1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016 Efraim Flashner <efraim@flashner.co.il>
9 ;;; This file is part of GNU Guix.
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.
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.
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/>.
24 (define-module (gnu packages bioinformatics)
25 #:use-module ((guix licenses) #:prefix license:)
26 #:use-module (guix packages)
27 #:use-module (guix utils)
28 #:use-module (guix download)
29 #:use-module (guix git-download)
30 #:use-module (guix build-system ant)
31 #:use-module (guix build-system gnu)
32 #:use-module (guix build-system cmake)
33 #:use-module (guix build-system perl)
34 #:use-module (guix build-system python)
35 #:use-module (guix build-system r)
36 #:use-module (guix build-system ruby)
37 #:use-module (guix build-system trivial)
38 #:use-module (gnu packages)
39 #:use-module (gnu packages autotools)
40 #:use-module (gnu packages algebra)
41 #:use-module (gnu packages base)
42 #:use-module (gnu packages bison)
43 #:use-module (gnu packages boost)
44 #:use-module (gnu packages compression)
45 #:use-module (gnu packages cpio)
46 #:use-module (gnu packages curl)
47 #:use-module (gnu packages documentation)
48 #:use-module (gnu packages datastructures)
49 #:use-module (gnu packages file)
50 #:use-module (gnu packages gawk)
51 #:use-module (gnu packages gcc)
52 #:use-module (gnu packages java)
53 #:use-module (gnu packages linux)
54 #:use-module (gnu packages machine-learning)
55 #:use-module (gnu packages maths)
56 #:use-module (gnu packages mpi)
57 #:use-module (gnu packages ncurses)
58 #:use-module (gnu packages pcre)
59 #:use-module (gnu packages perl)
60 #:use-module (gnu packages pkg-config)
61 #:use-module (gnu packages popt)
62 #:use-module (gnu packages protobuf)
63 #:use-module (gnu packages python)
64 #:use-module (gnu packages ruby)
65 #:use-module (gnu packages statistics)
66 #:use-module (gnu packages tbb)
67 #:use-module (gnu packages textutils)
68 #:use-module (gnu packages time)
69 #:use-module (gnu packages tls)
70 #:use-module (gnu packages vim)
71 #:use-module (gnu packages web)
72 #:use-module (gnu packages xml)
73 #:use-module (gnu packages zip)
74 #:use-module (srfi srfi-1))
76 (define-public aragorn
83 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
87 "1dg7jlz1qpqy88igjxd6ncs11ccsirb36qv1z01a0np4i4jh61mb"))))
88 (build-system gnu-build-system)
90 `(#:tests? #f ; there are no tests
92 (modify-phases %standard-phases
102 (string-append "aragorn" ,version ".c")))))
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")))
110 (string-append bin "/aragorn"))
112 (copy-file "aragorn.1"
113 (string-append man "/aragorn.1")))
115 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
116 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
118 "Aragorn identifies transfer RNA, mitochondrial RNA and
119 transfer-messenger RNA from nucleotide sequences, based on homology to known
120 tRNA consensus sequences and RNA structure. It also outputs the secondary
121 structure of the predicted RNA.")
122 (license license:gpl2)))
124 (define-public bamtools
131 "https://github.com/pezmaster31/bamtools/archive/v"
133 (file-name (string-append name "-" version ".tar.gz"))
136 "1brry29bw2xr2l9pqn240rkqwayg85b8qq78zk2zs6nlspk4d018"))))
137 (build-system cmake-build-system)
139 `(#:tests? #f ;no "check" target
141 (modify-phases %standard-phases
143 'configure 'set-ldflags
144 (lambda* (#:key outputs #:allow-other-keys)
148 (assoc-ref outputs "out") "/lib/bamtools")))))))
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")
153 "BamTools provides both a C++ API and a command-line toolkit for handling
155 (license license:expat)))
157 (define-public bedops
163 (uri (string-append "https://github.com/bedops/bedops/archive/v"
165 (file-name (string-append name "-" version ".tar.gz"))
168 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
169 (build-system gnu-build-system)
172 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
175 'unpack 'unpack-tarballs
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
185 ;; See upstream discussion:
186 ;; https://github.com/bedops/bedops/issues/124
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")
203 "BEDOPS is a suite of tools to address common questions raised in genomic
204 studies---mostly with regard to overlap and proximity relationships between
205 data sets. It aims to be scalable and flexible, facilitating the efficient
206 and accurate analysis and management of large-scale genomic data.
208 BEDOPS provides tools that perform highly efficient and scalable Boolean and
209 other set operations, statistical calculations, archiving, conversion and
210 other management of genomic data of arbitrary scale. Tasks can be easily
211 split by chromosome for distributing whole-genome analyses across a
212 computational cluster.")
213 (license license:gpl2+)))
215 (define-public bedtools
221 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
223 (file-name (string-append name "-" version ".tar.gz"))
226 "1ywcy3yfwzhl905b51l0ffjia55h75vv3mw5xkvib04pp6pj548m"))))
227 (build-system gnu-build-system)
228 (native-inputs `(("python" ,python-2)))
229 (inputs `(("samtools" ,samtools)
232 '(#:test-target "test"
234 (modify-phases %standard-phases
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" ".*")))
243 (home-page "https://github.com/arq5x/bedtools2")
244 (synopsis "Tools for genome analysis and arithmetic")
246 "Collectively, the bedtools utilities are a swiss-army knife of tools for
247 a wide-range of genomics analysis tasks. The most widely-used tools enable
248 genome arithmetic: that is, set theory on the genome. For example, bedtools
249 allows one to intersect, merge, count, complement, and shuffle genomic
250 intervals from multiple files in widely-used genomic file formats such as BAM,
252 (license license:gpl2)))
254 (define-public bioawk
260 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
262 (file-name (string-append name "-" version ".tar.gz"))
264 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
265 (build-system gnu-build-system)
271 `(#:tests? #f ; There are no tests to run.
272 ;; Bison must generate files, before other targets can build.
275 (modify-phases %standard-phases
276 (delete 'configure) ; There is no configure phase.
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")))
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
288 support of several common biological data formats, including optionally gzip'ed
289 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
290 also adds a few built-in functions and a command line option to use TAB as the
291 input/output delimiter. When the new functionality is not used, bioawk is
292 intended to behave exactly the same as the original BWK awk.")
293 (license license:x11)))
295 (define-public python2-pybedtools
297 (name "python2-pybedtools")
302 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
306 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
307 (build-system python-build-system)
308 (arguments `(#:python ,python-2)) ; no Python 3 support
310 `(("python-cython" ,python2-cython)
311 ("python-matplotlib" ,python2-matplotlib)))
313 `(("bedtools" ,bedtools)
314 ("samtools" ,samtools)))
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")
322 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
323 which are widely used for genomic interval manipulation or \"genome algebra\".
324 pybedtools extends BEDTools by offering feature-level manipulations from with
326 (license license:gpl2+)))
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)))
334 (map (compose package-name cadr)
337 (map (compose package-transitive-target-inputs cadr) inputs))))))
339 (name "bioperl-minimal")
344 (uri (string-append "mirror://cpan/authors/id/C/CJ/CJFIELDS/BioPerl-"
348 "1l3npcvvvwjlhkna9dndpfv1hklhrgva013kw96m0n1wpd37ask1"))))
349 (build-system perl-build-system)
352 (modify-phases %standard-phases
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/"))
363 (cons (string-append out "/lib/perl5/site_perl")
365 (assoc-ref %build-inputs name))
366 ',transitive-inputs))
368 (for-each (lambda (file)
370 `("PERL5LIB" ":" prefix (,path))))
371 (find-files bin "\\.pl$"))
375 `(("perl-test-most" ,perl-test-most)))
376 (home-page "http://search.cpan.org/dist/BioPerl")
377 (synopsis "Bioinformatics toolkit")
379 "BioPerl is the product of a community effort to produce Perl code which
380 is useful in biology. Examples include Sequence objects, Alignment objects
381 and database searching objects. These objects not only do what they are
382 advertised to do in the documentation, but they also interact - Alignment
383 objects are made from the Sequence objects, Sequence objects have access to
384 Annotation and SeqFeature objects and databases, Blast objects can be
385 converted to Alignment objects, and so on. This means that the objects
386 provide a coordinated and extensible framework to do computational biology.")
387 (license (package-license perl)))))
389 (define-public python-biopython
391 (name "python-biopython")
395 ;; use PyPi rather than biopython.org to ease updating
396 (uri (pypi-uri "biopython" version))
399 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))
400 (build-system python-build-system)
402 `(("python-numpy" ,python-numpy)))
404 `(("python-setuptools" ,python2-setuptools)))
405 (home-page "http://biopython.org/")
406 (synopsis "Tools for biological computation in Python")
408 "Biopython is a set of tools for biological computation including parsers
409 for bioinformatics files into Python data structures; interfaces to common
410 bioinformatics programs; a standard sequence class and tools for performing
411 common operations on them; code to perform data classification; code for
412 dealing with alignments; code making it easy to split up parallelizable tasks
413 into separate processes; and more.")
414 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
416 (define-public python2-biopython
417 (package (inherit (package-with-python2 python-biopython))
419 `(("python2-numpy" ,python2-numpy)))))
421 (define-public blast+
428 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
429 version "/ncbi-blast-" version "+-src.tar.gz"))
432 "19gq6as4k1jrgsd26158ads6h7v4jca3h4r5dzg1y0m6ya50x5ph"))
433 (modules '((guix build utils)))
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")
445 (build-system gnu-build-system)
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)
454 #:parallel-build? #f ; not supported
456 (modify-phases %standard-phases
459 ;; $HOME needs to be set at some point during the configure phase
460 (lambda _ (setenv "HOME" "/tmp") #t))
463 (lambda _ (chdir "c++") #t))
465 'enter-dir 'fix-build-system
468 (cond ((string=? cmd "date")
469 ;; make call to "date" deterministic
474 (format (current-error-port)
475 "WARNING: Unable to find absolute path for ~s~%"
479 ;; Rewrite hardcoded paths to various tools
480 (substitute* (append '("src/build-system/configure.ac"
481 "src/build-system/configure"
482 "scripts/common/impl/if_diff.sh"
483 "scripts/common/impl/run_with_lock.sh"
484 "src/build-system/Makefile.configurables.real"
485 "src/build-system/Makefile.in.top"
486 "src/build-system/Makefile.meta.gmake=no"
487 "src/build-system/Makefile.meta.in"
488 "src/build-system/Makefile.meta_l"
489 "src/build-system/Makefile.meta_p"
490 "src/build-system/Makefile.meta_r"
491 "src/build-system/Makefile.mk.in"
492 "src/build-system/Makefile.requirements"
493 "src/build-system/Makefile.rules_with_autodep.in")
494 (find-files "scripts/common/check" "\\.sh$"))
495 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
496 (or (which* cmd) all)))
498 (substitute* (find-files "src/build-system" "^config.*")
499 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
502 ;; rewrite "/var/tmp" in check script
503 (substitute* "scripts/common/check/check_make_unix.sh"
504 (("/var/tmp") "/tmp"))
507 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
509 (("action=/bin/") "action=")
510 (("export PATH") ":"))
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
535 (outputs '("out" ; 19 MB
543 (home-page "http://blast.ncbi.nlm.nih.gov")
544 (synopsis "Basic local alignment search tool")
546 "BLAST is a popular method of performing a DNA or protein sequence
547 similarity search, using heuristics to produce results quickly. It also
548 calculates an “expect value” that estimates how many matches would have
549 occurred at a given score by chance, which can aid a user in judging how much
550 confidence to have in an alignment.")
551 ;; Most of the sources are in the public domain, with the following
554 ;; * ./c++/include/util/bitset/
555 ;; * ./c++/src/html/ncbi_menu*.js
557 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
559 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
561 ;; * ./c++/src/corelib/teamcity_*
562 (license (list license:public-domain
574 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
578 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
579 (modules '((guix build utils)))
582 ;; Remove bundled boost, pigz, zlib, and .git directory
583 ;; FIXME: also remove bundled sources for murmurhash3 and
584 ;; kmc once packaged.
585 (delete-file-recursively "boost")
586 (delete-file-recursively "pigz")
587 (delete-file-recursively "google-sparsehash")
588 (delete-file-recursively "zlib")
589 (delete-file-recursively ".git")
591 (build-system gnu-build-system)
593 '(#:tests? #f ;no "check" target
595 (list (string-append "ZLIB="
596 (assoc-ref %build-inputs "zlib")
598 (string-append "LDFLAGS="
599 (string-join '("-lboost_filesystem"
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") ""))
612 (add-after 'unpack 'patch-paths-to-executables
613 (lambda* (#:key inputs outputs #:allow-other-keys)
614 (substitute* "parse_args.cpp"
616 (string-append "kmc_binary = \""
617 (assoc-ref outputs "out")
619 (("pigz_binary = .*")
620 (string-append "pigz_binary = \""
621 (assoc-ref inputs "pigz")
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"))
631 (delete 'configure))))
635 `(("openmpi" ,openmpi)
637 ("sparsehash" ,sparsehash)
640 (supported-systems '("x86_64-linux"))
641 (home-page "http://sourceforge.net/p/bless-ec/wiki/Home/")
642 (synopsis "Bloom-filter-based error correction tool for NGS reads")
644 "@dfn{Bloom-filter-based error correction solution for high-throughput
645 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
646 correction tool for genomic reads produced by @dfn{Next-generation
647 sequencing} (NGS). BLESS produces accurate correction results with much less
648 memory compared with previous solutions and is also able to tolerate a higher
649 false-positive rate. BLESS can extend reads like DNA assemblers to correct
650 errors at the end of reads.")
651 (license license:gpl3+)))
653 (define-public bowtie
659 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
661 (file-name (string-append name "-" version ".tar.gz"))
664 "1ssfvymxfrap6f9pf86s9bvsbqdgka4abr2r7j3mgr4w1l289m86"))
665 (modules '((guix build utils)))
667 '(substitute* "Makefile"
668 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
669 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
670 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
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)
682 (string-append "prefix=" (assoc-ref %outputs "out")))
688 (lambda* (#:key outputs #:allow-other-keys)
690 "scripts/test/simple_tests.pl"
691 "--bowtie2=./bowtie2"
692 "--bowtie2-build=./bowtie2-build"))
694 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
695 (synopsis "Fast and sensitive nucleotide sequence read aligner")
697 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
698 reads to long reference sequences. It is particularly good at aligning reads
699 of about 50 up to 100s or 1,000s of characters, and particularly good at
700 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
701 genome with an FM Index to keep its memory footprint small: for the human
702 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
703 gapped, local, and paired-end alignment modes.")
704 (supported-systems '("x86_64-linux"))
705 (license license:gpl3+)))
707 (define-public tophat
714 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
718 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
719 (patches (search-patches "tophat-build-with-later-seqan.patch"))
720 (modules '((guix build utils)))
723 ;; Remove bundled SeqAn and samtools
724 (delete-file-recursively "src/SeqAn-1.3")
725 (delete-file-recursively "src/samtools-0.1.18")
727 (build-system gnu-build-system)
729 '(#:parallel-build? #f ; not supported
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"
742 (("samtools_0.1.18") (which "samtools")))
743 (substitute* '("src/common.h"
745 (("#include \"bam.h\"") "#include <samtools/bam.h>")
746 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
747 (substitute* '("src/bwt_map.h"
749 "src/align_status.h")
750 (("#include <bam.h>") "#include <samtools/bam.h>")
751 (("#include <sam.h>") "#include <samtools/sam.h>"))
756 ("samtools" ,samtools-0.1)
762 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
763 (synopsis "Spliced read mapper for RNA-Seq data")
765 "TopHat is a fast splice junction mapper for nucleotide sequence
766 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
767 mammalian-sized genomes using the ultra high-throughput short read
768 aligner Bowtie, and then analyzes the mapping results to identify
769 splice 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)))
780 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
784 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
785 (build-system gnu-build-system)
787 '(#:tests? #f ;no "check" target
791 (lambda* (#:key outputs #:allow-other-keys)
792 (let ((bin (string-append
793 (assoc-ref outputs "out") "/bin"))
795 (assoc-ref outputs "out") "/share/doc/bwa"))
797 (assoc-ref outputs "out") "/share/man/man1")))
801 (install-file "bwa" bin)
802 (install-file "README.md" doc)
803 (install-file "bwa.1" man)))
804 ;; no "configure" script
805 (alist-delete 'configure %standard-phases))))
806 (inputs `(("zlib" ,zlib)))
807 ;; Non-portable SSE instructions are used so building fails on platforms
808 ;; other than x86_64.
809 (supported-systems '("x86_64-linux"))
810 (home-page "http://bio-bwa.sourceforge.net/")
811 (synopsis "Burrows-Wheeler sequence aligner")
813 "BWA is a software package for mapping low-divergent sequences against a
814 large reference genome, such as the human genome. It consists of three
815 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
816 designed for Illumina sequence reads up to 100bp, while the rest two for
817 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
818 features such as long-read support and split alignment, but BWA-MEM, which is
819 the latest, is generally recommended for high-quality queries as it is faster
820 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
821 70-100bp Illumina reads.")
822 (license license:gpl3+)))
824 (define-public bwa-pssm
825 (package (inherit bwa)
830 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
831 "archive/" version ".tar.gz"))
832 (file-name (string-append name "-" version ".tar.gz"))
835 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
836 (build-system gnu-build-system)
841 (home-page "http://bwa-pssm.binf.ku.dk/")
842 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
844 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
845 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
846 existing aligners it is fast and sensitive. Unlike most other aligners,
847 however, it is also adaptible in the sense that one can direct the alignment
848 based on known biases within the data set. It is coded as a modification of
849 the original BWA alignment program and shares the genome index structure as
850 well as many of the command line options.")
851 (license license:gpl3+)))
853 (define-public python2-bx-python
855 (name "python2-bx-python")
860 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
864 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
865 (modules '((guix build utils)))
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)
873 `(#:tests? #f ;tests fail because test data are not included
876 `(("python-numpy" ,python2-numpy)
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")
884 "bx-python provides tools for manipulating biological data, particularly
885 multiple sequence alignments.")
886 (license license:expat)))
888 (define-public python-pysam
890 (name "python-pysam")
894 (uri (pypi-uri "pysam" version))
897 "1slx5mb94mzm5qzk52q270sab0sar95j67w1g1k452nz3s9j7krh"))))
898 (build-system python-build-system)
900 `(#:tests? #f ; tests are excluded in the manifest
905 (setenv "LDFLAGS" "-lncurses")
906 (setenv "CFLAGS" "-D_CURSES_LIB=1"))
909 `(("ncurses" ,ncurses)
912 `(("python-cython" ,python-cython)
913 ("python-setuptools" ,python-setuptools)))
914 (home-page "https://github.com/pysam-developers/pysam")
915 (synopsis "Python bindings to the SAMtools C API")
917 "Pysam is a Python module for reading and manipulating files in the
918 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
919 also includes an interface for tabix.")
920 (license license:expat)))
922 (define-public python2-pysam
923 (package-with-python2 python-pysam))
925 (define-public python-twobitreader
927 (name "python-twobitreader")
931 (uri (pypi-uri "twobitreader" version))
934 "0y408fp6psqzwxpcpqn0wp7fr41dwz8d54wpj6j261fj5q8vs169"))))
935 (properties `((python2-variant . ,(delay python2-twobitreader))))
936 (build-system python-build-system)
938 `(("python-sphinx" ,python-sphinx)))
939 (home-page "https://github.com/benjschiller/twobitreader")
940 (synopsis "Python library for reading .2bit files")
942 "twobitreader is a Python library for reading .2bit files as used by the
943 UCSC genome browser.")
944 (license license:artistic2.0)))
946 (define-public python2-twobitreader
947 (let ((base (package-with-python2 (strip-python2-variant python-twobitreader))))
950 (native-inputs `(("python2-setuptools" ,python2-setuptools)
951 ,@(package-native-inputs base))))))
953 (define-public python-plastid
955 (name "python-plastid")
959 (uri (pypi-uri "plastid" version))
962 "1nhxw8a5gn9as58i2ih52c5cjwj48ik418pzsjwph3s66mmy9yvq"))))
963 (properties `((python2-variant . ,(delay python2-plastid))))
964 (build-system python-build-system)
966 ;; Some test files are not included.
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)))
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")
982 "plastid is a Python library for genomic analysis – in particular,
983 high-throughput sequencing data – with an emphasis on simplicity.")
984 (license license:bsd-3)))
986 (define-public python2-plastid
987 (let ((base (package-with-python2 (strip-python2-variant python-plastid))))
990 ;; setuptools is required at runtime
991 (propagated-inputs `(("python2-setuptools" ,python2-setuptools)
992 ,@(package-propagated-inputs base))))))
994 (define-public cd-hit
1000 (uri (string-append "https://github.com/weizhongli/cdhit"
1001 "/releases/download/V" version
1002 "/cd-hit-v" version "-2016-0304.tar.gz"))
1005 "15db0hq38yyifwqx9b6l34z14jcq576dmjavhj8a426c18lvnhp3"))))
1006 (build-system gnu-build-system)
1008 `(#:tests? #f ; there are no tests
1010 ;; Executables are copied directly to the PREFIX.
1011 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1013 (modify-phases %standard-phases
1014 ;; No "configure" script
1016 ;; Remove sources of non-determinism
1017 (add-after 'unpack 'be-timeless
1019 (substitute* "cdhit-utility.c++"
1020 ((" \\(built on \" __DATE__ \"\\)") ""))
1021 (substitute* "cdhit-common.c++"
1022 (("__DATE__") "\"0\"")
1023 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
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"))
1032 (home-page "http://weizhongli-lab.org/cd-hit/")
1033 (synopsis "Cluster and compare protein or nucleotide sequences")
1035 "CD-HIT is a program for clustering and comparing protein or nucleotide
1036 sequences. CD-HIT is designed to be fast and handle extremely large
1038 ;; The manual says: "It can be copied under the GNU General Public License
1039 ;; version 2 (GPLv2)."
1040 (license license:gpl2)))
1042 (define-public clipper
1049 "https://github.com/YeoLab/clipper/archive/"
1051 (file-name (string-append name "-" version ".tar.gz"))
1054 "1q7jpimsqln7ic44i8v2rx2haj5wvik8hc1s2syd31zcn0xk1iyq"))
1055 (modules '((guix build utils)))
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
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)))
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")
1078 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1079 (license license:gpl2)))
1081 (define-public codingquarry
1083 (name "codingquarry")
1088 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1092 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1093 (build-system gnu-build-system)
1095 '(#:tests? #f ; no "check" target
1097 (modify-phases %standard-phases
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
1117 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1118 (home-page "https://sourceforge.net/projects/codingquarry/")
1119 (license license:gpl3+)))
1121 (define-public couger
1128 "http://couger.oit.duke.edu/static/assets/COUGER"
1132 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1133 (build-system gnu-build-system)
1137 (modify-phases %standard-phases
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"
1149 (string-append "import sys\nsys.path.append(\""
1150 out "\")\nfrom argparse")))
1151 (copy-file "couger" (string-append out "/bin/couger")))
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))))
1163 `(("python" ,python-2)
1164 ("python2-pillow" ,python2-pillow)
1165 ("python2-numpy" ,python2-numpy)
1166 ("python2-scipy" ,python2-scipy)
1167 ("python2-matplotlib" ,python2-matplotlib)))
1171 ("randomjungle" ,randomjungle)))
1173 `(("unzip" ,unzip)))
1174 (home-page "http://couger.oit.duke.edu")
1175 (synopsis "Identify co-factors in sets of genomic regions")
1177 "COUGER can be applied to any two sets of genomic regions bound by
1178 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1179 putative co-factors that provide specificity to each TF. The framework
1180 determines the genomic targets uniquely-bound by each TF, and identifies a
1181 small set of co-factors that best explain the in vivo binding differences
1182 between the two TFs.
1184 COUGER uses classification algorithms (support vector machines and random
1185 forests) with features that reflect the DNA binding specificities of putative
1186 co-factors. The features are generated either from high-throughput TF-DNA
1187 binding data (from protein binding microarray experiments), or from large
1188 collections of DNA motifs.")
1189 (license license:gpl3+)))
1191 (define-public clustal-omega
1193 (name "clustal-omega")
1198 "http://www.clustal.org/omega/clustal-omega-"
1202 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1203 (build-system gnu-build-system)
1205 `(("argtable" ,argtable)))
1206 (home-page "http://www.clustal.org/omega/")
1207 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1209 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1210 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1211 of handling data-sets of hundreds of thousands of sequences in reasonable
1213 (license license:gpl2+)))
1215 (define-public crossmap
1221 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1225 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1226 ;; This patch has been sent upstream already and is available
1227 ;; for download from Sourceforge, but it has not been merged.
1228 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1229 (modules '((guix build utils)))
1230 ;; remove bundled copy of pysam
1232 '(delete-file-recursively "lib/pysam"))))
1233 (build-system python-build-system)
1235 `(#:python ,python-2
1239 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1242 `(("python-numpy" ,python2-numpy)
1243 ("python-pysam" ,python2-pysam)
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")
1252 "CrossMap is a program for conversion of genome coordinates or annotation
1253 files between different genome assemblies. It supports most commonly used
1254 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1255 (license license:gpl2+)))
1257 (define-public cufflinks
1263 (uri (string-append "http://cole-trapnell-lab.github.io/"
1264 "cufflinks/assets/downloads/cufflinks-"
1268 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1269 (build-system gnu-build-system)
1273 ;; The includes for "eigen" are located in a subdirectory.
1274 (string-append "EIGEN_CPPFLAGS="
1275 "-I" (assoc-ref %build-inputs "eigen")
1277 ;; Cufflinks must be linked with various boost libraries.
1278 (string-append "LDFLAGS="
1279 (string-join '("-lboost_system"
1280 "-lboost_serialization"
1281 "-lboost_thread"))))
1283 (modify-phases %standard-phases
1284 (add-after 'unpack 'fix-search-for-bam
1286 (substitute* '("ax_bam.m4"
1289 (("<bam/sam\\.h>") "<samtools/sam.h>")
1290 (("<bam/bam\\.h>") "<samtools/bam.h>")
1291 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1294 (list (string-append "--with-bam="
1295 (assoc-ref %build-inputs "samtools")))))
1298 ("samtools" ,samtools-0.1)
1301 ("python" ,python-2)
1303 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1304 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1306 "Cufflinks assembles RNA transcripts, estimates their abundances,
1307 and tests for differential expression and regulation in RNA-Seq
1308 samples. It accepts aligned RNA-Seq reads and assembles the
1309 alignments into a parsimonious set of transcripts. Cufflinks then
1310 estimates the relative abundances of these transcripts based on how
1311 many reads support each one, taking into account biases in library
1312 preparation protocols.")
1313 (license license:boost1.0)))
1315 (define-public cutadapt
1322 "https://github.com/marcelm/cutadapt/archive/v"
1324 (file-name (string-append name "-" version ".tar.gz"))
1327 "161bp87y6gd6r5bmvjpn2b1k942i3fizfpa139f0jn6jv1wcp5h5"))))
1328 (build-system python-build-system)
1330 ;; tests must be run after install
1331 `(#:phases (alist-cons-after
1333 (lambda* (#:key inputs outputs #:allow-other-keys)
1334 (setenv "PYTHONPATH"
1336 (getenv "PYTHONPATH")
1337 ":" (assoc-ref outputs "out")
1339 (string-take (string-take-right
1340 (assoc-ref inputs "python") 5) 3)
1342 (zero? (system* "nosetests" "-P" "tests")))
1343 (alist-delete 'check %standard-phases))))
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")
1351 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1352 other types of unwanted sequence from high-throughput sequencing reads.")
1353 (license license:expat)))
1355 (define-public libbigwig
1361 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1362 "archive/" version ".tar.gz"))
1363 (file-name (string-append name "-" version ".tar.gz"))
1366 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1367 (build-system gnu-build-system)
1369 `(#:test-target "test"
1372 (string-append "prefix=" (assoc-ref %outputs "out")))
1374 (modify-phases %standard-phases
1376 (add-before 'check 'disable-curl-test
1378 (substitute* "Makefile"
1379 (("./test/testRemote.*") ""))
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"))
1393 `(("doxygen" ,doxygen)))
1394 (home-page "https://github.com/dpryan79/libBigWig")
1395 (synopsis "C library for handling bigWig files")
1397 "This package provides a C library for parsing local and remote BigWig
1399 (license license:expat)))
1401 (define-public python-pybigwig
1403 (name "python-pybigwig")
1407 (uri (pypi-uri "pyBigWig" version))
1410 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1411 (modules '((guix build utils)))
1414 ;; Delete bundled libBigWig sources
1415 (delete-file-recursively "libBigWig")))))
1416 (build-system python-build-system)
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\", "))
1426 `(("libbigwig" ,libbigwig)
1429 (home-page "https://github.com/dpryan79/pyBigWig")
1430 (synopsis "Access bigWig files in Python using libBigWig")
1432 "This package provides Python bindings to the libBigWig library for
1433 accessing bigWig files.")
1434 (license license:expat)))
1436 (define-public python2-pybigwig
1437 (let ((pybigwig (package-with-python2 python-pybigwig)))
1438 (package (inherit pybigwig)
1440 `(("python-setuptools" ,python2-setuptools))))))
1442 (define-public deeptools
1448 (uri (string-append "https://github.com/fidelram/deepTools/"
1449 "archive/" version ".tar.gz"))
1450 (file-name (string-append name "-" version ".tar.gz"))
1453 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
1454 (build-system python-build-system)
1456 `(#:python ,python-2))
1458 `(("python-scipy" ,python2-scipy)
1459 ("python-numpy" ,python2-numpy)
1460 ("python-numpydoc" ,python2-numpydoc)
1461 ("python-matplotlib" ,python2-matplotlib)
1462 ("python-bx-python" ,python2-bx-python)
1463 ("python-pysam" ,python2-pysam)
1464 ("python-pybigwig" ,python2-pybigwig)))
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")
1472 "DeepTools addresses the challenge of handling the large amounts of data
1473 that are now routinely generated from DNA sequencing centers. To do so,
1474 deepTools contains useful modules to process the mapped reads data to create
1475 coverage files in standard bedGraph and bigWig file formats. By doing so,
1476 deepTools allows the creation of normalized coverage files or the comparison
1477 between two files (for example, treatment and control). Finally, using such
1478 normalized and standardized files, multiple visualizations can be created to
1479 identify enrichments with functional annotations of the genome.")
1480 (license license:gpl3+)))
1482 (define-public diamond
1489 "https://github.com/bbuchfink/diamond/archive/v"
1491 (file-name (string-append name "-" version ".tar.gz"))
1494 "15r7gcrqc4pv5d4kvv530zc3xnni92c74y63zrxzidriss7591yx"))))
1495 (build-system cmake-build-system)
1497 '(#:tests? #f ; no "check" target
1499 (modify-phases %standard-phases
1500 (add-after 'unpack 'remove-native-compilation
1502 (substitute* "CMakeLists.txt" (("-march=native") ""))
1506 (home-page "https://github.com/bbuchfink/diamond")
1507 (synopsis "Accelerated BLAST compatible local sequence aligner")
1509 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
1510 translated DNA query sequences against a protein reference database (BLASTP
1511 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
1512 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
1513 data and settings.")
1514 ;; diamond fails to build on other platforms
1515 ;; https://github.com/bbuchfink/diamond/issues/18
1516 (supported-systems '("x86_64-linux"))
1517 (license (license:non-copyleft "file://src/COPYING"
1518 "See src/COPYING in the distribution."))))
1520 (define-public edirect
1526 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
1527 "versions/2016-05-03/edirect.tar.gz"))
1530 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
1531 (build-system perl-build-system)
1533 `(#:tests? #f ;no "check" target
1535 (modify-phases %standard-phases
1539 (lambda* (#:key outputs #:allow-other-keys)
1540 (let ((target (string-append (assoc-ref outputs "out")
1543 (copy-file "edirect.pl"
1544 (string-append target "/edirect.pl"))
1547 'install 'wrap-program
1548 (lambda* (#:key inputs outputs #:allow-other-keys)
1549 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
1550 (let* ((out (assoc-ref outputs "out"))
1551 (path (getenv "PERL5LIB")))
1552 (wrap-program (string-append out "/bin/edirect.pl")
1553 `("PERL5LIB" ":" prefix (,path)))))))))
1555 `(("perl-html-parser" ,perl-html-parser)
1556 ("perl-encode-locale" ,perl-encode-locale)
1557 ("perl-file-listing" ,perl-file-listing)
1558 ("perl-html-tagset" ,perl-html-tagset)
1559 ("perl-html-tree" ,perl-html-tree)
1560 ("perl-http-cookies" ,perl-http-cookies)
1561 ("perl-http-date" ,perl-http-date)
1562 ("perl-http-message" ,perl-http-message)
1563 ("perl-http-negotiate" ,perl-http-negotiate)
1564 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
1565 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
1566 ("perl-net-http" ,perl-net-http)
1567 ("perl-uri" ,perl-uri)
1568 ("perl-www-robotrules" ,perl-www-robotrules)
1570 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
1571 (synopsis "Tools for accessing the NCBI's set of databases")
1573 "Entrez Direct (EDirect) is a method for accessing the National Center
1574 for Biotechnology Information's (NCBI) set of interconnected
1575 databases (publication, sequence, structure, gene, variation, expression,
1576 etc.) from a terminal. Functions take search terms from command-line
1577 arguments. Individual operations are combined to build multi-step queries.
1578 Record retrieval and formatting normally complete the process.
1580 EDirect also provides an argument-driven function that simplifies the
1581 extraction of data from document summaries or other results that are returned
1582 in structured XML format. This can eliminate the need for writing custom
1583 software to answer ad hoc questions.")
1584 (license license:public-domain)))
1586 (define-public express
1594 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
1595 version "/express-" version "-src.tgz"))
1598 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
1599 (build-system cmake-build-system)
1601 `(#:tests? #f ;no "check" target
1604 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
1605 (lambda* (#:key inputs #:allow-other-keys)
1606 (substitute* "CMakeLists.txt"
1607 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
1608 "set(Boost_USE_STATIC_LIBS OFF)")
1609 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
1610 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
1611 (substitute* "src/CMakeLists.txt"
1612 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
1613 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
1618 ("bamtools" ,bamtools)
1619 ("protobuf" ,protobuf)
1621 (home-page "http://bio.math.berkeley.edu/eXpress")
1622 (synopsis "Streaming quantification for high-throughput genomic sequencing")
1624 "eXpress is a streaming tool for quantifying the abundances of a set of
1625 target sequences from sampled subsequences. Example applications include
1626 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
1627 analysis (from RNA-Seq), transcription factor binding quantification in
1628 ChIP-Seq, and analysis of metagenomic data.")
1629 (license license:artistic2.0)))
1631 (define-public express-beta-diversity
1633 (name "express-beta-diversity")
1639 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
1641 (file-name (string-append name "-" version ".tar.gz"))
1644 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
1645 (build-system gnu-build-system)
1648 (modify-phases %standard-phases
1650 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
1652 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
1654 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
1656 (lambda* (#:key outputs #:allow-other-keys)
1657 (let ((bin (string-append (assoc-ref outputs "out")
1660 (copy-file "scripts/convertToEBD.py"
1661 (string-append bin "/convertToEBD.py"))
1662 (copy-file "bin/ExpressBetaDiversity"
1663 (string-append bin "/ExpressBetaDiversity"))
1666 `(("python" ,python-2)))
1667 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
1668 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
1670 "Express Beta Diversity (EBD) calculates ecological beta diversity
1671 (dissimilarity) measures between biological communities. EBD implements a
1672 variety of diversity measures including those that make use of phylogenetic
1673 similarity of community members.")
1674 (license license:gpl3+)))
1676 (define-public fasttree
1683 "http://www.microbesonline.org/fasttree/FastTree-"
1687 "0dzqc9vr9iiiw21y159xfjl2z90vw0y7r4x6456pcaxiy5hd2wmi"))))
1688 (build-system gnu-build-system)
1690 `(#:tests? #f ; no "check" target
1692 (modify-phases %standard-phases
1696 (lambda* (#:key source #:allow-other-keys)
1697 (and (zero? (system* "gcc"
1699 "-finline-functions"
1706 (zero? (system* "gcc"
1710 "-finline-functions"
1718 (lambda* (#:key outputs #:allow-other-keys)
1719 (let ((bin (string-append (assoc-ref outputs "out")
1722 (copy-file "FastTree"
1723 (string-append bin "/FastTree"))
1724 (copy-file "FastTreeMP"
1725 (string-append bin "/FastTreeMP"))
1727 (home-page "http://www.microbesonline.org/fasttree")
1728 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
1730 "FastTree can handle alignments with up to a million of sequences in a
1731 reasonable amount of time and memory. For large alignments, FastTree is
1732 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
1733 (license license:gpl2+)))
1735 (define-public fastx-toolkit
1737 (name "fastx-toolkit")
1743 "https://github.com/agordon/fastx_toolkit/releases/download/"
1744 version "/fastx_toolkit-" version ".tar.bz2"))
1747 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
1748 (build-system gnu-build-system)
1750 `(("libgtextutils" ,libgtextutils)))
1752 `(("pkg-config" ,pkg-config)))
1753 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
1754 (synopsis "Tools for FASTA/FASTQ file preprocessing")
1756 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
1757 FASTA/FASTQ files preprocessing.
1759 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
1760 containing multiple short-reads sequences. The main processing of such
1761 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
1762 is sometimes more productive to preprocess the files before mapping the
1763 sequences to the genome---manipulating the sequences to produce better mapping
1764 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
1765 (license license:agpl3+)))
1767 (define-public flexbar
1774 (string-append "mirror://sourceforge/flexbar/"
1775 version "/flexbar_v" version "_src.tgz"))
1778 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
1779 (build-system cmake-build-system)
1781 `(#:configure-flags (list
1782 (string-append "-DFLEXBAR_BINARY_DIR="
1783 (assoc-ref %outputs "out")
1788 (lambda* (#:key outputs #:allow-other-keys)
1789 (setenv "PATH" (string-append
1790 (assoc-ref outputs "out") "/bin:"
1792 (chdir "../flexbar_v2.5_src/test")
1793 (zero? (system* "bash" "flexbar_validate.sh")))
1794 (alist-delete 'install %standard-phases))))
1799 `(("pkg-config" ,pkg-config)
1801 (home-page "http://flexbar.sourceforge.net")
1802 (synopsis "Barcode and adapter removal tool for sequencing platforms")
1804 "Flexbar preprocesses high-throughput nucleotide sequencing data
1805 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
1806 Moreover, trimming and filtering features are provided. Flexbar increases
1807 read mapping rates and improves genome and transcriptome assemblies. It
1808 supports next-generation sequencing data in fasta/q and csfasta/q format from
1809 Illumina, Roche 454, and the SOLiD platform.")
1810 (license license:gpl3)))
1812 (define-public fraggenescan
1814 (name "fraggenescan")
1820 (string-append "mirror://sourceforge/fraggenescan/"
1821 "FragGeneScan" version ".tar.gz"))
1823 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
1824 (build-system gnu-build-system)
1827 (modify-phases %standard-phases
1829 (add-before 'build 'patch-paths
1830 (lambda* (#:key outputs #:allow-other-keys)
1831 (let* ((out (string-append (assoc-ref outputs "out")))
1832 (share (string-append out "/share/fraggenescan/")))
1833 (substitute* "run_FragGeneScan.pl"
1835 (string-append "system(\"" (which "rm")))
1837 (string-append "system(\"" (which "mv")))
1838 ;; This script and other programs expect the training files
1839 ;; to be in the non-standard location bin/train/XXX. Change
1840 ;; this to be share/fraggenescan/train/XXX instead.
1841 (("^\\$train.file = \\$dir.*")
1842 (string-append "$train_file = \""
1844 "train/\".$FGS_train_file;")))
1845 (substitute* "run_hmm.c"
1846 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
1847 (string-append " strcpy(train_dir, \"" share "/train/\");")))
1848 (substitute* "post_process.pl"
1849 (("^my \\$dir = substr.*")
1850 (string-append "my $dir = \"" share "\";"))))
1853 (lambda _ (and (zero? (system* "make" "clean"))
1854 (zero? (system* "make" "fgs")))))
1856 (lambda* (#:key outputs #:allow-other-keys)
1857 (let* ((out (string-append (assoc-ref outputs "out")))
1858 (bin (string-append out "/bin/"))
1859 (share (string-append out "/share/fraggenescan/train")))
1860 (install-file "run_FragGeneScan.pl" bin)
1861 (install-file "FragGeneScan" bin)
1862 (install-file "FGS_gff.py" bin)
1863 (install-file "post_process.pl" bin)
1864 (copy-recursively "train" share))))
1866 (add-after 'install 'post-install-check
1867 ;; In lieu of 'make check', run one of the examples and check the
1868 ;; output files gets created.
1869 (lambda* (#:key outputs #:allow-other-keys)
1870 (let* ((out (string-append (assoc-ref outputs "out")))
1871 (bin (string-append out "/bin/")))
1872 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
1873 "-genome=./example/NC_000913.fna"
1877 (file-exists? "test2.faa")
1878 (file-exists? "test2.ffn")
1879 (file-exists? "test2.gff")
1880 (file-exists? "test2.out"))))))))
1883 ("python" ,python-2))) ;not compatible with python 3.
1884 (home-page "https://sourceforge.net/projects/fraggenescan/")
1885 (synopsis "Finds potentially fragmented genes in short reads")
1887 "FragGeneScan is a program for predicting bacterial and archaeal genes in
1888 short and error-prone DNA sequencing reads. It can also be applied to predict
1889 genes in incomplete assemblies or complete genomes.")
1890 ;; GPL3+ according to private correspondense with the authors.
1891 (license license:gpl3+)))
1893 (define-public fxtract
1894 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
1902 "https://github.com/ctSkennerton/fxtract/archive/"
1904 (file-name (string-append "ctstennerton-util-"
1905 (string-take util-commit 7)
1909 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
1910 (build-system gnu-build-system)
1912 `(#:make-flags (list
1913 (string-append "PREFIX=" (assoc-ref %outputs "out"))
1915 #:test-target "fxtract_test"
1917 (modify-phases %standard-phases
1919 (add-before 'build 'copy-util
1920 (lambda* (#:key inputs #:allow-other-keys)
1922 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
1924 ;; Do not use make install as this requires additional dependencies.
1926 (lambda* (#:key outputs #:allow-other-keys)
1927 (let* ((out (assoc-ref outputs "out"))
1928 (bin (string-append out"/bin")))
1929 (install-file "fxtract" bin)
1935 ;; ctskennerton-util is licensed under GPL2.
1936 `(("ctskennerton-util"
1940 (url "https://github.com/ctSkennerton/util.git")
1941 (commit util-commit)))
1942 (file-name (string-append
1943 "ctstennerton-util-" util-commit "-checkout"))
1946 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
1947 (home-page "https://github.com/ctSkennerton/fxtract")
1948 (synopsis "Extract sequences from FASTA and FASTQ files")
1950 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
1951 or FASTQ) file given a subsequence. It uses a simple substring search for
1952 basic tasks but can change to using POSIX regular expressions, PCRE, hash
1953 lookups or multi-pattern searching as required. By default fxtract looks in
1954 the sequence of each record but can also be told to look in the header,
1955 comment or quality sections.")
1956 (license license:expat))))
1965 "https://github.com/nboley/grit/archive/"
1967 (file-name (string-append name "-" version ".tar.gz"))
1970 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
1971 (build-system python-build-system)
1973 `(#:python ,python-2
1976 'unpack 'generate-from-cython-sources
1977 (lambda* (#:key inputs outputs #:allow-other-keys)
1978 ;; Delete these C files to force fresh generation from pyx sources.
1979 (delete-file "grit/sparsify_support_fns.c")
1980 (delete-file "grit/call_peaks_support_fns.c")
1981 (substitute* "setup.py"
1982 (("Cython.Setup") "Cython.Build")
1983 ;; Add numpy include path to fix compilation
1985 (string-append "pyx\", ], include_dirs = ['"
1986 (assoc-ref inputs "python-numpy")
1987 "/lib/python2.7/site-packages/numpy/core/include/"
1991 `(("python-scipy" ,python2-scipy)
1992 ("python-numpy" ,python2-numpy)
1993 ("python-pysam" ,python2-pysam)
1994 ("python-networkx" ,python2-networkx)))
1996 `(("python-cython" ,python2-cython)
1997 ("python-setuptools" ,python2-setuptools)))
1998 (home-page "http://grit-bio.org")
1999 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2001 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2002 full length transcript models. When none of these data sources are available,
2003 GRIT can be run by providing a candidate set of TES or TSS sites. In
2004 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2005 also be run in quantification mode, where it uses a provided GTF file and just
2006 estimates transcript expression.")
2007 (license license:gpl3+)))
2009 (define-public hisat
2016 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2017 version "-beta-source.zip"))
2020 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2021 (build-system gnu-build-system)
2023 `(#:tests? #f ;no check target
2024 #:make-flags '("allall"
2025 ;; Disable unsupported `popcnt' instructions on
2026 ;; architectures other than x86_64
2027 ,@(if (string-prefix? "x86_64"
2028 (or (%current-target-system)
2031 '("POPCNT_CAPABILITY=0")))
2034 'unpack 'patch-sources
2036 ;; XXX Cannot use snippet because zip files are not supported
2037 (substitute* "Makefile"
2038 (("^CC = .*$") "CC = gcc")
2039 (("^CPP = .*$") "CPP = g++")
2040 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2041 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2042 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2043 (substitute* '("hisat-build" "hisat-inspect")
2044 (("/usr/bin/env") (which "env"))))
2047 (lambda* (#:key outputs #:allow-other-keys)
2048 (let ((bin (string-append (assoc-ref outputs "out") "/bi/")))
2049 (for-each (lambda (file)
2050 (install-file file bin))
2053 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2054 (alist-delete 'configure %standard-phases)))))
2056 `(("unzip" ,unzip)))
2061 ;; Non-portable SSE instructions are used so building fails on platforms
2062 ;; other than x86_64.
2063 (supported-systems '("x86_64-linux"))
2064 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2065 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2067 "HISAT is a fast and sensitive spliced alignment program for mapping
2068 RNA-seq reads. In addition to one global FM index that represents a whole
2069 genome, HISAT uses a large set of small FM indexes that collectively cover the
2070 whole genome. These small indexes (called local indexes) combined with
2071 several alignment strategies enable effective alignment of RNA-seq reads, in
2072 particular, reads spanning multiple exons.")
2073 (license license:gpl3+)))
2075 (define-public hmmer
2082 "http://eddylab.org/software/hmmer"
2083 (version-prefix version 1) "/"
2084 version "/hmmer-" version ".tar.gz"))
2087 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
2088 (build-system gnu-build-system)
2089 (native-inputs `(("perl" ,perl)))
2090 (home-page "http://hmmer.org/")
2091 (synopsis "Biosequence analysis using profile hidden Markov models")
2093 "HMMER is used for searching sequence databases for homologs of protein
2094 sequences, and for making protein sequence alignments. It implements methods
2095 using probabilistic models called profile hidden Markov models (profile
2097 (license (list license:gpl3+
2098 ;; The bundled library 'easel' is distributed
2099 ;; under The Janelia Farm Software License.
2100 (license:non-copyleft
2101 "file://easel/LICENSE"
2102 "See easel/LICENSE in the distribution.")))))
2104 (define-public htseq
2111 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2115 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2116 (build-system python-build-system)
2117 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2118 ;; Numpy needs to be propagated when htseq is used as a Python library.
2120 `(("python-numpy" ,python2-numpy)))
2122 `(("python-pysam" ,python2-pysam)))
2124 `(("python-setuptools" ,python2-setuptools)))
2125 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2126 (synopsis "Analysing high-throughput sequencing data with Python")
2128 "HTSeq is a Python package that provides infrastructure to process data
2129 from high-throughput sequencing assays.")
2130 (license license:gpl3+)))
2132 (define-public java-htsjdk
2134 (name "java-htsjdk")
2139 "https://github.com/samtools/htsjdk/archive/"
2141 (file-name (string-append name "-" version ".tar.gz"))
2144 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2145 (modules '((guix build utils)))
2146 ;; remove build dependency on git
2147 (snippet '(substitute* "build.xml"
2148 (("failifexecutionfails=\"true\"")
2149 "failifexecutionfails=\"false\"")))))
2150 (build-system ant-build-system)
2152 `(#:tests? #f ; test require Internet access
2154 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2155 "/share/java/htsjdk/"))
2156 #:build-target "all"
2158 (modify-phases %standard-phases
2159 ;; The build phase also installs the jars
2160 (delete 'install))))
2161 (home-page "http://samtools.github.io/htsjdk/")
2162 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2164 "HTSJDK is an implementation of a unified Java library for accessing
2165 common file formats, such as SAM and VCF, used for high-throughput
2166 sequencing (HTS) data. There are also an number of useful utilities for
2167 manipulating HTS data.")
2168 (license license:expat)))
2170 (define-public htslib
2177 "https://github.com/samtools/htslib/releases/download/"
2178 version "/htslib-" version ".tar.bz2"))
2181 "1c32ssscbnjwfw3dra140fq7riarp2x990qxybh34nr1p5r17nxx"))))
2182 (build-system gnu-build-system)
2185 (modify-phases %standard-phases
2187 'unpack 'patch-tests
2189 (substitute* "test/test.pl"
2190 (("/bin/bash") (which "bash")))
2196 (home-page "http://www.htslib.org")
2197 (synopsis "C library for reading/writing high-throughput sequencing data")
2199 "HTSlib is a C library for reading/writing high-throughput sequencing
2200 data. It also provides the bgzip, htsfile, and tabix utilities.")
2201 ;; Files under cram/ are released under the modified BSD license;
2202 ;; the rest is released under the Expat license
2203 (license (list license:expat license:bsd-3))))
2212 "https://github.com/nboley/idr/archive/"
2214 (file-name (string-append name "-" version ".tar.gz"))
2217 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
2218 (build-system python-build-system)
2221 (modify-phases %standard-phases
2223 'install 'wrap-program
2224 (lambda* (#:key inputs outputs #:allow-other-keys)
2225 (let* ((out (assoc-ref outputs "out"))
2226 (python-version (string-take (string-take-right
2227 (assoc-ref inputs "python") 5) 3))
2230 (string-append (assoc-ref inputs name)
2231 "/lib/python" python-version
2235 "python-matplotlib"))
2237 (wrap-program (string-append out "/bin/idr")
2238 `("PYTHONPATH" ":" prefix (,path))))
2241 `(("python-scipy" ,python-scipy)
2242 ("python-numpy" ,python-numpy)
2243 ("python-matplotlib" ,python-matplotlib)))
2245 `(("python-cython" ,python-cython)
2246 ("python-setuptools" ,python-setuptools)))
2247 (home-page "https://github.com/nboley/idr")
2248 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
2250 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
2251 to measure the reproducibility of findings identified from replicate
2252 experiments and provide highly stable thresholds based on reproducibility.")
2253 (license license:gpl3+)))
2255 (define-public jellyfish
2261 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
2262 "releases/download/v" version
2263 "/jellyfish-" version ".tar.gz"))
2266 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
2267 (build-system gnu-build-system)
2268 (outputs '("out" ;for library
2269 "ruby" ;for Ruby bindings
2270 "python")) ;for Python bindings
2273 (list (string-append "--enable-ruby-binding="
2274 (assoc-ref %outputs "ruby"))
2275 (string-append "--enable-python-binding="
2276 (assoc-ref %outputs "python")))
2278 (modify-phases %standard-phases
2279 (add-before 'check 'set-SHELL-variable
2281 ;; generator_manager.hpp either uses /bin/sh or $SHELL
2283 (setenv "SHELL" (which "bash"))
2289 ("python" ,python-2)))
2290 (synopsis "Tool for fast counting of k-mers in DNA")
2292 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
2293 DNA. A k-mer is a substring of length k, and counting the occurrences of all
2294 such substrings is a central step in many analyses of DNA sequence. Jellyfish
2295 is a command-line program that reads FASTA and multi-FASTA files containing
2296 DNA sequences. It outputs its k-mer counts in a binary format, which can be
2297 translated into a human-readable text format using the @code{jellyfish dump}
2298 command, or queried for specific k-mers with @code{jellyfish query}.")
2299 (home-page "http://www.genome.umd.edu/jellyfish.html")
2300 ;; The combined work is published under the GPLv3 or later. Individual
2301 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
2302 (license (list license:gpl3+ license:expat))))
2304 (define-public khmer
2311 (uri (pypi-uri "khmer" version))
2314 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
2315 (patches (search-patches "khmer-use-libraries.patch"))))
2316 (build-system python-build-system)
2319 (modify-phases %standard-phases
2320 (add-after 'unpack 'set-paths
2321 (lambda* (#:key inputs outputs #:allow-other-keys)
2322 ;; Delete bundled libraries.
2323 (delete-file-recursively "third-party/zlib")
2324 (delete-file-recursively "third-party/bzip2")
2325 ;; Replace bundled seqan.
2326 (let* ((seqan-all "third-party/seqan")
2327 (seqan-include (string-append
2328 seqan-all "/core/include")))
2329 (delete-file-recursively seqan-all)
2330 (copy-recursively (string-append (assoc-ref inputs "seqan")
2332 (string-append seqan-include "/seqan")))
2333 ;; We do not replace the bundled MurmurHash as the canonical
2334 ;; repository for this code 'SMHasher' is unsuitable for
2335 ;; providing a library. See
2336 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
2338 (add-after 'unpack 'set-cc
2342 ;; It is simpler to test after installation.
2344 (add-after 'install 'post-install-check
2345 (lambda* (#:key inputs outputs #:allow-other-keys)
2346 (let ((out (assoc-ref outputs "out")))
2351 (assoc-ref outputs "out")
2353 (setenv "PYTHONPATH"
2355 (getenv "PYTHONPATH")
2359 (string-take (string-take-right
2360 (assoc-ref inputs "python") 5) 3)
2362 (with-directory-excursion "build"
2363 (zero? (system* "nosetests" "khmer" "--attr"
2364 "!known_failing")))))))))
2367 ("python-nose" ,python-nose)))
2371 ("python-screed" ,python-screed)
2372 ("python-bz2file" ,python-bz2file)))
2373 (home-page "https://khmer.readthedocs.org/")
2374 (synopsis "K-mer counting, filtering and graph traversal library")
2375 (description "The khmer software is a set of command-line tools for
2376 working with DNA shotgun sequencing data from genomes, transcriptomes,
2377 metagenomes and single cells. Khmer can make de novo assemblies faster, and
2378 sometimes better. Khmer can also identify and fix problems with shotgun
2380 (license license:bsd-3)))
2385 (version "2.1.0.20151222")
2388 (uri (pypi-uri "MACS2" version))
2391 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
2392 (build-system python-build-system)
2394 `(#:python ,python-2 ; only compatible with Python 2.7
2395 #:tests? #f)) ; no test target
2397 `(("python-numpy" ,python2-numpy)))
2399 `(("python-setuptools" ,python2-setuptools)))
2400 (home-page "http://github.com/taoliu/MACS/")
2401 (synopsis "Model based analysis for ChIP-Seq data")
2403 "MACS is an implementation of a ChIP-Seq analysis algorithm for
2404 identifying transcript factor binding sites named Model-based Analysis of
2405 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
2406 the significance of enriched ChIP regions and it improves the spatial
2407 resolution of binding sites through combining the information of both
2408 sequencing tag position and orientation.")
2409 (license license:bsd-3)))
2411 (define-public mafft
2418 "http://mafft.cbrc.jp/alignment/software/mafft-" version
2419 "-without-extensions-src.tgz"))
2420 (file-name (string-append name "-" version ".tgz"))
2423 "1xl6xq1rfxkws0svrlhyqxhhwbv6r77jwblsdpcyiwzsscw6wlk0"))))
2424 (build-system gnu-build-system)
2426 `(#:tests? #f ; no automated tests, though there are tests in the read me
2427 #:make-flags (let ((out (assoc-ref %outputs "out")))
2428 (list (string-append "PREFIX=" out)
2429 (string-append "BINDIR="
2430 (string-append out "/bin"))))
2432 (modify-phases %standard-phases
2433 (add-after 'unpack 'enter-dir
2434 (lambda _ (chdir "core") #t))
2435 (add-after 'enter-dir 'patch-makefile
2437 ;; on advice from the MAFFT authors, there is no need to
2438 ;; distribute mafft-profile, mafft-distance, or
2439 ;; mafft-homologs.rb as they are too "specialised".
2440 (substitute* "Makefile"
2441 ;; remove mafft-homologs.rb from SCRIPTS
2442 (("^SCRIPTS = mafft mafft-homologs.rb")
2444 ;; remove mafft-homologs from MANPAGES
2445 (("^MANPAGES = mafft.1 mafft-homologs.1")
2446 "MANPAGES = mafft.1")
2447 ;; remove mafft-distance from PROGS
2448 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
2449 "PROGS = dvtditr dndfast7 dndblast sextet5")
2450 ;; remove mafft-profile from PROGS
2451 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
2452 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
2453 (("^rm -f mafft-profile mafft-profile.exe") "#")
2454 (("^rm -f mafft-distance mafft-distance.exe") ")#")
2455 ;; do not install MAN pages in libexec folder
2456 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
2457 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
2459 (add-after 'enter-dir 'patch-paths
2460 (lambda* (#:key inputs #:allow-other-keys)
2461 (substitute* '("pairash.c"
2463 (("perl") (which "perl"))
2464 (("([\"`| ])awk" _ prefix)
2465 (string-append prefix (which "awk")))
2466 (("grep") (which "grep")))
2468 (delete 'configure))))
2474 `(("coreutils" ,coreutils)))
2475 (home-page "http://mafft.cbrc.jp/alignment/software/")
2476 (synopsis "Multiple sequence alignment program")
2478 "MAFFT offers a range of multiple alignment methods for nucleotide and
2479 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
2480 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
2482 (license (license:non-copyleft
2483 "http://mafft.cbrc.jp/alignment/software/license.txt"
2484 "BSD-3 with different formatting"))))
2486 (define-public metabat
2493 "https://bitbucket.org/berkeleylab/metabat/get/"
2494 version ".tar.bz2"))
2495 (file-name (string-append name "-" version ".tar.bz2"))
2498 "0vgrhbaxg4dkxyax2kbigak7w0arhqvw0szwp6gd9wmyilc44kfa"))))
2499 (build-system gnu-build-system)
2502 (modify-phases %standard-phases
2503 (add-after 'unpack 'fix-includes
2505 (substitute* "SConstruct"
2506 (("/include/bam/bam.h")
2507 "/include/samtools/bam.h"))
2508 (substitute* "src/BamUtils.h"
2509 (("^#include \"bam/bam\\.h\"")
2510 "#include \"samtools/bam.h\"")
2511 (("^#include \"bam/sam\\.h\"")
2512 "#include \"samtools/sam.h\""))
2513 (substitute* "src/KseqReader.h"
2514 (("^#include \"bam/kseq\\.h\"")
2515 "#include \"samtools/kseq.h\""))
2517 (add-after 'unpack 'fix-scons
2519 (substitute* "SConstruct" ; Do not distribute README
2520 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)")
2525 (lambda* (#:key inputs outputs #:allow-other-keys)
2526 (mkdir (assoc-ref outputs "out"))
2527 (zero? (system* "scons"
2530 (assoc-ref outputs "out"))
2533 (assoc-ref inputs "htslib"))
2536 (assoc-ref inputs "samtools"))
2539 (assoc-ref inputs "boost"))
2541 ;; check and install carried out during build phase
2543 (delete 'install))))
2547 ("samtools" ,samtools)
2551 `(("scons" ,scons)))
2552 (home-page "https://bitbucket.org/berkeleylab/metabat")
2554 "Reconstruction of single genomes from complex microbial communities")
2556 "Grouping large genomic fragments assembled from shotgun metagenomic
2557 sequences to deconvolute complex microbial communities, or metagenome binning,
2558 enables the study of individual organisms and their interactions. MetaBAT is
2559 an automated metagenome binning software, which integrates empirical
2560 probabilistic distances of genome abundance and tetranucleotide frequency.")
2561 (license (license:non-copyleft "file://license.txt"
2562 "See license.txt in the distribution."))))
2571 "https://pypi.python.org/packages/source/m/misopy/misopy-"
2575 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
2576 (modules '((guix build utils)))
2578 '(substitute* "setup.py"
2579 ;; Use setuptools, or else the executables are not
2581 (("distutils.core") "setuptools")
2582 ;; use "gcc" instead of "cc" for compilation
2584 "cc.set_executables(
2588 linker_so='gcc -shared'); defines")))))
2589 (build-system python-build-system)
2591 `(#:python ,python-2 ; only Python 2 is supported
2592 #:tests? #f)) ; no "test" target
2594 `(("samtools" ,samtools)
2595 ("python-numpy" ,python2-numpy)
2596 ("python-pysam" ,python2-pysam)
2597 ("python-scipy" ,python2-scipy)
2598 ("python-matplotlib" ,python2-matplotlib)))
2600 `(("python-mock" ,python2-mock) ;for tests
2601 ("python-pytz" ,python2-pytz) ;for tests
2602 ("python-setuptools" ,python2-setuptools)))
2603 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
2604 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
2606 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
2607 the expression level of alternatively spliced genes from RNA-Seq data, and
2608 identifies differentially regulated isoforms or exons across samples. By
2609 modeling the generative process by which reads are produced from isoforms in
2610 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
2611 that a read originated from a particular isoform.")
2612 (license license:gpl2)))
2614 (define-public muscle
2617 (version "3.8.1551")
2619 (method url-fetch/tarbomb)
2620 (file-name (string-append name "-" version))
2622 "http://www.drive5.com/muscle/muscle_src_"
2626 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
2627 (build-system gnu-build-system)
2629 `(#:make-flags (list "LDLIBS = -lm")
2631 (modify-phases %standard-phases
2634 ;; There are no tests, so just test if it runs.
2635 (lambda _ (zero? (system* "./muscle" "-version"))))
2637 (lambda* (#:key outputs #:allow-other-keys)
2638 (let* ((out (assoc-ref outputs "out"))
2639 (bin (string-append out "/bin")))
2640 (install-file "muscle" bin)))))))
2641 (home-page "http://www.drive5.com/muscle")
2642 (synopsis "Multiple sequence alignment program")
2644 "MUSCLE aims to be a fast and accurate multiple sequence alignment
2645 program for nucleotide and protein sequences.")
2646 ;; License information found in 'muscle -h' and usage.cpp.
2647 (license license:public-domain)))
2656 "https://github.com/wwood/OrfM/releases/download/v"
2657 version "/orfm-" version ".tar.gz"))
2660 "0vb6d771gl4mix8bwx919x5ayy9pkj44n7ki336nz3rz2rx4c7gk"))))
2661 (build-system gnu-build-system)
2662 (inputs `(("zlib" ,zlib)))
2664 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
2665 ("ruby-rspec" ,ruby-rspec)
2667 (synopsis "Simple and not slow open reading frame (ORF) caller")
2669 "An ORF caller finds stretches of DNA that, when translated, are not
2670 interrupted by stop codons. OrfM finds and prints these ORFs.")
2671 (home-page "https://github.com/wwood/OrfM")
2672 (license license:lgpl3+)))
2674 (define-public python2-pbcore
2676 (name "python2-pbcore")
2680 (uri (pypi-uri "pbcore" version))
2683 "02pfn5raa3zf739672bg0dkx7z3j2c4nx7vmpfjqy5b12jrqpymk"))))
2684 (build-system python-build-system)
2685 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
2687 `(("python-cython" ,python2-cython)
2688 ("python-numpy" ,python2-numpy)
2689 ("python-pysam" ,python2-pysam)
2690 ("python-h5py" ,python2-h5py)))
2692 `(("python-docutils" ,python2-docutils)
2693 ("python-nose" ,python2-nose)
2694 ("python-setuptools" ,python2-setuptools)
2695 ("python-sphinx" ,python2-sphinx)))
2696 (home-page "http://pacificbiosciences.github.io/pbcore/")
2697 (synopsis "Library for reading and writing PacBio data files")
2699 "The pbcore package provides Python APIs for interacting with PacBio data
2700 files and writing bioinformatics applications.")
2701 (license license:bsd-3)))
2703 (define-public python2-warpedlmm
2705 (name "python2-warpedlmm")
2711 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
2715 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
2716 (build-system python-build-system)
2718 `(#:python ,python-2 ; requires Python 2.7
2720 (modify-phases %standard-phases
2722 'install 'remove-bin-directory
2723 (lambda* (#:key outputs #:allow-other-keys)
2724 ;; The "bin" directory only contains wrappers for running
2725 ;; the module tests. They are not needed after the
2727 (delete-file-recursively
2728 (string-append (assoc-ref outputs "out") "/bin"))
2731 `(("python-scipy" ,python2-scipy)
2732 ("python-numpy" ,python2-numpy)
2733 ("python-matplotlib" ,python2-matplotlib)
2734 ("python-fastlmm" ,python2-fastlmm)
2735 ("python-pandas" ,python2-pandas)
2736 ("python-pysnptools" ,python2-pysnptools)))
2738 `(("python-setuptools" ,python2-setuptools)
2739 ("python-mock" ,python2-mock)
2740 ("python-nose" ,python2-nose)
2742 (home-page "https://github.com/PMBio/warpedLMM")
2743 (synopsis "Implementation of warped linear mixed models")
2745 "WarpedLMM is a Python implementation of the warped linear mixed model,
2746 which automatically learns an optimal warping function (or transformation) for
2747 the phenotype as it models the data.")
2748 (license license:asl2.0)))
2750 (define-public pbtranscript-tofu
2751 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
2753 (name "pbtranscript-tofu")
2754 (version (string-append "2.2.3." (string-take commit 7)))
2758 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
2760 (file-name (string-append name "-" version "-checkout"))
2763 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
2764 (modules '((guix build utils)))
2767 ;; remove bundled Cython sources
2768 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
2770 (build-system python-build-system)
2772 `(#:python ,python-2
2773 ;; With standard flags, the install phase attempts to create a zip'd
2774 ;; egg file, and fails with an error: 'ZIP does not support timestamps
2776 #:configure-flags '("--single-version-externally-managed"
2777 "--record=pbtranscript-tofu.txt")
2779 (modify-phases %standard-phases
2780 (add-after 'unpack 'enter-directory
2782 (chdir "pbtranscript-tofu/pbtranscript/")
2784 ;; With setuptools version 18.0 and later this setup.py hack causes
2785 ;; a build error, so we disable it.
2786 (add-after 'enter-directory 'patch-setuppy
2788 (substitute* "setup.py"
2789 (("if 'setuptools.extension' in sys.modules:")
2793 `(("python-numpy" ,python2-numpy)
2794 ("python-bx-python" ,python2-bx-python)
2795 ("python-networkx" ,python2-networkx)
2796 ("python-scipy" ,python2-scipy)
2797 ("python-pbcore" ,python2-pbcore)
2798 ("python-h5py" ,python2-h5py)))
2800 `(("python-cython" ,python2-cython)
2801 ("python-nose" ,python2-nose)
2802 ("python-setuptools" ,python2-setuptools)))
2803 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
2804 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
2806 "pbtranscript-tofu contains scripts to analyze transcriptome data
2807 generated using the PacBio Iso-Seq protocol.")
2808 (license license:bsd-3))))
2810 (define-public pyicoteo
2817 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
2818 "pyicoteo/get/v" version ".tar.bz2"))
2819 (file-name (string-append name "-" version ".tar.bz2"))
2822 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
2823 (build-system python-build-system)
2825 `(#:python ,python-2 ; does not work with Python 3
2826 #:tests? #f)) ; there are no tests
2828 `(("python2-matplotlib" ,python2-matplotlib)))
2829 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
2830 (synopsis "Analyze high-throughput genetic sequencing data")
2832 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
2833 sequencing data. It works with genomic coordinates. There are currently six
2834 different command-line tools:
2837 @item pyicoregion: for generating exploratory regions automatically;
2838 @item pyicoenrich: for differential enrichment between two conditions;
2839 @item pyicoclip: for calling CLIP-Seq peaks without a control;
2840 @item pyicos: for genomic coordinates manipulation;
2841 @item pyicoller: for peak calling on punctuated ChIP-Seq;
2842 @item pyicount: to count how many reads from N experiment files overlap in a
2844 @item pyicotrocol: to combine operations from pyicoteo.
2846 (license license:gpl3+)))
2848 (define-public prodigal
2855 "https://github.com/hyattpd/Prodigal/archive/v"
2857 (file-name (string-append name "-" version ".tar.gz"))
2860 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
2861 (build-system gnu-build-system)
2863 `(#:tests? #f ;no check target
2864 #:make-flags (list (string-append "INSTALLDIR="
2865 (assoc-ref %outputs "out")
2868 (modify-phases %standard-phases
2869 (delete 'configure))))
2870 (home-page "http://prodigal.ornl.gov")
2871 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
2873 "Prodigal runs smoothly on finished genomes, draft genomes, and
2874 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
2875 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
2876 partial genes, and identifies translation initiation sites.")
2877 (license license:gpl3+)))
2887 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
2890 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
2891 (patches (search-patches "rsem-makefile.patch"))
2892 (modules '((guix build utils)))
2895 ;; remove bundled copy of boost
2896 (delete-file-recursively "boost")
2898 (build-system gnu-build-system)
2900 `(#:tests? #f ;no "check" target
2902 (modify-phases %standard-phases
2903 ;; No "configure" script.
2904 ;; Do not build bundled samtools library.
2907 (substitute* "Makefile"
2908 (("^all : sam/libbam.a") "all : "))
2911 (lambda* (#:key outputs #:allow-other-keys)
2912 (let* ((out (string-append (assoc-ref outputs "out")))
2913 (bin (string-append out "/bin/"))
2914 (perl (string-append out "/lib/perl5/site_perl")))
2917 (for-each (lambda (file)
2919 (string-append bin (basename file))))
2920 (find-files "." "rsem-.*"))
2921 (copy-file "rsem_perl_utils.pm"
2922 (string-append perl "/rsem_perl_utils.pm")))
2925 'install 'wrap-program
2926 (lambda* (#:key outputs #:allow-other-keys)
2927 (let ((out (assoc-ref outputs "out")))
2928 (for-each (lambda (prog)
2929 (wrap-program (string-append out "/bin/" prog)
2930 `("PERL5LIB" ":" prefix
2931 (,(string-append out "/lib/perl5/site_perl")))))
2932 '("rsem-plot-transcript-wiggles"
2933 "rsem-calculate-expression"
2934 "rsem-generate-ngvector"
2936 "rsem-prepare-reference")))
2940 ("ncurses" ,ncurses)
2943 ("samtools" ,samtools-0.1)
2945 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
2946 (synopsis "Estimate gene expression levels from RNA-Seq data")
2948 "RSEM is a software package for estimating gene and isoform expression
2949 levels from RNA-Seq data. The RSEM package provides a user-friendly
2950 interface, supports threads for parallel computation of the EM algorithm,
2951 single-end and paired-end read data, quality scores, variable-length reads and
2952 RSPD estimation. In addition, it provides posterior mean and 95% credibility
2953 interval estimates for expression levels. For visualization, it can generate
2954 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
2955 (license license:gpl3+)))
2957 (define-public rseqc
2965 (string-append "mirror://sourceforge/rseqc/"
2966 version "/RSeQC-" version ".tar.gz"))
2968 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
2969 (modules '((guix build utils)))
2972 ;; remove bundled copy of pysam
2973 (delete-file-recursively "lib/pysam")
2974 (substitute* "setup.py"
2975 ;; remove dependency on outdated "distribute" module
2976 (("^from distribute_setup import use_setuptools") "")
2977 (("^use_setuptools\\(\\)") "")
2978 ;; do not use bundled copy of pysam
2979 (("^have_pysam = False") "have_pysam = True"))))))
2980 (build-system python-build-system)
2981 (arguments `(#:python ,python-2))
2983 `(("python-cython" ,python2-cython)
2984 ("python-pysam" ,python2-pysam)
2985 ("python-numpy" ,python2-numpy)
2986 ("python-setuptools" ,python2-setuptools)
2989 `(("python-nose" ,python2-nose)))
2990 (home-page "http://rseqc.sourceforge.net/")
2991 (synopsis "RNA-seq quality control package")
2993 "RSeQC provides a number of modules that can comprehensively evaluate
2994 high throughput sequence data, especially RNA-seq data. Some basic modules
2995 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
2996 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
2997 distribution, coverage uniformity, strand specificity, etc.")
2998 (license license:gpl3+)))
3000 (define-public samtools
3008 (string-append "mirror://sourceforge/samtools/"
3009 version "/samtools-" version ".tar.bz2"))
3012 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
3013 (build-system gnu-build-system)
3015 `(#:modules ((ice-9 ftw)
3017 (guix build gnu-build-system)
3019 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
3020 #:configure-flags (list "--with-ncurses")
3023 'unpack 'patch-tests
3025 (substitute* "test/test.pl"
3026 ;; The test script calls out to /bin/bash
3027 (("/bin/bash") (which "bash")))
3030 'install 'install-library
3031 (lambda* (#:key outputs #:allow-other-keys)
3032 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
3033 (install-file "libbam.a" lib)))
3035 'install 'install-headers
3036 (lambda* (#:key outputs #:allow-other-keys)
3037 (let ((include (string-append (assoc-ref outputs "out")
3038 "/include/samtools/")))
3039 (for-each (lambda (file)
3040 (install-file file include))
3041 (scandir "." (lambda (name) (string-match "\\.h$" name))))
3043 %standard-phases)))))
3044 (native-inputs `(("pkg-config" ,pkg-config)))
3045 (inputs `(("ncurses" ,ncurses)
3049 (home-page "http://samtools.sourceforge.net")
3050 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
3052 "Samtools implements various utilities for post-processing nucleotide
3053 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
3054 variant calling (in conjunction with bcftools), and a simple alignment
3056 (license license:expat)))
3058 (define-public samtools-0.1
3059 ;; This is the most recent version of the 0.1 line of samtools. The input
3060 ;; and output formats differ greatly from that used and produced by samtools
3061 ;; 1.x and is still used in many bioinformatics pipelines.
3062 (package (inherit samtools)
3068 (string-append "mirror://sourceforge/samtools/"
3069 version "/samtools-" version ".tar.bz2"))
3071 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
3073 `(#:tests? #f ;no "check" target
3074 ,@(substitute-keyword-arguments (package-arguments samtools)
3075 ((#:make-flags flags)
3076 `(cons "LIBCURSES=-lncurses" ,flags))
3078 `(modify-phases ,phases
3080 (lambda* (#:key outputs #:allow-other-keys)
3081 (let ((bin (string-append
3082 (assoc-ref outputs "out") "/bin")))
3084 (copy-file "samtools"
3085 (string-append bin "/samtools")))))
3086 (delete 'patch-tests)
3087 (delete 'configure))))))))
3089 (define-public mosaik
3090 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
3095 ;; There are no release tarballs nor tags.
3098 (url "https://github.com/wanpinglee/MOSAIK.git")
3100 (file-name (string-append name "-" version))
3103 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
3104 (build-system gnu-build-system)
3106 `(#:tests? #f ; no tests
3107 #:make-flags (list "CC=gcc")
3109 (modify-phases %standard-phases
3111 (lambda _ (chdir "src") #t))
3113 (lambda* (#:key outputs #:allow-other-keys)
3114 (let ((bin (string-append (assoc-ref outputs "out")
3117 (copy-recursively "../bin" bin)
3122 (supported-systems '("x86_64-linux"))
3123 (home-page "https://code.google.com/p/mosaik-aligner/")
3124 (synopsis "Map nucleotide sequence reads to reference genomes")
3126 "MOSAIK is a program for mapping second and third-generation sequencing
3127 reads to a reference genome. MOSAIK can align reads generated by all the
3128 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
3129 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
3130 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
3131 ;; code released into the public domain:
3132 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
3133 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
3134 (license (list license:gpl2+ license:public-domain)))))
3136 (define-public ngs-sdk
3144 (string-append "https://github.com/ncbi/ngs/archive/"
3146 (file-name (string-append name "-" version ".tar.gz"))
3149 "15074fdi94c6pjy83hhk22r86kfvzpaz2i07h3rqg9yy6x3w0pk2"))))
3150 (build-system gnu-build-system)
3152 `(#:parallel-build? #f ; not supported
3153 #:tests? #f ; no "check" target
3157 (lambda* (#:key outputs #:allow-other-keys)
3158 (let ((out (assoc-ref outputs "out")))
3159 ;; The 'configure' script doesn't recognize things like
3160 ;; '--enable-fast-install'.
3161 (zero? (system* "./configure"
3162 (string-append "--build-prefix=" (getcwd) "/build")
3163 (string-append "--prefix=" out)))))
3166 (lambda _ (chdir "ngs-sdk") #t)
3167 %standard-phases))))
3168 (native-inputs `(("perl" ,perl)))
3169 ;; According to the test
3170 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
3171 ;; in ngs-sdk/setup/konfigure.perl
3172 (supported-systems '("i686-linux" "x86_64-linux"))
3173 (home-page "https://github.com/ncbi/ngs")
3174 (synopsis "API for accessing Next Generation Sequencing data")
3176 "NGS is a domain-specific API for accessing reads, alignments and pileups
3177 produced from Next Generation Sequencing. The API itself is independent from
3178 any particular back-end implementation, and supports use of multiple back-ends
3180 (license license:public-domain)))
3182 (define-public java-ngs
3183 (package (inherit ngs-sdk)
3186 `(,@(substitute-keyword-arguments
3187 `(#:modules ((guix build gnu-build-system)
3191 ,@(package-arguments ngs-sdk))
3193 `(modify-phases ,phases
3194 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
3196 `(("jdk" ,icedtea "jdk")
3197 ("ngs-sdk" ,ngs-sdk)))
3198 (synopsis "Java bindings for NGS SDK")))
3200 (define-public ncbi-vdb
3208 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
3210 (file-name (string-append name "-" version ".tar.gz"))
3213 "0hay5hy8ynva3mi5wbn4wmq1q23qwxc3aqzbb86hg3x4f1r73270"))))
3214 (build-system gnu-build-system)
3216 `(#:parallel-build? #f ; not supported
3217 #:tests? #f ; no "check" target
3221 (lambda* (#:key inputs outputs #:allow-other-keys)
3222 (let ((out (assoc-ref outputs "out")))
3223 ;; Override include path for libmagic
3224 (substitute* "setup/package.prl"
3225 (("name => 'magic', Include => '/usr/include'")
3226 (string-append "name=> 'magic', Include => '"
3227 (assoc-ref inputs "libmagic")
3230 ;; Install kdf5 library (needed by sra-tools)
3231 (substitute* "build/Makefile.install"
3232 (("LIBRARIES_TO_INSTALL =")
3233 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
3235 ;; The 'configure' script doesn't recognize things like
3236 ;; '--enable-fast-install'.
3239 (string-append "--build-prefix=" (getcwd) "/build")
3240 (string-append "--prefix=" (assoc-ref outputs "out"))
3241 (string-append "--debug")
3242 (string-append "--with-xml2-prefix="
3243 (assoc-ref inputs "libxml2"))
3244 (string-append "--with-ngs-sdk-prefix="
3245 (assoc-ref inputs "ngs-sdk"))
3246 (string-append "--with-ngs-java-prefix="
3247 (assoc-ref inputs "java-ngs"))
3248 (string-append "--with-hdf5-prefix="
3249 (assoc-ref inputs "hdf5"))))))
3251 'install 'install-interfaces
3252 (lambda* (#:key outputs #:allow-other-keys)
3253 ;; Install interface libraries. On i686 the interface libraries
3254 ;; are installed to "linux/gcc/i386", so we need to use the Linux
3255 ;; architecture name ("i386") instead of the target system prefix
3257 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
3258 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
3259 ,(system->linux-architecture
3260 (or (%current-target-system)
3263 (string-append (assoc-ref outputs "out")
3265 ;; Install interface headers
3266 (copy-recursively "interfaces"
3267 (string-append (assoc-ref outputs "out")
3269 %standard-phases))))
3271 `(("libxml2" ,libxml2)
3272 ("ngs-sdk" ,ngs-sdk)
3273 ("java-ngs" ,java-ngs)
3276 (native-inputs `(("perl" ,perl)))
3277 (home-page "https://github.com/ncbi/ncbi-vdb")
3278 (synopsis "Database engine for genetic information")
3280 "The NCBI-VDB library implements a highly compressed columnar data
3281 warehousing engine that is most often used to store genetic information.
3282 Databases are stored in a portable image within the file system, and can be
3283 accessed/downloaded on demand across HTTP.")
3284 (license license:public-domain)))
3286 (define-public plink
3294 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
3295 version "-src.zip"))
3297 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
3298 (patches (search-patches "plink-1.07-unclobber-i.patch"))))
3299 (build-system gnu-build-system)
3301 '(#:tests? #f ;no "check" target
3302 #:make-flags (list (string-append "LIB_LAPACK="
3303 (assoc-ref %build-inputs "lapack")
3304 "/lib/liblapack.so")
3307 ;; disable phoning home
3310 (modify-phases %standard-phases
3311 ;; no "configure" script
3314 (lambda* (#:key outputs #:allow-other-keys)
3315 (let ((bin (string-append (assoc-ref outputs "out")
3317 (install-file "plink" bin)
3321 ("lapack" ,lapack)))
3323 `(("unzip" ,unzip)))
3324 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
3325 (synopsis "Whole genome association analysis toolset")
3327 "PLINK is a whole genome association analysis toolset, designed to
3328 perform a range of basic, large-scale analyses in a computationally efficient
3329 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
3330 so there is no support for steps prior to this (e.g. study design and
3331 planning, generating genotype or CNV calls from raw data). Through
3332 integration with gPLINK and Haploview, there is some support for the
3333 subsequent visualization, annotation and storage of results.")
3334 ;; Code is released under GPLv2, except for fisher.h, which is under
3336 (license (list license:gpl2 license:lgpl2.1+))))
3338 (define-public smithlab-cpp
3339 (let ((revision "1")
3340 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
3342 (name "smithlab-cpp")
3343 (version (string-append "0." revision "." (string-take commit 7)))
3347 (url "https://github.com/smithlabcode/smithlab_cpp.git")
3349 (file-name (string-append name "-" version "-checkout"))
3352 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
3353 (build-system gnu-build-system)
3355 `(#:modules ((guix build gnu-build-system)
3358 #:tests? #f ;no "check" target
3360 (modify-phases %standard-phases
3361 (add-after 'unpack 'use-samtools-headers
3363 (substitute* '("SAM.cpp"
3365 (("sam.h") "samtools/sam.h"))
3368 (lambda* (#:key outputs #:allow-other-keys)
3369 (let* ((out (assoc-ref outputs "out"))
3370 (lib (string-append out "/lib"))
3371 (include (string-append out "/include/smithlab-cpp")))
3374 (for-each (cut install-file <> lib)
3375 (find-files "." "\\.o$"))
3376 (for-each (cut install-file <> include)
3377 (find-files "." "\\.hpp$")))
3379 (delete 'configure))))
3381 `(("samtools" ,samtools-0.1)
3383 (home-page "https://github.com/smithlabcode/smithlab_cpp")
3384 (synopsis "C++ helper library for functions used in Smith lab projects")
3386 "Smithlab CPP is a C++ library that includes functions used in many of
3387 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
3388 structures, classes for genomic regions, mapped sequencing reads, etc.")
3389 (license license:gpl3+))))
3391 (define-public preseq
3397 (uri (string-append "https://github.com/smithlabcode/"
3398 "preseq/archive/v" version ".tar.gz"))
3399 (file-name (string-append name "-" version ".tar.gz"))
3401 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
3402 (modules '((guix build utils)))
3404 ;; Remove bundled samtools.
3405 '(delete-file-recursively "samtools"))))
3406 (build-system gnu-build-system)
3408 `(#:tests? #f ;no "check" target
3410 (modify-phases %standard-phases
3411 (delete 'configure))
3413 (list (string-append "PREFIX="
3414 (assoc-ref %outputs "out"))
3415 (string-append "LIBBAM="
3416 (assoc-ref %build-inputs "samtools")
3418 (string-append "SMITHLAB_CPP="
3419 (assoc-ref %build-inputs "smithlab-cpp")
3422 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
3425 ("samtools" ,samtools-0.1)
3426 ("smithlab-cpp" ,smithlab-cpp)
3428 (home-page "http://smithlabresearch.org/software/preseq/")
3429 (synopsis "Program for analyzing library complexity")
3431 "The preseq package is aimed at predicting and estimating the complexity
3432 of a genomic sequencing library, equivalent to predicting and estimating the
3433 number of redundant reads from a given sequencing depth and how many will be
3434 expected from additional sequencing using an initial sequencing experiment.
3435 The estimates can then be used to examine the utility of further sequencing,
3436 optimize the sequencing depth, or to screen multiple libraries to avoid low
3437 complexity samples.")
3438 (license license:gpl3+)))
3440 (define-public python-screed
3442 (name "python-screed")
3447 (uri (pypi-uri "screed" version))
3450 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
3451 (build-system python-build-system)
3454 (modify-phases %standard-phases
3457 (setenv "PYTHONPATH"
3458 (string-append (getenv "PYTHONPATH") ":."))
3459 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
3461 `(("python-nose" ,python-nose)))
3463 `(("python-bz2file" ,python-bz2file)))
3464 (home-page "http://github.com/dib-lab/screed/")
3465 (synopsis "Short read sequence database utilities")
3466 (description "Screed parses FASTA and FASTQ files and generates databases.
3467 Values such as sequence name, sequence description, sequence quality and the
3468 sequence itself can be retrieved from these databases.")
3469 (license license:bsd-3)))
3471 (define-public python2-screed
3472 (let ((base (package-with-python2 (strip-python2-variant python-screed))))
3475 (native-inputs `(("python2-setuptools" ,python2-setuptools)
3476 ,@(package-native-inputs base))))))
3478 (define-public sra-tools
3486 (string-append "https://github.com/ncbi/sra-tools/archive/"
3488 (file-name (string-append name "-" version ".tar.gz"))
3491 "0q93qg744x787d08qmjmdafki1wkbvkdwynayjnjd454gkd26jl5"))))
3492 (build-system gnu-build-system)
3494 `(#:parallel-build? #f ; not supported
3495 #:tests? #f ; no "check" target
3499 (lambda* (#:key inputs outputs #:allow-other-keys)
3500 ;; The build system expects a directory containing the sources and
3501 ;; raw build output of ncbi-vdb, including files that are not
3502 ;; installed. Since we are building against an installed version of
3503 ;; ncbi-vdb, the following modifications are needed.
3504 (substitute* "setup/konfigure.perl"
3505 ;; Make the configure script look for the "ilib" directory of
3506 ;; "ncbi-vdb" without first checking for the existence of a
3507 ;; matching library in its "lib" directory.
3508 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
3509 "my $f = File::Spec->catdir($ilibdir, $ilib);")
3510 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
3511 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
3512 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
3514 ;; The 'configure' script doesn't recognize things like
3515 ;; '--enable-fast-install'.
3518 (string-append "--build-prefix=" (getcwd) "/build")
3519 (string-append "--prefix=" (assoc-ref outputs "out"))
3520 (string-append "--debug")
3521 (string-append "--with-fuse-prefix="
3522 (assoc-ref inputs "fuse"))
3523 (string-append "--with-magic-prefix="
3524 (assoc-ref inputs "libmagic"))
3525 ;; TODO: building with libxml2 fails with linker errors
3526 ;; (string-append "--with-xml2-prefix="
3527 ;; (assoc-ref inputs "libxml2"))
3528 (string-append "--with-ncbi-vdb-sources="
3529 (assoc-ref inputs "ncbi-vdb"))
3530 (string-append "--with-ncbi-vdb-build="
3531 (assoc-ref inputs "ncbi-vdb"))
3532 (string-append "--with-ngs-sdk-prefix="
3533 (assoc-ref inputs "ngs-sdk"))
3534 (string-append "--with-hdf5-prefix="
3535 (assoc-ref inputs "hdf5")))))
3537 (native-inputs `(("perl" ,perl)))
3539 `(("ngs-sdk" ,ngs-sdk)
3540 ("ncbi-vdb" ,ncbi-vdb)
3545 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
3546 (synopsis "Tools and libraries for reading and writing sequencing data")
3548 "The SRA Toolkit from NCBI is a collection of tools and libraries for
3549 reading of sequencing files from the Sequence Read Archive (SRA) database and
3550 writing files into the .sra format.")
3551 (license license:public-domain)))
3553 (define-public seqan
3559 (uri (string-append "http://packages.seqan.de/seqan-library/"
3560 "seqan-library-" version ".tar.bz2"))
3563 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
3564 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
3565 ;; makes sense to split the outputs.
3566 (outputs '("out" "doc"))
3567 (build-system trivial-build-system)
3569 `(#:modules ((guix build utils))
3572 (use-modules (guix build utils))
3573 (let ((tar (assoc-ref %build-inputs "tar"))
3574 (bzip (assoc-ref %build-inputs "bzip2"))
3575 (out (assoc-ref %outputs "out"))
3576 (doc (assoc-ref %outputs "doc")))
3577 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
3578 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
3579 (chdir (string-append "seqan-library-" ,version))
3580 (copy-recursively "include" (string-append out "/include"))
3581 (copy-recursively "share" (string-append doc "/share"))))))
3583 `(("source" ,source)
3586 (home-page "http://www.seqan.de")
3587 (synopsis "Library for nucleotide sequence analysis")
3589 "SeqAn is a C++ library of efficient algorithms and data structures for
3590 the analysis of sequences with the focus on biological data. It contains
3591 algorithms and data structures for string representation and their
3592 manipulation, online and indexed string search, efficient I/O of
3593 bioinformatics file formats, sequence alignment, and more.")
3594 (license license:bsd-3)))
3596 (define-public seqmagick
3604 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
3608 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
3609 (build-system python-build-system)
3611 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
3612 `(#:python ,python-2
3614 (modify-phases %standard-phases
3615 ;; Current test in setup.py does not work as of 0.6.1,
3616 ;; so use nose to run tests instead for now. See
3617 ;; https://github.com/fhcrc/seqmagick/issues/55
3618 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
3620 `(("python-biopython" ,python2-biopython)))
3622 `(("python-setuptools" ,python2-setuptools)
3623 ("python-nose" ,python2-nose)))
3624 (home-page "http://github.com/fhcrc/seqmagick")
3625 (synopsis "Tools for converting and modifying sequence files")
3627 "Bioinformaticians often have to convert sequence files between formats
3628 and do little manipulations on them, and it's not worth writing scripts for
3629 that. Seqmagick is a utility to expose the file format conversion in
3630 BioPython in a convenient way. Instead of having a big mess of scripts, there
3631 is one that takes arguments.")
3632 (license license:gpl3)))
3634 (define-public snap-aligner
3636 (name "snap-aligner")
3637 (version "1.0beta.18")
3641 "https://github.com/amplab/snap/archive/v"
3643 (file-name (string-append name "-" version ".tar.gz"))
3646 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
3647 (build-system gnu-build-system)
3650 (modify-phases %standard-phases
3652 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
3654 (lambda* (#:key outputs #:allow-other-keys)
3655 (let* ((out (assoc-ref outputs "out"))
3656 (bin (string-append out "/bin")))
3658 (install-file "snap-aligner" bin)
3659 (install-file "SNAPCommand" bin)
3663 (home-page "http://snap.cs.berkeley.edu/")
3664 (synopsis "Short read DNA sequence aligner")
3666 "SNAP is a fast and accurate aligner for short DNA reads. It is
3667 optimized for modern read lengths of 100 bases or higher, and takes advantage
3668 of these reads to align data quickly through a hash-based indexing scheme.")
3669 (license license:asl2.0)))
3671 (define-public sortmerna
3679 "https://github.com/biocore/sortmerna/archive/"
3681 (file-name (string-append name "-" version ".tar.gz"))
3684 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
3685 (build-system gnu-build-system)
3686 (outputs '("out" ;for binaries
3687 "db")) ;for sequence databases
3690 (modify-phases %standard-phases
3692 (lambda* (#:key outputs #:allow-other-keys)
3693 (let* ((out (assoc-ref outputs "out"))
3694 (bin (string-append out "/bin"))
3695 (db (assoc-ref outputs "db"))
3697 (string-append db "/share/sortmerna/rRNA_databases")))
3698 (install-file "sortmerna" bin)
3699 (install-file "indexdb_rna" bin)
3700 (for-each (lambda (file)
3701 (install-file file share))
3702 (find-files "rRNA_databases" ".*fasta"))
3706 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
3707 (synopsis "Biological sequence analysis tool for NGS reads")
3709 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
3710 and operational taxonomic unit (OTU) picking of next generation
3711 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
3712 allows for fast and sensitive analyses of nucleotide sequences. The main
3713 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
3714 (license license:lgpl3)))
3722 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
3724 (file-name (string-append name "-" version ".tar.gz"))
3727 "0wzcfhkg10apnh0y73xlarfa79xxwxdizicbdl11wb48awk44iq4"))
3728 (modules '((guix build utils)))
3731 (substitute* "source/Makefile"
3733 ;; Remove pre-built binaries and bundled htslib sources.
3734 (delete-file-recursively "bin/MacOSX_x86_64")
3735 (delete-file-recursively "bin/Linux_x86_64")
3736 (delete-file-recursively "source/htslib")
3738 (build-system gnu-build-system)
3740 '(#:tests? #f ;no check target
3741 #:make-flags '("STAR")
3743 (modify-phases %standard-phases
3744 (add-after 'unpack 'enter-source-dir
3745 (lambda _ (chdir "source") #t))
3746 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
3748 (substitute* "Makefile"
3749 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
3751 (substitute* '("BAMfunctions.cpp"
3756 "bamRemoveDuplicates.cpp")
3757 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
3758 (string-append "#include <" header ">")))
3759 (substitute* "IncludeDefine.h"
3760 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
3761 (string-append "<" header ">")))
3764 (lambda* (#:key outputs #:allow-other-keys)
3765 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3766 (install-file "STAR" bin))
3768 (delete 'configure))))
3770 `(("vim" ,vim))) ; for xxd
3772 `(("htslib" ,htslib)
3774 (home-page "https://github.com/alexdobin/STAR")
3775 (synopsis "Universal RNA-seq aligner")
3777 "The Spliced Transcripts Alignment to a Reference (STAR) software is
3778 based on a previously undescribed RNA-seq alignment algorithm that uses
3779 sequential maximum mappable seed search in uncompressed suffix arrays followed
3780 by seed clustering and stitching procedure. In addition to unbiased de novo
3781 detection of canonical junctions, STAR can discover non-canonical splices and
3782 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
3784 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
3785 (license license:gpl3+)))
3787 (define-public subread
3790 (version "1.4.6-p2")
3794 "mirror://sourceforge/subread/subread-"
3795 version "-source.tar.gz"))
3798 "06sv9mpcsdj6p68y15d6gi70lca3lxmzk0dn61hg0kfsa7rxmsr3"))))
3799 (build-system gnu-build-system)
3801 `(#:tests? #f ;no "check" target
3802 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
3803 ;; optimizations by default, so we override these flags such that x86_64
3804 ;; flags are only added when the build target is an x86_64 system.
3806 (list (let ((system ,(or (%current-target-system)
3808 (flags '("-ggdb" "-fomit-frame-pointer"
3809 "-ffast-math" "-funroll-loops"
3810 "-fmessage-length=0"
3811 "-O9" "-Wall" "-DMAKE_FOR_EXON"
3813 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
3814 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
3815 (if (string-prefix? "x86_64" system)
3816 (string-append "CCFLAGS=" (string-join (append flags flags64)))
3817 (string-append "CCFLAGS=" (string-join flags))))
3818 "-f" "Makefile.Linux"
3819 "CC=gcc ${CCFLAGS}")
3823 (lambda _ (chdir "src") #t)
3826 (lambda* (#:key outputs #:allow-other-keys)
3827 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3829 (copy-recursively "../bin" bin)))
3830 ;; no "configure" script
3831 (alist-delete 'configure %standard-phases)))))
3832 (inputs `(("zlib" ,zlib)))
3833 (home-page "http://bioinf.wehi.edu.au/subread-package/")
3834 (synopsis "Tool kit for processing next-gen sequencing data")
3836 "The subread package contains the following tools: subread aligner, a
3837 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
3838 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
3839 features; exactSNP: a SNP caller that discovers SNPs by testing signals
3840 against local background noises.")
3841 (license license:gpl3+)))
3843 (define-public stringtie
3849 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
3850 "stringtie-" version ".tar.gz"))
3853 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
3854 (modules '((guix build utils)))
3857 (delete-file-recursively "samtools-0.1.18")
3859 (build-system gnu-build-system)
3861 `(#:tests? #f ;no test suite
3863 (modify-phases %standard-phases
3864 ;; no configure script
3866 (add-before 'build 'use-system-samtools
3868 (substitute* "Makefile"
3869 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
3871 (substitute* '("gclib/GBam.h"
3873 (("#include \"(bam|sam|kstring).h\"" _ header)
3874 (string-append "#include <samtools/" header ".h>")))
3877 (lambda* (#:key outputs #:allow-other-keys)
3878 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3879 (install-file "stringtie" bin)
3882 `(("samtools" ,samtools-0.1)
3884 (home-page "http://ccb.jhu.edu/software/stringtie/")
3885 (synopsis "Transcript assembly and quantification for RNA-Seq data")
3887 "StringTie is a fast and efficient assembler of RNA-Seq sequence
3888 alignments into potential transcripts. It uses a novel network flow algorithm
3889 as well as an optional de novo assembly step to assemble and quantitate
3890 full-length transcripts representing multiple splice variants for each gene
3891 locus. Its input can include not only the alignments of raw reads used by
3892 other transcript assemblers, but also alignments of longer sequences that have
3893 been assembled from those reads. To identify differentially expressed genes
3894 between experiments, StringTie's output can be processed either by the
3895 Cuffdiff or Ballgown programs.")
3896 (license license:artistic2.0)))
3898 (define-public vcftools
3905 "https://github.com/vcftools/vcftools/releases/download/v"
3906 version "/vcftools-" version ".tar.gz"))
3909 "10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
3910 (build-system gnu-build-system)
3912 `(#:tests? #f ; no "check" target
3914 "CFLAGS=-O2" ; override "-m64" flag
3915 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3916 (string-append "MANDIR=" (assoc-ref %outputs "out")
3917 "/share/man/man1"))))
3919 `(("pkg-config" ,pkg-config)))
3923 (home-page "https://vcftools.github.io/")
3924 (synopsis "Tools for working with VCF files")
3926 "VCFtools is a program package designed for working with VCF files, such
3927 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
3928 provide easily accessible methods for working with complex genetic variation
3929 data in the form of VCF files.")
3930 ;; The license is declared as LGPLv3 in the README and
3931 ;; at https://vcftools.github.io/license.html
3932 (license license:lgpl3)))
3934 (define-public r-vegan
3941 (uri (cran-uri "vegan" version))
3944 "10cygzkyg2m0y054ygivqxrkvqz792qsg6bmbdfzaqq37qv4wc7z"))))
3945 (build-system r-build-system)
3948 (modify-phases %standard-phases
3949 (add-after 'unpack 'revert-test-deletion
3950 ;; The distributed sources do not include tests with the CRAN
3951 ;; package. Here we revert the commit
3952 ;; `591d0e8ba1deaaf82445474ec6619c0b43db4e63' which deletes these
3953 ;; tests. There are plans to not delete tests in future as
3954 ;; documented at https://github.com/vegandevs/vegan/issues/181.
3955 (lambda* (#:key inputs #:allow-other-keys)
3957 (system* "patch" "-R" "-p1" "-i"
3958 (assoc-ref inputs "r-vegan-delete-tests-patch"))))))))
3960 `(("gfortran" ,gfortran)
3961 ("r-knitr" ,r-knitr)
3962 ("r-vegan-delete-tests-patch"
3966 "https://github.com/vegandevs/vegan/commit/"
3967 "591d0e8ba1deaaf82445474ec6619c0b43db4e63.patch"))
3970 "0b1bi7y4jjdl3ph721vm9apm51dr2z9piwvhy4355sf2b4kyyj5a"))))))
3972 `(("r-cluster" ,r-cluster)
3973 ("r-lattice" ,r-lattice)
3975 ("r-permute" ,r-permute)))
3976 (home-page "https://cran.r-project.org/web/packages/vegan")
3977 (synopsis "Functions for community ecology")
3979 "The vegan package provides tools for descriptive community ecology. It
3980 has most basic functions of diversity analysis, community ordination and
3981 dissimilarity analysis. Most of its multivariate tools can be used for other
3982 data types as well.")
3983 (license license:gpl2+)))
3985 (define-public vsearch
3993 "https://github.com/torognes/vsearch/archive/v"
3995 (file-name (string-append name "-" version ".tar.gz"))
3998 "1sd57abgx077icqrbj36jq9q7pdpzc6dbics2pn1555kisq2jhfh"))
3999 (modules '((guix build utils)))
4002 ;; Remove bundled cityhash and '-mtune=native'.
4003 (substitute* "src/Makefile.am"
4004 (("^AM_CXXFLAGS=-I\\$\\{srcdir\\}/cityhash \
4005 -O3 -mtune=native -Wall -Wsign-compare")
4006 (string-append "AM_CXXFLAGS=-lcityhash"
4007 " -O3 -Wall -Wsign-compare"))
4008 (("^__top_builddir__bin_vsearch_SOURCES = city.h \\\\")
4009 "__top_builddir__bin_vsearch_SOURCES = \\")
4010 (("^city.h \\\\") "\\")
4011 (("^citycrc.h \\\\") "\\")
4012 (("^libcityhash_a.*") "")
4013 (("noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a \
4015 "noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a")
4016 (("__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
4017 libcpu_sse2.a libcityhash.a")
4018 "__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
4019 libcpu_sse2.a -lcityhash"))
4020 (substitute* "src/vsearch.h"
4021 (("^\\#include \"city.h\"") "#include <city.h>")
4022 (("^\\#include \"citycrc.h\"") "#include <citycrc.h>"))
4023 (delete-file "src/city.h")
4024 (delete-file "src/citycrc.h")
4025 (delete-file "src/city.cc")
4027 (build-system gnu-build-system)
4030 (modify-phases %standard-phases
4031 (add-before 'configure 'autogen
4032 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
4036 ("cityhash" ,cityhash)))
4038 `(("autoconf" ,autoconf)
4039 ("automake" ,automake)))
4040 (synopsis "Sequence search tools for metagenomics")
4042 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
4043 dereplication, pairwise alignment, shuffling, subsampling, sorting and
4044 masking. The tool takes advantage of parallelism in the form of SIMD
4045 vectorization as well as multiple threads to perform accurate alignments at
4046 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
4047 Needleman-Wunsch).")
4048 (home-page "https://github.com/torognes/vsearch")
4049 ;; vsearch uses non-portable SSE intrinsics so building fails on other
4051 (supported-systems '("x86_64-linux"))
4052 ;; Dual licensed; also includes public domain source.
4053 (license (list license:gpl3 license:bsd-2))))
4055 (define-public pardre
4062 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
4066 "0zkyjzv4s8q2h5npalhirbk17r5b1h0n2a42mh7njzlf047h9bhy"))))
4067 (build-system gnu-build-system)
4069 `(#:tests? #f ; no tests included
4071 (modify-phases %standard-phases
4074 (lambda* (#:key outputs #:allow-other-keys)
4075 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4077 (install-file "ParDRe" bin)
4080 `(("openmpi" ,openmpi)
4082 (synopsis "Parallel tool to remove duplicate DNA reads")
4084 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
4085 Duplicate reads can be seen as identical or nearly identical sequences with
4086 some mismatches. This tool lets users avoid the analysis of unnecessary
4087 reads, reducing the time of subsequent procedures with the
4088 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
4089 in order to exploit the parallel capabilities of multicore clusters. It is
4090 faster than multithreaded counterparts (end of 2015) for the same number of
4091 cores and, thanks to the message-passing technology, it can be executed on
4093 (home-page "https://sourceforge.net/projects/pardre/")
4094 (license license:gpl3+)))
4096 (define-public ruby-bio-kseq
4098 (name "ruby-bio-kseq")
4103 (uri (rubygems-uri "bio-kseq" version))
4106 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
4107 (build-system ruby-build-system)
4109 `(#:test-target "spec"))
4111 `(("bundler" ,bundler)
4112 ("ruby-rspec" ,ruby-rspec)
4113 ("ruby-rake-compiler" ,ruby-rake-compiler)))
4116 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
4118 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
4119 FASTQ parsing code. It provides a fast iterator over sequences and their
4121 (home-page "https://github.com/gusevfe/bio-kseq")
4122 (license license:expat)))
4124 (define-public bio-locus
4131 (uri (rubygems-uri "bio-locus" version))
4134 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
4135 (build-system ruby-build-system)
4137 `(("ruby-rspec" ,ruby-rspec)))
4138 (synopsis "Tool for fast querying of genome locations")
4140 "Bio-locus is a tabix-like tool for fast querying of genome
4141 locations. Many file formats in bioinformatics contain records that
4142 start with a chromosome name and a position for a SNP, or a start-end
4143 position for indels. Bio-locus allows users to store this chr+pos or
4144 chr+pos+alt information in a database.")
4145 (home-page "https://github.com/pjotrp/bio-locus")
4146 (license license:expat)))
4148 (define-public bio-blastxmlparser
4150 (name "bio-blastxmlparser")
4154 (uri (rubygems-uri "bio-blastxmlparser" version))
4157 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
4158 (build-system ruby-build-system)
4160 `(("ruby-bio-logger" ,ruby-bio-logger)
4161 ("ruby-nokogiri" ,ruby-nokogiri)))
4163 `(("ruby-rspec" ,ruby-rspec)))
4164 (synopsis "Fast big data BLAST XML parser and library")
4166 "Very fast parallel big-data BLAST XML file parser which can be used as
4167 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
4168 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
4169 (home-page "http://github.com/pjotrp/blastxmlparser")
4170 (license license:expat)))
4172 (define-public bioruby
4179 (uri (rubygems-uri "bio" version))
4182 "01k2fyjl5fpx4zn8g6gqiqvsg2j1fgixrs9p03vzxckynxdq3wmc"))))
4183 (build-system ruby-build-system)
4185 `(("ruby-libxml" ,ruby-libxml)))
4187 `(("which" ,which))) ; required for test phase
4190 (modify-phases %standard-phases
4191 (add-before 'build 'patch-test-command
4193 (substitute* '("test/functional/bio/test_command.rb")
4194 (("/bin/sh") (which "sh")))
4195 (substitute* '("test/functional/bio/test_command.rb")
4196 (("/bin/ls") (which "ls")))
4197 (substitute* '("test/functional/bio/test_command.rb")
4198 (("which") (which "which")))
4199 (substitute* '("test/functional/bio/test_command.rb",
4200 "test/data/command/echoarg2.sh")
4201 (("/bin/echo") (which "echo")))
4203 (synopsis "Ruby library, shell and utilities for bioinformatics")
4204 (description "BioRuby comes with a comprehensive set of Ruby development
4205 tools and libraries for bioinformatics and molecular biology. BioRuby has
4206 components for sequence analysis, pathway analysis, protein modelling and
4207 phylogenetic analysis; it supports many widely used data formats and provides
4208 easy access to databases, external programs and public web services, including
4209 BLAST, KEGG, GenBank, MEDLINE and GO.")
4210 (home-page "http://bioruby.org/")
4211 ;; Code is released under Ruby license, except for setup
4212 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
4213 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
4215 (define-public r-acsnminer
4217 (name "r-acsnminer")
4218 (version "0.16.01.29")
4221 (uri (cran-uri "ACSNMineR" version))
4224 "1b1243wkncanm1blkqzicjgzb576vzcg4iwinsgn2xqr7f264amf"))))
4225 (properties `((upstream-name . "ACSNMineR")))
4226 (build-system r-build-system)
4228 `(("r-ggplot2" ,r-ggplot2)
4229 ("r-gridextra" ,r-gridextra)))
4230 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
4231 (synopsis "Gene enrichment analysis")
4233 "This package provides tools to compute and represent gene set enrichment
4234 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
4235 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
4236 enrichment can be run with hypergeometric test or Fisher exact test, and can
4237 use multiple corrections. Visualization of data can be done either by
4238 barplots or heatmaps.")
4239 (license license:gpl2+)))
4241 (define-public r-biocgenerics
4243 (name "r-biocgenerics")
4247 (uri (bioconductor-uri "BiocGenerics" version))
4250 "1jjp48vbph09w5bmc7368gjjywsa1lmzfybpiwlypr60b51vlkp6"))))
4252 `((upstream-name . "BiocGenerics")))
4253 (build-system r-build-system)
4254 (home-page "http://bioconductor.org/packages/BiocGenerics")
4255 (synopsis "S4 generic functions for Bioconductor")
4257 "This package provides S4 generic functions needed by many Bioconductor
4259 (license license:artistic2.0)))
4261 (define-public r-dnacopy
4267 (uri (bioconductor-uri "DNAcopy" version))
4270 "0vwv2mndfjpcjp4sybg75abc7xnx8zyw8zjk717k6xh8c33ymcip"))))
4272 `((upstream-name . "DNAcopy")))
4273 (build-system r-build-system)
4275 `(("gfortran" ,gfortran)))
4276 (home-page "https://bioconductor.org/packages/DNAcopy")
4277 (synopsis "Implementation of a circular binary segmentation algorithm")
4278 (description "This package implements the circular binary segmentation (CBS)
4279 algorithm to segment DNA copy number data and identify genomic regions with
4280 abnormal copy number.")
4281 (license license:gpl2+)))
4283 (define-public r-s4vectors
4285 (name "r-s4vectors")
4289 (uri (bioconductor-uri "S4Vectors" version))
4292 "1mi6lf6pnb9l657igy0vj4yz03yawbr2jhk22l757fzbjc7n9q3b"))))
4294 `((upstream-name . "S4Vectors")))
4295 (build-system r-build-system)
4297 `(("r-biocgenerics" ,r-biocgenerics)))
4298 (home-page "http://bioconductor.org/packages/S4Vectors")
4299 (synopsis "S4 implementation of vectors and lists")
4301 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
4302 classes and a set of generic functions that extend the semantic of ordinary
4303 vectors and lists in R. Package developers can easily implement vector-like
4304 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
4305 In addition, a few low-level concrete subclasses of general interest (e.g.
4306 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
4307 S4Vectors package itself.")
4308 (license license:artistic2.0)))
4310 (define-public r-iranges
4316 (uri (bioconductor-uri "IRanges" version))
4319 "0dz7z0pk8hq79mcgylw920999s08h6j8xrl31rdxhssmi7l8v6vy"))))
4321 `((upstream-name . "IRanges")))
4322 (build-system r-build-system)
4324 `(("r-biocgenerics" ,r-biocgenerics)
4325 ("r-s4vectors" ,r-s4vectors)))
4326 (home-page "http://bioconductor.org/packages/IRanges")
4327 (synopsis "Infrastructure for manipulating intervals on sequences")
4329 "This package provides efficient low-level and highly reusable S4 classes
4330 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
4331 generally, data that can be organized sequentially (formally defined as
4332 @code{Vector} objects), as well as views on these @code{Vector} objects.
4333 Efficient list-like classes are also provided for storing big collections of
4334 instances of the basic classes. All classes in the package use consistent
4335 naming and share the same rich and consistent \"Vector API\" as much as
4337 (license license:artistic2.0)))
4339 (define-public r-genomeinfodb
4341 (name "r-genomeinfodb")
4345 (uri (bioconductor-uri "GenomeInfoDb" version))
4348 "0k4s6z5qj53zkfnyrmcbn3l2nzgm56bhv58rv321j22qa56cpz7d"))))
4350 `((upstream-name . "GenomeInfoDb")))
4351 (build-system r-build-system)
4353 `(("r-biocgenerics" ,r-biocgenerics)
4354 ("r-iranges" ,r-iranges)
4355 ("r-s4vectors" ,r-s4vectors)))
4356 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
4357 (synopsis "Utilities for manipulating chromosome identifiers")
4359 "This package contains data and functions that define and allow
4360 translation between different chromosome sequence naming conventions (e.g.,
4361 \"chr1\" versus \"1\"), including a function that attempts to place sequence
4362 names in their natural, rather than lexicographic, order.")
4363 (license license:artistic2.0)))
4365 (define-public r-variantannotation
4367 (name "r-variantannotation")
4371 (uri (bioconductor-uri "VariantAnnotation" version))
4374 "1jdpdnp7l81xfprba2ykfnj6i64fd84vxaax0wvrz6qahxvnjzyw"))))
4376 `((upstream-name . "VariantAnnotation")))
4380 `(("r-annotationdbi" ,r-annotationdbi)
4381 ("r-biocgenerics" ,r-biocgenerics)
4382 ("r-bsgenome" ,r-bsgenome)
4384 ("r-genomeinfodb" ,r-genomeinfodb)
4385 ("r-genomicfeatures" ,r-genomicfeatures)
4386 ("r-genomicranges" ,r-genomicranges)
4387 ("r-summarizedexperiment" ,r-summarizedexperiment)
4388 ("r-rsamtools" ,r-rsamtools)
4389 ("r-zlibbioc" ,r-zlibbioc)))
4390 (build-system r-build-system)
4391 (home-page "https://bioconductor.org/packages/VariantAnnotation")
4392 (synopsis "Package for annotation of genetic variants")
4393 (description "This R package can annotate variants, compute amino acid
4394 coding changes and predict coding outcomes.")
4395 (license license:artistic2.0)))
4397 (define-public r-xvector
4403 (uri (bioconductor-uri "XVector" version))
4406 "0c9cqjcxxks3an4wiq167h2grxlfyazajn7bmxhbk42zifp8vmqp"))))
4408 `((upstream-name . "XVector")))
4409 (build-system r-build-system)
4412 (modify-phases %standard-phases
4413 (add-after 'unpack 'use-system-zlib
4415 (substitute* "DESCRIPTION"
4416 (("zlibbioc, ") ""))
4417 (substitute* "NAMESPACE"
4418 (("import\\(zlibbioc\\)") ""))
4423 `(("r-biocgenerics" ,r-biocgenerics)
4424 ("r-iranges" ,r-iranges)
4425 ("r-s4vectors" ,r-s4vectors)))
4426 (home-page "http://bioconductor.org/packages/XVector")
4427 (synopsis "Representation and manpulation of external sequences")
4429 "This package provides memory efficient S4 classes for storing sequences
4430 \"externally\" (behind an R external pointer, or on disk).")
4431 (license license:artistic2.0)))
4433 (define-public r-genomicranges
4435 (name "r-genomicranges")
4439 (uri (bioconductor-uri "GenomicRanges" version))
4442 "1iyzg1npl3rnnslwq3h759vf0xhshnn5v801rnlj6bnxzhn9yaqh"))))
4444 `((upstream-name . "GenomicRanges")))
4445 (build-system r-build-system)
4447 `(("r-biocgenerics" ,r-biocgenerics)
4448 ("r-genomeinfodb" ,r-genomeinfodb)
4449 ("r-xvector" ,r-xvector)))
4450 (home-page "http://bioconductor.org/packages/GenomicRanges")
4451 (synopsis "Representation and manipulation of genomic intervals")
4453 "This package provides tools to efficiently represent and manipulate
4454 genomic annotations and alignments is playing a central role when it comes to
4455 analyzing high-throughput sequencing data (a.k.a. NGS data). The
4456 GenomicRanges package defines general purpose containers for storing and
4457 manipulating genomic intervals and variables defined along a genome.")
4458 (license license:artistic2.0)))
4460 (define-public r-biobase
4466 (uri (bioconductor-uri "Biobase" version))
4469 "0q4icv9n5rc2qfkv6k1wjhmfcpzcyr8f45m2z3xharbdv912kl1i"))))
4471 `((upstream-name . "Biobase")))
4472 (build-system r-build-system)
4474 `(("r-biocgenerics" ,r-biocgenerics)))
4475 (home-page "http://bioconductor.org/packages/Biobase")
4476 (synopsis "Base functions for Bioconductor")
4478 "This package provides functions that are needed by many other packages
4479 on Bioconductor or which replace R functions.")
4480 (license license:artistic2.0)))
4482 (define-public r-annotationdbi
4484 (name "r-annotationdbi")
4488 (uri (bioconductor-uri "AnnotationDbi" version))
4491 "0nw6c23098gkjlwlrra4rh1m65azczb31qr01pq81cn5gya1zkr4"))))
4493 `((upstream-name . "AnnotationDbi")))
4494 (build-system r-build-system)
4496 `(("r-biobase" ,r-biobase)
4497 ("r-biocgenerics" ,r-biocgenerics)
4499 ("r-iranges" ,r-iranges)
4500 ("r-rsqlite" ,r-rsqlite)
4501 ("r-s4vectors" ,r-s4vectors)))
4502 (home-page "http://bioconductor.org/packages/AnnotationDbi")
4503 (synopsis "Annotation database interface")
4505 "This package provides user interface and database connection code for
4506 annotation data packages using SQLite data storage.")
4507 (license license:artistic2.0)))
4509 (define-public r-biomart
4515 (uri (bioconductor-uri "biomaRt" version))
4518 "1g0w6an9hkflgyhvq6pmrs92s93qarv23v636b9a4bz771wjvm5v"))))
4520 `((upstream-name . "biomaRt")))
4521 (build-system r-build-system)
4523 `(("r-annotationdbi" ,r-annotationdbi)
4524 ("r-rcurl" ,r-rcurl)
4526 (home-page "http://bioconductor.org/packages/biomaRt")
4527 (synopsis "Interface to BioMart databases")
4529 "biomaRt provides an interface to a growing collection of databases
4530 implementing the @url{BioMart software suite, http://www.biomart.org}. The
4531 package enables retrieval of large amounts of data in a uniform way without
4532 the need to know the underlying database schemas or write complex SQL queries.
4533 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
4534 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
4535 users direct access to a diverse set of data and enable a wide range of
4536 powerful online queries from gene annotation to database mining.")
4537 (license license:artistic2.0)))
4539 (define-public r-biocparallel
4541 (name "r-biocparallel")
4545 (uri (bioconductor-uri "BiocParallel" version))
4548 "0ki5xvb3cwjmlsx81gr8ylk1qy3imlj2dd04mzpvl28x42ay4dqj"))))
4550 `((upstream-name . "BiocParallel")))
4551 (build-system r-build-system)
4553 `(("r-futile-logger" ,r-futile-logger)
4554 ("r-snow" ,r-snow)))
4555 (home-page "http://bioconductor.org/packages/BiocParallel")
4556 (synopsis "Bioconductor facilities for parallel evaluation")
4558 "This package provides modified versions and novel implementation of
4559 functions for parallel evaluation, tailored to use with Bioconductor
4561 (license (list license:gpl2+ license:gpl3+))))
4563 (define-public r-biostrings
4565 (name "r-biostrings")
4569 (uri (bioconductor-uri "Biostrings" version))
4572 "03gyhiz14xy51nzg0glihk1rv19pq4p1aa3y5g23bzcshs67ggj9"))))
4574 `((upstream-name . "Biostrings")))
4575 (build-system r-build-system)
4577 `(("r-biocgenerics" ,r-biocgenerics)
4578 ("r-iranges" ,r-iranges)
4579 ("r-s4vectors" ,r-s4vectors)
4580 ("r-xvector" ,r-xvector)))
4581 (home-page "http://bioconductor.org/packages/Biostrings")
4582 (synopsis "String objects and algorithms for biological sequences")
4584 "This package provides memory efficient string containers, string
4585 matching algorithms, and other utilities, for fast manipulation of large
4586 biological sequences or sets of sequences.")
4587 (license license:artistic2.0)))
4589 (define-public r-rsamtools
4591 (name "r-rsamtools")
4595 (uri (bioconductor-uri "Rsamtools" version))
4598 "0w0drs8cpk8nlazq64ag7nm1w5jd1m8riialivm01hz5zcra7scb"))))
4600 `((upstream-name . "Rsamtools")))
4601 (build-system r-build-system)
4604 (modify-phases %standard-phases
4605 (add-after 'unpack 'use-system-zlib
4607 (substitute* "DESCRIPTION"
4608 (("zlibbioc, ") ""))
4609 (substitute* "NAMESPACE"
4610 (("import\\(zlibbioc\\)") ""))
4615 `(("r-biocgenerics" ,r-biocgenerics)
4616 ("r-biocparallel" ,r-biocparallel)
4617 ("r-biostrings" ,r-biostrings)
4618 ("r-bitops" ,r-bitops)
4619 ("r-genomeinfodb" ,r-genomeinfodb)
4620 ("r-genomicranges" ,r-genomicranges)
4621 ("r-iranges" ,r-iranges)
4622 ("r-s4vectors" ,r-s4vectors)
4623 ("r-xvector" ,r-xvector)))
4624 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
4625 (synopsis "Interface to samtools, bcftools, and tabix")
4627 "This package provides an interface to the 'samtools', 'bcftools', and
4628 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
4629 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
4631 (license license:expat)))
4633 (define-public r-summarizedexperiment
4635 (name "r-summarizedexperiment")
4639 (uri (bioconductor-uri "SummarizedExperiment" version))
4642 "1c81acgw3a0ha5fgapfh9xq8yhryqqf8k259n2dz0mgz1k2d9klg"))))
4644 `((upstream-name . "SummarizedExperiment")))
4645 (build-system r-build-system)
4647 `(("r-biobase" ,r-biobase)
4648 ("r-biocgenerics" ,r-biocgenerics)
4649 ("r-genomeinfodb" ,r-genomeinfodb)
4650 ("r-genomicranges" ,r-genomicranges)
4651 ("r-iranges" ,r-iranges)
4652 ("r-s4vectors" ,r-s4vectors)))
4653 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
4654 (synopsis "Container for representing genomic ranges by sample")
4656 "The SummarizedExperiment container contains one or more assays, each
4657 represented by a matrix-like object of numeric or other mode. The rows
4658 typically represent genomic ranges of interest and the columns represent
4660 (license license:artistic2.0)))
4662 (define-public r-genomicalignments
4664 (name "r-genomicalignments")
4668 (uri (bioconductor-uri "GenomicAlignments" version))
4671 "1y4qgqxq8dax9swgl59m6i7ggjpqrjllgx87b9vwls3z0nf1i6xj"))))
4673 `((upstream-name . "GenomicAlignments")))
4674 (build-system r-build-system)
4676 `(("r-biocgenerics" ,r-biocgenerics)
4677 ("r-biocparallel" ,r-biocparallel)
4678 ("r-biostrings" ,r-biostrings)
4679 ("r-genomeinfodb" ,r-genomeinfodb)
4680 ("r-genomicranges" ,r-genomicranges)
4681 ("r-iranges" ,r-iranges)
4682 ("r-rsamtools" ,r-rsamtools)
4683 ("r-s4vectors" ,r-s4vectors)
4684 ("r-summarizedexperiment" ,r-summarizedexperiment)))
4685 (home-page "http://bioconductor.org/packages/GenomicAlignments")
4686 (synopsis "Representation and manipulation of short genomic alignments")
4688 "This package provides efficient containers for storing and manipulating
4689 short genomic alignments (typically obtained by aligning short reads to a
4690 reference genome). This includes read counting, computing the coverage,
4691 junction detection, and working with the nucleotide content of the
4693 (license license:artistic2.0)))
4695 (define-public r-rtracklayer
4697 (name "r-rtracklayer")
4701 (uri (bioconductor-uri "rtracklayer" version))
4704 "0nrwk1g8b1ymvbgnqniimbvwfq13r01va9rx3b03xj4hpywzy5nv"))))
4705 (build-system r-build-system)
4708 (modify-phases %standard-phases
4709 (add-after 'unpack 'use-system-zlib
4711 (substitute* "DESCRIPTION"
4712 (("zlibbioc, ") ""))
4713 (substitute* "NAMESPACE"
4714 (("import\\(zlibbioc\\)") ""))
4719 `(("r-biocgenerics" ,r-biocgenerics)
4720 ("r-biostrings" ,r-biostrings)
4721 ("r-genomeinfodb" ,r-genomeinfodb)
4722 ("r-genomicalignments" ,r-genomicalignments)
4723 ("r-genomicranges" ,r-genomicranges)
4724 ("r-iranges" ,r-iranges)
4725 ("r-rcurl" ,r-rcurl)
4726 ("r-rsamtools" ,r-rsamtools)
4727 ("r-s4vectors" ,r-s4vectors)
4729 ("r-xvector" ,r-xvector)))
4730 (home-page "http://bioconductor.org/packages/rtracklayer")
4731 (synopsis "R interface to genome browsers and their annotation tracks")
4733 "rtracklayer is an extensible framework for interacting with multiple
4734 genome browsers (currently UCSC built-in) and manipulating annotation tracks
4735 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
4736 built-in). The user may export/import tracks to/from the supported browsers,
4737 as well as query and modify the browser state, such as the current viewport.")
4738 (license license:artistic2.0)))
4740 (define-public r-genomicfeatures
4742 (name "r-genomicfeatures")
4746 (uri (bioconductor-uri "GenomicFeatures" version))
4749 "0ga5a7w8jnnq2k0kc07mshl6cggmbhzh42pzvhnilgl4x3kpbysl"))))
4751 `((upstream-name . "GenomicFeatures")))
4752 (build-system r-build-system)
4754 `(("r-annotationdbi" ,r-annotationdbi)
4755 ("r-biobase" ,r-biobase)
4756 ("r-biocgenerics" ,r-biocgenerics)
4757 ("r-biomart" ,r-biomart)
4758 ("r-biostrings" ,r-biostrings)
4760 ("r-genomeinfodb" ,r-genomeinfodb)
4761 ("r-genomicranges" ,r-genomicranges)
4762 ("r-iranges" ,r-iranges)
4763 ("r-rcurl" ,r-rcurl)
4764 ("r-rsqlite" ,r-rsqlite)
4765 ("r-rtracklayer" ,r-rtracklayer)
4766 ("r-s4vectors" ,r-s4vectors)
4767 ("r-xvector" ,r-xvector)))
4768 (home-page "http://bioconductor.org/packages/GenomicFeatures")
4769 (synopsis "Tools for working with transcript centric annotations")
4771 "This package provides a set of tools and methods for making and
4772 manipulating transcript centric annotations. With these tools the user can
4773 easily download the genomic locations of the transcripts, exons and cds of a
4774 given organism, from either the UCSC Genome Browser or a BioMart
4775 database (more sources will be supported in the future). This information is
4776 then stored in a local database that keeps track of the relationship between
4777 transcripts, exons, cds and genes. Flexible methods are provided for
4778 extracting the desired features in a convenient format.")
4779 (license license:artistic2.0)))
4781 (define-public r-go-db
4787 (uri (string-append "http://www.bioconductor.org/packages/"
4788 "release/data/annotation/src/contrib/GO.db_"
4792 "00gariag9ampz82dh0xllrc26r85d7vdcwc0vca5zdy147rwxr7f"))))
4794 `((upstream-name . "GO.db")))
4795 (build-system r-build-system)
4797 `(("r-annotationdbi" ,r-annotationdbi)))
4798 (home-page "http://bioconductor.org/packages/GO.db")
4799 (synopsis "Annotation maps describing the entire Gene Ontology")
4801 "The purpose of this GO.db annotation package is to provide detailed
4802 information about the latest version of the Gene Ontologies.")
4803 (license license:artistic2.0)))
4805 (define-public r-graph
4811 (uri (bioconductor-uri "graph" version))
4814 "0ys5s19m5r30rlr0fnx2h0z2qw7n2xrad4l2yfb1bbrk8dwyf4pi"))))
4815 (build-system r-build-system)
4817 `(("r-biocgenerics" ,r-biocgenerics)))
4818 (home-page "http://bioconductor.org/packages/graph")
4819 (synopsis "Handle graph data structures in R")
4821 "This package implements some simple graph handling capabilities for R.")
4822 (license license:artistic2.0)))
4824 (define-public r-topgo
4830 (uri (bioconductor-uri "topGO" version))
4833 "1p4vsl32qhjw15yv9ym01ni63gjg73jaghlf17wc4zfn3iaz2zar"))))
4835 `((upstream-name . "topGO")))
4836 (build-system r-build-system)
4838 `(("r-annotationdbi" ,r-annotationdbi)
4839 ("r-biobase" ,r-biobase)
4840 ("r-biocgenerics" ,r-biocgenerics)
4841 ("r-go-db" ,r-go-db)
4842 ("r-matrixstats" ,r-matrixstats)
4843 ("r-graph" ,r-graph)
4844 ("r-sparsem" ,r-sparsem)))
4845 (home-page "http://bioconductor.org/packages/topGO")
4846 (synopsis "Enrichment analysis for gene ontology")
4848 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
4849 terms while accounting for the topology of the GO graph. Different test
4850 statistics and different methods for eliminating local similarities and
4851 dependencies between GO terms can be implemented and applied.")
4852 ;; Any version of the LGPL applies.
4853 (license license:lgpl2.1+)))
4855 (define-public r-bsgenome
4861 (uri (bioconductor-uri "BSgenome" version))
4864 "08g3w47ysbmgj4hclb0x2wsn7pi9cnm3xkkfk4shgrka2g23qz44"))))
4866 `((upstream-name . "BSgenome")))
4867 (build-system r-build-system)
4869 `(("r-biocgenerics" ,r-biocgenerics)
4870 ("r-biostrings" ,r-biostrings)
4871 ("r-genomeinfodb" ,r-genomeinfodb)
4872 ("r-genomicranges" ,r-genomicranges)
4873 ("r-iranges" ,r-iranges)
4874 ("r-rsamtools" ,r-rsamtools)
4875 ("r-rtracklayer" ,r-rtracklayer)
4876 ("r-s4vectors" ,r-s4vectors)
4877 ("r-xvector" ,r-xvector)))
4878 (home-page "http://bioconductor.org/packages/BSgenome")
4879 (synopsis "Infrastructure for Biostrings-based genome data packages")
4881 "This package provides infrastructure shared by all Biostrings-based
4882 genome data packages and support for efficient SNP representation.")
4883 (license license:artistic2.0)))
4885 (define-public r-impute
4891 (uri (bioconductor-uri "impute" version))
4894 "0v9ibgv8kp8il52miz7b7z65mv6irqxylx6lfzkxgvxd970dgrz0"))))
4896 `(("gfortran" ,gfortran)))
4897 (build-system r-build-system)
4898 (home-page "http://bioconductor.org/packages/impute")
4899 (synopsis "Imputation for microarray data")
4901 "This package provides a function to impute missing gene expression
4902 microarray data, using nearest neighbor averaging.")
4903 (license license:gpl2+)))
4905 (define-public r-seqpattern
4907 (name "r-seqpattern")
4911 (uri (bioconductor-uri "seqPattern" version))
4914 "1dj9hfnbdj11yjxwd8jmxrdkj7n6gmaaj6244g2psgarhjcp4wfb"))))
4916 `((upstream-name . "seqPattern")))
4917 (build-system r-build-system)
4919 `(("r-biostrings" ,r-biostrings)
4920 ("r-genomicranges" ,r-genomicranges)
4921 ("r-iranges" ,r-iranges)
4922 ("r-plotrix" ,r-plotrix)))
4923 (home-page "http://bioconductor.org/packages/seqPattern")
4924 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
4926 "This package provides tools to visualize oligonucleotide patterns and
4927 sequence motif occurrences across a large set of sequences centred at a common
4928 reference point and sorted by a user defined feature.")
4929 (license license:gpl3+)))
4931 (define-public r-genomation
4933 (name "r-genomation")
4937 (uri (bioconductor-uri "genomation" version))
4940 "017hxh3yhizlsswd2vw8504arkckrcgq5zraiw67lldq9wzs5qzg"))))
4941 (build-system r-build-system)
4943 `(("r-biostrings" ,r-biostrings)
4944 ("r-bsgenome" ,r-bsgenome)
4945 ("r-data-table" ,r-data-table)
4946 ("r-genomeinfodb" ,r-genomeinfodb)
4947 ("r-genomicalignments" ,r-genomicalignments)
4948 ("r-genomicranges" ,r-genomicranges)
4949 ("r-ggplot2" ,r-ggplot2)
4950 ("r-gridbase" ,r-gridbase)
4951 ("r-impute" ,r-impute)
4952 ("r-iranges" ,r-iranges)
4953 ("r-matrixstats" ,r-matrixstats)
4954 ("r-plotrix" ,r-plotrix)
4956 ("r-readr" ,r-readr)
4957 ("r-reshape2" ,r-reshape2)
4958 ("r-rsamtools" ,r-rsamtools)
4959 ("r-rtracklayer" ,r-rtracklayer)
4960 ("r-seqpattern" ,r-seqpattern)))
4961 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
4962 (synopsis "Summary, annotation and visualization of genomic data")
4964 "This package provides a package for summary and annotation of genomic
4965 intervals. Users can visualize and quantify genomic intervals over
4966 pre-defined functional regions, such as promoters, exons, introns, etc. The
4967 genomic intervals represent regions with a defined chromosome position, which
4968 may be associated with a score, such as aligned reads from HT-seq experiments,
4969 TF binding sites, methylation scores, etc. The package can use any tabular
4970 genomic feature data as long as it has minimal information on the locations of
4971 genomic intervals. In addition, it can use BAM or BigWig files as input.")
4972 (license license:artistic2.0)))
4974 (define-public r-genomationdata
4976 (name "r-genomationdata")
4980 ;; We cannot use bioconductor-uri here because this tarball is
4981 ;; located under "data/annotation/" instead of "bioc/".
4982 (uri (string-append "https://bioconductor.org/packages/"
4983 "release/data/experiment/src/contrib/"
4984 "genomationData_" version ".tar.gz"))
4987 "1xzq2j722d8lcn5bc3aq3yb34xwis2d0bpsf6jsq4xw1bg0bsy79"))))
4988 (build-system r-build-system)
4989 ;; As this package provides little more than large data files, it doesn't
4990 ;; make sense to build substitutes.
4991 (arguments `(#:substitutable? #f))
4993 `(("r-knitr" ,r-knitr)))
4994 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
4995 (synopsis "Experimental data for use with the genomation package")
4997 "This package contains experimental genetic data for use with the
4998 genomation package. Included are Chip Seq, Methylation and Cage data,
4999 downloaded from Encode.")
5000 (license license:gpl3+)))
5002 (define-public r-org-hs-eg-db
5004 (name "r-org-hs-eg-db")
5008 ;; We cannot use bioconductor-uri here because this tarball is
5009 ;; located under "data/annotation/" instead of "bioc/".
5010 (uri (string-append "http://www.bioconductor.org/packages/"
5011 "release/data/annotation/src/contrib/"
5012 "org.Hs.eg.db_" version ".tar.gz"))
5015 "0xicgkbh6xkvs74s1piafqac63dyz2ycdyil4pj4ghhxx2sabm6p"))))
5017 `((upstream-name . "org.Hs.eg.db")))
5018 (build-system r-build-system)
5020 `(("r-annotationdbi" ,r-annotationdbi)))
5021 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
5022 (synopsis "Genome wide annotation for Human")
5024 "This package provides mappings from Entrez gene identifiers to various
5025 annotations for the human genome.")
5026 (license license:artistic2.0)))
5028 (define-public r-org-ce-eg-db
5030 (name "r-org-ce-eg-db")
5034 ;; We cannot use bioconductor-uri here because this tarball is
5035 ;; located under "data/annotation/" instead of "bioc/".
5036 (uri (string-append "http://www.bioconductor.org/packages/"
5037 "release/data/annotation/src/contrib/"
5038 "org.Ce.eg.db_" version ".tar.gz"))
5041 "1d0lx00ybq34yqs6mziaa0lrh77xm0ggsmi76g6k95f77gi7m1sw"))))
5043 `((upstream-name . "org.Ce.eg.db")))
5044 (build-system r-build-system)
5046 `(("r-annotationdbi" ,r-annotationdbi)))
5047 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
5048 (synopsis "Genome wide annotation for Worm")
5050 "This package provides mappings from Entrez gene identifiers to various
5051 annotations for the genome of the model worm Caenorhabditis elegans.")
5052 (license license:artistic2.0)))
5054 (define-public r-org-dm-eg-db
5056 (name "r-org-dm-eg-db")
5060 ;; We cannot use bioconductor-uri here because this tarball is
5061 ;; located under "data/annotation/" instead of "bioc/".
5062 (uri (string-append "http://www.bioconductor.org/packages/"
5063 "release/data/annotation/src/contrib/"
5064 "org.Dm.eg.db_" version ".tar.gz"))
5067 "0mib46c7nr00l7mh290n383za9hyl91a1dc6jhjbk884jmxaxyz6"))))
5069 `((upstream-name . "org.Dm.eg.db")))
5070 (build-system r-build-system)
5072 `(("r-annotationdbi" ,r-annotationdbi)))
5073 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
5074 (synopsis "Genome wide annotation for Fly")
5076 "This package provides mappings from Entrez gene identifiers to various
5077 annotations for the genome of the model fruit fly Drosophila melanogaster.")
5078 (license license:artistic2.0)))
5080 (define-public r-org-mm-eg-db
5082 (name "r-org-mm-eg-db")
5086 ;; We cannot use bioconductor-uri here because this tarball is
5087 ;; located under "data/annotation/" instead of "bioc/".
5088 (uri (string-append "http://www.bioconductor.org/packages/"
5089 "release/data/annotation/src/contrib/"
5090 "org.Mm.eg.db_" version ".tar.gz"))
5093 "0wh1pm3npdg7070875kfgiid3bqkz3q7rq6snhk6bxfvph00298y"))))
5095 `((upstream-name . "org.Mm.eg.db")))
5096 (build-system r-build-system)
5098 `(("r-annotationdbi" ,r-annotationdbi)))
5099 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
5100 (synopsis "Genome wide annotation for Mouse")
5102 "This package provides mappings from Entrez gene identifiers to various
5103 annotations for the genome of the model mouse Mus musculus.")
5104 (license license:artistic2.0)))
5106 (define-public r-seqlogo
5113 (uri (bioconductor-uri "seqLogo" version))
5116 "01jddx62nhi3r7czbh9hxy0wwpazbc9ax1fgagfxl6p4kx9xz9rb"))))
5117 (properties `((upstream-name . "seqLogo")))
5118 (build-system r-build-system)
5119 (home-page "http://bioconductor.org/packages/seqLogo")
5120 (synopsis "Sequence logos for DNA sequence alignments")
5122 "seqLogo takes the position weight matrix of a DNA sequence motif and
5123 plots the corresponding sequence logo as introduced by Schneider and
5125 (license license:lgpl2.0+)))
5127 (define-public r-bsgenome-hsapiens-ucsc-hg19
5129 (name "r-bsgenome-hsapiens-ucsc-hg19")
5133 ;; We cannot use bioconductor-uri here because this tarball is
5134 ;; located under "data/annotation/" instead of "bioc/".
5135 (uri (string-append "http://www.bioconductor.org/packages/"
5136 "release/data/annotation/src/contrib/"
5137 "BSgenome.Hsapiens.UCSC.hg19_"
5141 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
5143 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
5144 (build-system r-build-system)
5145 ;; As this package provides little more than a very large data file it
5146 ;; doesn't make sense to build substitutes.
5147 (arguments `(#:substitutable? #f))
5149 `(("r-bsgenome" ,r-bsgenome)))
5151 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
5152 (synopsis "Full genome sequences for Homo sapiens")
5154 "This package provides full genome sequences for Homo sapiens as provided
5155 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
5156 (license license:artistic2.0)))
5158 (define-public r-bsgenome-mmusculus-ucsc-mm9
5160 (name "r-bsgenome-mmusculus-ucsc-mm9")
5164 ;; We cannot use bioconductor-uri here because this tarball is
5165 ;; located under "data/annotation/" instead of "bioc/".
5166 (uri (string-append "http://www.bioconductor.org/packages/"
5167 "release/data/annotation/src/contrib/"
5168 "BSgenome.Mmusculus.UCSC.mm9_"
5172 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
5174 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
5175 (build-system r-build-system)
5176 ;; As this package provides little more than a very large data file it
5177 ;; doesn't make sense to build substitutes.
5178 (arguments `(#:substitutable? #f))
5180 `(("r-bsgenome" ,r-bsgenome)))
5182 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
5183 (synopsis "Full genome sequences for Mouse")
5185 "This package provides full genome sequences for Mus musculus (Mouse) as
5186 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
5187 (license license:artistic2.0)))
5189 (define-public r-bsgenome-mmusculus-ucsc-mm10
5191 (name "r-bsgenome-mmusculus-ucsc-mm10")
5195 ;; We cannot use bioconductor-uri here because this tarball is
5196 ;; located under "data/annotation/" instead of "bioc/".
5197 (uri (string-append "http://www.bioconductor.org/packages/"
5198 "release/data/annotation/src/contrib/"
5199 "BSgenome.Mmusculus.UCSC.mm10_"
5203 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
5205 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
5206 (build-system r-build-system)
5207 ;; As this package provides little more than a very large data file it
5208 ;; doesn't make sense to build substitutes.
5209 (arguments `(#:substitutable? #f))
5211 `(("r-bsgenome" ,r-bsgenome)))
5213 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
5214 (synopsis "Full genome sequences for Mouse")
5216 "This package provides full genome sequences for Mus
5217 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
5218 in Biostrings objects.")
5219 (license license:artistic2.0)))
5221 (define-public r-bsgenome-celegans-ucsc-ce6
5223 (name "r-bsgenome-celegans-ucsc-ce6")
5227 ;; We cannot use bioconductor-uri here because this tarball is
5228 ;; located under "data/annotation/" instead of "bioc/".
5229 (uri (string-append "http://www.bioconductor.org/packages/"
5230 "release/data/annotation/src/contrib/"
5231 "BSgenome.Celegans.UCSC.ce6_"
5235 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
5237 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
5238 (build-system r-build-system)
5239 ;; As this package provides little more than a very large data file it
5240 ;; doesn't make sense to build substitutes.
5241 (arguments `(#:substitutable? #f))
5243 `(("r-bsgenome" ,r-bsgenome)))
5245 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
5246 (synopsis "Full genome sequences for Worm")
5248 "This package provides full genome sequences for Caenorhabditis
5249 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
5251 (license license:artistic2.0)))
5253 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
5255 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
5259 ;; We cannot use bioconductor-uri here because this tarball is
5260 ;; located under "data/annotation/" instead of "bioc/".
5261 (uri (string-append "http://www.bioconductor.org/packages/"
5262 "release/data/annotation/src/contrib/"
5263 "BSgenome.Dmelanogaster.UCSC.dm3_"
5267 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
5269 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
5270 (build-system r-build-system)
5271 ;; As this package provides little more than a very large data file it
5272 ;; doesn't make sense to build substitutes.
5273 (arguments `(#:substitutable? #f))
5275 `(("r-bsgenome" ,r-bsgenome)))
5277 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
5278 (synopsis "Full genome sequences for Fly")
5280 "This package provides full genome sequences for Drosophila
5281 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
5282 Biostrings objects.")
5283 (license license:artistic2.0)))
5285 (define-public r-motifrg
5292 (uri (bioconductor-uri "motifRG" version))
5295 "1ds22paqc0923y6z1fy0arw0wxvvmglfvfgarhywv1qywhq68mbq"))))
5296 (properties `((upstream-name . "motifRG")))
5297 (build-system r-build-system)
5299 `(("r-biostrings" ,r-biostrings)
5300 ("r-bsgenome" ,r-bsgenome)
5301 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
5302 ("r-iranges" ,r-iranges)
5303 ("r-seqlogo" ,r-seqlogo)
5304 ("r-xvector" ,r-xvector)))
5305 (home-page "http://bioconductor.org/packages/motifRG")
5306 (synopsis "Discover motifs in high throughput sequencing data")
5308 "This package provides tools for discriminative motif discovery in high
5309 throughput genetic sequencing data sets using regression methods.")
5310 (license license:artistic2.0)))
5312 (define-public r-qtl
5319 (uri (string-append "mirror://cran/src/contrib/qtl_"
5323 "1grwgvyv7x0dgay1858bg7qf4wk47gpnq7qkqpcda9cn0h970d6f"))))
5324 (build-system r-build-system)
5325 (home-page "http://rqtl.org/")
5326 (synopsis "R package for analyzing QTL experiments in genetics")
5327 (description "R/qtl is an extension library for the R statistics
5328 system. It is used to analyze experimental crosses for identifying
5329 genes contributing to variation in quantitative traits (so-called
5330 quantitative trait loci, QTLs).
5332 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
5333 identify genotyping errors, and to perform single-QTL and two-QTL,
5334 two-dimensional genome scans.")
5335 (license license:gpl3)))
5337 (define-public r-zlibbioc
5343 (uri (bioconductor-uri "zlibbioc" version))
5346 "0m8l7zpx1l3qsk73k3ibkxxzzff938x3qhnwki1ymf3cnsg8cb36"))))
5348 `((upstream-name . "zlibbioc")))
5349 (build-system r-build-system)
5350 (home-page "https://bioconductor.org/packages/zlibbioc")
5351 (synopsis "Provider for zlib-1.2.5 to R packages")
5352 (description "This package uses the source code of zlib-1.2.5 to create
5353 libraries for systems that do not have these available via other means.")
5354 (license license:artistic2.0)))
5356 (define-public piranha
5357 ;; There is no release tarball for the latest version. The latest commit is
5358 ;; older than one year at the time of this writing.
5359 (let ((revision "1")
5360 (commit "0466d364b71117d01e4471b74c514436cc281233"))
5363 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
5367 (url "https://github.com/smithlabcode/piranha.git")
5371 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
5372 (build-system gnu-build-system)
5374 `(#:test-target "test"
5376 (modify-phases %standard-phases
5377 (add-after 'unpack 'copy-smithlab-cpp
5378 (lambda* (#:key inputs #:allow-other-keys)
5379 (for-each (lambda (file)
5380 (install-file file "./src/smithlab_cpp/"))
5381 (find-files (assoc-ref inputs "smithlab-cpp")))
5383 (add-after 'install 'install-to-store
5384 (lambda* (#:key outputs #:allow-other-keys)
5385 (let* ((out (assoc-ref outputs "out"))
5386 (bin (string-append out "/bin")))
5388 (for-each (lambda (file)
5389 (install-file file bin))
5390 (find-files "bin" ".*")))
5393 (list (string-append "--with-bam_tools_headers="
5394 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
5395 (string-append "--with-bam_tools_library="
5396 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
5398 `(("bamtools" ,bamtools)
5399 ("samtools" ,samtools-0.1)
5402 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
5406 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5408 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
5411 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
5413 `(("python" ,python-2)))
5414 (home-page "https://github.com/smithlabcode/piranha")
5415 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
5417 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
5418 RIP-seq experiments. It takes input in BED or BAM format and identifies
5419 regions of statistically significant read enrichment. Additional covariates
5420 may optionally be provided to further inform the peak-calling process.")
5421 (license license:gpl3+))))
5429 (uri (string-append "https://pypi.python.org/packages/source/P"
5430 "/PePr/PePr-" version ".tar.gz"))
5433 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
5434 (build-system python-build-system)
5436 `(#:python ,python-2 ; python2 only
5437 #:tests? #f ; no tests included
5439 (modify-phases %standard-phases
5440 ;; When setuptools is used a ".egg" archive is generated and
5441 ;; installed. This makes it hard to actually run PePr. This issue
5442 ;; has been reported upstream:
5443 ;; https://github.com/shawnzhangyx/PePr/issues/9
5444 (add-after 'unpack 'disable-egg-generation
5446 (substitute* "setup.py"
5447 (("from setuptools import setup")
5448 "from distutils.core import setup"))
5451 `(("python2-numpy" ,python2-numpy)
5452 ("python2-scipy" ,python2-scipy)
5453 ("python2-pysam" ,python2-pysam)))
5454 (home-page "https://code.google.com/p/pepr-chip-seq/")
5455 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
5457 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
5458 that is primarily designed for data with biological replicates. It uses a
5459 negative binomial distribution to model the read counts among the samples in
5460 the same group, and look for consistent differences between ChIP and control
5461 group or two ChIP groups run under different conditions.")
5462 (license license:gpl3+)))
5464 (define-public filevercmp
5465 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
5468 (version (string-append "0-1." (string-take commit 7)))
5471 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
5473 (file-name (string-append name "-" version ".tar.gz"))
5475 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
5476 (build-system gnu-build-system)
5478 `(#:tests? #f ; There are no tests to run.
5480 (modify-phases %standard-phases
5481 (delete 'configure) ; There is no configure phase.
5483 (lambda* (#:key outputs #:allow-other-keys)
5484 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
5485 (install-file "filevercmp" bin)))))))
5486 (home-page "https://github.com/ekg/filevercmp")
5487 (synopsis "This program compares version strings")
5488 (description "This program compares version strings. It intends to be a
5489 replacement for strverscmp.")
5490 (license license:gpl3+))))