HCoop / jackhill / guix / guix.git / blame
? search:
summary | shortlog | log | commit | commitdiff | tree
blob | blame (incremental) | history | HEAD
gnu: Update module imports for asciidoc and doxygen.
[jackhill/guix/guix.git] / gnu / packages / bioinformatics.scm
CommitLineData
4e10a221 1;;; GNU Guix --- Functional package management for GNU
0047d26a 2;;; Copyright © 2014, 2015, 2016 Ricardo Wurmus <rekado@elephly.net>
9b9b7ffd 3;;; Copyright © 2015, 2016 Ben Woodcroft <donttrustben@gmail.com>
8921841d 4;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
a5002ae7 5;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
a0a71439 6;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
ddb83129 7;;; Copyright © 2016 Efraim Flashner <efraim@flashner.co.il>
4e10a221
RW		 8;;;
9;;; This file is part of GNU Guix.
10;;;
11;;; GNU Guix is free software; you can redistribute it and/or modify it
12;;; under the terms of the GNU General Public License as published by
13;;; the Free Software Foundation; either version 3 of the License, or (at
14;;; your option) any later version.
15;;;
16;;; GNU Guix is distributed in the hope that it will be useful, but
17;;; WITHOUT ANY WARRANTY; without even the implied warranty of
18;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19;;; GNU General Public License for more details.
20;;;
21;;; You should have received a copy of the GNU General Public License
22;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
23
24(define-module (gnu packages bioinformatics)
25 #:use-module ((guix licenses) #:prefix license:)
26 #:use-module (guix packages)
8e913213 27 #:use-module (guix utils)
4e10a221 28 #:use-module (guix download)
2c16316e 29 #:use-module (guix git-download)
10b4a969 30 #:use-module (guix build-system ant)
4e10a221 31 #:use-module (guix build-system gnu)
d7678942 32 #:use-module (guix build-system cmake)
365c8153 33 #:use-module (guix build-system perl)
8622a072 34 #:use-module (guix build-system python)
a5002ae7 35 #:use-module (guix build-system r)
9c38b540 36 #:use-module (guix build-system ruby)
d3517eda 37 #:use-module (guix build-system trivial)
4e10a221 38 #:use-module (gnu packages)
a2950fa4 39 #:use-module (gnu packages autotools)
684bf7c7 40 #:use-module (gnu packages algebra)
d3517eda 41 #:use-module (gnu packages base)
a0a71439 42 #:use-module (gnu packages bison)
e4e5a4d8 43 #:use-module (gnu packages boost)
4e10a221 44 #:use-module (gnu packages compression)
82c370de 45 #:use-module (gnu packages cpio)
1baee943 46 #:use-module (gnu packages curl)
99828fa7 47 #:use-module (gnu packages documentation)
d29150b5 48 #:use-module (gnu packages datastructures)
75dd2424 49 #:use-module (gnu packages file)
02f35bb5 50 #:use-module (gnu packages gawk)
2409f37f 51 #:use-module (gnu packages gcc)
15a3c3d4 52 #:use-module (gnu packages java)
51c64999 53 #:use-module (gnu packages linux)
36742f43 54 #:use-module (gnu packages machine-learning)
c833ab55 55 #:use-module (gnu packages maths)
6c2b26e2 56 #:use-module (gnu packages mpi)
4e10a221 57 #:use-module (gnu packages ncurses)
81f3e0c1 58 #:use-module (gnu packages pcre)
4e10a221
RW		 59 #:use-module (gnu packages perl)
60 #:use-module (gnu packages pkg-config)
bfe3c685 61 #:use-module (gnu packages popt)
e4e5a4d8 62 #:use-module (gnu packages protobuf)
346a829a 63 #:use-module (gnu packages python)
9c38b540 64 #:use-module (gnu packages ruby)
c833ab55 65 #:use-module (gnu packages statistics)
d7678942 66 #:use-module (gnu packages tbb)
2127cedb 67 #:use-module (gnu packages textutils)
43c565d2 68 #:use-module (gnu packages time)
a2950fa4 69 #:use-module (gnu packages tls)
ce7155d5 70 #:use-module (gnu packages vim)
365c8153 71 #:use-module (gnu packages web)
c833ab55 72 #:use-module (gnu packages xml)
f7283db3
RW		 73 #:use-module (gnu packages zip)
74 #:use-module (srfi srfi-1))
4e10a221 75
8dc797fa
BW		 76(define-public aragorn
77 (package
78 (name "aragorn")
79 (version "1.2.36")
80 (source (origin
81 (method url-fetch)
82 (uri (string-append
83 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
84 version ".tgz"))
85 (sha256
86 (base32
87 "1dg7jlz1qpqy88igjxd6ncs11ccsirb36qv1z01a0np4i4jh61mb"))))
88 (build-system gnu-build-system)
89 (arguments
90 `(#:tests? #f ; there are no tests
91 #:phases
92 (modify-phases %standard-phases
93 (delete 'configure)
94 (replace 'build
95 (lambda _
96 (zero? (system* "gcc"
97 "-O3"
98 "-ffast-math"
99 "-finline-functions"
100 "-o"
101 "aragorn"
102 (string-append "aragorn" ,version ".c")))))
103 (replace 'install
104 (lambda* (#:key outputs #:allow-other-keys)
105 (let* ((out (assoc-ref outputs "out"))
106 (bin (string-append out "/bin"))
107 (man (string-append out "/share/man/man1")))
108 (mkdir-p bin)
109 (copy-file "aragorn"
110 (string-append bin "/aragorn"))
111 (mkdir-p man)
112 (copy-file "aragorn.1"
113 (string-append man "/aragorn.1")))
114 #t)))))
115 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
116 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
117 (description
118 "Aragorn identifies transfer RNA, mitochondrial RNA and
119transfer-messenger RNA from nucleotide sequences, based on homology to known
120tRNA consensus sequences and RNA structure. It also outputs the secondary
121structure of the predicted RNA.")
122 (license license:gpl2)))
123
9794180d
RW		 124(define-public bamtools
125 (package
126 (name "bamtools")
127 (version "2.3.0")
128 (source (origin
129 (method url-fetch)
130 (uri (string-append
131 "https://github.com/pezmaster31/bamtools/archive/v"
132 version ".tar.gz"))
133 (file-name (string-append name "-" version ".tar.gz"))
134 (sha256
135 (base32
136 "1brry29bw2xr2l9pqn240rkqwayg85b8qq78zk2zs6nlspk4d018"))))
137 (build-system cmake-build-system)
4702cec2
RW		 138 (arguments
139 `(#:tests? #f ;no "check" target
140 #:phases
141 (modify-phases %standard-phases
142 (add-before
143 'configure 'set-ldflags
144 (lambda* (#:key outputs #:allow-other-keys)
145 (setenv "LDFLAGS"
146 (string-append
147 "-Wl,-rpath="
148 (assoc-ref outputs "out") "/lib/bamtools")))))))
9794180d
RW		 149 (inputs `(("zlib" ,zlib)))
150 (home-page "https://github.com/pezmaster31/bamtools")
151 (synopsis "C++ API and command-line toolkit for working with BAM data")
152 (description
153 "BamTools provides both a C++ API and a command-line toolkit for handling
154BAM files.")
155 (license license:expat)))
156
8dd4ff11
RW		 157(define-public bedops
158 (package
159 (name "bedops")
1bbc3b1d 160 (version "2.4.14")
8dd4ff11
RW		 161 (source (origin
162 (method url-fetch)
163 (uri (string-append "https://github.com/bedops/bedops/archive/v"
164 version ".tar.gz"))
f586c877 165 (file-name (string-append name "-" version ".tar.gz"))
8dd4ff11
RW		 166 (sha256
167 (base32
1bbc3b1d 168 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
8dd4ff11
RW		 169 (build-system gnu-build-system)
170 (arguments
171 '(#:tests? #f
172 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
173 #:phases
174 (alist-cons-after
175 'unpack 'unpack-tarballs
176 (lambda _
177 ;; FIXME: Bedops includes tarballs of minimally patched upstream
178 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
179 ;; libraries because at least one of the libraries (zlib) is
180 ;; patched to add a C++ function definition (deflateInit2cpp).
181 ;; Until the Bedops developers offer a way to link against system
182 ;; libraries we have to build the in-tree copies of these three
183 ;; libraries.
184
185 ;; See upstream discussion:
186 ;; https://github.com/bedops/bedops/issues/124
187
188 ;; Unpack the tarballs to benefit from shebang patching.
189 (with-directory-excursion "third-party"
190 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
191 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
192 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
193 ;; Disable unpacking of tarballs in Makefile.
194 (substitute* "system.mk/Makefile.linux"
195 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
196 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
197 (substitute* "third-party/zlib-1.2.7/Makefile.in"
198 (("^SHELL=.*$") "SHELL=bash\n")))
199 (alist-delete 'configure %standard-phases))))
200 (home-page "https://github.com/bedops/bedops")
201 (synopsis "Tools for high-performance genomic feature operations")
202 (description
203 "BEDOPS is a suite of tools to address common questions raised in genomic
204studies---mostly with regard to overlap and proximity relationships between
205data sets. It aims to be scalable and flexible, facilitating the efficient
206and accurate analysis and management of large-scale genomic data.
207
208BEDOPS provides tools that perform highly efficient and scalable Boolean and
209other set operations, statistical calculations, archiving, conversion and
210other management of genomic data of arbitrary scale. Tasks can be easily
211split by chromosome for distributing whole-genome analyses across a
212computational cluster.")
213 (license license:gpl2+)))
214
81de5647
RW		 215(define-public bedtools
216 (package
217 (name "bedtools")
9b9b7ffd 218 (version "2.25.0")
81de5647
RW		 219 (source (origin
220 (method url-fetch)
221 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
222 version ".tar.gz"))
f586c877 223 (file-name (string-append name "-" version ".tar.gz"))
81de5647
RW		 224 (sha256
225 (base32
9b9b7ffd 226 "1ywcy3yfwzhl905b51l0ffjia55h75vv3mw5xkvib04pp6pj548m"))))
81de5647
RW		 227 (build-system gnu-build-system)
228 (native-inputs `(("python" ,python-2)))
229 (inputs `(("samtools" ,samtools)
230 ("zlib" ,zlib)))
231 (arguments
232 '(#:test-target "test"
233 #:phases
6573ac82 234 (modify-phases %standard-phases
6573ac82
BW		 235 (delete 'configure)
236 (replace 'install
237 (lambda* (#:key outputs #:allow-other-keys)
238 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
239 (for-each (lambda (file)
240 (install-file file bin))
241 (find-files "bin" ".*")))
242 #t)))))
81de5647
RW		 243 (home-page "https://github.com/arq5x/bedtools2")
244 (synopsis "Tools for genome analysis and arithmetic")
245 (description
246 "Collectively, the bedtools utilities are a swiss-army knife of tools for
247a wide-range of genomics analysis tasks. The most widely-used tools enable
248genome arithmetic: that is, set theory on the genome. For example, bedtools
249allows one to intersect, merge, count, complement, and shuffle genomic
250intervals from multiple files in widely-used genomic file formats such as BAM,
251BED, GFF/GTF, VCF.")
252 (license license:gpl2)))
253
a0a71439
RJ		 254(define-public bioawk
255 (package
256 (name "bioawk")
257 (version "1.0")
258 (source (origin
259 (method url-fetch)
260 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
261 version ".tar.gz"))
262 (file-name (string-append name "-" version ".tar.gz"))
263 (sha256
264 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
265 (build-system gnu-build-system)
266 (inputs
267 `(("zlib" ,zlib)))
268 (native-inputs
269 `(("bison" ,bison)))
270 (arguments
271 `(#:tests? #f ; There are no tests to run.
272 ;; Bison must generate files, before other targets can build.
273 #:parallel-build? #f
274 #:phases
275 (modify-phases %standard-phases
276 (delete 'configure) ; There is no configure phase.
277 (replace 'install
278 (lambda* (#:key outputs #:allow-other-keys)
279 (let* ((out (assoc-ref outputs "out"))
280 (bin (string-append out "/bin"))
281 (man (string-append out "/share/man/man1")))
282 (mkdir-p man)
283 (copy-file "awk.1" (string-append man "/bioawk.1"))
284 (install-file "bioawk" bin)))))))
285 (home-page "https://github.com/lh3/bioawk")
286 (synopsis "AWK with bioinformatics extensions")
287 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
288support of several common biological data formats, including optionally gzip'ed
289BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
290also adds a few built-in functions and a command line option to use TAB as the
291input/output delimiter. When the new functionality is not used, bioawk is
292intended to behave exactly the same as the original BWK awk.")
293 (license license:x11)))
294
a2fb1492
RW		 295(define-public python2-pybedtools
296 (package
297 (name "python2-pybedtools")
298 (version "0.6.9")
299 (source (origin
300 (method url-fetch)
301 (uri (string-append
302 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
303 version ".tar.gz"))
304 (sha256
305 (base32
306 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
307 (build-system python-build-system)
308 (arguments `(#:python ,python-2)) ; no Python 3 support
309 (inputs
310 `(("python-cython" ,python2-cython)
311 ("python-matplotlib" ,python2-matplotlib)))
312 (propagated-inputs
313 `(("bedtools" ,bedtools)
314 ("samtools" ,samtools)))
315 (native-inputs
316 `(("python-pyyaml" ,python2-pyyaml)
317 ("python-nose" ,python2-nose)
318 ("python-setuptools" ,python2-setuptools)))
319 (home-page "https://pythonhosted.org/pybedtools/")
320 (synopsis "Python wrapper for BEDtools programs")
321 (description
322 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
323which are widely used for genomic interval manipulation or \"genome algebra\".
324pybedtools extends BEDTools by offering feature-level manipulations from with
325Python.")
326 (license license:gpl2+)))
327
f7283db3
RW		 328(define-public bioperl-minimal
329 (let* ((inputs `(("perl-module-build" ,perl-module-build)
330 ("perl-data-stag" ,perl-data-stag)
331 ("perl-libwww" ,perl-libwww)
332 ("perl-uri" ,perl-uri)))
333 (transitive-inputs
334 (map (compose package-name cadr)
335 (delete-duplicates
336 (concatenate
337 (map (compose package-transitive-target-inputs cadr) inputs))))))
338 (package
339 (name "bioperl-minimal")
340 (version "1.6.924")
341 (source
342 (origin
343 (method url-fetch)
344 (uri (string-append "mirror://cpan/authors/id/C/CJ/CJFIELDS/BioPerl-"
345 version ".tar.gz"))
346 (sha256
347 (base32
348 "1l3npcvvvwjlhkna9dndpfv1hklhrgva013kw96m0n1wpd37ask1"))))
349 (build-system perl-build-system)
350 (arguments
351 `(#:phases
352 (modify-phases %standard-phases
353 (add-after
354 'install 'wrap-programs
355 (lambda* (#:key outputs #:allow-other-keys)
356 ;; Make sure all executables in "bin" find the required Perl
357 ;; modules at runtime. As the PERL5LIB variable contains also
358 ;; the paths of native inputs, we pick the transitive target
359 ;; inputs from %build-inputs.
360 (let* ((out (assoc-ref outputs "out"))
361 (bin (string-append out "/bin/"))
362 (path (string-join
363 (cons (string-append out "/lib/perl5/site_perl")
364 (map (lambda (name)
365 (assoc-ref %build-inputs name))
366 ',transitive-inputs))
367 ":")))
368 (for-each (lambda (file)
369 (wrap-program file
370 `("PERL5LIB" ":" prefix (,path))))
371 (find-files bin "\\.pl$"))
372 #t))))))
373 (inputs inputs)
374 (native-inputs
375 `(("perl-test-most" ,perl-test-most)))
376 (home-page "http://search.cpan.org/dist/BioPerl")
377 (synopsis "Bioinformatics toolkit")
378 (description
379 "BioPerl is the product of a community effort to produce Perl code which
380is useful in biology. Examples include Sequence objects, Alignment objects
381and database searching objects. These objects not only do what they are
382advertised to do in the documentation, but they also interact - Alignment
383objects are made from the Sequence objects, Sequence objects have access to
384Annotation and SeqFeature objects and databases, Blast objects can be
385converted to Alignment objects, and so on. This means that the objects
386provide a coordinated and extensible framework to do computational biology.")
387 (license (package-license perl)))))
388
85c37e29
RW		 389(define-public python-biopython
390 (package
391 (name "python-biopython")
e815c094 392 (version "1.66")
85c37e29
RW		 393 (source (origin
394 (method url-fetch)
e815c094
BW		 395 ;; use PyPi rather than biopython.org to ease updating
396 (uri (pypi-uri "biopython" version))
85c37e29
RW		 397 (sha256
398 (base32
e815c094 399 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))
85c37e29
RW		 400 (build-system python-build-system)
401 (inputs
402 `(("python-numpy" ,python-numpy)))
403 (native-inputs
404 `(("python-setuptools" ,python2-setuptools)))
405 (home-page "http://biopython.org/")
406 (synopsis "Tools for biological computation in Python")
407 (description
408 "Biopython is a set of tools for biological computation including parsers
409for bioinformatics files into Python data structures; interfaces to common
410bioinformatics programs; a standard sequence class and tools for performing
411common operations on them; code to perform data classification; code for
412dealing with alignments; code making it easy to split up parallelizable tasks
413into separate processes; and more.")
414 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
415
416(define-public python2-biopython
417 (package (inherit (package-with-python2 python-biopython))
418 (inputs
419 `(("python2-numpy" ,python2-numpy)))))
420
82c370de
RW		 421(define-public blast+
422 (package
423 (name "blast+")
424 (version "2.2.31")
425 (source (origin
426 (method url-fetch)
427 (uri (string-append
428 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
429 version "/ncbi-blast-" version "+-src.tar.gz"))
430 (sha256
431 (base32
432 "19gq6as4k1jrgsd26158ads6h7v4jca3h4r5dzg1y0m6ya50x5ph"))
433 (modules '((guix build utils)))
434 (snippet
435 '(begin
436 ;; Remove bundled bzip2 and zlib
437 (delete-file-recursively "c++/src/util/compress/bzip2")
438 (delete-file-recursively "c++/src/util/compress/zlib")
439 (substitute* "c++/src/util/compress/Makefile.in"
440 (("bzip2 zlib api") "api"))
441 ;; Remove useless msbuild directory
442 (delete-file-recursively
443 "c++/src/build-system/project_tree_builder/msbuild")
444 #t))))
445 (build-system gnu-build-system)
446 (arguments
447 `(;; There are three(!) tests for this massive library, and all fail with
448 ;; "unparsable timing stats".
449 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
450 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
451 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
452 #:tests? #f
453 #:out-of-source? #t
454 #:parallel-build? #f ; not supported
455 #:phases
456 (modify-phases %standard-phases
457 (add-before
458 'configure 'set-HOME
459 ;; $HOME needs to be set at some point during the configure phase
460 (lambda _ (setenv "HOME" "/tmp") #t))
461 (add-after
462 'unpack 'enter-dir
463 (lambda _ (chdir "c++") #t))
464 (add-after
465 'enter-dir 'fix-build-system
466 (lambda _
467 (define (which* cmd)
468 (cond ((string=? cmd "date")
469 ;; make call to "date" deterministic
470 "date -d @0")
471 ((which cmd)
472 => identity)
473 (else
474 (format (current-error-port)
475 "WARNING: Unable to find absolute path for ~s~%"
476 cmd)
477 #f)))
478
479 ;; Rewrite hardcoded paths to various tools
480 (substitute* (append '("src/build-system/configure.ac"
481 "src/build-system/configure"
482 "scripts/common/impl/if_diff.sh"
483 "scripts/common/impl/run_with_lock.sh"
484 "src/build-system/Makefile.configurables.real"
485 "src/build-system/Makefile.in.top"
486 "src/build-system/Makefile.meta.gmake=no"
487 "src/build-system/Makefile.meta.in"
488 "src/build-system/Makefile.meta_l"
489 "src/build-system/Makefile.meta_p"
490 "src/build-system/Makefile.meta_r"
491 "src/build-system/Makefile.mk.in"
492 "src/build-system/Makefile.requirements"
493 "src/build-system/Makefile.rules_with_autodep.in")
494 (find-files "scripts/common/check" "\\.sh$"))
495 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
496 (or (which* cmd) all)))
497
498 (substitute* (find-files "src/build-system" "^config.*")
499 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
500 (("^PATH=.*") ""))
501
502 ;; rewrite "/var/tmp" in check script
503 (substitute* "scripts/common/check/check_make_unix.sh"
504 (("/var/tmp") "/tmp"))
505
506 ;; do not reset PATH
507 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
508 (("^ *PATH=.*") "")
509 (("action=/bin/") "action=")
510 (("export PATH") ":"))
511 #t))
512 (replace
513 'configure
514 (lambda* (#:key inputs outputs #:allow-other-keys)
515 (let ((out (assoc-ref outputs "out"))
516 (lib (string-append (assoc-ref outputs "lib") "/lib"))
517 (include (string-append (assoc-ref outputs "include")
518 "/include/ncbi-tools++")))
519 ;; The 'configure' script doesn't recognize things like
520 ;; '--enable-fast-install'.
521 (zero? (system* "./configure.orig"
522 (string-append "--with-build-root=" (getcwd) "/build")
523 (string-append "--prefix=" out)
524 (string-append "--libdir=" lib)
525 (string-append "--includedir=" include)
526 (string-append "--with-bz2="
527 (assoc-ref inputs "bzip2"))
528 (string-append "--with-z="
529 (assoc-ref inputs "zlib"))
530 ;; Each library is built twice by default, once
531 ;; with "-static" in its name, and again
532 ;; without.
533 "--without-static"
534 "--with-dll"))))))))
535 (outputs '("out" ; 19 MB
536 "lib" ; 203 MB
537 "include")) ; 32 MB
538 (inputs
539 `(("bzip2" ,bzip2)
540 ("zlib" ,zlib)))
541 (native-inputs
542 `(("cpio" ,cpio)))
543 (home-page "http://blast.ncbi.nlm.nih.gov")
544 (synopsis "Basic local alignment search tool")
545 (description
546 "BLAST is a popular method of performing a DNA or protein sequence
547similarity search, using heuristics to produce results quickly. It also
548calculates an “expect value” that estimates how many matches would have
549occurred at a given score by chance, which can aid a user in judging how much
550confidence to have in an alignment.")
551 ;; Most of the sources are in the public domain, with the following
552 ;; exceptions:
553 ;; * Expat:
554 ;; * ./c++/include/util/bitset/
555 ;; * ./c++/src/html/ncbi_menu*.js
556 ;; * Boost license:
557 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
558 ;; * LGPL 2+:
559 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
560 ;; * ASL 2.0:
561 ;; * ./c++/src/corelib/teamcity_*
562 (license (list license:public-domain
563 license:expat
564 license:boost1.0
565 license:lgpl2.0+
566 license:asl2.0))))
567
6c2b26e2
RW		 568(define-public bless
569 (package
570 (name "bless")
571 (version "1p02")
572 (source (origin
573 (method url-fetch)
574 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
575 version ".tgz"))
576 (sha256
577 (base32
4d75e03a
RW		 578 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
579 (modules '((guix build utils)))
6c2b26e2
RW		 580 (snippet
581 `(begin
582 ;; Remove bundled boost, pigz, zlib, and .git directory
953c1223
RW		 583 ;; FIXME: also remove bundled sources for murmurhash3 and
584 ;; kmc once packaged.
6c2b26e2
RW		 585 (delete-file-recursively "boost")
586 (delete-file-recursively "pigz")
953c1223 587 (delete-file-recursively "google-sparsehash")
6c2b26e2
RW		 588 (delete-file-recursively "zlib")
589 (delete-file-recursively ".git")
590 #t))))
591 (build-system gnu-build-system)
592 (arguments
593 '(#:tests? #f ;no "check" target
594 #:make-flags
595 (list (string-append "ZLIB="
596 (assoc-ref %build-inputs "zlib")
597 "/lib/libz.a")
598 (string-append "LDFLAGS="
599 (string-join '("-lboost_filesystem"
600 "-lboost_system"
601 "-lboost_iostreams"
602 "-lz"
603 "-fopenmp"
604 "-std=c++11"))))
605 #:phases
606 (modify-phases %standard-phases
607 (add-after 'unpack 'do-not-build-bundled-pigz
608 (lambda* (#:key inputs outputs #:allow-other-keys)
609 (substitute* "Makefile"
610 (("cd pigz/pigz-2.3.3; make") ""))
611 #t))
612 (add-after 'unpack 'patch-paths-to-executables
613 (lambda* (#:key inputs outputs #:allow-other-keys)
614 (substitute* "parse_args.cpp"
615 (("kmc_binary = .*")
616 (string-append "kmc_binary = \""
617 (assoc-ref outputs "out")
618 "/bin/kmc\";"))
619 (("pigz_binary = .*")
620 (string-append "pigz_binary = \""
621 (assoc-ref inputs "pigz")
622 "/bin/pigz\";")))
623 #t))
624 (replace 'install
625 (lambda* (#:key outputs #:allow-other-keys)
626 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
627 (for-each (lambda (file)
628 (install-file file bin))
629 '("bless" "kmc/bin/kmc"))
630 #t)))
631 (delete 'configure))))
632 (native-inputs
633 `(("perl" ,perl)))
634 (inputs
635 `(("openmpi" ,openmpi)
636 ("boost" ,boost)
953c1223 637 ("sparsehash" ,sparsehash)
6c2b26e2
RW		 638 ("pigz" ,pigz)
639 ("zlib" ,zlib)))
9641a899 640 (supported-systems '("x86_64-linux"))
4d75e03a 641 (home-page "http://sourceforge.net/p/bless-ec/wiki/Home/")
6c2b26e2
RW		 642 (synopsis "Bloom-filter-based error correction tool for NGS reads")
643 (description
644 "@dfn{Bloom-filter-based error correction solution for high-throughput
645sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
646correction tool for genomic reads produced by @dfn{Next-generation
647sequencing} (NGS). BLESS produces accurate correction results with much less
648memory compared with previous solutions and is also able to tolerate a higher
649false-positive rate. BLESS can extend reads like DNA assemblers to correct
650errors at the end of reads.")
651 (license license:gpl3+)))
652
2c7ee167
RW		 653(define-public bowtie
654 (package
655 (name "bowtie")
0047d26a 656 (version "2.2.6")
2c7ee167
RW		 657 (source (origin
658 (method url-fetch)
659 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
660 version ".tar.gz"))
f586c877 661 (file-name (string-append name "-" version ".tar.gz"))
2c7ee167
RW		 662 (sha256
663 (base32
0047d26a 664 "1ssfvymxfrap6f9pf86s9bvsbqdgka4abr2r7j3mgr4w1l289m86"))
2c7ee167
RW		 665 (modules '((guix build utils)))
666 (snippet
667 '(substitute* "Makefile"
2c7ee167
RW		 668 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
669 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
0047d26a 670 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
2c7ee167
RW		 671 (build-system gnu-build-system)
672 (inputs `(("perl" ,perl)
673 ("perl-clone" ,perl-clone)
674 ("perl-test-deep" ,perl-test-deep)
675 ("perl-test-simple" ,perl-test-simple)
0047d26a
RW		 676 ("python" ,python-2)
677 ("tbb" ,tbb)))
2c7ee167 678 (arguments
0047d26a
RW		 679 '(#:make-flags
680 (list "allall"
681 "WITH_TBB=1"
682 (string-append "prefix=" (assoc-ref %outputs "out")))
2c7ee167
RW		 683 #:phases
684 (alist-delete
685 'configure
686 (alist-replace
0047d26a 687 'check
2c7ee167 688 (lambda* (#:key outputs #:allow-other-keys)
0047d26a
RW		 689 (system* "perl"
690 "scripts/test/simple_tests.pl"
691 "--bowtie2=./bowtie2"
692 "--bowtie2-build=./bowtie2-build"))
693 %standard-phases))))
2c7ee167
RW		 694 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
695 (synopsis "Fast and sensitive nucleotide sequence read aligner")
696 (description
697 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
698reads to long reference sequences. It is particularly good at aligning reads
699of about 50 up to 100s or 1,000s of characters, and particularly good at
700aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
701genome with an FM Index to keep its memory footprint small: for the human
702genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
703gapped, local, and paired-end alignment modes.")
241e1221 704 (supported-systems '("x86_64-linux"))
2c7ee167
RW		 705 (license license:gpl3+)))
706
94ce537e
RW		 707(define-public tophat
708 (package
709 (name "tophat")
710 (version "2.1.0")
711 (source (origin
712 (method url-fetch)
713 (uri (string-append
714 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
715 version ".tar.gz"))
716 (sha256
717 (base32
718 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
fc1adab1 719 (patches (search-patches "tophat-build-with-later-seqan.patch"))
94ce537e
RW		 720 (modules '((guix build utils)))
721 (snippet
722 '(begin
723 ;; Remove bundled SeqAn and samtools
724 (delete-file-recursively "src/SeqAn-1.3")
725 (delete-file-recursively "src/samtools-0.1.18")
726 #t))))
727 (build-system gnu-build-system)
728 (arguments
729 '(#:parallel-build? #f ; not supported
730 #:phases
731 (modify-phases %standard-phases
732 (add-after 'unpack 'use-system-samtools
733 (lambda* (#:key inputs #:allow-other-keys)
734 (substitute* "src/Makefile.in"
735 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
736 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
737 (("SAMPROG = samtools_0\\.1\\.18") "")
738 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
739 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
740 (substitute* '("src/common.cpp"
741 "src/tophat.py")
742 (("samtools_0.1.18") (which "samtools")))
743 (substitute* '("src/common.h"
744 "src/bam2fastx.cpp")
745 (("#include \"bam.h\"") "#include <samtools/bam.h>")
746 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
747 (substitute* '("src/bwt_map.h"
748 "src/map2gtf.h"
749 "src/align_status.h")
750 (("#include <bam.h>") "#include <samtools/bam.h>")
751 (("#include <sam.h>") "#include <samtools/sam.h>"))
752 #t)))))
753 (inputs
754 `(("boost" ,boost)
755 ("bowtie" ,bowtie)
756 ("samtools" ,samtools-0.1)
757 ("ncurses" ,ncurses)
758 ("python" ,python-2)
759 ("perl" ,perl)
760 ("zlib" ,zlib)
761 ("seqan" ,seqan)))
762 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
763 (synopsis "Spliced read mapper for RNA-Seq data")
764 (description
765 "TopHat is a fast splice junction mapper for nucleotide sequence
766reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
767mammalian-sized genomes using the ultra high-throughput short read
768aligner Bowtie, and then analyzes the mapping results to identify
769splice junctions between exons.")
770 ;; TopHat is released under the Boost Software License, Version 1.0
771 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
772 (license license:boost1.0)))
773
9a8336d8
RW		 774(define-public bwa
775 (package
776 (name "bwa")
777 (version "0.7.12")
778 (source (origin
779 (method url-fetch)
780 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
781 version ".tar.bz2"))
782 (sha256
783 (base32
784 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
785 (build-system gnu-build-system)
786 (arguments
787 '(#:tests? #f ;no "check" target
788 #:phases
789 (alist-replace
790 'install
791 (lambda* (#:key outputs #:allow-other-keys)
792 (let ((bin (string-append
793 (assoc-ref outputs "out") "/bin"))
794 (doc (string-append
795 (assoc-ref outputs "out") "/share/doc/bwa"))
796 (man (string-append
797 (assoc-ref outputs "out") "/share/man/man1")))
798 (mkdir-p bin)
799 (mkdir-p doc)
800 (mkdir-p man)
96c46210
LC		 801 (install-file "bwa" bin)
802 (install-file "README.md" doc)
803 (install-file "bwa.1" man)))
9a8336d8
RW		 804 ;; no "configure" script
805 (alist-delete 'configure %standard-phases))))
806 (inputs `(("zlib" ,zlib)))
db94f8c7
RW		 807 ;; Non-portable SSE instructions are used so building fails on platforms
808 ;; other than x86_64.
809 (supported-systems '("x86_64-linux"))
9a8336d8
RW		 810 (home-page "http://bio-bwa.sourceforge.net/")
811 (synopsis "Burrows-Wheeler sequence aligner")
812 (description
813 "BWA is a software package for mapping low-divergent sequences against a
814large reference genome, such as the human genome. It consists of three
815algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
816designed for Illumina sequence reads up to 100bp, while the rest two for
817longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
818features such as long-read support and split alignment, but BWA-MEM, which is
819the latest, is generally recommended for high-quality queries as it is faster
820and more accurate. BWA-MEM also has better performance than BWA-backtrack for
82170-100bp Illumina reads.")
822 (license license:gpl3+)))
823
d29150b5
RW		 824(define-public bwa-pssm
825 (package (inherit bwa)
826 (name "bwa-pssm")
827 (version "0.5.11")
828 (source (origin
829 (method url-fetch)
830 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
831 "archive/" version ".tar.gz"))
832 (file-name (string-append name "-" version ".tar.gz"))
833 (sha256
834 (base32
835 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
836 (build-system gnu-build-system)
837 (inputs
838 `(("gdsl" ,gdsl)
839 ("zlib" ,zlib)
840 ("perl" ,perl)))
841 (home-page "http://bwa-pssm.binf.ku.dk/")
842 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
843 (description
844 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
845the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
846existing aligners it is fast and sensitive. Unlike most other aligners,
847however, it is also adaptible in the sense that one can direct the alignment
848based on known biases within the data set. It is coded as a modification of
849the original BWA alignment program and shares the genome index structure as
850well as many of the command line options.")
851 (license license:gpl3+)))
852
ad641d53
RW		 853(define-public python2-bx-python
854 (package
855 (name "python2-bx-python")
856 (version "0.7.2")
857 (source (origin
858 (method url-fetch)
859 (uri (string-append
860 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
861 version ".tar.gz"))
862 (sha256
863 (base32
864 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
865 (modules '((guix build utils)))
866 (snippet
867 '(substitute* "setup.py"
868 ;; remove dependency on outdated "distribute" module
869 (("^from distribute_setup import use_setuptools") "")
870 (("^use_setuptools\\(\\)") "")))))
871 (build-system python-build-system)
872 (arguments
873 `(#:tests? #f ;tests fail because test data are not included
874 #:python ,python-2))
875 (inputs
876 `(("python-numpy" ,python2-numpy)
877 ("zlib" ,zlib)))
878 (native-inputs
879 `(("python-nose" ,python2-nose)
880 ("python-setuptools" ,python2-setuptools)))
881 (home-page "http://bitbucket.org/james_taylor/bx-python/")
882 (synopsis "Tools for manipulating biological data")
883 (description
884 "bx-python provides tools for manipulating biological data, particularly
885multiple sequence alignments.")
886 (license license:expat)))
887
55a9a8c2
RW		 888(define-public python-pysam
889 (package
890 (name "python-pysam")
d454640c
RW		 891 (version "0.8.4")
892 (source (origin
893 (method url-fetch)
894 (uri (pypi-uri "pysam" version))
895 (sha256
896 (base32
897 "1slx5mb94mzm5qzk52q270sab0sar95j67w1g1k452nz3s9j7krh"))))
55a9a8c2
RW		 898 (build-system python-build-system)
899 (arguments
900 `(#:tests? #f ; tests are excluded in the manifest
901 #:phases
902 (alist-cons-before
903 'build 'set-flags
904 (lambda _
905 (setenv "LDFLAGS" "-lncurses")
906 (setenv "CFLAGS" "-D_CURSES_LIB=1"))
907 %standard-phases)))
908 (inputs
649e9b3b 909 `(("ncurses" ,ncurses)
55a9a8c2 910 ("zlib" ,zlib)))
649e9b3b
RW		 911 (native-inputs
912 `(("python-cython" ,python-cython)
913 ("python-setuptools" ,python-setuptools)))
55a9a8c2
RW		 914 (home-page "https://github.com/pysam-developers/pysam")
915 (synopsis "Python bindings to the SAMtools C API")
916 (description
917 "Pysam is a Python module for reading and manipulating files in the
918SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
919also includes an interface for tabix.")
920 (license license:expat)))
921
922(define-public python2-pysam
923 (package-with-python2 python-pysam))
924
4db9433a
RW		 925(define-public python-twobitreader
926 (package
927 (name "python-twobitreader")
928 (version "3.1.2")
929 (source (origin
930 (method url-fetch)
931 (uri (pypi-uri "twobitreader" version))
932 (sha256
933 (base32
934 "0y408fp6psqzwxpcpqn0wp7fr41dwz8d54wpj6j261fj5q8vs169"))))
935 (properties `((python2-variant . ,(delay python2-twobitreader))))
936 (build-system python-build-system)
937 (native-inputs
938 `(("python-sphinx" ,python-sphinx)))
939 (home-page "https://github.com/benjschiller/twobitreader")
940 (synopsis "Python library for reading .2bit files")
941 (description
942 "twobitreader is a Python library for reading .2bit files as used by the
943UCSC genome browser.")
944 (license license:artistic2.0)))
945
946(define-public python2-twobitreader
947 (let ((base (package-with-python2 (strip-python2-variant python-twobitreader))))
948 (package
949 (inherit base)
950 (native-inputs `(("python2-setuptools" ,python2-setuptools)
951 ,@(package-native-inputs base))))))
952
f94bf198
RW		 953(define-public python-plastid
954 (package
955 (name "python-plastid")
956 (version "0.4.5")
957 (source (origin
958 (method url-fetch)
959 (uri (pypi-uri "plastid" version))
960 (sha256
961 (base32
962 "1nhxw8a5gn9as58i2ih52c5cjwj48ik418pzsjwph3s66mmy9yvq"))))
963 (properties `((python2-variant . ,(delay python2-plastid))))
964 (build-system python-build-system)
965 (arguments
966 ;; Some test files are not included.
967 `(#:tests? #f))
968 (propagated-inputs
969 `(("python-numpy" ,python-numpy)
970 ("python-scipy" ,python-scipy)
971 ("python-pandas" ,python-pandas)
972 ("python-pysam" ,python-pysam)
973 ("python-matplotlib" ,python-matplotlib)
974 ("python-biopython" ,python-biopython)
975 ("python-twobitreader" ,python-twobitreader)))
976 (native-inputs
977 `(("python-cython" ,python-cython)
978 ("python-nose" ,python-nose)))
979 (home-page "https://github.com/joshuagryphon/plastid")
980 (synopsis "Python library for genomic analysis")
981 (description
982 "plastid is a Python library for genomic analysis – in particular,
983high-throughput sequencing data – with an emphasis on simplicity.")
984 (license license:bsd-3)))
985
986(define-public python2-plastid
987 (let ((base (package-with-python2 (strip-python2-variant python-plastid))))
988 (package
989 (inherit base)
4d16cc51
RW		 990 ;; setuptools is required at runtime
991 (propagated-inputs `(("python2-setuptools" ,python2-setuptools)
992 ,@(package-propagated-inputs base))))))
f94bf198 993
6c1305f9
RW		 994(define-public cd-hit
995 (package
996 (name "cd-hit")
997 (version "4.6.5")
998 (source (origin
999 (method url-fetch)
1000 (uri (string-append "https://github.com/weizhongli/cdhit"
1001 "/releases/download/V" version
1002 "/cd-hit-v" version "-2016-0304.tar.gz"))
1003 (sha256
1004 (base32
1005 "15db0hq38yyifwqx9b6l34z14jcq576dmjavhj8a426c18lvnhp3"))))
1006 (build-system gnu-build-system)
1007 (arguments
1008 `(#:tests? #f ; there are no tests
1009 #:make-flags
1010 ;; Executables are copied directly to the PREFIX.
1011 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1012 #:phases
1013 (modify-phases %standard-phases
1014 ;; No "configure" script
1015 (delete 'configure)
1016 ;; Remove sources of non-determinism
1017 (add-after 'unpack 'be-timeless
1018 (lambda _
1019 (substitute* "cdhit-utility.c++"
1020 ((" \\(built on \" __DATE__ \"\\)") ""))
1021 (substitute* "cdhit-common.c++"
1022 (("__DATE__") "\"0\"")
1023 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1024 #t))
1025 ;; The "install" target does not create the target directory
1026 (add-before 'install 'create-target-dir
1027 (lambda* (#:key outputs #:allow-other-keys)
1028 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1029 #t)))))
1030 (inputs
1031 `(("perl" ,perl)))
1032 (home-page "http://weizhongli-lab.org/cd-hit/")
1033 (synopsis "Cluster and compare protein or nucleotide sequences")
1034 (description
1035 "CD-HIT is a program for clustering and comparing protein or nucleotide
1036sequences. CD-HIT is designed to be fast and handle extremely large
1037databases.")
1038 ;; The manual says: "It can be copied under the GNU General Public License
1039 ;; version 2 (GPLv2)."
1040 (license license:gpl2)))
1041
810cff85
RW		 1042(define-public clipper
1043 (package
1044 (name "clipper")
1045 (version "0.3.0")
1046 (source (origin
1047 (method url-fetch)
1048 (uri (string-append
1049 "https://github.com/YeoLab/clipper/archive/"
1050 version ".tar.gz"))
9ab5ea44 1051 (file-name (string-append name "-" version ".tar.gz"))
810cff85
RW		 1052 (sha256
1053 (base32
1054 "1q7jpimsqln7ic44i8v2rx2haj5wvik8hc1s2syd31zcn0xk1iyq"))
1055 (modules '((guix build utils)))
1056 (snippet
1057 ;; remove unnecessary setup dependency
1058 '(substitute* "setup.py"
1059 (("setup_requires = .*") "")))))
1060 (build-system python-build-system)
1061 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1062 (inputs
1063 `(("htseq" ,htseq)
1064 ("python-pybedtools" ,python2-pybedtools)
1065 ("python-cython" ,python2-cython)
1066 ("python-scikit-learn" ,python2-scikit-learn)
1067 ("python-matplotlib" ,python2-matplotlib)
1068 ("python-pysam" ,python2-pysam)
1069 ("python-numpy" ,python2-numpy)
1070 ("python-scipy" ,python2-scipy)))
1071 (native-inputs
1072 `(("python-mock" ,python2-mock) ; for tests
1073 ("python-pytz" ,python2-pytz) ; for tests
1074 ("python-setuptools" ,python2-setuptools)))
1075 (home-page "https://github.com/YeoLab/clipper")
1076 (synopsis "CLIP peak enrichment recognition")
1077 (description
1078 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1079 (license license:gpl2)))
1080
6a35566d
RS		 1081(define-public codingquarry
1082 (package
1083 (name "codingquarry")
1084 (version "2.0")
1085 (source (origin
1086 (method url-fetch)
1087 (uri (string-append
1088 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1089 version ".tar.gz"))
1090 (sha256
1091 (base32
1092 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1093 (build-system gnu-build-system)
1094 (arguments
1095 '(#:tests? #f ; no "check" target
1096 #:phases
1097 (modify-phases %standard-phases
1098 (delete 'configure)
1099 (replace 'install
1100 (lambda* (#:key outputs #:allow-other-keys)
1101 (let* ((out (assoc-ref outputs "out"))
1102 (bin (string-append out "/bin"))
1103 (doc (string-append out "/share/doc/codingquarry")))
1104 (install-file "INSTRUCTIONS.pdf" doc)
1105 (copy-recursively "QuarryFiles"
1106 (string-append out "/QuarryFiles"))
1107 (install-file "CodingQuarry" bin)
1108 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1109 (inputs `(("openmpi" ,openmpi)))
1110 (native-search-paths
1111 (list (search-path-specification
1112 (variable "QUARRY_PATH")
1113 (files '("QuarryFiles")))))
1114 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1115 (synopsis "Fungal gene predictor")
1116 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1117gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1118 (home-page "https://sourceforge.net/projects/codingquarry/")
1119 (license license:gpl3+)))
1120
36742f43
RW		 1121(define-public couger
1122 (package
1123 (name "couger")
1124 (version "1.8.2")
1125 (source (origin
1126 (method url-fetch)
1127 (uri (string-append
1128 "http://couger.oit.duke.edu/static/assets/COUGER"
1129 version ".zip"))
1130 (sha256
1131 (base32
1132 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1133 (build-system gnu-build-system)
1134 (arguments
1135 `(#:tests? #f
1136 #:phases
1137 (modify-phases %standard-phases
1138 (delete 'configure)
1139 (delete 'build)
1140 (replace
1141 'install
1142 (lambda* (#:key outputs #:allow-other-keys)
1143 (let ((out (assoc-ref outputs "out")))
1144 (copy-recursively "src" (string-append out "/src"))
1145 (mkdir (string-append out "/bin"))
1146 ;; Add "src" directory to module lookup path.
1147 (substitute* "couger"
1148 (("from argparse")
1149 (string-append "import sys\nsys.path.append(\""
1150 out "\")\nfrom argparse")))
1151 (copy-file "couger" (string-append out "/bin/couger")))
1152 #t))
1153 (add-after
1154 'install 'wrap-program
1155 (lambda* (#:key inputs outputs #:allow-other-keys)
1156 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1157 (let* ((out (assoc-ref outputs "out"))
1158 (path (getenv "PYTHONPATH")))
1159 (wrap-program (string-append out "/bin/couger")
1160 `("PYTHONPATH" ":" prefix (,path))))
1161 #t)))))
1162 (inputs
1163 `(("python" ,python-2)
1164 ("python2-pillow" ,python2-pillow)
1165 ("python2-numpy" ,python2-numpy)
1166 ("python2-scipy" ,python2-scipy)
1167 ("python2-matplotlib" ,python2-matplotlib)))
1168 (propagated-inputs
1169 `(("r" ,r)
1170 ("libsvm" ,libsvm)
1171 ("randomjungle" ,randomjungle)))
1172 (native-inputs
1173 `(("unzip" ,unzip)))
1174 (home-page "http://couger.oit.duke.edu")
1175 (synopsis "Identify co-factors in sets of genomic regions")
1176 (description
1177 "COUGER can be applied to any two sets of genomic regions bound by
1178paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1179putative co-factors that provide specificity to each TF. The framework
1180determines the genomic targets uniquely-bound by each TF, and identifies a
1181small set of co-factors that best explain the in vivo binding differences
1182between the two TFs.
1183
1184COUGER uses classification algorithms (support vector machines and random
1185forests) with features that reflect the DNA binding specificities of putative
1186co-factors. The features are generated either from high-throughput TF-DNA
1187binding data (from protein binding microarray experiments), or from large
1188collections of DNA motifs.")
1189 (license license:gpl3+)))
1190
bfe3c685
RW		 1191(define-public clustal-omega
1192 (package
1193 (name "clustal-omega")
1194 (version "1.2.1")
1195 (source (origin
1196 (method url-fetch)
1197 (uri (string-append
1198 "http://www.clustal.org/omega/clustal-omega-"
1199 version ".tar.gz"))
1200 (sha256
1201 (base32
1202 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1203 (build-system gnu-build-system)
1204 (inputs
1205 `(("argtable" ,argtable)))
1206 (home-page "http://www.clustal.org/omega/")
1207 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1208 (description
1209 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1210program for protein and DNA/RNA. It produces high quality MSAs and is capable
1211of handling data-sets of hundreds of thousands of sequences in reasonable
1212time.")
1213 (license license:gpl2+)))
1214
191c7101
RW		 1215(define-public crossmap
1216 (package
1217 (name "crossmap")
61d5fd03 1218 (version "0.2.1")
191c7101
RW		 1219 (source (origin
1220 (method url-fetch)
1221 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1222 version ".tar.gz"))
1223 (sha256
1224 (base32
61d5fd03
RW		 1225 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1226 ;; This patch has been sent upstream already and is available
1227 ;; for download from Sourceforge, but it has not been merged.
fc1adab1 1228 (patches (search-patches "crossmap-allow-system-pysam.patch"))
191c7101
RW		 1229 (modules '((guix build utils)))
1230 ;; remove bundled copy of pysam
1231 (snippet
1232 '(delete-file-recursively "lib/pysam"))))
1233 (build-system python-build-system)
1234 (arguments
1235 `(#:python ,python-2
1236 #:phases
1237 (alist-cons-after
1238 'unpack 'set-env
1239 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1240 %standard-phases)))
1241 (inputs
1242 `(("python-numpy" ,python2-numpy)
1243 ("python-pysam" ,python2-pysam)
1244 ("zlib" ,zlib)))
1245 (native-inputs
1246 `(("python-cython" ,python2-cython)
1247 ("python-nose" ,python2-nose)
1248 ("python-setuptools" ,python2-setuptools)))
1249 (home-page "http://crossmap.sourceforge.net/")
1250 (synopsis "Convert genome coordinates between assemblies")
1251 (description
1252 "CrossMap is a program for conversion of genome coordinates or annotation
1253files between different genome assemblies. It supports most commonly used
1254file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1255 (license license:gpl2+)))
1256
3a40a92c
RW		 1257(define-public cufflinks
1258 (package
1259 (name "cufflinks")
1260 (version "2.2.1")
1261 (source (origin
1262 (method url-fetch)
1263 (uri (string-append "http://cole-trapnell-lab.github.io/"
1264 "cufflinks/assets/downloads/cufflinks-"
1265 version ".tar.gz"))
1266 (sha256
1267 (base32
1268 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1269 (build-system gnu-build-system)
1270 (arguments
1271 `(#:make-flags
1272 (list
1273 ;; The includes for "eigen" are located in a subdirectory.
1274 (string-append "EIGEN_CPPFLAGS="
1275 "-I" (assoc-ref %build-inputs "eigen")
1276 "/include/eigen3/")
1277 ;; Cufflinks must be linked with various boost libraries.
1278 (string-append "LDFLAGS="
1279 (string-join '("-lboost_system"
1280 "-lboost_serialization"
1281 "-lboost_thread"))))
1282 #:phases
1283 (modify-phases %standard-phases
1284 (add-after 'unpack 'fix-search-for-bam
1285 (lambda _
1286 (substitute* '("ax_bam.m4"
1287 "configure"
1288 "src/hits.h")
1289 (("<bam/sam\\.h>") "<samtools/sam.h>")
1290 (("<bam/bam\\.h>") "<samtools/bam.h>")
1291 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1292 #t)))
1293 #:configure-flags
1294 (list (string-append "--with-bam="
1295 (assoc-ref %build-inputs "samtools")))))
1296 (inputs
1297 `(("eigen" ,eigen)
1298 ("samtools" ,samtools-0.1)
1299 ("htslib" ,htslib)
1300 ("boost" ,boost)
1301 ("python" ,python-2)
1302 ("zlib" ,zlib)))
1303 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1304 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1305 (description
1306 "Cufflinks assembles RNA transcripts, estimates their abundances,
1307and tests for differential expression and regulation in RNA-Seq
1308samples. It accepts aligned RNA-Seq reads and assembles the
1309alignments into a parsimonious set of transcripts. Cufflinks then
1310estimates the relative abundances of these transcripts based on how
1311many reads support each one, taking into account biases in library
1312preparation protocols.")
1313 (license license:boost1.0)))
1314
8e913213
RW		 1315(define-public cutadapt
1316 (package
1317 (name "cutadapt")
1318 (version "1.8")
1319 (source (origin
1320 (method url-fetch)
1321 (uri (string-append
1322 "https://github.com/marcelm/cutadapt/archive/v"
1323 version ".tar.gz"))
1324 (file-name (string-append name "-" version ".tar.gz"))
1325 (sha256
1326 (base32
1327 "161bp87y6gd6r5bmvjpn2b1k942i3fizfpa139f0jn6jv1wcp5h5"))))
1328 (build-system python-build-system)
1329 (arguments
1330 ;; tests must be run after install
1331 `(#:phases (alist-cons-after
1332 'install 'check
1333 (lambda* (#:key inputs outputs #:allow-other-keys)
1334 (setenv "PYTHONPATH"
1335 (string-append
1336 (getenv "PYTHONPATH")
1337 ":" (assoc-ref outputs "out")
1338 "/lib/python"
1339 (string-take (string-take-right
1340 (assoc-ref inputs "python") 5) 3)
1341 "/site-packages"))
1342 (zero? (system* "nosetests" "-P" "tests")))
1343 (alist-delete 'check %standard-phases))))
1344 (native-inputs
1345 `(("python-cython" ,python-cython)
1346 ("python-nose" ,python-nose)
1347 ("python-setuptools" ,python-setuptools)))
1348 (home-page "https://code.google.com/p/cutadapt/")
1349 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1350 (description
1351 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1352other types of unwanted sequence from high-throughput sequencing reads.")
1353 (license license:expat)))
1354
1baee943
RW		 1355(define-public libbigwig
1356 (package
1357 (name "libbigwig")
1358 (version "0.1.4")
1359 (source (origin
1360 (method url-fetch)
1361 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1362 "archive/" version ".tar.gz"))
1363 (file-name (string-append name "-" version ".tar.gz"))
1364 (sha256
1365 (base32
1366 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1367 (build-system gnu-build-system)
1368 (arguments
1369 `(#:test-target "test"
1370 #:make-flags
1371 (list "CC=gcc"
1372 (string-append "prefix=" (assoc-ref %outputs "out")))
1373 #:phases
1374 (modify-phases %standard-phases
1375 (delete 'configure)
1376 (add-before 'check 'disable-curl-test
1377 (lambda _
1378 (substitute* "Makefile"
1379 (("./test/testRemote.*") ""))
1380 #t))
1381 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1382 ;; there has not yet been a release containing this change.
1383 (add-before 'install 'create-target-dirs
1384 (lambda* (#:key outputs #:allow-other-keys)
1385 (let ((out (assoc-ref outputs "out")))
1386 (mkdir-p (string-append out "/lib"))
1387 (mkdir-p (string-append out "/include"))
1388 #t))))))
1389 (inputs
1390 `(("zlib" ,zlib)
1391 ("curl" ,curl)))
1392 (native-inputs
1393 `(("doxygen" ,doxygen)))
1394 (home-page "https://github.com/dpryan79/libBigWig")
1395 (synopsis "C library for handling bigWig files")
1396 (description
1397 "This package provides a C library for parsing local and remote BigWig
1398files.")
1399 (license license:expat)))
1400
69e0e03c
RW		 1401(define-public python-pybigwig
1402 (package
1403 (name "python-pybigwig")
1404 (version "0.2.5")
1405 (source (origin
1406 (method url-fetch)
1407 (uri (pypi-uri "pyBigWig" version))
1408 (sha256
1409 (base32
1410 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1411 (modules '((guix build utils)))
1412 (snippet
1413 '(begin
1414 ;; Delete bundled libBigWig sources
1415 (delete-file-recursively "libBigWig")))))
1416 (build-system python-build-system)
1417 (arguments
1418 `(#:phases
1419 (modify-phases %standard-phases
1420 (add-after 'unpack 'link-with-libBigWig
1421 (lambda* (#:key inputs #:allow-other-keys)
1422 (substitute* "setup.py"
1423 (("libs=\\[") "libs=[\"BigWig\", "))
1424 #t)))))
1425 (inputs
1426 `(("libbigwig" ,libbigwig)
1427 ("zlib" ,zlib)
1428 ("curl" ,curl)))
1429 (home-page "https://github.com/dpryan79/pyBigWig")
1430 (synopsis "Access bigWig files in Python using libBigWig")
1431 (description
1432 "This package provides Python bindings to the libBigWig library for
1433accessing bigWig files.")
1434 (license license:expat)))
1435
1436(define-public python2-pybigwig
1437 (let ((pybigwig (package-with-python2 python-pybigwig)))
1438 (package (inherit pybigwig)
1439 (native-inputs
1440 `(("python-setuptools" ,python2-setuptools))))))
1441
1921b1de
RW		 1442(define-public deeptools
1443 (package
1444 (name "deeptools")
3acb8c85 1445 (version "2.1.1")
1921b1de
RW		 1446 (source (origin
1447 (method url-fetch)
3acb8c85
RW		 1448 (uri (string-append "https://github.com/fidelram/deepTools/"
1449 "archive/" version ".tar.gz"))
1921b1de
RW		 1450 (file-name (string-append name "-" version ".tar.gz"))
1451 (sha256
1452 (base32
3acb8c85 1453 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
1921b1de
RW		 1454 (build-system python-build-system)
1455 (arguments
1456 `(#:python ,python-2))
14bda1ff 1457 (inputs
1921b1de
RW		 1458 `(("python-scipy" ,python2-scipy)
1459 ("python-numpy" ,python2-numpy)
3acb8c85 1460 ("python-numpydoc" ,python2-numpydoc)
1921b1de
RW		 1461 ("python-matplotlib" ,python2-matplotlib)
1462 ("python-bx-python" ,python2-bx-python)
3acb8c85
RW		 1463 ("python-pysam" ,python2-pysam)
1464 ("python-pybigwig" ,python2-pybigwig)))
1921b1de
RW		 1465 (native-inputs
1466 `(("python-mock" ,python2-mock) ;for tests
1467 ("python-pytz" ,python2-pytz) ;for tests
1468 ("python-setuptools" ,python2-setuptools)))
1469 (home-page "https://github.com/fidelram/deepTools")
1470 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
1471 (description
1472 "DeepTools addresses the challenge of handling the large amounts of data
1473that are now routinely generated from DNA sequencing centers. To do so,
1474deepTools contains useful modules to process the mapped reads data to create
1475coverage files in standard bedGraph and bigWig file formats. By doing so,
1476deepTools allows the creation of normalized coverage files or the comparison
1477between two files (for example, treatment and control). Finally, using such
1478normalized and standardized files, multiple visualizations can be created to
1479identify enrichments with functional annotations of the genome.")
1480 (license license:gpl3+)))
1481
684bf7c7
BW		 1482(define-public diamond
1483 (package
1484 (name "diamond")
1485 (version "0.7.9")
1486 (source (origin
1487 (method url-fetch)
1488 (uri (string-append
1489 "https://github.com/bbuchfink/diamond/archive/v"
1490 version ".tar.gz"))
1491 (file-name (string-append name "-" version ".tar.gz"))
1492 (sha256
1493 (base32
1494 "0hfkcfv9f76h5brbyw9fyvmc0l9cmbsxrcdqk0fa9xv82zj47p15"))
1495 (snippet '(begin
1496 (delete-file "bin/diamond")
1497 #t))))
1498 (build-system gnu-build-system)
1499 (arguments
1500 '(#:tests? #f ;no "check" target
1501 #:phases
1502 (modify-phases %standard-phases
1503 (add-after 'unpack 'enter-source-dir
1504 (lambda _
1505 (chdir "src")
1506 #t))
1507 (delete 'configure)
1508 (replace 'install
1509 (lambda* (#:key outputs #:allow-other-keys)
1510 (let ((bin (string-append (assoc-ref outputs "out")
1511 "/bin")))
1512 (mkdir-p bin)
1513 (copy-file "../bin/diamond"
1514 (string-append bin "/diamond"))
1515 #t))))))
1516 (native-inputs
1517 `(("bc" ,bc)))
1518 (inputs
1519 `(("boost" ,boost)
1520 ("zlib" ,zlib)))
1521 (home-page "https://github.com/bbuchfink/diamond")
1522 (synopsis "Accelerated BLAST compatible local sequence aligner")
1523 (description
1524 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
1525translated DNA query sequences against a protein reference database (BLASTP
1526and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
1527reads at a typical sensitivity of 90-99% relative to BLAST depending on the
1528data and settings.")
d9c44e9c
BW		 1529 ;; diamond fails to build on other platforms
1530 ;; https://github.com/bbuchfink/diamond/issues/18
1531 (supported-systems '("x86_64-linux"))
684bf7c7
BW		 1532 (license (license:non-copyleft "file://src/COPYING"
1533 "See src/COPYING in the distribution."))))
1534
365c8153
RW		 1535(define-public edirect
1536 (package
1537 (name "edirect")
83b84fa8 1538 (version "4.10")
365c8153
RW		 1539 (source (origin
1540 (method url-fetch)
83b84fa8
RW		 1541 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
1542 "versions/2016-05-03/edirect.tar.gz"))
365c8153
RW		 1543 (sha256
1544 (base32
83b84fa8 1545 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
365c8153
RW		 1546 (build-system perl-build-system)
1547 (arguments
1548 `(#:tests? #f ;no "check" target
1549 #:phases
1550 (modify-phases %standard-phases
1551 (delete 'configure)
1552 (delete 'build)
1553 (replace 'install
1554 (lambda* (#:key outputs #:allow-other-keys)
1555 (let ((target (string-append (assoc-ref outputs "out")
1556 "/bin")))
1557 (mkdir-p target)
1558 (copy-file "edirect.pl"
1559 (string-append target "/edirect.pl"))
1560 #t)))
1561 (add-after
1562 'install 'wrap-program
1563 (lambda* (#:key inputs outputs #:allow-other-keys)
1564 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
1565 (let* ((out (assoc-ref outputs "out"))
1566 (path (getenv "PERL5LIB")))
1567 (wrap-program (string-append out "/bin/edirect.pl")
1568 `("PERL5LIB" ":" prefix (,path)))))))))
1569 (inputs
1570 `(("perl-html-parser" ,perl-html-parser)
1571 ("perl-encode-locale" ,perl-encode-locale)
1572 ("perl-file-listing" ,perl-file-listing)
1573 ("perl-html-tagset" ,perl-html-tagset)
1574 ("perl-html-tree" ,perl-html-tree)
1575 ("perl-http-cookies" ,perl-http-cookies)
1576 ("perl-http-date" ,perl-http-date)
1577 ("perl-http-message" ,perl-http-message)
1578 ("perl-http-negotiate" ,perl-http-negotiate)
1579 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
1580 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
1581 ("perl-net-http" ,perl-net-http)
1582 ("perl-uri" ,perl-uri)
1583 ("perl-www-robotrules" ,perl-www-robotrules)
1584 ("perl" ,perl)))
3d51ec91 1585 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
365c8153
RW		 1586 (synopsis "Tools for accessing the NCBI's set of databases")
1587 (description
1588 "Entrez Direct (EDirect) is a method for accessing the National Center
1589for Biotechnology Information's (NCBI) set of interconnected
1590databases (publication, sequence, structure, gene, variation, expression,
1591etc.) from a terminal. Functions take search terms from command-line
1592arguments. Individual operations are combined to build multi-step queries.
1593Record retrieval and formatting normally complete the process.
1594
1595EDirect also provides an argument-driven function that simplifies the
1596extraction of data from document summaries or other results that are returned
1597in structured XML format. This can eliminate the need for writing custom
1598software to answer ad hoc questions.")
1599 (license license:public-domain)))
1600
e4e5a4d8
RW		 1601(define-public express
1602 (package
1603 (name "express")
1604 (version "1.5.1")
1605 (source (origin
1606 (method url-fetch)
1607 (uri
1608 (string-append
1609 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
1610 version "/express-" version "-src.tgz"))
1611 (sha256
1612 (base32
1613 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
1614 (build-system cmake-build-system)
1615 (arguments
1616 `(#:tests? #f ;no "check" target
1617 #:phases
1618 (alist-cons-after
1619 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
1620 (lambda* (#:key inputs #:allow-other-keys)
1621 (substitute* "CMakeLists.txt"
1622 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
1623 "set(Boost_USE_STATIC_LIBS OFF)")
1624 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
1625 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
1626 (substitute* "src/CMakeLists.txt"
1627 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
1628 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
1629 #t)
1630 %standard-phases)))
1631 (inputs
1632 `(("boost" ,boost)
1633 ("bamtools" ,bamtools)
1634 ("protobuf" ,protobuf)
1635 ("zlib" ,zlib)))
1636 (home-page "http://bio.math.berkeley.edu/eXpress")
1637 (synopsis "Streaming quantification for high-throughput genomic sequencing")
1638 (description
1639 "eXpress is a streaming tool for quantifying the abundances of a set of
1640target sequences from sampled subsequences. Example applications include
1641transcript-level RNA-Seq quantification, allele-specific/haplotype expression
1642analysis (from RNA-Seq), transcription factor binding quantification in
1643ChIP-Seq, and analysis of metagenomic data.")
1644 (license license:artistic2.0)))
1645
f3674b1c
BW		 1646(define-public express-beta-diversity
1647 (package
1648 (name "express-beta-diversity")
1649 (version "1.0.7")
1650 (source (origin
1651 (method url-fetch)
1652 (uri
1653 (string-append
1654 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
1655 version ".tar.gz"))
1656 (file-name (string-append name "-" version ".tar.gz"))
1657 (sha256
1658 (base32
1659 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
1660 (build-system gnu-build-system)
1661 (arguments
1662 `(#:phases
1663 (modify-phases %standard-phases
1664 (delete 'configure)
1665 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
1666 (replace 'check
1667 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
1668 "-u"))))
1669 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
1670 (replace 'install
1671 (lambda* (#:key outputs #:allow-other-keys)
1672 (let ((bin (string-append (assoc-ref outputs "out")
1673 "/bin")))
1674 (mkdir-p bin)
1675 (copy-file "scripts/convertToEBD.py"
1676 (string-append bin "/convertToEBD.py"))
1677 (copy-file "bin/ExpressBetaDiversity"
1678 (string-append bin "/ExpressBetaDiversity"))
1679 #t))))))
1680 (inputs
1681 `(("python" ,python-2)))
1682 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
1683 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
1684 (description
1685 "Express Beta Diversity (EBD) calculates ecological beta diversity
1686(dissimilarity) measures between biological communities. EBD implements a
1687variety of diversity measures including those that make use of phylogenetic
1688similarity of community members.")
1689 (license license:gpl3+)))
1690
12b04cbe
BW		 1691(define-public fasttree
1692 (package
1693 (name "fasttree")
1694 (version "2.1.8")
1695 (source (origin
1696 (method url-fetch)
1697 (uri (string-append
1698 "http://www.microbesonline.org/fasttree/FastTree-"
1699 version ".c"))
1700 (sha256
1701 (base32
1702 "0dzqc9vr9iiiw21y159xfjl2z90vw0y7r4x6456pcaxiy5hd2wmi"))))
1703 (build-system gnu-build-system)
1704 (arguments
1705 `(#:tests? #f ; no "check" target
1706 #:phases
1707 (modify-phases %standard-phases
1708 (delete 'unpack)
1709 (delete 'configure)
1710 (replace 'build
1711 (lambda* (#:key source #:allow-other-keys)
1712 (and (zero? (system* "gcc"
1713 "-O3"
1714 "-finline-functions"
1715 "-funroll-loops"
1716 "-Wall"
1717 "-o"
1718 "FastTree"
1719 source
1720 "-lm"))
1721 (zero? (system* "gcc"
1722 "-DOPENMP"
1723 "-fopenmp"
1724 "-O3"
1725 "-finline-functions"
1726 "-funroll-loops"
1727 "-Wall"
1728 "-o"
1729 "FastTreeMP"
1730 source
1731 "-lm")))))
1732 (replace 'install
1733 (lambda* (#:key outputs #:allow-other-keys)
1734 (let ((bin (string-append (assoc-ref outputs "out")
1735 "/bin")))
1736 (mkdir-p bin)
1737 (copy-file "FastTree"
1738 (string-append bin "/FastTree"))
1739 (copy-file "FastTreeMP"
1740 (string-append bin "/FastTreeMP"))
1741 #t))))))
1742 (home-page "http://www.microbesonline.org/fasttree")
1743 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
1744 (description
1745 "FastTree can handle alignments with up to a million of sequences in a
1746reasonable amount of time and memory. For large alignments, FastTree is
1747100-1,000 times faster than PhyML 3.0 or RAxML 7.")
1748 (license license:gpl2+)))
1749
2127cedb
RW		 1750(define-public fastx-toolkit
1751 (package
1752 (name "fastx-toolkit")
1753 (version "0.0.14")
1754 (source (origin
1755 (method url-fetch)
1756 (uri
1757 (string-append
1758 "https://github.com/agordon/fastx_toolkit/releases/download/"
1759 version "/fastx_toolkit-" version ".tar.bz2"))
1760 (sha256
1761 (base32
1762 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
1763 (build-system gnu-build-system)
1764 (inputs
1765 `(("libgtextutils" ,libgtextutils)))
1766 (native-inputs
1767 `(("pkg-config" ,pkg-config)))
1768 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
1769 (synopsis "Tools for FASTA/FASTQ file preprocessing")
1770 (description
1771 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
1772FASTA/FASTQ files preprocessing.
1773
1774Next-Generation sequencing machines usually produce FASTA or FASTQ files,
1775containing multiple short-reads sequences. The main processing of such
1776FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
1777is sometimes more productive to preprocess the files before mapping the
1778sequences to the genome---manipulating the sequences to produce better mapping
1779results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
1780 (license license:agpl3+)))
1781
d7678942
RW		 1782(define-public flexbar
1783 (package
1784 (name "flexbar")
1785 (version "2.5")
1786 (source (origin
1787 (method url-fetch)
1788 (uri
1789 (string-append "mirror://sourceforge/flexbar/"
1790 version "/flexbar_v" version "_src.tgz"))
1791 (sha256
1792 (base32
1793 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
1794 (build-system cmake-build-system)
1795 (arguments
4ca009c0 1796 `(#:configure-flags (list
d7678942
RW		 1797 (string-append "-DFLEXBAR_BINARY_DIR="
1798 (assoc-ref %outputs "out")
1799 "/bin/"))
1800 #:phases
4ca009c0
RW		 1801 (alist-replace
1802 'check
1803 (lambda* (#:key outputs #:allow-other-keys)
1804 (setenv "PATH" (string-append
1805 (assoc-ref outputs "out") "/bin:"
1806 (getenv "PATH")))
1807 (chdir "../flexbar_v2.5_src/test")
1808 (zero? (system* "bash" "flexbar_validate.sh")))
1809 (alist-delete 'install %standard-phases))))
d7678942
RW		 1810 (inputs
1811 `(("tbb" ,tbb)
1812 ("zlib" ,zlib)))
1813 (native-inputs
1814 `(("pkg-config" ,pkg-config)
1815 ("seqan" ,seqan)))
1816 (home-page "http://flexbar.sourceforge.net")
1817 (synopsis "Barcode and adapter removal tool for sequencing platforms")
1818 (description
1819 "Flexbar preprocesses high-throughput nucleotide sequencing data
1820efficiently. It demultiplexes barcoded runs and removes adapter sequences.
1821Moreover, trimming and filtering features are provided. Flexbar increases
1822read mapping rates and improves genome and transcriptome assemblies. It
1823supports next-generation sequencing data in fasta/q and csfasta/q format from
1824Illumina, Roche 454, and the SOLiD platform.")
1825 (license license:gpl3)))
1826
19f4554c
BW		 1827(define-public fraggenescan
1828 (package
1829 (name "fraggenescan")
1830 (version "1.20")
1831 (source
1832 (origin
1833 (method url-fetch)
1834 (uri
1835 (string-append "mirror://sourceforge/fraggenescan/"
1836 "FragGeneScan" version ".tar.gz"))
1837 (sha256
1838 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
1839 (build-system gnu-build-system)
1840 (arguments
1841 `(#:phases
1842 (modify-phases %standard-phases
1843 (delete 'configure)
1844 (add-before 'build 'patch-paths
1845 (lambda* (#:key outputs #:allow-other-keys)
1846 (let* ((out (string-append (assoc-ref outputs "out")))
1847 (share (string-append out "/share/fraggenescan/")))
1848 (substitute* "run_FragGeneScan.pl"
1849 (("system\\(\"rm")
1850 (string-append "system(\"" (which "rm")))
1851 (("system\\(\"mv")
1852 (string-append "system(\"" (which "mv")))
1853 ;; This script and other programs expect the training files
1854 ;; to be in the non-standard location bin/train/XXX. Change
1855 ;; this to be share/fraggenescan/train/XXX instead.
1856 (("^\\$train.file = \\$dir.*")
1857 (string-append "$train_file = \""
1858 share
1859 "train/\".$FGS_train_file;")))
1860 (substitute* "run_hmm.c"
1861 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
1862 (string-append " strcpy(train_dir, \"" share "/train/\");")))
1863 (substitute* "post_process.pl"
1864 (("^my \\$dir = substr.*")
1865 (string-append "my $dir = \"" share "\";"))))
1866 #t))
1867 (replace 'build
1868 (lambda _ (and (zero? (system* "make" "clean"))
1869 (zero? (system* "make" "fgs")))))
1870 (replace 'install
1871 (lambda* (#:key outputs #:allow-other-keys)
1872 (let* ((out (string-append (assoc-ref outputs "out")))
1873 (bin (string-append out "/bin/"))
1874 (share (string-append out "/share/fraggenescan/train")))
1875 (install-file "run_FragGeneScan.pl" bin)
1876 (install-file "FragGeneScan" bin)
1877 (install-file "FGS_gff.py" bin)
1878 (install-file "post_process.pl" bin)
1879 (copy-recursively "train" share))))
1880 (delete 'check)
1881 (add-after 'install 'post-install-check
1882 ;; In lieu of 'make check', run one of the examples and check the
1883 ;; output files gets created.
1884 (lambda* (#:key outputs #:allow-other-keys)
1885 (let* ((out (string-append (assoc-ref outputs "out")))
1886 (bin (string-append out "/bin/")))
1887 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
1888 "-genome=./example/NC_000913.fna"
1889 "-out=./test2"
1890 "-complete=1"
1891 "-train=complete"))
1892 (file-exists? "test2.faa")
1893 (file-exists? "test2.ffn")
1894 (file-exists? "test2.gff")
1895 (file-exists? "test2.out"))))))))
1896 (inputs
1897 `(("perl" ,perl)
1898 ("python" ,python-2))) ;not compatible with python 3.
1899 (home-page "https://sourceforge.net/projects/fraggenescan/")
1900 (synopsis "Finds potentially fragmented genes in short reads")
1901 (description
1902 "FragGeneScan is a program for predicting bacterial and archaeal genes in
1903short and error-prone DNA sequencing reads. It can also be applied to predict
1904genes in incomplete assemblies or complete genomes.")
1905 ;; GPL3+ according to private correspondense with the authors.
1906 (license license:gpl3+)))
1907
81f3e0c1
BW		 1908(define-public fxtract
1909 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
1910 (package
1911 (name "fxtract")
1912 (version "2.3")
1913 (source
1914 (origin
1915 (method url-fetch)
1916 (uri (string-append
1917 "https://github.com/ctSkennerton/fxtract/archive/"
1918 version ".tar.gz"))
1919 (file-name (string-append "ctstennerton-util-"
1920 (string-take util-commit 7)
1921 "-checkout"))
1922 (sha256
1923 (base32
1924 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
1925 (build-system gnu-build-system)
1926 (arguments
1927 `(#:make-flags (list
1928 (string-append "PREFIX=" (assoc-ref %outputs "out"))
1929 "CC=gcc")
1930 #:test-target "fxtract_test"
1931 #:phases
1932 (modify-phases %standard-phases
1933 (delete 'configure)
1934 (add-before 'build 'copy-util
1935 (lambda* (#:key inputs #:allow-other-keys)
1936 (rmdir "util")
1937 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
1938 #t))
1939 ;; Do not use make install as this requires additional dependencies.
1940 (replace 'install
1941 (lambda* (#:key outputs #:allow-other-keys)
1942 (let* ((out (assoc-ref outputs "out"))
1943 (bin (string-append out"/bin")))
1944 (install-file "fxtract" bin)
1945 #t))))))
1946 (inputs
1947 `(("pcre" ,pcre)
1948 ("zlib" ,zlib)))
1949 (native-inputs
1950 ;; ctskennerton-util is licensed under GPL2.
1951 `(("ctskennerton-util"
1952 ,(origin
1953 (method git-fetch)
1954 (uri (git-reference
1955 (url "https://github.com/ctSkennerton/util.git")
1956 (commit util-commit)))
1957 (file-name (string-append
1958 "ctstennerton-util-" util-commit "-checkout"))
1959 (sha256
1960 (base32
1961 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
1962 (home-page "https://github.com/ctSkennerton/fxtract")
1963 (synopsis "Extract sequences from FASTA and FASTQ files")
1964 (description
1965 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
1966or FASTQ) file given a subsequence. It uses a simple substring search for
1967basic tasks but can change to using POSIX regular expressions, PCRE, hash
1968lookups or multi-pattern searching as required. By default fxtract looks in
1969the sequence of each record but can also be told to look in the header,
1970comment or quality sections.")
1971 (license license:expat))))
1972
5854f685
RW		 1973(define-public grit
1974 (package
1975 (name "grit")
1976 (version "2.0.2")
1977 (source (origin
1978 (method url-fetch)
1979 (uri (string-append
1980 "https://github.com/nboley/grit/archive/"
1981 version ".tar.gz"))
1982 (file-name (string-append name "-" version ".tar.gz"))
1983 (sha256
1984 (base32
1985 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
1986 (build-system python-build-system)
1987 (arguments
1988 `(#:python ,python-2
1989 #:phases
1990 (alist-cons-after
1991 'unpack 'generate-from-cython-sources
1992 (lambda* (#:key inputs outputs #:allow-other-keys)
1993 ;; Delete these C files to force fresh generation from pyx sources.
1994 (delete-file "grit/sparsify_support_fns.c")
1995 (delete-file "grit/call_peaks_support_fns.c")
1996 (substitute* "setup.py"
1997 (("Cython.Setup") "Cython.Build")
1998 ;; Add numpy include path to fix compilation
1999 (("pyx\", \\]")
2000 (string-append "pyx\", ], include_dirs = ['"
2001 (assoc-ref inputs "python-numpy")
2002 "/lib/python2.7/site-packages/numpy/core/include/"
2003 "']"))) #t)
2004 %standard-phases)))
2005 (inputs
2006 `(("python-scipy" ,python2-scipy)
2007 ("python-numpy" ,python2-numpy)
2008 ("python-pysam" ,python2-pysam)
2009 ("python-networkx" ,python2-networkx)))
2010 (native-inputs
2011 `(("python-cython" ,python2-cython)
2012 ("python-setuptools" ,python2-setuptools)))
2013 (home-page "http://grit-bio.org")
2014 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2015 (description
2016 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2017full length transcript models. When none of these data sources are available,
2018GRIT can be run by providing a candidate set of TES or TSS sites. In
2019addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2020also be run in quantification mode, where it uses a provided GTF file and just
2021estimates transcript expression.")
2022 (license license:gpl3+)))
2023
346a829a
RW		 2024(define-public hisat
2025 (package
2026 (name "hisat")
2027 (version "0.1.4")
2028 (source (origin
2029 (method url-fetch)
2030 (uri (string-append
2031 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2032 version "-beta-source.zip"))
2033 (sha256
2034 (base32
2035 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2036 (build-system gnu-build-system)
2037 (arguments
e58d01fa
RW		 2038 `(#:tests? #f ;no check target
2039 #:make-flags '("allall"
2040 ;; Disable unsupported `popcnt' instructions on
2041 ;; architectures other than x86_64
2042 ,@(if (string-prefix? "x86_64"
2043 (or (%current-target-system)
2044 (%current-system)))
2045 '()
2046 '("POPCNT_CAPABILITY=0")))
346a829a 2047 #:phases
da6dd842
LC		 2048 (alist-cons-after
2049 'unpack 'patch-sources
2050 (lambda _
2051 ;; XXX Cannot use snippet because zip files are not supported
2052 (substitute* "Makefile"
2053 (("^CC = .*$") "CC = gcc")
2054 (("^CPP = .*$") "CPP = g++")
2055 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2056 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2057 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2058 (substitute* '("hisat-build" "hisat-inspect")
2059 (("/usr/bin/env") (which "env"))))
2060 (alist-replace
2061 'install
2062 (lambda* (#:key outputs #:allow-other-keys)
96c46210
LC		 2063 (let ((bin (string-append (assoc-ref outputs "out") "/bi/")))
2064 (for-each (lambda (file)
2065 (install-file file bin))
2066 (find-files
2067 "."
2068 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
da6dd842 2069 (alist-delete 'configure %standard-phases)))))
346a829a
RW		 2070 (native-inputs
2071 `(("unzip" ,unzip)))
2072 (inputs
2073 `(("perl" ,perl)
2074 ("python" ,python)
2075 ("zlib" ,zlib)))
60af3d82
RW		 2076 ;; Non-portable SSE instructions are used so building fails on platforms
2077 ;; other than x86_64.
2078 (supported-systems '("x86_64-linux"))
346a829a
RW		 2079 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2080 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2081 (description
2082 "HISAT is a fast and sensitive spliced alignment program for mapping
2083RNA-seq reads. In addition to one global FM index that represents a whole
2084genome, HISAT uses a large set of small FM indexes that collectively cover the
2085whole genome. These small indexes (called local indexes) combined with
2086several alignment strategies enable effective alignment of RNA-seq reads, in
2087particular, reads spanning multiple exons.")
2088 (license license:gpl3+)))
2089
c684629f
BW		 2090(define-public hmmer
2091 (package
2092 (name "hmmer")
2093 (version "3.1b2")
2094 (source (origin
2095 (method url-fetch)
2096 (uri (string-append
2097 "http://selab.janelia.org/software/hmmer"
2098 (version-prefix version 1) "/"
2099 version "/hmmer-" version ".tar.gz"))
2100 (sha256
2101 (base32
2102 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
2103 (build-system gnu-build-system)
b3546174 2104 (native-inputs `(("perl" ,perl)))
c684629f
BW		 2105 (home-page "http://hmmer.janelia.org")
2106 (synopsis "Biosequence analysis using profile hidden Markov models")
2107 (description
2108 "HMMER is used for searching sequence databases for homologs of protein
2109sequences, and for making protein sequence alignments. It implements methods
2110using probabilistic models called profile hidden Markov models (profile
2111HMMs).")
2112 (license (list license:gpl3+
2113 ;; The bundled library 'easel' is distributed
2114 ;; under The Janelia Farm Software License.
2115 (license:non-copyleft
2116 "file://easel/LICENSE"
2117 "See easel/LICENSE in the distribution.")))))
2118
85652f59
RW		 2119(define-public htseq
2120 (package
2121 (name "htseq")
2122 (version "0.6.1")
2123 (source (origin
2124 (method url-fetch)
2125 (uri (string-append
2126 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2127 version ".tar.gz"))
2128 (sha256
2129 (base32
2130 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2131 (build-system python-build-system)
2132 (arguments `(#:python ,python-2)) ; only Python 2 is supported
0536727e
RW		 2133 ;; Numpy needs to be propagated when htseq is used as a Python library.
2134 (propagated-inputs
2135 `(("python-numpy" ,python2-numpy)))
578b05d9
RW		 2136 (inputs
2137 `(("python-pysam" ,python2-pysam)))
0536727e
RW		 2138 (native-inputs
2139 `(("python-setuptools" ,python2-setuptools)))
85652f59
RW		 2140 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2141 (synopsis "Analysing high-throughput sequencing data with Python")
2142 (description
2143 "HTSeq is a Python package that provides infrastructure to process data
2144from high-throughput sequencing assays.")
2145 (license license:gpl3+)))
2146
1ad15c16 2147(define-public java-htsjdk
15a3c3d4 2148 (package
1ad15c16 2149 (name "java-htsjdk")
15a3c3d4
RW		 2150 (version "1.129")
2151 (source (origin
2152 (method url-fetch)
2153 (uri (string-append
2154 "https://github.com/samtools/htsjdk/archive/"
2155 version ".tar.gz"))
2156 (file-name (string-append name "-" version ".tar.gz"))
2157 (sha256
2158 (base32
2159 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2160 (modules '((guix build utils)))
2161 ;; remove build dependency on git
2162 (snippet '(substitute* "build.xml"
2163 (("failifexecutionfails=\"true\"")
2164 "failifexecutionfails=\"false\"")))))
10b4a969 2165 (build-system ant-build-system)
15a3c3d4 2166 (arguments
10b4a969
RW		 2167 `(#:tests? #f ; test require Internet access
2168 #:make-flags
2169 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2170 "/share/java/htsjdk/"))
2171 #:build-target "all"
2172 #:phases
2173 (modify-phases %standard-phases
2174 ;; The build phase also installs the jars
2175 (delete 'install))))
15a3c3d4
RW		 2176 (home-page "http://samtools.github.io/htsjdk/")
2177 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2178 (description
2179 "HTSJDK is an implementation of a unified Java library for accessing
2180common file formats, such as SAM and VCF, used for high-throughput
2181sequencing (HTS) data. There are also an number of useful utilities for
2182manipulating HTS data.")
2183 (license license:expat)))
2184
e7c09730
RW		 2185(define-public htslib
2186 (package
2187 (name "htslib")
2188 (version "1.2.1")
2189 (source (origin
2190 (method url-fetch)
2191 (uri (string-append
2192 "https://github.com/samtools/htslib/releases/download/"
2193 version "/htslib-" version ".tar.bz2"))
2194 (sha256
2195 (base32
2196 "1c32ssscbnjwfw3dra140fq7riarp2x990qxybh34nr1p5r17nxx"))))
2197 (build-system gnu-build-system)
2198 (arguments
2199 `(#:phases
2200 (modify-phases %standard-phases
2201 (add-after
2202 'unpack 'patch-tests
2203 (lambda _
2204 (substitute* "test/test.pl"
2205 (("/bin/bash") (which "bash")))
2206 #t)))))
2207 (inputs
2208 `(("zlib" ,zlib)))
2209 (native-inputs
2210 `(("perl" ,perl)))
2211 (home-page "http://www.htslib.org")
2212 (synopsis "C library for reading/writing high-throughput sequencing data")
2213 (description
2214 "HTSlib is a C library for reading/writing high-throughput sequencing
2215data. It also provides the bgzip, htsfile, and tabix utilities.")
2216 ;; Files under cram/ are released under the modified BSD license;
2217 ;; the rest is released under the Expat license
2218 (license (list license:expat license:bsd-3))))
2219
c4325f62
RW		 2220(define-public idr
2221 (package
2222 (name "idr")
2223 (version "2.0.0")
2224 (source (origin
2225 (method url-fetch)
2226 (uri (string-append
2227 "https://github.com/nboley/idr/archive/"
2228 version ".tar.gz"))
2229 (file-name (string-append name "-" version ".tar.gz"))
2230 (sha256
2231 (base32
2232 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
2233 (build-system python-build-system)
2234 (arguments
2235 `(#:phases
2236 (modify-phases %standard-phases
2237 (add-after
2238 'install 'wrap-program
2239 (lambda* (#:key inputs outputs #:allow-other-keys)
2240 (let* ((out (assoc-ref outputs "out"))
2241 (python-version (string-take (string-take-right
2242 (assoc-ref inputs "python") 5) 3))
2243 (path (string-join
2244 (map (lambda (name)
2245 (string-append (assoc-ref inputs name)
2246 "/lib/python" python-version
2247 "/site-packages"))
2248 '("python-scipy"
2249 "python-numpy"
2250 "python-matplotlib"))
2251 ":")))
2252 (wrap-program (string-append out "/bin/idr")
2253 `("PYTHONPATH" ":" prefix (,path))))
2254 #t)))))
2255 (inputs
2256 `(("python-scipy" ,python-scipy)
2257 ("python-numpy" ,python-numpy)
2258 ("python-matplotlib" ,python-matplotlib)))
2259 (native-inputs
2260 `(("python-cython" ,python-cython)
2261 ("python-setuptools" ,python-setuptools)))
2262 (home-page "https://github.com/nboley/idr")
2263 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
2264 (description
2265 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
2266to measure the reproducibility of findings identified from replicate
2267experiments and provide highly stable thresholds based on reproducibility.")
2268 (license license:gpl3+)))
2269
43c565d2
RW		 2270(define-public jellyfish
2271 (package
2272 (name "jellyfish")
2273 (version "2.2.4")
2274 (source (origin
2275 (method url-fetch)
2276 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
2277 "releases/download/v" version
2278 "/jellyfish-" version ".tar.gz"))
2279 (sha256
2280 (base32
2281 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
2282 (build-system gnu-build-system)
2283 (outputs '("out" ;for library
2284 "ruby" ;for Ruby bindings
2285 "python")) ;for Python bindings
2286 (arguments
2287 `(#:configure-flags
2288 (list (string-append "--enable-ruby-binding="
2289 (assoc-ref %outputs "ruby"))
2290 (string-append "--enable-python-binding="
2291 (assoc-ref %outputs "python")))
2292 #:phases
2293 (modify-phases %standard-phases
2294 (add-before 'check 'set-SHELL-variable
2295 (lambda _
2296 ;; generator_manager.hpp either uses /bin/sh or $SHELL
2297 ;; to run tests.
2298 (setenv "SHELL" (which "bash"))
2299 #t)))))
2300 (native-inputs
2301 `(("bc" ,bc)
2302 ("time" ,time)
2303 ("ruby" ,ruby)
2304 ("python" ,python-2)))
2305 (synopsis "Tool for fast counting of k-mers in DNA")
2306 (description
2307 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
2308DNA. A k-mer is a substring of length k, and counting the occurrences of all
2309such substrings is a central step in many analyses of DNA sequence. Jellyfish
2310is a command-line program that reads FASTA and multi-FASTA files containing
2311DNA sequences. It outputs its k-mer counts in a binary format, which can be
2312translated into a human-readable text format using the @code{jellyfish dump}
2313command, or queried for specific k-mers with @code{jellyfish query}.")
2314 (home-page "http://www.genome.umd.edu/jellyfish.html")
2315 ;; The combined work is published under the GPLv3 or later. Individual
2316 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
2317 (license (list license:gpl3+ license:expat))))
2318
d57e6d0f
RW		 2319(define-public macs
2320 (package
2321 (name "macs")
0d0bcaa0 2322 (version "2.1.0.20151222")
d57e6d0f
RW		 2323 (source (origin
2324 (method url-fetch)
43ec07f1 2325 (uri (pypi-uri "MACS2" version))
d57e6d0f
RW		 2326 (sha256
2327 (base32
0d0bcaa0 2328 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
d57e6d0f
RW		 2329 (build-system python-build-system)
2330 (arguments
2331 `(#:python ,python-2 ; only compatible with Python 2.7
2332 #:tests? #f)) ; no test target
2333 (inputs
2334 `(("python-numpy" ,python2-numpy)))
2335 (native-inputs
2336 `(("python-setuptools" ,python2-setuptools)))
2337 (home-page "http://github.com/taoliu/MACS/")
2338 (synopsis "Model based analysis for ChIP-Seq data")
2339 (description
2340 "MACS is an implementation of a ChIP-Seq analysis algorithm for
2341identifying transcript factor binding sites named Model-based Analysis of
2342ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
2343the significance of enriched ChIP regions and it improves the spatial
2344resolution of binding sites through combining the information of both
2345sequencing tag position and orientation.")
2346 (license license:bsd-3)))
2347
41ddebdd
BW		 2348(define-public mafft
2349 (package
2350 (name "mafft")
02f35bb5 2351 (version "7.267")
41ddebdd
BW		 2352 (source (origin
2353 (method url-fetch)
2354 (uri (string-append
2355 "http://mafft.cbrc.jp/alignment/software/mafft-" version
2356 "-without-extensions-src.tgz"))
2357 (file-name (string-append name "-" version ".tgz"))
2358 (sha256
2359 (base32
02f35bb5 2360 "1xl6xq1rfxkws0svrlhyqxhhwbv6r77jwblsdpcyiwzsscw6wlk0"))))
41ddebdd
BW		 2361 (build-system gnu-build-system)
2362 (arguments
2363 `(#:tests? #f ; no automated tests, though there are tests in the read me
2364 #:make-flags (let ((out (assoc-ref %outputs "out")))
2365 (list (string-append "PREFIX=" out)
2366 (string-append "BINDIR="
2367 (string-append out "/bin"))))
2368 #:phases
2369 (modify-phases %standard-phases
2370 (add-after 'unpack 'enter-dir
2371 (lambda _ (chdir "core") #t))
2372 (add-after 'enter-dir 'patch-makefile
2373 (lambda _
2374 ;; on advice from the MAFFT authors, there is no need to
2375 ;; distribute mafft-profile, mafft-distance, or
2376 ;; mafft-homologs.rb as they are too "specialised".
2377 (substitute* "Makefile"
2378 ;; remove mafft-homologs.rb from SCRIPTS
2379 (("^SCRIPTS = mafft mafft-homologs.rb")
2380 "SCRIPTS = mafft")
02f35bb5
BW		 2381 ;; remove mafft-homologs from MANPAGES
2382 (("^MANPAGES = mafft.1 mafft-homologs.1")
2383 "MANPAGES = mafft.1")
41ddebdd
BW		 2384 ;; remove mafft-distance from PROGS
2385 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
2386 "PROGS = dvtditr dndfast7 dndblast sextet5")
2387 ;; remove mafft-profile from PROGS
2388 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
2389 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
2390 (("^rm -f mafft-profile mafft-profile.exe") "#")
2391 (("^rm -f mafft-distance mafft-distance.exe") ")#")
2392 ;; do not install MAN pages in libexec folder
2393 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
2394\\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
2395 #t))
02f35bb5
BW		 2396 (add-after 'enter-dir 'patch-paths
2397 (lambda* (#:key inputs #:allow-other-keys)
2398 (substitute* '("pairash.c"
2399 "mafft.tmpl")
2400 (("perl") (which "perl"))
2401 (("([\"`| ])awk" _ prefix)
2402 (string-append prefix (which "awk")))
2403 (("grep") (which "grep")))
2404 #t))
41ddebdd
BW		 2405 (delete 'configure))))
2406 (inputs
02f35bb5
BW		 2407 `(("perl" ,perl)
2408 ("gawk" ,gawk)
2409 ("grep" ,grep)))
2410 (propagated-inputs
2411 `(("coreutils" ,coreutils)))
41ddebdd
BW		 2412 (home-page "http://mafft.cbrc.jp/alignment/software/")
2413 (synopsis "Multiple sequence alignment program")
2414 (description
2415 "MAFFT offers a range of multiple alignment methods for nucleotide and
2416protein sequences. For instance, it offers L-INS-i (accurate; for alignment
2417of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
2418sequences).")
2419 (license (license:non-copyleft
2420 "http://mafft.cbrc.jp/alignment/software/license.txt"
2421 "BSD-3 with different formatting"))))
8fd790eb
BW		 2422
2423(define-public metabat
2424 (package
2425 (name "metabat")
2426 (version "0.26.1")
2427 (source (origin
2428 (method url-fetch)
2429 (uri (string-append
2430 "https://bitbucket.org/berkeleylab/metabat/get/"
2431 version ".tar.bz2"))
2432 (file-name (string-append name "-" version ".tar.bz2"))
2433 (sha256
2434 (base32
2435 "0vgrhbaxg4dkxyax2kbigak7w0arhqvw0szwp6gd9wmyilc44kfa"))))
2436 (build-system gnu-build-system)
2437 (arguments
2438 `(#:phases
2439 (modify-phases %standard-phases
2440 (add-after 'unpack 'fix-includes
2441 (lambda _
5ede5f2f
MW		 2442 (substitute* "SConstruct"
2443 (("/include/bam/bam.h")
2444 "/include/samtools/bam.h"))
2445 (substitute* "src/BamUtils.h"
2446 (("^#include \"bam/bam\\.h\"")
2447 "#include \"samtools/bam.h\"")
2448 (("^#include \"bam/sam\\.h\"")
2449 "#include \"samtools/sam.h\""))
2450 (substitute* "src/KseqReader.h"
2451 (("^#include \"bam/kseq\\.h\"")
2452 "#include \"samtools/kseq.h\""))
2453 #t))
8fd790eb
BW		 2454 (add-after 'unpack 'fix-scons
2455 (lambda _
2456 (substitute* "SConstruct" ; Do not distribute README
2457 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)")
2458 ""))
2459 #t))
2460 (delete 'configure)
2461 (replace 'build
2462 (lambda* (#:key inputs outputs #:allow-other-keys)
2463 (mkdir (assoc-ref outputs "out"))
2464 (zero? (system* "scons"
2465 (string-append
2466 "PREFIX="
2467 (assoc-ref outputs "out"))
2468 (string-append
2469 "HTSLIB_DIR="
2470 (assoc-ref inputs "htslib"))
2471 (string-append
2472 "SAMTOOLS_DIR="
2473 (assoc-ref inputs "samtools"))
2474 (string-append
2475 "BOOST_ROOT="
2476 (assoc-ref inputs "boost"))
2477 "install"))))
2478 ;; check and install carried out during build phase
2479 (delete 'check)
2480 (delete 'install))))
2481 (inputs
2482 `(("zlib" ,zlib)
2483 ("perl" ,perl)
2484 ("samtools" ,samtools)
2485 ("htslib" ,htslib)
2486 ("boost" ,boost)))
2487 (native-inputs
2488 `(("scons" ,scons)))
2489 (home-page "https://bitbucket.org/berkeleylab/metabat")
2490 (synopsis
2491 "Reconstruction of single genomes from complex microbial communities")
2492 (description
2493 "Grouping large genomic fragments assembled from shotgun metagenomic
2494sequences to deconvolute complex microbial communities, or metagenome binning,
2495enables the study of individual organisms and their interactions. MetaBAT is
2496an automated metagenome binning software, which integrates empirical
2497probabilistic distances of genome abundance and tetranucleotide frequency.")
2498 (license (license:non-copyleft "file://license.txt"
5ede5f2f 2499 "See license.txt in the distribution."))))
8fd790eb 2500
ddd82e0e
RW		 2501(define-public miso
2502 (package
2503 (name "miso")
2504 (version "0.5.3")
2505 (source (origin
2506 (method url-fetch)
2507 (uri (string-append
86517de6 2508 "https://pypi.python.org/packages/source/m/misopy/misopy-"
ddd82e0e
RW		 2509 version ".tar.gz"))
2510 (sha256
2511 (base32
2512 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
2513 (modules '((guix build utils)))
ddd82e0e
RW		 2514 (snippet
2515 '(substitute* "setup.py"
0ec8b206
RW		 2516 ;; Use setuptools, or else the executables are not
2517 ;; installed.
2518 (("distutils.core") "setuptools")
2519 ;; use "gcc" instead of "cc" for compilation
ddd82e0e
RW		 2520 (("^defines")
2521 "cc.set_executables(
2522compiler='gcc',
2523compiler_so='gcc',
2524linker_exe='gcc',
2525linker_so='gcc -shared'); defines")))))
2526 (build-system python-build-system)
2527 (arguments
2528 `(#:python ,python-2 ; only Python 2 is supported
2529 #:tests? #f)) ; no "test" target
2530 (inputs
2531 `(("samtools" ,samtools)
2532 ("python-numpy" ,python2-numpy)
2533 ("python-pysam" ,python2-pysam)
2534 ("python-scipy" ,python2-scipy)
2535 ("python-matplotlib" ,python2-matplotlib)))
2536 (native-inputs
0ec8b206
RW		 2537 `(("python-mock" ,python2-mock) ;for tests
2538 ("python-pytz" ,python2-pytz) ;for tests
2539 ("python-setuptools" ,python2-setuptools)))
ddd82e0e
RW		 2540 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
2541 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
2542 (description
2543 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
2544the expression level of alternatively spliced genes from RNA-Seq data, and
2545identifies differentially regulated isoforms or exons across samples. By
2546modeling the generative process by which reads are produced from isoforms in
2547RNA-Seq, the MISO model uses Bayesian inference to compute the probability
2548that a read originated from a particular isoform.")
2549 (license license:gpl2)))
2550
324efb88
BW		 2551(define-public muscle
2552 (package
2553 (name "muscle")
2554 (version "3.8.1551")
2555 (source (origin
2556 (method url-fetch/tarbomb)
2557 (file-name (string-append name "-" version))
2558 (uri (string-append
2559 "http://www.drive5.com/muscle/muscle_src_"
2560 version ".tar.gz"))
2561 (sha256
2562 (base32
2563 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
2564 (build-system gnu-build-system)
2565 (arguments
2566 `(#:make-flags (list "LDLIBS = -lm")
2567 #:phases
2568 (modify-phases %standard-phases
2569 (delete 'configure)
2570 (replace 'check
2571 ;; There are no tests, so just test if it runs.
2572 (lambda _ (zero? (system* "./muscle" "-version"))))
2573 (replace 'install
2574 (lambda* (#:key outputs #:allow-other-keys)
2575 (let* ((out (assoc-ref outputs "out"))
2576 (bin (string-append out "/bin")))
2577 (install-file "muscle" bin)))))))
2578 (home-page "http://www.drive5.com/muscle")
2579 (synopsis "Multiple sequence alignment program")
2580 (description
2581 "MUSCLE aims to be a fast and accurate multiple sequence alignment
2582program for nucleotide and protein sequences.")
2583 ;; License information found in 'muscle -h' and usage.cpp.
2584 (license license:public-domain)))
2585
1e44cf8b
BW		 2586(define-public orfm
2587 (package
2588 (name "orfm")
6b6f7d6a 2589 (version "0.5.3")
1e44cf8b
BW		 2590 (source (origin
2591 (method url-fetch)
2592 (uri (string-append
2593 "https://github.com/wwood/OrfM/releases/download/v"
2594 version "/orfm-" version ".tar.gz"))
2595 (sha256
2596 (base32
6b6f7d6a 2597 "0vb6d771gl4mix8bwx919x5ayy9pkj44n7ki336nz3rz2rx4c7gk"))))
1e44cf8b
BW		 2598 (build-system gnu-build-system)
2599 (inputs `(("zlib" ,zlib)))
6b6f7d6a
BW		 2600 (native-inputs
2601 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
2602 ("ruby-rspec" ,ruby-rspec)
2603 ("ruby" ,ruby)))
1e44cf8b
BW		 2604 (synopsis "Simple and not slow open reading frame (ORF) caller")
2605 (description
6b6f7d6a 2606 "An ORF caller finds stretches of DNA that, when translated, are not
1e44cf8b
BW		 2607interrupted by stop codons. OrfM finds and prints these ORFs.")
2608 (home-page "https://github.com/wwood/OrfM")
2609 (license license:lgpl3+)))
2610
19ee9201
RW		 2611(define-public python2-pbcore
2612 (package
2613 (name "python2-pbcore")
ddb83129 2614 (version "1.2.8")
19ee9201
RW		 2615 (source (origin
2616 (method url-fetch)
ddb83129 2617 (uri (pypi-uri "pbcore" version))
19ee9201
RW		 2618 (sha256
2619 (base32
ddb83129 2620 "02pfn5raa3zf739672bg0dkx7z3j2c4nx7vmpfjqy5b12jrqpymk"))))
19ee9201
RW		 2621 (build-system python-build-system)
2622 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
2623 (inputs
2624 `(("python-cython" ,python2-cython)
2625 ("python-numpy" ,python2-numpy)
2626 ("python-pysam" ,python2-pysam)
2627 ("python-h5py" ,python2-h5py)))
2628 (native-inputs
ddb83129
EF		 2629 `(("python-docutils" ,python2-docutils)
2630 ("python-nose" ,python2-nose)
2631 ("python-setuptools" ,python2-setuptools)
2632 ("python-sphinx" ,python2-sphinx)))
19ee9201
RW		 2633 (home-page "http://pacificbiosciences.github.io/pbcore/")
2634 (synopsis "Library for reading and writing PacBio data files")
2635 (description
2636 "The pbcore package provides Python APIs for interacting with PacBio data
2637files and writing bioinformatics applications.")
2638 (license license:bsd-3)))
2639
c61fe02c
RW		 2640(define-public python2-warpedlmm
2641 (package
2642 (name "python2-warpedlmm")
2643 (version "0.21")
2644 (source
2645 (origin
2646 (method url-fetch)
2647 (uri (string-append
2648 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
2649 version ".zip"))
2650 (sha256
2651 (base32
2652 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
2653 (build-system python-build-system)
2654 (arguments
2655 `(#:python ,python-2 ; requires Python 2.7
2656 #:phases
2657 (modify-phases %standard-phases
2658 (add-after
2659 'install 'remove-bin-directory
2660 (lambda* (#:key outputs #:allow-other-keys)
2661 ;; The "bin" directory only contains wrappers for running
2662 ;; the module tests. They are not needed after the
2663 ;; "check" phase.
2664 (delete-file-recursively
2665 (string-append (assoc-ref outputs "out") "/bin"))
2666 #t)))))
2667 (propagated-inputs
2668 `(("python-scipy" ,python2-scipy)
2669 ("python-numpy" ,python2-numpy)
2670 ("python-matplotlib" ,python2-matplotlib)
2671 ("python-fastlmm" ,python2-fastlmm)
2672 ("python-pandas" ,python2-pandas)
2673 ("python-pysnptools" ,python2-pysnptools)))
2674 (native-inputs
2675 `(("python-setuptools" ,python2-setuptools)
2676 ("python-mock" ,python2-mock)
2677 ("python-nose" ,python2-nose)
2678 ("unzip" ,unzip)))
2679 (home-page "https://github.com/PMBio/warpedLMM")
2680 (synopsis "Implementation of warped linear mixed models")
2681 (description
2682 "WarpedLMM is a Python implementation of the warped linear mixed model,
2683which automatically learns an optimal warping function (or transformation) for
2684the phenotype as it models the data.")
2685 (license license:asl2.0)))
2686
2c16316e 2687(define-public pbtranscript-tofu
9a067efd 2688 (let ((commit "8f5467fe6"))
2c16316e
RW		 2689 (package
2690 (name "pbtranscript-tofu")
9a067efd 2691 (version (string-append "2.2.3." commit))
2c16316e
RW		 2692 (source (origin
2693 (method git-fetch)
2694 (uri (git-reference
2695 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
2696 (commit commit)))
9a067efd 2697 (file-name (string-append name "-" version "-checkout"))
2c16316e
RW		 2698 (sha256
2699 (base32
9a067efd
RW		 2700 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
2701 (modules '((guix build utils)))
2702 (snippet
2703 '(begin
2704 ;; remove bundled Cython sources
2705 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
2706 #t))))
2c16316e
RW		 2707 (build-system python-build-system)
2708 (arguments
2709 `(#:python ,python-2
2710 ;; With standard flags, the install phase attempts to create a zip'd
2711 ;; egg file, and fails with an error: 'ZIP does not support timestamps
2712 ;; before 1980'
2713 #:configure-flags '("--single-version-externally-managed"
2714 "--record=pbtranscript-tofu.txt")
2715 #:phases
9a067efd
RW		 2716 (modify-phases %standard-phases
2717 (add-after 'unpack 'enter-directory
2718 (lambda _
2719 (chdir "pbtranscript-tofu/pbtranscript/")
2720 #t))
2721 ;; With setuptools version 18.0 and later this setup.py hack causes
2722 ;; a build error, so we disable it.
2723 (add-after 'enter-directory 'patch-setuppy
2724 (lambda _
2725 (substitute* "setup.py"
2726 (("if 'setuptools.extension' in sys.modules:")
2727 "if False:"))
2728 #t)))))
2c16316e 2729 (inputs
9a067efd 2730 `(("python-numpy" ,python2-numpy)
2c16316e 2731 ("python-bx-python" ,python2-bx-python)
c5372108
RW		 2732 ("python-networkx" ,python2-networkx)
2733 ("python-scipy" ,python2-scipy)
9a067efd
RW		 2734 ("python-pbcore" ,python2-pbcore)
2735 ("python-h5py" ,python2-h5py)))
2c16316e 2736 (native-inputs
9a067efd
RW		 2737 `(("python-cython" ,python2-cython)
2738 ("python-nose" ,python2-nose)
2c16316e
RW		 2739 ("python-setuptools" ,python2-setuptools)))
2740 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
2741 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
2742 (description
2743 "pbtranscript-tofu contains scripts to analyze transcriptome data
2744generated using the PacBio Iso-Seq protocol.")
2745 (license license:bsd-3))))
2746
846e3409
RW		 2747(define-public pyicoteo
2748 (package
2749 (name "pyicoteo")
2750 (version "2.0.7")
2751 (source
2752 (origin
2753 (method url-fetch)
2754 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
2755 "pyicoteo/get/v" version ".tar.bz2"))
2756 (file-name (string-append name "-" version ".tar.bz2"))
2757 (sha256
2758 (base32
2759 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
2760 (build-system python-build-system)
2761 (arguments
2762 `(#:python ,python-2 ; does not work with Python 3
2763 #:tests? #f)) ; there are no tests
2764 (inputs
2765 `(("python2-matplotlib" ,python2-matplotlib)))
2766 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
2767 (synopsis "Analyze high-throughput genetic sequencing data")
2768 (description
2769 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
2770sequencing data. It works with genomic coordinates. There are currently six
2771different command-line tools:
2772
2773@enumerate
2774@item pyicoregion: for generating exploratory regions automatically;
2775@item pyicoenrich: for differential enrichment between two conditions;
2776@item pyicoclip: for calling CLIP-Seq peaks without a control;
2777@item pyicos: for genomic coordinates manipulation;
2778@item pyicoller: for peak calling on punctuated ChIP-Seq;
2779@item pyicount: to count how many reads from N experiment files overlap in a
2780 region file;
2781@item pyicotrocol: to combine operations from pyicoteo.
2782@end enumerate\n")
2783 (license license:gpl3+)))
2784
af860475
BW		 2785(define-public prodigal
2786 (package
2787 (name "prodigal")
e70f7a23 2788 (version "2.6.3")
af860475
BW		 2789 (source (origin
2790 (method url-fetch)
2791 (uri (string-append
2792 "https://github.com/hyattpd/Prodigal/archive/v"
2793 version ".tar.gz"))
2794 (file-name (string-append name "-" version ".tar.gz"))
2795 (sha256
2796 (base32
e70f7a23 2797 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
af860475
BW		 2798 (build-system gnu-build-system)
2799 (arguments
2800 `(#:tests? #f ;no check target
2801 #:make-flags (list (string-append "INSTALLDIR="
2802 (assoc-ref %outputs "out")
2803 "/bin"))
2804 #:phases
2805 (modify-phases %standard-phases
2806 (delete 'configure))))
2807 (home-page "http://prodigal.ornl.gov")
2808 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
2809 (description
2810 "Prodigal runs smoothly on finished genomes, draft genomes, and
2811metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
2812format. It runs quickly, in an unsupervised fashion, handles gaps, handles
2813partial genes, and identifies translation initiation sites.")
2814 (license license:gpl3+)))
2815
66e3eff1
RW		 2816(define-public rsem
2817 (package
2818 (name "rsem")
2819 (version "1.2.20")
2820 (source
2821 (origin
2822 (method url-fetch)
2823 (uri
2824 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
2825 version ".tar.gz"))
2826 (sha256
2827 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
fc1adab1 2828 (patches (search-patches "rsem-makefile.patch"))
66e3eff1
RW		 2829 (modules '((guix build utils)))
2830 (snippet
2831 '(begin
2832 ;; remove bundled copy of boost
2833 (delete-file-recursively "boost")
2834 #t))))
2835 (build-system gnu-build-system)
2836 (arguments
2837 `(#:tests? #f ;no "check" target
2838 #:phases
2839 (modify-phases %standard-phases
2840 ;; No "configure" script.
2841 ;; Do not build bundled samtools library.
2842 (replace 'configure
2843 (lambda _
2844 (substitute* "Makefile"
2845 (("^all : sam/libbam.a") "all : "))
2846 #t))
2847 (replace 'install
2848 (lambda* (#:key outputs #:allow-other-keys)
2849 (let* ((out (string-append (assoc-ref outputs "out")))
2850 (bin (string-append out "/bin/"))
2851 (perl (string-append out "/lib/perl5/site_perl")))
2852 (mkdir-p bin)
2853 (mkdir-p perl)
2854 (for-each (lambda (file)
2855 (copy-file file
2856 (string-append bin (basename file))))
2857 (find-files "." "rsem-.*"))
2858 (copy-file "rsem_perl_utils.pm"
2859 (string-append perl "/rsem_perl_utils.pm")))
2860 #t))
2861 (add-after
2862 'install 'wrap-program
2863 (lambda* (#:key outputs #:allow-other-keys)
2864 (let ((out (assoc-ref outputs "out")))
2865 (for-each (lambda (prog)
2866 (wrap-program (string-append out "/bin/" prog)
2867 `("PERL5LIB" ":" prefix
2868 (,(string-append out "/lib/perl5/site_perl")))))
2869 '("rsem-plot-transcript-wiggles"
2870 "rsem-calculate-expression"
2871 "rsem-generate-ngvector"
2872 "rsem-run-ebseq"
2873 "rsem-prepare-reference")))
2874 #t)))))
2875 (inputs
2876 `(("boost" ,boost)
2877 ("ncurses" ,ncurses)
2878 ("r" ,r)
2879 ("perl" ,perl)
2880 ("samtools" ,samtools-0.1)
2881 ("zlib" ,zlib)))
2882 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
2883 (synopsis "Estimate gene expression levels from RNA-Seq data")
2884 (description
2885 "RSEM is a software package for estimating gene and isoform expression
2886levels from RNA-Seq data. The RSEM package provides a user-friendly
2887interface, supports threads for parallel computation of the EM algorithm,
2888single-end and paired-end read data, quality scores, variable-length reads and
2889RSPD estimation. In addition, it provides posterior mean and 95% credibility
2890interval estimates for expression levels. For visualization, it can generate
2891BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
2892 (license license:gpl3+)))
2893
8622a072
RW		 2894(define-public rseqc
2895 (package
2896 (name "rseqc")
2897 (version "2.6.1")
2898 (source
2899 (origin
2900 (method url-fetch)
2901 (uri
2902 (string-append "mirror://sourceforge/rseqc/"
2903 version "/RSeQC-" version ".tar.gz"))
2904 (sha256
8214b7fb 2905 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
8622a072
RW		 2906 (modules '((guix build utils)))
2907 (snippet
2908 '(begin
2909 ;; remove bundled copy of pysam
2910 (delete-file-recursively "lib/pysam")
2911 (substitute* "setup.py"
2912 ;; remove dependency on outdated "distribute" module
2913 (("^from distribute_setup import use_setuptools") "")
2914 (("^use_setuptools\\(\\)") "")
2915 ;; do not use bundled copy of pysam
2916 (("^have_pysam = False") "have_pysam = True"))))))
2917 (build-system python-build-system)
2918 (arguments `(#:python ,python-2))
2919 (inputs
2920 `(("python-cython" ,python2-cython)
2921 ("python-pysam" ,python2-pysam)
2922 ("python-numpy" ,python2-numpy)
2923 ("python-setuptools" ,python2-setuptools)
2924 ("zlib" ,zlib)))
2925 (native-inputs
2926 `(("python-nose" ,python2-nose)))
2927 (home-page "http://rseqc.sourceforge.net/")
2928 (synopsis "RNA-seq quality control package")
2929 (description
2930 "RSeQC provides a number of modules that can comprehensively evaluate
2931high throughput sequence data, especially RNA-seq data. Some basic modules
2932inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
2933while RNA-seq specific modules evaluate sequencing saturation, mapped reads
2934distribution, coverage uniformity, strand specificity, etc.")
2935 (license license:gpl3+)))
2936
4e10a221
RW		 2937(define-public samtools
2938 (package
2939 (name "samtools")
79b555ed 2940 (version "1.3.1")
4e10a221
RW		 2941 (source
2942 (origin
2943 (method url-fetch)
2944 (uri
2945 (string-append "mirror://sourceforge/samtools/"
2946 version "/samtools-" version ".tar.bz2"))
2947 (sha256
2948 (base32
79b555ed 2949 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4e10a221
RW		 2950 (build-system gnu-build-system)
2951 (arguments
c4473411 2952 `(#:modules ((ice-9 ftw)
5bdda30b
RW		 2953 (ice-9 regex)
2954 (guix build gnu-build-system)
2955 (guix build utils))
c4473411
RW		 2956 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
2957 #:configure-flags (list "--with-ncurses")
4e10a221
RW		 2958 #:phases
2959 (alist-cons-after
c4473411
RW		 2960 'unpack 'patch-tests
2961 (lambda _
2962 (substitute* "test/test.pl"
2963 ;; The test script calls out to /bin/bash
2964 (("/bin/bash") (which "bash")))
2965 #t)
41dd7126
RW		 2966 (alist-cons-after
2967 'install 'install-library
2968 (lambda* (#:key outputs #:allow-other-keys)
2969 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
96c46210 2970 (install-file "libbam.a" lib)))
5bdda30b
RW		 2971 (alist-cons-after
2972 'install 'install-headers
2973 (lambda* (#:key outputs #:allow-other-keys)
2974 (let ((include (string-append (assoc-ref outputs "out")
2975 "/include/samtools/")))
5bdda30b 2976 (for-each (lambda (file)
96c46210 2977 (install-file file include))
5bdda30b
RW		 2978 (scandir "." (lambda (name) (string-match "\\.h$" name))))
2979 #t))
c4473411 2980 %standard-phases)))))
4e10a221
RW		 2981 (native-inputs `(("pkg-config" ,pkg-config)))
2982 (inputs `(("ncurses" ,ncurses)
2983 ("perl" ,perl)
2984 ("python" ,python)
2985 ("zlib" ,zlib)))
2986 (home-page "http://samtools.sourceforge.net")
2987 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
2988 (description
2989 "Samtools implements various utilities for post-processing nucleotide
2990sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
2991variant calling (in conjunction with bcftools), and a simple alignment
2992viewer.")
2993 (license license:expat)))
d3517eda 2994
0b84a0aa
RW		 2995(define-public samtools-0.1
2996 ;; This is the most recent version of the 0.1 line of samtools. The input
2997 ;; and output formats differ greatly from that used and produced by samtools
2998 ;; 1.x and is still used in many bioinformatics pipelines.
2999 (package (inherit samtools)
3000 (version "0.1.19")
3001 (source
3002 (origin
3003 (method url-fetch)
3004 (uri
3005 (string-append "mirror://sourceforge/samtools/"
3006 version "/samtools-" version ".tar.bz2"))
3007 (sha256
3008 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
3009 (arguments
2309ed68
RW		 3010 `(#:tests? #f ;no "check" target
3011 ,@(substitute-keyword-arguments (package-arguments samtools)
3012 ((#:make-flags flags)
3013 `(cons "LIBCURSES=-lncurses" ,flags))
3014 ((#:phases phases)
3015 `(modify-phases ,phases
3016 (replace 'install
3017 (lambda* (#:key outputs #:allow-other-keys)
3018 (let ((bin (string-append
3019 (assoc-ref outputs "out") "/bin")))
3020 (mkdir-p bin)
3021 (copy-file "samtools"
3022 (string-append bin "/samtools")))))
3023 (delete 'patch-tests)
3024 (delete 'configure))))))))
0b84a0aa 3025
fe4c37c2
RW		 3026(define-public mosaik
3027 (let ((commit "5c25216d"))
3028 (package
3029 (name "mosaik")
3030 (version "2.2.30")
3031 (source (origin
3032 ;; There are no release tarballs nor tags.
3033 (method git-fetch)
3034 (uri (git-reference
3035 (url "https://github.com/wanpinglee/MOSAIK.git")
3036 (commit commit)))
3037 (file-name (string-append name "-" version))
3038 (sha256
3039 (base32
3040 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
3041 (build-system gnu-build-system)
3042 (arguments
3043 `(#:tests? #f ; no tests
3044 #:make-flags (list "CC=gcc")
3045 #:phases
3046 (modify-phases %standard-phases
3047 (replace 'configure
3048 (lambda _ (chdir "src") #t))
3049 (replace 'install
3050 (lambda* (#:key outputs #:allow-other-keys)
3051 (let ((bin (string-append (assoc-ref outputs "out")
3052 "/bin")))
3053 (mkdir-p bin)
3054 (copy-recursively "../bin" bin)
3055 #t))))))
3056 (inputs
3057 `(("perl" ,perl)
3058 ("zlib" ,zlib)))
029d9f77 3059 (supported-systems '("x86_64-linux"))
fe4c37c2
RW		 3060 (home-page "https://code.google.com/p/mosaik-aligner/")
3061 (synopsis "Map nucleotide sequence reads to reference genomes")
3062 (description
3063 "MOSAIK is a program for mapping second and third-generation sequencing
3064reads to a reference genome. MOSAIK can align reads generated by all the
3065major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
3066Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
3067 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
3068 ;; code released into the public domain:
3069 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
3070 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
3071 (license (list license:gpl2+ license:public-domain)))))
3072
282c5087
RW		 3073(define-public ngs-sdk
3074 (package
3075 (name "ngs-sdk")
d3b39bc2 3076 (version "1.2.3")
282c5087
RW		 3077 (source
3078 (origin
3079 (method url-fetch)
3080 (uri
3081 (string-append "https://github.com/ncbi/ngs/archive/"
3082 version ".tar.gz"))
3083 (file-name (string-append name "-" version ".tar.gz"))
3084 (sha256
3085 (base32
d3b39bc2 3086 "15074fdi94c6pjy83hhk22r86kfvzpaz2i07h3rqg9yy6x3w0pk2"))))
282c5087
RW		 3087 (build-system gnu-build-system)
3088 (arguments
3089 `(#:parallel-build? #f ; not supported
3090 #:tests? #f ; no "check" target
3091 #:phases
3092 (alist-replace
3093 'configure
3094 (lambda* (#:key outputs #:allow-other-keys)
3095 (let ((out (assoc-ref outputs "out")))
282c5087
RW		 3096 ;; The 'configure' script doesn't recognize things like
3097 ;; '--enable-fast-install'.
3098 (zero? (system* "./configure"
3099 (string-append "--build-prefix=" (getcwd) "/build")
3100 (string-append "--prefix=" out)))))
3101 (alist-cons-after
3102 'unpack 'enter-dir
3103 (lambda _ (chdir "ngs-sdk") #t)
3104 %standard-phases))))
3105 (native-inputs `(("perl" ,perl)))
a0dadf0c
AE		 3106 ;; According to the test
3107 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
3108 ;; in ngs-sdk/setup/konfigure.perl
ab29be81 3109 (supported-systems '("i686-linux" "x86_64-linux"))
282c5087
RW		 3110 (home-page "https://github.com/ncbi/ngs")
3111 (synopsis "API for accessing Next Generation Sequencing data")
3112 (description
3113 "NGS is a domain-specific API for accessing reads, alignments and pileups
3114produced from Next Generation Sequencing. The API itself is independent from
3115any particular back-end implementation, and supports use of multiple back-ends
3116simultaneously.")
3117 (license license:public-domain)))
3118
1ad15c16 3119(define-public java-ngs
2651a5e6 3120 (package (inherit ngs-sdk)
1ad15c16 3121 (name "java-ngs")
2651a5e6
RW		 3122 (arguments
3123 `(,@(substitute-keyword-arguments
3124 `(#:modules ((guix build gnu-build-system)
3125 (guix build utils)
3126 (srfi srfi-1)
3127 (srfi srfi-26))
3128 ,@(package-arguments ngs-sdk))
3129 ((#:phases phases)
614a8977
RW		 3130 `(modify-phases ,phases
3131 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
2651a5e6 3132 (inputs
d2540f80 3133 `(("jdk" ,icedtea "jdk")
2651a5e6
RW		 3134 ("ngs-sdk" ,ngs-sdk)))
3135 (synopsis "Java bindings for NGS SDK")))
3136
75dd2424
RW		 3137(define-public ncbi-vdb
3138 (package
3139 (name "ncbi-vdb")
fe91666b 3140 (version "2.5.7")
75dd2424
RW		 3141 (source
3142 (origin
3143 (method url-fetch)
3144 (uri
3145 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
3146 version ".tar.gz"))
3147 (file-name (string-append name "-" version ".tar.gz"))
3148 (sha256
3149 (base32
fe91666b 3150 "0hay5hy8ynva3mi5wbn4wmq1q23qwxc3aqzbb86hg3x4f1r73270"))))
75dd2424
RW		 3151 (build-system gnu-build-system)
3152 (arguments
3153 `(#:parallel-build? #f ; not supported
3154 #:tests? #f ; no "check" target
3155 #:phases
3156 (alist-replace
3157 'configure
3158 (lambda* (#:key inputs outputs #:allow-other-keys)
3159 (let ((out (assoc-ref outputs "out")))
75dd2424
RW		 3160 ;; Override include path for libmagic
3161 (substitute* "setup/package.prl"
3162 (("name => 'magic', Include => '/usr/include'")
3163 (string-append "name=> 'magic', Include => '"
3164 (assoc-ref inputs "libmagic")
3165 "/include" "'")))
3166
3167 ;; Install kdf5 library (needed by sra-tools)
3168 (substitute* "build/Makefile.install"
3169 (("LIBRARIES_TO_INSTALL =")
3170 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
3171
3172 ;; The 'configure' script doesn't recognize things like
3173 ;; '--enable-fast-install'.
3174 (zero? (system*
3175 "./configure"
3176 (string-append "--build-prefix=" (getcwd) "/build")
3177 (string-append "--prefix=" (assoc-ref outputs "out"))
3178 (string-append "--debug")
3179 (string-append "--with-xml2-prefix="
3180 (assoc-ref inputs "libxml2"))
3181 (string-append "--with-ngs-sdk-prefix="
3182 (assoc-ref inputs "ngs-sdk"))
3183 (string-append "--with-ngs-java-prefix="
1ad15c16 3184 (assoc-ref inputs "java-ngs"))
75dd2424
RW		 3185 (string-append "--with-hdf5-prefix="
3186 (assoc-ref inputs "hdf5"))))))
3187 (alist-cons-after
3188 'install 'install-interfaces
132b4c8c
RW		 3189 (lambda* (#:key outputs #:allow-other-keys)
3190 ;; Install interface libraries. On i686 the interface libraries
3191 ;; are installed to "linux/gcc/i386", so we need to use the Linux
3192 ;; architecture name ("i386") instead of the target system prefix
3193 ;; ("i686").
75dd2424
RW		 3194 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
3195 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
132b4c8c
RW		 3196 ,(system->linux-architecture
3197 (or (%current-target-system)
3198 (%current-system)))
75dd2424
RW		 3199 "/rel/ilib")
3200 (string-append (assoc-ref outputs "out")
3201 "/ilib"))
3202 ;; Install interface headers
3203 (copy-recursively "interfaces"
3204 (string-append (assoc-ref outputs "out")
3205 "/include")))
3206 %standard-phases))))
3207 (inputs
3208 `(("libxml2" ,libxml2)
3209 ("ngs-sdk" ,ngs-sdk)
1ad15c16 3210 ("java-ngs" ,java-ngs)
75dd2424
RW		 3211 ("libmagic" ,file)
3212 ("hdf5" ,hdf5)))
3213 (native-inputs `(("perl" ,perl)))
3214 (home-page "https://github.com/ncbi/ncbi-vdb")
3215 (synopsis "Database engine for genetic information")
3216 (description
3217 "The NCBI-VDB library implements a highly compressed columnar data
3218warehousing engine that is most often used to store genetic information.
3219Databases are stored in a portable image within the file system, and can be
3220accessed/downloaded on demand across HTTP.")
3221 (license license:public-domain)))
3222
cc6ed477
RW		 3223(define-public plink
3224 (package
3225 (name "plink")
3226 (version "1.07")
3227 (source
3228 (origin
3229 (method url-fetch)
3230 (uri (string-append
3231 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
3232 version "-src.zip"))
3233 (sha256
3234 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
fc1adab1 3235 (patches (search-patches "plink-1.07-unclobber-i.patch"))))
cc6ed477
RW		 3236 (build-system gnu-build-system)
3237 (arguments
3238 '(#:tests? #f ;no "check" target
3239 #:make-flags (list (string-append "LIB_LAPACK="
3240 (assoc-ref %build-inputs "lapack")
3241 "/lib/liblapack.so")
3242 "WITH_LAPACK=1"
3243 "FORCE_DYNAMIC=1"
3244 ;; disable phoning home
3245 "WITH_WEBCHECK=")
3246 #:phases
3247 (modify-phases %standard-phases
3248 ;; no "configure" script
3249 (delete 'configure)
3250 (replace 'install
3251 (lambda* (#:key outputs #:allow-other-keys)
3252 (let ((bin (string-append (assoc-ref outputs "out")
3253 "/bin/")))
96c46210 3254 (install-file "plink" bin)
cc6ed477
RW		 3255 #t))))))
3256 (inputs
3257 `(("zlib" ,zlib)
3258 ("lapack" ,lapack)))
3259 (native-inputs
3260 `(("unzip" ,unzip)))
3261 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
3262 (synopsis "Whole genome association analysis toolset")
3263 (description
3264 "PLINK is a whole genome association analysis toolset, designed to
3265perform a range of basic, large-scale analyses in a computationally efficient
3266manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
3267so there is no support for steps prior to this (e.g. study design and
3268planning, generating genotype or CNV calls from raw data). Through
3269integration with gPLINK and Haploview, there is some support for the
3270subsequent visualization, annotation and storage of results.")
3271 ;; Code is released under GPLv2, except for fisher.h, which is under
3272 ;; LGPLv2.1+
3273 (license (list license:gpl2 license:lgpl2.1+))))
3274
c6a24d6e
RW		 3275(define-public smithlab-cpp
3276 (let ((revision "1")
3277 (commit "728a097"))
3278 (package
3279 (name "smithlab-cpp")
3280 (version (string-append "0." revision "." commit))
3281 (source (origin
3282 (method git-fetch)
3283 (uri (git-reference
3284 (url "https://github.com/smithlabcode/smithlab_cpp.git")
3285 (commit commit)))
3286 (file-name (string-append name "-" version "-checkout"))
3287 (sha256
3288 (base32
3289 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
3290 (build-system gnu-build-system)
3291 (arguments
3292 `(#:modules ((guix build gnu-build-system)
3293 (guix build utils)
3294 (srfi srfi-26))
3295 #:tests? #f ;no "check" target
3296 #:phases
3297 (modify-phases %standard-phases
3298 (add-after 'unpack 'use-samtools-headers
3299 (lambda _
3300 (substitute* '("SAM.cpp"
3301 "SAM.hpp")
3302 (("sam.h") "samtools/sam.h"))
3303 #t))
3304 (replace 'install
3305 (lambda* (#:key outputs #:allow-other-keys)
3306 (let* ((out (assoc-ref outputs "out"))
3307 (lib (string-append out "/lib"))
3308 (include (string-append out "/include/smithlab-cpp")))
3309 (mkdir-p lib)
3310 (mkdir-p include)
3311 (for-each (cut install-file <> lib)
3312 (find-files "." "\\.o$"))
3313 (for-each (cut install-file <> include)
3314 (find-files "." "\\.hpp$")))
3315 #t))
3316 (delete 'configure))))
3317 (inputs
3318 `(("samtools" ,samtools-0.1)
3319 ("zlib" ,zlib)))
3320 (home-page "https://github.com/smithlabcode/smithlab_cpp")
3321 (synopsis "C++ helper library for functions used in Smith lab projects")
3322 (description
3323 "Smithlab CPP is a C++ library that includes functions used in many of
3324the Smith lab bioinformatics projects, such as a wrapper around Samtools data
3325structures, classes for genomic regions, mapped sequencing reads, etc.")
3326 (license license:gpl3+))))
3327
56e373ef
RW		 3328(define-public preseq
3329 (package
3330 (name "preseq")
b49c5a58 3331 (version "2.0")
56e373ef
RW		 3332 (source (origin
3333 (method url-fetch)
b49c5a58
RW		 3334 (uri (string-append "https://github.com/smithlabcode/"
3335 "preseq/archive/v" version ".tar.gz"))
3336 (file-name (string-append name "-" version ".tar.gz"))
56e373ef 3337 (sha256
b49c5a58 3338 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
56e373ef
RW		 3339 (modules '((guix build utils)))
3340 (snippet
3341 ;; Remove bundled samtools.
b49c5a58 3342 '(delete-file-recursively "samtools"))))
56e373ef
RW		 3343 (build-system gnu-build-system)
3344 (arguments
3345 `(#:tests? #f ;no "check" target
3346 #:phases
3347 (modify-phases %standard-phases
56e373ef 3348 (delete 'configure))
b49c5a58
RW		 3349 #:make-flags
3350 (list (string-append "PREFIX="
3351 (assoc-ref %outputs "out"))
3352 (string-append "LIBBAM="
3353 (assoc-ref %build-inputs "samtools")
3354 "/lib/libbam.a")
3355 (string-append "SMITHLAB_CPP="
3356 (assoc-ref %build-inputs "smithlab-cpp")
3357 "/lib")
3358 "PROGS=preseq"
3359 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
56e373ef
RW		 3360 (inputs
3361 `(("gsl" ,gsl)
3362 ("samtools" ,samtools-0.1)
b49c5a58 3363 ("smithlab-cpp" ,smithlab-cpp)
56e373ef
RW		 3364 ("zlib" ,zlib)))
3365 (home-page "http://smithlabresearch.org/software/preseq/")
3366 (synopsis "Program for analyzing library complexity")
3367 (description
3368 "The preseq package is aimed at predicting and estimating the complexity
3369of a genomic sequencing library, equivalent to predicting and estimating the
3370number of redundant reads from a given sequencing depth and how many will be
3371expected from additional sequencing using an initial sequencing experiment.
3372The estimates can then be used to examine the utility of further sequencing,
3373optimize the sequencing depth, or to screen multiple libraries to avoid low
3374complexity samples.")
3375 (license license:gpl3+)))
3376
51c64999
RW		 3377(define-public sra-tools
3378 (package
3379 (name "sra-tools")
a78d62f4 3380 (version "2.5.7")
51c64999
RW		 3381 (source
3382 (origin
3383 (method url-fetch)
3384 (uri
3385 (string-append "https://github.com/ncbi/sra-tools/archive/"
3386 version ".tar.gz"))
3387 (file-name (string-append name "-" version ".tar.gz"))
3388 (sha256
3389 (base32
a78d62f4 3390 "0q93qg744x787d08qmjmdafki1wkbvkdwynayjnjd454gkd26jl5"))))
51c64999
RW		 3391 (build-system gnu-build-system)
3392 (arguments
3393 `(#:parallel-build? #f ; not supported
3394 #:tests? #f ; no "check" target
3395 #:phases
3396 (alist-replace
3397 'configure
3398 (lambda* (#:key inputs outputs #:allow-other-keys)
3399 ;; The build system expects a directory containing the sources and
3400 ;; raw build output of ncbi-vdb, including files that are not
3401 ;; installed. Since we are building against an installed version of
3402 ;; ncbi-vdb, the following modifications are needed.
3403 (substitute* "setup/konfigure.perl"
3404 ;; Make the configure script look for the "ilib" directory of
3405 ;; "ncbi-vdb" without first checking for the existence of a
3406 ;; matching library in its "lib" directory.
3407 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
3408 "my $f = File::Spec->catdir($ilibdir, $ilib);")
3409 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
3410 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
3411 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
3412
3413 ;; The 'configure' script doesn't recognize things like
3414 ;; '--enable-fast-install'.
3415 (zero? (system*
3416 "./configure"
3417 (string-append "--build-prefix=" (getcwd) "/build")
3418 (string-append "--prefix=" (assoc-ref outputs "out"))
3419 (string-append "--debug")
3420 (string-append "--with-fuse-prefix="
3421 (assoc-ref inputs "fuse"))
3422 (string-append "--with-magic-prefix="
3423 (assoc-ref inputs "libmagic"))
3424 ;; TODO: building with libxml2 fails with linker errors
3425 ;; (string-append "--with-xml2-prefix="
3426 ;; (assoc-ref inputs "libxml2"))
3427 (string-append "--with-ncbi-vdb-sources="
3428 (assoc-ref inputs "ncbi-vdb"))
3429 (string-append "--with-ncbi-vdb-build="
3430 (assoc-ref inputs "ncbi-vdb"))
3431 (string-append "--with-ngs-sdk-prefix="
3432 (assoc-ref inputs "ngs-sdk"))
3433 (string-append "--with-hdf5-prefix="
3434 (assoc-ref inputs "hdf5")))))
3435 %standard-phases)))
3436 (native-inputs `(("perl" ,perl)))
3437 (inputs
3438 `(("ngs-sdk" ,ngs-sdk)
3439 ("ncbi-vdb" ,ncbi-vdb)
3440 ("libmagic" ,file)
3441 ("fuse" ,fuse)
3442 ("hdf5" ,hdf5)
3443 ("zlib" ,zlib)))
3444 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
3445 (synopsis "Tools and libraries for reading and writing sequencing data")
3446 (description
3447 "The SRA Toolkit from NCBI is a collection of tools and libraries for
3448reading of sequencing files from the Sequence Read Archive (SRA) database and
3449writing files into the .sra format.")
3450 (license license:public-domain)))
3451
d3517eda
RW		 3452(define-public seqan
3453 (package
3454 (name "seqan")
3455 (version "1.4.2")
3456 (source (origin
3457 (method url-fetch)
3458 (uri (string-append "http://packages.seqan.de/seqan-library/"
3459 "seqan-library-" version ".tar.bz2"))
3460 (sha256
3461 (base32
3462 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
3463 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
3464 ;; makes sense to split the outputs.
3465 (outputs '("out" "doc"))
3466 (build-system trivial-build-system)
3467 (arguments
3468 `(#:modules ((guix build utils))
3469 #:builder
3470 (begin
3471 (use-modules (guix build utils))
3472 (let ((tar (assoc-ref %build-inputs "tar"))
3473 (bzip (assoc-ref %build-inputs "bzip2"))
3474 (out (assoc-ref %outputs "out"))
3475 (doc (assoc-ref %outputs "doc")))
3476 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
3477 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
3478 (chdir (string-append "seqan-library-" ,version))
3479 (copy-recursively "include" (string-append out "/include"))
3480 (copy-recursively "share" (string-append doc "/share"))))))
3481 (native-inputs
3482 `(("source" ,source)
3483 ("tar" ,tar)
3484 ("bzip2" ,bzip2)))
3485 (home-page "http://www.seqan.de")
3486 (synopsis "Library for nucleotide sequence analysis")
3487 (description
3488 "SeqAn is a C++ library of efficient algorithms and data structures for
3489the analysis of sequences with the focus on biological data. It contains
3490algorithms and data structures for string representation and their
3491manipulation, online and indexed string search, efficient I/O of
3492bioinformatics file formats, sequence alignment, and more.")
3493 (license license:bsd-3)))
ce7155d5 3494
d708b7a9
BW		 3495(define-public seqmagick
3496 (package
3497 (name "seqmagick")
3498 (version "0.6.1")
3499 (source
3500 (origin
3501 (method url-fetch)
3502 (uri (string-append
3503 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
3504 version ".tar.gz"))
3505 (sha256
3506 (base32
3507 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
3508 (build-system python-build-system)
3509 (arguments
3510 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
3511 `(#:python ,python-2
3512 #:phases
3513 (modify-phases %standard-phases
3514 ;; Current test in setup.py does not work as of 0.6.1,
3515 ;; so use nose to run tests instead for now. See
3516 ;; https://github.com/fhcrc/seqmagick/issues/55
3517 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
3518 (inputs
3519 `(("python-biopython" ,python2-biopython)))
3520 (native-inputs
3521 `(("python-setuptools" ,python2-setuptools)
3522 ("python-nose" ,python2-nose)))
3523 (home-page "http://github.com/fhcrc/seqmagick")
3524 (synopsis "Tools for converting and modifying sequence files")
3525 (description
3526 "Bioinformaticians often have to convert sequence files between formats
3527and do little manipulations on them, and it's not worth writing scripts for
3528that. Seqmagick is a utility to expose the file format conversion in
3529BioPython in a convenient way. Instead of having a big mess of scripts, there
3530is one that takes arguments.")
3531 (license license:gpl3)))
3532
5f7e17be
BW		 3533(define-public snap-aligner
3534 (package
3535 (name "snap-aligner")
3536 (version "1.0beta.18")
3537 (source (origin
3538 (method url-fetch)
3539 (uri (string-append
3540 "https://github.com/amplab/snap/archive/v"
3541 version ".tar.gz"))
3542 (file-name (string-append name "-" version ".tar.gz"))
3543 (sha256
3544 (base32
3545 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
3546 (build-system gnu-build-system)
3547 (arguments
3548 '(#:phases
3549 (modify-phases %standard-phases
3550 (delete 'configure)
3551 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
3552 (replace 'install
3553 (lambda* (#:key outputs #:allow-other-keys)
3554 (let* ((out (assoc-ref outputs "out"))
3555 (bin (string-append out "/bin")))
3556 (mkdir-p bin)
3557 (install-file "snap-aligner" bin)
3558 (install-file "SNAPCommand" bin)
3559 #t))))))
3560 (native-inputs
3561 `(("zlib" ,zlib)))
3562 (home-page "http://snap.cs.berkeley.edu/")
3563 (synopsis "Short read DNA sequence aligner")
3564 (description
3565 "SNAP is a fast and accurate aligner for short DNA reads. It is
3566optimized for modern read lengths of 100 bases or higher, and takes advantage
3567of these reads to align data quickly through a hash-based indexing scheme.")
3568 (license license:asl2.0)))
3569
bcadaf00
BW		 3570(define-public sortmerna
3571 (package
3572 (name "sortmerna")
ce294c04 3573 (version "2.1")
bcadaf00
BW		 3574 (source
3575 (origin
3576 (method url-fetch)
3577 (uri (string-append
3578 "https://github.com/biocore/sortmerna/archive/"
3579 version ".tar.gz"))
3580 (file-name (string-append name "-" version ".tar.gz"))
3581 (sha256
3582 (base32
ce294c04 3583 "1mc5cf1c7xh0h7xb11vh7gqgzx0qvrfa606cb8ixlfg3f2av58s4"))))
bcadaf00
BW		 3584 (build-system gnu-build-system)
3585 (outputs '("out" ;for binaries
3586 "db")) ;for sequence databases
3587 (arguments
3588 `(#:phases
3589 (modify-phases %standard-phases
3590 (replace 'install
3591 (lambda* (#:key outputs #:allow-other-keys)
3592 (let* ((out (assoc-ref outputs "out"))
3593 (bin (string-append out "/bin"))
3594 (db (assoc-ref outputs "db"))
3595 (share
3596 (string-append db "/share/sortmerna/rRNA_databases")))
3597 (install-file "sortmerna" bin)
3598 (install-file "indexdb_rna" bin)
3599 (for-each (lambda (file)
3600 (install-file file share))
3601 (find-files "rRNA_databases" ".*fasta"))
3602 #t))))))
3603 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
3604 (synopsis "Biological sequence analysis tool for NGS reads")
3605 (description
3606 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
3607and operational taxonomic unit (OTU) picking of next generation
3608sequencing (NGS) reads. The core algorithm is based on approximate seeds and
3609allows for fast and sensitive analyses of nucleotide sequences. The main
3610application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
3611 (license license:lgpl3)))
3612
ce7155d5
RW		 3613(define-public star
3614 (package
3615 (name "star")
3062d750 3616 (version "2.5.1b")
ce7155d5
RW		 3617 (source (origin
3618 (method url-fetch)
3062d750
RW		 3619 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
3620 version ".tar.gz"))
3621 (file-name (string-append name "-" version ".tar.gz"))
ce7155d5
RW		 3622 (sha256
3623 (base32
3062d750 3624 "0wzcfhkg10apnh0y73xlarfa79xxwxdizicbdl11wb48awk44iq4"))
ce7155d5
RW		 3625 (modules '((guix build utils)))
3626 (snippet
3062d750
RW		 3627 '(begin
3628 (substitute* "source/Makefile"
3629 (("/bin/rm") "rm"))
3630 ;; Remove pre-built binaries and bundled htslib sources.
3631 (delete-file-recursively "bin/MacOSX_x86_64")
3632 (delete-file-recursively "bin/Linux_x86_64")
3633 (delete-file-recursively "source/htslib")
3634 #t))))
ce7155d5
RW		 3635 (build-system gnu-build-system)
3636 (arguments
3637 '(#:tests? #f ;no check target
3638 #:make-flags '("STAR")
3639 #:phases
c0266e8d
RW		 3640 (modify-phases %standard-phases
3641 (add-after 'unpack 'enter-source-dir
3642 (lambda _ (chdir "source") #t))
3062d750
RW		 3643 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
3644 (lambda _
3645 (substitute* "Makefile"
3646 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
3647 _ prefix) prefix))
3648 (substitute* '("BAMfunctions.cpp"
3649 "signalFromBAM.h"
3650 "bam_cat.h"
3651 "bam_cat.c"
3652 "STAR.cpp"
3653 "bamRemoveDuplicates.cpp")
3654 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
3655 (string-append "#include <" header ">")))
3656 (substitute* "IncludeDefine.h"
3657 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
3658 (string-append "<" header ">")))
3659 #t))
c0266e8d
RW		 3660 (replace 'install
3661 (lambda* (#:key outputs #:allow-other-keys)
3662 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3663 (install-file "STAR" bin))
3664 #t))
3665 (delete 'configure))))
ce7155d5
RW		 3666 (native-inputs
3667 `(("vim" ,vim))) ; for xxd
3668 (inputs
3062d750
RW		 3669 `(("htslib" ,htslib)
3670 ("zlib" ,zlib)))
ce7155d5
RW		 3671 (home-page "https://github.com/alexdobin/STAR")
3672 (synopsis "Universal RNA-seq aligner")
3673 (description
3674 "The Spliced Transcripts Alignment to a Reference (STAR) software is
3675based on a previously undescribed RNA-seq alignment algorithm that uses
3676sequential maximum mappable seed search in uncompressed suffix arrays followed
3677by seed clustering and stitching procedure. In addition to unbiased de novo
3678detection of canonical junctions, STAR can discover non-canonical splices and
3679chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
3680sequences.")
3681 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
3682 (license license:gpl3+)))
de07c0db 3683
dbf4ed7c
RW		 3684(define-public subread
3685 (package
3686 (name "subread")
3687 (version "1.4.6-p2")
3688 (source (origin
3689 (method url-fetch)
3690 (uri (string-append
3691 "mirror://sourceforge/subread/subread-"
3692 version "-source.tar.gz"))
3693 (sha256
3694 (base32
3695 "06sv9mpcsdj6p68y15d6gi70lca3lxmzk0dn61hg0kfsa7rxmsr3"))))
3696 (build-system gnu-build-system)
3697 (arguments
3698 `(#:tests? #f ;no "check" target
104c1986
RW		 3699 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
3700 ;; optimizations by default, so we override these flags such that x86_64
3701 ;; flags are only added when the build target is an x86_64 system.
3702 #:make-flags
3703 (list (let ((system ,(or (%current-target-system)
3704 (%current-system)))
3705 (flags '("-ggdb" "-fomit-frame-pointer"
3706 "-ffast-math" "-funroll-loops"
3707 "-fmessage-length=0"
3708 "-O9" "-Wall" "-DMAKE_FOR_EXON"
3709 "-DMAKE_STANDALONE"
3710 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
3711 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
3712 (if (string-prefix? "x86_64" system)
3713 (string-append "CCFLAGS=" (string-join (append flags flags64)))
3714 (string-append "CCFLAGS=" (string-join flags))))
3715 "-f" "Makefile.Linux"
3716 "CC=gcc ${CCFLAGS}")
dbf4ed7c
RW		 3717 #:phases
3718 (alist-cons-after
3719 'unpack 'enter-dir
3720 (lambda _ (chdir "src") #t)
3721 (alist-replace
3722 'install
3723 (lambda* (#:key outputs #:allow-other-keys)
3724 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3725 (mkdir-p bin)
3726 (copy-recursively "../bin" bin)))
3727 ;; no "configure" script
3728 (alist-delete 'configure %standard-phases)))))
3729 (inputs `(("zlib" ,zlib)))
3730 (home-page "http://bioinf.wehi.edu.au/subread-package/")
3731 (synopsis "Tool kit for processing next-gen sequencing data")
3732 (description
3733 "The subread package contains the following tools: subread aligner, a
3734general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
3735and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
3736features; exactSNP: a SNP caller that discovers SNPs by testing signals
3737against local background noises.")
3738 (license license:gpl3+)))
3739
d15d981e
RW		 3740(define-public stringtie
3741 (package
3742 (name "stringtie")
3743 (version "1.2.1")
3744 (source (origin
3745 (method url-fetch)
3746 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
3747 "stringtie-" version ".tar.gz"))
3748 (sha256
3749 (base32
3750 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
3751 (modules '((guix build utils)))
3752 (snippet
3753 '(begin
3754 (delete-file-recursively "samtools-0.1.18")
3755 #t))))
3756 (build-system gnu-build-system)
3757 (arguments
3758 `(#:tests? #f ;no test suite
3759 #:phases
3760 (modify-phases %standard-phases
3761 ;; no configure script
3762 (delete 'configure)
3763 (add-before 'build 'use-system-samtools
3764 (lambda _
3765 (substitute* "Makefile"
3766 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
3767 "stringtie: "))
3768 (substitute* '("gclib/GBam.h"
3769 "gclib/GBam.cpp")
3770 (("#include \"(bam|sam|kstring).h\"" _ header)
3771 (string-append "#include <samtools/" header ".h>")))
3772 #t))
3773 (replace 'install
3774 (lambda* (#:key outputs #:allow-other-keys)
3775 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3776 (install-file "stringtie" bin)
3777 #t))))))
3778 (inputs
3779 `(("samtools" ,samtools-0.1)
3780 ("zlib" ,zlib)))
3781 (home-page "http://ccb.jhu.edu/software/stringtie/")
3782 (synopsis "Transcript assembly and quantification for RNA-Seq data")
3783 (description
3784 "StringTie is a fast and efficient assembler of RNA-Seq sequence
3785alignments into potential transcripts. It uses a novel network flow algorithm
3786as well as an optional de novo assembly step to assemble and quantitate
3787full-length transcripts representing multiple splice variants for each gene
3788locus. Its input can include not only the alignments of raw reads used by
3789other transcript assemblers, but also alignments of longer sequences that have
3790been assembled from those reads. To identify differentially expressed genes
3791between experiments, StringTie's output can be processed either by the
3792Cuffdiff or Ballgown programs.")
3793 (license license:artistic2.0)))
3794
de07c0db
RW		 3795(define-public vcftools
3796 (package
3797 (name "vcftools")
9b36e256 3798 (version "0.1.14")
de07c0db
RW		 3799 (source (origin
3800 (method url-fetch)
3801 (uri (string-append
9b36e256
RJ		 3802 "https://github.com/vcftools/vcftools/releases/download/v"
3803 version "/vcftools-" version ".tar.gz"))
de07c0db
RW		 3804 (sha256
3805 (base32
9b36e256 3806 "10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
de07c0db
RW		 3807 (build-system gnu-build-system)
3808 (arguments
3809 `(#:tests? #f ; no "check" target
3810 #:make-flags (list
7c3958e1 3811 "CFLAGS=-O2" ; override "-m64" flag
de07c0db
RW		 3812 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3813 (string-append "MANDIR=" (assoc-ref %outputs "out")
9b36e256
RJ		 3814 "/share/man/man1"))))
3815 (native-inputs
3816 `(("pkg-config" ,pkg-config)))
de07c0db
RW		 3817 (inputs
3818 `(("perl" ,perl)
3819 ("zlib" ,zlib)))
9b36e256 3820 (home-page "https://vcftools.github.io/")
de07c0db
RW		 3821 (synopsis "Tools for working with VCF files")
3822 (description
3823 "VCFtools is a program package designed for working with VCF files, such
3824as those generated by the 1000 Genomes Project. The aim of VCFtools is to
3825provide easily accessible methods for working with complex genetic variation
3826data in the form of VCF files.")
3827 ;; The license is declared as LGPLv3 in the README and
9b36e256 3828 ;; at https://vcftools.github.io/license.html
de07c0db 3829 (license license:lgpl3)))
9c38b540 3830
a2950fa4
BW		 3831(define-public vsearch
3832 (package
3833 (name "vsearch")
cf6edaba 3834 (version "1.10.0")
a2950fa4
BW		 3835 (source
3836 (origin
3837 (method url-fetch)
3838 (uri (string-append
3839 "https://github.com/torognes/vsearch/archive/v"
3840 version ".tar.gz"))
3841 (file-name (string-append name "-" version ".tar.gz"))
3842 (sha256
3843 (base32
cf6edaba 3844 "1i3bad7gnn2y3a1yfixzshd99xdkjc8w5bxzgifpysc6jiljwvb5"))
a2950fa4
BW		 3845 (modules '((guix build utils)))
3846 (snippet
3847 '(begin
3848 ;; Remove bundled cityhash and '-mtune=native'.
3849 (substitute* "src/Makefile.am"
3850 (("^AM_CXXFLAGS=-I\\$\\{srcdir\\}/cityhash \
3851-O3 -mtune=native -Wall -Wsign-compare")
3852 (string-append "AM_CXXFLAGS=-lcityhash"
3853 " -O3 -Wall -Wsign-compare"))
cf6edaba 3854 (("^__top_builddir__bin_vsearch_SOURCES = city.h \\\\")
a2950fa4 3855 "__top_builddir__bin_vsearch_SOURCES = \\")
cf6edaba
BW		 3856 (("^city.h \\\\") "\\")
3857 (("^citycrc.h \\\\") "\\")
3858 (("^libcityhash_a.*") "")
3859 (("noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a \
3860libcityhash.a")
3861 "noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a")
3862 (("__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
3863libcpu_sse2.a libcityhash.a")
3864 "__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
3865libcpu_sse2.a -lcityhash"))
a2950fa4 3866 (substitute* "src/vsearch.h"
cf6edaba
BW		 3867 (("^\\#include \"city.h\"") "#include <city.h>")
3868 (("^\\#include \"citycrc.h\"") "#include <citycrc.h>"))
3869 (delete-file "src/city.h")
3870 (delete-file "src/citycrc.h")
3871 (delete-file "src/city.cc")
a2950fa4
BW		 3872 #t))))
3873 (build-system gnu-build-system)
3874 (arguments
3875 `(#:phases
3876 (modify-phases %standard-phases
3877 (add-before 'configure 'autogen
3878 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3879 (inputs
3880 `(("zlib" ,zlib)
3881 ("bzip2" ,bzip2)
3882 ("cityhash" ,cityhash)))
3883 (native-inputs
3884 `(("autoconf" ,autoconf)
3885 ("automake" ,automake)))
3886 (synopsis "Sequence search tools for metagenomics")
3887 (description
3888 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
3889dereplication, pairwise alignment, shuffling, subsampling, sorting and
3890masking. The tool takes advantage of parallelism in the form of SIMD
3891vectorization as well as multiple threads to perform accurate alignments at
3892high speed. VSEARCH uses an optimal global aligner (full dynamic programming
3893Needleman-Wunsch).")
3894 (home-page "https://github.com/torognes/vsearch")
6f04e515
BW		 3895 ;; vsearch uses non-portable SSE intrinsics so building fails on other
3896 ;; platforms.
3897 (supported-systems '("x86_64-linux"))
a2950fa4
BW		 3898 ;; Dual licensed; also includes public domain source.
3899 (license (list license:gpl3 license:bsd-2))))
3900
9c38b540
PP		 3901(define-public bio-locus
3902 (package
3903 (name "bio-locus")
3904 (version "0.0.7")
3905 (source
3906 (origin
3907 (method url-fetch)
3908 (uri (rubygems-uri "bio-locus" version))
3909 (sha256
3910 (base32
3911 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
3912 (build-system ruby-build-system)
3913 (native-inputs
3914 `(("ruby-rspec" ,ruby-rspec)))
3915 (synopsis "Tool for fast querying of genome locations")
3916 (description
3917 "Bio-locus is a tabix-like tool for fast querying of genome
3918locations. Many file formats in bioinformatics contain records that
3919start with a chromosome name and a position for a SNP, or a start-end
3920position for indels. Bio-locus allows users to store this chr+pos or
3921chr+pos+alt information in a database.")
3922 (home-page "https://github.com/pjotrp/bio-locus")
3923 (license license:expat)))
edb15985 3924
b2bddb07
PP		 3925(define-public bio-blastxmlparser
3926 (package
3927 (name "bio-blastxmlparser")
3928 (version "2.0.4")
3929 (source (origin
3930 (method url-fetch)
3931 (uri (rubygems-uri "bio-blastxmlparser" version))
3932 (sha256
3933 (base32
3934 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
3935 (build-system ruby-build-system)
3936 (propagated-inputs
3937 `(("ruby-bio-logger" ,ruby-bio-logger)
3938 ("ruby-nokogiri" ,ruby-nokogiri)))
3939 (inputs
3940 `(("ruby-rspec" ,ruby-rspec)))
3941 (synopsis "Fast big data BLAST XML parser and library")
3942 (description
3943 "Very fast parallel big-data BLAST XML file parser which can be used as
3944command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
3945generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
3946 (home-page "http://github.com/pjotrp/blastxmlparser")
3947 (license license:expat)))
3948
edb15985
PP		 3949(define-public bioruby
3950 (package
3951 (name "bioruby")
3952 (version "1.5.0")
3953 (source
3954 (origin
3955 (method url-fetch)
3956 (uri (rubygems-uri "bio" version))
3957 (sha256
3958 (base32
3959 "01k2fyjl5fpx4zn8g6gqiqvsg2j1fgixrs9p03vzxckynxdq3wmc"))))
3960 (build-system ruby-build-system)
3961 (propagated-inputs
3962 `(("ruby-libxml" ,ruby-libxml)))
3963 (native-inputs
3964 `(("which" ,which))) ; required for test phase
3965 (arguments
3966 `(#:phases
3967 (modify-phases %standard-phases
3968 (add-before 'build 'patch-test-command
3969 (lambda _
3970 (substitute* '("test/functional/bio/test_command.rb")
3971 (("/bin/sh") (which "sh")))
3972 (substitute* '("test/functional/bio/test_command.rb")
3973 (("/bin/ls") (which "ls")))
3974 (substitute* '("test/functional/bio/test_command.rb")
3975 (("which") (which "which")))
3976 (substitute* '("test/functional/bio/test_command.rb",
3977 "test/data/command/echoarg2.sh")
3978 (("/bin/echo") (which "echo")))
3979 #t)))))
3980 (synopsis "Ruby library, shell and utilities for bioinformatics")
3981 (description "BioRuby comes with a comprehensive set of Ruby development
3982tools and libraries for bioinformatics and molecular biology. BioRuby has
3983components for sequence analysis, pathway analysis, protein modelling and
3984phylogenetic analysis; it supports many widely used data formats and provides
3985easy access to databases, external programs and public web services, including
3986BLAST, KEGG, GenBank, MEDLINE and GO.")
3987 (home-page "http://bioruby.org/")
3988 ;; Code is released under Ruby license, except for setup
3989 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
3990 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
a5002ae7 3991
9fba89e8
RW		 3992(define-public r-acsnminer
3993 (package
3994 (name "r-acsnminer")
fb868e33 3995 (version "0.16.01.29")
9fba89e8
RW		 3996 (source (origin
3997 (method url-fetch)
3998 (uri (cran-uri "ACSNMineR" version))
3999 (sha256
4000 (base32
fb868e33 4001 "1b1243wkncanm1blkqzicjgzb576vzcg4iwinsgn2xqr7f264amf"))))
9fba89e8
RW		 4002 (properties `((upstream-name . "ACSNMineR")))
4003 (build-system r-build-system)
4004 (propagated-inputs
4005 `(("r-ggplot2" ,r-ggplot2)
4006 ("r-gridextra" ,r-gridextra)))
4007 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
4008 (synopsis "Gene enrichment analysis")
4009 (description
4010 "This package provides tools to compute and represent gene set enrichment
4011or depletion from your data based on pre-saved maps from the @dfn{Atlas of
4012Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
4013enrichment can be run with hypergeometric test or Fisher exact test, and can
4014use multiple corrections. Visualization of data can be done either by
4015barplots or heatmaps.")
4016 (license license:gpl2+)))
4017
d29b25c4
RW		 4018(define-public r-biocgenerics
4019 (package
4020 (name "r-biocgenerics")
4021 (version "0.16.1")
4022 (source (origin
4023 (method url-fetch)
4024 (uri (bioconductor-uri "BiocGenerics" version))
4025 (sha256
4026 (base32
4027 "0f16ryy5f012hvksrwlmm33bcl7lw97i2jvhbnwfwl03j4w7nhc1"))))
4028 (properties
1d216b6e 4029 `((upstream-name . "BiocGenerics")))
d29b25c4
RW		 4030 (build-system r-build-system)
4031 (home-page "http://bioconductor.org/packages/BiocGenerics")
4032 (synopsis "S4 generic functions for Bioconductor")
4033 (description
4034 "This package provides S4 generic functions needed by many Bioconductor
4035packages.")
4036 (license license:artistic2.0)))
4037
247d498a
RJ		 4038(define-public r-dnacopy
4039 (package
4040 (name "r-dnacopy")
4041 (version "1.44.0")
4042 (source (origin
4043 (method url-fetch)
4044 (uri (bioconductor-uri "DNAcopy" version))
4045 (sha256
4046 (base32
4047 "1c1px4rbr36xx929hp59k7ca9k5ab66qmn8k63fk13278ncm6h66"))))
4048 (properties
4049 `((upstream-name . "DNAcopy")))
4050 (build-system r-build-system)
4051 (inputs
4052 `(("gfortran" ,gfortran)))
5697fdc3 4053 (home-page "https://bioconductor.org/packages/DNAcopy")
247d498a
RJ		 4054 (synopsis "Implementation of a circular binary segmentation algorithm")
4055 (description "This package implements the circular binary segmentation (CBS)
4056algorithm to segment DNA copy number data and identify genomic regions with
4057abnormal copy number.")
4058 (license license:gpl2+)))
4059
7485129e
RW		 4060(define-public r-s4vectors
4061 (package
4062 (name "r-s4vectors")
8921841d 4063 (version "0.8.11")
7485129e
RW		 4064 (source (origin
4065 (method url-fetch)
4066 (uri (bioconductor-uri "S4Vectors" version))
4067 (sha256
4068 (base32
8921841d 4069 "12iibcs63m9iy7f45wgjcqsna2dnqwckphk682389grshz0g4x66"))))
7485129e 4070 (properties
1d216b6e 4071 `((upstream-name . "S4Vectors")))
7485129e
RW		 4072 (build-system r-build-system)
4073 (propagated-inputs
4074 `(("r-biocgenerics" ,r-biocgenerics)))
4075 (home-page "http://bioconductor.org/packages/S4Vectors")
4076 (synopsis "S4 implementation of vectors and lists")
4077 (description
4078 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
4079classes and a set of generic functions that extend the semantic of ordinary
4080vectors and lists in R. Package developers can easily implement vector-like
4081or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
4082In addition, a few low-level concrete subclasses of general interest (e.g.
4083@code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
4084S4Vectors package itself.")
4085 (license license:artistic2.0)))
4086
78addcb0
RW		 4087(define-public r-iranges
4088 (package
4089 (name "r-iranges")
27acfaea 4090 (version "2.4.8")
78addcb0
RW		 4091 (source (origin
4092 (method url-fetch)
4093 (uri (bioconductor-uri "IRanges" version))
4094 (sha256
4095 (base32
27acfaea 4096 "0hi5k1j5jm4xrg1l506g279qw1xkvp1gg1zgsjzpbng4vx4k4iyl"))))
78addcb0 4097 (properties
1d216b6e 4098 `((upstream-name . "IRanges")))
78addcb0
RW		 4099 (build-system r-build-system)
4100 (propagated-inputs
4101 `(("r-biocgenerics" ,r-biocgenerics)
4102 ("r-s4vectors" ,r-s4vectors)))
4103 (home-page "http://bioconductor.org/packages/IRanges")
4104 (synopsis "Infrastructure for manipulating intervals on sequences")
4105 (description
4106 "This package provides efficient low-level and highly reusable S4 classes
4107for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
4108generally, data that can be organized sequentially (formally defined as
4109@code{Vector} objects), as well as views on these @code{Vector} objects.
4110Efficient list-like classes are also provided for storing big collections of
4111instances of the basic classes. All classes in the package use consistent
4112naming and share the same rich and consistent \"Vector API\" as much as
4113possible.")
4114 (license license:artistic2.0)))
4115
bf7764b7
RW		 4116(define-public r-genomeinfodb
4117 (package
4118 (name "r-genomeinfodb")
9cc22d28 4119 (version "1.6.3")
bf7764b7
RW		 4120 (source (origin
4121 (method url-fetch)
4122 (uri (bioconductor-uri "GenomeInfoDb" version))
4123 (sha256
4124 (base32
9cc22d28 4125 "1ggp005n2rlkad00ilzn95y4rd484yr1chdhnd6fwg45rbi94d63"))))
bf7764b7 4126 (properties
1d216b6e 4127 `((upstream-name . "GenomeInfoDb")))
bf7764b7
RW		 4128 (build-system r-build-system)
4129 (propagated-inputs
4130 `(("r-biocgenerics" ,r-biocgenerics)
4131 ("r-iranges" ,r-iranges)
4132 ("r-s4vectors" ,r-s4vectors)))
4133 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
4134 (synopsis "Utilities for manipulating chromosome identifiers")
4135 (description
4136 "This package contains data and functions that define and allow
4137translation between different chromosome sequence naming conventions (e.g.,
4138\"chr1\" versus \"1\"), including a function that attempts to place sequence
4139names in their natural, rather than lexicographic, order.")
4140 (license license:artistic2.0)))
4141
b669d9c4
RJ		 4142(define-public r-variantannotation
4143 (package
4144 (name "r-variantannotation")
4145 (version "1.16.4")
4146 (source (origin
4147 (method url-fetch)
4148 (uri (bioconductor-uri "VariantAnnotation" version))
4149 (sha256
4150 (base32
4151 "1z42j3p9b8h725inq8n0230llsdbav3gwcxy1nliypzfkxbzahsb"))))
4152 (properties
4153 `((upstream-name . "VariantAnnotation")))
4154 (inputs
4155 `(("zlib" ,zlib)))
4156 (propagated-inputs
4157 `(("r-annotationdbi" ,r-annotationdbi)
4158 ("r-biocgenerics" ,r-biocgenerics)
4159 ("r-bsgenome" ,r-bsgenome)
4160 ("r-dbi" ,r-dbi)
4161 ("r-genomeinfodb" ,r-genomeinfodb)
4162 ("r-genomicfeatures" ,r-genomicfeatures)
4163 ("r-genomicranges" ,r-genomicranges)
4164 ("r-summarizedexperiment" ,r-summarizedexperiment)
4165 ("r-rsamtools" ,r-rsamtools)
4166 ("r-zlibbioc" ,r-zlibbioc)))
4167 (build-system r-build-system)
4168 (home-page "https://bioconductor.org/packages/VariantAnnotation")
4169 (synopsis "Package for annotation of genetic variants")
4170 (description "This R package can annotate variants, compute amino acid
4171coding changes and predict coding outcomes.")
4172 (license license:artistic2.0)))
4173
0e7d5560
RW		 4174(define-public r-xvector
4175 (package
4176 (name "r-xvector")
4177 (version "0.10.0")
4178 (source (origin
4179 (method url-fetch)
4180 (uri (bioconductor-uri "XVector" version))
4181 (sha256
4182 (base32
4183 "0havwyr6xqk7w0rmbwfj9jq1djz7wzdz7w39adhklwzwz9l4ih3a"))))
4184 (properties
1d216b6e 4185 `((upstream-name . "XVector")))
0e7d5560
RW		 4186 (build-system r-build-system)
4187 (arguments
4188 `(#:phases
4189 (modify-phases %standard-phases
4190 (add-after 'unpack 'use-system-zlib
4191 (lambda _
4192 (substitute* "DESCRIPTION"
4193 (("zlibbioc, ") ""))
4194 (substitute* "NAMESPACE"
4195 (("import\\(zlibbioc\\)") ""))
4196 #t)))))
4197 (inputs
4198 `(("zlib" ,zlib)))
4199 (propagated-inputs
4200 `(("r-biocgenerics" ,r-biocgenerics)
4201 ("r-iranges" ,r-iranges)
4202 ("r-s4vectors" ,r-s4vectors)))
4203 (home-page "http://bioconductor.org/packages/XVector")
4204 (synopsis "Representation and manpulation of external sequences")
4205 (description
4206 "This package provides memory efficient S4 classes for storing sequences
4207\"externally\" (behind an R external pointer, or on disk).")
4208 (license license:artistic2.0)))
4209
e2cd1d0f
RW		 4210(define-public r-genomicranges
4211 (package
4212 (name "r-genomicranges")
5fe31154 4213 (version "1.22.4")
e2cd1d0f
RW		 4214 (source (origin
4215 (method url-fetch)
4216 (uri (bioconductor-uri "GenomicRanges" version))
4217 (sha256
4218 (base32
5fe31154 4219 "02df5683nrpn9d10ws8jz9b55nr9055hh882xp2i154xdddir0k0"))))
e2cd1d0f 4220 (properties
1d216b6e 4221 `((upstream-name . "GenomicRanges")))
e2cd1d0f
RW		 4222 (build-system r-build-system)
4223 (propagated-inputs
4224 `(("r-biocgenerics" ,r-biocgenerics)
4225 ("r-genomeinfodb" ,r-genomeinfodb)
4226 ("r-xvector" ,r-xvector)))
4227 (home-page "http://bioconductor.org/packages/GenomicRanges")
4228 (synopsis "Representation and manipulation of genomic intervals")
4229 (description
4230 "This package provides tools to efficiently represent and manipulate
4231genomic annotations and alignments is playing a central role when it comes to
4232analyzing high-throughput sequencing data (a.k.a. NGS data). The
4233GenomicRanges package defines general purpose containers for storing and
4234manipulating genomic intervals and variables defined along a genome.")
4235 (license license:artistic2.0)))
4236
555e3399
RW		 4237(define-public r-biobase
4238 (package
4239 (name "r-biobase")
4240 (version "2.30.0")
4241 (source (origin
4242 (method url-fetch)
4243 (uri (bioconductor-uri "Biobase" version))
4244 (sha256
4245 (base32
4246 "1qasjpq3kw8h7qw8cin3bjvv1256hqr1mm24fq3v0ymxzlb66szi"))))
4247 (properties
4248 `((upstream-name . "Biobase")))
4249 (build-system r-build-system)
4250 (propagated-inputs
4251 `(("r-biocgenerics" ,r-biocgenerics)))
4252 (home-page "http://bioconductor.org/packages/Biobase")
4253 (synopsis "Base functions for Bioconductor")
4254 (description
4255 "This package provides functions that are needed by many other packages
4256on Bioconductor or which replace R functions.")
4257 (license license:artistic2.0)))
4258
8b7bce74
RW		 4259(define-public r-annotationdbi
4260 (package
4261 (name "r-annotationdbi")
258c0a36 4262 (version "1.32.3")
8b7bce74
RW		 4263 (source (origin
4264 (method url-fetch)
4265 (uri (bioconductor-uri "AnnotationDbi" version))
4266 (sha256
4267 (base32
258c0a36 4268 "1v6x62hgys5827yg2xayjrd9xawbayzm6wy0q4vxh1s6yxc9bklj"))))
8b7bce74
RW		 4269 (properties
4270 `((upstream-name . "AnnotationDbi")))
4271 (build-system r-build-system)
4272 (propagated-inputs
4273 `(("r-biobase" ,r-biobase)
4274 ("r-biocgenerics" ,r-biocgenerics)
4275 ("r-dbi" ,r-dbi)
4276 ("r-iranges" ,r-iranges)
4277 ("r-rsqlite" ,r-rsqlite)
4278 ("r-s4vectors" ,r-s4vectors)))
4279 (home-page "http://bioconductor.org/packages/AnnotationDbi")
4280 (synopsis "Annotation database interface")
4281 (description
4282 "This package provides user interface and database connection code for
4283annotation data packages using SQLite data storage.")
4284 (license license:artistic2.0)))
4285
c465fa72
RW		 4286(define-public r-biomart
4287 (package
4288 (name "r-biomart")
4289 (version "2.26.1")
4290 (source (origin
4291 (method url-fetch)
4292 (uri (bioconductor-uri "biomaRt" version))
4293 (sha256
4294 (base32
4295 "1s709055abj2gd35g6nnk5d2ai5ii09iir270l2xika6pi62gj3f"))))
4296 (properties
4297 `((upstream-name . "biomaRt")))
4298 (build-system r-build-system)
4299 (propagated-inputs
4300 `(("r-annotationdbi" ,r-annotationdbi)
4301 ("r-rcurl" ,r-rcurl)
4302 ("r-xml" ,r-xml)))
4303 (home-page "http://bioconductor.org/packages/biomaRt")
4304 (synopsis "Interface to BioMart databases")
4305 (description
4306 "biomaRt provides an interface to a growing collection of databases
4307implementing the @url{BioMart software suite, http://www.biomart.org}. The
4308package enables retrieval of large amounts of data in a uniform way without
4309the need to know the underlying database schemas or write complex SQL queries.
4310Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
4311Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
4312users direct access to a diverse set of data and enable a wide range of
4313powerful online queries from gene annotation to database mining.")
4314 (license license:artistic2.0)))
4315
e91d362e
RW		 4316(define-public r-biocparallel
4317 (package
4318 (name "r-biocparallel")
4319 (version "1.4.3")
4320 (source (origin
4321 (method url-fetch)
4322 (uri (bioconductor-uri "BiocParallel" version))
4323 (sha256
4324 (base32
4325 "1f5mndx66vampcsq0n66afg6x851crl0h3nyv2nyp9bsgzj9cdzq"))))
4326 (properties
4327 `((upstream-name . "BiocParallel")))
4328 (build-system r-build-system)
4329 (propagated-inputs
4330 `(("r-futile-logger" ,r-futile-logger)
4331 ("r-snow" ,r-snow)))
4332 (home-page "http://bioconductor.org/packages/BiocParallel")
4333 (synopsis "Bioconductor facilities for parallel evaluation")
4334 (description
4335 "This package provides modified versions and novel implementation of
4336functions for parallel evaluation, tailored to use with Bioconductor
4337objects.")
4338 (license (list license:gpl2+ license:gpl3+))))
4339
bf159353
RW		 4340(define-public r-biostrings
4341 (package
4342 (name "r-biostrings")
53fd0f5e 4343 (version "2.38.4")
bf159353
RW		 4344 (source (origin
4345 (method url-fetch)
4346 (uri (bioconductor-uri "Biostrings" version))
4347 (sha256
4348 (base32
53fd0f5e 4349 "0cjd7i4bdwabzb02gm753aji5xaihkj5ak8nb0d32cclxbj0hp33"))))
bf159353
RW		 4350 (properties
4351 `((upstream-name . "Biostrings")))
4352 (build-system r-build-system)
4353 (propagated-inputs
4354 `(("r-biocgenerics" ,r-biocgenerics)
4355 ("r-iranges" ,r-iranges)
4356 ("r-s4vectors" ,r-s4vectors)
4357 ("r-xvector" ,r-xvector)))
4358 (home-page "http://bioconductor.org/packages/Biostrings")
4359 (synopsis "String objects and algorithms for biological sequences")
4360 (description
4361 "This package provides memory efficient string containers, string
4362matching algorithms, and other utilities, for fast manipulation of large
4363biological sequences or sets of sequences.")
4364 (license license:artistic2.0)))
4365
f8d74f70
RW		 4366(define-public r-rsamtools
4367 (package
4368 (name "r-rsamtools")
4369 (version "1.22.0")
4370 (source (origin
4371 (method url-fetch)
4372 (uri (bioconductor-uri "Rsamtools" version))
4373 (sha256
4374 (base32
4375 "1yc3nzzms3igjwr4l9yd3wdac95glcs08b4cfp7disyly0wcskjd"))))
4376 (properties
4377 `((upstream-name . "Rsamtools")))
4378 (build-system r-build-system)
4379 (arguments
4380 `(#:phases
4381 (modify-phases %standard-phases
4382 (add-after 'unpack 'use-system-zlib
4383 (lambda _
4384 (substitute* "DESCRIPTION"
4385 (("zlibbioc, ") ""))
4386 (substitute* "NAMESPACE"
4387 (("import\\(zlibbioc\\)") ""))
4388 #t)))))
4389 (inputs
4390 `(("zlib" ,zlib)))
4391 (propagated-inputs
4392 `(("r-biocgenerics" ,r-biocgenerics)
4393 ("r-biocparallel" ,r-biocparallel)
4394 ("r-biostrings" ,r-biostrings)
4395 ("r-bitops" ,r-bitops)
4396 ("r-genomeinfodb" ,r-genomeinfodb)
4397 ("r-genomicranges" ,r-genomicranges)
4398 ("r-iranges" ,r-iranges)
4399 ("r-s4vectors" ,r-s4vectors)
4400 ("r-xvector" ,r-xvector)))
4401 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
4402 (synopsis "Interface to samtools, bcftools, and tabix")
4403 (description
4404 "This package provides an interface to the 'samtools', 'bcftools', and
4405'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
4406binary variant call (BCF) and compressed indexed tab-delimited (tabix)
4407files.")
4408 (license license:expat)))
4409
6e76dda2
RW		 4410(define-public r-summarizedexperiment
4411 (package
4412 (name "r-summarizedexperiment")
7eade1c5 4413 (version "1.0.2")
6e76dda2
RW		 4414 (source (origin
4415 (method url-fetch)
4416 (uri (bioconductor-uri "SummarizedExperiment" version))
4417 (sha256
4418 (base32
7eade1c5 4419 "1gpmh1mi70m5k5qnyjs1h0qn8ajrzalzic7k3762xchxsmmdvxn4"))))
6e76dda2
RW		 4420 (properties
4421 `((upstream-name . "SummarizedExperiment")))
4422 (build-system r-build-system)
4423 (propagated-inputs
4424 `(("r-biobase" ,r-biobase)
4425 ("r-biocgenerics" ,r-biocgenerics)
4426 ("r-genomeinfodb" ,r-genomeinfodb)
4427 ("r-genomicranges" ,r-genomicranges)
4428 ("r-iranges" ,r-iranges)
4429 ("r-s4vectors" ,r-s4vectors)))
4430 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
4431 (synopsis "Container for representing genomic ranges by sample")
4432 (description
4433 "The SummarizedExperiment container contains one or more assays, each
4434represented by a matrix-like object of numeric or other mode. The rows
4435typically represent genomic ranges of interest and the columns represent
4436samples.")
4437 (license license:artistic2.0)))
4438
d8a828af
RW		 4439(define-public r-genomicalignments
4440 (package
4441 (name "r-genomicalignments")
ac2d8b0f 4442 (version "1.6.3")
d8a828af
RW		 4443 (source (origin
4444 (method url-fetch)
4445 (uri (bioconductor-uri "GenomicAlignments" version))
4446 (sha256
4447 (base32
ac2d8b0f 4448 "02b9j1pfd39bkvb623k5k0ziq9rpw093hifqw65vb954dwj29jhd"))))
d8a828af
RW		 4449 (properties
4450 `((upstream-name . "GenomicAlignments")))
4451 (build-system r-build-system)
4452 (propagated-inputs
4453 `(("r-biocgenerics" ,r-biocgenerics)
4454 ("r-biocparallel" ,r-biocparallel)
4455 ("r-biostrings" ,r-biostrings)
4456 ("r-genomeinfodb" ,r-genomeinfodb)
4457 ("r-genomicranges" ,r-genomicranges)
4458 ("r-iranges" ,r-iranges)
4459 ("r-rsamtools" ,r-rsamtools)
4460 ("r-s4vectors" ,r-s4vectors)
4461 ("r-summarizedexperiment" ,r-summarizedexperiment)))
4462 (home-page "http://bioconductor.org/packages/GenomicAlignments")
4463 (synopsis "Representation and manipulation of short genomic alignments")
4464 (description
4465 "This package provides efficient containers for storing and manipulating
4466short genomic alignments (typically obtained by aligning short reads to a
4467reference genome). This includes read counting, computing the coverage,
4468junction detection, and working with the nucleotide content of the
4469alignments.")
4470 (license license:artistic2.0)))
4471
317755ff
RW		 4472(define-public r-rtracklayer
4473 (package
4474 (name "r-rtracklayer")
ffaf72ad 4475 (version "1.30.4")
317755ff
RW		 4476 (source (origin
4477 (method url-fetch)
4478 (uri (bioconductor-uri "rtracklayer" version))
4479 (sha256
4480 (base32
ffaf72ad 4481 "0knjnwywh9k726mq28s3sy013zhw6d6nfa8hfw670720nq18i2p0"))))
317755ff
RW		 4482 (build-system r-build-system)
4483 (arguments
4484 `(#:phases
4485 (modify-phases %standard-phases
4486 (add-after 'unpack 'use-system-zlib
4487 (lambda _
4488 (substitute* "DESCRIPTION"
4489 (("zlibbioc, ") ""))
4490 (substitute* "NAMESPACE"
4491 (("import\\(zlibbioc\\)") ""))
4492 #t)))))
4493 (inputs
4494 `(("zlib" ,zlib)))
4495 (propagated-inputs
4496 `(("r-biocgenerics" ,r-biocgenerics)
4497 ("r-biostrings" ,r-biostrings)
4498 ("r-genomeinfodb" ,r-genomeinfodb)
4499 ("r-genomicalignments" ,r-genomicalignments)
4500 ("r-genomicranges" ,r-genomicranges)
4501 ("r-iranges" ,r-iranges)
4502 ("r-rcurl" ,r-rcurl)
4503 ("r-rsamtools" ,r-rsamtools)
4504 ("r-s4vectors" ,r-s4vectors)
4505 ("r-xml" ,r-xml)
4506 ("r-xvector" ,r-xvector)))
4507 (home-page "http://bioconductor.org/packages/rtracklayer")
4508 (synopsis "R interface to genome browsers and their annotation tracks")
4509 (description
4510 "rtracklayer is an extensible framework for interacting with multiple
4511genome browsers (currently UCSC built-in) and manipulating annotation tracks
4512in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
4513built-in). The user may export/import tracks to/from the supported browsers,
4514as well as query and modify the browser state, such as the current viewport.")
4515 (license license:artistic2.0)))
4516
2fd7c049
RW		 4517(define-public r-genomicfeatures
4518 (package
4519 (name "r-genomicfeatures")
571f0b63 4520 (version "1.22.13")
2fd7c049
RW		 4521 (source (origin
4522 (method url-fetch)
4523 (uri (bioconductor-uri "GenomicFeatures" version))
4524 (sha256
4525 (base32
571f0b63 4526 "0n3rkj66la6wizgcsf2rmwcsyfxz9kv5zak337lmk1raqfnancz4"))))
2fd7c049
RW		 4527 (properties
4528 `((upstream-name . "GenomicFeatures")))
4529 (build-system r-build-system)
4530 (propagated-inputs
4531 `(("r-annotationdbi" ,r-annotationdbi)
4532 ("r-biobase" ,r-biobase)
4533 ("r-biocgenerics" ,r-biocgenerics)
4534 ("r-biomart" ,r-biomart)
4535 ("r-biostrings" ,r-biostrings)
4536 ("r-dbi" ,r-dbi)
4537 ("r-genomeinfodb" ,r-genomeinfodb)
4538 ("r-genomicranges" ,r-genomicranges)
4539 ("r-iranges" ,r-iranges)
4540 ("r-rcurl" ,r-rcurl)
4541 ("r-rsqlite" ,r-rsqlite)
4542 ("r-rtracklayer" ,r-rtracklayer)
4543 ("r-s4vectors" ,r-s4vectors)
4544 ("r-xvector" ,r-xvector)))
4545 (home-page "http://bioconductor.org/packages/GenomicFeatures")
4546 (synopsis "Tools for working with transcript centric annotations")
4547 (description
4548 "This package provides a set of tools and methods for making and
4549manipulating transcript centric annotations. With these tools the user can
4550easily download the genomic locations of the transcripts, exons and cds of a
4551given organism, from either the UCSC Genome Browser or a BioMart
4552database (more sources will be supported in the future). This information is
4553then stored in a local database that keeps track of the relationship between
4554transcripts, exons, cds and genes. Flexible methods are provided for
4555extracting the desired features in a convenient format.")
4556 (license license:artistic2.0)))
4557
fb25d880
RW		 4558(define-public r-go-db
4559 (package
4560 (name "r-go-db")
4561 (version "3.2.2")
4562 (source (origin
4563 (method url-fetch)
f82c8c3c
PP		 4564 (uri (string-append "http://www.bioconductor.org/packages/"
4565 "release/data/annotation/src/contrib/GO.db_"
4566 version ".tar.gz"))
fb25d880
RW		 4567 (sha256
4568 (base32
4569 "00gariag9ampz82dh0xllrc26r85d7vdcwc0vca5zdy147rwxr7f"))))
4570 (properties
4571 `((upstream-name . "GO.db")))
4572 (build-system r-build-system)
3141b83d
RW		 4573 (propagated-inputs
4574 `(("r-annotationdbi" ,r-annotationdbi)))
fb25d880
RW		 4575 (home-page "http://bioconductor.org/packages/GO.db")
4576 (synopsis "Annotation maps describing the entire Gene Ontology")
4577 (description
4578 "The purpose of this GO.db annotation package is to provide detailed
4579information about the latest version of the Gene Ontologies.")
4580 (license license:artistic2.0)))
4581
d1dbde6a
RW		 4582(define-public r-graph
4583 (package
4584 (name "r-graph")
4585 (version "1.48.0")
4586 (source (origin
4587 (method url-fetch)
4588 (uri (bioconductor-uri "graph" version))
4589 (sha256
4590 (base32
4591 "16w75rji3kv24gfv44w66y1a2y75ax26rl470y3ypna0ndc3rrcd"))))
4592 (build-system r-build-system)
4593 (propagated-inputs
4594 `(("r-biocgenerics" ,r-biocgenerics)))
4595 (home-page "http://bioconductor.org/packages/graph")
4596 (synopsis "Handle graph data structures in R")
4597 (description
4598 "This package implements some simple graph handling capabilities for R.")
4599 (license license:artistic2.0)))
4600
d547ce5e
RW		 4601(define-public r-topgo
4602 (package
4603 (name "r-topgo")
4604 (version "2.22.0")
4605 (source (origin
4606 (method url-fetch)
4607 (uri (bioconductor-uri "topGO" version))
4608 (sha256
4609 (base32
4610 "029j9nb39b8l9xlzsp83pmjr8ap247aia387yzaa1yyw8klapdaf"))))
4611 (properties
4612 `((upstream-name . "topGO")))
4613 (build-system r-build-system)
4614 (propagated-inputs
4615 `(("r-annotationdbi" ,r-annotationdbi)
4616 ("r-biobase" ,r-biobase)
4617 ("r-biocgenerics" ,r-biocgenerics)
4618 ("r-go-db" ,r-go-db)
6d415db2 4619 ("r-graph" ,r-graph)
d547ce5e
RW		 4620 ("r-sparsem" ,r-sparsem)))
4621 (home-page "http://bioconductor.org/packages/topGO")
4622 (synopsis "Enrichment analysis for gene ontology")
4623 (description
4624 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
4625terms while accounting for the topology of the GO graph. Different test
4626statistics and different methods for eliminating local similarities and
4627dependencies between GO terms can be implemented and applied.")
4628 ;; Any version of the LGPL applies.
4629 (license license:lgpl2.1+)))
4630
c63cef66
RW		 4631(define-public r-bsgenome
4632 (package
4633 (name "r-bsgenome")
4634 (version "1.38.0")
4635 (source (origin
4636 (method url-fetch)
4637 (uri (bioconductor-uri "BSgenome" version))
4638 (sha256
4639 (base32
4640 "130w0m6q8kkca7gyz1aqj5jjhalwvwi6rk2yvbjrnj4gpnncyrd2"))))
4641 (properties
4642 `((upstream-name . "BSgenome")))
4643 (build-system r-build-system)
4644 (propagated-inputs
4645 `(("r-biocgenerics" ,r-biocgenerics)
4646 ("r-biostrings" ,r-biostrings)
4647 ("r-genomeinfodb" ,r-genomeinfodb)
4648 ("r-genomicranges" ,r-genomicranges)
4649 ("r-iranges" ,r-iranges)
4650 ("r-rsamtools" ,r-rsamtools)
4651 ("r-rtracklayer" ,r-rtracklayer)
4652 ("r-s4vectors" ,r-s4vectors)
4653 ("r-xvector" ,r-xvector)))
4654 (home-page "http://bioconductor.org/packages/BSgenome")
4655 (synopsis "Infrastructure for Biostrings-based genome data packages")
4656 (description
4657 "This package provides infrastructure shared by all Biostrings-based
4658genome data packages and support for efficient SNP representation.")
4659 (license license:artistic2.0)))
4660
c43a011d
RW		 4661(define-public r-impute
4662 (package
4663 (name "r-impute")
4664 (version "1.44.0")
4665 (source (origin
4666 (method url-fetch)
4667 (uri (bioconductor-uri "impute" version))
4668 (sha256
4669 (base32
4670 "0y4x5jk7gsf4xn56jrkdcdnxpcfll4h6ivncd7n4snmzixldvmvw"))))
4671 (inputs
4672 `(("gfortran" ,gfortran)))
4673 (build-system r-build-system)
4674 (home-page "http://bioconductor.org/packages/impute")
4675 (synopsis "Imputation for microarray data")
4676 (description
4677 "This package provides a function to impute missing gene expression
4678microarray data, using nearest neighbor averaging.")
4679 (license license:gpl2+)))
4680
03ea5a35
RW		 4681(define-public r-seqpattern
4682 (package
4683 (name "r-seqpattern")
4684 (version "1.2.0")
4685 (source (origin
4686 (method url-fetch)
4687 (uri (bioconductor-uri "seqPattern" version))
4688 (sha256
4689 (base32
4690 "0p9zj6bic7sa0hb2bjm988kkk5n9r1kvlbqkzvy702f642n0j53i"))))
4691 (properties
4692 `((upstream-name . "seqPattern")))
4693 (build-system r-build-system)
4694 (propagated-inputs
4695 `(("r-biostrings" ,r-biostrings)
4696 ("r-genomicranges" ,r-genomicranges)
4697 ("r-iranges" ,r-iranges)
4698 ("r-plotrix" ,r-plotrix)))
4699 (home-page "http://bioconductor.org/packages/seqPattern")
4700 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
4701 (description
4702 "This package provides tools to visualize oligonucleotide patterns and
4703sequence motif occurrences across a large set of sequences centred at a common
4704reference point and sorted by a user defined feature.")
4705 (license license:gpl3+)))
4706
cb933df6
RW		 4707(define-public r-genomation
4708 (package
4709 (name "r-genomation")
f315f4fc 4710 (version "1.2.2")
cb933df6
RW		 4711 (source (origin
4712 (method url-fetch)
4713 (uri (bioconductor-uri "genomation" version))
4714 (sha256
4715 (base32
f315f4fc 4716 "0kvzwc21zsh2c8d34yn935ncn38bfkpzmknycd8h7b0521x20mi9"))))
cb933df6
RW		 4717 (build-system r-build-system)
4718 (propagated-inputs
4719 `(("r-biostrings" ,r-biostrings)
4720 ("r-bsgenome" ,r-bsgenome)
4721 ("r-data-table" ,r-data-table)
4722 ("r-genomeinfodb" ,r-genomeinfodb)
4723 ("r-genomicalignments" ,r-genomicalignments)
4724 ("r-genomicranges" ,r-genomicranges)
4725 ("r-ggplot2" ,r-ggplot2)
4726 ("r-gridbase" ,r-gridbase)
4727 ("r-impute" ,r-impute)
4728 ("r-iranges" ,r-iranges)
4729 ("r-matrixstats" ,r-matrixstats)
4730 ("r-plotrix" ,r-plotrix)
4731 ("r-plyr" ,r-plyr)
4732 ("r-readr" ,r-readr)
4733 ("r-reshape2" ,r-reshape2)
4734 ("r-rsamtools" ,r-rsamtools)
4735 ("r-rtracklayer" ,r-rtracklayer)
4736 ("r-seqpattern" ,r-seqpattern)))
4737 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
4738 (synopsis "Summary, annotation and visualization of genomic data")
4739 (description
4740 "This package provides a package for summary and annotation of genomic
4741intervals. Users can visualize and quantify genomic intervals over
4742pre-defined functional regions, such as promoters, exons, introns, etc. The
4743genomic intervals represent regions with a defined chromosome position, which
4744may be associated with a score, such as aligned reads from HT-seq experiments,
4745TF binding sites, methylation scores, etc. The package can use any tabular
4746genomic feature data as long as it has minimal information on the locations of
4747genomic intervals. In addition, it can use BAM or BigWig files as input.")
4748 (license license:artistic2.0)))
4749
486da491
RW		 4750(define-public r-org-hs-eg-db
4751 (package
4752 (name "r-org-hs-eg-db")
4753 (version "3.2.3")
4754 (source (origin
4755 (method url-fetch)
4756 ;; We cannot use bioconductor-uri here because this tarball is
4757 ;; located under "data/annotation/" instead of "bioc/".
4758 (uri (string-append "http://www.bioconductor.org/packages/"
4759 "release/data/annotation/src/contrib/"
4760 "org.Hs.eg.db_" version ".tar.gz"))
4761 (sha256
4762 (base32
4763 "0xicgkbh6xkvs74s1piafqac63dyz2ycdyil4pj4ghhxx2sabm6p"))))
4764 (properties
4765 `((upstream-name . "org.Hs.eg.db")))
4766 (build-system r-build-system)
4767 (propagated-inputs
4768 `(("r-annotationdbi" ,r-annotationdbi)))
4769 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
4770 (synopsis "Genome wide annotation for Human")
4771 (description
4772 "This package provides mappings from Entrez gene identifiers to various
4773annotations for the human genome.")
4774 (license license:artistic2.0)))
4775
fefedf98
RW		 4776(define-public r-org-ce-eg-db
4777 (package
4778 (name "r-org-ce-eg-db")
4779 (version "3.2.3")
4780 (source (origin
4781 (method url-fetch)
4782 ;; We cannot use bioconductor-uri here because this tarball is
4783 ;; located under "data/annotation/" instead of "bioc/".
4784 (uri (string-append "http://www.bioconductor.org/packages/"
4785 "release/data/annotation/src/contrib/"
4786 "org.Ce.eg.db_" version ".tar.gz"))
4787 (sha256
4788 (base32
4789 "1d0lx00ybq34yqs6mziaa0lrh77xm0ggsmi76g6k95f77gi7m1sw"))))
4790 (properties
4791 `((upstream-name . "org.Ce.eg.db")))
4792 (build-system r-build-system)
4793 (propagated-inputs
4794 `(("r-annotationdbi" ,r-annotationdbi)))
4795 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
4796 (synopsis "Genome wide annotation for Worm")
4797 (description
4798 "This package provides mappings from Entrez gene identifiers to various
4799annotations for the genome of the model worm Caenorhabditis elegans.")
4800 (license license:artistic2.0)))
4801
16c53a1e
RW		 4802(define-public r-org-dm-eg-db
4803 (package
4804 (name "r-org-dm-eg-db")
4805 (version "3.2.3")
4806 (source (origin
4807 (method url-fetch)
4808 ;; We cannot use bioconductor-uri here because this tarball is
4809 ;; located under "data/annotation/" instead of "bioc/".
4810 (uri (string-append "http://www.bioconductor.org/packages/"
4811 "release/data/annotation/src/contrib/"
4812 "org.Dm.eg.db_" version ".tar.gz"))
4813 (sha256
4814 (base32
4815 "0mib46c7nr00l7mh290n383za9hyl91a1dc6jhjbk884jmxaxyz6"))))
4816 (properties
4817 `((upstream-name . "org.Dm.eg.db")))
4818 (build-system r-build-system)
4819 (propagated-inputs
4820 `(("r-annotationdbi" ,r-annotationdbi)))
4821 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
4822 (synopsis "Genome wide annotation for Fly")
4823 (description
4824 "This package provides mappings from Entrez gene identifiers to various
4825annotations for the genome of the model fruit fly Drosophila melanogaster.")
4826 (license license:artistic2.0)))
4827
e761beb9
RW		 4828(define-public r-org-mm-eg-db
4829 (package
4830 (name "r-org-mm-eg-db")
4831 (version "3.2.3")
4832 (source (origin
4833 (method url-fetch)
4834 ;; We cannot use bioconductor-uri here because this tarball is
4835 ;; located under "data/annotation/" instead of "bioc/".
4836 (uri (string-append "http://www.bioconductor.org/packages/"
4837 "release/data/annotation/src/contrib/"
4838 "org.Mm.eg.db_" version ".tar.gz"))
4839 (sha256
4840 (base32
4841 "0wh1pm3npdg7070875kfgiid3bqkz3q7rq6snhk6bxfvph00298y"))))
4842 (properties
4843 `((upstream-name . "org.Mm.eg.db")))
4844 (build-system r-build-system)
4845 (propagated-inputs
4846 `(("r-annotationdbi" ,r-annotationdbi)))
4847 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
4848 (synopsis "Genome wide annotation for Mouse")
4849 (description
4850 "This package provides mappings from Entrez gene identifiers to various
4851annotations for the genome of the model mouse Mus musculus.")
4852 (license license:artistic2.0)))
4853
936e7d67
RW		 4854(define-public r-seqlogo
4855 (package
4856 (name "r-seqlogo")
4857 (version "1.36.0")
4858 (source
4859 (origin
4860 (method url-fetch)
4861 (uri (bioconductor-uri "seqLogo" version))
4862 (sha256
4863 (base32
4864 "0kn1a1nf2j4v9c09vjkz9bmxlln7yhg87bnyrdsxy1m55x56rn5k"))))
4865 (properties `((upstream-name . "seqLogo")))
4866 (build-system r-build-system)
4867 (home-page "http://bioconductor.org/packages/seqLogo")
4868 (synopsis "Sequence logos for DNA sequence alignments")
4869 (description
4870 "seqLogo takes the position weight matrix of a DNA sequence motif and
4871plots the corresponding sequence logo as introduced by Schneider and
4872Stephens (1990).")
4873 (license license:lgpl2.0+)))
4874
c90a4baf
RW		 4875(define-public r-bsgenome-hsapiens-ucsc-hg19
4876 (package
4877 (name "r-bsgenome-hsapiens-ucsc-hg19")
4878 (version "1.4.0")
4879 (source (origin
4880 (method url-fetch)
4881 ;; We cannot use bioconductor-uri here because this tarball is
4882 ;; located under "data/annotation/" instead of "bioc/".
4883 (uri (string-append "http://www.bioconductor.org/packages/"
4884 "release/data/annotation/src/contrib/"
4885 "BSgenome.Hsapiens.UCSC.hg19_"
4886 version ".tar.gz"))
4887 (sha256
4888 (base32
4889 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
4890 (properties
4891 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
4892 (build-system r-build-system)
4893 ;; As this package provides little more than a very large data file it
4894 ;; doesn't make sense to build substitutes.
4895 (arguments `(#:substitutable? #f))
4896 (propagated-inputs
4897 `(("r-bsgenome" ,r-bsgenome)))
4898 (home-page
4899 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
4900 (synopsis "Full genome sequences for Homo sapiens")
4901 (description
4902 "This package provides full genome sequences for Homo sapiens as provided
4903by UCSC (hg19, February 2009) and stored in Biostrings objects.")
4904 (license license:artistic2.0)))
4905
a3e90287
RW		 4906(define-public r-bsgenome-mmusculus-ucsc-mm9
4907 (package
4908 (name "r-bsgenome-mmusculus-ucsc-mm9")
4909 (version "1.4.0")
4910 (source (origin
4911 (method url-fetch)
4912 ;; We cannot use bioconductor-uri here because this tarball is
4913 ;; located under "data/annotation/" instead of "bioc/".
4914 (uri (string-append "http://www.bioconductor.org/packages/"
4915 "release/data/annotation/src/contrib/"
4916 "BSgenome.Mmusculus.UCSC.mm9_"
4917 version ".tar.gz"))
4918 (sha256
4919 (base32
4920 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
4921 (properties
4922 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
4923 (build-system r-build-system)
4924 ;; As this package provides little more than a very large data file it
4925 ;; doesn't make sense to build substitutes.
4926 (arguments `(#:substitutable? #f))
4927 (propagated-inputs
4928 `(("r-bsgenome" ,r-bsgenome)))
4929 (home-page
4930 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
4931 (synopsis "Full genome sequences for Mouse")
4932 (description
4933 "This package provides full genome sequences for Mus musculus (Mouse) as
4934provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
4935 (license license:artistic2.0)))
4936
943bd627
RW		 4937(define-public r-bsgenome-celegans-ucsc-ce6
4938 (package
4939 (name "r-bsgenome-celegans-ucsc-ce6")
4940 (version "1.4.0")
4941 (source (origin
4942 (method url-fetch)
4943 ;; We cannot use bioconductor-uri here because this tarball is
4944 ;; located under "data/annotation/" instead of "bioc/".
4945 (uri (string-append "http://www.bioconductor.org/packages/"
4946 "release/data/annotation/src/contrib/"
4947 "BSgenome.Celegans.UCSC.ce6_"
4948 version ".tar.gz"))
4949 (sha256
4950 (base32
4951 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
4952 (properties
4953 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
4954 (build-system r-build-system)
4955 ;; As this package provides little more than a very large data file it
4956 ;; doesn't make sense to build substitutes.
4957 (arguments `(#:substitutable? #f))
4958 (propagated-inputs
4959 `(("r-bsgenome" ,r-bsgenome)))
4960 (home-page
4961 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
4962 (synopsis "Full genome sequences for Worm")
4963 (description
4964 "This package provides full genome sequences for Caenorhabditis
4965elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
4966objects.")
4967 (license license:artistic2.0)))
4968
6dc60998
RW		 4969(define-public r-bsgenome-dmelanogaster-ucsc-dm3
4970 (package
4971 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
4972 (version "1.4.0")
4973 (source (origin
4974 (method url-fetch)
4975 ;; We cannot use bioconductor-uri here because this tarball is
4976 ;; located under "data/annotation/" instead of "bioc/".
4977 (uri (string-append "http://www.bioconductor.org/packages/"
4978 "release/data/annotation/src/contrib/"
4979 "BSgenome.Dmelanogaster.UCSC.dm3_"
4980 version ".tar.gz"))
4981 (sha256
4982 (base32
4983 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
4984 (properties
4985 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
4986 (build-system r-build-system)
4987 ;; As this package provides little more than a very large data file it
4988 ;; doesn't make sense to build substitutes.
4989 (arguments `(#:substitutable? #f))
4990 (propagated-inputs
4991 `(("r-bsgenome" ,r-bsgenome)))
4992 (home-page
4993 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
4994 (synopsis "Full genome sequences for Fly")
4995 (description
4996 "This package provides full genome sequences for Drosophila
4997melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
4998Biostrings objects.")
4999 (license license:artistic2.0)))
5000
ae2462f7
RW		 5001(define-public r-motifrg
5002 (package
5003 (name "r-motifrg")
5004 (version "1.14.0")
5005 (source
5006 (origin
5007 (method url-fetch)
5008 (uri (bioconductor-uri "motifRG" version))
5009 (sha256
5010 (base32
5011 "1v9zm5629k2lcqbbgw8bwflvbircyxkfavbkvmbd212kgwcng8vn"))))
5012 (properties `((upstream-name . "motifRG")))
5013 (build-system r-build-system)
5014 (propagated-inputs
5015 `(("r-biostrings" ,r-biostrings)
5016 ("r-bsgenome" ,r-bsgenome)
5017 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
5018 ("r-iranges" ,r-iranges)
5019 ("r-seqlogo" ,r-seqlogo)
5020 ("r-xvector" ,r-xvector)))
5021 (home-page "http://bioconductor.org/packages/motifRG")
5022 (synopsis "Discover motifs in high throughput sequencing data")
5023 (description
5024 "This package provides tools for discriminative motif discovery in high
5025throughput genetic sequencing data sets using regression methods.")
5026 (license license:artistic2.0)))
5027
a5002ae7
AE		 5028(define-public r-qtl
5029 (package
5030 (name "r-qtl")
e1c2ad67 5031 (version "1.39-5")
a5002ae7
AE		 5032 (source
5033 (origin
5034 (method url-fetch)
5035 (uri (string-append "mirror://cran/src/contrib/qtl_"
5036 version ".tar.gz"))
5037 (sha256
5038 (base32
e1c2ad67 5039 "1grwgvyv7x0dgay1858bg7qf4wk47gpnq7qkqpcda9cn0h970d6f"))))
a5002ae7
AE		 5040 (build-system r-build-system)
5041 (home-page "http://rqtl.org/")
5042 (synopsis "R package for analyzing QTL experiments in genetics")
5043 (description "R/qtl is an extension library for the R statistics
5044system. It is used to analyze experimental crosses for identifying
5045genes contributing to variation in quantitative traits (so-called
5046quantitative trait loci, QTLs).
5047
5048Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
5049identify genotyping errors, and to perform single-QTL and two-QTL,
5050two-dimensional genome scans.")
5051 (license license:gpl3)))
d1e32822 5052
9e3ba31c
RJ		 5053(define-public r-zlibbioc
5054 (package
5055 (name "r-zlibbioc")
5056 (version "1.16.0")
5057 (source (origin
5058 (method url-fetch)
5059 (uri (bioconductor-uri "zlibbioc" version))
5060 (sha256
5061 (base32
5062 "01wc26ndg4jsn1wyrl6zzq636gxaip5fci0xapym4lh9wryc4wnw"))))
5063 (properties
5064 `((upstream-name . "zlibbioc")))
5065 (build-system r-build-system)
5066 (home-page "https://bioconductor.org/packages/zlibbioc")
5067 (synopsis "Provider for zlib-1.2.5 to R packages")
5068 (description "This package uses the source code of zlib-1.2.5 to create
5069libraries for systems that do not have these available via other means.")
5070 (license license:artistic2.0)))
5071
d1e32822
RW		 5072(define-public pepr
5073 (package
5074 (name "pepr")
5075 (version "1.0.9")
5076 (source (origin
5077 (method url-fetch)
5078 (uri (string-append "https://pypi.python.org/packages/source/P"
5079 "/PePr/PePr-" version ".tar.gz"))
5080 (sha256
5081 (base32
5082 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
5083 (build-system python-build-system)
5084 (arguments
5085 `(#:python ,python-2 ; python2 only
5086 #:tests? #f ; no tests included
5087 #:phases
5088 (modify-phases %standard-phases
5089 ;; When setuptools is used a ".egg" archive is generated and
5090 ;; installed. This makes it hard to actually run PePr. This issue
5091 ;; has been reported upstream:
5092 ;; https://github.com/shawnzhangyx/PePr/issues/9
5093 (add-after 'unpack 'disable-egg-generation
5094 (lambda _
5095 (substitute* "setup.py"
5096 (("from setuptools import setup")
5097 "from distutils.core import setup"))
5098 #t)))))
5099 (propagated-inputs
5100 `(("python2-numpy" ,python2-numpy)
5101 ("python2-scipy" ,python2-scipy)
5102 ("python2-pysam" ,python2-pysam)))
5103 (home-page "https://code.google.com/p/pepr-chip-seq/")
5104 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
5105 (description
5106 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
5107that is primarily designed for data with biological replicates. It uses a
5108negative binomial distribution to model the read counts among the samples in
5109the same group, and look for consistent differences between ChIP and control
5110group or two ChIP groups run under different conditions.")
5111 (license license:gpl3+)))
6b49a37e
RJ		 5112
5113(define-public filevercmp
5114 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
5115 (package
5116 (name "filevercmp")
5117 (version (string-append "0-1." (string-take commit 7)))
5118 (source (origin
5119 (method url-fetch)
5120 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
5121 commit ".tar.gz"))
5122 (file-name (string-append name "-" version ".tar.gz"))
5123 (sha256
5124 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
5125 (build-system gnu-build-system)
5126 (arguments
5127 `(#:tests? #f ; There are no tests to run.
5128 #:phases
5129 (modify-phases %standard-phases
5130 (delete 'configure) ; There is no configure phase.
5131 (replace 'install
5132 (lambda* (#:key outputs #:allow-other-keys)
5133 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
5134 (install-file "filevercmp" bin)))))))
5135 (home-page "https://github.com/ekg/filevercmp")
5136 (synopsis "This program compares version strings")
5137 (description "This program compares version strings. It intends to be a
5138replacement for strverscmp.")
5139 (license license:gpl3+))))
jackhill's copy of GNU Guix: https://guix.gnu.org/