Newer
Older
;;; Copyright © 2014, 2015 Ricardo Wurmus <rekado@elephly.net>
;;; Copyright © 2015 Ben Woodcroft <donttrustben@gmail.com>
;;;
;;; This file is part of GNU Guix.
;;;
;;; GNU Guix is free software; you can redistribute it and/or modify it
;;; under the terms of the GNU General Public License as published by
;;; the Free Software Foundation; either version 3 of the License, or (at
;;; your option) any later version.
;;;
;;; GNU Guix is distributed in the hope that it will be useful, but
;;; WITHOUT ANY WARRANTY; without even the implied warranty of
;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
;;; GNU General Public License for more details.
;;;
;;; You should have received a copy of the GNU General Public License
;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
(define-module (gnu packages bioinformatics)
#:use-module ((guix licenses) #:prefix license:)
#:use-module (guix packages)
#:use-module (gnu packages ncurses)
#:use-module (gnu packages perl)
#:use-module (gnu packages pkg-config)
#:use-module (gnu packages zip)
#:use-module (srfi srfi-1))
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
(define-public aragorn
(package
(name "aragorn")
(version "1.2.36")
(source (origin
(method url-fetch)
(uri (string-append
"http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
version ".tgz"))
(sha256
(base32
"1dg7jlz1qpqy88igjxd6ncs11ccsirb36qv1z01a0np4i4jh61mb"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ; there are no tests
#:phases
(modify-phases %standard-phases
(delete 'configure)
(replace 'build
(lambda _
(zero? (system* "gcc"
"-O3"
"-ffast-math"
"-finline-functions"
"-o"
"aragorn"
(string-append "aragorn" ,version ".c")))))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin"))
(man (string-append out "/share/man/man1")))
(mkdir-p bin)
(copy-file "aragorn"
(string-append bin "/aragorn"))
(mkdir-p man)
(copy-file "aragorn.1"
(string-append man "/aragorn.1")))
#t)))))
(home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
(synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
(description
"Aragorn identifies transfer RNA, mitochondrial RNA and
transfer-messenger RNA from nucleotide sequences, based on homology to known
tRNA consensus sequences and RNA structure. It also outputs the secondary
structure of the predicted RNA.")
(license license:gpl2)))
(define-public bamtools
(package
(name "bamtools")
(version "2.3.0")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/pezmaster31/bamtools/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1brry29bw2xr2l9pqn240rkqwayg85b8qq78zk2zs6nlspk4d018"))))
(build-system cmake-build-system)
(arguments
`(#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
(add-before
'configure 'set-ldflags
(lambda* (#:key outputs #:allow-other-keys)
(setenv "LDFLAGS"
(string-append
"-Wl,-rpath="
(assoc-ref outputs "out") "/lib/bamtools")))))))
(inputs `(("zlib" ,zlib)))
(home-page "https://github.com/pezmaster31/bamtools")
(synopsis "C++ API and command-line toolkit for working with BAM data")
(description
"BamTools provides both a C++ API and a command-line toolkit for handling
BAM files.")
(license license:expat)))
(define-public bedops
(package
(name "bedops")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/bedops/bedops/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
"1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
(build-system gnu-build-system)
(arguments
'(#:tests? #f
#:make-flags (list (string-append "BINDIR=" %output "/bin"))
#:phases
(alist-cons-after
'unpack 'unpack-tarballs
(lambda _
;; FIXME: Bedops includes tarballs of minimally patched upstream
;; libraries jansson, zlib, and bzip2. We cannot just use stock
;; libraries because at least one of the libraries (zlib) is
;; patched to add a C++ function definition (deflateInit2cpp).
;; Until the Bedops developers offer a way to link against system
;; libraries we have to build the in-tree copies of these three
;; libraries.
;; See upstream discussion:
;; https://github.com/bedops/bedops/issues/124
;; Unpack the tarballs to benefit from shebang patching.
(with-directory-excursion "third-party"
(and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
(zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
(zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
;; Disable unpacking of tarballs in Makefile.
(substitute* "system.mk/Makefile.linux"
(("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
(("\\./configure") "CONFIG_SHELL=bash ./configure"))
(substitute* "third-party/zlib-1.2.7/Makefile.in"
(("^SHELL=.*$") "SHELL=bash\n")))
(alist-delete 'configure %standard-phases))))
(home-page "https://github.com/bedops/bedops")
(synopsis "Tools for high-performance genomic feature operations")
(description
"BEDOPS is a suite of tools to address common questions raised in genomic
studies---mostly with regard to overlap and proximity relationships between
data sets. It aims to be scalable and flexible, facilitating the efficient
and accurate analysis and management of large-scale genomic data.
BEDOPS provides tools that perform highly efficient and scalable Boolean and
other set operations, statistical calculations, archiving, conversion and
other management of genomic data of arbitrary scale. Tasks can be easily
split by chromosome for distributing whole-genome analyses across a
computational cluster.")
(license license:gpl2+)))
(define-public bedtools
(package
(name "bedtools")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
"0lnxrjvs3nnmb4bmskag1wg3h2hd80przz5q3xd0bvs7vyxrvpbl"))
(patches (list (search-patch "bedtools-32bit-compilation.patch")))))
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
(build-system gnu-build-system)
(native-inputs `(("python" ,python-2)))
(inputs `(("samtools" ,samtools)
("zlib" ,zlib)))
(arguments
'(#:test-target "test"
#:phases
(alist-cons-after
'unpack 'patch-makefile-SHELL-definition
(lambda _
;; patch-makefile-SHELL cannot be used here as it does not
;; yet patch definitions with `:='. Since changes to
;; patch-makefile-SHELL result in a full rebuild, features
;; of patch-makefile-SHELL are reimplemented here.
(substitute* "Makefile"
(("^SHELL := .*$") (string-append "SHELL := " (which "bash") " -e \n"))))
(alist-delete
'configure
(alist-replace
'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
(mkdir-p bin)
(for-each (lambda (file)
(copy-file file (string-append bin (basename file))))
(find-files "bin" ".*"))))
%standard-phases)))))
(home-page "https://github.com/arq5x/bedtools2")
(synopsis "Tools for genome analysis and arithmetic")
(description
"Collectively, the bedtools utilities are a swiss-army knife of tools for
a wide-range of genomics analysis tasks. The most widely-used tools enable
genome arithmetic: that is, set theory on the genome. For example, bedtools
allows one to intersect, merge, count, complement, and shuffle genomic
intervals from multiple files in widely-used genomic file formats such as BAM,
BED, GFF/GTF, VCF.")
(license license:gpl2)))
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
(define-public python2-pybedtools
(package
(name "python2-pybedtools")
(version "0.6.9")
(source (origin
(method url-fetch)
(uri (string-append
"https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
version ".tar.gz"))
(sha256
(base32
"1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
(build-system python-build-system)
(arguments `(#:python ,python-2)) ; no Python 3 support
(inputs
`(("python-cython" ,python2-cython)
("python-matplotlib" ,python2-matplotlib)))
(propagated-inputs
`(("bedtools" ,bedtools)
("samtools" ,samtools)))
(native-inputs
`(("python-pyyaml" ,python2-pyyaml)
("python-nose" ,python2-nose)
("python-setuptools" ,python2-setuptools)))
(home-page "https://pythonhosted.org/pybedtools/")
(synopsis "Python wrapper for BEDtools programs")
(description
"pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
which are widely used for genomic interval manipulation or \"genome algebra\".
pybedtools extends BEDTools by offering feature-level manipulations from with
Python.")
(license license:gpl2+)))
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
(define-public bioperl-minimal
(let* ((inputs `(("perl-module-build" ,perl-module-build)
("perl-data-stag" ,perl-data-stag)
("perl-libwww" ,perl-libwww)
("perl-uri" ,perl-uri)))
(transitive-inputs
(map (compose package-name cadr)
(delete-duplicates
(concatenate
(map (compose package-transitive-target-inputs cadr) inputs))))))
(package
(name "bioperl-minimal")
(version "1.6.924")
(source
(origin
(method url-fetch)
(uri (string-append "mirror://cpan/authors/id/C/CJ/CJFIELDS/BioPerl-"
version ".tar.gz"))
(sha256
(base32
"1l3npcvvvwjlhkna9dndpfv1hklhrgva013kw96m0n1wpd37ask1"))))
(build-system perl-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after
'install 'wrap-programs
(lambda* (#:key outputs #:allow-other-keys)
;; Make sure all executables in "bin" find the required Perl
;; modules at runtime. As the PERL5LIB variable contains also
;; the paths of native inputs, we pick the transitive target
;; inputs from %build-inputs.
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin/"))
(path (string-join
(cons (string-append out "/lib/perl5/site_perl")
(map (lambda (name)
(assoc-ref %build-inputs name))
',transitive-inputs))
":")))
(for-each (lambda (file)
(wrap-program file
`("PERL5LIB" ":" prefix (,path))))
(find-files bin "\\.pl$"))
#t))))))
(inputs inputs)
(native-inputs
`(("perl-test-most" ,perl-test-most)))
(home-page "http://search.cpan.org/dist/BioPerl")
(synopsis "Bioinformatics toolkit")
(description
"BioPerl is the product of a community effort to produce Perl code which
is useful in biology. Examples include Sequence objects, Alignment objects
and database searching objects. These objects not only do what they are
advertised to do in the documentation, but they also interact - Alignment
objects are made from the Sequence objects, Sequence objects have access to
Annotation and SeqFeature objects and databases, Blast objects can be
converted to Alignment objects, and so on. This means that the objects
provide a coordinated and extensible framework to do computational biology.")
(license (package-license perl)))))
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
(define-public python-biopython
(package
(name "python-biopython")
(version "1.65")
(source (origin
(method url-fetch)
(uri (string-append
"http://biopython.org/DIST/biopython-"
version ".tar.gz"))
(sha256
(base32
"13m8s9jkrw40zvdp1rl709n6lmgdh4f52aann7gzr6sfp0fwhg26"))))
(build-system python-build-system)
(inputs
`(("python-numpy" ,python-numpy)))
(native-inputs
`(("python-setuptools" ,python2-setuptools)))
(home-page "http://biopython.org/")
(synopsis "Tools for biological computation in Python")
(description
"Biopython is a set of tools for biological computation including parsers
for bioinformatics files into Python data structures; interfaces to common
bioinformatics programs; a standard sequence class and tools for performing
common operations on them; code to perform data classification; code for
dealing with alignments; code making it easy to split up parallelizable tasks
into separate processes; and more.")
(license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
(define-public python2-biopython
(package (inherit (package-with-python2 python-biopython))
(inputs
`(("python2-numpy" ,python2-numpy)))))
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
(define-public blast+
(package
(name "blast+")
(version "2.2.31")
(source (origin
(method url-fetch)
(uri (string-append
"ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
version "/ncbi-blast-" version "+-src.tar.gz"))
(sha256
(base32
"19gq6as4k1jrgsd26158ads6h7v4jca3h4r5dzg1y0m6ya50x5ph"))
(modules '((guix build utils)))
(snippet
'(begin
;; Remove bundled bzip2 and zlib
(delete-file-recursively "c++/src/util/compress/bzip2")
(delete-file-recursively "c++/src/util/compress/zlib")
(substitute* "c++/src/util/compress/Makefile.in"
(("bzip2 zlib api") "api"))
;; Remove useless msbuild directory
(delete-file-recursively
"c++/src/build-system/project_tree_builder/msbuild")
#t))))
(build-system gnu-build-system)
(arguments
`(;; There are three(!) tests for this massive library, and all fail with
;; "unparsable timing stats".
;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
#:tests? #f
#:out-of-source? #t
#:parallel-build? #f ; not supported
#:phases
(modify-phases %standard-phases
(add-before
'configure 'set-HOME
;; $HOME needs to be set at some point during the configure phase
(lambda _ (setenv "HOME" "/tmp") #t))
(add-after
'unpack 'enter-dir
(lambda _ (chdir "c++") #t))
(add-after
'enter-dir 'fix-build-system
(lambda _
(define (which* cmd)
(cond ((string=? cmd "date")
;; make call to "date" deterministic
"date -d @0")
((which cmd)
=> identity)
(else
(format (current-error-port)
"WARNING: Unable to find absolute path for ~s~%"
cmd)
#f)))
;; Rewrite hardcoded paths to various tools
(substitute* (append '("src/build-system/configure.ac"
"src/build-system/configure"
"scripts/common/impl/if_diff.sh"
"scripts/common/impl/run_with_lock.sh"
"src/build-system/Makefile.configurables.real"
"src/build-system/Makefile.in.top"
"src/build-system/Makefile.meta.gmake=no"
"src/build-system/Makefile.meta.in"
"src/build-system/Makefile.meta_l"
"src/build-system/Makefile.meta_p"
"src/build-system/Makefile.meta_r"
"src/build-system/Makefile.mk.in"
"src/build-system/Makefile.requirements"
"src/build-system/Makefile.rules_with_autodep.in")
(find-files "scripts/common/check" "\\.sh$"))
(("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
(or (which* cmd) all)))
(substitute* (find-files "src/build-system" "^config.*")
(("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
(("^PATH=.*") ""))
;; rewrite "/var/tmp" in check script
(substitute* "scripts/common/check/check_make_unix.sh"
(("/var/tmp") "/tmp"))
;; do not reset PATH
(substitute* (find-files "scripts/common/impl/" "\\.sh$")
(("^ *PATH=.*") "")
(("action=/bin/") "action=")
(("export PATH") ":"))
#t))
(replace
'configure
(lambda* (#:key inputs outputs #:allow-other-keys)
(let ((out (assoc-ref outputs "out"))
(lib (string-append (assoc-ref outputs "lib") "/lib"))
(include (string-append (assoc-ref outputs "include")
"/include/ncbi-tools++")))
;; The 'configure' script doesn't recognize things like
;; '--enable-fast-install'.
(zero? (system* "./configure.orig"
(string-append "--with-build-root=" (getcwd) "/build")
(string-append "--prefix=" out)
(string-append "--libdir=" lib)
(string-append "--includedir=" include)
(string-append "--with-bz2="
(assoc-ref inputs "bzip2"))
(string-append "--with-z="
(assoc-ref inputs "zlib"))
;; Each library is built twice by default, once
;; with "-static" in its name, and again
;; without.
"--without-static"
"--with-dll"))))))))
(outputs '("out" ; 19 MB
"lib" ; 203 MB
"include")) ; 32 MB
(inputs
`(("bzip2" ,bzip2)
("zlib" ,zlib)))
(native-inputs
`(("cpio" ,cpio)))
(home-page "http://blast.ncbi.nlm.nih.gov")
(synopsis "Basic local alignment search tool")
(description
"BLAST is a popular method of performing a DNA or protein sequence
similarity search, using heuristics to produce results quickly. It also
calculates an “expect value” that estimates how many matches would have
occurred at a given score by chance, which can aid a user in judging how much
confidence to have in an alignment.")
;; Most of the sources are in the public domain, with the following
;; exceptions:
;; * Expat:
;; * ./c++/include/util/bitset/
;; * ./c++/src/html/ncbi_menu*.js
;; * Boost license:
;; * ./c++/include/util/impl/floating_point_comparison.hpp
;; * LGPL 2+:
;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
;; * ASL 2.0:
;; * ./c++/src/corelib/teamcity_*
(license (list license:public-domain
license:expat
license:boost1.0
license:lgpl2.0+
license:asl2.0))))
(define-public bowtie
(package
(name "bowtie")
(version "2.2.4")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"15dnbqippwvhyh9zqjhaxkabk7lm1xbh1nvar1x4b5kwm117zijn"))
(modules '((guix build utils)))
(snippet
'(substitute* "Makefile"
(("^CC = .*$") "CC = gcc")
(("^CPP = .*$") "CPP = g++")
;; replace BUILD_HOST and BUILD_TIME for deterministic build
(("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
(("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))
(patches (list (search-patch "bowtie-fix-makefile.patch")))))
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
(build-system gnu-build-system)
(inputs `(("perl" ,perl)
("perl-clone" ,perl-clone)
("perl-test-deep" ,perl-test-deep)
("perl-test-simple" ,perl-test-simple)
("python" ,python-2)))
(arguments
'(#:make-flags '("allall")
#:phases
(alist-delete
'configure
(alist-replace
'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
(mkdir-p bin)
(for-each (lambda (file)
(copy-file file (string-append bin file)))
(find-files "." "bowtie2.*"))))
(alist-replace
'check
(lambda* (#:key outputs #:allow-other-keys)
(system* "perl"
"scripts/test/simple_tests.pl"
"--bowtie2=./bowtie2"
"--bowtie2-build=./bowtie2-build"))
%standard-phases)))))
(home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
(synopsis "Fast and sensitive nucleotide sequence read aligner")
(description
"Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
reads to long reference sequences. It is particularly good at aligning reads
of about 50 up to 100s or 1,000s of characters, and particularly good at
aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
genome with an FM Index to keep its memory footprint small: for the human
genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
gapped, local, and paired-end alignment modes.")
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
(define-public bwa
(package
(name "bwa")
(version "0.7.12")
(source (origin
(method url-fetch)
(uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
version ".tar.bz2"))
(sha256
(base32
"1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f ;no "check" target
#:phases
(alist-replace
'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append
(assoc-ref outputs "out") "/bin"))
(doc (string-append
(assoc-ref outputs "out") "/share/doc/bwa"))
(man (string-append
(assoc-ref outputs "out") "/share/man/man1")))
(mkdir-p bin)
(mkdir-p doc)
(mkdir-p man)
(copy-file "bwa" (string-append bin "/bwa"))
(copy-file "README.md" (string-append doc "/README.md"))
(copy-file "bwa.1" (string-append man "/bwa.1"))))
;; no "configure" script
(alist-delete 'configure %standard-phases))))
(inputs `(("zlib" ,zlib)))
(home-page "http://bio-bwa.sourceforge.net/")
(synopsis "Burrows-Wheeler sequence aligner")
(description
"BWA is a software package for mapping low-divergent sequences against a
large reference genome, such as the human genome. It consists of three
algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
designed for Illumina sequence reads up to 100bp, while the rest two for
longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
features such as long-read support and split alignment, but BWA-MEM, which is
the latest, is generally recommended for high-quality queries as it is faster
and more accurate. BWA-MEM also has better performance than BWA-backtrack for
70-100bp Illumina reads.")
(license license:gpl3+)))
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
(define-public python2-bx-python
(package
(name "python2-bx-python")
(version "0.7.2")
(source (origin
(method url-fetch)
(uri (string-append
"https://pypi.python.org/packages/source/b/bx-python/bx-python-"
version ".tar.gz"))
(sha256
(base32
"0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
(modules '((guix build utils)))
(snippet
'(substitute* "setup.py"
;; remove dependency on outdated "distribute" module
(("^from distribute_setup import use_setuptools") "")
(("^use_setuptools\\(\\)") "")))))
(build-system python-build-system)
(arguments
`(#:tests? #f ;tests fail because test data are not included
#:python ,python-2))
(inputs
`(("python-numpy" ,python2-numpy)
("zlib" ,zlib)))
(native-inputs
`(("python-nose" ,python2-nose)
("python-setuptools" ,python2-setuptools)))
(home-page "http://bitbucket.org/james_taylor/bx-python/")
(synopsis "Tools for manipulating biological data")
(description
"bx-python provides tools for manipulating biological data, particularly
multiple sequence alignments.")
(license license:expat)))
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
(define-public clipper
(package
(name "clipper")
(version "0.3.0")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/YeoLab/clipper/archive/"
version ".tar.gz"))
(sha256
(base32
"1q7jpimsqln7ic44i8v2rx2haj5wvik8hc1s2syd31zcn0xk1iyq"))
(modules '((guix build utils)))
(snippet
;; remove unnecessary setup dependency
'(substitute* "setup.py"
(("setup_requires = .*") "")))))
(build-system python-build-system)
(arguments `(#:python ,python-2)) ; only Python 2 is supported
(inputs
`(("htseq" ,htseq)
("python-pybedtools" ,python2-pybedtools)
("python-cython" ,python2-cython)
("python-scikit-learn" ,python2-scikit-learn)
("python-matplotlib" ,python2-matplotlib)
("python-pysam" ,python2-pysam)
("python-numpy" ,python2-numpy)
("python-scipy" ,python2-scipy)))
(native-inputs
`(("python-mock" ,python2-mock) ; for tests
("python-pytz" ,python2-pytz) ; for tests
("python-setuptools" ,python2-setuptools)))
(home-page "https://github.com/YeoLab/clipper")
(synopsis "CLIP peak enrichment recognition")
(description
"CLIPper is a tool to define peaks in CLIP-seq datasets.")
(license license:gpl2)))
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
(define-public couger
(package
(name "couger")
(version "1.8.2")
(source (origin
(method url-fetch)
(uri (string-append
"http://couger.oit.duke.edu/static/assets/COUGER"
version ".zip"))
(sha256
(base32
"04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f
#:phases
(modify-phases %standard-phases
(delete 'configure)
(delete 'build)
(replace
'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((out (assoc-ref outputs "out")))
(copy-recursively "src" (string-append out "/src"))
(mkdir (string-append out "/bin"))
;; Add "src" directory to module lookup path.
(substitute* "couger"
(("from argparse")
(string-append "import sys\nsys.path.append(\""
out "\")\nfrom argparse")))
(copy-file "couger" (string-append out "/bin/couger")))
#t))
(add-after
'install 'wrap-program
(lambda* (#:key inputs outputs #:allow-other-keys)
;; Make sure 'couger' runs with the correct PYTHONPATH.
(let* ((out (assoc-ref outputs "out"))
(path (getenv "PYTHONPATH")))
(wrap-program (string-append out "/bin/couger")
`("PYTHONPATH" ":" prefix (,path))))
#t)))))
(inputs
`(("python" ,python-2)
("python2-pillow" ,python2-pillow)
("python2-numpy" ,python2-numpy)
("python2-scipy" ,python2-scipy)
("python2-matplotlib" ,python2-matplotlib)))
(propagated-inputs
`(("r" ,r)
("libsvm" ,libsvm)
("randomjungle" ,randomjungle)))
(native-inputs
`(("unzip" ,unzip)))
(home-page "http://couger.oit.duke.edu")
(synopsis "Identify co-factors in sets of genomic regions")
(description
"COUGER can be applied to any two sets of genomic regions bound by
paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
putative co-factors that provide specificity to each TF. The framework
determines the genomic targets uniquely-bound by each TF, and identifies a
small set of co-factors that best explain the in vivo binding differences
between the two TFs.
COUGER uses classification algorithms (support vector machines and random
forests) with features that reflect the DNA binding specificities of putative
co-factors. The features are generated either from high-throughput TF-DNA
binding data (from protein binding microarray experiments), or from large
collections of DNA motifs.")
(license license:gpl3+)))
(define-public clustal-omega
(package
(name "clustal-omega")
(version "1.2.1")
(source (origin
(method url-fetch)
(uri (string-append
"http://www.clustal.org/omega/clustal-omega-"
version ".tar.gz"))
(sha256
(base32
"02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
(build-system gnu-build-system)
(inputs
`(("argtable" ,argtable)))
(home-page "http://www.clustal.org/omega/")
(synopsis "Multiple sequence aligner for protein and DNA/RNA")
(description
"Clustal-Omega is a general purpose multiple sequence alignment (MSA)
program for protein and DNA/RNA. It produces high quality MSAs and is capable
of handling data-sets of hundreds of thousands of sequences in reasonable
time.")
(license license:gpl2+)))
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
(define-public crossmap
(package
(name "crossmap")
(version "0.1.6")
(source (origin
(method url-fetch)
(uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
version ".tar.gz"))
(sha256
(base32
"163hi5gjgij6cndxlvbkp5jjwr0k4wbm9im6d2210278q7k9kpnp"))
;; patch has been sent upstream already
(patches (list
(search-patch "crossmap-allow-system-pysam.patch")))
(modules '((guix build utils)))
;; remove bundled copy of pysam
(snippet
'(delete-file-recursively "lib/pysam"))))
(build-system python-build-system)
(arguments
`(#:python ,python-2
#:phases
(alist-cons-after
'unpack 'set-env
(lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
%standard-phases)))
(inputs
`(("python-numpy" ,python2-numpy)
("python-pysam" ,python2-pysam)
("zlib" ,zlib)))
(native-inputs
`(("python-cython" ,python2-cython)
("python-nose" ,python2-nose)
("python-setuptools" ,python2-setuptools)))
(home-page "http://crossmap.sourceforge.net/")
(synopsis "Convert genome coordinates between assemblies")
(description
"CrossMap is a program for conversion of genome coordinates or annotation
files between different genome assemblies. It supports most commonly used
file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
(license license:gpl2+)))
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
(define-public cutadapt
(package
(name "cutadapt")
(version "1.8")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/marcelm/cutadapt/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"161bp87y6gd6r5bmvjpn2b1k942i3fizfpa139f0jn6jv1wcp5h5"))))
(build-system python-build-system)
(arguments
;; tests must be run after install
`(#:phases (alist-cons-after
'install 'check
(lambda* (#:key inputs outputs #:allow-other-keys)
(setenv "PYTHONPATH"
(string-append
(getenv "PYTHONPATH")
":" (assoc-ref outputs "out")
"/lib/python"
(string-take (string-take-right
(assoc-ref inputs "python") 5) 3)
"/site-packages"))
(zero? (system* "nosetests" "-P" "tests")))
(alist-delete 'check %standard-phases))))
(native-inputs
`(("python-cython" ,python-cython)
("python-nose" ,python-nose)
("python-setuptools" ,python-setuptools)))
(home-page "https://code.google.com/p/cutadapt/")
(synopsis "Remove adapter sequences from nucleotide sequencing reads")
(description
"Cutadapt finds and removes adapter sequences, primers, poly-A tails and
other types of unwanted sequence from high-throughput sequencing reads.")
(license license:expat)))
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
(define-public diamond
(package
(name "diamond")
(version "0.7.9")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/bbuchfink/diamond/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"0hfkcfv9f76h5brbyw9fyvmc0l9cmbsxrcdqk0fa9xv82zj47p15"))
(snippet '(begin
(delete-file "bin/diamond")
#t))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'enter-source-dir
(lambda _
(chdir "src")
#t))
(delete 'configure)
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out")
"/bin")))
(mkdir-p bin)
(copy-file "../bin/diamond"
(string-append bin "/diamond"))
#t))))))
(native-inputs
`(("bc" ,bc)))
(inputs
`(("boost" ,boost)
("zlib" ,zlib)))
(home-page "https://github.com/bbuchfink/diamond")
(synopsis "Accelerated BLAST compatible local sequence aligner")
(description
"DIAMOND is a BLAST-compatible local aligner for mapping protein and
translated DNA query sequences against a protein reference database (BLASTP
and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
reads at a typical sensitivity of 90-99% relative to BLAST depending on the
data and settings.")
(license (license:non-copyleft "file://src/COPYING"
"See src/COPYING in the distribution."))))
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
(define-public edirect
(package
(name "edirect")
(version "2.50")
(source (origin
(method url-fetch)
;; Note: older versions are not retained.
(uri "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/edirect.zip")
(sha256
(base32
"08afhz2ph66h8h381hl1mqyxkdi5nbvzsyj9gfw3jfbdijnpi4qj"))))
(build-system perl-build-system)
(arguments
`(#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
(delete 'configure)
(delete 'build)
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((target (string-append (assoc-ref outputs "out")
"/bin")))
(mkdir-p target)
(copy-file "edirect.pl"
(string-append target "/edirect.pl"))
#t)))
(add-after
'install 'wrap-program
(lambda* (#:key inputs outputs #:allow-other-keys)
;; Make sure 'edirect.pl' finds all perl inputs at runtime.
(let* ((out (assoc-ref outputs "out"))
(path (getenv "PERL5LIB")))
(wrap-program (string-append out "/bin/edirect.pl")
`("PERL5LIB" ":" prefix (,path)))))))))
(inputs
`(("perl-html-parser" ,perl-html-parser)
("perl-encode-locale" ,perl-encode-locale)
("perl-file-listing" ,perl-file-listing)
("perl-html-tagset" ,perl-html-tagset)
("perl-html-tree" ,perl-html-tree)
("perl-http-cookies" ,perl-http-cookies)
("perl-http-date" ,perl-http-date)
("perl-http-message" ,perl-http-message)
("perl-http-negotiate" ,perl-http-negotiate)
("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
("perl-net-http" ,perl-net-http)
("perl-uri" ,perl-uri)
("perl-www-robotrules" ,perl-www-robotrules)
("perl" ,perl)))
(native-inputs
`(("unzip" ,unzip)))
(home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288")
(synopsis "Tools for accessing the NCBI's set of databases")
(description
"Entrez Direct (EDirect) is a method for accessing the National Center
for Biotechnology Information's (NCBI) set of interconnected
databases (publication, sequence, structure, gene, variation, expression,
etc.) from a terminal. Functions take search terms from command-line
arguments. Individual operations are combined to build multi-step queries.
Record retrieval and formatting normally complete the process.
EDirect also provides an argument-driven function that simplifies the
extraction of data from document summaries or other results that are returned
in structured XML format. This can eliminate the need for writing custom
software to answer ad hoc questions.")
(license license:public-domain)))
(define-public express
(package
(name "express")
(version "1.5.1")
(source (origin