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>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
10 ;;; This file is part of GNU Guix.
12 ;;; GNU Guix is free software; you can redistribute it and/or modify it
13 ;;; under the terms of the GNU General Public License as published by
14 ;;; the Free Software Foundation; either version 3 of the License, or (at
15 ;;; your option) any later version.
17 ;;; GNU Guix is distributed in the hope that it will be useful, but
18 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
19 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
20 ;;; GNU General Public License for more details.
22 ;;; You should have received a copy of the GNU General Public License
23 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
25 (define-module (gnu packages bioinformatics)
26 #:use-module ((guix licenses) #:prefix license:)
27 #:use-module (guix packages)
28 #:use-module (guix utils)
29 #:use-module (guix download)
30 #:use-module (guix git-download)
31 #:use-module (guix hg-download)
32 #:use-module (guix build-system ant)
33 #:use-module (guix build-system gnu)
34 #:use-module (guix build-system cmake)
35 #:use-module (guix build-system perl)
36 #:use-module (guix build-system python)
37 #:use-module (guix build-system r)
38 #:use-module (guix build-system ruby)
39 #:use-module (guix build-system trivial)
40 #:use-module (gnu packages)
41 #:use-module (gnu packages autotools)
42 #:use-module (gnu packages algebra)
43 #:use-module (gnu packages base)
44 #:use-module (gnu packages bash)
45 #:use-module (gnu packages bison)
46 #:use-module (gnu packages boost)
47 #:use-module (gnu packages compression)
48 #:use-module (gnu packages cpio)
49 #:use-module (gnu packages curl)
50 #:use-module (gnu packages documentation)
51 #:use-module (gnu packages datastructures)
52 #:use-module (gnu packages file)
53 #:use-module (gnu packages flex)
54 #:use-module (gnu packages gawk)
55 #:use-module (gnu packages gcc)
56 #:use-module (gnu packages gd)
57 #:use-module (gnu packages gtk)
58 #:use-module (gnu packages glib)
59 #:use-module (gnu packages groff)
60 #:use-module (gnu packages guile)
61 #:use-module (gnu packages haskell)
62 #:use-module (gnu packages image)
63 #:use-module (gnu packages imagemagick)
64 #:use-module (gnu packages java)
65 #:use-module (gnu packages linux)
66 #:use-module (gnu packages logging)
67 #:use-module (gnu packages machine-learning)
68 #:use-module (gnu packages man)
69 #:use-module (gnu packages maths)
70 #:use-module (gnu packages mpi)
71 #:use-module (gnu packages ncurses)
72 #:use-module (gnu packages pcre)
73 #:use-module (gnu packages parallel)
74 #:use-module (gnu packages pdf)
75 #:use-module (gnu packages perl)
76 #:use-module (gnu packages pkg-config)
77 #:use-module (gnu packages popt)
78 #:use-module (gnu packages protobuf)
79 #:use-module (gnu packages python)
80 #:use-module (gnu packages readline)
81 #:use-module (gnu packages ruby)
82 #:use-module (gnu packages serialization)
83 #:use-module (gnu packages statistics)
84 #:use-module (gnu packages tbb)
85 #:use-module (gnu packages tex)
86 #:use-module (gnu packages texinfo)
87 #:use-module (gnu packages textutils)
88 #:use-module (gnu packages time)
89 #:use-module (gnu packages tls)
90 #:use-module (gnu packages vim)
91 #:use-module (gnu packages web)
92 #:use-module (gnu packages xml)
93 #:use-module (gnu packages xorg)
94 #:use-module (gnu packages zip)
95 #:use-module (srfi srfi-1))
97 (define-public aragorn
104 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
108 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
109 (build-system gnu-build-system)
111 `(#:tests? #f ; there are no tests
113 (modify-phases %standard-phases
117 (zero? (system* "gcc"
123 (string-append "aragorn" ,version ".c")))))
125 (lambda* (#:key outputs #:allow-other-keys)
126 (let* ((out (assoc-ref outputs "out"))
127 (bin (string-append out "/bin"))
128 (man (string-append out "/share/man/man1")))
131 (string-append bin "/aragorn"))
133 (copy-file "aragorn.1"
134 (string-append man "/aragorn.1")))
136 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
137 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
139 "Aragorn identifies transfer RNA, mitochondrial RNA and
140 transfer-messenger RNA from nucleotide sequences, based on homology to known
141 tRNA consensus sequences and RNA structure. It also outputs the secondary
142 structure of the predicted RNA.")
143 (license license:gpl2)))
151 ;; BamM is not available on pypi.
153 "https://github.com/Ecogenomics/BamM/archive/"
155 (file-name (string-append name "-" version ".tar.gz"))
158 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
159 (modules '((guix build utils)))
162 ;; Delete bundled htslib.
163 (delete-file-recursively "c/htslib-1.3.1")
165 (build-system python-build-system)
167 `(#:python ,python-2 ; BamM is Python 2 only.
168 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
169 ;; been modified from its original form.
171 (let ((htslib (assoc-ref %build-inputs "htslib")))
172 (list "--with-libhts-lib" (string-append htslib "/lib")
173 "--with-libhts-inc" (string-append htslib "/include/htslib")))
175 (modify-phases %standard-phases
176 (add-after 'unpack 'autogen
178 (with-directory-excursion "c"
179 (let ((sh (which "sh")))
180 ;; Use autogen so that 'configure' works.
181 (substitute* "autogen.sh" (("/bin/sh") sh))
182 (setenv "CONFIG_SHELL" sh)
183 (substitute* "configure" (("/bin/sh") sh))
184 (zero? (system* "./autogen.sh"))))))
186 ;; Run tests after installation so compilation only happens once.
188 (add-after 'install 'wrap-executable
189 (lambda* (#:key outputs #:allow-other-keys)
190 (let* ((out (assoc-ref outputs "out"))
191 (path (getenv "PATH")))
192 (wrap-program (string-append out "/bin/bamm")
193 `("PATH" ":" prefix (,path))))
195 (add-after 'wrap-executable 'post-install-check
196 (lambda* (#:key inputs outputs #:allow-other-keys)
198 (string-append (assoc-ref outputs "out")
203 (assoc-ref outputs "out")
205 (string-take (string-take-right
206 (assoc-ref inputs "python") 5) 3)
208 (getenv "PYTHONPATH")))
209 ;; There are 2 errors printed, but they are safe to ignore:
210 ;; 1) [E::hts_open_format] fail to open file ...
211 ;; 2) samtools view: failed to open ...
212 (zero? (system* "nosetests")))))))
214 `(("autoconf" ,autoconf)
215 ("automake" ,automake)
218 ("python-nose" ,python2-nose)
219 ("python-pysam" ,python2-pysam)))
222 ("samtools" ,samtools)
226 ("coreutils" ,coreutils)))
228 `(("python-numpy" ,python2-numpy)))
229 (home-page "http://ecogenomics.github.io/BamM/")
230 (synopsis "Metagenomics-focused BAM file manipulator")
232 "BamM is a C library, wrapped in python, to efficiently generate and
233 parse BAM files, specifically for the analysis of metagenomic data. For
234 instance, it implements several methods to assess contig-wise read coverage.")
235 (license license:lgpl3+)))
237 (define-public bamtools
244 "https://github.com/pezmaster31/bamtools/archive/v"
246 (file-name (string-append name "-" version ".tar.gz"))
249 "1brry29bw2xr2l9pqn240rkqwayg85b8qq78zk2zs6nlspk4d018"))))
250 (build-system cmake-build-system)
252 `(#:tests? #f ;no "check" target
254 (modify-phases %standard-phases
256 'configure 'set-ldflags
257 (lambda* (#:key outputs #:allow-other-keys)
261 (assoc-ref outputs "out") "/lib/bamtools")))))))
262 (inputs `(("zlib" ,zlib)))
263 (home-page "https://github.com/pezmaster31/bamtools")
264 (synopsis "C++ API and command-line toolkit for working with BAM data")
266 "BamTools provides both a C++ API and a command-line toolkit for handling
268 (license license:expat)))
270 (define-public bcftools
277 "https://github.com/samtools/bcftools/releases/download/"
278 version "/bcftools-" version ".tar.bz2"))
281 "095ry68vmz9q5s1scjsa698dhgyvgw5aicz24c19iwfbai07mhqj"))
282 (modules '((guix build utils)))
284 ;; Delete bundled htslib.
285 '(delete-file-recursively "htslib-1.3.1"))))
286 (build-system gnu-build-system)
288 `(#:test-target "test"
292 (string-append "prefix=" (assoc-ref %outputs "out"))
293 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
294 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.a")
295 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
296 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix"))
298 (modify-phases %standard-phases
299 (add-after 'unpack 'patch-Makefile
301 (substitute* "Makefile"
302 ;; Do not attempt to build htslib.
303 (("^include \\$\\(HTSDIR\\)/htslib\\.mk") "")
304 ;; Link against GSL cblas.
305 (("-lcblas") "-lgslcblas"))
308 (add-before 'check 'patch-tests
310 (substitute* "test/test.pl"
311 (("/bin/bash") (which "bash")))
319 (home-page "https://samtools.github.io/bcftools/")
320 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
322 "BCFtools is a set of utilities that manipulate variant calls in the
323 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
324 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
325 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
326 (license (list license:gpl3+ license:expat))))
328 (define-public bedops
334 (uri (string-append "https://github.com/bedops/bedops/archive/v"
336 (file-name (string-append name "-" version ".tar.gz"))
339 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
340 (build-system gnu-build-system)
343 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
346 'unpack 'unpack-tarballs
348 ;; FIXME: Bedops includes tarballs of minimally patched upstream
349 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
350 ;; libraries because at least one of the libraries (zlib) is
351 ;; patched to add a C++ function definition (deflateInit2cpp).
352 ;; Until the Bedops developers offer a way to link against system
353 ;; libraries we have to build the in-tree copies of these three
356 ;; See upstream discussion:
357 ;; https://github.com/bedops/bedops/issues/124
359 ;; Unpack the tarballs to benefit from shebang patching.
360 (with-directory-excursion "third-party"
361 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
362 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
363 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
364 ;; Disable unpacking of tarballs in Makefile.
365 (substitute* "system.mk/Makefile.linux"
366 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
367 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
368 (substitute* "third-party/zlib-1.2.7/Makefile.in"
369 (("^SHELL=.*$") "SHELL=bash\n")))
370 (alist-delete 'configure %standard-phases))))
371 (home-page "https://github.com/bedops/bedops")
372 (synopsis "Tools for high-performance genomic feature operations")
374 "BEDOPS is a suite of tools to address common questions raised in genomic
375 studies---mostly with regard to overlap and proximity relationships between
376 data sets. It aims to be scalable and flexible, facilitating the efficient
377 and accurate analysis and management of large-scale genomic data.
379 BEDOPS provides tools that perform highly efficient and scalable Boolean and
380 other set operations, statistical calculations, archiving, conversion and
381 other management of genomic data of arbitrary scale. Tasks can be easily
382 split by chromosome for distributing whole-genome analyses across a
383 computational cluster.")
384 (license license:gpl2+)))
386 (define-public bedtools
392 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
394 (file-name (string-append name "-" version ".tar.gz"))
397 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
398 (build-system gnu-build-system)
399 (native-inputs `(("python" ,python-2)))
400 (inputs `(("samtools" ,samtools)
403 '(#:test-target "test"
405 (modify-phases %standard-phases
408 (lambda* (#:key outputs #:allow-other-keys)
409 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
410 (for-each (lambda (file)
411 (install-file file bin))
412 (find-files "bin" ".*")))
414 (home-page "https://github.com/arq5x/bedtools2")
415 (synopsis "Tools for genome analysis and arithmetic")
417 "Collectively, the bedtools utilities are a swiss-army knife of tools for
418 a wide-range of genomics analysis tasks. The most widely-used tools enable
419 genome arithmetic: that is, set theory on the genome. For example, bedtools
420 allows one to intersect, merge, count, complement, and shuffle genomic
421 intervals from multiple files in widely-used genomic file formats such as BAM,
423 (license license:gpl2)))
425 ;; Later releases of bedtools produce files with more columns than
426 ;; what Ribotaper expects.
427 (define-public bedtools-2.18
428 (package (inherit bedtools)
433 (uri (string-append "https://github.com/arq5x/bedtools2/"
434 "archive/v" version ".tar.gz"))
435 (file-name (string-append name "-" version ".tar.gz"))
438 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
440 (define-public ribotaper
446 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
447 "files/RiboTaper/RiboTaper_Version_"
451 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
452 (build-system gnu-build-system)
454 `(("bedtools" ,bedtools-2.18)
455 ("samtools" ,samtools-0.1)
457 ("r-foreach" ,r-foreach)
458 ("r-xnomial" ,r-xnomial)
460 ("r-multitaper" ,r-multitaper)
461 ("r-seqinr" ,r-seqinr)))
462 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
463 (synopsis "Define translated ORFs using ribosome profiling data")
465 "Ribotaper is a method for defining translated @dfn{open reading
466 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
467 provides the Ribotaper pipeline.")
468 (license license:gpl3+)))
470 (define-public bioawk
476 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
478 (file-name (string-append name "-" version ".tar.gz"))
480 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
481 (build-system gnu-build-system)
487 `(#:tests? #f ; There are no tests to run.
488 ;; Bison must generate files, before other targets can build.
491 (modify-phases %standard-phases
492 (delete 'configure) ; There is no configure phase.
494 (lambda* (#:key outputs #:allow-other-keys)
495 (let* ((out (assoc-ref outputs "out"))
496 (bin (string-append out "/bin"))
497 (man (string-append out "/share/man/man1")))
499 (copy-file "awk.1" (string-append man "/bioawk.1"))
500 (install-file "bioawk" bin)))))))
501 (home-page "https://github.com/lh3/bioawk")
502 (synopsis "AWK with bioinformatics extensions")
503 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
504 support of several common biological data formats, including optionally gzip'ed
505 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
506 also adds a few built-in functions and a command line option to use TAB as the
507 input/output delimiter. When the new functionality is not used, bioawk is
508 intended to behave exactly the same as the original BWK awk.")
509 (license license:x11)))
511 (define-public python2-pybedtools
513 (name "python2-pybedtools")
518 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
522 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
523 (build-system python-build-system)
524 (arguments `(#:python ,python-2)) ; no Python 3 support
526 `(("python-matplotlib" ,python2-matplotlib)))
528 `(("bedtools" ,bedtools)
529 ("samtools" ,samtools)))
531 `(("python-cython" ,python2-cython)
532 ("python-pyyaml" ,python2-pyyaml)
533 ("python-nose" ,python2-nose)))
534 (home-page "https://pythonhosted.org/pybedtools/")
535 (synopsis "Python wrapper for BEDtools programs")
537 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
538 which are widely used for genomic interval manipulation or \"genome algebra\".
539 pybedtools extends BEDTools by offering feature-level manipulations from with
541 (license license:gpl2+)))
543 (define-public python-biom-format
545 (name "python-biom-format")
550 ;; Use GitHub as source because PyPI distribution does not contain
551 ;; test data: https://github.com/biocore/biom-format/issues/693
552 (uri (string-append "https://github.com/biocore/biom-format/archive/"
554 (file-name (string-append name "-" version ".tar.gz"))
557 "1n25w3p1rixbpac8iysmzcja6m4ip5r6sz19l8y6wlwi49hxn278"))))
558 (build-system python-build-system)
560 `(("python-numpy" ,python-numpy)
561 ("python-scipy" ,python-scipy)
562 ("python-future" ,python-future)
563 ("python-click" ,python-click)
564 ("python-h5py" ,python-h5py)))
565 (home-page "http://www.biom-format.org")
566 (synopsis "Biological Observation Matrix (BIOM) format utilities")
568 "The BIOM file format is designed to be a general-use format for
569 representing counts of observations e.g. operational taxonomic units, KEGG
570 orthology groups or lipid types, in one or more biological samples
571 e.g. microbiome samples, genomes, metagenomes.")
572 (license license:bsd-3)
573 (properties `((python2-variant . ,(delay python2-biom-format))))))
575 (define-public python2-biom-format
576 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
581 (modify-phases %standard-phases
582 ;; Do not require the unmaintained pyqi library.
583 (add-after 'unpack 'remove-pyqi
585 (substitute* "setup.py"
586 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
588 ,@(package-arguments base))))))
590 (define-public bioperl-minimal
591 (let* ((inputs `(("perl-module-build" ,perl-module-build)
592 ("perl-data-stag" ,perl-data-stag)
593 ("perl-libwww" ,perl-libwww)
594 ("perl-uri" ,perl-uri)))
596 (map (compose package-name cadr)
599 (map (compose package-transitive-target-inputs cadr) inputs))))))
601 (name "bioperl-minimal")
606 (uri (string-append "https://github.com/bioperl/bioperl-live/"
608 (string-map (lambda (c)
614 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
615 (build-system perl-build-system)
618 (modify-phases %standard-phases
620 'install 'wrap-programs
621 (lambda* (#:key outputs #:allow-other-keys)
622 ;; Make sure all executables in "bin" find the required Perl
623 ;; modules at runtime. As the PERL5LIB variable contains also
624 ;; the paths of native inputs, we pick the transitive target
625 ;; inputs from %build-inputs.
626 (let* ((out (assoc-ref outputs "out"))
627 (bin (string-append out "/bin/"))
629 (cons (string-append out "/lib/perl5/site_perl")
631 (assoc-ref %build-inputs name))
632 ',transitive-inputs))
634 (for-each (lambda (file)
636 `("PERL5LIB" ":" prefix (,path))))
637 (find-files bin "\\.pl$"))
641 `(("perl-test-most" ,perl-test-most)))
642 (home-page "http://search.cpan.org/dist/BioPerl")
643 (synopsis "Bioinformatics toolkit")
645 "BioPerl is the product of a community effort to produce Perl code which
646 is useful in biology. Examples include Sequence objects, Alignment objects
647 and database searching objects. These objects not only do what they are
648 advertised to do in the documentation, but they also interact - Alignment
649 objects are made from the Sequence objects, Sequence objects have access to
650 Annotation and SeqFeature objects and databases, Blast objects can be
651 converted to Alignment objects, and so on. This means that the objects
652 provide a coordinated and extensible framework to do computational biology.")
653 (license (package-license perl)))))
655 (define-public python-biopython
657 (name "python-biopython")
661 ;; use PyPi rather than biopython.org to ease updating
662 (uri (pypi-uri "biopython" version))
665 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
666 (build-system python-build-system)
669 (modify-phases %standard-phases
670 (add-before 'check 'set-home
671 ;; Some tests require a home directory to be set.
672 (lambda _ (setenv "HOME" "/tmp") #t)))))
674 `(("python-numpy" ,python-numpy)))
675 (home-page "http://biopython.org/")
676 (synopsis "Tools for biological computation in Python")
678 "Biopython is a set of tools for biological computation including parsers
679 for bioinformatics files into Python data structures; interfaces to common
680 bioinformatics programs; a standard sequence class and tools for performing
681 common operations on them; code to perform data classification; code for
682 dealing with alignments; code making it easy to split up parallelizable tasks
683 into separate processes; and more.")
684 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
686 (define-public python2-biopython
687 (package-with-python2 python-biopython))
689 ;; An outdated version of biopython is required for seqmagick, see
690 ;; https://github.com/fhcrc/seqmagick/issues/59
691 ;; When that issue has been resolved this package should be removed.
692 (define python2-biopython-1.66
694 (inherit python2-biopython)
698 (uri (pypi-uri "biopython" version))
701 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
703 (define-public bpp-core
704 ;; The last release was in 2014 and the recommended way to install from source
705 ;; is to clone the git repository, so we do this.
706 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
707 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
710 (version (string-append "2.2.0-1." (string-take commit 7)))
714 (url "http://biopp.univ-montp2.fr/git/bpp-core")
716 (file-name (string-append name "-" version "-checkout"))
719 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
720 (build-system cmake-build-system)
722 `(#:parallel-build? #f))
724 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
725 ; compile all of the bpp packages with GCC 5.
726 (home-page "http://biopp.univ-montp2.fr")
727 (synopsis "C++ libraries for Bioinformatics")
729 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
730 analysis, phylogenetics, molecular evolution and population genetics. It is
731 Object Oriented and is designed to be both easy to use and computer efficient.
732 Bio++ intends to help programmers to write computer expensive programs, by
733 providing them a set of re-usable tools.")
734 (license license:cecill-c))))
736 (define-public bpp-phyl
737 ;; The last release was in 2014 and the recommended way to install from source
738 ;; is to clone the git repository, so we do this.
739 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
740 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
743 (version (string-append "2.2.0-1." (string-take commit 7)))
747 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
749 (file-name (string-append name "-" version "-checkout"))
752 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
753 (build-system cmake-build-system)
755 `(#:parallel-build? #f
756 ;; If out-of-source, test data is not copied into the build directory
757 ;; so the tests fail.
758 #:out-of-source? #f))
760 `(("bpp-core" ,bpp-core)
762 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
765 (home-page "http://biopp.univ-montp2.fr")
766 (synopsis "Bio++ phylogenetic Library")
768 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
769 analysis, phylogenetics, molecular evolution and population genetics. This
770 library provides phylogenetics-related modules.")
771 (license license:cecill-c))))
773 (define-public bpp-popgen
774 ;; The last release was in 2014 and the recommended way to install from source
775 ;; is to clone the git repository, so we do this.
776 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
777 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
780 (version (string-append "2.2.0-1." (string-take commit 7)))
784 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
786 (file-name (string-append name "-" version "-checkout"))
789 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
790 (build-system cmake-build-system)
792 `(#:parallel-build? #f
793 #:tests? #f)) ; There are no tests.
795 `(("bpp-core" ,bpp-core)
798 (home-page "http://biopp.univ-montp2.fr")
799 (synopsis "Bio++ population genetics library")
801 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
802 analysis, phylogenetics, molecular evolution and population genetics. This
803 library provides population genetics-related modules.")
804 (license license:cecill-c))))
806 (define-public bpp-seq
807 ;; The last release was in 2014 and the recommended way to install from source
808 ;; is to clone the git repository, so we do this.
809 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
810 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
813 (version (string-append "2.2.0-1." (string-take commit 7)))
817 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
819 (file-name (string-append name "-" version "-checkout"))
822 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
823 (build-system cmake-build-system)
825 `(#:parallel-build? #f
826 ;; If out-of-source, test data is not copied into the build directory
827 ;; so the tests fail.
828 #:out-of-source? #f))
830 `(("bpp-core" ,bpp-core)
831 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
832 (home-page "http://biopp.univ-montp2.fr")
833 (synopsis "Bio++ sequence library")
835 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
836 analysis, phylogenetics, molecular evolution and population genetics. This
837 library provides sequence-related modules.")
838 (license license:cecill-c))))
840 (define-public bppsuite
841 ;; The last release was in 2014 and the recommended way to install from source
842 ;; is to clone the git repository, so we do this.
843 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
844 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
847 (version (string-append "2.2.0-1." (string-take commit 7)))
851 (url "http://biopp.univ-montp2.fr/git/bppsuite")
853 (file-name (string-append name "-" version "-checkout"))
856 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
857 (build-system cmake-build-system)
859 `(#:parallel-build? #f
860 #:tests? #f)) ; There are no tests.
864 ("texinfo" ,texinfo)))
866 `(("bpp-core" ,bpp-core)
868 ("bpp-phyl" ,bpp-phyl)
869 ("bpp-phyl" ,bpp-popgen)
871 (home-page "http://biopp.univ-montp2.fr")
872 (synopsis "Bioinformatics tools written with the Bio++ libraries")
874 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
875 analysis, phylogenetics, molecular evolution and population genetics. This
876 package provides command line tools using the Bio++ library.")
877 (license license:cecill-c))))
879 (define-public blast+
886 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
887 version "/ncbi-blast-" version "+-src.tar.gz"))
890 "14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
891 (modules '((guix build utils)))
894 ;; Remove bundled bzip2 and zlib
895 (delete-file-recursively "c++/src/util/compress/bzip2")
896 (delete-file-recursively "c++/src/util/compress/zlib")
897 (substitute* "c++/src/util/compress/Makefile.in"
898 (("bzip2 zlib api") "api"))
899 ;; Remove useless msbuild directory
900 (delete-file-recursively
901 "c++/src/build-system/project_tree_builder/msbuild")
903 (build-system gnu-build-system)
905 `(;; There are three(!) tests for this massive library, and all fail with
906 ;; "unparsable timing stats".
907 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
908 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
909 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
912 #:parallel-build? #f ; not supported
914 (modify-phases %standard-phases
917 ;; $HOME needs to be set at some point during the configure phase
918 (lambda _ (setenv "HOME" "/tmp") #t))
921 (lambda _ (chdir "c++") #t))
923 'enter-dir 'fix-build-system
926 (cond ((string=? cmd "date")
927 ;; make call to "date" deterministic
932 (format (current-error-port)
933 "WARNING: Unable to find absolute path for ~s~%"
937 ;; Rewrite hardcoded paths to various tools
938 (substitute* (append '("src/build-system/configure.ac"
939 "src/build-system/configure"
940 "scripts/common/impl/if_diff.sh"
941 "scripts/common/impl/run_with_lock.sh"
942 "src/build-system/Makefile.configurables.real"
943 "src/build-system/Makefile.in.top"
944 "src/build-system/Makefile.meta.gmake=no"
945 "src/build-system/Makefile.meta.in"
946 "src/build-system/Makefile.meta_l"
947 "src/build-system/Makefile.meta_p"
948 "src/build-system/Makefile.meta_r"
949 "src/build-system/Makefile.mk.in"
950 "src/build-system/Makefile.requirements"
951 "src/build-system/Makefile.rules_with_autodep.in")
952 (find-files "scripts/common/check" "\\.sh$"))
953 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
954 (or (which* cmd) all)))
956 (substitute* (find-files "src/build-system" "^config.*")
957 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
960 ;; rewrite "/var/tmp" in check script
961 (substitute* "scripts/common/check/check_make_unix.sh"
962 (("/var/tmp") "/tmp"))
965 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
967 (("action=/bin/") "action=")
968 (("export PATH") ":"))
972 (lambda* (#:key inputs outputs #:allow-other-keys)
973 (let ((out (assoc-ref outputs "out"))
974 (lib (string-append (assoc-ref outputs "lib") "/lib"))
975 (include (string-append (assoc-ref outputs "include")
976 "/include/ncbi-tools++")))
977 ;; The 'configure' script doesn't recognize things like
978 ;; '--enable-fast-install'.
979 (zero? (system* "./configure.orig"
980 (string-append "--with-build-root=" (getcwd) "/build")
981 (string-append "--prefix=" out)
982 (string-append "--libdir=" lib)
983 (string-append "--includedir=" include)
984 (string-append "--with-bz2="
985 (assoc-ref inputs "bzip2"))
986 (string-append "--with-z="
987 (assoc-ref inputs "zlib"))
988 ;; Each library is built twice by default, once
989 ;; with "-static" in its name, and again
993 (outputs '("out" ; 19 MB
1001 (home-page "http://blast.ncbi.nlm.nih.gov")
1002 (synopsis "Basic local alignment search tool")
1004 "BLAST is a popular method of performing a DNA or protein sequence
1005 similarity search, using heuristics to produce results quickly. It also
1006 calculates an “expect value” that estimates how many matches would have
1007 occurred at a given score by chance, which can aid a user in judging how much
1008 confidence to have in an alignment.")
1009 ;; Most of the sources are in the public domain, with the following
1012 ;; * ./c++/include/util/bitset/
1013 ;; * ./c++/src/html/ncbi_menu*.js
1015 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1017 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1019 ;; * ./c++/src/corelib/teamcity_*
1020 (license (list license:public-domain
1026 (define-public bless
1032 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1036 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1037 (modules '((guix build utils)))
1040 ;; Remove bundled boost, pigz, zlib, and .git directory
1041 ;; FIXME: also remove bundled sources for murmurhash3 and
1042 ;; kmc once packaged.
1043 (delete-file-recursively "boost")
1044 (delete-file-recursively "pigz")
1045 (delete-file-recursively "google-sparsehash")
1046 (delete-file-recursively "zlib")
1047 (delete-file-recursively ".git")
1049 (build-system gnu-build-system)
1051 '(#:tests? #f ;no "check" target
1053 (list (string-append "ZLIB="
1054 (assoc-ref %build-inputs "zlib")
1056 (string-append "LDFLAGS="
1057 (string-join '("-lboost_filesystem"
1064 (modify-phases %standard-phases
1065 (add-after 'unpack 'do-not-build-bundled-pigz
1066 (lambda* (#:key inputs outputs #:allow-other-keys)
1067 (substitute* "Makefile"
1068 (("cd pigz/pigz-2.3.3; make") ""))
1070 (add-after 'unpack 'patch-paths-to-executables
1071 (lambda* (#:key inputs outputs #:allow-other-keys)
1072 (substitute* "parse_args.cpp"
1073 (("kmc_binary = .*")
1074 (string-append "kmc_binary = \""
1075 (assoc-ref outputs "out")
1077 (("pigz_binary = .*")
1078 (string-append "pigz_binary = \""
1079 (assoc-ref inputs "pigz")
1083 (lambda* (#:key outputs #:allow-other-keys)
1084 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1085 (for-each (lambda (file)
1086 (install-file file bin))
1087 '("bless" "kmc/bin/kmc"))
1089 (delete 'configure))))
1093 `(("openmpi" ,openmpi)
1095 ("sparsehash" ,sparsehash)
1098 (supported-systems '("x86_64-linux"))
1099 (home-page "http://sourceforge.net/p/bless-ec/wiki/Home/")
1100 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1102 "@dfn{Bloom-filter-based error correction solution for high-throughput
1103 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1104 correction tool for genomic reads produced by @dfn{Next-generation
1105 sequencing} (NGS). BLESS produces accurate correction results with much less
1106 memory compared with previous solutions and is also able to tolerate a higher
1107 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1108 errors at the end of reads.")
1109 (license license:gpl3+)))
1111 (define-public bowtie
1117 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1119 (file-name (string-append name "-" version ".tar.gz"))
1122 "1vp5db8i7is57iwjybcdg18f5ivyzlj5g1ix1nlvxainzivhz55g"))
1123 (modules '((guix build utils)))
1125 '(substitute* "Makefile"
1126 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1127 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1128 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1129 (build-system gnu-build-system)
1130 (inputs `(("perl" ,perl)
1131 ("perl-clone" ,perl-clone)
1132 ("perl-test-deep" ,perl-test-deep)
1133 ("perl-test-simple" ,perl-test-simple)
1134 ("python" ,python-2)
1140 (string-append "prefix=" (assoc-ref %outputs "out")))
1146 (lambda* (#:key outputs #:allow-other-keys)
1148 "scripts/test/simple_tests.pl"
1149 "--bowtie2=./bowtie2"
1150 "--bowtie2-build=./bowtie2-build"))
1151 %standard-phases))))
1152 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1153 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1155 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1156 reads to long reference sequences. It is particularly good at aligning reads
1157 of about 50 up to 100s or 1,000s of characters, and particularly good at
1158 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1159 genome with an FM Index to keep its memory footprint small: for the human
1160 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1161 gapped, local, and paired-end alignment modes.")
1162 (supported-systems '("x86_64-linux"))
1163 (license license:gpl3+)))
1165 (define-public tophat
1172 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1176 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1177 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1178 (modules '((guix build utils)))
1181 ;; Remove bundled SeqAn and samtools
1182 (delete-file-recursively "src/SeqAn-1.3")
1183 (delete-file-recursively "src/samtools-0.1.18")
1185 (build-system gnu-build-system)
1187 '(#:parallel-build? #f ; not supported
1189 (modify-phases %standard-phases
1190 (add-after 'unpack 'use-system-samtools
1191 (lambda* (#:key inputs #:allow-other-keys)
1192 (substitute* "src/Makefile.in"
1193 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1194 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1195 (("SAMPROG = samtools_0\\.1\\.18") "")
1196 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1197 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1198 (substitute* '("src/common.cpp"
1200 (("samtools_0.1.18") (which "samtools")))
1201 (substitute* '("src/common.h"
1202 "src/bam2fastx.cpp")
1203 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1204 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1205 (substitute* '("src/bwt_map.h"
1207 "src/align_status.h")
1208 (("#include <bam.h>") "#include <samtools/bam.h>")
1209 (("#include <sam.h>") "#include <samtools/sam.h>"))
1214 ("samtools" ,samtools-0.1)
1215 ("ncurses" ,ncurses)
1216 ("python" ,python-2)
1220 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1221 (synopsis "Spliced read mapper for RNA-Seq data")
1223 "TopHat is a fast splice junction mapper for nucleotide sequence
1224 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1225 mammalian-sized genomes using the ultra high-throughput short read
1226 aligner Bowtie, and then analyzes the mapping results to identify
1227 splice junctions between exons.")
1228 ;; TopHat is released under the Boost Software License, Version 1.0
1229 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1230 (license license:boost1.0)))
1238 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1239 version ".tar.bz2"))
1242 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
1243 (build-system gnu-build-system)
1245 '(#:tests? #f ;no "check" target
1249 (lambda* (#:key outputs #:allow-other-keys)
1250 (let ((bin (string-append
1251 (assoc-ref outputs "out") "/bin"))
1253 (assoc-ref outputs "out") "/share/doc/bwa"))
1255 (assoc-ref outputs "out") "/share/man/man1")))
1256 (install-file "bwa" bin)
1257 (install-file "README.md" doc)
1258 (install-file "bwa.1" man)))
1259 ;; no "configure" script
1260 (alist-delete 'configure %standard-phases))))
1261 (inputs `(("zlib" ,zlib)))
1262 ;; Non-portable SSE instructions are used so building fails on platforms
1263 ;; other than x86_64.
1264 (supported-systems '("x86_64-linux"))
1265 (home-page "http://bio-bwa.sourceforge.net/")
1266 (synopsis "Burrows-Wheeler sequence aligner")
1268 "BWA is a software package for mapping low-divergent sequences against a
1269 large reference genome, such as the human genome. It consists of three
1270 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1271 designed for Illumina sequence reads up to 100bp, while the rest two for
1272 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1273 features such as long-read support and split alignment, but BWA-MEM, which is
1274 the latest, is generally recommended for high-quality queries as it is faster
1275 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1276 70-100bp Illumina reads.")
1277 (license license:gpl3+)))
1279 (define-public bwa-pssm
1280 (package (inherit bwa)
1285 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1286 "archive/" version ".tar.gz"))
1287 (file-name (string-append name "-" version ".tar.gz"))
1290 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1291 (build-system gnu-build-system)
1296 (home-page "http://bwa-pssm.binf.ku.dk/")
1297 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1299 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1300 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1301 existing aligners it is fast and sensitive. Unlike most other aligners,
1302 however, it is also adaptible in the sense that one can direct the alignment
1303 based on known biases within the data set. It is coded as a modification of
1304 the original BWA alignment program and shares the genome index structure as
1305 well as many of the command line options.")
1306 (license license:gpl3+)))
1308 (define-public python2-bx-python
1310 (name "python2-bx-python")
1315 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
1319 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
1320 (modules '((guix build utils)))
1322 '(substitute* "setup.py"
1323 ;; remove dependency on outdated "distribute" module
1324 (("^from distribute_setup import use_setuptools") "")
1325 (("^use_setuptools\\(\\)") "")))))
1326 (build-system python-build-system)
1328 `(#:tests? #f ;tests fail because test data are not included
1329 #:python ,python-2))
1331 `(("python-numpy" ,python2-numpy)
1334 `(("python-nose" ,python2-nose)))
1335 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1336 (synopsis "Tools for manipulating biological data")
1338 "bx-python provides tools for manipulating biological data, particularly
1339 multiple sequence alignments.")
1340 (license license:expat)))
1342 (define-public python-pysam
1344 (name "python-pysam")
1348 ;; Test data is missing on PyPi.
1350 "https://github.com/pysam-developers/pysam/archive/v"
1352 (file-name (string-append name "-" version ".tar.gz"))
1355 "0y41ssbg6nvn2jgcbnrvkzblpjcwszaiv1rgyd8dwzjkrbfsgsmc"))
1356 (modules '((guix build utils)))
1358 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1359 '(delete-file-recursively "htslib"))))
1360 (build-system python-build-system)
1363 (modify-phases %standard-phases
1364 (add-before 'build 'set-flags
1365 (lambda* (#:key inputs #:allow-other-keys)
1366 (setenv "HTSLIB_MODE" "external")
1367 (setenv "HTSLIB_LIBRARY_DIR"
1368 (string-append (assoc-ref inputs "htslib") "/lib"))
1369 (setenv "HTSLIB_INCLUDE_DIR"
1370 (string-append (assoc-ref inputs "htslib") "/include"))
1371 (setenv "LDFLAGS" "-lncurses")
1372 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1375 (add-after 'install 'check
1376 (lambda* (#:key inputs outputs #:allow-other-keys)
1377 (setenv "PYTHONPATH"
1379 (getenv "PYTHONPATH")
1380 ":" (assoc-ref outputs "out")
1382 (string-take (string-take-right
1383 (assoc-ref inputs "python") 5) 3)
1385 ;; Step out of source dir so python does not import from CWD.
1387 (setenv "HOME" "/tmp")
1388 (and (zero? (system* "make" "-C" "pysam_data"))
1389 (zero? (system* "make" "-C" "cbcf_data"))
1390 (zero? (system* "nosetests" "-v"))))))))
1392 `(("htslib" ,htslib))) ; Included from installed header files.
1394 `(("ncurses" ,ncurses)
1397 `(("python-cython" ,python-cython)
1398 ;; Dependencies below are are for tests only.
1399 ("samtools" ,samtools)
1400 ("bcftools" ,bcftools)
1401 ("python-nose" ,python-nose)))
1402 (home-page "https://github.com/pysam-developers/pysam")
1403 (synopsis "Python bindings to the SAMtools C API")
1405 "Pysam is a Python module for reading and manipulating files in the
1406 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1407 also includes an interface for tabix.")
1408 (license license:expat)))
1410 (define-public python2-pysam
1411 (package-with-python2 python-pysam))
1413 (define-public python-twobitreader
1415 (name "python-twobitreader")
1419 (uri (pypi-uri "twobitreader" version))
1422 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1423 (build-system python-build-system)
1425 '(;; Tests are not distributed in the PyPi release.
1426 ;; TODO Try building from the Git repo or asking the upstream maintainer
1427 ;; to distribute the tests on PyPi.
1430 `(("python-sphinx" ,python-sphinx)))
1431 (home-page "https://github.com/benjschiller/twobitreader")
1432 (synopsis "Python library for reading .2bit files")
1434 "twobitreader is a Python library for reading .2bit files as used by the
1435 UCSC genome browser.")
1436 (license license:artistic2.0)))
1438 (define-public python2-twobitreader
1439 (package-with-python2 python-twobitreader))
1441 (define-public python-plastid
1443 (name "python-plastid")
1447 (uri (pypi-uri "plastid" version))
1450 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
1451 (build-system python-build-system)
1453 ;; Some test files are not included.
1456 `(("python-numpy" ,python-numpy)
1457 ("python-scipy" ,python-scipy)
1458 ("python-pandas" ,python-pandas)
1459 ("python-pysam" ,python-pysam)
1460 ("python-matplotlib" ,python-matplotlib)
1461 ("python-biopython" ,python-biopython)
1462 ("python-twobitreader" ,python-twobitreader)
1463 ("python-termcolor" ,python-termcolor)))
1465 `(("python-cython" ,python-cython)
1466 ("python-nose" ,python-nose)))
1467 (home-page "https://github.com/joshuagryphon/plastid")
1468 (synopsis "Python library for genomic analysis")
1470 "plastid is a Python library for genomic analysis – in particular,
1471 high-throughput sequencing data – with an emphasis on simplicity.")
1472 (license license:bsd-3)))
1474 (define-public python2-plastid
1475 (package-with-python2 python-plastid))
1477 (define-public cd-hit
1483 (uri (string-append "https://github.com/weizhongli/cdhit"
1484 "/releases/download/V" version
1485 "/cd-hit-v" version "-2016-0304.tar.gz"))
1488 "15db0hq38yyifwqx9b6l34z14jcq576dmjavhj8a426c18lvnhp3"))))
1489 (build-system gnu-build-system)
1491 `(#:tests? #f ; there are no tests
1493 ;; Executables are copied directly to the PREFIX.
1494 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1496 (modify-phases %standard-phases
1497 ;; No "configure" script
1499 ;; Remove sources of non-determinism
1500 (add-after 'unpack 'be-timeless
1502 (substitute* "cdhit-utility.c++"
1503 ((" \\(built on \" __DATE__ \"\\)") ""))
1504 (substitute* "cdhit-common.c++"
1505 (("__DATE__") "\"0\"")
1506 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1508 ;; The "install" target does not create the target directory
1509 (add-before 'install 'create-target-dir
1510 (lambda* (#:key outputs #:allow-other-keys)
1511 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1515 (home-page "http://weizhongli-lab.org/cd-hit/")
1516 (synopsis "Cluster and compare protein or nucleotide sequences")
1518 "CD-HIT is a program for clustering and comparing protein or nucleotide
1519 sequences. CD-HIT is designed to be fast and handle extremely large
1521 ;; The manual says: "It can be copied under the GNU General Public License
1522 ;; version 2 (GPLv2)."
1523 (license license:gpl2)))
1525 (define-public clipper
1532 "https://github.com/YeoLab/clipper/archive/"
1534 (file-name (string-append name "-" version ".tar.gz"))
1537 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1538 (modules '((guix build utils)))
1541 ;; remove unnecessary setup dependency
1542 (substitute* "setup.py"
1543 (("setup_requires = .*") ""))
1544 (for-each delete-file
1545 '("clipper/src/peaks.so"
1546 "clipper/src/readsToWiggle.so"))
1547 (delete-file-recursively "dist/")
1549 (build-system python-build-system)
1550 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1553 ("python-pybedtools" ,python2-pybedtools)
1554 ("python-cython" ,python2-cython)
1555 ("python-scikit-learn" ,python2-scikit-learn)
1556 ("python-matplotlib" ,python2-matplotlib)
1557 ("python-pandas" ,python2-pandas)
1558 ("python-pysam" ,python2-pysam)
1559 ("python-numpy" ,python2-numpy)
1560 ("python-scipy" ,python2-scipy)))
1562 `(("python-mock" ,python2-mock) ; for tests
1563 ("python-pytz" ,python2-pytz))) ; for tests
1564 (home-page "https://github.com/YeoLab/clipper")
1565 (synopsis "CLIP peak enrichment recognition")
1567 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1568 (license license:gpl2)))
1570 (define-public codingquarry
1572 (name "codingquarry")
1577 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1581 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1582 (build-system gnu-build-system)
1584 '(#:tests? #f ; no "check" target
1586 (modify-phases %standard-phases
1589 (lambda* (#:key outputs #:allow-other-keys)
1590 (let* ((out (assoc-ref outputs "out"))
1591 (bin (string-append out "/bin"))
1592 (doc (string-append out "/share/doc/codingquarry")))
1593 (install-file "INSTRUCTIONS.pdf" doc)
1594 (copy-recursively "QuarryFiles"
1595 (string-append out "/QuarryFiles"))
1596 (install-file "CodingQuarry" bin)
1597 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1598 (inputs `(("openmpi" ,openmpi)))
1599 (native-search-paths
1600 (list (search-path-specification
1601 (variable "QUARRY_PATH")
1602 (files '("QuarryFiles")))))
1603 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1604 (synopsis "Fungal gene predictor")
1605 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1606 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1607 (home-page "https://sourceforge.net/projects/codingquarry/")
1608 (license license:gpl3+)))
1610 (define-public couger
1617 "http://couger.oit.duke.edu/static/assets/COUGER"
1621 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1622 (build-system gnu-build-system)
1626 (modify-phases %standard-phases
1631 (lambda* (#:key outputs #:allow-other-keys)
1632 (let ((out (assoc-ref outputs "out")))
1633 (copy-recursively "src" (string-append out "/src"))
1634 (mkdir (string-append out "/bin"))
1635 ;; Add "src" directory to module lookup path.
1636 (substitute* "couger"
1638 (string-append "import sys\nsys.path.append(\""
1639 out "\")\nfrom argparse")))
1640 (copy-file "couger" (string-append out "/bin/couger")))
1643 'install 'wrap-program
1644 (lambda* (#:key inputs outputs #:allow-other-keys)
1645 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1646 (let* ((out (assoc-ref outputs "out"))
1647 (path (getenv "PYTHONPATH")))
1648 (wrap-program (string-append out "/bin/couger")
1649 `("PYTHONPATH" ":" prefix (,path))))
1652 `(("python" ,python-2)
1653 ("python2-pillow" ,python2-pillow)
1654 ("python2-numpy" ,python2-numpy)
1655 ("python2-scipy" ,python2-scipy)
1656 ("python2-matplotlib" ,python2-matplotlib)))
1660 ("randomjungle" ,randomjungle)))
1662 `(("unzip" ,unzip)))
1663 (home-page "http://couger.oit.duke.edu")
1664 (synopsis "Identify co-factors in sets of genomic regions")
1666 "COUGER can be applied to any two sets of genomic regions bound by
1667 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1668 putative co-factors that provide specificity to each TF. The framework
1669 determines the genomic targets uniquely-bound by each TF, and identifies a
1670 small set of co-factors that best explain the in vivo binding differences
1671 between the two TFs.
1673 COUGER uses classification algorithms (support vector machines and random
1674 forests) with features that reflect the DNA binding specificities of putative
1675 co-factors. The features are generated either from high-throughput TF-DNA
1676 binding data (from protein binding microarray experiments), or from large
1677 collections of DNA motifs.")
1678 (license license:gpl3+)))
1680 (define-public clustal-omega
1682 (name "clustal-omega")
1687 "http://www.clustal.org/omega/clustal-omega-"
1691 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1692 (build-system gnu-build-system)
1694 `(("argtable" ,argtable)))
1695 (home-page "http://www.clustal.org/omega/")
1696 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1698 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1699 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1700 of handling data-sets of hundreds of thousands of sequences in reasonable
1702 (license license:gpl2+)))
1704 (define-public crossmap
1710 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1714 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1715 ;; This patch has been sent upstream already and is available
1716 ;; for download from Sourceforge, but it has not been merged.
1717 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1718 (modules '((guix build utils)))
1719 ;; remove bundled copy of pysam
1721 '(delete-file-recursively "lib/pysam"))))
1722 (build-system python-build-system)
1724 `(#:python ,python-2
1728 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1731 `(("python-numpy" ,python2-numpy)
1732 ("python-pysam" ,python2-pysam)
1735 `(("python-cython" ,python2-cython)
1736 ("python-nose" ,python2-nose)))
1737 (home-page "http://crossmap.sourceforge.net/")
1738 (synopsis "Convert genome coordinates between assemblies")
1740 "CrossMap is a program for conversion of genome coordinates or annotation
1741 files between different genome assemblies. It supports most commonly used
1742 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1743 (license license:gpl2+)))
1745 (define-public cufflinks
1751 (uri (string-append "http://cole-trapnell-lab.github.io/"
1752 "cufflinks/assets/downloads/cufflinks-"
1756 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1757 (build-system gnu-build-system)
1761 ;; The includes for "eigen" are located in a subdirectory.
1762 (string-append "EIGEN_CPPFLAGS="
1763 "-I" (assoc-ref %build-inputs "eigen")
1765 ;; Cufflinks must be linked with various boost libraries.
1766 (string-append "LDFLAGS="
1767 (string-join '("-lboost_system"
1768 "-lboost_serialization"
1769 "-lboost_thread"))))
1771 (modify-phases %standard-phases
1772 (add-after 'unpack 'fix-search-for-bam
1774 (substitute* '("ax_bam.m4"
1777 (("<bam/sam\\.h>") "<samtools/sam.h>")
1778 (("<bam/bam\\.h>") "<samtools/bam.h>")
1779 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1782 (list (string-append "--with-bam="
1783 (assoc-ref %build-inputs "samtools")))))
1786 ("samtools" ,samtools-0.1)
1789 ("python" ,python-2)
1791 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1792 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1794 "Cufflinks assembles RNA transcripts, estimates their abundances,
1795 and tests for differential expression and regulation in RNA-Seq
1796 samples. It accepts aligned RNA-Seq reads and assembles the
1797 alignments into a parsimonious set of transcripts. Cufflinks then
1798 estimates the relative abundances of these transcripts based on how
1799 many reads support each one, taking into account biases in library
1800 preparation protocols.")
1801 (license license:boost1.0)))
1803 (define-public cutadapt
1810 "https://github.com/marcelm/cutadapt/archive/v"
1812 (file-name (string-append name "-" version ".tar.gz"))
1815 "161bp87y6gd6r5bmvjpn2b1k942i3fizfpa139f0jn6jv1wcp5h5"))))
1816 (build-system python-build-system)
1818 ;; tests must be run after install
1819 `(#:phases (alist-cons-after
1821 (lambda* (#:key inputs outputs #:allow-other-keys)
1822 (setenv "PYTHONPATH"
1824 (getenv "PYTHONPATH")
1825 ":" (assoc-ref outputs "out")
1827 (string-take (string-take-right
1828 (assoc-ref inputs "python") 5) 3)
1830 (zero? (system* "nosetests" "-P" "tests")))
1831 (alist-delete 'check %standard-phases))))
1833 `(("python-cython" ,python-cython)
1834 ("python-nose" ,python-nose)))
1835 (home-page "https://code.google.com/p/cutadapt/")
1836 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1838 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1839 other types of unwanted sequence from high-throughput sequencing reads.")
1840 (license license:expat)))
1842 (define-public libbigwig
1848 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1849 "archive/" version ".tar.gz"))
1850 (file-name (string-append name "-" version ".tar.gz"))
1853 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1854 (build-system gnu-build-system)
1856 `(#:test-target "test"
1859 (string-append "prefix=" (assoc-ref %outputs "out")))
1861 (modify-phases %standard-phases
1863 (add-before 'check 'disable-curl-test
1865 (substitute* "Makefile"
1866 (("./test/testRemote.*") ""))
1868 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1869 ;; there has not yet been a release containing this change.
1870 (add-before 'install 'create-target-dirs
1871 (lambda* (#:key outputs #:allow-other-keys)
1872 (let ((out (assoc-ref outputs "out")))
1873 (mkdir-p (string-append out "/lib"))
1874 (mkdir-p (string-append out "/include"))
1880 `(("doxygen" ,doxygen)))
1881 (home-page "https://github.com/dpryan79/libBigWig")
1882 (synopsis "C library for handling bigWig files")
1884 "This package provides a C library for parsing local and remote BigWig
1886 (license license:expat)))
1888 (define-public python-pybigwig
1890 (name "python-pybigwig")
1894 (uri (pypi-uri "pyBigWig" version))
1897 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1898 (modules '((guix build utils)))
1901 ;; Delete bundled libBigWig sources
1902 (delete-file-recursively "libBigWig")))))
1903 (build-system python-build-system)
1906 (modify-phases %standard-phases
1907 (add-after 'unpack 'link-with-libBigWig
1908 (lambda* (#:key inputs #:allow-other-keys)
1909 (substitute* "setup.py"
1910 (("libs=\\[") "libs=[\"BigWig\", "))
1913 `(("libbigwig" ,libbigwig)
1916 (home-page "https://github.com/dpryan79/pyBigWig")
1917 (synopsis "Access bigWig files in Python using libBigWig")
1919 "This package provides Python bindings to the libBigWig library for
1920 accessing bigWig files.")
1921 (license license:expat)))
1923 (define-public python2-pybigwig
1924 (package-with-python2 python-pybigwig))
1926 (define-public python-dendropy
1928 (name "python-dendropy")
1933 (uri (pypi-uri "DendroPy" version))
1936 "1jfz7gp18wph311w1yygbvjanb3n5mdqal439bb6myw41dwb5m63"))
1937 ;; There are two known test failures that will be fixed in the next
1938 ;; release after 4.1.0.
1939 ;; https://github.com/jeetsukumaran/DendroPy/issues/48
1940 (patches (search-patches
1941 "python-dendropy-exclude-failing-tests.patch"))))
1942 (build-system python-build-system)
1943 (home-page "http://packages.python.org/DendroPy/")
1944 (synopsis "Library for phylogenetics and phylogenetic computing")
1946 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1947 writing, simulation, processing and manipulation of phylogenetic
1948 trees (phylogenies) and characters.")
1949 (license license:bsd-3)
1950 (properties `((python2-variant . ,(delay python2-dendropy))))))
1952 (define-public python2-dendropy
1953 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1956 ;; Do not use same source as 'python-dendropy' because the patched
1957 ;; failing tests do not occur on Python 2.
1961 (uri (pypi-uri "DendroPy" (package-version base)))
1964 "1jfz7gp18wph311w1yygbvjanb3n5mdqal439bb6myw41dwb5m63"))))
1966 `(#:python ,python-2
1968 (modify-phases %standard-phases
1970 ;; There is currently a test failure that only happens on some
1971 ;; systems, and only using "setup.py test"
1972 (lambda _ (zero? (system* "nosetests")))))))
1973 (native-inputs `(("python2-nose" ,python2-nose)
1974 ,@(package-native-inputs base))))))
1977 (define-public deeptools
1983 (uri (string-append "https://github.com/fidelram/deepTools/"
1984 "archive/" version ".tar.gz"))
1985 (file-name (string-append name "-" version ".tar.gz"))
1988 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
1989 (build-system python-build-system)
1991 `(#:python ,python-2))
1993 `(("python-scipy" ,python2-scipy)
1994 ("python-numpy" ,python2-numpy)
1995 ("python-numpydoc" ,python2-numpydoc)
1996 ("python-matplotlib" ,python2-matplotlib)
1997 ("python-bx-python" ,python2-bx-python)
1998 ("python-pysam" ,python2-pysam)
1999 ("python-pybigwig" ,python2-pybigwig)))
2001 `(("python-mock" ,python2-mock) ;for tests
2002 ("python-pytz" ,python2-pytz))) ;for tests
2003 (home-page "https://github.com/fidelram/deepTools")
2004 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2006 "DeepTools addresses the challenge of handling the large amounts of data
2007 that are now routinely generated from DNA sequencing centers. To do so,
2008 deepTools contains useful modules to process the mapped reads data to create
2009 coverage files in standard bedGraph and bigWig file formats. By doing so,
2010 deepTools allows the creation of normalized coverage files or the comparison
2011 between two files (for example, treatment and control). Finally, using such
2012 normalized and standardized files, multiple visualizations can be created to
2013 identify enrichments with functional annotations of the genome.")
2014 (license license:gpl3+)))
2016 (define-public diamond
2023 "https://github.com/bbuchfink/diamond/archive/v"
2025 (file-name (string-append name "-" version ".tar.gz"))
2028 "0g0zdyfnri9v7nfbh8f7zqs4af1xydqkiw8m0cx4jc2ql4chpf6a"))))
2029 (build-system cmake-build-system)
2031 '(#:tests? #f ; no "check" target
2033 (modify-phases %standard-phases
2034 (add-after 'unpack 'remove-native-compilation
2036 (substitute* "CMakeLists.txt" (("-march=native") ""))
2040 (home-page "https://github.com/bbuchfink/diamond")
2041 (synopsis "Accelerated BLAST compatible local sequence aligner")
2043 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2044 translated DNA query sequences against a protein reference database (BLASTP
2045 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2046 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2047 data and settings.")
2048 ;; diamond fails to build on other platforms
2049 ;; https://github.com/bbuchfink/diamond/issues/18
2050 (supported-systems '("x86_64-linux"))
2051 (license (license:non-copyleft "file://src/COPYING"
2052 "See src/COPYING in the distribution."))))
2054 (define-public discrover
2061 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2063 (file-name (string-append name "-" version ".tar.gz"))
2066 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2067 (build-system cmake-build-system)
2068 (arguments `(#:tests? #f)) ; there are no tests
2073 `(("texlive" ,texlive)
2074 ("imagemagick" ,imagemagick)))
2075 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2076 (synopsis "Discover discriminative nucleotide sequence motifs")
2077 (description "Discrover is a motif discovery method to find binding sites
2078 of nucleic acid binding proteins.")
2079 (license license:gpl3+)))
2081 (define-public eigensoft
2082 (let ((revision "1")
2083 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2086 (version (string-append "6.1.2-"
2088 (string-take commit 9)))
2093 (url "https://github.com/DReichLab/EIG.git")
2095 (file-name (string-append "eigensoft-" commit "-checkout"))
2098 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2099 (modules '((guix build utils)))
2100 ;; Remove pre-built binaries.
2102 (delete-file-recursively "bin")
2105 (build-system gnu-build-system)
2107 `(#:tests? #f ; There are no tests.
2108 #:make-flags '("CC=gcc")
2110 (modify-phases %standard-phases
2111 ;; There is no configure phase, but the Makefile is in a
2116 ;; The link flags are incomplete.
2117 (substitute* "Makefile"
2118 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2120 ;; The provided install target only copies executables to
2121 ;; the "bin" directory in the build root.
2122 (add-after 'install 'actually-install
2123 (lambda* (#:key outputs #:allow-other-keys)
2124 (let* ((out (assoc-ref outputs "out"))
2125 (bin (string-append out "/bin")))
2126 (for-each (lambda (file)
2127 (install-file file bin))
2128 (find-files "../bin" ".*"))
2133 ("openblas" ,openblas)
2135 ("gfortran" ,gfortran "lib")))
2136 (home-page "https://github.com/DReichLab/EIG")
2137 (synopsis "Tools for population genetics")
2138 (description "The EIGENSOFT package provides tools for population
2139 genetics and stratification correction. EIGENSOFT implements methods commonly
2140 used in population genetics analyses such as PCA, computation of Tracy-Widom
2141 statistics, and finding related individuals in structured populations. It
2142 comes with a built-in plotting script and supports multiple file formats and
2143 quantitative phenotypes.")
2144 ;; The license of the eigensoft tools is Expat, but since it's
2145 ;; linking with the GNU Scientific Library (GSL) the effective
2146 ;; license is the GPL.
2147 (license license:gpl3+))))
2149 (define-public edirect
2155 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2156 "versions/2016-05-03/edirect.tar.gz"))
2159 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2160 (build-system perl-build-system)
2162 `(#:tests? #f ;no "check" target
2164 (modify-phases %standard-phases
2168 (lambda* (#:key outputs #:allow-other-keys)
2169 (let ((target (string-append (assoc-ref outputs "out")
2172 (copy-file "edirect.pl"
2173 (string-append target "/edirect.pl"))
2176 'install 'wrap-program
2177 (lambda* (#:key inputs outputs #:allow-other-keys)
2178 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2179 (let* ((out (assoc-ref outputs "out"))
2180 (path (getenv "PERL5LIB")))
2181 (wrap-program (string-append out "/bin/edirect.pl")
2182 `("PERL5LIB" ":" prefix (,path)))))))))
2184 `(("perl-html-parser" ,perl-html-parser)
2185 ("perl-encode-locale" ,perl-encode-locale)
2186 ("perl-file-listing" ,perl-file-listing)
2187 ("perl-html-tagset" ,perl-html-tagset)
2188 ("perl-html-tree" ,perl-html-tree)
2189 ("perl-http-cookies" ,perl-http-cookies)
2190 ("perl-http-date" ,perl-http-date)
2191 ("perl-http-message" ,perl-http-message)
2192 ("perl-http-negotiate" ,perl-http-negotiate)
2193 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2194 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2195 ("perl-net-http" ,perl-net-http)
2196 ("perl-uri" ,perl-uri)
2197 ("perl-www-robotrules" ,perl-www-robotrules)
2199 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2200 (synopsis "Tools for accessing the NCBI's set of databases")
2202 "Entrez Direct (EDirect) is a method for accessing the National Center
2203 for Biotechnology Information's (NCBI) set of interconnected
2204 databases (publication, sequence, structure, gene, variation, expression,
2205 etc.) from a terminal. Functions take search terms from command-line
2206 arguments. Individual operations are combined to build multi-step queries.
2207 Record retrieval and formatting normally complete the process.
2209 EDirect also provides an argument-driven function that simplifies the
2210 extraction of data from document summaries or other results that are returned
2211 in structured XML format. This can eliminate the need for writing custom
2212 software to answer ad hoc questions.")
2213 (license license:public-domain)))
2215 (define-public exonerate
2224 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2225 "exonerate-" version ".tar.gz"))
2228 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2229 (build-system gnu-build-system)
2231 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2233 `(("pkg-config" ,pkg-config)))
2237 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2238 (synopsis "Generic tool for biological sequence alignment")
2240 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2241 the alignment of sequences using a many alignment models, either exhaustive
2242 dynamic programming or a variety of heuristics.")
2243 (license license:gpl3)))
2245 (define-public express
2253 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2254 version "/express-" version "-src.tgz"))
2257 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2258 (build-system cmake-build-system)
2260 `(#:tests? #f ;no "check" target
2263 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2264 (lambda* (#:key inputs #:allow-other-keys)
2265 (substitute* "CMakeLists.txt"
2266 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2267 "set(Boost_USE_STATIC_LIBS OFF)")
2268 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2269 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2270 (substitute* "src/CMakeLists.txt"
2271 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2272 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2277 ("bamtools" ,bamtools)
2278 ("protobuf" ,protobuf)
2280 (home-page "http://bio.math.berkeley.edu/eXpress")
2281 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2283 "eXpress is a streaming tool for quantifying the abundances of a set of
2284 target sequences from sampled subsequences. Example applications include
2285 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2286 analysis (from RNA-Seq), transcription factor binding quantification in
2287 ChIP-Seq, and analysis of metagenomic data.")
2288 (license license:artistic2.0)))
2290 (define-public express-beta-diversity
2292 (name "express-beta-diversity")
2298 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2300 (file-name (string-append name "-" version ".tar.gz"))
2303 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2304 (build-system gnu-build-system)
2307 (modify-phases %standard-phases
2309 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2311 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2313 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2315 (lambda* (#:key outputs #:allow-other-keys)
2316 (let ((bin (string-append (assoc-ref outputs "out")
2319 (copy-file "scripts/convertToEBD.py"
2320 (string-append bin "/convertToEBD.py"))
2321 (copy-file "bin/ExpressBetaDiversity"
2322 (string-append bin "/ExpressBetaDiversity"))
2325 `(("python" ,python-2)))
2326 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2327 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2329 "Express Beta Diversity (EBD) calculates ecological beta diversity
2330 (dissimilarity) measures between biological communities. EBD implements a
2331 variety of diversity measures including those that make use of phylogenetic
2332 similarity of community members.")
2333 (license license:gpl3+)))
2335 (define-public fasttree
2342 "http://www.microbesonline.org/fasttree/FastTree-"
2346 "0ljvvw8i1als1wbfzvrf15c3ii2vw9db20a259g6pzg34xyyb97k"))))
2347 (build-system gnu-build-system)
2349 `(#:tests? #f ; no "check" target
2351 (modify-phases %standard-phases
2355 (lambda* (#:key source #:allow-other-keys)
2356 (and (zero? (system* "gcc"
2358 "-finline-functions"
2365 (zero? (system* "gcc"
2369 "-finline-functions"
2377 (lambda* (#:key outputs #:allow-other-keys)
2378 (let ((bin (string-append (assoc-ref outputs "out")
2381 (copy-file "FastTree"
2382 (string-append bin "/FastTree"))
2383 (copy-file "FastTreeMP"
2384 (string-append bin "/FastTreeMP"))
2386 (home-page "http://www.microbesonline.org/fasttree")
2387 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2389 "FastTree can handle alignments with up to a million of sequences in a
2390 reasonable amount of time and memory. For large alignments, FastTree is
2391 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2392 (license license:gpl2+)))
2394 (define-public fastx-toolkit
2396 (name "fastx-toolkit")
2402 "https://github.com/agordon/fastx_toolkit/releases/download/"
2403 version "/fastx_toolkit-" version ".tar.bz2"))
2406 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2407 (build-system gnu-build-system)
2409 `(("libgtextutils" ,libgtextutils)))
2411 `(("pkg-config" ,pkg-config)))
2412 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2413 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2415 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2416 FASTA/FASTQ files preprocessing.
2418 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2419 containing multiple short-reads sequences. The main processing of such
2420 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2421 is sometimes more productive to preprocess the files before mapping the
2422 sequences to the genome---manipulating the sequences to produce better mapping
2423 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2424 (license license:agpl3+)))
2426 (define-public flexbar
2433 (string-append "mirror://sourceforge/flexbar/"
2434 version "/flexbar_v" version "_src.tgz"))
2437 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2438 (build-system cmake-build-system)
2440 `(#:configure-flags (list
2441 (string-append "-DFLEXBAR_BINARY_DIR="
2442 (assoc-ref %outputs "out")
2447 (lambda* (#:key outputs #:allow-other-keys)
2448 (setenv "PATH" (string-append
2449 (assoc-ref outputs "out") "/bin:"
2451 (chdir "../flexbar_v2.5_src/test")
2452 (zero? (system* "bash" "flexbar_validate.sh")))
2453 (alist-delete 'install %standard-phases))))
2458 `(("pkg-config" ,pkg-config)
2460 (home-page "http://flexbar.sourceforge.net")
2461 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2463 "Flexbar preprocesses high-throughput nucleotide sequencing data
2464 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2465 Moreover, trimming and filtering features are provided. Flexbar increases
2466 read mapping rates and improves genome and transcriptome assemblies. It
2467 supports next-generation sequencing data in fasta/q and csfasta/q format from
2468 Illumina, Roche 454, and the SOLiD platform.")
2469 (license license:gpl3)))
2471 (define-public fraggenescan
2473 (name "fraggenescan")
2479 (string-append "mirror://sourceforge/fraggenescan/"
2480 "FragGeneScan" version ".tar.gz"))
2482 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
2483 (build-system gnu-build-system)
2486 (modify-phases %standard-phases
2488 (add-before 'build 'patch-paths
2489 (lambda* (#:key outputs #:allow-other-keys)
2490 (let* ((out (string-append (assoc-ref outputs "out")))
2491 (share (string-append out "/share/fraggenescan/")))
2492 (substitute* "run_FragGeneScan.pl"
2494 (string-append "system(\"" (which "rm")))
2496 (string-append "system(\"" (which "mv")))
2497 ;; This script and other programs expect the training files
2498 ;; to be in the non-standard location bin/train/XXX. Change
2499 ;; this to be share/fraggenescan/train/XXX instead.
2500 (("^\\$train.file = \\$dir.*")
2501 (string-append "$train_file = \""
2503 "train/\".$FGS_train_file;")))
2504 (substitute* "run_hmm.c"
2505 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2506 (string-append " strcpy(train_dir, \"" share "/train/\");")))
2507 (substitute* "post_process.pl"
2508 (("^my \\$dir = substr.*")
2509 (string-append "my $dir = \"" share "\";"))))
2512 (lambda _ (and (zero? (system* "make" "clean"))
2513 (zero? (system* "make" "fgs")))))
2515 (lambda* (#:key outputs #:allow-other-keys)
2516 (let* ((out (string-append (assoc-ref outputs "out")))
2517 (bin (string-append out "/bin/"))
2518 (share (string-append out "/share/fraggenescan/train")))
2519 (install-file "run_FragGeneScan.pl" bin)
2520 (install-file "FragGeneScan" bin)
2521 (install-file "FGS_gff.py" bin)
2522 (install-file "post_process.pl" bin)
2523 (copy-recursively "train" share))))
2525 (add-after 'install 'post-install-check
2526 ;; In lieu of 'make check', run one of the examples and check the
2527 ;; output files gets created.
2528 (lambda* (#:key outputs #:allow-other-keys)
2529 (let* ((out (string-append (assoc-ref outputs "out")))
2530 (bin (string-append out "/bin/")))
2531 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
2532 "-genome=./example/NC_000913.fna"
2536 (file-exists? "test2.faa")
2537 (file-exists? "test2.ffn")
2538 (file-exists? "test2.gff")
2539 (file-exists? "test2.out"))))))))
2542 ("python" ,python-2))) ;not compatible with python 3.
2543 (home-page "https://sourceforge.net/projects/fraggenescan/")
2544 (synopsis "Finds potentially fragmented genes in short reads")
2546 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2547 short and error-prone DNA sequencing reads. It can also be applied to predict
2548 genes in incomplete assemblies or complete genomes.")
2549 ;; GPL3+ according to private correspondense with the authors.
2550 (license license:gpl3+)))
2552 (define-public fxtract
2553 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2561 "https://github.com/ctSkennerton/fxtract/archive/"
2563 (file-name (string-append "ctstennerton-util-"
2564 (string-take util-commit 7)
2568 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2569 (build-system gnu-build-system)
2571 `(#:make-flags (list
2572 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2574 #:test-target "fxtract_test"
2576 (modify-phases %standard-phases
2578 (add-before 'build 'copy-util
2579 (lambda* (#:key inputs #:allow-other-keys)
2581 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2583 ;; Do not use make install as this requires additional dependencies.
2585 (lambda* (#:key outputs #:allow-other-keys)
2586 (let* ((out (assoc-ref outputs "out"))
2587 (bin (string-append out"/bin")))
2588 (install-file "fxtract" bin)
2594 ;; ctskennerton-util is licensed under GPL2.
2595 `(("ctskennerton-util"
2599 (url "https://github.com/ctSkennerton/util.git")
2600 (commit util-commit)))
2601 (file-name (string-append
2602 "ctstennerton-util-" util-commit "-checkout"))
2605 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2606 (home-page "https://github.com/ctSkennerton/fxtract")
2607 (synopsis "Extract sequences from FASTA and FASTQ files")
2609 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2610 or FASTQ) file given a subsequence. It uses a simple substring search for
2611 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2612 lookups or multi-pattern searching as required. By default fxtract looks in
2613 the sequence of each record but can also be told to look in the header,
2614 comment or quality sections.")
2615 ;; 'util' requires SSE instructions.
2616 (supported-systems '("x86_64-linux"))
2617 (license license:expat))))
2626 "https://github.com/nboley/grit/archive/"
2628 (file-name (string-append name "-" version ".tar.gz"))
2631 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2632 (build-system python-build-system)
2634 `(#:python ,python-2
2637 'unpack 'generate-from-cython-sources
2638 (lambda* (#:key inputs outputs #:allow-other-keys)
2639 ;; Delete these C files to force fresh generation from pyx sources.
2640 (delete-file "grit/sparsify_support_fns.c")
2641 (delete-file "grit/call_peaks_support_fns.c")
2642 (substitute* "setup.py"
2643 (("Cython.Setup") "Cython.Build")
2644 ;; Add numpy include path to fix compilation
2646 (string-append "pyx\", ], include_dirs = ['"
2647 (assoc-ref inputs "python-numpy")
2648 "/lib/python2.7/site-packages/numpy/core/include/"
2652 `(("python-scipy" ,python2-scipy)
2653 ("python-numpy" ,python2-numpy)
2654 ("python-pysam" ,python2-pysam)
2655 ("python-networkx" ,python2-networkx)))
2657 `(("python-cython" ,python2-cython)))
2658 (home-page "http://grit-bio.org")
2659 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2661 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2662 full length transcript models. When none of these data sources are available,
2663 GRIT can be run by providing a candidate set of TES or TSS sites. In
2664 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2665 also be run in quantification mode, where it uses a provided GTF file and just
2666 estimates transcript expression.")
2667 (license license:gpl3+)))
2669 (define-public hisat
2676 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2677 version "-beta-source.zip"))
2680 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2681 (build-system gnu-build-system)
2683 `(#:tests? #f ;no check target
2684 #:make-flags '("allall"
2685 ;; Disable unsupported `popcnt' instructions on
2686 ;; architectures other than x86_64
2687 ,@(if (string-prefix? "x86_64"
2688 (or (%current-target-system)
2691 '("POPCNT_CAPABILITY=0")))
2694 'unpack 'patch-sources
2696 ;; XXX Cannot use snippet because zip files are not supported
2697 (substitute* "Makefile"
2698 (("^CC = .*$") "CC = gcc")
2699 (("^CPP = .*$") "CPP = g++")
2700 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2701 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2702 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2703 (substitute* '("hisat-build" "hisat-inspect")
2704 (("/usr/bin/env") (which "env"))))
2707 (lambda* (#:key outputs #:allow-other-keys)
2708 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2709 (for-each (lambda (file)
2710 (install-file file bin))
2713 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2714 (alist-delete 'configure %standard-phases)))))
2716 `(("unzip" ,unzip)))
2721 ;; Non-portable SSE instructions are used so building fails on platforms
2722 ;; other than x86_64.
2723 (supported-systems '("x86_64-linux"))
2724 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2725 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2727 "HISAT is a fast and sensitive spliced alignment program for mapping
2728 RNA-seq reads. In addition to one global FM index that represents a whole
2729 genome, HISAT uses a large set of small FM indexes that collectively cover the
2730 whole genome. These small indexes (called local indexes) combined with
2731 several alignment strategies enable effective alignment of RNA-seq reads, in
2732 particular, reads spanning multiple exons.")
2733 (license license:gpl3+)))
2735 (define-public hmmer
2742 "http://eddylab.org/software/hmmer"
2743 (version-prefix version 1) "/"
2744 version "/hmmer-" version ".tar.gz"))
2747 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
2748 (build-system gnu-build-system)
2749 (native-inputs `(("perl" ,perl)))
2750 (home-page "http://hmmer.org/")
2751 (synopsis "Biosequence analysis using profile hidden Markov models")
2753 "HMMER is used for searching sequence databases for homologs of protein
2754 sequences, and for making protein sequence alignments. It implements methods
2755 using probabilistic models called profile hidden Markov models (profile
2757 (license (list license:gpl3+
2758 ;; The bundled library 'easel' is distributed
2759 ;; under The Janelia Farm Software License.
2760 (license:non-copyleft
2761 "file://easel/LICENSE"
2762 "See easel/LICENSE in the distribution.")))))
2764 (define-public htseq
2771 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2775 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2776 (build-system python-build-system)
2777 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2778 ;; Numpy needs to be propagated when htseq is used as a Python library.
2780 `(("python-numpy" ,python2-numpy)))
2782 `(("python-pysam" ,python2-pysam)))
2783 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2784 (synopsis "Analysing high-throughput sequencing data with Python")
2786 "HTSeq is a Python package that provides infrastructure to process data
2787 from high-throughput sequencing assays.")
2788 (license license:gpl3+)))
2790 (define-public java-htsjdk
2792 (name "java-htsjdk")
2797 "https://github.com/samtools/htsjdk/archive/"
2799 (file-name (string-append name "-" version ".tar.gz"))
2802 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2803 (modules '((guix build utils)))
2804 ;; remove build dependency on git
2805 (snippet '(substitute* "build.xml"
2806 (("failifexecutionfails=\"true\"")
2807 "failifexecutionfails=\"false\"")))))
2808 (build-system ant-build-system)
2810 `(#:tests? #f ; test require Internet access
2812 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2813 "/share/java/htsjdk/"))
2814 #:build-target "all"
2816 (modify-phases %standard-phases
2817 ;; The build phase also installs the jars
2818 (delete 'install))))
2819 (home-page "http://samtools.github.io/htsjdk/")
2820 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2822 "HTSJDK is an implementation of a unified Java library for accessing
2823 common file formats, such as SAM and VCF, used for high-throughput
2824 sequencing (HTS) data. There are also an number of useful utilities for
2825 manipulating HTS data.")
2826 (license license:expat)))
2828 (define-public htslib
2835 "https://github.com/samtools/htslib/releases/download/"
2836 version "/htslib-" version ".tar.bz2"))
2839 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
2840 (build-system gnu-build-system)
2843 (modify-phases %standard-phases
2845 'unpack 'patch-tests
2847 (substitute* "test/test.pl"
2848 (("/bin/bash") (which "bash")))
2854 (home-page "http://www.htslib.org")
2855 (synopsis "C library for reading/writing high-throughput sequencing data")
2857 "HTSlib is a C library for reading/writing high-throughput sequencing
2858 data. It also provides the bgzip, htsfile, and tabix utilities.")
2859 ;; Files under cram/ are released under the modified BSD license;
2860 ;; the rest is released under the Expat license
2861 (license (list license:expat license:bsd-3))))
2870 "https://github.com/nboley/idr/archive/"
2872 (file-name (string-append name "-" version ".tar.gz"))
2875 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
2876 (build-system python-build-system)
2879 (modify-phases %standard-phases
2881 'install 'wrap-program
2882 (lambda* (#:key inputs outputs #:allow-other-keys)
2883 (let* ((out (assoc-ref outputs "out"))
2884 (python-version (string-take (string-take-right
2885 (assoc-ref inputs "python") 5) 3))
2888 (string-append (assoc-ref inputs name)
2889 "/lib/python" python-version
2893 "python-matplotlib"))
2895 (wrap-program (string-append out "/bin/idr")
2896 `("PYTHONPATH" ":" prefix (,path))))
2899 `(("python-scipy" ,python-scipy)
2900 ("python-numpy" ,python-numpy)
2901 ("python-matplotlib" ,python-matplotlib)))
2903 `(("python-cython" ,python-cython)))
2904 (home-page "https://github.com/nboley/idr")
2905 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
2907 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
2908 to measure the reproducibility of findings identified from replicate
2909 experiments and provide highly stable thresholds based on reproducibility.")
2910 (license license:gpl3+)))
2912 (define-public jellyfish
2918 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
2919 "releases/download/v" version
2920 "/jellyfish-" version ".tar.gz"))
2923 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
2924 (build-system gnu-build-system)
2925 (outputs '("out" ;for library
2926 "ruby" ;for Ruby bindings
2927 "python")) ;for Python bindings
2930 (list (string-append "--enable-ruby-binding="
2931 (assoc-ref %outputs "ruby"))
2932 (string-append "--enable-python-binding="
2933 (assoc-ref %outputs "python")))
2935 (modify-phases %standard-phases
2936 (add-before 'check 'set-SHELL-variable
2938 ;; generator_manager.hpp either uses /bin/sh or $SHELL
2940 (setenv "SHELL" (which "bash"))
2946 ("python" ,python-2)))
2947 (synopsis "Tool for fast counting of k-mers in DNA")
2949 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
2950 DNA. A k-mer is a substring of length k, and counting the occurrences of all
2951 such substrings is a central step in many analyses of DNA sequence. Jellyfish
2952 is a command-line program that reads FASTA and multi-FASTA files containing
2953 DNA sequences. It outputs its k-mer counts in a binary format, which can be
2954 translated into a human-readable text format using the @code{jellyfish dump}
2955 command, or queried for specific k-mers with @code{jellyfish query}.")
2956 (home-page "http://www.genome.umd.edu/jellyfish.html")
2957 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
2958 (supported-systems '("x86_64-linux"))
2959 ;; The combined work is published under the GPLv3 or later. Individual
2960 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
2961 (license (list license:gpl3+ license:expat))))
2963 (define-public khmer
2970 (uri (pypi-uri "khmer" version))
2973 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
2974 (patches (search-patches "khmer-use-libraries.patch"))))
2975 (build-system python-build-system)
2978 (modify-phases %standard-phases
2979 (add-after 'unpack 'set-paths
2980 (lambda* (#:key inputs outputs #:allow-other-keys)
2981 ;; Delete bundled libraries.
2982 (delete-file-recursively "third-party/zlib")
2983 (delete-file-recursively "third-party/bzip2")
2984 ;; Replace bundled seqan.
2985 (let* ((seqan-all "third-party/seqan")
2986 (seqan-include (string-append
2987 seqan-all "/core/include")))
2988 (delete-file-recursively seqan-all)
2989 (copy-recursively (string-append (assoc-ref inputs "seqan")
2991 (string-append seqan-include "/seqan")))
2992 ;; We do not replace the bundled MurmurHash as the canonical
2993 ;; repository for this code 'SMHasher' is unsuitable for
2994 ;; providing a library. See
2995 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
2997 (add-after 'unpack 'set-cc
3001 ;; It is simpler to test after installation.
3003 (add-after 'install 'post-install-check
3004 (lambda* (#:key inputs outputs #:allow-other-keys)
3005 (let ((out (assoc-ref outputs "out")))
3010 (assoc-ref outputs "out")
3012 (setenv "PYTHONPATH"
3014 (getenv "PYTHONPATH")
3018 (string-take (string-take-right
3019 (assoc-ref inputs "python") 5) 3)
3021 (with-directory-excursion "build"
3022 (zero? (system* "nosetests" "khmer" "--attr"
3023 "!known_failing")))))))))
3026 ("python-nose" ,python-nose)))
3030 ("python-screed" ,python-screed)
3031 ("python-bz2file" ,python-bz2file)))
3032 (home-page "https://khmer.readthedocs.org/")
3033 (synopsis "K-mer counting, filtering and graph traversal library")
3034 (description "The khmer software is a set of command-line tools for
3035 working with DNA shotgun sequencing data from genomes, transcriptomes,
3036 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3037 sometimes better. Khmer can also identify and fix problems with shotgun
3039 ;; When building on i686, armhf and mips64el, we get the following error:
3040 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3041 (supported-systems '("x86_64-linux"))
3042 (license license:bsd-3)))
3047 (version "2.1.0.20151222")
3050 (uri (pypi-uri "MACS2" version))
3053 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3054 (build-system python-build-system)
3056 `(#:python ,python-2 ; only compatible with Python 2.7
3057 #:tests? #f)) ; no test target
3059 `(("python-numpy" ,python2-numpy)))
3060 (home-page "http://github.com/taoliu/MACS/")
3061 (synopsis "Model based analysis for ChIP-Seq data")
3063 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3064 identifying transcript factor binding sites named Model-based Analysis of
3065 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3066 the significance of enriched ChIP regions and it improves the spatial
3067 resolution of binding sites through combining the information of both
3068 sequencing tag position and orientation.")
3069 (license license:bsd-3)))
3071 (define-public mafft
3078 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3079 "-without-extensions-src.tgz"))
3080 (file-name (string-append name "-" version ".tgz"))
3083 "0ziim7g58n3z8gppsa713f5fxprl60ldj3xck186z0n9dpp06i8r"))))
3084 (build-system gnu-build-system)
3086 `(#:tests? #f ; no automated tests, though there are tests in the read me
3087 #:make-flags (let ((out (assoc-ref %outputs "out")))
3088 (list (string-append "PREFIX=" out)
3089 (string-append "BINDIR="
3090 (string-append out "/bin"))))
3092 (modify-phases %standard-phases
3093 (add-after 'unpack 'enter-dir
3094 (lambda _ (chdir "core") #t))
3095 (add-after 'enter-dir 'patch-makefile
3097 ;; on advice from the MAFFT authors, there is no need to
3098 ;; distribute mafft-profile, mafft-distance, or
3099 ;; mafft-homologs.rb as they are too "specialised".
3100 (substitute* "Makefile"
3101 ;; remove mafft-homologs.rb from SCRIPTS
3102 (("^SCRIPTS = mafft mafft-homologs.rb")
3104 ;; remove mafft-homologs from MANPAGES
3105 (("^MANPAGES = mafft.1 mafft-homologs.1")
3106 "MANPAGES = mafft.1")
3107 ;; remove mafft-distance from PROGS
3108 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3109 "PROGS = dvtditr dndfast7 dndblast sextet5")
3110 ;; remove mafft-profile from PROGS
3111 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3112 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3113 (("^rm -f mafft-profile mafft-profile.exe") "#")
3114 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3115 ;; do not install MAN pages in libexec folder
3116 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3117 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3119 (add-after 'enter-dir 'patch-paths
3120 (lambda* (#:key inputs #:allow-other-keys)
3121 (substitute* '("pairash.c"
3123 (("perl") (which "perl"))
3124 (("([\"`| ])awk" _ prefix)
3125 (string-append prefix (which "awk")))
3126 (("grep") (which "grep")))
3129 (add-after 'install 'wrap-programs
3130 (lambda* (#:key outputs #:allow-other-keys)
3131 (let* ((out (assoc-ref outputs "out"))
3132 (bin (string-append out "/bin"))
3133 (path (string-append
3134 (assoc-ref %build-inputs "coreutils") "/bin:")))
3135 (for-each (lambda (file)
3137 `("PATH" ":" prefix (,path))))
3145 ("coreutils" ,coreutils)))
3146 (home-page "http://mafft.cbrc.jp/alignment/software/")
3147 (synopsis "Multiple sequence alignment program")
3149 "MAFFT offers a range of multiple alignment methods for nucleotide and
3150 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3151 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3153 (license (license:non-copyleft
3154 "http://mafft.cbrc.jp/alignment/software/license.txt"
3155 "BSD-3 with different formatting"))))
3164 "https://github.com/marbl/mash/archive/v"
3166 (file-name (string-append name "-" version ".tar.gz"))
3169 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3170 (modules '((guix build utils)))
3172 ;; Delete bundled kseq.
3173 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3174 '(delete-file "src/mash/kseq.h"))))
3175 (build-system gnu-build-system)
3177 `(#:tests? #f ; No tests.
3180 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3181 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3182 #:make-flags (list "CC=gcc")
3184 (modify-phases %standard-phases
3185 (add-after 'unpack 'fix-includes
3187 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3188 (("^#include \"kseq\\.h\"")
3189 "#include \"htslib/kseq.h\""))
3191 (add-before 'configure 'autoconf
3192 (lambda _ (zero? (system* "autoconf")))))))
3194 `(("autoconf" ,autoconf)
3195 ;; Capnproto and htslib are statically embedded in the final
3196 ;; application. Therefore we also list their licenses, below.
3197 ("capnproto" ,capnproto)
3198 ("htslib" ,htslib)))
3202 (supported-systems '("x86_64-linux"))
3203 (home-page "https://mash.readthedocs.io")
3204 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3205 (description "Mash is a fast sequence distance estimator that uses the
3206 MinHash algorithm and is designed to work with genomes and metagenomes in the
3207 form of assemblies or reads.")
3208 (license (list license:bsd-3 ; Mash
3209 license:expat ; HTSlib and capnproto
3210 license:public-domain ; MurmurHash 3
3211 license:cpl1.0)))) ; Open Bloom Filter
3213 (define-public metabat
3214 ;; We package from a git commit because compilation of the released version
3216 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3219 (version (string-append "0.32.4-1." (string-take commit 8)))
3224 (url "https://bitbucket.org/berkeleylab/metabat.git")
3226 (file-name (string-append name "-" version))
3229 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3230 (patches (search-patches "metabat-remove-compilation-date.patch"))))
3231 (build-system gnu-build-system)
3234 (modify-phases %standard-phases
3235 (add-after 'unpack 'fix-includes
3237 (substitute* "src/BamUtils.h"
3238 (("^#include \"bam/bam\\.h\"")
3239 "#include \"samtools/bam.h\"")
3240 (("^#include \"bam/sam\\.h\"")
3241 "#include \"samtools/sam.h\""))
3242 (substitute* "src/KseqReader.h"
3243 (("^#include \"bam/kseq\\.h\"")
3244 "#include \"htslib/kseq.h\""))
3246 (add-after 'unpack 'fix-scons
3247 (lambda* (#:key inputs #:allow-other-keys)
3248 (substitute* "SConstruct"
3249 (("^htslib_dir = 'samtools'")
3250 (string-append "hitslib_dir = '"
3251 (assoc-ref inputs "htslib")
3253 (("^samtools_dir = 'samtools'")
3254 (string-append "samtools_dir = '"
3255 (assoc-ref inputs "htslib")
3257 (("^findStaticOrShared\\('bam', hts_lib")
3258 (string-append "findStaticOrShared('bam', '"
3259 (assoc-ref inputs "samtools")
3261 ;; Do not distribute README.
3262 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3266 (lambda* (#:key inputs outputs #:allow-other-keys)
3267 (mkdir (assoc-ref outputs "out"))
3268 (zero? (system* "scons"
3271 (assoc-ref outputs "out"))
3274 (assoc-ref inputs "boost"))
3276 ;; Check and install are carried out during build phase.
3278 (delete 'install))))
3282 ("samtools" ,samtools)
3286 `(("scons" ,scons)))
3287 (home-page "https://bitbucket.org/berkeleylab/metabat")
3289 "Reconstruction of single genomes from complex microbial communities")
3291 "Grouping large genomic fragments assembled from shotgun metagenomic
3292 sequences to deconvolute complex microbial communities, or metagenome binning,
3293 enables the study of individual organisms and their interactions. MetaBAT is
3294 an automated metagenome binning software, which integrates empirical
3295 probabilistic distances of genome abundance and tetranucleotide frequency.")
3296 (license (license:non-copyleft "file://license.txt"
3297 "See license.txt in the distribution.")))))
3299 (define-public minced
3306 "https://github.com/ctSkennerton/minced/archive/"
3308 (file-name (string-append name "-" version ".tar.gz"))
3311 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3312 (build-system gnu-build-system)
3314 `(#:test-target "test"
3316 (modify-phases %standard-phases
3318 (add-before 'check 'fix-test
3320 ;; Fix test for latest version.
3321 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3322 (("minced:0.1.6") "minced:0.2.0"))
3324 (replace 'install ; No install target.
3325 (lambda* (#:key inputs outputs #:allow-other-keys)
3326 (let* ((out (assoc-ref outputs "out"))
3327 (bin (string-append out "/bin"))
3328 (wrapper (string-append bin "/minced")))
3329 ;; Minced comes with a wrapper script that tries to figure out where
3330 ;; it is located before running the JAR. Since these paths are known
3331 ;; to us, we build our own wrapper to avoid coreutils dependency.
3332 (install-file "minced.jar" bin)
3333 (with-output-to-file wrapper
3337 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3338 (assoc-ref inputs "jre") "/bin/java -jar "
3339 bin "/minced.jar \"$@\"\n"))))
3340 (chmod wrapper #o555)))))))
3342 `(("jdk" ,icedtea "jdk")))
3345 ("jre" ,icedtea "out")))
3346 (home-page "https://github.com/ctSkennerton/minced")
3347 (synopsis "Mining CRISPRs in Environmental Datasets")
3349 "MinCED is a program to find Clustered Regularly Interspaced Short
3350 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3351 unassembled metagenomic reads, but is mainly designed for full genomes and
3352 assembled metagenomic sequence.")
3353 (license license:gpl3+)))
3362 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3366 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3367 (modules '((guix build utils)))
3369 '(substitute* "setup.py"
3370 ;; Use setuptools, or else the executables are not
3372 (("distutils.core") "setuptools")
3373 ;; use "gcc" instead of "cc" for compilation
3375 "cc.set_executables(
3379 linker_so='gcc -shared'); defines")))))
3380 (build-system python-build-system)
3382 `(#:python ,python-2 ; only Python 2 is supported
3383 #:tests? #f)) ; no "test" target
3385 `(("samtools" ,samtools)
3386 ("python-numpy" ,python2-numpy)
3387 ("python-pysam" ,python2-pysam)
3388 ("python-scipy" ,python2-scipy)
3389 ("python-matplotlib" ,python2-matplotlib)))
3391 `(("python-mock" ,python2-mock) ;for tests
3392 ("python-pytz" ,python2-pytz))) ;for tests
3393 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3394 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3396 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3397 the expression level of alternatively spliced genes from RNA-Seq data, and
3398 identifies differentially regulated isoforms or exons across samples. By
3399 modeling the generative process by which reads are produced from isoforms in
3400 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3401 that a read originated from a particular isoform.")
3402 (license license:gpl2)))
3404 (define-public muscle
3407 (version "3.8.1551")
3409 (method url-fetch/tarbomb)
3410 (file-name (string-append name "-" version))
3412 "http://www.drive5.com/muscle/muscle_src_"
3416 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3417 (build-system gnu-build-system)
3419 `(#:make-flags (list "LDLIBS = -lm")
3421 (modify-phases %standard-phases
3424 ;; There are no tests, so just test if it runs.
3425 (lambda _ (zero? (system* "./muscle" "-version"))))
3427 (lambda* (#:key outputs #:allow-other-keys)
3428 (let* ((out (assoc-ref outputs "out"))
3429 (bin (string-append out "/bin")))
3430 (install-file "muscle" bin)))))))
3431 (home-page "http://www.drive5.com/muscle")
3432 (synopsis "Multiple sequence alignment program")
3434 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3435 program for nucleotide and protein sequences.")
3436 ;; License information found in 'muscle -h' and usage.cpp.
3437 (license license:public-domain)))
3439 (define-public newick-utils
3440 ;; There are no recent releases so we package from git.
3441 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3443 (name "newick-utils")
3444 (version (string-append "1.6-1." (string-take commit 8)))
3448 (url "https://github.com/tjunier/newick_utils.git")
3450 (file-name (string-append name "-" version "-checkout"))
3453 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3454 (build-system gnu-build-system)
3457 (modify-phases %standard-phases
3458 (add-after 'unpack 'autoconf
3459 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3461 ;; XXX: TODO: Enable Lua and Guile bindings.
3462 ;; https://github.com/tjunier/newick_utils/issues/13
3463 `(("libxml2" ,libxml2)
3467 `(("autoconf" ,autoconf)
3468 ("automake" ,automake)
3469 ("libtool" ,libtool)))
3470 (synopsis "Programs for working with newick format phylogenetic trees")
3472 "Newick-utils is a suite of utilities for processing phylogenetic trees
3473 in Newick format. Functions include re-rooting, extracting subtrees,
3474 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3475 (home-page "https://github.com/tjunier/newick_utils")
3476 (license license:bsd-3))))
3485 "https://github.com/wwood/OrfM/releases/download/v"
3486 version "/orfm-" version ".tar.gz"))
3489 "0vb6d771gl4mix8bwx919x5ayy9pkj44n7ki336nz3rz2rx4c7gk"))))
3490 (build-system gnu-build-system)
3491 (inputs `(("zlib" ,zlib)))
3493 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3494 ("ruby-rspec" ,ruby-rspec)
3496 (synopsis "Simple and not slow open reading frame (ORF) caller")
3498 "An ORF caller finds stretches of DNA that, when translated, are not
3499 interrupted by stop codons. OrfM finds and prints these ORFs.")
3500 (home-page "https://github.com/wwood/OrfM")
3501 (license license:lgpl3+)))
3503 (define-public python2-pbcore
3505 (name "python2-pbcore")
3509 (uri (pypi-uri "pbcore" version))
3512 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3513 (build-system python-build-system)
3514 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3516 `(("python-cython" ,python2-cython)
3517 ("python-numpy" ,python2-numpy)
3518 ("python-pysam" ,python2-pysam)
3519 ("python-h5py" ,python2-h5py)))
3521 `(("python-nose" ,python2-nose)
3522 ("python-sphinx" ,python2-sphinx)
3523 ("python-pyxb" ,python2-pyxb)))
3524 (home-page "http://pacificbiosciences.github.io/pbcore/")
3525 (synopsis "Library for reading and writing PacBio data files")
3527 "The pbcore package provides Python APIs for interacting with PacBio data
3528 files and writing bioinformatics applications.")
3529 (license license:bsd-3)))
3531 (define-public python2-warpedlmm
3533 (name "python2-warpedlmm")
3539 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3543 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3544 (build-system python-build-system)
3546 `(#:python ,python-2)) ; requires Python 2.7
3548 `(("python-scipy" ,python2-scipy)
3549 ("python-numpy" ,python2-numpy)
3550 ("python-matplotlib" ,python2-matplotlib)
3551 ("python-fastlmm" ,python2-fastlmm)
3552 ("python-pandas" ,python2-pandas)
3553 ("python-pysnptools" ,python2-pysnptools)))
3555 `(("python-mock" ,python2-mock)
3556 ("python-nose" ,python2-nose)
3558 (home-page "https://github.com/PMBio/warpedLMM")
3559 (synopsis "Implementation of warped linear mixed models")
3561 "WarpedLMM is a Python implementation of the warped linear mixed model,
3562 which automatically learns an optimal warping function (or transformation) for
3563 the phenotype as it models the data.")
3564 (license license:asl2.0)))
3566 (define-public pbtranscript-tofu
3567 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3569 (name "pbtranscript-tofu")
3570 (version (string-append "2.2.3." (string-take commit 7)))
3574 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3576 (file-name (string-append name "-" version "-checkout"))
3579 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3580 (modules '((guix build utils)))
3583 ;; remove bundled Cython sources
3584 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3586 (build-system python-build-system)
3588 `(#:python ,python-2
3590 (modify-phases %standard-phases
3591 (add-after 'unpack 'enter-directory
3593 (chdir "pbtranscript-tofu/pbtranscript/")
3595 ;; With setuptools version 18.0 and later this setup.py hack causes
3596 ;; a build error, so we disable it.
3597 (add-after 'enter-directory 'patch-setuppy
3599 (substitute* "setup.py"
3600 (("if 'setuptools.extension' in sys.modules:")
3604 `(("python-numpy" ,python2-numpy)
3605 ("python-bx-python" ,python2-bx-python)
3606 ("python-networkx" ,python2-networkx)
3607 ("python-scipy" ,python2-scipy)
3608 ("python-pbcore" ,python2-pbcore)
3609 ("python-h5py" ,python2-h5py)))
3611 `(("python-cython" ,python2-cython)
3612 ("python-nose" ,python2-nose)))
3613 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3614 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3616 "pbtranscript-tofu contains scripts to analyze transcriptome data
3617 generated using the PacBio Iso-Seq protocol.")
3618 (license license:bsd-3))))
3620 (define-public prank
3627 "http://wasabiapp.org/download/prank/prank.source."
3631 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3632 (build-system gnu-build-system)
3635 (modify-phases %standard-phases
3636 (add-after 'unpack 'enter-src-dir
3640 (add-after 'unpack 'remove-m64-flag
3641 ;; Prank will build with the correct 'bit-ness' without this flag
3642 ;; and this allows building on 32-bit machines.
3643 (lambda _ (substitute* "src/Makefile"
3648 (lambda* (#:key outputs #:allow-other-keys)
3649 (let* ((out (assoc-ref outputs "out"))
3650 (bin (string-append out "/bin"))
3651 (man (string-append out "/share/man/man1"))
3652 (path (string-append
3653 (assoc-ref %build-inputs "mafft") "/bin:"
3654 (assoc-ref %build-inputs "exonerate") "/bin:"
3655 (assoc-ref %build-inputs "bppsuite") "/bin")))
3656 (install-file "prank" bin)
3657 (wrap-program (string-append bin "/prank")
3658 `("PATH" ":" prefix (,path)))
3659 (install-file "prank.1" man))
3663 ("exonerate" ,exonerate)
3664 ("bppsuite" ,bppsuite)))
3665 (home-page "http://wasabiapp.org/software/prank/")
3666 (synopsis "Probabilistic multiple sequence alignment program")
3668 "PRANK is a probabilistic multiple sequence alignment program for DNA,
3669 codon and amino-acid sequences. It is based on a novel algorithm that treats
3670 insertions correctly and avoids over-estimation of the number of deletion
3671 events. In addition, PRANK borrows ideas from maximum likelihood methods used
3672 in phylogenetics and correctly takes into account the evolutionary distances
3673 between sequences. Lastly, PRANK allows for defining a potential structure
3674 for sequences to be aligned and then, simultaneously with the alignment,
3675 predicts the locations of structural units in the sequences.")
3676 (license license:gpl2+)))
3678 (define-public proteinortho
3680 (name "proteinortho")
3687 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
3688 version "_src.tar.gz"))
3691 "05wacnnbx56avpcwhzlcf6b7s77swcpv3qnwz5sh1z54i51gg2ki"))))
3692 (build-system gnu-build-system)
3694 `(#:test-target "test"
3696 (modify-phases %standard-phases
3698 ;; There is no configure script, so we modify the Makefile directly.
3699 (lambda* (#:key outputs #:allow-other-keys)
3700 (substitute* "Makefile"
3703 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
3705 (add-before 'install 'make-install-directory
3706 ;; The install directory is not created during 'make install'.
3707 (lambda* (#:key outputs #:allow-other-keys)
3708 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3710 (add-after 'install 'wrap-programs
3711 (lambda* (#:key inputs outputs #:allow-other-keys)
3712 (let* ((path (getenv "PATH"))
3713 (out (assoc-ref outputs "out"))
3714 (binary (string-append out "/bin/proteinortho5.pl")))
3715 (wrap-program binary `("PATH" ":" prefix (,path))))
3719 ("python" ,python-2)
3720 ("blast+" ,blast+)))
3721 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
3722 (synopsis "Detect orthologous genes across species")
3724 "Proteinortho is a tool to detect orthologous genes across different
3725 species. For doing so, it compares similarities of given gene sequences and
3726 clusters them to find significant groups. The algorithm was designed to handle
3727 large-scale data and can be applied to hundreds of species at once.")
3728 (license license:gpl2+)))
3730 (define-public pyicoteo
3737 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
3738 "pyicoteo/get/v" version ".tar.bz2"))
3739 (file-name (string-append name "-" version ".tar.bz2"))
3742 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
3743 (build-system python-build-system)
3745 `(#:python ,python-2 ; does not work with Python 3
3746 #:tests? #f)) ; there are no tests
3748 `(("python2-matplotlib" ,python2-matplotlib)))
3749 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
3750 (synopsis "Analyze high-throughput genetic sequencing data")
3752 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
3753 sequencing data. It works with genomic coordinates. There are currently six
3754 different command-line tools:
3757 @item pyicoregion: for generating exploratory regions automatically;
3758 @item pyicoenrich: for differential enrichment between two conditions;
3759 @item pyicoclip: for calling CLIP-Seq peaks without a control;
3760 @item pyicos: for genomic coordinates manipulation;
3761 @item pyicoller: for peak calling on punctuated ChIP-Seq;
3762 @item pyicount: to count how many reads from N experiment files overlap in a
3764 @item pyicotrocol: to combine operations from pyicoteo.
3766 (license license:gpl3+)))
3768 (define-public prodigal
3775 "https://github.com/hyattpd/Prodigal/archive/v"
3777 (file-name (string-append name "-" version ".tar.gz"))
3780 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
3781 (build-system gnu-build-system)
3783 `(#:tests? #f ;no check target
3784 #:make-flags (list (string-append "INSTALLDIR="
3785 (assoc-ref %outputs "out")
3788 (modify-phases %standard-phases
3789 (delete 'configure))))
3790 (home-page "http://prodigal.ornl.gov")
3791 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
3793 "Prodigal runs smoothly on finished genomes, draft genomes, and
3794 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
3795 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
3796 partial genes, and identifies translation initiation sites.")
3797 (license license:gpl3+)))
3799 (define-public roary
3807 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
3811 "0x2hpb3nfsc6x2nq1788w0fhqfzc7cn2dp4xwyva9m3k6xlz0m43"))))
3812 (build-system perl-build-system)
3815 (modify-phases %standard-phases
3820 ;; The tests are not run by default, so we run each test file
3822 (setenv "PATH" (string-append (getcwd) "/bin" ":"
3824 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
3825 (getenv "PERL5LIB")))
3826 (zero? (length (filter (lambda (file)
3827 (display file)(display "\n")
3828 (not (zero? (system* "perl" file))))
3829 (find-files "t" ".*\\.t$"))))))
3831 ;; There is no 'install' target in the Makefile.
3832 (lambda* (#:key outputs #:allow-other-keys)
3833 (let* ((out (assoc-ref outputs "out"))
3834 (bin (string-append out "/bin"))
3835 (perl (string-append out "/lib/perl5/site_perl"))
3836 (roary-plots "contrib/roary_plots"))
3839 (copy-recursively "bin" bin)
3840 (copy-recursively "lib" perl)
3842 (add-after 'install 'wrap-programs
3843 (lambda* (#:key inputs outputs #:allow-other-keys)
3844 (let* ((out (assoc-ref outputs "out"))
3845 (perl5lib (getenv "PERL5LIB"))
3846 (path (getenv "PATH")))
3847 (for-each (lambda (prog)
3848 (let ((binary (string-append out "/" prog)))
3849 (wrap-program binary
3850 `("PERL5LIB" ":" prefix
3851 (,(string-append perl5lib ":" out
3852 "/lib/perl5/site_perl"))))
3853 (wrap-program binary
3855 (,(string-append path ":" out "/bin"))))))
3856 (find-files "bin" ".*[^R]$"))
3858 (string-append out "/bin/roary-create_pan_genome_plots.R"))
3859 (r-site-lib (getenv "R_LIBS_SITE"))
3861 (string-append (assoc-ref inputs "coreutils") "/bin")))
3863 `("R_LIBS_SITE" ":" prefix
3864 (,(string-append r-site-lib ":" out "/site-library/"))))
3867 (,(string-append coreutils-path ":" out "/bin"))))))
3870 `(("perl-env-path" ,perl-env-path)
3871 ("perl-test-files" ,perl-test-files)
3872 ("perl-test-most" ,perl-test-most)
3873 ("perl-test-output" ,perl-test-output)))
3875 `(("perl-array-utils" ,perl-array-utils)
3876 ("bioperl" ,bioperl-minimal)
3877 ("perl-exception-class" ,perl-exception-class)
3878 ("perl-file-find-rule" ,perl-file-find-rule)
3879 ("perl-file-grep" ,perl-file-grep)
3880 ("perl-file-slurper" ,perl-file-slurper)
3881 ("perl-file-which" ,perl-file-which)
3882 ("perl-graph" ,perl-graph)
3883 ("perl-graph-readwrite" ,perl-graph-readwrite)
3884 ("perl-log-log4perl" ,perl-log-log4perl)
3885 ("perl-moose" ,perl-moose)
3886 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
3887 ("perl-text-csv" ,perl-text-csv)
3888 ("bedtools" ,bedtools)
3892 ("parallel" ,parallel)
3895 ("fasttree" ,fasttree)
3900 ("r-ggplot2" ,r-ggplot2)
3901 ("coreutils" ,coreutils)))
3902 (home-page "http://sanger-pathogens.github.io/Roary")
3903 (synopsis "High speed stand-alone pan genome pipeline")
3905 "Roary is a high speed stand alone pan genome pipeline, which takes
3906 annotated assemblies in GFF3 format (produced by the Prokka program) and
3907 calculates the pan genome. Using a standard desktop PC, it can analyse
3908 datasets with thousands of samples, without compromising the quality of the
3909 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
3910 single processor. Roary is not intended for metagenomics or for comparing
3911 extremely diverse sets of genomes.")
3912 (license license:gpl3)))
3914 (define-public raxml
3923 "https://github.com/stamatak/standard-RAxML/archive/v"
3925 (file-name (string-append name "-" version ".tar.gz"))
3928 "1pv8p2fy67y21a9y4cm7xpvxqjwz2v4201flfjshdq1p8j52rqf7"))))
3929 (build-system gnu-build-system)
3931 `(#:tests? #f ; There are no tests.
3932 ;; Use 'standard' Makefile rather than SSE or AVX ones.
3933 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
3935 (modify-phases %standard-phases
3938 (lambda* (#:key outputs #:allow-other-keys)
3939 (let* ((out (assoc-ref outputs "out"))
3940 (bin (string-append out "/bin"))
3941 (executable "raxmlHPC-HYBRID"))
3942 (install-file executable bin)
3943 (symlink (string-append bin "/" executable) "raxml"))
3946 `(("openmpi" ,openmpi)))
3947 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
3948 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
3950 "RAxML is a tool for phylogenetic analysis and post-analysis of large
3952 (license license:gpl2+)))
3962 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
3965 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
3966 (patches (search-patches "rsem-makefile.patch"))
3967 (modules '((guix build utils)))
3970 ;; remove bundled copy of boost
3971 (delete-file-recursively "boost")
3973 (build-system gnu-build-system)
3975 `(#:tests? #f ;no "check" target
3977 (modify-phases %standard-phases
3978 ;; No "configure" script.
3979 ;; Do not build bundled samtools library.
3982 (substitute* "Makefile"
3983 (("^all : sam/libbam.a") "all : "))
3986 (lambda* (#:key outputs #:allow-other-keys)
3987 (let* ((out (string-append (assoc-ref outputs "out")))
3988 (bin (string-append out "/bin/"))
3989 (perl (string-append out "/lib/perl5/site_perl")))
3992 (for-each (lambda (file)
3994 (string-append bin (basename file))))
3995 (find-files "." "rsem-.*"))
3996 (copy-file "rsem_perl_utils.pm"
3997 (string-append perl "/rsem_perl_utils.pm")))
4000 'install 'wrap-program
4001 (lambda* (#:key outputs #:allow-other-keys)
4002 (let ((out (assoc-ref outputs "out")))
4003 (for-each (lambda (prog)
4004 (wrap-program (string-append out "/bin/" prog)
4005 `("PERL5LIB" ":" prefix
4006 (,(string-append out "/lib/perl5/site_perl")))))
4007 '("rsem-plot-transcript-wiggles"
4008 "rsem-calculate-expression"
4009 "rsem-generate-ngvector"
4011 "rsem-prepare-reference")))
4015 ("ncurses" ,ncurses)
4018 ("samtools" ,samtools-0.1)
4020 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4021 (synopsis "Estimate gene expression levels from RNA-Seq data")
4023 "RSEM is a software package for estimating gene and isoform expression
4024 levels from RNA-Seq data. The RSEM package provides a user-friendly
4025 interface, supports threads for parallel computation of the EM algorithm,
4026 single-end and paired-end read data, quality scores, variable-length reads and
4027 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4028 interval estimates for expression levels. For visualization, it can generate
4029 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4030 (license license:gpl3+)))
4032 (define-public rseqc
4040 (string-append "mirror://sourceforge/rseqc/"
4041 "RSeQC-" version ".tar.gz"))
4043 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4044 (modules '((guix build utils)))
4047 ;; remove bundled copy of pysam
4048 (delete-file-recursively "lib/pysam")
4049 (substitute* "setup.py"
4050 ;; remove dependency on outdated "distribute" module
4051 (("^from distribute_setup import use_setuptools") "")
4052 (("^use_setuptools\\(\\)") "")
4053 ;; do not use bundled copy of pysam
4054 (("^have_pysam = False") "have_pysam = True"))))))
4055 (build-system python-build-system)
4056 (arguments `(#:python ,python-2))
4058 `(("python-cython" ,python2-cython)
4059 ("python-pysam" ,python2-pysam)
4060 ("python-numpy" ,python2-numpy)
4063 `(("python-nose" ,python2-nose)))
4064 (home-page "http://rseqc.sourceforge.net/")
4065 (synopsis "RNA-seq quality control package")
4067 "RSeQC provides a number of modules that can comprehensively evaluate
4068 high throughput sequence data, especially RNA-seq data. Some basic modules
4069 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4070 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4071 distribution, coverage uniformity, strand specificity, etc.")
4072 (license license:gpl3+)))
4075 ;; There are no release tarballs. According to the installation
4076 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4077 ;; stable release is identified by this changeset ID.
4078 (let ((changeset "2329130")
4082 (version (string-append "0-" revision "." changeset))
4086 (url "https://bitbucket.org/libsleipnir/sleipnir")
4087 (changeset changeset)))
4090 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4091 (build-system gnu-build-system)
4093 `(#:modules ((srfi srfi-1)
4094 (guix build gnu-build-system)
4097 (let ((dirs '("SeekMiner"
4103 (modify-phases %standard-phases
4104 (add-before 'configure 'bootstrap
4106 (zero? (system* "bash" "gen_auto"))))
4107 (add-after 'build 'build-additional-tools
4108 (lambda* (#:key make-flags #:allow-other-keys)
4109 (every (lambda (dir)
4110 (with-directory-excursion (string-append "tools/" dir)
4111 (zero? (apply system* "make" make-flags))))
4113 (add-after 'install 'install-additional-tools
4114 (lambda* (#:key make-flags #:allow-other-keys)
4115 (fold (lambda (dir result)
4116 (with-directory-excursion (string-append "tools/" dir)
4118 (zero? (apply system*
4119 `("make" ,@make-flags "install"))))))
4125 ("readline" ,readline)
4126 ("gengetopt" ,gengetopt)
4127 ("log4cpp" ,log4cpp)))
4129 `(("autoconf" ,autoconf)
4130 ("automake" ,automake)
4132 (home-page "http://seek.princeton.edu")
4133 (synopsis "Gene co-expression search engine")
4135 "SEEK is a computational gene co-expression search engine. SEEK provides
4136 biologists with a way to navigate the massive human expression compendium that
4137 now contains thousands of expression datasets. SEEK returns a robust ranking
4138 of co-expressed genes in the biological area of interest defined by the user's
4139 query genes. It also prioritizes thousands of expression datasets according
4140 to the user's query of interest.")
4141 (license license:cc-by3.0))))
4143 (define-public samtools
4151 (string-append "mirror://sourceforge/samtools/samtools/"
4152 version "/samtools-" version ".tar.bz2"))
4155 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4156 (build-system gnu-build-system)
4158 `(#:modules ((ice-9 ftw)
4160 (guix build gnu-build-system)
4162 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4163 #:configure-flags (list "--with-ncurses")
4166 'unpack 'patch-tests
4168 (substitute* "test/test.pl"
4169 ;; The test script calls out to /bin/bash
4170 (("/bin/bash") (which "bash")))
4173 'install 'install-library
4174 (lambda* (#:key outputs #:allow-other-keys)
4175 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4176 (install-file "libbam.a" lib)))
4178 'install 'install-headers
4179 (lambda* (#:key outputs #:allow-other-keys)
4180 (let ((include (string-append (assoc-ref outputs "out")
4181 "/include/samtools/")))
4182 (for-each (lambda (file)
4183 (install-file file include))
4184 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4186 %standard-phases)))))
4187 (native-inputs `(("pkg-config" ,pkg-config)))
4188 (inputs `(("ncurses" ,ncurses)
4192 (home-page "http://samtools.sourceforge.net")
4193 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4195 "Samtools implements various utilities for post-processing nucleotide
4196 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4197 variant calling (in conjunction with bcftools), and a simple alignment
4199 (license license:expat)))
4201 (define-public samtools-0.1
4202 ;; This is the most recent version of the 0.1 line of samtools. The input
4203 ;; and output formats differ greatly from that used and produced by samtools
4204 ;; 1.x and is still used in many bioinformatics pipelines.
4205 (package (inherit samtools)
4211 (string-append "mirror://sourceforge/samtools/samtools/"
4212 version "/samtools-" version ".tar.bz2"))
4214 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4216 `(#:tests? #f ;no "check" target
4217 ,@(substitute-keyword-arguments (package-arguments samtools)
4218 ((#:make-flags flags)
4219 `(cons "LIBCURSES=-lncurses" ,flags))
4221 `(modify-phases ,phases
4223 (lambda* (#:key outputs #:allow-other-keys)
4224 (let ((bin (string-append
4225 (assoc-ref outputs "out") "/bin")))
4227 (copy-file "samtools"
4228 (string-append bin "/samtools")))))
4229 (delete 'patch-tests)
4230 (delete 'configure))))))))
4232 (define-public mosaik
4233 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4238 ;; There are no release tarballs nor tags.
4241 (url "https://github.com/wanpinglee/MOSAIK.git")
4243 (file-name (string-append name "-" version))
4246 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4247 (build-system gnu-build-system)
4249 `(#:tests? #f ; no tests
4250 #:make-flags (list "CC=gcc")
4252 (modify-phases %standard-phases
4254 (lambda _ (chdir "src") #t))
4256 (lambda* (#:key outputs #:allow-other-keys)
4257 (let ((bin (string-append (assoc-ref outputs "out")
4260 (copy-recursively "../bin" bin)
4265 (supported-systems '("x86_64-linux"))
4266 (home-page "https://code.google.com/p/mosaik-aligner/")
4267 (synopsis "Map nucleotide sequence reads to reference genomes")
4269 "MOSAIK is a program for mapping second and third-generation sequencing
4270 reads to a reference genome. MOSAIK can align reads generated by all the
4271 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4272 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4273 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4274 ;; code released into the public domain:
4275 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4276 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4277 (license (list license:gpl2+ license:public-domain)))))
4279 (define-public ngs-sdk
4287 (string-append "https://github.com/ncbi/ngs/archive/"
4289 (file-name (string-append name "-" version ".tar.gz"))
4292 "04y1fsmdnb5y86m3gg6f5g9wcscr6r25n7m8mdlcxy0i2q6w6cia"))))
4293 (build-system gnu-build-system)
4295 `(#:parallel-build? #f ; not supported
4296 #:tests? #f ; no "check" target
4300 (lambda* (#:key outputs #:allow-other-keys)
4301 (let ((out (assoc-ref outputs "out")))
4302 ;; The 'configure' script doesn't recognize things like
4303 ;; '--enable-fast-install'.
4304 (zero? (system* "./configure"
4305 (string-append "--build-prefix=" (getcwd) "/build")
4306 (string-append "--prefix=" out)))))
4309 (lambda _ (chdir "ngs-sdk") #t)
4310 %standard-phases))))
4311 (native-inputs `(("perl" ,perl)))
4312 ;; According to the test
4313 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4314 ;; in ngs-sdk/setup/konfigure.perl
4315 (supported-systems '("i686-linux" "x86_64-linux"))
4316 (home-page "https://github.com/ncbi/ngs")
4317 (synopsis "API for accessing Next Generation Sequencing data")
4319 "NGS is a domain-specific API for accessing reads, alignments and pileups
4320 produced from Next Generation Sequencing. The API itself is independent from
4321 any particular back-end implementation, and supports use of multiple back-ends
4323 (license license:public-domain)))
4325 (define-public java-ngs
4326 (package (inherit ngs-sdk)
4329 `(,@(substitute-keyword-arguments
4330 `(#:modules ((guix build gnu-build-system)
4334 ,@(package-arguments ngs-sdk))
4336 `(modify-phases ,phases
4337 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4339 `(("jdk" ,icedtea "jdk")
4340 ("ngs-sdk" ,ngs-sdk)))
4341 (synopsis "Java bindings for NGS SDK")))
4343 (define-public ncbi-vdb
4351 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4353 (file-name (string-append name "-" version ".tar.gz"))
4356 "0x1cg1x8vy0yjlkp0snc1533zcjhxqzqsaiwqk598n7vvw37n8lf"))))
4357 (build-system gnu-build-system)
4359 `(#:parallel-build? #f ; not supported
4360 #:tests? #f ; no "check" target
4364 (lambda* (#:key inputs outputs #:allow-other-keys)
4365 (let ((out (assoc-ref outputs "out")))
4366 ;; Override include path for libmagic
4367 (substitute* "setup/package.prl"
4368 (("name => 'magic', Include => '/usr/include'")
4369 (string-append "name=> 'magic', Include => '"
4370 (assoc-ref inputs "libmagic")
4373 ;; Install kdf5 library (needed by sra-tools)
4374 (substitute* "build/Makefile.install"
4375 (("LIBRARIES_TO_INSTALL =")
4376 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4378 (substitute* "build/Makefile.env"
4379 (("CFLAGS =" prefix)
4380 (string-append prefix "-msse2 ")))
4382 ;; The 'configure' script doesn't recognize things like
4383 ;; '--enable-fast-install'.
4386 (string-append "--build-prefix=" (getcwd) "/build")
4387 (string-append "--prefix=" (assoc-ref outputs "out"))
4388 (string-append "--debug")
4389 (string-append "--with-xml2-prefix="
4390 (assoc-ref inputs "libxml2"))
4391 (string-append "--with-ngs-sdk-prefix="
4392 (assoc-ref inputs "ngs-sdk"))
4393 (string-append "--with-ngs-java-prefix="
4394 (assoc-ref inputs "java-ngs"))
4395 (string-append "--with-hdf5-prefix="
4396 (assoc-ref inputs "hdf5"))))))
4398 'install 'install-interfaces
4399 (lambda* (#:key outputs #:allow-other-keys)
4400 ;; Install interface libraries. On i686 the interface libraries
4401 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4402 ;; architecture name ("i386") instead of the target system prefix
4404 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4405 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4406 ,(system->linux-architecture
4407 (or (%current-target-system)
4410 (string-append (assoc-ref outputs "out")
4412 ;; Install interface headers
4413 (copy-recursively "interfaces"
4414 (string-append (assoc-ref outputs "out")
4416 %standard-phases))))
4418 `(("libxml2" ,libxml2)
4419 ("ngs-sdk" ,ngs-sdk)
4420 ("java-ngs" ,java-ngs)
4423 (native-inputs `(("perl" ,perl)))
4424 ;; NCBI-VDB requires SSE capability.
4425 (supported-systems '("i686-linux" "x86_64-linux"))
4426 (home-page "https://github.com/ncbi/ncbi-vdb")
4427 (synopsis "Database engine for genetic information")
4429 "The NCBI-VDB library implements a highly compressed columnar data
4430 warehousing engine that is most often used to store genetic information.
4431 Databases are stored in a portable image within the file system, and can be
4432 accessed/downloaded on demand across HTTP.")
4433 (license license:public-domain)))
4435 (define-public plink
4443 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4444 version "-src.zip"))
4446 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4447 (patches (search-patches "plink-1.07-unclobber-i.patch"
4448 "plink-endian-detection.patch"))))
4449 (build-system gnu-build-system)
4451 '(#:tests? #f ;no "check" target
4452 #:make-flags (list (string-append "LIB_LAPACK="
4453 (assoc-ref %build-inputs "lapack")
4454 "/lib/liblapack.so")
4457 ;; disable phoning home
4460 (modify-phases %standard-phases
4461 ;; no "configure" script
4464 (lambda* (#:key outputs #:allow-other-keys)
4465 (let ((bin (string-append (assoc-ref outputs "out")
4467 (install-file "plink" bin)
4471 ("lapack" ,lapack)))
4473 `(("unzip" ,unzip)))
4474 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4475 (synopsis "Whole genome association analysis toolset")
4477 "PLINK is a whole genome association analysis toolset, designed to
4478 perform a range of basic, large-scale analyses in a computationally efficient
4479 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4480 so there is no support for steps prior to this (e.g. study design and
4481 planning, generating genotype or CNV calls from raw data). Through
4482 integration with gPLINK and Haploview, there is some support for the
4483 subsequent visualization, annotation and storage of results.")
4484 ;; Code is released under GPLv2, except for fisher.h, which is under
4486 (license (list license:gpl2 license:lgpl2.1+))))
4488 (define-public smithlab-cpp
4489 (let ((revision "1")
4490 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4492 (name "smithlab-cpp")
4493 (version (string-append "0." revision "." (string-take commit 7)))
4497 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4499 (file-name (string-append name "-" version "-checkout"))
4502 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4503 (build-system gnu-build-system)
4505 `(#:modules ((guix build gnu-build-system)
4508 #:tests? #f ;no "check" target
4510 (modify-phases %standard-phases
4511 (add-after 'unpack 'use-samtools-headers
4513 (substitute* '("SAM.cpp"
4515 (("sam.h") "samtools/sam.h"))
4518 (lambda* (#:key outputs #:allow-other-keys)
4519 (let* ((out (assoc-ref outputs "out"))
4520 (lib (string-append out "/lib"))
4521 (include (string-append out "/include/smithlab-cpp")))
4524 (for-each (cut install-file <> lib)
4525 (find-files "." "\\.o$"))
4526 (for-each (cut install-file <> include)
4527 (find-files "." "\\.hpp$")))
4529 (delete 'configure))))
4531 `(("samtools" ,samtools-0.1)
4533 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4534 (synopsis "C++ helper library for functions used in Smith lab projects")
4536 "Smithlab CPP is a C++ library that includes functions used in many of
4537 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4538 structures, classes for genomic regions, mapped sequencing reads, etc.")
4539 (license license:gpl3+))))
4541 (define-public preseq
4547 (uri (string-append "https://github.com/smithlabcode/"
4548 "preseq/archive/v" version ".tar.gz"))
4549 (file-name (string-append name "-" version ".tar.gz"))
4551 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4552 (modules '((guix build utils)))
4554 ;; Remove bundled samtools.
4555 '(delete-file-recursively "samtools"))))
4556 (build-system gnu-build-system)
4558 `(#:tests? #f ;no "check" target
4560 (modify-phases %standard-phases
4561 (delete 'configure))
4563 (list (string-append "PREFIX="
4564 (assoc-ref %outputs "out"))
4565 (string-append "LIBBAM="
4566 (assoc-ref %build-inputs "samtools")
4568 (string-append "SMITHLAB_CPP="
4569 (assoc-ref %build-inputs "smithlab-cpp")
4572 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4575 ("samtools" ,samtools-0.1)
4576 ("smithlab-cpp" ,smithlab-cpp)
4578 (home-page "http://smithlabresearch.org/software/preseq/")
4579 (synopsis "Program for analyzing library complexity")
4581 "The preseq package is aimed at predicting and estimating the complexity
4582 of a genomic sequencing library, equivalent to predicting and estimating the
4583 number of redundant reads from a given sequencing depth and how many will be
4584 expected from additional sequencing using an initial sequencing experiment.
4585 The estimates can then be used to examine the utility of further sequencing,
4586 optimize the sequencing depth, or to screen multiple libraries to avoid low
4587 complexity samples.")
4588 (license license:gpl3+)))
4590 (define-public python-screed
4592 (name "python-screed")
4597 (uri (pypi-uri "screed" version))
4600 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4601 (build-system python-build-system)
4604 (modify-phases %standard-phases
4607 (setenv "PYTHONPATH"
4608 (string-append (getenv "PYTHONPATH") ":."))
4609 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4611 `(("python-nose" ,python-nose)))
4613 `(("python-bz2file" ,python-bz2file)))
4614 (home-page "http://github.com/dib-lab/screed/")
4615 (synopsis "Short read sequence database utilities")
4616 (description "Screed parses FASTA and FASTQ files and generates databases.
4617 Values such as sequence name, sequence description, sequence quality and the
4618 sequence itself can be retrieved from these databases.")
4619 (license license:bsd-3)))
4621 (define-public python2-screed
4622 (package-with-python2 python-screed))
4624 (define-public sra-tools
4632 (string-append "https://github.com/ncbi/sra-tools/archive/"
4634 (file-name (string-append name "-" version ".tar.gz"))
4637 "13paw7bq6y47d2pl0ac5gpgcqp1xsy1g7v1fwysm3hr8lb2dck17"))))
4638 (build-system gnu-build-system)
4640 `(#:parallel-build? #f ; not supported
4641 #:tests? #f ; no "check" target
4643 (list (string-append "VDB_LIBDIR="
4644 (assoc-ref %build-inputs "ncbi-vdb")
4645 ,(if (string-prefix? "x86_64"
4646 (or (%current-target-system)
4653 (lambda* (#:key inputs outputs #:allow-other-keys)
4654 ;; The build system expects a directory containing the sources and
4655 ;; raw build output of ncbi-vdb, including files that are not
4656 ;; installed. Since we are building against an installed version of
4657 ;; ncbi-vdb, the following modifications are needed.
4658 (substitute* "setup/konfigure.perl"
4659 ;; Make the configure script look for the "ilib" directory of
4660 ;; "ncbi-vdb" without first checking for the existence of a
4661 ;; matching library in its "lib" directory.
4662 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
4663 "my $f = File::Spec->catdir($ilibdir, $ilib);")
4664 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
4665 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
4666 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
4669 (substitute* "tools/copycat/Makefile"
4670 (("smagic-static") "lmagic"))
4672 ;; The 'configure' script doesn't recognize things like
4673 ;; '--enable-fast-install'.
4676 (string-append "--build-prefix=" (getcwd) "/build")
4677 (string-append "--prefix=" (assoc-ref outputs "out"))
4678 (string-append "--debug")
4679 (string-append "--with-fuse-prefix="
4680 (assoc-ref inputs "fuse"))
4681 (string-append "--with-magic-prefix="
4682 (assoc-ref inputs "libmagic"))
4683 ;; TODO: building with libxml2 fails with linker errors
4684 ;; (string-append "--with-xml2-prefix="
4685 ;; (assoc-ref inputs "libxml2"))
4686 (string-append "--with-ncbi-vdb-sources="
4687 (assoc-ref inputs "ncbi-vdb"))
4688 (string-append "--with-ncbi-vdb-build="
4689 (assoc-ref inputs "ncbi-vdb"))
4690 (string-append "--with-ngs-sdk-prefix="
4691 (assoc-ref inputs "ngs-sdk"))
4692 (string-append "--with-hdf5-prefix="
4693 (assoc-ref inputs "hdf5")))))
4695 (native-inputs `(("perl" ,perl)))
4697 `(("ngs-sdk" ,ngs-sdk)
4698 ("ncbi-vdb" ,ncbi-vdb)
4703 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
4704 (synopsis "Tools and libraries for reading and writing sequencing data")
4706 "The SRA Toolkit from NCBI is a collection of tools and libraries for
4707 reading of sequencing files from the Sequence Read Archive (SRA) database and
4708 writing files into the .sra format.")
4709 (license license:public-domain)))
4711 (define-public seqan
4717 (uri (string-append "http://packages.seqan.de/seqan-library/"
4718 "seqan-library-" version ".tar.bz2"))
4721 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
4722 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
4723 ;; makes sense to split the outputs.
4724 (outputs '("out" "doc"))
4725 (build-system trivial-build-system)
4727 `(#:modules ((guix build utils))
4730 (use-modules (guix build utils))
4731 (let ((tar (assoc-ref %build-inputs "tar"))
4732 (bzip (assoc-ref %build-inputs "bzip2"))
4733 (out (assoc-ref %outputs "out"))
4734 (doc (assoc-ref %outputs "doc")))
4735 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
4736 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
4737 (chdir (string-append "seqan-library-" ,version))
4738 (copy-recursively "include" (string-append out "/include"))
4739 (copy-recursively "share" (string-append doc "/share"))))))
4741 `(("source" ,source)
4744 (home-page "http://www.seqan.de")
4745 (synopsis "Library for nucleotide sequence analysis")
4747 "SeqAn is a C++ library of efficient algorithms and data structures for
4748 the analysis of sequences with the focus on biological data. It contains
4749 algorithms and data structures for string representation and their
4750 manipulation, online and indexed string search, efficient I/O of
4751 bioinformatics file formats, sequence alignment, and more.")
4752 (license license:bsd-3)))
4754 (define-public seqmagick
4762 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
4766 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
4767 (build-system python-build-system)
4769 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
4770 `(#:python ,python-2
4772 (modify-phases %standard-phases
4773 ;; Current test in setup.py does not work as of 0.6.1,
4774 ;; so use nose to run tests instead for now. See
4775 ;; https://github.com/fhcrc/seqmagick/issues/55
4776 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
4778 ;; biopython-1.66 is required due to
4779 ;; https://github.com/fhcrc/seqmagick/issues/59
4780 ;; When that issue is resolved the 'python2-biopython-1.66' package
4781 ;; should be removed.
4782 `(("python-biopython" ,python2-biopython-1.66)))
4784 `(("python-nose" ,python2-nose)))
4785 (home-page "http://github.com/fhcrc/seqmagick")
4786 (synopsis "Tools for converting and modifying sequence files")
4788 "Bioinformaticians often have to convert sequence files between formats
4789 and do little manipulations on them, and it's not worth writing scripts for
4790 that. Seqmagick is a utility to expose the file format conversion in
4791 BioPython in a convenient way. Instead of having a big mess of scripts, there
4792 is one that takes arguments.")
4793 (license license:gpl3)))
4795 (define-public seqtk
4802 "https://github.com/lh3/seqtk/archive/v"
4804 (file-name (string-append name "-" version ".tar.gz"))
4807 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
4808 (modules '((guix build utils)))
4811 ;; Remove extraneous header files, as is done in the seqtk
4813 (for-each (lambda (file) (delete-file file))
4814 (list "ksort.h" "kstring.h" "kvec.h"))
4816 (build-system gnu-build-system)
4819 (modify-phases %standard-phases
4822 ;; There are no tests, so we just run a sanity check.
4823 (lambda _ (zero? (system* "./seqtk" "seq"))))
4825 (lambda* (#:key outputs #:allow-other-keys)
4826 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4827 (install-file "seqtk" bin)))))))
4830 (home-page "https://github.com/lh3/seqtk")
4831 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
4833 "Seqtk is a fast and lightweight tool for processing sequences in the
4834 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
4835 optionally compressed by gzip.")
4836 (license license:expat)))
4838 (define-public snap-aligner
4840 (name "snap-aligner")
4841 (version "1.0beta.18")
4845 "https://github.com/amplab/snap/archive/v"
4847 (file-name (string-append name "-" version ".tar.gz"))
4850 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
4851 (build-system gnu-build-system)
4854 (modify-phases %standard-phases
4856 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
4858 (lambda* (#:key outputs #:allow-other-keys)
4859 (let* ((out (assoc-ref outputs "out"))
4860 (bin (string-append out "/bin")))
4861 (install-file "snap-aligner" bin)
4862 (install-file "SNAPCommand" bin)
4866 (home-page "http://snap.cs.berkeley.edu/")
4867 (synopsis "Short read DNA sequence aligner")
4869 "SNAP is a fast and accurate aligner for short DNA reads. It is
4870 optimized for modern read lengths of 100 bases or higher, and takes advantage
4871 of these reads to align data quickly through a hash-based indexing scheme.")
4872 ;; 32-bit systems are not supported by the unpatched code.
4873 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
4874 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
4875 ;; systems without a lot of memory cannot make good use of this program.
4876 (supported-systems '("x86_64-linux"))
4877 (license license:asl2.0)))
4879 (define-public sortmerna
4887 "https://github.com/biocore/sortmerna/archive/"
4889 (file-name (string-append name "-" version ".tar.gz"))
4892 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
4893 (build-system gnu-build-system)
4894 (outputs '("out" ;for binaries
4895 "db")) ;for sequence databases
4898 (modify-phases %standard-phases
4900 (lambda* (#:key outputs #:allow-other-keys)
4901 (let* ((out (assoc-ref outputs "out"))
4902 (bin (string-append out "/bin"))
4903 (db (assoc-ref outputs "db"))
4905 (string-append db "/share/sortmerna/rRNA_databases")))
4906 (install-file "sortmerna" bin)
4907 (install-file "indexdb_rna" bin)
4908 (for-each (lambda (file)
4909 (install-file file share))
4910 (find-files "rRNA_databases" ".*fasta"))
4914 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
4915 (synopsis "Biological sequence analysis tool for NGS reads")
4917 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
4918 and operational taxonomic unit (OTU) picking of next generation
4919 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
4920 allows for fast and sensitive analyses of nucleotide sequences. The main
4921 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
4922 (license license:lgpl3)))
4930 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
4932 (file-name (string-append name "-" version ".tar.gz"))
4935 "0xjlsm4p9flln111hv4xx7xy94c2nl53zvdvbk9winmiradjsdra"))
4936 (modules '((guix build utils)))
4939 (substitute* "source/Makefile"
4941 ;; Remove pre-built binaries and bundled htslib sources.
4942 (delete-file-recursively "bin/MacOSX_x86_64")
4943 (delete-file-recursively "bin/Linux_x86_64")
4944 (delete-file-recursively "source/htslib")
4946 (build-system gnu-build-system)
4948 '(#:tests? #f ;no check target
4949 #:make-flags '("STAR")
4951 (modify-phases %standard-phases
4952 (add-after 'unpack 'enter-source-dir
4953 (lambda _ (chdir "source") #t))
4954 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
4956 (substitute* "Makefile"
4957 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
4959 (substitute* '("BAMfunctions.cpp"
4964 "bamRemoveDuplicates.cpp")
4965 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
4966 (string-append "#include <" header ">")))
4967 (substitute* "IncludeDefine.h"
4968 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
4969 (string-append "<" header ">")))
4972 (lambda* (#:key outputs #:allow-other-keys)
4973 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4974 (install-file "STAR" bin))
4976 (delete 'configure))))
4978 `(("vim" ,vim))) ; for xxd
4980 `(("htslib" ,htslib)
4982 (home-page "https://github.com/alexdobin/STAR")
4983 (synopsis "Universal RNA-seq aligner")
4985 "The Spliced Transcripts Alignment to a Reference (STAR) software is
4986 based on a previously undescribed RNA-seq alignment algorithm that uses
4987 sequential maximum mappable seed search in uncompressed suffix arrays followed
4988 by seed clustering and stitching procedure. In addition to unbiased de novo
4989 detection of canonical junctions, STAR can discover non-canonical splices and
4990 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
4992 ;; Only 64-bit systems are supported according to the README.
4993 (supported-systems '("x86_64-linux" "mips64el-linux"))
4994 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
4995 (license license:gpl3+)))
4997 (define-public subread
5003 (uri (string-append "mirror://sourceforge/subread/subread-"
5004 version "/subread-" version "-source.tar.gz"))
5007 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5008 (build-system gnu-build-system)
5010 `(#:tests? #f ;no "check" target
5011 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5012 ;; optimizations by default, so we override these flags such that x86_64
5013 ;; flags are only added when the build target is an x86_64 system.
5015 (list (let ((system ,(or (%current-target-system)
5017 (flags '("-ggdb" "-fomit-frame-pointer"
5018 "-ffast-math" "-funroll-loops"
5019 "-fmessage-length=0"
5020 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5022 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5023 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5024 (if (string-prefix? "x86_64" system)
5025 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5026 (string-append "CCFLAGS=" (string-join flags))))
5027 "-f" "Makefile.Linux"
5028 "CC=gcc ${CCFLAGS}")
5032 (lambda _ (chdir "src") #t)
5035 (lambda* (#:key outputs #:allow-other-keys)
5036 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5038 (copy-recursively "../bin" bin)))
5039 ;; no "configure" script
5040 (alist-delete 'configure %standard-phases)))))
5041 (inputs `(("zlib" ,zlib)))
5042 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5043 (synopsis "Tool kit for processing next-gen sequencing data")
5045 "The subread package contains the following tools: subread aligner, a
5046 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5047 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5048 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5049 against local background noises.")
5050 (license license:gpl3+)))
5052 (define-public stringtie
5058 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5059 "stringtie-" version ".tar.gz"))
5062 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5063 (modules '((guix build utils)))
5066 (delete-file-recursively "samtools-0.1.18")
5068 (build-system gnu-build-system)
5070 `(#:tests? #f ;no test suite
5072 (modify-phases %standard-phases
5073 ;; no configure script
5075 (add-before 'build 'use-system-samtools
5077 (substitute* "Makefile"
5078 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5080 (substitute* '("gclib/GBam.h"
5082 (("#include \"(bam|sam|kstring).h\"" _ header)
5083 (string-append "#include <samtools/" header ".h>")))
5086 (lambda* (#:key outputs #:allow-other-keys)
5087 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5088 (install-file "stringtie" bin)
5091 `(("samtools" ,samtools-0.1)
5093 (home-page "http://ccb.jhu.edu/software/stringtie/")
5094 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5096 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5097 alignments into potential transcripts. It uses a novel network flow algorithm
5098 as well as an optional de novo assembly step to assemble and quantitate
5099 full-length transcripts representing multiple splice variants for each gene
5100 locus. Its input can include not only the alignments of raw reads used by
5101 other transcript assemblers, but also alignments of longer sequences that have
5102 been assembled from those reads. To identify differentially expressed genes
5103 between experiments, StringTie's output can be processed either by the
5104 Cuffdiff or Ballgown programs.")
5105 (license license:artistic2.0)))
5107 (define-public vcftools
5114 "https://github.com/vcftools/vcftools/releases/download/v"
5115 version "/vcftools-" version ".tar.gz"))
5118 "10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
5119 (build-system gnu-build-system)
5121 `(#:tests? #f ; no "check" target
5123 "CFLAGS=-O2" ; override "-m64" flag
5124 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5125 (string-append "MANDIR=" (assoc-ref %outputs "out")
5126 "/share/man/man1"))))
5128 `(("pkg-config" ,pkg-config)))
5132 (home-page "https://vcftools.github.io/")
5133 (synopsis "Tools for working with VCF files")
5135 "VCFtools is a program package designed for working with VCF files, such
5136 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5137 provide easily accessible methods for working with complex genetic variation
5138 data in the form of VCF files.")
5139 ;; The license is declared as LGPLv3 in the README and
5140 ;; at https://vcftools.github.io/license.html
5141 (license license:lgpl3)))
5143 (define-public infernal
5149 (uri (string-append "http://eddylab.org/software/infernal/"
5150 "infernal-" version ".tar.gz"))
5153 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5154 (build-system gnu-build-system)
5156 `(("perl" ,perl))) ; for tests
5157 (home-page "http://eddylab.org/infernal/")
5158 (synopsis "Inference of RNA alignments")
5159 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5160 searching DNA sequence databases for RNA structure and sequence similarities.
5161 It is an implementation of a special case of profile stochastic context-free
5162 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5163 profile, but it scores a combination of sequence consensus and RNA secondary
5164 structure consensus, so in many cases, it is more capable of identifying RNA
5165 homologs that conserve their secondary structure more than their primary
5167 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5168 (supported-systems '("i686-linux" "x86_64-linux"))
5169 (license license:bsd-3)))
5171 (define-public r-vegan
5178 (uri (cran-uri "vegan" version))
5181 "0i0c7rc0nzgbysd1nlxzxd2rvy75qcnw3yc7nggzqjzzj5d7yzsd"))))
5182 (build-system r-build-system)
5185 (modify-phases %standard-phases
5186 (add-after 'unpack 'revert-test-deletion
5187 ;; The distributed sources do not include tests with the CRAN
5188 ;; package. Here we revert the commit
5189 ;; `591d0e8ba1deaaf82445474ec6619c0b43db4e63' which deletes these
5190 ;; tests. There are plans to not delete tests in future as
5191 ;; documented at https://github.com/vegandevs/vegan/issues/181.
5192 (lambda* (#:key inputs #:allow-other-keys)
5194 (system* "patch" "-R" "-p1" "-i"
5195 (assoc-ref inputs "r-vegan-delete-tests-patch"))))))))
5197 `(("gfortran" ,gfortran)
5198 ("r-knitr" ,r-knitr)
5199 ("r-vegan-delete-tests-patch"
5203 "https://github.com/vegandevs/vegan/commit/"
5204 "591d0e8ba1deaaf82445474ec6619c0b43db4e63.patch"))
5207 "0b1bi7y4jjdl3ph721vm9apm51dr2z9piwvhy4355sf2b4kyyj5a"))))))
5209 `(("r-cluster" ,r-cluster)
5210 ("r-lattice" ,r-lattice)
5212 ("r-permute" ,r-permute)))
5213 (home-page "https://cran.r-project.org/web/packages/vegan")
5214 (synopsis "Functions for community ecology")
5216 "The vegan package provides tools for descriptive community ecology. It
5217 has most basic functions of diversity analysis, community ordination and
5218 dissimilarity analysis. Most of its multivariate tools can be used for other
5219 data types as well.")
5220 (license license:gpl2+)))
5222 (define-public r-annotate
5229 (uri (bioconductor-uri "annotate" version))
5232 "1fd2csq7dcs2gwndgwdx2nwkymz8gsmlnqqzv3p0vjjsvvq5n2a8"))))
5233 (build-system r-build-system)
5235 `(("r-annotationdbi" ,r-annotationdbi)
5236 ("r-biobase" ,r-biobase)
5237 ("r-biocgenerics" ,r-biocgenerics)
5240 ("r-xtable" ,r-xtable)))
5242 "http://bioconductor.org/packages/annotate")
5243 (synopsis "Annotation for microarrays")
5244 (description "This package provides R enviroments for the annotation of
5246 (license license:artistic2.0)))
5248 (define-public r-geneplotter
5250 (name "r-geneplotter")
5255 (uri (bioconductor-uri "geneplotter" version))
5258 "1p6yvxi243irhjxwm97hp73abhwampj0myyf8z00ij166674pc7h"))))
5259 (build-system r-build-system)
5261 `(("r-annotate" ,r-annotate)
5262 ("r-annotationdbi" ,r-annotationdbi)
5263 ("r-biobase" ,r-biobase)
5264 ("r-biocgenerics" ,r-biocgenerics)
5265 ("r-lattice" ,r-lattice)
5266 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5267 (home-page "http://bioconductor.org/packages/geneplotter")
5268 (synopsis "Graphics functions for genomic data")
5270 "This package provides functions for plotting genomic data.")
5271 (license license:artistic2.0)))
5273 (define-public r-genefilter
5275 (name "r-genefilter")
5280 (uri (bioconductor-uri "genefilter" version))
5283 "1vzgciqd09csqcw9qync8blsv51ylrd86a65iadgyy6j26g01fwd"))))
5284 (build-system r-build-system)
5286 `(("gfortran" ,gfortran)))
5288 `(("r-annotate" ,r-annotate)
5289 ("r-annotationdbi" ,r-annotationdbi)
5290 ("r-biobase" ,r-biobase)
5291 ("r-s4vectors" ,r-s4vectors)))
5292 (home-page "http://bioconductor.org/packages/genefilter")
5293 (synopsis "Filter genes from high-throughput experiments")
5295 "This package provides basic functions for filtering genes from
5296 high-throughput sequencing experiments.")
5297 (license license:artistic2.0)))
5299 (define-public r-deseq2
5306 (uri (bioconductor-uri "DESeq2" version))
5309 "0kq06jy4xg5ii3a9l62f17kirsfx0gsiwq6mhiy985cqzpdn893g"))))
5310 (properties `((upstream-name . "DESeq2")))
5311 (build-system r-build-system)
5314 (modify-phases %standard-phases
5315 (add-after 'unpack 'link-against-armadillo
5317 (substitute* "src/Makevars"
5318 (("PKG_LIBS =" prefix)
5319 (string-append prefix "-larmadillo"))))))))
5321 `(("r-biobase" ,r-biobase)
5322 ("r-biocgenerics" ,r-biocgenerics)
5323 ("r-biocparallel" ,r-biocparallel)
5324 ("r-genefilter" ,r-genefilter)
5325 ("r-geneplotter" ,r-geneplotter)
5326 ("r-genomicranges" ,r-genomicranges)
5327 ("r-ggplot2" ,r-ggplot2)
5328 ("r-hmisc" ,r-hmisc)
5329 ("r-iranges" ,r-iranges)
5330 ("r-locfit" ,r-locfit)
5332 ("r-rcpparmadillo" ,r-rcpparmadillo)
5333 ("r-s4vectors" ,r-s4vectors)
5334 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5335 (home-page "http://bioconductor.org/packages/DESeq2")
5336 (synopsis "Differential gene expression analysis")
5338 "This package provides functions to estimate variance-mean dependence in
5339 count data from high-throughput nucleotide sequencing assays and test for
5340 differential expression based on a model using the negative binomial
5342 (license license:lgpl3+)))
5344 (define-public r-annotationforge
5346 (name "r-annotationforge")
5351 (uri (bioconductor-uri "AnnotationForge" version))
5354 "02msyb9p3hywrryx00zpjkjl126mrv827i1ah1092s0cplm6xxvf"))))
5356 `((upstream-name . "AnnotationForge")))
5357 (build-system r-build-system)
5359 `(("r-annotationdbi" ,r-annotationdbi)
5360 ("r-biobase" ,r-biobase)
5361 ("r-biocgenerics" ,r-biocgenerics)
5363 ("r-rcurl" ,r-rcurl)
5364 ("r-rsqlite" ,r-rsqlite)
5365 ("r-s4vectors" ,r-s4vectors)
5367 (home-page "http://bioconductor.org/packages/AnnotationForge")
5368 (synopsis "Code for building annotation database packages")
5370 "This package provides code for generating Annotation packages and their
5371 databases. Packages produced are intended to be used with AnnotationDbi.")
5372 (license license:artistic2.0)))
5374 (define-public r-rbgl
5381 (uri (bioconductor-uri "RBGL" version))
5384 "1q14m8w6ih56v680kf3d9wh1qbgp7af33kz3cxafdf1vvzx9km08"))))
5385 (properties `((upstream-name . "RBGL")))
5386 (build-system r-build-system)
5387 (propagated-inputs `(("r-graph" ,r-graph)))
5388 (home-page "http://www.bioconductor.org/packages/RBGL")
5389 (synopsis "Interface to the Boost graph library")
5391 "This package provides a fairly extensive and comprehensive interface to
5392 the graph algorithms contained in the Boost library.")
5393 (license license:artistic2.0)))
5395 (define-public r-gseabase
5402 (uri (bioconductor-uri "GSEABase" version))
5405 "0l2x7yj7lfb0m2dmsav5ib026dikpgl4crdckrnj776yy08lgxpj"))))
5406 (properties `((upstream-name . "GSEABase")))
5407 (build-system r-build-system)
5409 `(("r-annotate" ,r-annotate)
5410 ("r-annotationdbi" ,r-annotationdbi)
5411 ("r-biobase" ,r-biobase)
5412 ("r-biocgenerics" ,r-biocgenerics)
5413 ("r-graph" ,r-graph)
5415 (home-page "http://bioconductor.org/packages/GSEABase")
5416 (synopsis "Gene set enrichment data structures and methods")
5418 "This package provides classes and methods to support @dfn{Gene Set
5419 Enrichment Analysis} (GSEA).")
5420 (license license:artistic2.0)))
5422 (define-public r-category
5429 (uri (bioconductor-uri "Category" version))
5432 "16ncwz7b4y48k0p3fvbrbmvf7nfz63li9ysgcl8kp9kl4hg7llng"))))
5433 (properties `((upstream-name . "Category")))
5434 (build-system r-build-system)
5436 `(("r-annotate" ,r-annotate)
5437 ("r-annotationdbi" ,r-annotationdbi)
5438 ("r-biobase" ,r-biobase)
5439 ("r-biocgenerics" ,r-biocgenerics)
5440 ("r-genefilter" ,r-genefilter)
5441 ("r-graph" ,r-graph)
5442 ("r-gseabase" ,r-gseabase)
5443 ("r-matrix" ,r-matrix)
5445 ("r-rsqlite" ,r-rsqlite)))
5446 (home-page "http://bioconductor.org/packages/Category")
5447 (synopsis "Category analysis")
5449 "This package provides a collection of tools for performing category
5451 (license license:artistic2.0)))
5453 (define-public r-gostats
5460 (uri (bioconductor-uri "GOstats" version))
5463 "0g2czm94zhzx92z7y2r4mjfxhwml7bhab2db6820ks8nkw1zvr9n"))))
5464 (properties `((upstream-name . "GOstats")))
5465 (build-system r-build-system)
5467 `(("r-annotate" ,r-annotate)
5468 ("r-annotationdbi" ,r-annotationdbi)
5469 ("r-annotationforge" ,r-annotationforge)
5470 ("r-biobase" ,r-biobase)
5471 ("r-category" ,r-category)
5472 ("r-go-db" ,r-go-db)
5473 ("r-graph" ,r-graph)
5474 ("r-rbgl" ,r-rbgl)))
5475 (home-page "http://bioconductor.org/packages/GOstats")
5476 (synopsis "Tools for manipulating GO and microarrays")
5478 "This package provides a set of tools for interacting with GO and
5479 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5480 testing and other simple calculations.")
5481 (license license:artistic2.0)))
5483 (define-public r-shortread
5485 (name "r-shortread")
5490 (uri (bioconductor-uri "ShortRead" version))
5493 "0mjdlg92x5qw4x2djc4dv5lxwl7ai6ix56nnf86zr07jk8vc7yls"))))
5494 (properties `((upstream-name . "ShortRead")))
5495 (build-system r-build-system)
5499 `(("r-biobase" ,r-biobase)
5500 ("r-biocgenerics" ,r-biocgenerics)
5501 ("r-biocparallel" ,r-biocparallel)
5502 ("r-biostrings" ,r-biostrings)
5503 ("r-genomeinfodb" ,r-genomeinfodb)
5504 ("r-genomicalignments" ,r-genomicalignments)
5505 ("r-genomicranges" ,r-genomicranges)
5506 ("r-hwriter" ,r-hwriter)
5507 ("r-iranges" ,r-iranges)
5508 ("r-lattice" ,r-lattice)
5509 ("r-latticeextra" ,r-latticeextra)
5510 ("r-rsamtools" ,r-rsamtools)
5511 ("r-s4vectors" ,r-s4vectors)
5512 ("r-xvector" ,r-xvector)
5513 ("r-zlibbioc" ,r-zlibbioc)))
5514 (home-page "http://bioconductor.org/packages/ShortRead")
5515 (synopsis "FASTQ input and manipulation tools")
5517 "This package implements sampling, iteration, and input of FASTQ files.
5518 It includes functions for filtering and trimming reads, and for generating a
5519 quality assessment report. Data are represented as
5520 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5521 purposes. The package also contains legacy support for early single-end,
5522 ungapped alignment formats.")
5523 (license license:artistic2.0)))
5525 (define-public r-systempiper
5527 (name "r-systempiper")
5532 (uri (bioconductor-uri "systemPipeR" version))
5535 "0hyi841w8fm2yzpm6lwqi3jz5kc8ny8dy5p29dxynzaw5bpjw56d"))))
5536 (properties `((upstream-name . "systemPipeR")))
5537 (build-system r-build-system)
5539 `(("r-annotate" ,r-annotate)
5540 ("r-batchjobs" ,r-batchjobs)
5541 ("r-biocgenerics" ,r-biocgenerics)
5542 ("r-biostrings" ,r-biostrings)
5543 ("r-deseq2" ,r-deseq2)
5544 ("r-edger" ,r-edger)
5545 ("r-genomicfeatures" ,r-genomicfeatures)
5546 ("r-genomicranges" ,r-genomicranges)
5547 ("r-ggplot2" ,r-ggplot2)
5548 ("r-go-db" ,r-go-db)
5549 ("r-gostats" ,r-gostats)
5550 ("r-limma" ,r-limma)
5551 ("r-pheatmap" ,r-pheatmap)
5552 ("r-rjson" ,r-rjson)
5553 ("r-rsamtools" ,r-rsamtools)
5554 ("r-shortread" ,r-shortread)
5555 ("r-summarizedexperiment" ,r-summarizedexperiment)
5556 ("r-variantannotation" ,r-variantannotation)))
5557 (home-page "https://github.com/tgirke/systemPipeR")
5558 (synopsis "Next generation sequencing workflow and reporting environment")
5560 "This R package provides tools for building and running automated
5561 end-to-end analysis workflows for a wide range of @dfn{next generation
5562 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5563 Important features include a uniform workflow interface across different NGS
5564 applications, automated report generation, and support for running both R and
5565 command-line software, such as NGS aligners or peak/variant callers, on local
5566 computers or compute clusters. Efficient handling of complex sample sets and
5567 experimental designs is facilitated by a consistently implemented sample
5568 annotation infrastructure.")
5569 (license license:artistic2.0)))
5571 (define-public r-grohmm
5578 (uri (bioconductor-uri "groHMM" version))
5581 "0d91nyhqbi5hv3mgmr2z0g29wg2md26g0hyv5mgapmz20cd9zi4y"))))
5582 (properties `((upstream-name . "groHMM")))
5583 (build-system r-build-system)
5585 `(("r-genomeinfodb" ,r-genomeinfodb)
5586 ("r-genomicalignments" ,r-genomicalignments)
5587 ("r-genomicranges" ,r-genomicranges)
5588 ("r-iranges" ,r-iranges)
5589 ("r-rtracklayer" ,r-rtracklayer)
5590 ("r-s4vectors" ,r-s4vectors)))
5591 (home-page "https://github.com/Kraus-Lab/groHMM")
5592 (synopsis "GRO-seq analysis pipeline")
5594 "This package provides a pipeline for the analysis of GRO-seq data.")
5595 (license license:gpl3+)))
5597 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
5599 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
5603 ;; We cannot use bioconductor-uri here because this tarball is
5604 ;; located under "data/annotation/" instead of "bioc/".
5605 (uri (string-append "http://bioconductor.org/packages/"
5606 "release/data/annotation/src/contrib"
5607 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
5611 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
5613 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
5614 (build-system r-build-system)
5615 ;; As this package provides little more than a very large data file it
5616 ;; doesn't make sense to build substitutes.
5617 (arguments `(#:substitutable? #f))
5619 `(("r-genomicfeatures" ,r-genomicfeatures)))
5621 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
5622 (synopsis "Annotation package for human genome in TxDb format")
5624 "This package provides an annotation database of Homo sapiens genome
5625 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
5626 track. The database is exposed as a @code{TxDb} object.")
5627 (license license:artistic2.0)))
5629 (define-public vsearch
5637 "https://github.com/torognes/vsearch/archive/v"
5639 (file-name (string-append name "-" version ".tar.gz"))
5642 "1r8fk3whkil348y5hfsd4r56qjmchhq4nxm6s7ra5rlisw0mf9fy"))
5643 (modules '((guix build utils)))
5646 ;; Remove bundled cityhash and '-mtune=native'.
5647 (substitute* "src/Makefile.am"
5648 (("^AM_CXXFLAGS=-I\\$\\{srcdir\\}/cityhash \
5649 -O3 -mtune=native -Wall -Wsign-compare")
5650 (string-append "AM_CXXFLAGS=-lcityhash"
5651 " -O3 -Wall -Wsign-compare"))
5652 (("^__top_builddir__bin_vsearch_SOURCES = city.h \\\\")
5653 "__top_builddir__bin_vsearch_SOURCES = \\")
5654 (("^city.h \\\\") "\\")
5655 (("^citycrc.h \\\\") "\\")
5656 (("^libcityhash_a.*") "")
5657 (("noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a \
5659 "noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a")
5660 (("__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
5661 libcpu_sse2.a libcityhash.a")
5662 "__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
5663 libcpu_sse2.a -lcityhash"))
5664 (substitute* "src/vsearch.h"
5665 (("^\\#include \"city.h\"") "#include <city.h>")
5666 (("^\\#include \"citycrc.h\"") "#include <citycrc.h>"))
5667 (delete-file "src/city.h")
5668 (delete-file "src/citycrc.h")
5669 (delete-file "src/city.cc")
5671 (build-system gnu-build-system)
5674 (modify-phases %standard-phases
5675 (add-before 'configure 'autogen
5676 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
5680 ("cityhash" ,cityhash)))
5682 `(("autoconf" ,autoconf)
5683 ("automake" ,automake)))
5684 (synopsis "Sequence search tools for metagenomics")
5686 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
5687 dereplication, pairwise alignment, shuffling, subsampling, sorting and
5688 masking. The tool takes advantage of parallelism in the form of SIMD
5689 vectorization as well as multiple threads to perform accurate alignments at
5690 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
5691 Needleman-Wunsch).")
5692 (home-page "https://github.com/torognes/vsearch")
5693 ;; vsearch uses non-portable SSE intrinsics so building fails on other
5695 (supported-systems '("x86_64-linux"))
5696 ;; Dual licensed; also includes public domain source.
5697 (license (list license:gpl3 license:bsd-2))))
5699 (define-public pardre
5706 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
5710 "0zkyjzv4s8q2h5npalhirbk17r5b1h0n2a42mh7njzlf047h9bhy"))))
5711 (build-system gnu-build-system)
5713 `(#:tests? #f ; no tests included
5715 (modify-phases %standard-phases
5718 (lambda* (#:key outputs #:allow-other-keys)
5719 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
5720 (install-file "ParDRe" bin)
5723 `(("openmpi" ,openmpi)
5725 (synopsis "Parallel tool to remove duplicate DNA reads")
5727 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
5728 Duplicate reads can be seen as identical or nearly identical sequences with
5729 some mismatches. This tool lets users avoid the analysis of unnecessary
5730 reads, reducing the time of subsequent procedures with the
5731 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
5732 in order to exploit the parallel capabilities of multicore clusters. It is
5733 faster than multithreaded counterparts (end of 2015) for the same number of
5734 cores and, thanks to the message-passing technology, it can be executed on
5736 (home-page "https://sourceforge.net/projects/pardre/")
5737 (license license:gpl3+)))
5739 (define-public ruby-bio-kseq
5741 (name "ruby-bio-kseq")
5746 (uri (rubygems-uri "bio-kseq" version))
5749 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
5750 (build-system ruby-build-system)
5752 `(#:test-target "spec"))
5754 `(("bundler" ,bundler)
5755 ("ruby-rspec" ,ruby-rspec)
5756 ("ruby-rake-compiler" ,ruby-rake-compiler)))
5759 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
5761 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
5762 FASTQ parsing code. It provides a fast iterator over sequences and their
5764 (home-page "https://github.com/gusevfe/bio-kseq")
5765 (license license:expat)))
5767 (define-public bio-locus
5774 (uri (rubygems-uri "bio-locus" version))
5777 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
5778 (build-system ruby-build-system)
5780 `(("ruby-rspec" ,ruby-rspec)))
5781 (synopsis "Tool for fast querying of genome locations")
5783 "Bio-locus is a tabix-like tool for fast querying of genome
5784 locations. Many file formats in bioinformatics contain records that
5785 start with a chromosome name and a position for a SNP, or a start-end
5786 position for indels. Bio-locus allows users to store this chr+pos or
5787 chr+pos+alt information in a database.")
5788 (home-page "https://github.com/pjotrp/bio-locus")
5789 (license license:expat)))
5791 (define-public bio-blastxmlparser
5793 (name "bio-blastxmlparser")
5797 (uri (rubygems-uri "bio-blastxmlparser" version))
5800 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
5801 (build-system ruby-build-system)
5803 `(("ruby-bio-logger" ,ruby-bio-logger)
5804 ("ruby-nokogiri" ,ruby-nokogiri)))
5806 `(("ruby-rspec" ,ruby-rspec)))
5807 (synopsis "Fast big data BLAST XML parser and library")
5809 "Very fast parallel big-data BLAST XML file parser which can be used as
5810 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
5811 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
5812 (home-page "http://github.com/pjotrp/blastxmlparser")
5813 (license license:expat)))
5815 (define-public bioruby
5822 (uri (rubygems-uri "bio" version))
5825 "01k2fyjl5fpx4zn8g6gqiqvsg2j1fgixrs9p03vzxckynxdq3wmc"))))
5826 (build-system ruby-build-system)
5828 `(("ruby-libxml" ,ruby-libxml)))
5830 `(("which" ,which))) ; required for test phase
5833 (modify-phases %standard-phases
5834 (add-before 'build 'patch-test-command
5836 (substitute* '("test/functional/bio/test_command.rb")
5837 (("/bin/sh") (which "sh")))
5838 (substitute* '("test/functional/bio/test_command.rb")
5839 (("/bin/ls") (which "ls")))
5840 (substitute* '("test/functional/bio/test_command.rb")
5841 (("which") (which "which")))
5842 (substitute* '("test/functional/bio/test_command.rb",
5843 "test/data/command/echoarg2.sh")
5844 (("/bin/echo") (which "echo")))
5846 (synopsis "Ruby library, shell and utilities for bioinformatics")
5847 (description "BioRuby comes with a comprehensive set of Ruby development
5848 tools and libraries for bioinformatics and molecular biology. BioRuby has
5849 components for sequence analysis, pathway analysis, protein modelling and
5850 phylogenetic analysis; it supports many widely used data formats and provides
5851 easy access to databases, external programs and public web services, including
5852 BLAST, KEGG, GenBank, MEDLINE and GO.")
5853 (home-page "http://bioruby.org/")
5854 ;; Code is released under Ruby license, except for setup
5855 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
5856 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
5858 (define-public r-acsnminer
5860 (name "r-acsnminer")
5861 (version "0.16.8.25")
5864 (uri (cran-uri "ACSNMineR" version))
5867 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
5868 (properties `((upstream-name . "ACSNMineR")))
5869 (build-system r-build-system)
5871 `(("r-ggplot2" ,r-ggplot2)
5872 ("r-gridextra" ,r-gridextra)))
5873 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
5874 (synopsis "Gene enrichment analysis")
5876 "This package provides tools to compute and represent gene set enrichment
5877 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
5878 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
5879 enrichment can be run with hypergeometric test or Fisher exact test, and can
5880 use multiple corrections. Visualization of data can be done either by
5881 barplots or heatmaps.")
5882 (license license:gpl2+)))
5884 (define-public r-biocgenerics
5886 (name "r-biocgenerics")
5890 (uri (bioconductor-uri "BiocGenerics" version))
5893 "06szdz7dfs1iyv5zdl4fjzad18nnf1zf3wvglc6c6yd9mrqlf7vk"))))
5895 `((upstream-name . "BiocGenerics")))
5896 (build-system r-build-system)
5897 (home-page "http://bioconductor.org/packages/BiocGenerics")
5898 (synopsis "S4 generic functions for Bioconductor")
5900 "This package provides S4 generic functions needed by many Bioconductor
5902 (license license:artistic2.0)))
5904 (define-public r-biocinstaller
5906 (name "r-biocinstaller")
5910 (uri (bioconductor-uri "BiocInstaller" version))
5913 "0y1y5wmy6lzjqx3hdg15n91d417ccjj8dbvdkhmp99bs5aijwcpn"))))
5915 `((upstream-name . "BiocInstaller")))
5916 (build-system r-build-system)
5917 (home-page "http://bioconductor.org/packages/BiocInstaller")
5918 (synopsis "Install Bioconductor packages")
5919 (description "This package is used to install and update R packages from
5920 Bioconductor, CRAN, and Github.")
5921 (license license:artistic2.0)))
5923 (define-public r-biocviews
5925 (name "r-biocviews")
5929 (uri (bioconductor-uri "biocViews" version))
5932 "07rjk10b91pkriyq297w86199r2d3sfji3ggs9mq2gyalsa8y4b6"))))
5934 `((upstream-name . "biocViews")))
5935 (build-system r-build-system)
5937 `(("r-biobase" ,r-biobase)
5938 ("r-graph" ,r-graph)
5940 ("r-rcurl" ,r-rcurl)
5942 ("r-knitr" ,r-knitr)
5943 ("r-runit" ,r-runit)))
5944 (home-page "http://bioconductor.org/packages/biocViews")
5945 (synopsis "Bioconductor package categorization helper")
5946 (description "The purpose of biocViews is to create HTML pages that
5947 categorize packages in a Bioconductor package repository according to keywords,
5948 also known as views, in a controlled vocabulary.")
5949 (license license:artistic2.0)))
5951 (define-public r-biocstyle
5953 (name "r-biocstyle")
5957 (uri (bioconductor-uri "BiocStyle" version))
5960 "0qbk23fz8cn260isd9xlh9lxfj4adar6iqzai01c4kz0p31f45za"))))
5962 `((upstream-name . "BiocStyle")))
5963 (build-system r-build-system)
5964 (home-page "http://bioconductor.org/packages/BiocStyle")
5965 (synopsis "Bioconductor formatting styles")
5966 (description "This package provides standard formatting styles for
5967 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
5969 (license license:artistic2.0)))
5971 (define-public r-bioccheck
5973 (name "r-bioccheck")
5977 (uri (bioconductor-uri "BiocCheck" version))
5980 "1rfy37xg1nc2cmgbclvzsi7sgmdcdjiahsx9crgx3yaw7kxgiack"))))
5982 `((upstream-name . "BiocCheck")))
5983 (build-system r-build-system)
5986 (modify-phases %standard-phases
5987 ;; This package can be used by calling BiocCheck(<package>) from
5988 ;; within R, or by running R CMD BiocCheck <package>. This phase
5989 ;; makes sure the latter works. For this to work, the BiocCheck
5990 ;; script must be somewhere on the PATH (not the R bin directory).
5991 (add-after 'install 'install-bioccheck-subcommand
5992 (lambda* (#:key outputs #:allow-other-keys)
5993 (let* ((out (assoc-ref outputs "out"))
5994 (dest-dir (string-append out "/bin"))
5996 (string-append out "/site-library/BiocCheck/script/")))
5998 (symlink (string-append script-dir "/checkBadDeps.R")
5999 (string-append dest-dir "/checkBadDeps.R"))
6000 (symlink (string-append script-dir "/BiocCheck")
6001 (string-append dest-dir "/BiocCheck")))
6004 `(("which" ,which)))
6006 `(("r-graph" ,r-graph)
6007 ("r-knitr" ,r-knitr)
6009 ("r-optparse" ,r-optparse)
6010 ("r-devtools" ,r-devtools)
6011 ("r-biocinstaller" ,r-biocinstaller)
6012 ("r-biocviews" ,r-biocviews)))
6013 (home-page "http://bioconductor.org/packages/BiocCheck")
6014 (synopsis "Executes Bioconductor-specific package checks")
6015 (description "This package contains tools to perform additional quality
6016 checks on R packages that are to be submitted to the Bioconductor repository.")
6017 (license license:artistic2.0)))
6019 (define-public r-getopt
6026 (uri (cran-uri "getopt" version))
6029 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6030 (build-system r-build-system)
6031 (home-page "https://github.com/trevorld/getopt")
6032 (synopsis "Command-line option processor for R")
6034 "This package is designed to be used with Rscript to write shebang
6035 scripts that accept short and long options. Many users will prefer to
6036 use the packages @code{optparse} or @code{argparse} which add extra
6037 features like automatically generated help options and usage texts,
6038 support for default values, positional argument support, etc.")
6039 (license license:gpl2+)))
6041 (define-public r-optparse
6048 (uri (cran-uri "optparse" version))
6051 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6052 (build-system r-build-system)
6054 `(("r-getopt" ,r-getopt)))
6056 "https://github.com/trevorld/optparse")
6057 (synopsis "Command line option parser")
6059 "This package provides a command line parser inspired by Python's
6060 @code{optparse} library to be used with Rscript to write shebang scripts
6061 that accept short and long options.")
6062 (license license:gpl2+)))
6064 (define-public r-dnacopy
6070 (uri (bioconductor-uri "DNAcopy" version))
6073 "1idyvfvy7xx8k9vk00y4k3819qmip8iqm809j3vpxabmsn7r9zyh"))))
6075 `((upstream-name . "DNAcopy")))
6076 (build-system r-build-system)
6078 `(("gfortran" ,gfortran)))
6079 (home-page "https://bioconductor.org/packages/DNAcopy")
6080 (synopsis "Implementation of a circular binary segmentation algorithm")
6081 (description "This package implements the circular binary segmentation (CBS)
6082 algorithm to segment DNA copy number data and identify genomic regions with
6083 abnormal copy number.")
6084 (license license:gpl2+)))
6086 (define-public r-s4vectors
6088 (name "r-s4vectors")
6092 (uri (bioconductor-uri "S4Vectors" version))
6095 "0m0npc0vhmcwcxws7v2f8k4hvvrjvnlrsr94klxf4a8m4xw2xzzk"))))
6097 `((upstream-name . "S4Vectors")))
6098 (build-system r-build-system)
6100 `(("r-biocgenerics" ,r-biocgenerics)))
6101 (home-page "http://bioconductor.org/packages/S4Vectors")
6102 (synopsis "S4 implementation of vectors and lists")
6104 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6105 classes and a set of generic functions that extend the semantic of ordinary
6106 vectors and lists in R. Package developers can easily implement vector-like
6107 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6108 In addition, a few low-level concrete subclasses of general interest (e.g.
6109 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6110 S4Vectors package itself.")
6111 (license license:artistic2.0)))
6113 (define-public r-seqinr
6120 (uri (cran-uri "seqinr" version))
6123 "0rk4yba8km26c0rh1f4h474zsb5n6kjmqsi55bnzr6p8pymp18hj"))))
6124 (build-system r-build-system)
6126 `(("r-ade4" ,r-ade4)
6127 ("r-segmented" ,r-segmented)))
6130 (home-page "http://seqinr.r-forge.r-project.org/")
6131 (synopsis "Biological sequences retrieval and analysis")
6133 "This package provides tools for exploratory data analysis and data
6134 visualization of biological sequence (DNA and protein) data. It also includes
6135 utilities for sequence data management under the ACNUC system.")
6136 (license license:gpl2+)))
6138 (define-public r-iranges
6144 (uri (bioconductor-uri "IRanges" version))
6147 "0cdl1sfd3cvf93lnz91fdk64fbg1mnd5g958dwh1il8r358hqq3f"))))
6149 `((upstream-name . "IRanges")))
6150 (build-system r-build-system)
6152 `(("r-biocgenerics" ,r-biocgenerics)
6153 ("r-s4vectors" ,r-s4vectors)))
6154 (home-page "http://bioconductor.org/packages/IRanges")
6155 (synopsis "Infrastructure for manipulating intervals on sequences")
6157 "This package provides efficient low-level and highly reusable S4 classes
6158 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6159 generally, data that can be organized sequentially (formally defined as
6160 @code{Vector} objects), as well as views on these @code{Vector} objects.
6161 Efficient list-like classes are also provided for storing big collections of
6162 instances of the basic classes. All classes in the package use consistent
6163 naming and share the same rich and consistent \"Vector API\" as much as
6165 (license license:artistic2.0)))
6167 (define-public r-genomeinfodb
6169 (name "r-genomeinfodb")
6173 (uri (bioconductor-uri "GenomeInfoDb" version))
6176 "0nhg4bk38gzvf3mvnbqgisbbhfv1kzjld27z1z9knnlkplkiyyyv"))))
6178 `((upstream-name . "GenomeInfoDb")))
6179 (build-system r-build-system)
6181 `(("r-biocgenerics" ,r-biocgenerics)
6182 ("r-iranges" ,r-iranges)
6183 ("r-s4vectors" ,r-s4vectors)))
6184 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6185 (synopsis "Utilities for manipulating chromosome identifiers")
6187 "This package contains data and functions that define and allow
6188 translation between different chromosome sequence naming conventions (e.g.,
6189 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6190 names in their natural, rather than lexicographic, order.")
6191 (license license:artistic2.0)))
6193 (define-public r-edger
6199 (uri (bioconductor-uri "edgeR" version))
6202 "1r6hhwkqp13m022hjajzr1lnjsbai0yjhykwn0kp1f0la990a808"))))
6203 (properties `((upstream-name . "edgeR")))
6204 (build-system r-build-system)
6206 `(("r-limma" ,r-limma)
6207 ("r-locfit" ,r-locfit)))
6208 (home-page "http://bioinf.wehi.edu.au/edgeR")
6209 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6210 (description "This package can do differential expression analysis of
6211 RNA-seq expression profiles with biological replication. It implements a range
6212 of statistical methodology based on the negative binomial distributions,
6213 including empirical Bayes estimation, exact tests, generalized linear models
6214 and quasi-likelihood tests. It be applied to differential signal analysis of
6215 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6217 (license license:gpl2+)))
6219 (define-public r-variantannotation
6221 (name "r-variantannotation")
6225 (uri (bioconductor-uri "VariantAnnotation" version))
6228 "1lwzfgahz8ipwli73kcfqb18y6adi129hap1gnycnj3980m54i8q"))))
6230 `((upstream-name . "VariantAnnotation")))
6234 `(("r-annotationdbi" ,r-annotationdbi)
6235 ("r-biobase" ,r-biobase)
6236 ("r-biocgenerics" ,r-biocgenerics)
6237 ("r-biostrings" ,r-biostrings)
6238 ("r-bsgenome" ,r-bsgenome)
6240 ("r-genomeinfodb" ,r-genomeinfodb)
6241 ("r-genomicfeatures" ,r-genomicfeatures)
6242 ("r-genomicranges" ,r-genomicranges)
6243 ("r-iranges" ,r-iranges)
6244 ("r-summarizedexperiment" ,r-summarizedexperiment)
6245 ("r-rsamtools" ,r-rsamtools)
6246 ("r-rtracklayer" ,r-rtracklayer)
6247 ("r-s4vectors" ,r-s4vectors)
6248 ("r-xvector" ,r-xvector)
6249 ("r-zlibbioc" ,r-zlibbioc)))
6250 (build-system r-build-system)
6251 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6252 (synopsis "Package for annotation of genetic variants")
6253 (description "This R package can annotate variants, compute amino acid
6254 coding changes and predict coding outcomes.")
6255 (license license:artistic2.0)))
6257 (define-public r-limma
6263 (uri (bioconductor-uri "limma" version))
6266 "04jris7wk2lxksrrvrjsysznsdb2k04lfgrnp18ic49sazva0hfy"))))
6267 (build-system r-build-system)
6268 (home-page "http://bioinf.wehi.edu.au/limma")
6269 (synopsis "Package for linear models for microarray and RNA-seq data")
6270 (description "This package can be used for the analysis of gene expression
6271 studies, especially the use of linear models for analysing designed experiments
6272 and the assessment of differential expression. The analysis methods apply to
6273 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6274 (license license:gpl2+)))
6276 (define-public r-xvector
6282 (uri (bioconductor-uri "XVector" version))
6285 "09lbqxpqr80g0kw77mpz0p1a8cq706j33kz8194wp71il67cdzi7"))))
6287 `((upstream-name . "XVector")))
6288 (build-system r-build-system)
6291 (modify-phases %standard-phases
6292 (add-after 'unpack 'use-system-zlib
6294 (substitute* "DESCRIPTION"
6295 (("zlibbioc, ") ""))
6296 (substitute* "NAMESPACE"
6297 (("import\\(zlibbioc\\)") ""))
6302 `(("r-biocgenerics" ,r-biocgenerics)
6303 ("r-iranges" ,r-iranges)
6304 ("r-s4vectors" ,r-s4vectors)))
6305 (home-page "http://bioconductor.org/packages/XVector")
6306 (synopsis "Representation and manpulation of external sequences")
6308 "This package provides memory efficient S4 classes for storing sequences
6309 \"externally\" (behind an R external pointer, or on disk).")
6310 (license license:artistic2.0)))
6312 (define-public r-genomicranges
6314 (name "r-genomicranges")
6318 (uri (bioconductor-uri "GenomicRanges" version))
6321 "039nxccg9i2an8q2wni79x8dr9p1fcfcqvih9hg9w243pczg2g3c"))))
6323 `((upstream-name . "GenomicRanges")))
6324 (build-system r-build-system)
6326 `(("r-biocgenerics" ,r-biocgenerics)
6327 ("r-genomeinfodb" ,r-genomeinfodb)
6328 ("r-iranges" ,r-iranges)
6329 ("r-s4vectors" ,r-s4vectors)
6330 ("r-xvector" ,r-xvector)))
6331 (home-page "http://bioconductor.org/packages/GenomicRanges")
6332 (synopsis "Representation and manipulation of genomic intervals")
6334 "This package provides tools to efficiently represent and manipulate
6335 genomic annotations and alignments is playing a central role when it comes to
6336 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6337 GenomicRanges package defines general purpose containers for storing and
6338 manipulating genomic intervals and variables defined along a genome.")
6339 (license license:artistic2.0)))
6341 (define-public r-biobase
6347 (uri (bioconductor-uri "Biobase" version))
6350 "0js9j9wqls8f571ifl9ylllbb9a9hwf7b7drf2grwb1fl31ldazl"))))
6352 `((upstream-name . "Biobase")))
6353 (build-system r-build-system)
6355 `(("r-biocgenerics" ,r-biocgenerics)))
6356 (home-page "http://bioconductor.org/packages/Biobase")
6357 (synopsis "Base functions for Bioconductor")
6359 "This package provides functions that are needed by many other packages
6360 on Bioconductor or which replace R functions.")
6361 (license license:artistic2.0)))
6363 (define-public r-annotationdbi
6365 (name "r-annotationdbi")
6369 (uri (bioconductor-uri "AnnotationDbi" version))
6372 "0ydrqw1k1j5p6w76bwc753cx545c055x88q87wzya93858synj6r"))))
6374 `((upstream-name . "AnnotationDbi")))
6375 (build-system r-build-system)
6377 `(("r-biobase" ,r-biobase)
6378 ("r-biocgenerics" ,r-biocgenerics)
6380 ("r-iranges" ,r-iranges)
6381 ("r-rsqlite" ,r-rsqlite)
6382 ("r-s4vectors" ,r-s4vectors)))
6383 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6384 (synopsis "Annotation database interface")
6386 "This package provides user interface and database connection code for
6387 annotation data packages using SQLite data storage.")
6388 (license license:artistic2.0)))
6390 (define-public r-biomart
6396 (uri (bioconductor-uri "biomaRt" version))
6399 "1x0flcghq71784q2l02j0g4f9jkmyb14f6i307n6c59d6ji7h7x6"))))
6401 `((upstream-name . "biomaRt")))
6402 (build-system r-build-system)
6404 `(("r-annotationdbi" ,r-annotationdbi)
6405 ("r-rcurl" ,r-rcurl)
6407 (home-page "http://bioconductor.org/packages/biomaRt")
6408 (synopsis "Interface to BioMart databases")
6410 "biomaRt provides an interface to a growing collection of databases
6411 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6412 package enables retrieval of large amounts of data in a uniform way without
6413 the need to know the underlying database schemas or write complex SQL queries.
6414 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6415 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6416 users direct access to a diverse set of data and enable a wide range of
6417 powerful online queries from gene annotation to database mining.")
6418 (license license:artistic2.0)))
6420 (define-public r-biocparallel
6422 (name "r-biocparallel")
6426 (uri (bioconductor-uri "BiocParallel" version))
6429 "123i928rwi4h4sy4fpysv6pinw5nns0sm3myxi2ghqhm34ws8gyl"))))
6431 `((upstream-name . "BiocParallel")))
6432 (build-system r-build-system)
6434 `(("r-futile-logger" ,r-futile-logger)
6435 ("r-snow" ,r-snow)))
6436 (home-page "http://bioconductor.org/packages/BiocParallel")
6437 (synopsis "Bioconductor facilities for parallel evaluation")
6439 "This package provides modified versions and novel implementation of
6440 functions for parallel evaluation, tailored to use with Bioconductor
6442 (license (list license:gpl2+ license:gpl3+))))
6444 (define-public r-biostrings
6446 (name "r-biostrings")
6450 (uri (bioconductor-uri "Biostrings" version))
6453 "08z8lkz3axa94wkf144a931ry6vf6cc25avi1ywr84ln2k5czz9f"))))
6455 `((upstream-name . "Biostrings")))
6456 (build-system r-build-system)
6458 `(("r-biocgenerics" ,r-biocgenerics)
6459 ("r-iranges" ,r-iranges)
6460 ("r-s4vectors" ,r-s4vectors)
6461 ("r-xvector" ,r-xvector)))
6462 (home-page "http://bioconductor.org/packages/Biostrings")
6463 (synopsis "String objects and algorithms for biological sequences")
6465 "This package provides memory efficient string containers, string
6466 matching algorithms, and other utilities, for fast manipulation of large
6467 biological sequences or sets of sequences.")
6468 (license license:artistic2.0)))
6470 (define-public r-rsamtools
6472 (name "r-rsamtools")
6476 (uri (bioconductor-uri "Rsamtools" version))
6479 "0pf4f6brf4bl5zgjrah0f38qslazrs49ayqgyh0xfqgrh63yx4ck"))))
6481 `((upstream-name . "Rsamtools")))
6482 (build-system r-build-system)
6485 (modify-phases %standard-phases
6486 (add-after 'unpack 'use-system-zlib
6488 (substitute* "DESCRIPTION"
6489 (("zlibbioc, ") ""))
6490 (substitute* "NAMESPACE"
6491 (("import\\(zlibbioc\\)") ""))
6496 `(("r-biocgenerics" ,r-biocgenerics)
6497 ("r-biocparallel" ,r-biocparallel)
6498 ("r-biostrings" ,r-biostrings)
6499 ("r-bitops" ,r-bitops)
6500 ("r-genomeinfodb" ,r-genomeinfodb)
6501 ("r-genomicranges" ,r-genomicranges)
6502 ("r-iranges" ,r-iranges)
6503 ("r-s4vectors" ,r-s4vectors)
6504 ("r-xvector" ,r-xvector)))
6505 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6506 (synopsis "Interface to samtools, bcftools, and tabix")
6508 "This package provides an interface to the 'samtools', 'bcftools', and
6509 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6510 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6512 (license license:expat)))
6514 (define-public r-summarizedexperiment
6516 (name "r-summarizedexperiment")
6520 (uri (bioconductor-uri "SummarizedExperiment" version))
6523 "1kbj8sg2ik9f8d6g95wz0py62jldg01qy5rsdpg1cxw95nf7dzi3"))))
6525 `((upstream-name . "SummarizedExperiment")))
6526 (build-system r-build-system)
6528 `(("r-biobase" ,r-biobase)
6529 ("r-biocgenerics" ,r-biocgenerics)
6530 ("r-genomeinfodb" ,r-genomeinfodb)
6531 ("r-genomicranges" ,r-genomicranges)
6532 ("r-iranges" ,r-iranges)
6533 ("r-s4vectors" ,r-s4vectors)))
6534 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
6535 (synopsis "Container for representing genomic ranges by sample")
6537 "The SummarizedExperiment container contains one or more assays, each
6538 represented by a matrix-like object of numeric or other mode. The rows
6539 typically represent genomic ranges of interest and the columns represent
6541 (license license:artistic2.0)))
6543 (define-public r-genomicalignments
6545 (name "r-genomicalignments")
6549 (uri (bioconductor-uri "GenomicAlignments" version))
6552 "11vb0a0zd36i4yhg4mfijv787v0nihn6pkjj6q7rfy19gwy61xlc"))))
6554 `((upstream-name . "GenomicAlignments")))
6555 (build-system r-build-system)
6557 `(("r-biocgenerics" ,r-biocgenerics)
6558 ("r-biocparallel" ,r-biocparallel)
6559 ("r-biostrings" ,r-biostrings)
6560 ("r-genomeinfodb" ,r-genomeinfodb)
6561 ("r-genomicranges" ,r-genomicranges)
6562 ("r-iranges" ,r-iranges)
6563 ("r-rsamtools" ,r-rsamtools)
6564 ("r-s4vectors" ,r-s4vectors)
6565 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6566 (home-page "http://bioconductor.org/packages/GenomicAlignments")
6567 (synopsis "Representation and manipulation of short genomic alignments")
6569 "This package provides efficient containers for storing and manipulating
6570 short genomic alignments (typically obtained by aligning short reads to a
6571 reference genome). This includes read counting, computing the coverage,
6572 junction detection, and working with the nucleotide content of the
6574 (license license:artistic2.0)))
6576 (define-public r-rtracklayer
6578 (name "r-rtracklayer")
6582 (uri (bioconductor-uri "rtracklayer" version))
6585 "0x59k2fd0iaqi93gy6bm58p2j2z90z1b7a6w5b4c098y98n096rc"))))
6586 (build-system r-build-system)
6589 (modify-phases %standard-phases
6590 (add-after 'unpack 'use-system-zlib
6592 (substitute* "DESCRIPTION"
6593 (("zlibbioc, ") ""))
6594 (substitute* "NAMESPACE"
6595 (("import\\(zlibbioc\\)") ""))
6600 `(("r-biocgenerics" ,r-biocgenerics)
6601 ("r-biostrings" ,r-biostrings)
6602 ("r-genomeinfodb" ,r-genomeinfodb)
6603 ("r-genomicalignments" ,r-genomicalignments)
6604 ("r-genomicranges" ,r-genomicranges)
6605 ("r-iranges" ,r-iranges)
6606 ("r-rcurl" ,r-rcurl)
6607 ("r-rsamtools" ,r-rsamtools)
6608 ("r-s4vectors" ,r-s4vectors)
6610 ("r-xvector" ,r-xvector)))
6611 (home-page "http://bioconductor.org/packages/rtracklayer")
6612 (synopsis "R interface to genome browsers and their annotation tracks")
6614 "rtracklayer is an extensible framework for interacting with multiple
6615 genome browsers (currently UCSC built-in) and manipulating annotation tracks
6616 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
6617 built-in). The user may export/import tracks to/from the supported browsers,
6618 as well as query and modify the browser state, such as the current viewport.")
6619 (license license:artistic2.0)))
6621 (define-public r-genomicfeatures
6623 (name "r-genomicfeatures")
6627 (uri (bioconductor-uri "GenomicFeatures" version))
6630 "0z8spi2knwzwi10c38vr7xlvi3ah9faj7m1lka880mmxkl9cai4k"))))
6632 `((upstream-name . "GenomicFeatures")))
6633 (build-system r-build-system)
6635 `(("r-annotationdbi" ,r-annotationdbi)
6636 ("r-biobase" ,r-biobase)
6637 ("r-biocgenerics" ,r-biocgenerics)
6638 ("r-biomart" ,r-biomart)
6639 ("r-biostrings" ,r-biostrings)
6641 ("r-genomeinfodb" ,r-genomeinfodb)
6642 ("r-genomicranges" ,r-genomicranges)
6643 ("r-iranges" ,r-iranges)
6644 ("r-rcurl" ,r-rcurl)
6645 ("r-rsqlite" ,r-rsqlite)
6646 ("r-rtracklayer" ,r-rtracklayer)
6647 ("r-s4vectors" ,r-s4vectors)
6648 ("r-xvector" ,r-xvector)))
6649 (home-page "http://bioconductor.org/packages/GenomicFeatures")
6650 (synopsis "Tools for working with transcript centric annotations")
6652 "This package provides a set of tools and methods for making and
6653 manipulating transcript centric annotations. With these tools the user can
6654 easily download the genomic locations of the transcripts, exons and cds of a
6655 given organism, from either the UCSC Genome Browser or a BioMart
6656 database (more sources will be supported in the future). This information is
6657 then stored in a local database that keeps track of the relationship between
6658 transcripts, exons, cds and genes. Flexible methods are provided for
6659 extracting the desired features in a convenient format.")
6660 (license license:artistic2.0)))
6662 (define-public r-go-db
6668 (uri (string-append "http://www.bioconductor.org/packages/"
6669 "release/data/annotation/src/contrib/GO.db_"
6673 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
6675 `((upstream-name . "GO.db")))
6676 (build-system r-build-system)
6678 `(("r-annotationdbi" ,r-annotationdbi)))
6679 (home-page "http://bioconductor.org/packages/GO.db")
6680 (synopsis "Annotation maps describing the entire Gene Ontology")
6682 "The purpose of this GO.db annotation package is to provide detailed
6683 information about the latest version of the Gene Ontologies.")
6684 (license license:artistic2.0)))
6686 (define-public r-graph
6692 (uri (bioconductor-uri "graph" version))
6695 "0g3dk5vsdp489fmyg8mifczmzgqrjlakkkr8i96dj15gghp3l135"))))
6696 (build-system r-build-system)
6698 `(("r-biocgenerics" ,r-biocgenerics)))
6699 (home-page "http://bioconductor.org/packages/graph")
6700 (synopsis "Handle graph data structures in R")
6702 "This package implements some simple graph handling capabilities for R.")
6703 (license license:artistic2.0)))
6705 (define-public r-topgo
6711 (uri (bioconductor-uri "topGO" version))
6714 "0j6sgvam4lk9348ag6pypcbkv93x4fk0di8ivhr23mz2s2yqzwrx"))))
6716 `((upstream-name . "topGO")))
6717 (build-system r-build-system)
6719 `(("r-annotationdbi" ,r-annotationdbi)
6721 ("r-biobase" ,r-biobase)
6722 ("r-biocgenerics" ,r-biocgenerics)
6723 ("r-go-db" ,r-go-db)
6724 ("r-matrixstats" ,r-matrixstats)
6725 ("r-graph" ,r-graph)
6726 ("r-sparsem" ,r-sparsem)))
6727 (home-page "http://bioconductor.org/packages/topGO")
6728 (synopsis "Enrichment analysis for gene ontology")
6730 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
6731 terms while accounting for the topology of the GO graph. Different test
6732 statistics and different methods for eliminating local similarities and
6733 dependencies between GO terms can be implemented and applied.")
6734 ;; Any version of the LGPL applies.
6735 (license license:lgpl2.1+)))
6737 (define-public r-bsgenome
6743 (uri (bioconductor-uri "BSgenome" version))
6746 "0hxwc02h5mzhkrk60d1jmlsfjf0ai9jxdc0128kj1sg4r2k1q94y"))))
6748 `((upstream-name . "BSgenome")))
6749 (build-system r-build-system)
6751 `(("r-biocgenerics" ,r-biocgenerics)
6752 ("r-biostrings" ,r-biostrings)
6753 ("r-genomeinfodb" ,r-genomeinfodb)
6754 ("r-genomicranges" ,r-genomicranges)
6755 ("r-iranges" ,r-iranges)
6756 ("r-rsamtools" ,r-rsamtools)
6757 ("r-rtracklayer" ,r-rtracklayer)
6758 ("r-s4vectors" ,r-s4vectors)
6759 ("r-xvector" ,r-xvector)))
6760 (home-page "http://bioconductor.org/packages/BSgenome")
6761 (synopsis "Infrastructure for Biostrings-based genome data packages")
6763 "This package provides infrastructure shared by all Biostrings-based
6764 genome data packages and support for efficient SNP representation.")
6765 (license license:artistic2.0)))
6767 (define-public r-impute
6773 (uri (bioconductor-uri "impute" version))
6776 "1164zvnikbjd0ybdn9xwn520rlmdjd824vmhnl83zgv3v9lzp9bm"))))
6778 `(("gfortran" ,gfortran)))
6779 (build-system r-build-system)
6780 (home-page "http://bioconductor.org/packages/impute")
6781 (synopsis "Imputation for microarray data")
6783 "This package provides a function to impute missing gene expression
6784 microarray data, using nearest neighbor averaging.")
6785 (license license:gpl2+)))
6787 (define-public r-seqpattern
6789 (name "r-seqpattern")
6793 (uri (bioconductor-uri "seqPattern" version))
6796 "0lsa5pz36xapi3yiv78k3z286a5md5sm5g21pgfyg8zmhmkxr7y8"))))
6798 `((upstream-name . "seqPattern")))
6799 (build-system r-build-system)
6801 `(("r-biostrings" ,r-biostrings)
6802 ("r-genomicranges" ,r-genomicranges)
6803 ("r-iranges" ,r-iranges)
6804 ("r-kernsmooth" ,r-kernsmooth)
6805 ("r-plotrix" ,r-plotrix)))
6806 (home-page "http://bioconductor.org/packages/seqPattern")
6807 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
6809 "This package provides tools to visualize oligonucleotide patterns and
6810 sequence motif occurrences across a large set of sequences centred at a common
6811 reference point and sorted by a user defined feature.")
6812 (license license:gpl3+)))
6814 (define-public r-genomation
6816 (name "r-genomation")
6820 (uri (bioconductor-uri "genomation" version))
6823 "1m4mz7wihj8yqivwkzw68div8ybk4rjsai3ffki7xp7sh21ax03y"))))
6824 (build-system r-build-system)
6826 `(("r-biostrings" ,r-biostrings)
6827 ("r-bsgenome" ,r-bsgenome)
6828 ("r-data-table" ,r-data-table)
6829 ("r-genomeinfodb" ,r-genomeinfodb)
6830 ("r-genomicalignments" ,r-genomicalignments)
6831 ("r-genomicranges" ,r-genomicranges)
6832 ("r-ggplot2" ,r-ggplot2)
6833 ("r-gridbase" ,r-gridbase)
6834 ("r-impute" ,r-impute)
6835 ("r-iranges" ,r-iranges)
6836 ("r-matrixstats" ,r-matrixstats)
6837 ("r-plotrix" ,r-plotrix)
6840 ("r-readr" ,r-readr)
6841 ("r-reshape2" ,r-reshape2)
6842 ("r-rhtslib" ,r-rhtslib)
6843 ("r-rsamtools" ,r-rsamtools)
6844 ("r-rtracklayer" ,r-rtracklayer)
6845 ("r-runit" ,r-runit)
6846 ("r-s4vectors" ,r-s4vectors)
6847 ("r-seqpattern" ,r-seqpattern)))
6850 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
6851 (synopsis "Summary, annotation and visualization of genomic data")
6853 "This package provides a package for summary and annotation of genomic
6854 intervals. Users can visualize and quantify genomic intervals over
6855 pre-defined functional regions, such as promoters, exons, introns, etc. The
6856 genomic intervals represent regions with a defined chromosome position, which
6857 may be associated with a score, such as aligned reads from HT-seq experiments,
6858 TF binding sites, methylation scores, etc. The package can use any tabular
6859 genomic feature data as long as it has minimal information on the locations of
6860 genomic intervals. In addition, it can use BAM or BigWig files as input.")
6861 (license license:artistic2.0)))
6863 (define-public r-genomationdata
6865 (name "r-genomationdata")
6869 ;; We cannot use bioconductor-uri here because this tarball is
6870 ;; located under "data/annotation/" instead of "bioc/".
6871 (uri (string-append "https://bioconductor.org/packages/"
6872 "release/data/experiment/src/contrib/"
6873 "genomationData_" version ".tar.gz"))
6876 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
6877 (build-system r-build-system)
6878 ;; As this package provides little more than large data files, it doesn't
6879 ;; make sense to build substitutes.
6880 (arguments `(#:substitutable? #f))
6882 `(("r-knitr" ,r-knitr)))
6883 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
6884 (synopsis "Experimental data for use with the genomation package")
6886 "This package contains experimental genetic data for use with the
6887 genomation package. Included are Chip Seq, Methylation and Cage data,
6888 downloaded from Encode.")
6889 (license license:gpl3+)))
6891 (define-public r-org-hs-eg-db
6893 (name "r-org-hs-eg-db")
6897 ;; We cannot use bioconductor-uri here because this tarball is
6898 ;; located under "data/annotation/" instead of "bioc/".
6899 (uri (string-append "http://www.bioconductor.org/packages/"
6900 "release/data/annotation/src/contrib/"
6901 "org.Hs.eg.db_" version ".tar.gz"))
6904 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
6906 `((upstream-name . "org.Hs.eg.db")))
6907 (build-system r-build-system)
6909 `(("r-annotationdbi" ,r-annotationdbi)))
6910 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
6911 (synopsis "Genome wide annotation for Human")
6913 "This package provides mappings from Entrez gene identifiers to various
6914 annotations for the human genome.")
6915 (license license:artistic2.0)))
6917 (define-public r-org-ce-eg-db
6919 (name "r-org-ce-eg-db")
6923 ;; We cannot use bioconductor-uri here because this tarball is
6924 ;; located under "data/annotation/" instead of "bioc/".
6925 (uri (string-append "http://www.bioconductor.org/packages/"
6926 "release/data/annotation/src/contrib/"
6927 "org.Ce.eg.db_" version ".tar.gz"))
6930 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
6932 `((upstream-name . "org.Ce.eg.db")))
6933 (build-system r-build-system)
6935 `(("r-annotationdbi" ,r-annotationdbi)))
6936 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
6937 (synopsis "Genome wide annotation for Worm")
6939 "This package provides mappings from Entrez gene identifiers to various
6940 annotations for the genome of the model worm Caenorhabditis elegans.")
6941 (license license:artistic2.0)))
6943 (define-public r-org-dm-eg-db
6945 (name "r-org-dm-eg-db")
6949 ;; We cannot use bioconductor-uri here because this tarball is
6950 ;; located under "data/annotation/" instead of "bioc/".
6951 (uri (string-append "http://www.bioconductor.org/packages/"
6952 "release/data/annotation/src/contrib/"
6953 "org.Dm.eg.db_" version ".tar.gz"))
6956 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
6958 `((upstream-name . "org.Dm.eg.db")))
6959 (build-system r-build-system)
6961 `(("r-annotationdbi" ,r-annotationdbi)))
6962 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
6963 (synopsis "Genome wide annotation for Fly")
6965 "This package provides mappings from Entrez gene identifiers to various
6966 annotations for the genome of the model fruit fly Drosophila melanogaster.")
6967 (license license:artistic2.0)))
6969 (define-public r-org-mm-eg-db
6971 (name "r-org-mm-eg-db")
6975 ;; We cannot use bioconductor-uri here because this tarball is
6976 ;; located under "data/annotation/" instead of "bioc/".
6977 (uri (string-append "http://www.bioconductor.org/packages/"
6978 "release/data/annotation/src/contrib/"
6979 "org.Mm.eg.db_" version ".tar.gz"))
6982 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
6984 `((upstream-name . "org.Mm.eg.db")))
6985 (build-system r-build-system)
6987 `(("r-annotationdbi" ,r-annotationdbi)))
6988 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
6989 (synopsis "Genome wide annotation for Mouse")
6991 "This package provides mappings from Entrez gene identifiers to various
6992 annotations for the genome of the model mouse Mus musculus.")
6993 (license license:artistic2.0)))
6995 (define-public r-seqlogo
7002 (uri (bioconductor-uri "seqLogo" version))
7005 "18bajdl75h3039559d81rgllqqvnq8ygsfxfx081xphxs0v6xggy"))))
7006 (properties `((upstream-name . "seqLogo")))
7007 (build-system r-build-system)
7008 (home-page "http://bioconductor.org/packages/seqLogo")
7009 (synopsis "Sequence logos for DNA sequence alignments")
7011 "seqLogo takes the position weight matrix of a DNA sequence motif and
7012 plots the corresponding sequence logo as introduced by Schneider and
7014 (license license:lgpl2.0+)))
7016 (define-public r-bsgenome-hsapiens-ucsc-hg19
7018 (name "r-bsgenome-hsapiens-ucsc-hg19")
7022 ;; We cannot use bioconductor-uri here because this tarball is
7023 ;; located under "data/annotation/" instead of "bioc/".
7024 (uri (string-append "http://www.bioconductor.org/packages/"
7025 "release/data/annotation/src/contrib/"
7026 "BSgenome.Hsapiens.UCSC.hg19_"
7030 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7032 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7033 (build-system r-build-system)
7034 ;; As this package provides little more than a very large data file it
7035 ;; doesn't make sense to build substitutes.
7036 (arguments `(#:substitutable? #f))
7038 `(("r-bsgenome" ,r-bsgenome)))
7040 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7041 (synopsis "Full genome sequences for Homo sapiens")
7043 "This package provides full genome sequences for Homo sapiens as provided
7044 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7045 (license license:artistic2.0)))
7047 (define-public r-bsgenome-mmusculus-ucsc-mm9
7049 (name "r-bsgenome-mmusculus-ucsc-mm9")
7053 ;; We cannot use bioconductor-uri here because this tarball is
7054 ;; located under "data/annotation/" instead of "bioc/".
7055 (uri (string-append "http://www.bioconductor.org/packages/"
7056 "release/data/annotation/src/contrib/"
7057 "BSgenome.Mmusculus.UCSC.mm9_"
7061 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7063 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7064 (build-system r-build-system)
7065 ;; As this package provides little more than a very large data file it
7066 ;; doesn't make sense to build substitutes.
7067 (arguments `(#:substitutable? #f))
7069 `(("r-bsgenome" ,r-bsgenome)))
7071 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7072 (synopsis "Full genome sequences for Mouse")
7074 "This package provides full genome sequences for Mus musculus (Mouse) as
7075 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7076 (license license:artistic2.0)))
7078 (define-public r-bsgenome-mmusculus-ucsc-mm10
7080 (name "r-bsgenome-mmusculus-ucsc-mm10")
7084 ;; We cannot use bioconductor-uri here because this tarball is
7085 ;; located under "data/annotation/" instead of "bioc/".
7086 (uri (string-append "http://www.bioconductor.org/packages/"
7087 "release/data/annotation/src/contrib/"
7088 "BSgenome.Mmusculus.UCSC.mm10_"
7092 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7094 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7095 (build-system r-build-system)
7096 ;; As this package provides little more than a very large data file it
7097 ;; doesn't make sense to build substitutes.
7098 (arguments `(#:substitutable? #f))
7100 `(("r-bsgenome" ,r-bsgenome)))
7102 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7103 (synopsis "Full genome sequences for Mouse")
7105 "This package provides full genome sequences for Mus
7106 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7107 in Biostrings objects.")
7108 (license license:artistic2.0)))
7110 (define-public r-bsgenome-celegans-ucsc-ce6
7112 (name "r-bsgenome-celegans-ucsc-ce6")
7116 ;; We cannot use bioconductor-uri here because this tarball is
7117 ;; located under "data/annotation/" instead of "bioc/".
7118 (uri (string-append "http://www.bioconductor.org/packages/"
7119 "release/data/annotation/src/contrib/"
7120 "BSgenome.Celegans.UCSC.ce6_"
7124 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7126 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7127 (build-system r-build-system)
7128 ;; As this package provides little more than a very large data file it
7129 ;; doesn't make sense to build substitutes.
7130 (arguments `(#:substitutable? #f))
7132 `(("r-bsgenome" ,r-bsgenome)))
7134 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7135 (synopsis "Full genome sequences for Worm")
7137 "This package provides full genome sequences for Caenorhabditis
7138 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7140 (license license:artistic2.0)))
7142 (define-public r-bsgenome-celegans-ucsc-ce10
7144 (name "r-bsgenome-celegans-ucsc-ce10")
7148 ;; We cannot use bioconductor-uri here because this tarball is
7149 ;; located under "data/annotation/" instead of "bioc/".
7150 (uri (string-append "http://www.bioconductor.org/packages/"
7151 "release/data/annotation/src/contrib/"
7152 "BSgenome.Celegans.UCSC.ce10_"
7156 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7158 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7159 (build-system r-build-system)
7160 ;; As this package provides little more than a very large data file it
7161 ;; doesn't make sense to build substitutes.
7162 (arguments `(#:substitutable? #f))
7164 `(("r-bsgenome" ,r-bsgenome)))
7166 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7167 (synopsis "Full genome sequences for Worm")
7169 "This package provides full genome sequences for Caenorhabditis
7170 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7172 (license license:artistic2.0)))
7174 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7176 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7180 ;; We cannot use bioconductor-uri here because this tarball is
7181 ;; located under "data/annotation/" instead of "bioc/".
7182 (uri (string-append "http://www.bioconductor.org/packages/"
7183 "release/data/annotation/src/contrib/"
7184 "BSgenome.Dmelanogaster.UCSC.dm3_"
7188 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7190 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7191 (build-system r-build-system)
7192 ;; As this package provides little more than a very large data file it
7193 ;; doesn't make sense to build substitutes.
7194 (arguments `(#:substitutable? #f))
7196 `(("r-bsgenome" ,r-bsgenome)))
7198 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7199 (synopsis "Full genome sequences for Fly")
7201 "This package provides full genome sequences for Drosophila
7202 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7203 Biostrings objects.")
7204 (license license:artistic2.0)))
7206 (define-public r-motifrg
7213 (uri (bioconductor-uri "motifRG" version))
7216 "1pa97aj6c5f3gx4bgriw110764dj3m9h104ddi8rv2bpy41yd98d"))))
7217 (properties `((upstream-name . "motifRG")))
7218 (build-system r-build-system)
7220 `(("r-biostrings" ,r-biostrings)
7221 ("r-bsgenome" ,r-bsgenome)
7222 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7223 ("r-iranges" ,r-iranges)
7224 ("r-seqlogo" ,r-seqlogo)
7225 ("r-xvector" ,r-xvector)))
7226 (home-page "http://bioconductor.org/packages/motifRG")
7227 (synopsis "Discover motifs in high throughput sequencing data")
7229 "This package provides tools for discriminative motif discovery in high
7230 throughput genetic sequencing data sets using regression methods.")
7231 (license license:artistic2.0)))
7233 (define-public r-qtl
7240 (uri (string-append "mirror://cran/src/contrib/qtl_"
7244 "1grwgvyv7x0dgay1858bg7qf4wk47gpnq7qkqpcda9cn0h970d6f"))))
7245 (build-system r-build-system)
7246 (home-page "http://rqtl.org/")
7247 (synopsis "R package for analyzing QTL experiments in genetics")
7248 (description "R/qtl is an extension library for the R statistics
7249 system. It is used to analyze experimental crosses for identifying
7250 genes contributing to variation in quantitative traits (so-called
7251 quantitative trait loci, QTLs).
7253 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7254 identify genotyping errors, and to perform single-QTL and two-QTL,
7255 two-dimensional genome scans.")
7256 (license license:gpl3)))
7258 (define-public r-zlibbioc
7264 (uri (bioconductor-uri "zlibbioc" version))
7267 "0hbk90q5hl0fycfvy5nxxa4hxgglag9lzp7i0fg849bqygg5nbyq"))))
7269 `((upstream-name . "zlibbioc")))
7270 (build-system r-build-system)
7271 (home-page "https://bioconductor.org/packages/zlibbioc")
7272 (synopsis "Provider for zlib-1.2.5 to R packages")
7273 (description "This package uses the source code of zlib-1.2.5 to create
7274 libraries for systems that do not have these available via other means.")
7275 (license license:artistic2.0)))
7277 (define-public r-r4rna
7284 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7288 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7289 (build-system r-build-system)
7291 `(("r-optparse" ,r-optparse)
7292 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7293 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7294 (synopsis "Analysis framework for RNA secondary structure")
7296 "The R4RNA package aims to be a general framework for the analysis of RNA
7297 secondary structure and comparative analysis in R.")
7298 (license license:gpl3+)))
7300 (define-public r-rhtslib
7307 (uri (bioconductor-uri "Rhtslib" version))
7310 "1vk3ng61dhi3pbia1lp3gl3mlr3i1vb2lkq83qb53i9dzz128wh9"))))
7311 (properties `((upstream-name . "Rhtslib")))
7312 (build-system r-build-system)
7314 `(("r-zlibbioc" ,r-zlibbioc)))
7318 `(("autoconf" ,autoconf)))
7319 (home-page "https://github.com/nhayden/Rhtslib")
7320 (synopsis "High-throughput sequencing library as an R package")
7322 "This package provides the HTSlib C library for high-throughput
7323 nucleotide sequence analysis. The package is primarily useful to developers
7324 of other R packages who wish to make use of HTSlib.")
7325 (license license:lgpl2.0+)))
7327 (define-public r-bamsignals
7329 (name "r-bamsignals")
7334 (uri (bioconductor-uri "bamsignals" version))
7337 "1k42gvk5mgq4la1fp0in3an2zfdz69h6522jsqhmk0f6i75kg4mb"))))
7338 (build-system r-build-system)
7340 `(("r-biocgenerics" ,r-biocgenerics)
7341 ("r-genomicranges" ,r-genomicranges)
7342 ("r-iranges" ,r-iranges)
7344 ("r-rhtslib" ,r-rhtslib)
7345 ("r-zlibbioc" ,r-zlibbioc)))
7348 (home-page "http://bioconductor.org/packages/bamsignals")
7349 (synopsis "Extract read count signals from bam files")
7351 "This package allows to efficiently obtain count vectors from indexed bam
7352 files. It counts the number of nucleotide sequence reads in given genomic
7353 ranges and it computes reads profiles and coverage profiles. It also handles
7355 (license license:gpl2+)))
7357 (define-public r-rcas
7363 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7365 (file-name (string-append name "-" version ".tar.gz"))
7368 "1h7di822ihgkhmmmlfbfz3c2dkjyjxl307i6mx8w0cwjqbna1kp6"))))
7369 (build-system r-build-system)
7371 `(("r-knitr" ,r-knitr)
7372 ("r-testthat" ,r-testthat)
7373 ;; During vignette building knitr checks that "pandoc-citeproc"
7375 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7377 `(("r-data-table" ,r-data-table)
7378 ("r-biomart" ,r-biomart)
7379 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7380 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7381 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7382 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7383 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7384 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7385 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7386 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7387 ("r-topgo" ,r-topgo)
7389 ("r-plotly" ,r-plotly)
7390 ("r-motifrg" ,r-motifrg)
7391 ("r-genomation" ,r-genomation)
7392 ("r-genomicfeatures" ,r-genomicfeatures)
7393 ("r-rtracklayer" ,r-rtracklayer)
7394 ("r-rmarkdown" ,r-rmarkdown)))
7395 (synopsis "RNA-centric annotation system")
7397 "RCAS aims to be a standalone RNA-centric annotation system that provides
7398 intuitive reports and publication-ready graphics. This package provides the R
7399 library implementing most of the pipeline's features.")
7400 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7401 (license license:expat)))
7403 (define-public rcas-web
7410 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7411 "releases/download/v" version
7412 "/rcas-web-" version ".tar.gz"))
7415 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7416 (build-system gnu-build-system)
7419 (modify-phases %standard-phases
7420 (add-after 'install 'wrap-executable
7421 (lambda* (#:key inputs outputs #:allow-other-keys)
7422 (let* ((out (assoc-ref outputs "out"))
7423 (json (assoc-ref inputs "guile-json"))
7424 (redis (assoc-ref inputs "guile-redis"))
7425 (path (string-append
7426 json "/share/guile/site/2.2:"
7427 redis "/share/guile/site/2.2")))
7428 (wrap-program (string-append out "/bin/rcas-web")
7429 `("GUILE_LOAD_PATH" ":" = (,path))
7430 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
7431 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
7436 ("guile-next" ,guile-next)
7437 ("guile-json" ,guile2.2-json)
7438 ("guile-redis" ,guile2.2-redis)))
7440 `(("pkg-config" ,pkg-config)))
7441 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
7442 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
7443 (description "This package provides a simple web interface for the
7444 @dfn{RNA-centric annotation system} (RCAS).")
7445 (license license:agpl3+)))
7447 (define-public r-mutationalpatterns
7449 (name "r-mutationalpatterns")
7454 (uri (bioconductor-uri "MutationalPatterns" version))
7457 "1a3c2bm0xx0q4gf98jiw74msmdf2fr8rbsdysd5ww9kqlzmsbr17"))))
7458 (build-system r-build-system)
7460 `(("r-biocgenerics" ,r-biocgenerics)
7461 ("r-biostrings" ,r-biostrings)
7462 ("r-genomicranges" ,r-genomicranges)
7463 ("r-genomeinfodb" ,r-genomeinfodb)
7464 ("r-ggplot2" ,r-ggplot2)
7465 ("r-gridextra" ,r-gridextra)
7466 ("r-iranges" ,r-iranges)
7469 ("r-pracma" ,r-pracma)
7470 ("r-reshape2" ,r-reshape2)
7471 ("r-summarizedexperiment" ,r-summarizedexperiment)
7472 ("r-variantannotation" ,r-variantannotation)))
7473 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
7474 (synopsis "Extract and visualize mutational patterns in genomic data")
7475 (description "This package provides an extensive toolset for the
7476 characterization and visualization of a wide range of mutational patterns
7477 in SNV base substitution data.")
7478 (license license:expat)))
7480 (define-public r-wgcna
7487 (uri (cran-uri "WGCNA" version))
7490 "0hzvnhw76vwg8bl8x368f0c5szpwb8323bmrb3bir93i5bmfjsxx"))))
7491 (properties `((upstream-name . "WGCNA")))
7492 (build-system r-build-system)
7494 `(("r-annotationdbi" ,r-annotationdbi)
7495 ("r-doparallel" ,r-doparallel)
7496 ("r-dynamictreecut" ,r-dynamictreecut)
7497 ("r-fastcluster" ,r-fastcluster)
7498 ("r-foreach" ,r-foreach)
7499 ("r-go-db" ,r-go-db)
7500 ("r-hmisc" ,r-hmisc)
7501 ("r-impute" ,r-impute)
7502 ("r-matrixstats" ,r-matrixstats)
7503 ("r-preprocesscore" ,r-preprocesscore)))
7505 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
7506 (synopsis "Weighted correlation network analysis")
7508 "This package provides functions necessary to perform Weighted
7509 Correlation Network Analysis on high-dimensional data. It includes functions
7510 for rudimentary data cleaning, construction and summarization of correlation
7511 networks, module identification and functions for relating both variables and
7512 modules to sample traits. It also includes a number of utility functions for
7513 data manipulation and visualization.")
7514 (license license:gpl2+)))
7516 (define-public r-chipkernels
7517 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
7520 (name "r-chipkernels")
7521 (version (string-append "1.1-" revision "." (string-take commit 9)))
7526 (url "https://github.com/ManuSetty/ChIPKernels.git")
7528 (file-name (string-append name "-" version))
7531 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
7532 (build-system r-build-system)
7534 `(("r-iranges" ,r-iranges)
7535 ("r-xvector" ,r-xvector)
7536 ("r-biostrings" ,r-biostrings)
7537 ("r-bsgenome" ,r-bsgenome)
7538 ("r-gtools" ,r-gtools)
7539 ("r-genomicranges" ,r-genomicranges)
7540 ("r-sfsmisc" ,r-sfsmisc)
7541 ("r-kernlab" ,r-kernlab)
7542 ("r-s4vectors" ,r-s4vectors)
7543 ("r-biocgenerics" ,r-biocgenerics)))
7544 (home-page "https://github.com/ManuSetty/ChIPKernels")
7545 (synopsis "Build string kernels for DNA Sequence analysis")
7546 (description "ChIPKernels is an R package for building different string
7547 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
7548 must be built and this dictionary can be used for determining kernels for DNA
7550 (license license:gpl2+))))
7552 (define-public r-seqgl
7559 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
7560 "archive/" version ".tar.gz"))
7561 (file-name (string-append name "-" version ".tar.gz"))
7564 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
7565 (build-system r-build-system)
7567 `(("r-biostrings" ,r-biostrings)
7568 ("r-chipkernels" ,r-chipkernels)
7569 ("r-genomicranges" ,r-genomicranges)
7570 ("r-spams" ,r-spams)
7571 ("r-wgcna" ,r-wgcna)
7572 ("r-fastcluster" ,r-fastcluster)))
7573 (home-page "https://github.com/ManuSetty/SeqGL")
7574 (synopsis "Group lasso for Dnase/ChIP-seq data")
7575 (description "SeqGL is a group lasso based algorithm to extract
7576 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
7577 This package presents a method which uses group lasso to discriminate between
7578 bound and non bound genomic regions to accurately identify transcription
7579 factors bound at the specific regions.")
7580 (license license:gpl2+)))
7582 (define-public r-gkmsvm
7589 (uri (cran-uri "gkmSVM" version))
7592 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
7593 (properties `((upstream-name . "gkmSVM")))
7594 (build-system r-build-system)
7596 `(("r-biocgenerics" ,r-biocgenerics)
7597 ("r-biostrings" ,r-biostrings)
7598 ("r-genomeinfodb" ,r-genomeinfodb)
7599 ("r-genomicranges" ,r-genomicranges)
7600 ("r-iranges" ,r-iranges)
7601 ("r-kernlab" ,r-kernlab)
7604 ("r-rtracklayer" ,r-rtracklayer)
7605 ("r-s4vectors" ,r-s4vectors)
7606 ("r-seqinr" ,r-seqinr)))
7607 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
7608 (synopsis "Gapped-kmer support vector machine")
7610 "This R package provides tools for training gapped-kmer SVM classifiers
7611 for DNA and protein sequences. This package supports several sequence
7612 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
7613 (license license:gpl2+)))
7615 (define-public emboss
7621 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
7622 (version-major+minor version) ".0/"
7623 "EMBOSS-" version ".tar.gz"))
7626 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
7627 (build-system gnu-build-system)
7630 (list (string-append "--with-hpdf="
7631 (assoc-ref %build-inputs "libharu")))
7633 (modify-phases %standard-phases
7634 (add-after 'unpack 'fix-checks
7636 ;; The PNGDRIVER tests check for the presence of libgd, libpng
7637 ;; and zlib, but assume that they are all found at the same
7639 (substitute* "configure.in"
7640 (("CHECK_PNGDRIVER")
7641 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
7642 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
7643 AM_CONDITIONAL(AMPNG, true)"))
7645 (add-after 'unpack 'disable-update-check
7647 ;; At build time there is no connection to the Internet, so
7648 ;; looking for updates will not work.
7649 (substitute* "Makefile.am"
7650 (("\\$\\(bindir\\)/embossupdate") ""))
7652 (add-before 'configure 'autogen
7653 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
7659 ("libharu" ,libharu)
7662 `(("autoconf" ,autoconf)
7663 ("automake" ,automake)
7664 ("libtool" ,libtool)
7665 ("pkg-config" ,pkg-config)))
7666 (home-page "http://emboss.sourceforge.net")
7667 (synopsis "Molecular biology analysis suite")
7668 (description "EMBOSS is the \"European Molecular Biology Open Software
7669 Suite\". EMBOSS is an analysis package specially developed for the needs of
7670 the molecular biology (e.g. EMBnet) user community. The software
7671 automatically copes with data in a variety of formats and even allows
7672 transparent retrieval of sequence data from the web. It also provides a
7673 number of libraries for the development of software in the field of molecular
7674 biology. EMBOSS also integrates a range of currently available packages and
7675 tools for sequence analysis into a seamless whole.")
7676 (license license:gpl2+)))
7679 (let ((revision "1")
7680 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
7683 ;; The version is 2.13.0 even though no release archives have been
7684 ;; published as yet.
7685 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
7689 (url "https://github.com/arq5x/bits.git")
7691 (file-name (string-append name "-" version "-checkout"))
7694 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
7695 (build-system gnu-build-system)
7697 `(#:tests? #f ;no tests included
7699 (modify-phases %standard-phases
7701 (add-after 'unpack 'remove-cuda
7703 (substitute* "Makefile"
7705 (("(bits_test_intersections) \\\\" _ match) match))
7708 (lambda* (#:key outputs #:allow-other-keys)
7710 "bin" (string-append (assoc-ref outputs "out") "/bin"))
7715 (home-page "https://github.com/arq5x/bits")
7716 (synopsis "Implementation of binary interval search algorithm")
7717 (description "This package provides an implementation of the
7718 BITS (Binary Interval Search) algorithm, an approach to interval set
7719 intersection. It is especially suited for the comparison of diverse genomic
7720 datasets and the exploration of large datasets of genome
7721 intervals (e.g. genes, sequence alignments).")
7722 (license license:gpl2))))
7724 (define-public piranha
7725 ;; There is no release tarball for the latest version. The latest commit is
7726 ;; older than one year at the time of this writing.
7727 (let ((revision "1")
7728 (commit "0466d364b71117d01e4471b74c514436cc281233"))
7731 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
7735 (url "https://github.com/smithlabcode/piranha.git")
7739 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
7740 (build-system gnu-build-system)
7742 `(#:test-target "test"
7744 (modify-phases %standard-phases
7745 (add-after 'unpack 'copy-smithlab-cpp
7746 (lambda* (#:key inputs #:allow-other-keys)
7747 (for-each (lambda (file)
7748 (install-file file "./src/smithlab_cpp/"))
7749 (find-files (assoc-ref inputs "smithlab-cpp")))
7751 (add-after 'install 'install-to-store
7752 (lambda* (#:key outputs #:allow-other-keys)
7753 (let* ((out (assoc-ref outputs "out"))
7754 (bin (string-append out "/bin")))
7755 (for-each (lambda (file)
7756 (install-file file bin))
7757 (find-files "bin" ".*")))
7760 (list (string-append "--with-bam_tools_headers="
7761 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
7762 (string-append "--with-bam_tools_library="
7763 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
7765 `(("bamtools" ,bamtools)
7766 ("samtools" ,samtools-0.1)
7769 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
7773 (url "https://github.com/smithlabcode/smithlab_cpp.git")
7775 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
7778 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
7780 `(("python" ,python-2)))
7781 (home-page "https://github.com/smithlabcode/piranha")
7782 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
7784 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
7785 RIP-seq experiments. It takes input in BED or BAM format and identifies
7786 regions of statistically significant read enrichment. Additional covariates
7787 may optionally be provided to further inform the peak-calling process.")
7788 (license license:gpl3+))))
7796 (uri (string-append "https://pypi.python.org/packages/source/P"
7797 "/PePr/PePr-" version ".tar.gz"))
7800 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
7801 (build-system python-build-system)
7803 `(#:python ,python-2 ; python2 only
7804 #:tests? #f)) ; no tests included
7806 `(("python2-numpy" ,python2-numpy)
7807 ("python2-scipy" ,python2-scipy)
7808 ("python2-pysam" ,python2-pysam)))
7809 (home-page "https://code.google.com/p/pepr-chip-seq/")
7810 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
7812 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
7813 that is primarily designed for data with biological replicates. It uses a
7814 negative binomial distribution to model the read counts among the samples in
7815 the same group, and look for consistent differences between ChIP and control
7816 group or two ChIP groups run under different conditions.")
7817 (license license:gpl3+)))
7819 (define-public filevercmp
7820 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
7823 (version (string-append "0-1." (string-take commit 7)))
7826 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
7828 (file-name (string-append name "-" version ".tar.gz"))
7830 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
7831 (build-system gnu-build-system)
7833 `(#:tests? #f ; There are no tests to run.
7835 (modify-phases %standard-phases
7836 (delete 'configure) ; There is no configure phase.
7838 (lambda* (#:key outputs #:allow-other-keys)
7839 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7840 (install-file "filevercmp" bin)))))))
7841 (home-page "https://github.com/ekg/filevercmp")
7842 (synopsis "This program compares version strings")
7843 (description "This program compares version strings. It intends to be a
7844 replacement for strverscmp.")
7845 (license license:gpl3+))))
7847 (define-public multiqc
7854 (uri (pypi-uri "multiqc" version))
7857 "0avw11h63ldpxy5pizc3wl1wa01ha7q10wb240nggsjz3jaqvyiy"))))
7858 (build-system python-build-system)
7860 `(("python-jinja2" ,python-jinja2)
7861 ("python-simplejson" ,python-simplejson)
7862 ("python-pyyaml" ,python-pyyaml)
7863 ("python-click" ,python-click)
7864 ("python-matplotlib" ,python-matplotlib)
7865 ("python-numpy" ,python-numpy)))
7866 (home-page "http://multiqc.info")
7867 (synopsis "Aggregate bioinformatics analysis reports")
7869 "MultiQC is a tool to aggregate bioinformatics results across many
7870 samples into a single report. It contains modules for a large number of
7871 common bioinformatics tools.")
7872 (license license:gpl3)))