
9289 ("r-geneplotter" ,r-geneplotter)
9290 ("r-lattice" ,r-lattice)
9291 ("r-locfit" ,r-locfit)
9292 ("r-mass" ,r-mass)
9293 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9294 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9295 (synopsis "Differential gene expression analysis")
9296 (description
9297 "This package provides tools for estimating variance-mean dependence in
9298 count data from high-throughput genetic sequencing assays and for testing for
9299 differential expression based on a model using the negative binomial
9300 distribution.")
9301 (license license:gpl3+)))
9302
9303 (define-public r-edaseq
9304 (package
9305 (name "r-edaseq")
9306 (version "2.10.0")
9307 (source
9308 (origin
9309 (method url-fetch)
9310 (uri (bioconductor-uri "EDASeq" version))
9311 (sha256
9312 (base32
9313 "0f25dfc8hdii9fjm3bf89vy9jkxv23sa62fkcga5b4gkipwrvm9a"))))
9314 (properties `((upstream-name . "EDASeq")))
9315 (build-system r-build-system)
9316 (propagated-inputs
9317 `(("r-annotationdbi" ,r-annotationdbi)
9318 ("r-aroma-light" ,r-aroma-light)
9319 ("r-biobase" ,r-biobase)
9320 ("r-biocgenerics" ,r-biocgenerics)
9321 ("r-biomart" ,r-biomart)
9322 ("r-biostrings" ,r-biostrings)
9323 ("r-deseq" ,r-deseq)
9324 ("r-genomicfeatures" ,r-genomicfeatures)
9325 ("r-genomicranges" ,r-genomicranges)
9326 ("r-iranges" ,r-iranges)
9327 ("r-rsamtools" ,r-rsamtools)
9328 ("r-shortread" ,r-shortread)))
9329 (home-page "https://github.com/drisso/EDASeq")
9330 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9331 (description
9332 "This package provides support for numerical and graphical summaries of
9333 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9334 adjust for GC-content effect (or other gene-level effects) on read counts:
9335 loess robust local regression, global-scaling, and full-quantile
9336 normalization. Between-lane normalization procedures to adjust for
9337 distributional differences between lanes (e.g., sequencing depth):
9338 global-scaling and full-quantile normalization.")
9339 (license license:artistic2.0)))
9340
9341 (define-public r-interactivedisplaybase
9342 (package
9343 (name "r-interactivedisplaybase")
9344 (version "1.14.0")
9345 (source
9346 (origin
9347 (method url-fetch)
9348 (uri (bioconductor-uri "interactiveDisplayBase" version))
9349 (sha256
9350 (base32
9351 "12f6ap4bl3h2iwwhg8i3r9a7yyd28d8i5lb3fj1vnfvjs762r7r7"))))
9352 (properties
9353 `((upstream-name . "interactiveDisplayBase")))
9354 (build-system r-build-system)
9355 (propagated-inputs
9356 `(("r-biocgenerics" ,r-biocgenerics)
9357 ("r-shiny" ,r-shiny)))
9358 (home-page "http://bioconductor.org/packages/interactiveDisplayBase")
9359 (synopsis "Base package for web displays of Bioconductor objects")
9360 (description
9361 "This package contains the basic methods needed to generate interactive
9362 Shiny-based display methods for Bioconductor objects.")
9363 (license license:artistic2.0)))
9364
9365 (define-public r-annotationhub
9366 (package
9367 (name "r-annotationhub")
9368 (version "2.8.2")
9369 (source
9370 (origin
9371 (method url-fetch)
9372 (uri (bioconductor-uri "AnnotationHub" version))
9373 (sha256
9374 (base32
9375 "1nh5si3j1nv37jcg4260582ayjg18851np47cskrm54prnvhwd9r"))))
9376 (properties `((upstream-name . "AnnotationHub")))
9377 (build-system r-build-system)
9378 (propagated-inputs
9379 `(("r-annotationdbi" ,r-annotationdbi)
9380 ("r-biocgenerics" ,r-biocgenerics)
9381 ("r-biocinstaller" ,r-biocinstaller)
9382 ("r-httr" ,r-httr)
9383 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9384 ("r-rsqlite" ,r-rsqlite)
9385 ("r-s4vectors" ,r-s4vectors)
9386 ("r-yaml" ,r-yaml)))
9387 (home-page "http://bioconductor.org/packages/AnnotationHub")
9388 (synopsis "Client to access AnnotationHub resources")
9389 (description
9390 "This package provides a client for the Bioconductor AnnotationHub web
9391 resource. The AnnotationHub web resource provides a central location where
9392 genomic files (e.g. VCF, bed, wig) and other resources from standard
9393 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9394 metadata about each resource, e.g., a textual description, tags, and date of
9395 modification. The client creates and manages a local cache of files retrieved
9396 by the user, helping with quick and reproducible access.")
9397 (license license:artistic2.0)))
9398
9399 (define-public r-fastseg
9400 (package
9401 (name "r-fastseg")
9402 (version "1.22.0")
9403 (source
9404 (origin
9405 (method url-fetch)
9406 (uri (bioconductor-uri "fastseg" version))
9407 (sha256
9408 (base32
9409 "083wiz03q9mynwchs9frlpp6c84dncri5ncibx6h82p228cpja6h"))))
9410 (build-system r-build-system)
9411 (propagated-inputs
9412 `(("r-biobase" ,r-biobase)
9413 ("r-biocgenerics" ,r-biocgenerics)
9414 ("r-genomicranges" ,r-genomicranges)
9415 ("r-iranges" ,r-iranges)
9416 ("r-s4vectors" ,r-s4vectors)))
9417 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9418 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9419 (description
9420 "Fastseg implements a very fast and efficient segmentation algorithm.
9421 It can segment data from DNA microarrays and data from next generation
9422 sequencing for example to detect copy number segments. Further it can segment
9423 data from RNA microarrays like tiling arrays to identify transcripts. Most
9424 generally, it can segment data given as a matrix or as a vector. Various data
9425 formats can be used as input to fastseg like expression set objects for
9426 microarrays or GRanges for sequencing data.")
9427 (license license:lgpl2.0+)))
9428
9429 (define-public r-qvalue
9430 (package
9431 (name "r-qvalue")
9432 (version "2.8.0")
9433 (source
9434 (origin
9435 (method url-fetch)
9436 (uri (bioconductor-uri "qvalue" version))
9437 (sha256
9438 (base32
9439 "1dxdwa767a9r8n61r272ypi09qblcdfpzzwkmri74y5mbp1r3y4i"))))
9440 (build-system r-build-system)
9441 (propagated-inputs
9442 `(("r-ggplot2" ,r-ggplot2)
9443 ("r-reshape2" ,r-reshape2)))
9444 (home-page "http://github.com/jdstorey/qvalue")
9445 (synopsis "Q-value estimation for false discovery rate control")
9446 (description
9447 "This package takes a list of p-values resulting from the simultaneous
9448 testing of many hypotheses and estimates their q-values and local @dfn{false
9449 discovery rate} (FDR) values. The q-value of a test measures the proportion
9450 of false positives incurred when that particular test is called significant.
9451 The local FDR measures the posterior probability the null hypothesis is true
9452 given the test's p-value. Various plots are automatically generated, allowing
9453 one to make sensible significance cut-offs. The software can be applied to
9454 problems in genomics, brain imaging, astrophysics, and data mining.")
9455 ;; Any version of the LGPL.
9456 (license license:lgpl3+)))
9457
9458 (define htslib-for-sambamba
9459 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
9460 (package
9461 (inherit htslib)
9462 (name "htslib-for-sambamba")
9463 (version (string-append "1.3.1-1." (string-take commit 9)))
9464 (source
9465 (origin
9466 (method git-fetch)
9467 (uri (git-reference
9468 (url "https://github.com/lomereiter/htslib.git")
9469 (commit commit)))
9470 (file-name (string-append "htslib-" version "-checkout"))
9471 (sha256
9472 (base32
9473 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
9474 (arguments
9475 (substitute-keyword-arguments (package-arguments htslib)
9476 ((#:phases phases)
9477 `(modify-phases ,phases
9478 (add-after 'unpack 'bootstrap
9479 (lambda _
9480 (zero? (system* "autoreconf" "-vif"))))))))
9481 (native-inputs
9482 `(("autoconf" ,autoconf)
9483 ("automake" ,automake)
9484 ,@(package-native-inputs htslib))))))
9485
9486 (define-public sambamba
9487 (package
9488 (name "sambamba")
9489 (version "0.6.5")
9490 (source
9491 (origin
9492 (method url-fetch)
9493 (uri (string-append "https://github.com/lomereiter/sambamba/"
9494 "archive/v" version ".tar.gz"))
9495 (file-name (string-append name "-" version ".tar.gz"))
9496 (sha256
9497 (base32
9498 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
9499 (build-system gnu-build-system)
9500 (arguments
9501 `(#:tests? #f ; there is no test target
9502 #:make-flags
9503 '("D_COMPILER=ldc2"
9504 ;; Override "--compiler" flag only.
9505 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
9506 "sambamba-ldmd2-64")
9507 #:phases
9508 (modify-phases %standard-phases
9509 (delete 'configure)
9510 (add-after 'unpack 'place-biod
9511 (lambda* (#:key inputs #:allow-other-keys)
9512 (copy-recursively (assoc-ref inputs "biod") "BioD")
9513 #t))
9514 (add-after 'unpack 'unbundle-prerequisites
9515 (lambda _
9516 (substitute* "Makefile"
9517 ((" htslib-static lz4-static") ""))
9518 #t))
9519 (replace 'install
9520 (lambda* (#:key outputs #:allow-other-keys)
9521 (let* ((out (assoc-ref outputs "out"))
9522 (bin (string-append out "/bin")))
9523 (mkdir-p bin)
9524 (install-file "build/sambamba" bin)
9525 #t))))))
9526 (native-inputs
9527 `(("ldc" ,ldc)
9528 ("rdmd" ,rdmd)
9529 ("biod"
9530 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
9531 (origin
9532 (method git-fetch)
9533 (uri (git-reference
9534 (url "https://github.com/biod/BioD.git")
9535 (commit commit)))
9536 (file-name (string-append "biod-"
9537 (string-take commit 9)
9538 "-checkout"))
9539 (sha256
9540 (base32
9541 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
9542 (inputs
9543 `(("lz4" ,lz4)
9544 ("htslib" ,htslib-for-sambamba)))
9545 (home-page "http://lomereiter.github.io/sambamba")
9546 (synopsis "Tools for working with SAM/BAM data")
9547 (description "Sambamba is a high performance modern robust and
9548 fast tool (and library), written in the D programming language, for
9549 working with SAM and BAM files. Current parallelised functionality is
9550 an important subset of samtools functionality, including view, index,
9551 sort, markdup, and depth.")
9552 (license license:gpl2+)))
9553
9554 (define-public ritornello
9555 (package
9556 (name "ritornello")
9557 (version "1.0.0")
9558 (source (origin
9559 (method url-fetch)
9560 (uri (string-append "https://github.com/KlugerLab/"
9561 "Ritornello/archive/v"
9562 version ".tar.gz"))
9563 (file-name (string-append name "-" version ".tar.gz"))
9564 (sha256
9565 (base32
9566 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
9567 (build-system gnu-build-system)
9568 (arguments
9569 `(#:tests? #f ; there are no tests
9570 #:phases
9571 (modify-phases %standard-phases
9572 (add-after 'unpack 'patch-samtools-references
9573 (lambda* (#:key inputs #:allow-other-keys)
9574 (substitute* '("src/SamStream.h"
9575 "src/BufferedGenomeReader.h")
9576 (("<sam.h>") "<samtools/sam.h>"))
9577 #t))
9578 (delete 'configure)
9579 (replace 'install
9580 (lambda* (#:key inputs outputs #:allow-other-keys)
9581 (let* ((out (assoc-ref outputs "out"))
9582 (bin (string-append out "/bin/")))
9583 (mkdir-p bin)
9584 (install-file "bin/Ritornello" bin)
9585 #t))))))
9586 (inputs
9587 `(("samtools" ,samtools-0.1)
9588 ("fftw" ,fftw)
9589 ("boost" ,boost)
9590 ("zlib" ,zlib)))
9591 (home-page "https://github.com/KlugerLab/Ritornello")
9592 (synopsis "Control-free peak caller for ChIP-seq data")
9593 (description "Ritornello is a ChIP-seq peak calling algorithm based on
9594 signal processing that can accurately call binding events without the need to
9595 do a pair total DNA input or IgG control sample. It has been tested for use
9596 with narrow binding events such as transcription factor ChIP-seq.")
9597 (license license:gpl3+)))
9598
9599 (define-public trim-galore
9600 (package
9601 (name "trim-galore")
9602 (version "0.4.2")
9603 (source
9604 (origin
9605 (method url-fetch)
9606 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
9607 "projects/trim_galore/trim_galore_v"
9608 version ".zip"))
9609 (sha256
9610 (base32
9611 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
9612 (build-system gnu-build-system)
9613 (arguments
9614 `(#:tests? #f ; no tests
9615 #:phases
9616 (modify-phases %standard-phases
9617 ;; The archive contains plain files.
9618 (replace 'unpack
9619 (lambda* (#:key source #:allow-other-keys)
9620 (zero? (system* "unzip" source))))
9621 (delete 'configure)
9622 (delete 'build)
9623 (add-after 'unpack 'hardcode-tool-references
9624 (lambda* (#:key inputs #:allow-other-keys)
9625 (substitute* "trim_galore"
9626 (("\\$path_to_cutadapt = 'cutadapt'")
9627 (string-append "$path_to_cutadapt = '"
9628 (assoc-ref inputs "cutadapt")
9629 "/bin/cutadapt'"))
9630 (("\\| gzip")
9631 (string-append "| "
9632 (assoc-ref inputs "gzip")
9633 "/bin/gzip"))
9634 (("\"gunzip")
9635 (string-append "\""
9636 (assoc-ref inputs "gzip")
9637 "/bin/gunzip")))
9638 #t))
9639 (replace 'install
9640 (lambda* (#:key outputs #:allow-other-keys)
9641 (let ((bin (string-append (assoc-ref outputs "out")
9642 "/bin")))
9643 (mkdir-p bin)
9644 (install-file "trim_galore" bin)
9645 #t))))))
9646 (inputs
9647 `(("gzip" ,gzip)
9648 ("perl" ,perl)
9649 ("cutadapt" ,cutadapt)))
9650 (native-inputs
9651 `(("unzip" ,unzip)))
9652 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
9653 (synopsis "Wrapper around Cutadapt and FastQC")
9654 (description "Trim Galore! is a wrapper script to automate quality and
9655 adapter trimming as well as quality control, with some added functionality to
9656 remove biased methylation positions for RRBS sequence files.")
9657 (license license:gpl3+)))
9658
9659 (define-public gess
9660 (package
9661 (name "gess")
9662 (version "1.0")
9663 (source (origin
9664 (method url-fetch)
9665 (uri (string-append "http://compbio.uthscsa.edu/"
9666 "GESS_Web/files/"
9667 "gess-" version ".src.tar.gz"))
9668 (sha256
9669 (base32
9670 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
9671 (build-system gnu-build-system)
9672 (arguments
9673 `(#:tests? #f ; no tests
9674 #:phases
9675 (modify-phases %standard-phases
9676 (delete 'configure)
9677 (delete 'build)
9678 (replace 'install
9679 (lambda* (#:key inputs outputs #:allow-other-keys)
9680 (let* ((python (assoc-ref inputs "python"))
9681 (out (assoc-ref outputs "out"))
9682 (bin (string-append out "/bin/"))
9683 (target (string-append
9684 out "/lib/python2.7/site-packages/gess/")))
9685 (mkdir-p target)
9686 (copy-recursively "." target)
9687 ;; Make GESS.py executable
9688 (chmod (string-append target "GESS.py") #o555)
9689 ;; Add Python shebang to the top and make Matplotlib
9690 ;; usable.
9691 (substitute* (string-append target "GESS.py")
9692 (("\"\"\"Description:" line)
9693 (string-append "#!" (which "python") "
9694 import matplotlib
9695 matplotlib.use('Agg')
9696 " line)))
9697 ;; Make sure GESS has all modules in its path
9698 (wrap-program (string-append target "GESS.py")
9699 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
9700 (mkdir-p bin)
9701 (symlink (string-append target "GESS.py")
9702 (string-append bin "GESS.py"))
9703 #t))))))
9704 (inputs
9705 `(("python" ,python-2)
9706 ("python2-pysam" ,python2-pysam)
9707 ("python2-scipy" ,python2-scipy)
9708 ("python2-numpy" ,python2-numpy)
9709 ("python2-networkx" ,python2-networkx)
9710 ("python2-biopython" ,python2-biopython)))
9711 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
9712 (synopsis "Detect exon-skipping events from raw RNA-seq data")
9713 (description
9714 "GESS is an implementation of a novel computational method to detect de
9715 novo exon-skipping events directly from raw RNA-seq data without the prior
9716 knowledge of gene annotation information. GESS stands for the graph-based
9717 exon-skipping scanner detection scheme.")
9718 (license license:bsd-3)))
9719
9720 (define-public phylip
9721 (package
9722 (name "phylip")
9723 (version "3.696")
9724 (source
9725 (origin
9726 (method url-fetch)
9727 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
9728 "download/phylip-" version ".tar.gz"))
9729 (sha256
9730 (base32
9731 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
9732 (build-system gnu-build-system)
9733 (arguments
9734 `(#:tests? #f ; no check target
9735 #:make-flags (list "-f" "Makefile.unx" "install")
9736 #:parallel-build? #f ; not supported
9737 #:phases
9738 (modify-phases %standard-phases
9739 (add-after 'unpack 'enter-dir
9740 (lambda _ (chdir "src") #t))
9741 (delete 'configure)
9742 (replace 'install
9743 (lambda* (#:key inputs outputs #:allow-other-keys)
9744 (let ((target (string-append (assoc-ref outputs "out")
9745 "/bin")))
9746 (mkdir-p target)
9747 (for-each (lambda (file)
9748 (install-file file target))
9749 (find-files "../exe" ".*")))
9750 #t)))))
9751 (home-page "http://evolution.genetics.washington.edu/phylip/")
9752 (synopsis "Tools for inferring phylogenies")
9753 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
9754 programs for inferring phylogenies (evolutionary trees).")
9755 (license license:bsd-2)))
9756
9757 (define-public imp
9758 (package
9759 (name "imp")
9760 (version "2.6.2")
9761 (source
9762 (origin
9763 (method url-fetch)
9764 (uri (string-append "https://integrativemodeling.org/"
9765 version "/download/imp-" version ".tar.gz"))
9766 (sha256
9767 (base32
9768 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
9769 (build-system cmake-build-system)
9770 (arguments
9771 `(;; FIXME: Some tests fail because they produce warnings, others fail
9772 ;; because the PYTHONPATH does not include the modeller's directory.
9773 #:tests? #f
9774 ;; Do not place libraries in an architecture-specific directory.
9775 #:configure-flags
9776 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
9777 (inputs
9778 `(("boost" ,boost)
9779 ("gsl" ,gsl)
9780 ("swig" ,swig)
9781 ("hdf5" ,hdf5)
9782 ("fftw" ,fftw)
9783 ("python" ,python-2)))
9784 (propagated-inputs
9785 `(("python2-numpy" ,python2-numpy)
9786 ("python2-scipy" ,python2-scipy)
9787 ("python2-pandas" ,python2-pandas)
9788 ("python2-scikit-learn" ,python2-scikit-learn)
9789 ("python2-networkx" ,python2-networkx)))
9790 (home-page "https://integrativemodeling.org")
9791 (synopsis "Integrative modeling platform")
9792 (description "IMP's broad goal is to contribute to a comprehensive
9793 structural characterization of biomolecules ranging in size and complexity
9794 from small peptides to large macromolecular assemblies, by integrating data
9795 from diverse biochemical and biophysical experiments. IMP provides a C++ and
9796 Python toolbox for solving complex modeling problems, and a number of
9797 applications for tackling some common problems in a user-friendly way.")
9798 ;; IMP is largely available under the GNU Lesser GPL; see the file
9799 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
9800 ;; available under the GNU GPL (see the file COPYING.GPL).
9801 (license (list license:lgpl2.1+
9802 license:gpl3+))))
9803
9804 (define-public tadbit
9805 (package
9806 (name "tadbit")
9807 (version "0.2")
9808 (source (origin
9809 (method url-fetch)
9810 (uri (string-append "https://github.com/3DGenomes/TADbit/"
9811 "archive/v" version ".tar.gz"))
9812 (file-name (string-append name "-" version ".tar.gz"))
9813 (sha256
9814 (base32
9815 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
9816 (build-system python-build-system)
9817 (arguments
9818 `(;; Tests are included and must be run after installation, but
9819 ;; they are incomplete and thus cannot be run.
9820 #:tests? #f
9821 #:python ,python-2
9822 #:phases
9823 (modify-phases %standard-phases
9824 (add-after 'unpack 'fix-problems-with-setup.py
9825 (lambda* (#:key outputs #:allow-other-keys)
9826 ;; setup.py opens these files for writing
9827 (chmod "_pytadbit/_version.py" #o664)
9828 (chmod "README.rst" #o664)
9829
9830 ;; Don't attempt to install the bash completions to
9831 ;; the home directory.
9832 (rename-file "extras/.bash_completion"
9833 "extras/tadbit")
9834 (substitute* "setup.py"
9835 (("\\(path.expanduser\\('~'\\)")
9836 (string-append "(\""
9837 (assoc-ref outputs "out")
9838 "/etc/bash_completion.d\""))
9839 (("extras/\\.bash_completion")
9840 "extras/tadbit"))
9841 #t)))))
9842 (inputs
9843 ;; TODO: add Chimera for visualization
9844 `(("imp" ,imp)
9845 ("mcl" ,mcl)
9846 ("python2-scipy" ,python2-scipy)
9847 ("python2-numpy" ,python2-numpy)
9848 ("python2-matplotlib" ,python2-matplotlib)
9849 ("python2-pysam" ,python2-pysam)))
9850 (home-page "http://3dgenomes.github.io/TADbit/")
9851 (synopsis "Analyze, model, and explore 3C-based data")
9852 (description
9853 "TADbit is a complete Python library to deal with all steps to analyze,
9854 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
9855 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
9856 correct interaction matrices, identify and compare the so-called
9857 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
9858 interaction matrices, and finally, extract structural properties from the
9859 models. TADbit is complemented by TADkit for visualizing 3D models.")
9860 (license license:gpl3+)))
9861
9862 (define-public kentutils
9863 (package
9864 (name "kentutils")
9865 ;; 302.1.0 is out, but the only difference is the inclusion of
9866 ;; pre-built binaries.
9867 (version "302.0.0")
9868 (source
9869 (origin
9870 (method url-fetch)
9871 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
9872 "archive/v" version ".tar.gz"))
9873 (file-name (string-append name "-" version ".tar.gz"))
9874 (sha256
9875 (base32
9876 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
9877 (modules '((guix build utils)
9878 (srfi srfi-26)
9879 (ice-9 ftw)))
9880 (snippet
9881 '(begin
9882 ;; Only the contents of the specified directories are free
9883 ;; for all uses, so we remove the rest. "hg/autoSql" and
9884 ;; "hg/autoXml" are nominally free, but they depend on a
9885 ;; library that is built from the sources in "hg/lib",
9886 ;; which is nonfree.
9887 (let ((free (list "." ".."
9888 "utils" "lib" "inc" "tagStorm"
9889 "parasol" "htslib"))
9890 (directory? (lambda (file)
9891 (eq? 'directory (stat:type (stat file))))))
9892 (for-each (lambda (file)
9893 (and (directory? file)
9894 (delete-file-recursively file)))
9895 (map (cut string-append "src/" <>)
9896 (scandir "src"
9897 (lambda (file)
9898 (not (member file free)))))))
9899 ;; Only make the utils target, not the userApps target,
9900 ;; because that requires libraries we won't build.
9901 (substitute* "Makefile"
9902 ((" userApps") " utils"))
9903 ;; Only build libraries that are free.
9904 (substitute* "src/makefile"
9905 (("DIRS =.*") "DIRS =\n")
9906 (("cd jkOwnLib.*") "")
9907 ((" hgLib") "")
9908 (("cd hg.*") ""))
9909 (substitute* "src/utils/makefile"
9910 ;; These tools depend on "jkhgap.a", which is part of the
9911 ;; nonfree "src/hg/lib" directory.
9912 (("raSqlQuery") "")
9913 (("pslLiftSubrangeBlat") "")
9914
9915 ;; Do not build UCSC tools, which may require nonfree
9916 ;; components.
9917 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
9918 #t))))
9919 (build-system gnu-build-system)
9920 (arguments
9921 `( ;; There is no global test target and the test target for
9922 ;; individual tools depends on input files that are not
9923 ;; included.
9924 #:tests? #f
9925 #:phases
9926 (modify-phases %standard-phases
9927 (add-after 'unpack 'fix-paths
9928 (lambda _
9929 (substitute* "Makefile"
9930 (("/bin/echo") (which "echo")))
9931 #t))
9932 (add-after 'unpack 'prepare-samtabix
9933 (lambda* (#:key inputs #:allow-other-keys)
9934 (copy-recursively (assoc-ref inputs "samtabix")
9935 "samtabix")
9936 #t))
9937 (delete 'configure)
9938 (replace 'install
9939 (lambda* (#:key outputs #:allow-other-keys)
9940 (let ((bin (string-append (assoc-ref outputs "out")
9941 "/bin")))
9942 (copy-recursively "bin" bin))
9943 #t)))))
9944 (native-inputs
9945 `(("samtabix"
9946 ,(origin
9947 (method git-fetch)
9948 (uri (git-reference
9949 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
9950 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
9951 (sha256
9952 (base32
9953 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
9954 (inputs
9955 `(("zlib" ,zlib)
9956 ("tcsh" ,tcsh)
9957 ("perl" ,perl)
9958 ("libpng" ,libpng)
9959 ("mysql" ,mysql)
9960 ("openssl" ,openssl)))
9961 (home-page "http://genome.cse.ucsc.edu/index.html")
9962 (synopsis "Assorted bioinformatics utilities")
9963 (description "This package provides the kentUtils, a selection of
9964 bioinformatics utilities used in combination with the UCSC genome
9965 browser.")
9966 ;; Only a subset of the sources are released under a non-copyleft
9967 ;; free software license. All other sources are removed in a
9968 ;; snippet. See this bug report for an explanation of how the
9969 ;; license statements apply:
9970 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
9971 (license (license:non-copyleft
9972 "http://genome.ucsc.edu/license/"
9973 "The contents of this package are free for all uses."))))
9974
9975 (define-public f-seq
9976 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
9977 (revision "1"))
9978 (package
9979 (name "f-seq")
9980 (version (string-append "1.1-" revision "." commit))
9981 (source (origin
9982 (method git-fetch)
9983 (uri (git-reference
9984 (url "https://github.com/aboyle/F-seq.git")
9985 (commit commit)))
9986 (file-name (string-append name "-" version))
9987 (sha256
9988 (base32
9989 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
9990 (modules '((guix build utils)))
9991 ;; Remove bundled Java library archives.
9992 (snippet
9993 '(begin
9994 (for-each delete-file (find-files "lib" ".*"))
9995 #t))))
9996 (build-system ant-build-system)
9997 (arguments
9998 `(#:tests? #f ; no tests included
9999 #:phases
10000 (modify-phases %standard-phases
10001 (replace 'install
10002 (lambda* (#:key outputs #:allow-other-keys)
10003 (let* ((target (assoc-ref outputs "out"))
10004 (doc (string-append target "/share/doc/f-seq/")))
10005 (mkdir-p target)
10006 (mkdir-p doc)
10007 (substitute* "bin/linux/fseq"
10008 (("java") (which "java")))
10009 (install-file "README.txt" doc)
10010 (install-file "bin/linux/fseq" (string-append target "/bin"))
10011 (install-file "build~/fseq.jar" (string-append target "/lib"))
10012 (copy-recursively "lib" (string-append target "/lib"))
10013 #t))))))
10014 (inputs
10015 `(("perl" ,perl)
10016 ("java-commons-cli" ,java-commons-cli)))
10017 (home-page "http://fureylab.web.unc.edu/software/fseq/")
10018 (synopsis "Feature density estimator for high-throughput sequence tags")
10019 (description
10020 "F-Seq is a software package that generates a continuous tag sequence
10021 density estimation allowing identification of biologically meaningful sites
10022 such as transcription factor binding sites (ChIP-seq) or regions of open
10023 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
10024 Browser.")
10025 (license license:gpl3+))))
10026
10027 (define-public bismark
10028 (package
10029 (name "bismark")
10030 (version "0.16.3")
10031 (source
10032 (origin
10033 (method url-fetch)
10034 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
10035 "archive/" version ".tar.gz"))
10036 (file-name (string-append name "-" version ".tar.gz"))
10037 (sha256
10038 (base32
10039 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
10040 (build-system perl-build-system)
10041 (arguments
10042 `(#:tests? #f ; there are no tests
10043 #:phases
10044 (modify-phases %standard-phases
10045 (delete 'configure)
10046 (delete 'build)
10047 (replace 'install
10048 (lambda* (#:key outputs #:allow-other-keys)
10049 (let ((bin (string-append (assoc-ref outputs "out")
10050 "/bin"))
10051 (docdir (string-append (assoc-ref outputs "out")
10052 "/share/doc/bismark"))
10053 (docs '("Bismark_User_Guide.pdf"
10054 "RELEASE_NOTES.txt"))
10055 (scripts '("bismark"
10056 "bismark_genome_preparation"
10057 "bismark_methylation_extractor"
10058 "bismark2bedGraph"
10059 "bismark2report"
10060 "coverage2cytosine"
10061 "deduplicate_bismark"
10062 "bismark_sitrep.tpl"
10063 "bam2nuc"
10064 "bismark2summary")))
10065 (mkdir-p docdir)
10066 (mkdir-p bin)
10067 (for-each (lambda (file) (install-file file bin))
10068 scripts)
10069 (for-each (lambda (file) (install-file file docdir))
10070 docs)
10071 #t))))))
10072 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
10073 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
10074 (description "Bismark is a program to map bisulfite treated sequencing
10075 reads to a genome of interest and perform methylation calls in a single step.
10076 The output can be easily imported into a genome viewer, such as SeqMonk, and
10077 enables a researcher to analyse the methylation levels of their samples
10078 straight away. Its main features are:
10079
10080 @itemize
10081 @item Bisulfite mapping and methylation calling in one single step
10082 @item Supports single-end and paired-end read alignments
10083 @item Supports ungapped and gapped alignments
10084 @item Alignment seed length, number of mismatches etc are adjustable
10085 @item Output discriminates between cytosine methylation in CpG, CHG
10086 and CHH context
10087 @end itemize\n")
10088 (license license:gpl3+)))