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 gawk)
54 #:use-module (gnu packages gcc)
55 #:use-module (gnu packages gd)
56 #:use-module (gnu packages gtk)
57 #:use-module (gnu packages glib)
58 #:use-module (gnu packages groff)
59 #:use-module (gnu packages guile)
60 #:use-module (gnu packages haskell)
61 #:use-module (gnu packages image)
62 #:use-module (gnu packages imagemagick)
63 #:use-module (gnu packages java)
64 #:use-module (gnu packages linux)
65 #:use-module (gnu packages logging)
66 #:use-module (gnu packages machine-learning)
67 #:use-module (gnu packages man)
68 #:use-module (gnu packages maths)
69 #:use-module (gnu packages mpi)
70 #:use-module (gnu packages ncurses)
71 #:use-module (gnu packages pcre)
72 #:use-module (gnu packages parallel)
73 #:use-module (gnu packages pdf)
74 #:use-module (gnu packages perl)
75 #:use-module (gnu packages pkg-config)
76 #:use-module (gnu packages popt)
77 #:use-module (gnu packages protobuf)
78 #:use-module (gnu packages python)
79 #:use-module (gnu packages readline)
80 #:use-module (gnu packages ruby)
81 #:use-module (gnu packages serialization)
82 #:use-module (gnu packages statistics)
83 #:use-module (gnu packages tbb)
84 #:use-module (gnu packages tex)
85 #:use-module (gnu packages texinfo)
86 #:use-module (gnu packages textutils)
87 #:use-module (gnu packages time)
88 #:use-module (gnu packages tls)
89 #:use-module (gnu packages vim)
90 #:use-module (gnu packages web)
91 #:use-module (gnu packages xml)
92 #:use-module (gnu packages xorg)
93 #:use-module (gnu packages zip)
94 #:use-module (srfi srfi-1))
96 (define-public aragorn
103 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
107 "1c7zxk0h8wsjbix82fmmfyywcq6zn3q9h5y67kcl5y3qal2bv2xr"))))
108 (build-system gnu-build-system)
110 `(#:tests? #f ; there are no tests
112 (modify-phases %standard-phases
116 (zero? (system* "gcc"
122 (string-append "aragorn" ,version ".c")))))
124 (lambda* (#:key outputs #:allow-other-keys)
125 (let* ((out (assoc-ref outputs "out"))
126 (bin (string-append out "/bin"))
127 (man (string-append out "/share/man/man1")))
130 (string-append bin "/aragorn"))
132 (copy-file "aragorn.1"
133 (string-append man "/aragorn.1")))
135 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
136 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
138 "Aragorn identifies transfer RNA, mitochondrial RNA and
139 transfer-messenger RNA from nucleotide sequences, based on homology to known
140 tRNA consensus sequences and RNA structure. It also outputs the secondary
141 structure of the predicted RNA.")
142 (license license:gpl2)))
150 ;; BamM is not available on pypi.
152 "https://github.com/Ecogenomics/BamM/archive/"
154 (file-name (string-append name "-" version ".tar.gz"))
157 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
158 (modules '((guix build utils)))
161 ;; Delete bundled htslib.
162 (delete-file-recursively "c/htslib-1.3.1")
164 (build-system python-build-system)
166 `(#:python ,python-2 ; BamM is Python 2 only.
167 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
168 ;; been modified from its original form.
170 (let ((htslib (assoc-ref %build-inputs "htslib")))
171 (list "--with-libhts-lib" (string-append htslib "/lib")
172 "--with-libhts-inc" (string-append htslib "/include/htslib")))
174 (modify-phases %standard-phases
175 (add-after 'unpack 'autogen
177 (with-directory-excursion "c"
178 (let ((sh (which "sh")))
179 ;; Use autogen so that 'configure' works.
180 (substitute* "autogen.sh" (("/bin/sh") sh))
181 (setenv "CONFIG_SHELL" sh)
182 (substitute* "configure" (("/bin/sh") sh))
183 (zero? (system* "./autogen.sh"))))))
185 ;; Run tests after installation so compilation only happens once.
187 (add-after 'install 'wrap-executable
188 (lambda* (#:key outputs #:allow-other-keys)
189 (let* ((out (assoc-ref outputs "out"))
190 (path (getenv "PATH")))
191 (wrap-program (string-append out "/bin/bamm")
192 `("PATH" ":" prefix (,path))))
194 (add-after 'wrap-executable 'post-install-check
195 (lambda* (#:key inputs outputs #:allow-other-keys)
197 (string-append (assoc-ref outputs "out")
202 (assoc-ref outputs "out")
204 (string-take (string-take-right
205 (assoc-ref inputs "python") 5) 3)
207 (getenv "PYTHONPATH")))
208 ;; There are 2 errors printed, but they are safe to ignore:
209 ;; 1) [E::hts_open_format] fail to open file ...
210 ;; 2) samtools view: failed to open ...
211 (zero? (system* "nosetests")))))))
213 `(("autoconf" ,autoconf)
214 ("automake" ,automake)
217 ("python-nose" ,python2-nose)
218 ("python-pysam" ,python2-pysam)
219 ("python-setuptools" ,python2-setuptools)))
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-cython" ,python2-cython)
527 ("python-matplotlib" ,python2-matplotlib)))
529 `(("bedtools" ,bedtools)
530 ("samtools" ,samtools)))
532 `(("python-pyyaml" ,python2-pyyaml)
533 ("python-nose" ,python2-nose)
534 ("python-setuptools" ,python2-setuptools)))
535 (home-page "https://pythonhosted.org/pybedtools/")
536 (synopsis "Python wrapper for BEDtools programs")
538 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
539 which are widely used for genomic interval manipulation or \"genome algebra\".
540 pybedtools extends BEDTools by offering feature-level manipulations from with
542 (license license:gpl2+)))
544 (define-public python-biom-format
546 (name "python-biom-format")
551 ;; Use GitHub as source because PyPI distribution does not contain
552 ;; test data: https://github.com/biocore/biom-format/issues/693
553 (uri (string-append "https://github.com/biocore/biom-format/archive/"
555 (file-name (string-append name "-" version ".tar.gz"))
558 "1n25w3p1rixbpac8iysmzcja6m4ip5r6sz19l8y6wlwi49hxn278"))))
559 (build-system python-build-system)
561 `(("python-numpy" ,python-numpy)
562 ("python-scipy" ,python-scipy)
563 ("python-future" ,python-future)
564 ("python-click" ,python-click)
565 ("python-h5py" ,python-h5py)))
566 (home-page "http://www.biom-format.org")
567 (synopsis "Biological Observation Matrix (BIOM) format utilities")
569 "The BIOM file format is designed to be a general-use format for
570 representing counts of observations e.g. operational taxonomic units, KEGG
571 orthology groups or lipid types, in one or more biological samples
572 e.g. microbiome samples, genomes, metagenomes.")
573 (license license:bsd-3)
574 (properties `((python2-variant . ,(delay python2-biom-format))))))
576 (define-public python2-biom-format
577 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
582 (modify-phases %standard-phases
583 ;; Do not require the unmaintained pyqi library.
584 (add-after 'unpack 'remove-pyqi
586 (substitute* "setup.py"
587 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
589 ,@(package-arguments base)))
590 (native-inputs `(("python2-setuptools" ,python2-setuptools)
591 ,@(package-native-inputs base))))))
593 (define-public bioperl-minimal
594 (let* ((inputs `(("perl-module-build" ,perl-module-build)
595 ("perl-data-stag" ,perl-data-stag)
596 ("perl-libwww" ,perl-libwww)
597 ("perl-uri" ,perl-uri)))
599 (map (compose package-name cadr)
602 (map (compose package-transitive-target-inputs cadr) inputs))))))
604 (name "bioperl-minimal")
609 (uri (string-append "https://github.com/bioperl/bioperl-live/"
611 (string-map (lambda (c)
617 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
618 (build-system perl-build-system)
621 (modify-phases %standard-phases
623 'install 'wrap-programs
624 (lambda* (#:key outputs #:allow-other-keys)
625 ;; Make sure all executables in "bin" find the required Perl
626 ;; modules at runtime. As the PERL5LIB variable contains also
627 ;; the paths of native inputs, we pick the transitive target
628 ;; inputs from %build-inputs.
629 (let* ((out (assoc-ref outputs "out"))
630 (bin (string-append out "/bin/"))
632 (cons (string-append out "/lib/perl5/site_perl")
634 (assoc-ref %build-inputs name))
635 ',transitive-inputs))
637 (for-each (lambda (file)
639 `("PERL5LIB" ":" prefix (,path))))
640 (find-files bin "\\.pl$"))
644 `(("perl-test-most" ,perl-test-most)))
645 (home-page "http://search.cpan.org/dist/BioPerl")
646 (synopsis "Bioinformatics toolkit")
648 "BioPerl is the product of a community effort to produce Perl code which
649 is useful in biology. Examples include Sequence objects, Alignment objects
650 and database searching objects. These objects not only do what they are
651 advertised to do in the documentation, but they also interact - Alignment
652 objects are made from the Sequence objects, Sequence objects have access to
653 Annotation and SeqFeature objects and databases, Blast objects can be
654 converted to Alignment objects, and so on. This means that the objects
655 provide a coordinated and extensible framework to do computational biology.")
656 (license (package-license perl)))))
658 (define-public python-biopython
660 (name "python-biopython")
664 ;; use PyPi rather than biopython.org to ease updating
665 (uri (pypi-uri "biopython" version))
668 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
669 (build-system python-build-system)
672 (modify-phases %standard-phases
673 (add-before 'check 'set-home
674 ;; Some tests require a home directory to be set.
675 (lambda _ (setenv "HOME" "/tmp") #t)))))
677 `(("python-numpy" ,python-numpy)))
678 (home-page "http://biopython.org/")
679 (synopsis "Tools for biological computation in Python")
681 "Biopython is a set of tools for biological computation including parsers
682 for bioinformatics files into Python data structures; interfaces to common
683 bioinformatics programs; a standard sequence class and tools for performing
684 common operations on them; code to perform data classification; code for
685 dealing with alignments; code making it easy to split up parallelizable tasks
686 into separate processes; and more.")
687 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))
688 (properties `((python2-variant . ,(delay python2-biopython))))))
690 (define-public python2-biopython
691 (let ((base (package-with-python2 (strip-python2-variant python-biopython))))
694 (native-inputs `(("python2-setuptools" ,python2-setuptools)
695 ,@(package-native-inputs base))))))
697 ;; An outdated version of biopython is required for seqmagick, see
698 ;; https://github.com/fhcrc/seqmagick/issues/59
699 ;; When that issue has been resolved this package should be removed.
700 (define python2-biopython-1.66
702 (inherit python2-biopython)
706 (uri (pypi-uri "biopython" version))
709 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
711 (define-public bpp-core
712 ;; The last release was in 2014 and the recommended way to install from source
713 ;; is to clone the git repository, so we do this.
714 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
715 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
718 (version (string-append "2.2.0-1." (string-take commit 7)))
722 (url "http://biopp.univ-montp2.fr/git/bpp-core")
724 (file-name (string-append name "-" version "-checkout"))
727 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
728 (build-system cmake-build-system)
730 `(#:parallel-build? #f))
732 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
733 ; compile all of the bpp packages with GCC 5.
734 (home-page "http://biopp.univ-montp2.fr")
735 (synopsis "C++ libraries for Bioinformatics")
737 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
738 analysis, phylogenetics, molecular evolution and population genetics. It is
739 Object Oriented and is designed to be both easy to use and computer efficient.
740 Bio++ intends to help programmers to write computer expensive programs, by
741 providing them a set of re-usable tools.")
742 (license license:cecill-c))))
744 (define-public bpp-phyl
745 ;; The last release was in 2014 and the recommended way to install from source
746 ;; is to clone the git repository, so we do this.
747 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
748 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
751 (version (string-append "2.2.0-1." (string-take commit 7)))
755 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
757 (file-name (string-append name "-" version "-checkout"))
760 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
761 (build-system cmake-build-system)
763 `(#:parallel-build? #f
764 ;; If out-of-source, test data is not copied into the build directory
765 ;; so the tests fail.
766 #:out-of-source? #f))
768 `(("bpp-core" ,bpp-core)
770 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
773 (home-page "http://biopp.univ-montp2.fr")
774 (synopsis "Bio++ phylogenetic Library")
776 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
777 analysis, phylogenetics, molecular evolution and population genetics. This
778 library provides phylogenetics-related modules.")
779 (license license:cecill-c))))
781 (define-public bpp-popgen
782 ;; The last release was in 2014 and the recommended way to install from source
783 ;; is to clone the git repository, so we do this.
784 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
785 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
788 (version (string-append "2.2.0-1." (string-take commit 7)))
792 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
794 (file-name (string-append name "-" version "-checkout"))
797 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
798 (build-system cmake-build-system)
800 `(#:parallel-build? #f
801 #:tests? #f)) ; There are no tests.
803 `(("bpp-core" ,bpp-core)
806 (home-page "http://biopp.univ-montp2.fr")
807 (synopsis "Bio++ population genetics library")
809 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
810 analysis, phylogenetics, molecular evolution and population genetics. This
811 library provides population genetics-related modules.")
812 (license license:cecill-c))))
814 (define-public bpp-seq
815 ;; The last release was in 2014 and the recommended way to install from source
816 ;; is to clone the git repository, so we do this.
817 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
818 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
821 (version (string-append "2.2.0-1." (string-take commit 7)))
825 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
827 (file-name (string-append name "-" version "-checkout"))
830 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
831 (build-system cmake-build-system)
833 `(#:parallel-build? #f
834 ;; If out-of-source, test data is not copied into the build directory
835 ;; so the tests fail.
836 #:out-of-source? #f))
838 `(("bpp-core" ,bpp-core)
839 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
840 (home-page "http://biopp.univ-montp2.fr")
841 (synopsis "Bio++ sequence library")
843 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
844 analysis, phylogenetics, molecular evolution and population genetics. This
845 library provides sequence-related modules.")
846 (license license:cecill-c))))
848 (define-public bppsuite
849 ;; The last release was in 2014 and the recommended way to install from source
850 ;; is to clone the git repository, so we do this.
851 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
852 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
855 (version (string-append "2.2.0-1." (string-take commit 7)))
859 (url "http://biopp.univ-montp2.fr/git/bppsuite")
861 (file-name (string-append name "-" version "-checkout"))
864 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
865 (build-system cmake-build-system)
867 `(#:parallel-build? #f
868 #:tests? #f)) ; There are no tests.
872 ("texinfo" ,texinfo)))
874 `(("bpp-core" ,bpp-core)
876 ("bpp-phyl" ,bpp-phyl)
877 ("bpp-phyl" ,bpp-popgen)
879 (home-page "http://biopp.univ-montp2.fr")
880 (synopsis "Bioinformatics tools written with the Bio++ libraries")
882 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
883 analysis, phylogenetics, molecular evolution and population genetics. This
884 package provides command line tools using the Bio++ library.")
885 (license license:cecill-c))))
887 (define-public blast+
894 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
895 version "/ncbi-blast-" version "+-src.tar.gz"))
898 "14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
899 (modules '((guix build utils)))
902 ;; Remove bundled bzip2 and zlib
903 (delete-file-recursively "c++/src/util/compress/bzip2")
904 (delete-file-recursively "c++/src/util/compress/zlib")
905 (substitute* "c++/src/util/compress/Makefile.in"
906 (("bzip2 zlib api") "api"))
907 ;; Remove useless msbuild directory
908 (delete-file-recursively
909 "c++/src/build-system/project_tree_builder/msbuild")
911 (build-system gnu-build-system)
913 `(;; There are three(!) tests for this massive library, and all fail with
914 ;; "unparsable timing stats".
915 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
916 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
917 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
920 #:parallel-build? #f ; not supported
922 (modify-phases %standard-phases
925 ;; $HOME needs to be set at some point during the configure phase
926 (lambda _ (setenv "HOME" "/tmp") #t))
929 (lambda _ (chdir "c++") #t))
931 'enter-dir 'fix-build-system
934 (cond ((string=? cmd "date")
935 ;; make call to "date" deterministic
940 (format (current-error-port)
941 "WARNING: Unable to find absolute path for ~s~%"
945 ;; Rewrite hardcoded paths to various tools
946 (substitute* (append '("src/build-system/configure.ac"
947 "src/build-system/configure"
948 "scripts/common/impl/if_diff.sh"
949 "scripts/common/impl/run_with_lock.sh"
950 "src/build-system/Makefile.configurables.real"
951 "src/build-system/Makefile.in.top"
952 "src/build-system/Makefile.meta.gmake=no"
953 "src/build-system/Makefile.meta.in"
954 "src/build-system/Makefile.meta_l"
955 "src/build-system/Makefile.meta_p"
956 "src/build-system/Makefile.meta_r"
957 "src/build-system/Makefile.mk.in"
958 "src/build-system/Makefile.requirements"
959 "src/build-system/Makefile.rules_with_autodep.in")
960 (find-files "scripts/common/check" "\\.sh$"))
961 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
962 (or (which* cmd) all)))
964 (substitute* (find-files "src/build-system" "^config.*")
965 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
968 ;; rewrite "/var/tmp" in check script
969 (substitute* "scripts/common/check/check_make_unix.sh"
970 (("/var/tmp") "/tmp"))
973 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
975 (("action=/bin/") "action=")
976 (("export PATH") ":"))
980 (lambda* (#:key inputs outputs #:allow-other-keys)
981 (let ((out (assoc-ref outputs "out"))
982 (lib (string-append (assoc-ref outputs "lib") "/lib"))
983 (include (string-append (assoc-ref outputs "include")
984 "/include/ncbi-tools++")))
985 ;; The 'configure' script doesn't recognize things like
986 ;; '--enable-fast-install'.
987 (zero? (system* "./configure.orig"
988 (string-append "--with-build-root=" (getcwd) "/build")
989 (string-append "--prefix=" out)
990 (string-append "--libdir=" lib)
991 (string-append "--includedir=" include)
992 (string-append "--with-bz2="
993 (assoc-ref inputs "bzip2"))
994 (string-append "--with-z="
995 (assoc-ref inputs "zlib"))
996 ;; Each library is built twice by default, once
997 ;; with "-static" in its name, and again
1000 "--with-dll"))))))))
1001 (outputs '("out" ; 19 MB
1009 (home-page "http://blast.ncbi.nlm.nih.gov")
1010 (synopsis "Basic local alignment search tool")
1012 "BLAST is a popular method of performing a DNA or protein sequence
1013 similarity search, using heuristics to produce results quickly. It also
1014 calculates an “expect value” that estimates how many matches would have
1015 occurred at a given score by chance, which can aid a user in judging how much
1016 confidence to have in an alignment.")
1017 ;; Most of the sources are in the public domain, with the following
1020 ;; * ./c++/include/util/bitset/
1021 ;; * ./c++/src/html/ncbi_menu*.js
1023 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1025 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1027 ;; * ./c++/src/corelib/teamcity_*
1028 (license (list license:public-domain
1034 (define-public bless
1040 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1044 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1045 (modules '((guix build utils)))
1048 ;; Remove bundled boost, pigz, zlib, and .git directory
1049 ;; FIXME: also remove bundled sources for murmurhash3 and
1050 ;; kmc once packaged.
1051 (delete-file-recursively "boost")
1052 (delete-file-recursively "pigz")
1053 (delete-file-recursively "google-sparsehash")
1054 (delete-file-recursively "zlib")
1055 (delete-file-recursively ".git")
1057 (build-system gnu-build-system)
1059 '(#:tests? #f ;no "check" target
1061 (list (string-append "ZLIB="
1062 (assoc-ref %build-inputs "zlib")
1064 (string-append "LDFLAGS="
1065 (string-join '("-lboost_filesystem"
1072 (modify-phases %standard-phases
1073 (add-after 'unpack 'do-not-build-bundled-pigz
1074 (lambda* (#:key inputs outputs #:allow-other-keys)
1075 (substitute* "Makefile"
1076 (("cd pigz/pigz-2.3.3; make") ""))
1078 (add-after 'unpack 'patch-paths-to-executables
1079 (lambda* (#:key inputs outputs #:allow-other-keys)
1080 (substitute* "parse_args.cpp"
1081 (("kmc_binary = .*")
1082 (string-append "kmc_binary = \""
1083 (assoc-ref outputs "out")
1085 (("pigz_binary = .*")
1086 (string-append "pigz_binary = \""
1087 (assoc-ref inputs "pigz")
1091 (lambda* (#:key outputs #:allow-other-keys)
1092 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1093 (for-each (lambda (file)
1094 (install-file file bin))
1095 '("bless" "kmc/bin/kmc"))
1097 (delete 'configure))))
1101 `(("openmpi" ,openmpi)
1103 ("sparsehash" ,sparsehash)
1106 (supported-systems '("x86_64-linux"))
1107 (home-page "http://sourceforge.net/p/bless-ec/wiki/Home/")
1108 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1110 "@dfn{Bloom-filter-based error correction solution for high-throughput
1111 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1112 correction tool for genomic reads produced by @dfn{Next-generation
1113 sequencing} (NGS). BLESS produces accurate correction results with much less
1114 memory compared with previous solutions and is also able to tolerate a higher
1115 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1116 errors at the end of reads.")
1117 (license license:gpl3+)))
1119 (define-public bowtie
1125 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1127 (file-name (string-append name "-" version ".tar.gz"))
1130 "1vp5db8i7is57iwjybcdg18f5ivyzlj5g1ix1nlvxainzivhz55g"))
1131 (modules '((guix build utils)))
1133 '(substitute* "Makefile"
1134 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1135 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1136 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1137 (build-system gnu-build-system)
1138 (inputs `(("perl" ,perl)
1139 ("perl-clone" ,perl-clone)
1140 ("perl-test-deep" ,perl-test-deep)
1141 ("perl-test-simple" ,perl-test-simple)
1142 ("python" ,python-2)
1148 (string-append "prefix=" (assoc-ref %outputs "out")))
1154 (lambda* (#:key outputs #:allow-other-keys)
1156 "scripts/test/simple_tests.pl"
1157 "--bowtie2=./bowtie2"
1158 "--bowtie2-build=./bowtie2-build"))
1159 %standard-phases))))
1160 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1161 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1163 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1164 reads to long reference sequences. It is particularly good at aligning reads
1165 of about 50 up to 100s or 1,000s of characters, and particularly good at
1166 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1167 genome with an FM Index to keep its memory footprint small: for the human
1168 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1169 gapped, local, and paired-end alignment modes.")
1170 (supported-systems '("x86_64-linux"))
1171 (license license:gpl3+)))
1173 (define-public tophat
1180 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1184 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1185 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1186 (modules '((guix build utils)))
1189 ;; Remove bundled SeqAn and samtools
1190 (delete-file-recursively "src/SeqAn-1.3")
1191 (delete-file-recursively "src/samtools-0.1.18")
1193 (build-system gnu-build-system)
1195 '(#:parallel-build? #f ; not supported
1197 (modify-phases %standard-phases
1198 (add-after 'unpack 'use-system-samtools
1199 (lambda* (#:key inputs #:allow-other-keys)
1200 (substitute* "src/Makefile.in"
1201 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1202 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1203 (("SAMPROG = samtools_0\\.1\\.18") "")
1204 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1205 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1206 (substitute* '("src/common.cpp"
1208 (("samtools_0.1.18") (which "samtools")))
1209 (substitute* '("src/common.h"
1210 "src/bam2fastx.cpp")
1211 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1212 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1213 (substitute* '("src/bwt_map.h"
1215 "src/align_status.h")
1216 (("#include <bam.h>") "#include <samtools/bam.h>")
1217 (("#include <sam.h>") "#include <samtools/sam.h>"))
1222 ("samtools" ,samtools-0.1)
1223 ("ncurses" ,ncurses)
1224 ("python" ,python-2)
1228 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1229 (synopsis "Spliced read mapper for RNA-Seq data")
1231 "TopHat is a fast splice junction mapper for nucleotide sequence
1232 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1233 mammalian-sized genomes using the ultra high-throughput short read
1234 aligner Bowtie, and then analyzes the mapping results to identify
1235 splice junctions between exons.")
1236 ;; TopHat is released under the Boost Software License, Version 1.0
1237 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1238 (license license:boost1.0)))
1246 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1247 version ".tar.bz2"))
1250 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
1251 (build-system gnu-build-system)
1253 '(#:tests? #f ;no "check" target
1257 (lambda* (#:key outputs #:allow-other-keys)
1258 (let ((bin (string-append
1259 (assoc-ref outputs "out") "/bin"))
1261 (assoc-ref outputs "out") "/share/doc/bwa"))
1263 (assoc-ref outputs "out") "/share/man/man1")))
1267 (install-file "bwa" bin)
1268 (install-file "README.md" doc)
1269 (install-file "bwa.1" man)))
1270 ;; no "configure" script
1271 (alist-delete 'configure %standard-phases))))
1272 (inputs `(("zlib" ,zlib)))
1273 ;; Non-portable SSE instructions are used so building fails on platforms
1274 ;; other than x86_64.
1275 (supported-systems '("x86_64-linux"))
1276 (home-page "http://bio-bwa.sourceforge.net/")
1277 (synopsis "Burrows-Wheeler sequence aligner")
1279 "BWA is a software package for mapping low-divergent sequences against a
1280 large reference genome, such as the human genome. It consists of three
1281 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1282 designed for Illumina sequence reads up to 100bp, while the rest two for
1283 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1284 features such as long-read support and split alignment, but BWA-MEM, which is
1285 the latest, is generally recommended for high-quality queries as it is faster
1286 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1287 70-100bp Illumina reads.")
1288 (license license:gpl3+)))
1290 (define-public bwa-pssm
1291 (package (inherit bwa)
1296 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1297 "archive/" version ".tar.gz"))
1298 (file-name (string-append name "-" version ".tar.gz"))
1301 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1302 (build-system gnu-build-system)
1307 (home-page "http://bwa-pssm.binf.ku.dk/")
1308 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1310 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1311 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1312 existing aligners it is fast and sensitive. Unlike most other aligners,
1313 however, it is also adaptible in the sense that one can direct the alignment
1314 based on known biases within the data set. It is coded as a modification of
1315 the original BWA alignment program and shares the genome index structure as
1316 well as many of the command line options.")
1317 (license license:gpl3+)))
1319 (define-public python2-bx-python
1321 (name "python2-bx-python")
1326 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
1330 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
1331 (modules '((guix build utils)))
1333 '(substitute* "setup.py"
1334 ;; remove dependency on outdated "distribute" module
1335 (("^from distribute_setup import use_setuptools") "")
1336 (("^use_setuptools\\(\\)") "")))))
1337 (build-system python-build-system)
1339 `(#:tests? #f ;tests fail because test data are not included
1340 #:python ,python-2))
1342 `(("python-numpy" ,python2-numpy)
1345 `(("python-nose" ,python2-nose)
1346 ("python-setuptools" ,python2-setuptools)))
1347 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1348 (synopsis "Tools for manipulating biological data")
1350 "bx-python provides tools for manipulating biological data, particularly
1351 multiple sequence alignments.")
1352 (license license:expat)))
1354 (define-public python-pysam
1356 (name "python-pysam")
1360 ;; Test data is missing on PyPi.
1362 "https://github.com/pysam-developers/pysam/archive/v"
1364 (file-name (string-append name "-" version ".tar.gz"))
1367 "0y41ssbg6nvn2jgcbnrvkzblpjcwszaiv1rgyd8dwzjkrbfsgsmc"))
1368 (modules '((guix build utils)))
1370 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1371 '(delete-file-recursively "htslib"))))
1372 (build-system python-build-system)
1375 (modify-phases %standard-phases
1376 (add-before 'build 'set-flags
1377 (lambda* (#:key inputs #:allow-other-keys)
1378 (setenv "HTSLIB_MODE" "external")
1379 (setenv "HTSLIB_LIBRARY_DIR"
1380 (string-append (assoc-ref inputs "htslib") "/lib"))
1381 (setenv "HTSLIB_INCLUDE_DIR"
1382 (string-append (assoc-ref inputs "htslib") "/include"))
1383 (setenv "LDFLAGS" "-lncurses")
1384 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1387 (add-after 'install 'check
1388 (lambda* (#:key inputs outputs #:allow-other-keys)
1389 (setenv "PYTHONPATH"
1391 (getenv "PYTHONPATH")
1392 ":" (assoc-ref outputs "out")
1394 (string-take (string-take-right
1395 (assoc-ref inputs "python") 5) 3)
1397 ;; Step out of source dir so python does not import from CWD.
1399 (setenv "HOME" "/tmp")
1400 (and (zero? (system* "make" "-C" "pysam_data"))
1401 (zero? (system* "make" "-C" "cbcf_data"))
1402 (zero? (system* "nosetests" "-v"))))))))
1404 `(("htslib" ,htslib))) ; Included from installed header files.
1406 `(("ncurses" ,ncurses)
1409 `(("python-cython" ,python-cython)
1410 ("python-setuptools" ,python-setuptools)
1411 ;; Dependencies below are are for tests only.
1412 ("samtools" ,samtools)
1413 ("bcftools" ,bcftools)
1414 ("python-nose" ,python-nose)))
1415 (home-page "https://github.com/pysam-developers/pysam")
1416 (synopsis "Python bindings to the SAMtools C API")
1418 "Pysam is a Python module for reading and manipulating files in the
1419 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1420 also includes an interface for tabix.")
1421 (license license:expat)))
1423 (define-public python2-pysam
1424 (package-with-python2 python-pysam))
1426 (define-public python-twobitreader
1428 (name "python-twobitreader")
1432 (uri (pypi-uri "twobitreader" version))
1435 "0y408fp6psqzwxpcpqn0wp7fr41dwz8d54wpj6j261fj5q8vs169"))))
1436 (properties `((python2-variant . ,(delay python2-twobitreader))))
1437 (build-system python-build-system)
1439 `(("python-sphinx" ,python-sphinx)))
1440 (home-page "https://github.com/benjschiller/twobitreader")
1441 (synopsis "Python library for reading .2bit files")
1443 "twobitreader is a Python library for reading .2bit files as used by the
1444 UCSC genome browser.")
1445 (license license:artistic2.0)))
1447 (define-public python2-twobitreader
1448 (let ((base (package-with-python2 (strip-python2-variant python-twobitreader))))
1451 (native-inputs `(("python2-setuptools" ,python2-setuptools)
1452 ,@(package-native-inputs base))))))
1454 (define-public python-plastid
1456 (name "python-plastid")
1460 (uri (pypi-uri "plastid" version))
1463 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
1464 (properties `((python2-variant . ,(delay python2-plastid))))
1465 (build-system python-build-system)
1467 ;; Some test files are not included.
1470 `(("python-numpy" ,python-numpy)
1471 ("python-scipy" ,python-scipy)
1472 ("python-pandas" ,python-pandas)
1473 ("python-pysam" ,python-pysam)
1474 ("python-matplotlib" ,python-matplotlib)
1475 ("python-biopython" ,python-biopython)
1476 ("python-twobitreader" ,python-twobitreader)
1477 ("python-termcolor" ,python-termcolor)))
1479 `(("python-cython" ,python-cython)
1480 ("python-nose" ,python-nose)))
1481 (home-page "https://github.com/joshuagryphon/plastid")
1482 (synopsis "Python library for genomic analysis")
1484 "plastid is a Python library for genomic analysis – in particular,
1485 high-throughput sequencing data – with an emphasis on simplicity.")
1486 (license license:bsd-3)))
1488 (define-public python2-plastid
1489 (let ((base (package-with-python2 (strip-python2-variant python-plastid))))
1492 ;; setuptools is required at runtime
1493 (propagated-inputs `(("python2-setuptools" ,python2-setuptools)
1494 ,@(package-propagated-inputs base))))))
1496 (define-public cd-hit
1502 (uri (string-append "https://github.com/weizhongli/cdhit"
1503 "/releases/download/V" version
1504 "/cd-hit-v" version "-2016-0304.tar.gz"))
1507 "15db0hq38yyifwqx9b6l34z14jcq576dmjavhj8a426c18lvnhp3"))))
1508 (build-system gnu-build-system)
1510 `(#:tests? #f ; there are no tests
1512 ;; Executables are copied directly to the PREFIX.
1513 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1515 (modify-phases %standard-phases
1516 ;; No "configure" script
1518 ;; Remove sources of non-determinism
1519 (add-after 'unpack 'be-timeless
1521 (substitute* "cdhit-utility.c++"
1522 ((" \\(built on \" __DATE__ \"\\)") ""))
1523 (substitute* "cdhit-common.c++"
1524 (("__DATE__") "\"0\"")
1525 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1527 ;; The "install" target does not create the target directory
1528 (add-before 'install 'create-target-dir
1529 (lambda* (#:key outputs #:allow-other-keys)
1530 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1534 (home-page "http://weizhongli-lab.org/cd-hit/")
1535 (synopsis "Cluster and compare protein or nucleotide sequences")
1537 "CD-HIT is a program for clustering and comparing protein or nucleotide
1538 sequences. CD-HIT is designed to be fast and handle extremely large
1540 ;; The manual says: "It can be copied under the GNU General Public License
1541 ;; version 2 (GPLv2)."
1542 (license license:gpl2)))
1544 (define-public clipper
1551 "https://github.com/YeoLab/clipper/archive/"
1553 (file-name (string-append name "-" version ".tar.gz"))
1556 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1557 (modules '((guix build utils)))
1560 ;; remove unnecessary setup dependency
1561 (substitute* "setup.py"
1562 (("setup_requires = .*") ""))
1563 (for-each delete-file
1564 '("clipper/src/peaks.so"
1565 "clipper/src/readsToWiggle.so"))
1566 (delete-file-recursively "dist/")
1568 (build-system python-build-system)
1569 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1572 ("python-pybedtools" ,python2-pybedtools)
1573 ("python-cython" ,python2-cython)
1574 ("python-scikit-learn" ,python2-scikit-learn)
1575 ("python-matplotlib" ,python2-matplotlib)
1576 ("python-pandas" ,python2-pandas)
1577 ("python-pysam" ,python2-pysam)
1578 ("python-numpy" ,python2-numpy)
1579 ("python-scipy" ,python2-scipy)))
1581 `(("python-mock" ,python2-mock) ; for tests
1582 ("python-pytz" ,python2-pytz) ; for tests
1583 ("python-setuptools" ,python2-setuptools)))
1584 (home-page "https://github.com/YeoLab/clipper")
1585 (synopsis "CLIP peak enrichment recognition")
1587 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1588 (license license:gpl2)))
1590 (define-public codingquarry
1592 (name "codingquarry")
1597 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1601 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1602 (build-system gnu-build-system)
1604 '(#:tests? #f ; no "check" target
1606 (modify-phases %standard-phases
1609 (lambda* (#:key outputs #:allow-other-keys)
1610 (let* ((out (assoc-ref outputs "out"))
1611 (bin (string-append out "/bin"))
1612 (doc (string-append out "/share/doc/codingquarry")))
1613 (install-file "INSTRUCTIONS.pdf" doc)
1614 (copy-recursively "QuarryFiles"
1615 (string-append out "/QuarryFiles"))
1616 (install-file "CodingQuarry" bin)
1617 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1618 (inputs `(("openmpi" ,openmpi)))
1619 (native-search-paths
1620 (list (search-path-specification
1621 (variable "QUARRY_PATH")
1622 (files '("QuarryFiles")))))
1623 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1624 (synopsis "Fungal gene predictor")
1625 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1626 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1627 (home-page "https://sourceforge.net/projects/codingquarry/")
1628 (license license:gpl3+)))
1630 (define-public couger
1637 "http://couger.oit.duke.edu/static/assets/COUGER"
1641 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1642 (build-system gnu-build-system)
1646 (modify-phases %standard-phases
1651 (lambda* (#:key outputs #:allow-other-keys)
1652 (let ((out (assoc-ref outputs "out")))
1653 (copy-recursively "src" (string-append out "/src"))
1654 (mkdir (string-append out "/bin"))
1655 ;; Add "src" directory to module lookup path.
1656 (substitute* "couger"
1658 (string-append "import sys\nsys.path.append(\""
1659 out "\")\nfrom argparse")))
1660 (copy-file "couger" (string-append out "/bin/couger")))
1663 'install 'wrap-program
1664 (lambda* (#:key inputs outputs #:allow-other-keys)
1665 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1666 (let* ((out (assoc-ref outputs "out"))
1667 (path (getenv "PYTHONPATH")))
1668 (wrap-program (string-append out "/bin/couger")
1669 `("PYTHONPATH" ":" prefix (,path))))
1672 `(("python" ,python-2)
1673 ("python2-pillow" ,python2-pillow)
1674 ("python2-numpy" ,python2-numpy)
1675 ("python2-scipy" ,python2-scipy)
1676 ("python2-matplotlib" ,python2-matplotlib)))
1680 ("randomjungle" ,randomjungle)))
1682 `(("unzip" ,unzip)))
1683 (home-page "http://couger.oit.duke.edu")
1684 (synopsis "Identify co-factors in sets of genomic regions")
1686 "COUGER can be applied to any two sets of genomic regions bound by
1687 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1688 putative co-factors that provide specificity to each TF. The framework
1689 determines the genomic targets uniquely-bound by each TF, and identifies a
1690 small set of co-factors that best explain the in vivo binding differences
1691 between the two TFs.
1693 COUGER uses classification algorithms (support vector machines and random
1694 forests) with features that reflect the DNA binding specificities of putative
1695 co-factors. The features are generated either from high-throughput TF-DNA
1696 binding data (from protein binding microarray experiments), or from large
1697 collections of DNA motifs.")
1698 (license license:gpl3+)))
1700 (define-public clustal-omega
1702 (name "clustal-omega")
1707 "http://www.clustal.org/omega/clustal-omega-"
1711 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1712 (build-system gnu-build-system)
1714 `(("argtable" ,argtable)))
1715 (home-page "http://www.clustal.org/omega/")
1716 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1718 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1719 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1720 of handling data-sets of hundreds of thousands of sequences in reasonable
1722 (license license:gpl2+)))
1724 (define-public crossmap
1730 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1734 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1735 ;; This patch has been sent upstream already and is available
1736 ;; for download from Sourceforge, but it has not been merged.
1737 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1738 (modules '((guix build utils)))
1739 ;; remove bundled copy of pysam
1741 '(delete-file-recursively "lib/pysam"))))
1742 (build-system python-build-system)
1744 `(#:python ,python-2
1748 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1751 `(("python-numpy" ,python2-numpy)
1752 ("python-pysam" ,python2-pysam)
1755 `(("python-cython" ,python2-cython)
1756 ("python-nose" ,python2-nose)
1757 ("python-setuptools" ,python2-setuptools)))
1758 (home-page "http://crossmap.sourceforge.net/")
1759 (synopsis "Convert genome coordinates between assemblies")
1761 "CrossMap is a program for conversion of genome coordinates or annotation
1762 files between different genome assemblies. It supports most commonly used
1763 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1764 (license license:gpl2+)))
1766 (define-public cufflinks
1772 (uri (string-append "http://cole-trapnell-lab.github.io/"
1773 "cufflinks/assets/downloads/cufflinks-"
1777 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1778 (build-system gnu-build-system)
1782 ;; The includes for "eigen" are located in a subdirectory.
1783 (string-append "EIGEN_CPPFLAGS="
1784 "-I" (assoc-ref %build-inputs "eigen")
1786 ;; Cufflinks must be linked with various boost libraries.
1787 (string-append "LDFLAGS="
1788 (string-join '("-lboost_system"
1789 "-lboost_serialization"
1790 "-lboost_thread"))))
1792 (modify-phases %standard-phases
1793 (add-after 'unpack 'fix-search-for-bam
1795 (substitute* '("ax_bam.m4"
1798 (("<bam/sam\\.h>") "<samtools/sam.h>")
1799 (("<bam/bam\\.h>") "<samtools/bam.h>")
1800 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1803 (list (string-append "--with-bam="
1804 (assoc-ref %build-inputs "samtools")))))
1807 ("samtools" ,samtools-0.1)
1810 ("python" ,python-2)
1812 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1813 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1815 "Cufflinks assembles RNA transcripts, estimates their abundances,
1816 and tests for differential expression and regulation in RNA-Seq
1817 samples. It accepts aligned RNA-Seq reads and assembles the
1818 alignments into a parsimonious set of transcripts. Cufflinks then
1819 estimates the relative abundances of these transcripts based on how
1820 many reads support each one, taking into account biases in library
1821 preparation protocols.")
1822 (license license:boost1.0)))
1824 (define-public cutadapt
1831 "https://github.com/marcelm/cutadapt/archive/v"
1833 (file-name (string-append name "-" version ".tar.gz"))
1836 "161bp87y6gd6r5bmvjpn2b1k942i3fizfpa139f0jn6jv1wcp5h5"))))
1837 (build-system python-build-system)
1839 ;; tests must be run after install
1840 `(#:phases (alist-cons-after
1842 (lambda* (#:key inputs outputs #:allow-other-keys)
1843 (setenv "PYTHONPATH"
1845 (getenv "PYTHONPATH")
1846 ":" (assoc-ref outputs "out")
1848 (string-take (string-take-right
1849 (assoc-ref inputs "python") 5) 3)
1851 (zero? (system* "nosetests" "-P" "tests")))
1852 (alist-delete 'check %standard-phases))))
1854 `(("python-cython" ,python-cython)
1855 ("python-nose" ,python-nose)
1856 ("python-setuptools" ,python-setuptools)))
1857 (home-page "https://code.google.com/p/cutadapt/")
1858 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1860 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1861 other types of unwanted sequence from high-throughput sequencing reads.")
1862 (license license:expat)))
1864 (define-public libbigwig
1870 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1871 "archive/" version ".tar.gz"))
1872 (file-name (string-append name "-" version ".tar.gz"))
1875 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1876 (build-system gnu-build-system)
1878 `(#:test-target "test"
1881 (string-append "prefix=" (assoc-ref %outputs "out")))
1883 (modify-phases %standard-phases
1885 (add-before 'check 'disable-curl-test
1887 (substitute* "Makefile"
1888 (("./test/testRemote.*") ""))
1890 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1891 ;; there has not yet been a release containing this change.
1892 (add-before 'install 'create-target-dirs
1893 (lambda* (#:key outputs #:allow-other-keys)
1894 (let ((out (assoc-ref outputs "out")))
1895 (mkdir-p (string-append out "/lib"))
1896 (mkdir-p (string-append out "/include"))
1902 `(("doxygen" ,doxygen)))
1903 (home-page "https://github.com/dpryan79/libBigWig")
1904 (synopsis "C library for handling bigWig files")
1906 "This package provides a C library for parsing local and remote BigWig
1908 (license license:expat)))
1910 (define-public python-pybigwig
1912 (name "python-pybigwig")
1916 (uri (pypi-uri "pyBigWig" version))
1919 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1920 (modules '((guix build utils)))
1923 ;; Delete bundled libBigWig sources
1924 (delete-file-recursively "libBigWig")))))
1925 (build-system python-build-system)
1928 (modify-phases %standard-phases
1929 (add-after 'unpack 'link-with-libBigWig
1930 (lambda* (#:key inputs #:allow-other-keys)
1931 (substitute* "setup.py"
1932 (("libs=\\[") "libs=[\"BigWig\", "))
1935 `(("libbigwig" ,libbigwig)
1938 (home-page "https://github.com/dpryan79/pyBigWig")
1939 (synopsis "Access bigWig files in Python using libBigWig")
1941 "This package provides Python bindings to the libBigWig library for
1942 accessing bigWig files.")
1943 (license license:expat)))
1945 (define-public python2-pybigwig
1946 (let ((pybigwig (package-with-python2 python-pybigwig)))
1947 (package (inherit pybigwig)
1949 `(("python-setuptools" ,python2-setuptools))))))
1951 (define-public python-dendropy
1953 (name "python-dendropy")
1958 (uri (pypi-uri "DendroPy" version))
1961 "1jfz7gp18wph311w1yygbvjanb3n5mdqal439bb6myw41dwb5m63"))
1962 ;; There are two known test failures that will be fixed in the next
1963 ;; release after 4.1.0.
1964 ;; https://github.com/jeetsukumaran/DendroPy/issues/48
1965 (patches (search-patches
1966 "python-dendropy-exclude-failing-tests.patch"))))
1967 (build-system python-build-system)
1968 (home-page "http://packages.python.org/DendroPy/")
1969 (synopsis "Library for phylogenetics and phylogenetic computing")
1971 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1972 writing, simulation, processing and manipulation of phylogenetic
1973 trees (phylogenies) and characters.")
1974 (license license:bsd-3)
1975 (properties `((python2-variant . ,(delay python2-dendropy))))))
1977 (define-public python2-dendropy
1978 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1981 ;; Do not use same source as 'python-dendropy' because the patched
1982 ;; failing tests do not occur on Python 2.
1986 (uri (pypi-uri "DendroPy" (package-version base)))
1989 "1jfz7gp18wph311w1yygbvjanb3n5mdqal439bb6myw41dwb5m63"))))
1991 `(#:python ,python-2
1993 (modify-phases %standard-phases
1995 ;; There is currently a test failure that only happens on some
1996 ;; systems, and only using "setup.py test"
1997 (lambda _ (zero? (system* "nosetests")))))))
1998 (native-inputs `(("python2-setuptools" ,python2-setuptools)
1999 ("python2-nose" ,python2-nose)
2000 ,@(package-native-inputs base))))))
2003 (define-public deeptools
2009 (uri (string-append "https://github.com/fidelram/deepTools/"
2010 "archive/" version ".tar.gz"))
2011 (file-name (string-append name "-" version ".tar.gz"))
2014 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
2015 (build-system python-build-system)
2017 `(#:python ,python-2))
2019 `(("python-scipy" ,python2-scipy)
2020 ("python-numpy" ,python2-numpy)
2021 ("python-numpydoc" ,python2-numpydoc)
2022 ("python-matplotlib" ,python2-matplotlib)
2023 ("python-bx-python" ,python2-bx-python)
2024 ("python-pysam" ,python2-pysam)
2025 ("python-pybigwig" ,python2-pybigwig)))
2027 `(("python-mock" ,python2-mock) ;for tests
2028 ("python-pytz" ,python2-pytz) ;for tests
2029 ("python-setuptools" ,python2-setuptools)))
2030 (home-page "https://github.com/fidelram/deepTools")
2031 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2033 "DeepTools addresses the challenge of handling the large amounts of data
2034 that are now routinely generated from DNA sequencing centers. To do so,
2035 deepTools contains useful modules to process the mapped reads data to create
2036 coverage files in standard bedGraph and bigWig file formats. By doing so,
2037 deepTools allows the creation of normalized coverage files or the comparison
2038 between two files (for example, treatment and control). Finally, using such
2039 normalized and standardized files, multiple visualizations can be created to
2040 identify enrichments with functional annotations of the genome.")
2041 (license license:gpl3+)))
2043 (define-public diamond
2050 "https://github.com/bbuchfink/diamond/archive/v"
2052 (file-name (string-append name "-" version ".tar.gz"))
2055 "0xpcq3fbk4c52xbpgyk5brl58rljvl83bg8nkxy8vs00pxanm7i2"))))
2056 (build-system cmake-build-system)
2058 '(#:tests? #f ; no "check" target
2060 (modify-phases %standard-phases
2061 (add-after 'unpack 'remove-native-compilation
2063 (substitute* "CMakeLists.txt" (("-march=native") ""))
2067 (home-page "https://github.com/bbuchfink/diamond")
2068 (synopsis "Accelerated BLAST compatible local sequence aligner")
2070 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2071 translated DNA query sequences against a protein reference database (BLASTP
2072 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2073 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2074 data and settings.")
2075 ;; diamond fails to build on other platforms
2076 ;; https://github.com/bbuchfink/diamond/issues/18
2077 (supported-systems '("x86_64-linux"))
2078 (license (license:non-copyleft "file://src/COPYING"
2079 "See src/COPYING in the distribution."))))
2081 (define-public discrover
2088 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2090 (file-name (string-append name "-" version ".tar.gz"))
2093 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2094 (build-system cmake-build-system)
2095 (arguments `(#:tests? #f)) ; there are no tests
2100 `(("texlive" ,texlive)
2101 ("imagemagick" ,imagemagick)))
2102 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2103 (synopsis "Discover discriminative nucleotide sequence motifs")
2104 (description "Discrover is a motif discovery method to find binding sites
2105 of nucleic acid binding proteins.")
2106 (license license:gpl3+)))
2108 (define-public eigensoft
2109 (let ((revision "1")
2110 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2113 (version (string-append "6.1.2-"
2115 (string-take commit 9)))
2120 (url "https://github.com/DReichLab/EIG.git")
2122 (file-name (string-append "eigensoft-" commit "-checkout"))
2125 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2126 (modules '((guix build utils)))
2127 ;; Remove pre-built binaries.
2129 (delete-file-recursively "bin")
2132 (build-system gnu-build-system)
2134 `(#:tests? #f ; There are no tests.
2135 #:make-flags '("CC=gcc")
2137 (modify-phases %standard-phases
2138 ;; There is no configure phase, but the Makefile is in a
2143 ;; The link flags are incomplete.
2144 (substitute* "Makefile"
2145 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2147 ;; The provided install target only copies executables to
2148 ;; the "bin" directory in the build root.
2149 (add-after 'install 'actually-install
2150 (lambda* (#:key outputs #:allow-other-keys)
2151 (let* ((out (assoc-ref outputs "out"))
2152 (bin (string-append out "/bin")))
2154 (for-each (lambda (file)
2155 (install-file file bin))
2156 (find-files "../bin" ".*"))
2161 ("openblas" ,openblas)
2163 ("gfortran" ,gfortran "lib")))
2164 (home-page "https://github.com/DReichLab/EIG")
2165 (synopsis "Tools for population genetics")
2166 (description "The EIGENSOFT package provides tools for population
2167 genetics and stratification correction. EIGENSOFT implements methods commonly
2168 used in population genetics analyses such as PCA, computation of Tracy-Widom
2169 statistics, and finding related individuals in structured populations. It
2170 comes with a built-in plotting script and supports multiple file formats and
2171 quantitative phenotypes.")
2172 ;; The license of the eigensoft tools is Expat, but since it's
2173 ;; linking with the GNU Scientific Library (GSL) the effective
2174 ;; license is the GPL.
2175 (license license:gpl3+))))
2177 (define-public edirect
2183 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2184 "versions/2016-05-03/edirect.tar.gz"))
2187 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2188 (build-system perl-build-system)
2190 `(#:tests? #f ;no "check" target
2192 (modify-phases %standard-phases
2196 (lambda* (#:key outputs #:allow-other-keys)
2197 (let ((target (string-append (assoc-ref outputs "out")
2200 (copy-file "edirect.pl"
2201 (string-append target "/edirect.pl"))
2204 'install 'wrap-program
2205 (lambda* (#:key inputs outputs #:allow-other-keys)
2206 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2207 (let* ((out (assoc-ref outputs "out"))
2208 (path (getenv "PERL5LIB")))
2209 (wrap-program (string-append out "/bin/edirect.pl")
2210 `("PERL5LIB" ":" prefix (,path)))))))))
2212 `(("perl-html-parser" ,perl-html-parser)
2213 ("perl-encode-locale" ,perl-encode-locale)
2214 ("perl-file-listing" ,perl-file-listing)
2215 ("perl-html-tagset" ,perl-html-tagset)
2216 ("perl-html-tree" ,perl-html-tree)
2217 ("perl-http-cookies" ,perl-http-cookies)
2218 ("perl-http-date" ,perl-http-date)
2219 ("perl-http-message" ,perl-http-message)
2220 ("perl-http-negotiate" ,perl-http-negotiate)
2221 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2222 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2223 ("perl-net-http" ,perl-net-http)
2224 ("perl-uri" ,perl-uri)
2225 ("perl-www-robotrules" ,perl-www-robotrules)
2227 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2228 (synopsis "Tools for accessing the NCBI's set of databases")
2230 "Entrez Direct (EDirect) is a method for accessing the National Center
2231 for Biotechnology Information's (NCBI) set of interconnected
2232 databases (publication, sequence, structure, gene, variation, expression,
2233 etc.) from a terminal. Functions take search terms from command-line
2234 arguments. Individual operations are combined to build multi-step queries.
2235 Record retrieval and formatting normally complete the process.
2237 EDirect also provides an argument-driven function that simplifies the
2238 extraction of data from document summaries or other results that are returned
2239 in structured XML format. This can eliminate the need for writing custom
2240 software to answer ad hoc questions.")
2241 (license license:public-domain)))
2243 (define-public exonerate
2252 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2253 "exonerate-" version ".tar.gz"))
2256 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2257 (build-system gnu-build-system)
2259 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2261 `(("pkg-config" ,pkg-config)))
2265 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2266 (synopsis "Generic tool for biological sequence alignment")
2268 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2269 the alignment of sequences using a many alignment models, either exhaustive
2270 dynamic programming or a variety of heuristics.")
2271 (license license:gpl3)))
2273 (define-public express
2281 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2282 version "/express-" version "-src.tgz"))
2285 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2286 (build-system cmake-build-system)
2288 `(#:tests? #f ;no "check" target
2291 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2292 (lambda* (#:key inputs #:allow-other-keys)
2293 (substitute* "CMakeLists.txt"
2294 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2295 "set(Boost_USE_STATIC_LIBS OFF)")
2296 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2297 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2298 (substitute* "src/CMakeLists.txt"
2299 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2300 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2305 ("bamtools" ,bamtools)
2306 ("protobuf" ,protobuf)
2308 (home-page "http://bio.math.berkeley.edu/eXpress")
2309 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2311 "eXpress is a streaming tool for quantifying the abundances of a set of
2312 target sequences from sampled subsequences. Example applications include
2313 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2314 analysis (from RNA-Seq), transcription factor binding quantification in
2315 ChIP-Seq, and analysis of metagenomic data.")
2316 (license license:artistic2.0)))
2318 (define-public express-beta-diversity
2320 (name "express-beta-diversity")
2326 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2328 (file-name (string-append name "-" version ".tar.gz"))
2331 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2332 (build-system gnu-build-system)
2335 (modify-phases %standard-phases
2337 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2339 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2341 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2343 (lambda* (#:key outputs #:allow-other-keys)
2344 (let ((bin (string-append (assoc-ref outputs "out")
2347 (copy-file "scripts/convertToEBD.py"
2348 (string-append bin "/convertToEBD.py"))
2349 (copy-file "bin/ExpressBetaDiversity"
2350 (string-append bin "/ExpressBetaDiversity"))
2353 `(("python" ,python-2)))
2354 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2355 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2357 "Express Beta Diversity (EBD) calculates ecological beta diversity
2358 (dissimilarity) measures between biological communities. EBD implements a
2359 variety of diversity measures including those that make use of phylogenetic
2360 similarity of community members.")
2361 (license license:gpl3+)))
2363 (define-public fasttree
2370 "http://www.microbesonline.org/fasttree/FastTree-"
2374 "0ljvvw8i1als1wbfzvrf15c3ii2vw9db20a259g6pzg34xyyb97k"))))
2375 (build-system gnu-build-system)
2377 `(#:tests? #f ; no "check" target
2379 (modify-phases %standard-phases
2383 (lambda* (#:key source #:allow-other-keys)
2384 (and (zero? (system* "gcc"
2386 "-finline-functions"
2393 (zero? (system* "gcc"
2397 "-finline-functions"
2405 (lambda* (#:key outputs #:allow-other-keys)
2406 (let ((bin (string-append (assoc-ref outputs "out")
2409 (copy-file "FastTree"
2410 (string-append bin "/FastTree"))
2411 (copy-file "FastTreeMP"
2412 (string-append bin "/FastTreeMP"))
2414 (home-page "http://www.microbesonline.org/fasttree")
2415 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2417 "FastTree can handle alignments with up to a million of sequences in a
2418 reasonable amount of time and memory. For large alignments, FastTree is
2419 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2420 (license license:gpl2+)))
2422 (define-public fastx-toolkit
2424 (name "fastx-toolkit")
2430 "https://github.com/agordon/fastx_toolkit/releases/download/"
2431 version "/fastx_toolkit-" version ".tar.bz2"))
2434 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2435 (build-system gnu-build-system)
2437 `(("libgtextutils" ,libgtextutils)))
2439 `(("pkg-config" ,pkg-config)))
2440 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2441 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2443 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2444 FASTA/FASTQ files preprocessing.
2446 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2447 containing multiple short-reads sequences. The main processing of such
2448 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2449 is sometimes more productive to preprocess the files before mapping the
2450 sequences to the genome---manipulating the sequences to produce better mapping
2451 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2452 (license license:agpl3+)))
2454 (define-public flexbar
2461 (string-append "mirror://sourceforge/flexbar/"
2462 version "/flexbar_v" version "_src.tgz"))
2465 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2466 (build-system cmake-build-system)
2468 `(#:configure-flags (list
2469 (string-append "-DFLEXBAR_BINARY_DIR="
2470 (assoc-ref %outputs "out")
2475 (lambda* (#:key outputs #:allow-other-keys)
2476 (setenv "PATH" (string-append
2477 (assoc-ref outputs "out") "/bin:"
2479 (chdir "../flexbar_v2.5_src/test")
2480 (zero? (system* "bash" "flexbar_validate.sh")))
2481 (alist-delete 'install %standard-phases))))
2486 `(("pkg-config" ,pkg-config)
2488 (home-page "http://flexbar.sourceforge.net")
2489 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2491 "Flexbar preprocesses high-throughput nucleotide sequencing data
2492 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2493 Moreover, trimming and filtering features are provided. Flexbar increases
2494 read mapping rates and improves genome and transcriptome assemblies. It
2495 supports next-generation sequencing data in fasta/q and csfasta/q format from
2496 Illumina, Roche 454, and the SOLiD platform.")
2497 (license license:gpl3)))
2499 (define-public fraggenescan
2501 (name "fraggenescan")
2507 (string-append "mirror://sourceforge/fraggenescan/"
2508 "FragGeneScan" version ".tar.gz"))
2510 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
2511 (build-system gnu-build-system)
2514 (modify-phases %standard-phases
2516 (add-before 'build 'patch-paths
2517 (lambda* (#:key outputs #:allow-other-keys)
2518 (let* ((out (string-append (assoc-ref outputs "out")))
2519 (share (string-append out "/share/fraggenescan/")))
2520 (substitute* "run_FragGeneScan.pl"
2522 (string-append "system(\"" (which "rm")))
2524 (string-append "system(\"" (which "mv")))
2525 ;; This script and other programs expect the training files
2526 ;; to be in the non-standard location bin/train/XXX. Change
2527 ;; this to be share/fraggenescan/train/XXX instead.
2528 (("^\\$train.file = \\$dir.*")
2529 (string-append "$train_file = \""
2531 "train/\".$FGS_train_file;")))
2532 (substitute* "run_hmm.c"
2533 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2534 (string-append " strcpy(train_dir, \"" share "/train/\");")))
2535 (substitute* "post_process.pl"
2536 (("^my \\$dir = substr.*")
2537 (string-append "my $dir = \"" share "\";"))))
2540 (lambda _ (and (zero? (system* "make" "clean"))
2541 (zero? (system* "make" "fgs")))))
2543 (lambda* (#:key outputs #:allow-other-keys)
2544 (let* ((out (string-append (assoc-ref outputs "out")))
2545 (bin (string-append out "/bin/"))
2546 (share (string-append out "/share/fraggenescan/train")))
2547 (install-file "run_FragGeneScan.pl" bin)
2548 (install-file "FragGeneScan" bin)
2549 (install-file "FGS_gff.py" bin)
2550 (install-file "post_process.pl" bin)
2551 (copy-recursively "train" share))))
2553 (add-after 'install 'post-install-check
2554 ;; In lieu of 'make check', run one of the examples and check the
2555 ;; output files gets created.
2556 (lambda* (#:key outputs #:allow-other-keys)
2557 (let* ((out (string-append (assoc-ref outputs "out")))
2558 (bin (string-append out "/bin/")))
2559 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
2560 "-genome=./example/NC_000913.fna"
2564 (file-exists? "test2.faa")
2565 (file-exists? "test2.ffn")
2566 (file-exists? "test2.gff")
2567 (file-exists? "test2.out"))))))))
2570 ("python" ,python-2))) ;not compatible with python 3.
2571 (home-page "https://sourceforge.net/projects/fraggenescan/")
2572 (synopsis "Finds potentially fragmented genes in short reads")
2574 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2575 short and error-prone DNA sequencing reads. It can also be applied to predict
2576 genes in incomplete assemblies or complete genomes.")
2577 ;; GPL3+ according to private correspondense with the authors.
2578 (license license:gpl3+)))
2580 (define-public fxtract
2581 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2589 "https://github.com/ctSkennerton/fxtract/archive/"
2591 (file-name (string-append "ctstennerton-util-"
2592 (string-take util-commit 7)
2596 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2597 (build-system gnu-build-system)
2599 `(#:make-flags (list
2600 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2602 #:test-target "fxtract_test"
2604 (modify-phases %standard-phases
2606 (add-before 'build 'copy-util
2607 (lambda* (#:key inputs #:allow-other-keys)
2609 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2611 ;; Do not use make install as this requires additional dependencies.
2613 (lambda* (#:key outputs #:allow-other-keys)
2614 (let* ((out (assoc-ref outputs "out"))
2615 (bin (string-append out"/bin")))
2616 (install-file "fxtract" bin)
2622 ;; ctskennerton-util is licensed under GPL2.
2623 `(("ctskennerton-util"
2627 (url "https://github.com/ctSkennerton/util.git")
2628 (commit util-commit)))
2629 (file-name (string-append
2630 "ctstennerton-util-" util-commit "-checkout"))
2633 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2634 (home-page "https://github.com/ctSkennerton/fxtract")
2635 (synopsis "Extract sequences from FASTA and FASTQ files")
2637 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2638 or FASTQ) file given a subsequence. It uses a simple substring search for
2639 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2640 lookups or multi-pattern searching as required. By default fxtract looks in
2641 the sequence of each record but can also be told to look in the header,
2642 comment or quality sections.")
2643 ;; 'util' requires SSE instructions.
2644 (supported-systems '("x86_64-linux"))
2645 (license license:expat))))
2654 "https://github.com/nboley/grit/archive/"
2656 (file-name (string-append name "-" version ".tar.gz"))
2659 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2660 (build-system python-build-system)
2662 `(#:python ,python-2
2665 'unpack 'generate-from-cython-sources
2666 (lambda* (#:key inputs outputs #:allow-other-keys)
2667 ;; Delete these C files to force fresh generation from pyx sources.
2668 (delete-file "grit/sparsify_support_fns.c")
2669 (delete-file "grit/call_peaks_support_fns.c")
2670 (substitute* "setup.py"
2671 (("Cython.Setup") "Cython.Build")
2672 ;; Add numpy include path to fix compilation
2674 (string-append "pyx\", ], include_dirs = ['"
2675 (assoc-ref inputs "python-numpy")
2676 "/lib/python2.7/site-packages/numpy/core/include/"
2680 `(("python-scipy" ,python2-scipy)
2681 ("python-numpy" ,python2-numpy)
2682 ("python-pysam" ,python2-pysam)
2683 ("python-networkx" ,python2-networkx)))
2685 `(("python-cython" ,python2-cython)
2686 ("python-setuptools" ,python2-setuptools)))
2687 (home-page "http://grit-bio.org")
2688 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2690 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2691 full length transcript models. When none of these data sources are available,
2692 GRIT can be run by providing a candidate set of TES or TSS sites. In
2693 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2694 also be run in quantification mode, where it uses a provided GTF file and just
2695 estimates transcript expression.")
2696 (license license:gpl3+)))
2698 (define-public hisat
2705 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2706 version "-beta-source.zip"))
2709 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2710 (build-system gnu-build-system)
2712 `(#:tests? #f ;no check target
2713 #:make-flags '("allall"
2714 ;; Disable unsupported `popcnt' instructions on
2715 ;; architectures other than x86_64
2716 ,@(if (string-prefix? "x86_64"
2717 (or (%current-target-system)
2720 '("POPCNT_CAPABILITY=0")))
2723 'unpack 'patch-sources
2725 ;; XXX Cannot use snippet because zip files are not supported
2726 (substitute* "Makefile"
2727 (("^CC = .*$") "CC = gcc")
2728 (("^CPP = .*$") "CPP = g++")
2729 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2730 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2731 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2732 (substitute* '("hisat-build" "hisat-inspect")
2733 (("/usr/bin/env") (which "env"))))
2736 (lambda* (#:key outputs #:allow-other-keys)
2737 (let ((bin (string-append (assoc-ref outputs "out") "/bi/")))
2738 (for-each (lambda (file)
2739 (install-file file bin))
2742 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2743 (alist-delete 'configure %standard-phases)))))
2745 `(("unzip" ,unzip)))
2750 ;; Non-portable SSE instructions are used so building fails on platforms
2751 ;; other than x86_64.
2752 (supported-systems '("x86_64-linux"))
2753 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2754 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2756 "HISAT is a fast and sensitive spliced alignment program for mapping
2757 RNA-seq reads. In addition to one global FM index that represents a whole
2758 genome, HISAT uses a large set of small FM indexes that collectively cover the
2759 whole genome. These small indexes (called local indexes) combined with
2760 several alignment strategies enable effective alignment of RNA-seq reads, in
2761 particular, reads spanning multiple exons.")
2762 (license license:gpl3+)))
2764 (define-public hmmer
2771 "http://eddylab.org/software/hmmer"
2772 (version-prefix version 1) "/"
2773 version "/hmmer-" version ".tar.gz"))
2776 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
2777 (build-system gnu-build-system)
2778 (native-inputs `(("perl" ,perl)))
2779 (home-page "http://hmmer.org/")
2780 (synopsis "Biosequence analysis using profile hidden Markov models")
2782 "HMMER is used for searching sequence databases for homologs of protein
2783 sequences, and for making protein sequence alignments. It implements methods
2784 using probabilistic models called profile hidden Markov models (profile
2786 (license (list license:gpl3+
2787 ;; The bundled library 'easel' is distributed
2788 ;; under The Janelia Farm Software License.
2789 (license:non-copyleft
2790 "file://easel/LICENSE"
2791 "See easel/LICENSE in the distribution.")))))
2793 (define-public htseq
2800 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2804 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2805 (build-system python-build-system)
2806 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2807 ;; Numpy needs to be propagated when htseq is used as a Python library.
2809 `(("python-numpy" ,python2-numpy)))
2811 `(("python-pysam" ,python2-pysam)))
2813 `(("python-setuptools" ,python2-setuptools)))
2814 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2815 (synopsis "Analysing high-throughput sequencing data with Python")
2817 "HTSeq is a Python package that provides infrastructure to process data
2818 from high-throughput sequencing assays.")
2819 (license license:gpl3+)))
2821 (define-public java-htsjdk
2823 (name "java-htsjdk")
2828 "https://github.com/samtools/htsjdk/archive/"
2830 (file-name (string-append name "-" version ".tar.gz"))
2833 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2834 (modules '((guix build utils)))
2835 ;; remove build dependency on git
2836 (snippet '(substitute* "build.xml"
2837 (("failifexecutionfails=\"true\"")
2838 "failifexecutionfails=\"false\"")))))
2839 (build-system ant-build-system)
2841 `(#:tests? #f ; test require Internet access
2843 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2844 "/share/java/htsjdk/"))
2845 #:build-target "all"
2847 (modify-phases %standard-phases
2848 ;; The build phase also installs the jars
2849 (delete 'install))))
2850 (home-page "http://samtools.github.io/htsjdk/")
2851 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2853 "HTSJDK is an implementation of a unified Java library for accessing
2854 common file formats, such as SAM and VCF, used for high-throughput
2855 sequencing (HTS) data. There are also an number of useful utilities for
2856 manipulating HTS data.")
2857 (license license:expat)))
2859 (define-public htslib
2866 "https://github.com/samtools/htslib/releases/download/"
2867 version "/htslib-" version ".tar.bz2"))
2870 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
2871 (build-system gnu-build-system)
2874 (modify-phases %standard-phases
2876 'unpack 'patch-tests
2878 (substitute* "test/test.pl"
2879 (("/bin/bash") (which "bash")))
2885 (home-page "http://www.htslib.org")
2886 (synopsis "C library for reading/writing high-throughput sequencing data")
2888 "HTSlib is a C library for reading/writing high-throughput sequencing
2889 data. It also provides the bgzip, htsfile, and tabix utilities.")
2890 ;; Files under cram/ are released under the modified BSD license;
2891 ;; the rest is released under the Expat license
2892 (license (list license:expat license:bsd-3))))
2901 "https://github.com/nboley/idr/archive/"
2903 (file-name (string-append name "-" version ".tar.gz"))
2906 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
2907 (build-system python-build-system)
2910 (modify-phases %standard-phases
2912 'install 'wrap-program
2913 (lambda* (#:key inputs outputs #:allow-other-keys)
2914 (let* ((out (assoc-ref outputs "out"))
2915 (python-version (string-take (string-take-right
2916 (assoc-ref inputs "python") 5) 3))
2919 (string-append (assoc-ref inputs name)
2920 "/lib/python" python-version
2924 "python-matplotlib"))
2926 (wrap-program (string-append out "/bin/idr")
2927 `("PYTHONPATH" ":" prefix (,path))))
2930 `(("python-scipy" ,python-scipy)
2931 ("python-numpy" ,python-numpy)
2932 ("python-matplotlib" ,python-matplotlib)))
2934 `(("python-cython" ,python-cython)
2935 ("python-setuptools" ,python-setuptools)))
2936 (home-page "https://github.com/nboley/idr")
2937 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
2939 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
2940 to measure the reproducibility of findings identified from replicate
2941 experiments and provide highly stable thresholds based on reproducibility.")
2942 (license license:gpl3+)))
2944 (define-public jellyfish
2950 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
2951 "releases/download/v" version
2952 "/jellyfish-" version ".tar.gz"))
2955 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
2956 (build-system gnu-build-system)
2957 (outputs '("out" ;for library
2958 "ruby" ;for Ruby bindings
2959 "python")) ;for Python bindings
2962 (list (string-append "--enable-ruby-binding="
2963 (assoc-ref %outputs "ruby"))
2964 (string-append "--enable-python-binding="
2965 (assoc-ref %outputs "python")))
2967 (modify-phases %standard-phases
2968 (add-before 'check 'set-SHELL-variable
2970 ;; generator_manager.hpp either uses /bin/sh or $SHELL
2972 (setenv "SHELL" (which "bash"))
2978 ("python" ,python-2)))
2979 (synopsis "Tool for fast counting of k-mers in DNA")
2981 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
2982 DNA. A k-mer is a substring of length k, and counting the occurrences of all
2983 such substrings is a central step in many analyses of DNA sequence. Jellyfish
2984 is a command-line program that reads FASTA and multi-FASTA files containing
2985 DNA sequences. It outputs its k-mer counts in a binary format, which can be
2986 translated into a human-readable text format using the @code{jellyfish dump}
2987 command, or queried for specific k-mers with @code{jellyfish query}.")
2988 (home-page "http://www.genome.umd.edu/jellyfish.html")
2989 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
2990 (supported-systems '("x86_64-linux"))
2991 ;; The combined work is published under the GPLv3 or later. Individual
2992 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
2993 (license (list license:gpl3+ license:expat))))
2995 (define-public khmer
3002 (uri (pypi-uri "khmer" version))
3005 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3006 (patches (search-patches "khmer-use-libraries.patch"))))
3007 (build-system python-build-system)
3010 (modify-phases %standard-phases
3011 (add-after 'unpack 'set-paths
3012 (lambda* (#:key inputs outputs #:allow-other-keys)
3013 ;; Delete bundled libraries.
3014 (delete-file-recursively "third-party/zlib")
3015 (delete-file-recursively "third-party/bzip2")
3016 ;; Replace bundled seqan.
3017 (let* ((seqan-all "third-party/seqan")
3018 (seqan-include (string-append
3019 seqan-all "/core/include")))
3020 (delete-file-recursively seqan-all)
3021 (copy-recursively (string-append (assoc-ref inputs "seqan")
3023 (string-append seqan-include "/seqan")))
3024 ;; We do not replace the bundled MurmurHash as the canonical
3025 ;; repository for this code 'SMHasher' is unsuitable for
3026 ;; providing a library. See
3027 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3029 (add-after 'unpack 'set-cc
3033 ;; It is simpler to test after installation.
3035 (add-after 'install 'post-install-check
3036 (lambda* (#:key inputs outputs #:allow-other-keys)
3037 (let ((out (assoc-ref outputs "out")))
3042 (assoc-ref outputs "out")
3044 (setenv "PYTHONPATH"
3046 (getenv "PYTHONPATH")
3050 (string-take (string-take-right
3051 (assoc-ref inputs "python") 5) 3)
3053 (with-directory-excursion "build"
3054 (zero? (system* "nosetests" "khmer" "--attr"
3055 "!known_failing")))))))))
3058 ("python-nose" ,python-nose)))
3062 ("python-screed" ,python-screed)
3063 ("python-bz2file" ,python-bz2file)))
3064 (home-page "https://khmer.readthedocs.org/")
3065 (synopsis "K-mer counting, filtering and graph traversal library")
3066 (description "The khmer software is a set of command-line tools for
3067 working with DNA shotgun sequencing data from genomes, transcriptomes,
3068 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3069 sometimes better. Khmer can also identify and fix problems with shotgun
3071 ;; When building on i686, armhf and mips64el, we get the following error:
3072 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3073 (supported-systems '("x86_64-linux"))
3074 (license license:bsd-3)))
3079 (version "2.1.0.20151222")
3082 (uri (pypi-uri "MACS2" version))
3085 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3086 (build-system python-build-system)
3088 `(#:python ,python-2 ; only compatible with Python 2.7
3089 #:tests? #f)) ; no test target
3091 `(("python-numpy" ,python2-numpy)))
3093 `(("python-setuptools" ,python2-setuptools)))
3094 (home-page "http://github.com/taoliu/MACS/")
3095 (synopsis "Model based analysis for ChIP-Seq data")
3097 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3098 identifying transcript factor binding sites named Model-based Analysis of
3099 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3100 the significance of enriched ChIP regions and it improves the spatial
3101 resolution of binding sites through combining the information of both
3102 sequencing tag position and orientation.")
3103 (license license:bsd-3)))
3105 (define-public mafft
3112 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3113 "-without-extensions-src.tgz"))
3114 (file-name (string-append name "-" version ".tgz"))
3117 "0ziim7g58n3z8gppsa713f5fxprl60ldj3xck186z0n9dpp06i8r"))))
3118 (build-system gnu-build-system)
3120 `(#:tests? #f ; no automated tests, though there are tests in the read me
3121 #:make-flags (let ((out (assoc-ref %outputs "out")))
3122 (list (string-append "PREFIX=" out)
3123 (string-append "BINDIR="
3124 (string-append out "/bin"))))
3126 (modify-phases %standard-phases
3127 (add-after 'unpack 'enter-dir
3128 (lambda _ (chdir "core") #t))
3129 (add-after 'enter-dir 'patch-makefile
3131 ;; on advice from the MAFFT authors, there is no need to
3132 ;; distribute mafft-profile, mafft-distance, or
3133 ;; mafft-homologs.rb as they are too "specialised".
3134 (substitute* "Makefile"
3135 ;; remove mafft-homologs.rb from SCRIPTS
3136 (("^SCRIPTS = mafft mafft-homologs.rb")
3138 ;; remove mafft-homologs from MANPAGES
3139 (("^MANPAGES = mafft.1 mafft-homologs.1")
3140 "MANPAGES = mafft.1")
3141 ;; remove mafft-distance from PROGS
3142 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3143 "PROGS = dvtditr dndfast7 dndblast sextet5")
3144 ;; remove mafft-profile from PROGS
3145 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3146 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3147 (("^rm -f mafft-profile mafft-profile.exe") "#")
3148 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3149 ;; do not install MAN pages in libexec folder
3150 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3151 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3153 (add-after 'enter-dir 'patch-paths
3154 (lambda* (#:key inputs #:allow-other-keys)
3155 (substitute* '("pairash.c"
3157 (("perl") (which "perl"))
3158 (("([\"`| ])awk" _ prefix)
3159 (string-append prefix (which "awk")))
3160 (("grep") (which "grep")))
3163 (add-after 'install 'wrap-programs
3164 (lambda* (#:key outputs #:allow-other-keys)
3165 (let* ((out (assoc-ref outputs "out"))
3166 (bin (string-append out "/bin"))
3167 (path (string-append
3168 (assoc-ref %build-inputs "coreutils") "/bin:")))
3169 (for-each (lambda (file)
3171 `("PATH" ":" prefix (,path))))
3179 ("coreutils" ,coreutils)))
3180 (home-page "http://mafft.cbrc.jp/alignment/software/")
3181 (synopsis "Multiple sequence alignment program")
3183 "MAFFT offers a range of multiple alignment methods for nucleotide and
3184 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3185 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3187 (license (license:non-copyleft
3188 "http://mafft.cbrc.jp/alignment/software/license.txt"
3189 "BSD-3 with different formatting"))))
3198 "https://github.com/marbl/mash/archive/v"
3200 (file-name (string-append name "-" version ".tar.gz"))
3203 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3204 (modules '((guix build utils)))
3206 ;; Delete bundled kseq.
3207 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3208 '(delete-file "src/mash/kseq.h"))))
3209 (build-system gnu-build-system)
3211 `(#:tests? #f ; No tests.
3214 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3215 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3216 #:make-flags (list "CC=gcc")
3218 (modify-phases %standard-phases
3219 (add-after 'unpack 'fix-includes
3221 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3222 (("^#include \"kseq\\.h\"")
3223 "#include \"htslib/kseq.h\""))
3225 (add-before 'configure 'autoconf
3226 (lambda _ (zero? (system* "autoconf")))))))
3228 `(("autoconf" ,autoconf)
3229 ;; Capnproto and htslib are statically embedded in the final
3230 ;; application. Therefore we also list their licenses, below.
3231 ("capnproto" ,capnproto)
3232 ("htslib" ,htslib)))
3236 (supported-systems '("x86_64-linux"))
3237 (home-page "https://mash.readthedocs.io")
3238 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3239 (description "Mash is a fast sequence distance estimator that uses the
3240 MinHash algorithm and is designed to work with genomes and metagenomes in the
3241 form of assemblies or reads.")
3242 (license (list license:bsd-3 ; Mash
3243 license:expat ; HTSlib and capnproto
3244 license:public-domain ; MurmurHash 3
3245 license:cpl1.0)))) ; Open Bloom Filter
3247 (define-public metabat
3248 ;; We package from a git commit because compilation of the released version
3250 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3253 (version (string-append "0.32.4-1." (string-take commit 8)))
3258 (url "https://bitbucket.org/berkeleylab/metabat.git")
3260 (file-name (string-append name "-" version))
3263 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3264 (patches (search-patches "metabat-remove-compilation-date.patch"))))
3265 (build-system gnu-build-system)
3268 (modify-phases %standard-phases
3269 (add-after 'unpack 'fix-includes
3271 (substitute* "src/BamUtils.h"
3272 (("^#include \"bam/bam\\.h\"")
3273 "#include \"samtools/bam.h\"")
3274 (("^#include \"bam/sam\\.h\"")
3275 "#include \"samtools/sam.h\""))
3276 (substitute* "src/KseqReader.h"
3277 (("^#include \"bam/kseq\\.h\"")
3278 "#include \"htslib/kseq.h\""))
3280 (add-after 'unpack 'fix-scons
3281 (lambda* (#:key inputs #:allow-other-keys)
3282 (substitute* "SConstruct"
3283 (("^htslib_dir = 'samtools'")
3284 (string-append "hitslib_dir = '"
3285 (assoc-ref inputs "htslib")
3287 (("^samtools_dir = 'samtools'")
3288 (string-append "samtools_dir = '"
3289 (assoc-ref inputs "htslib")
3291 (("^findStaticOrShared\\('bam', hts_lib")
3292 (string-append "findStaticOrShared('bam', '"
3293 (assoc-ref inputs "samtools")
3295 ;; Do not distribute README.
3296 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3300 (lambda* (#:key inputs outputs #:allow-other-keys)
3301 (mkdir (assoc-ref outputs "out"))
3302 (zero? (system* "scons"
3305 (assoc-ref outputs "out"))
3308 (assoc-ref inputs "boost"))
3310 ;; Check and install are carried out during build phase.
3312 (delete 'install))))
3316 ("samtools" ,samtools)
3320 `(("scons" ,scons)))
3321 (home-page "https://bitbucket.org/berkeleylab/metabat")
3323 "Reconstruction of single genomes from complex microbial communities")
3325 "Grouping large genomic fragments assembled from shotgun metagenomic
3326 sequences to deconvolute complex microbial communities, or metagenome binning,
3327 enables the study of individual organisms and their interactions. MetaBAT is
3328 an automated metagenome binning software, which integrates empirical
3329 probabilistic distances of genome abundance and tetranucleotide frequency.")
3330 (license (license:non-copyleft "file://license.txt"
3331 "See license.txt in the distribution.")))))
3333 (define-public minced
3340 "https://github.com/ctSkennerton/minced/archive/"
3342 (file-name (string-append name "-" version ".tar.gz"))
3345 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3346 (build-system gnu-build-system)
3348 `(#:test-target "test"
3350 (modify-phases %standard-phases
3352 (add-before 'check 'fix-test
3354 ;; Fix test for latest version.
3355 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3356 (("minced:0.1.6") "minced:0.2.0"))
3358 (replace 'install ; No install target.
3359 (lambda* (#:key inputs outputs #:allow-other-keys)
3360 (let* ((out (assoc-ref outputs "out"))
3361 (bin (string-append out "/bin"))
3362 (wrapper (string-append bin "/minced")))
3363 ;; Minced comes with a wrapper script that tries to figure out where
3364 ;; it is located before running the JAR. Since these paths are known
3365 ;; to us, we build our own wrapper to avoid coreutils dependency.
3366 (install-file "minced.jar" bin)
3367 (with-output-to-file wrapper
3371 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3372 (assoc-ref inputs "jre") "/bin/java -jar "
3373 bin "/minced.jar \"$@\"\n"))))
3374 (chmod wrapper #o555)))))))
3376 `(("jdk" ,icedtea "jdk")))
3379 ("jre" ,icedtea "out")))
3380 (home-page "https://github.com/ctSkennerton/minced")
3381 (synopsis "Mining CRISPRs in Environmental Datasets")
3383 "MinCED is a program to find Clustered Regularly Interspaced Short
3384 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3385 unassembled metagenomic reads, but is mainly designed for full genomes and
3386 assembled metagenomic sequence.")
3387 (license license:gpl3+)))
3396 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3400 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3401 (modules '((guix build utils)))
3403 '(substitute* "setup.py"
3404 ;; Use setuptools, or else the executables are not
3406 (("distutils.core") "setuptools")
3407 ;; use "gcc" instead of "cc" for compilation
3409 "cc.set_executables(
3413 linker_so='gcc -shared'); defines")))))
3414 (build-system python-build-system)
3416 `(#:python ,python-2 ; only Python 2 is supported
3417 #:tests? #f)) ; no "test" target
3419 `(("samtools" ,samtools)
3420 ("python-numpy" ,python2-numpy)
3421 ("python-pysam" ,python2-pysam)
3422 ("python-scipy" ,python2-scipy)
3423 ("python-matplotlib" ,python2-matplotlib)))
3425 `(("python-mock" ,python2-mock) ;for tests
3426 ("python-pytz" ,python2-pytz) ;for tests
3427 ("python-setuptools" ,python2-setuptools)))
3428 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3429 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3431 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3432 the expression level of alternatively spliced genes from RNA-Seq data, and
3433 identifies differentially regulated isoforms or exons across samples. By
3434 modeling the generative process by which reads are produced from isoforms in
3435 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3436 that a read originated from a particular isoform.")
3437 (license license:gpl2)))
3439 (define-public muscle
3442 (version "3.8.1551")
3444 (method url-fetch/tarbomb)
3445 (file-name (string-append name "-" version))
3447 "http://www.drive5.com/muscle/muscle_src_"
3451 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3452 (build-system gnu-build-system)
3454 `(#:make-flags (list "LDLIBS = -lm")
3456 (modify-phases %standard-phases
3459 ;; There are no tests, so just test if it runs.
3460 (lambda _ (zero? (system* "./muscle" "-version"))))
3462 (lambda* (#:key outputs #:allow-other-keys)
3463 (let* ((out (assoc-ref outputs "out"))
3464 (bin (string-append out "/bin")))
3465 (install-file "muscle" bin)))))))
3466 (home-page "http://www.drive5.com/muscle")
3467 (synopsis "Multiple sequence alignment program")
3469 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3470 program for nucleotide and protein sequences.")
3471 ;; License information found in 'muscle -h' and usage.cpp.
3472 (license license:public-domain)))
3481 "https://github.com/wwood/OrfM/releases/download/v"
3482 version "/orfm-" version ".tar.gz"))
3485 "0vb6d771gl4mix8bwx919x5ayy9pkj44n7ki336nz3rz2rx4c7gk"))))
3486 (build-system gnu-build-system)
3487 (inputs `(("zlib" ,zlib)))
3489 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3490 ("ruby-rspec" ,ruby-rspec)
3492 (synopsis "Simple and not slow open reading frame (ORF) caller")
3494 "An ORF caller finds stretches of DNA that, when translated, are not
3495 interrupted by stop codons. OrfM finds and prints these ORFs.")
3496 (home-page "https://github.com/wwood/OrfM")
3497 (license license:lgpl3+)))
3499 (define-public python2-pbcore
3501 (name "python2-pbcore")
3505 (uri (pypi-uri "pbcore" version))
3508 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3509 (build-system python-build-system)
3510 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3512 `(("python-cython" ,python2-cython)
3513 ("python-numpy" ,python2-numpy)
3514 ("python-pysam" ,python2-pysam)
3515 ("python-h5py" ,python2-h5py)))
3517 `(("python-docutils" ,python2-docutils)
3518 ("python-nose" ,python2-nose)
3519 ("python-setuptools" ,python2-setuptools)
3520 ("python-sphinx" ,python2-sphinx)))
3522 `(("python-pyxb" ,python2-pyxb)))
3523 (home-page "http://pacificbiosciences.github.io/pbcore/")
3524 (synopsis "Library for reading and writing PacBio data files")
3526 "The pbcore package provides Python APIs for interacting with PacBio data
3527 files and writing bioinformatics applications.")
3528 (license license:bsd-3)))
3530 (define-public python2-warpedlmm
3532 (name "python2-warpedlmm")
3538 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3542 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3543 (build-system python-build-system)
3545 `(#:python ,python-2 ; requires Python 2.7
3547 (modify-phases %standard-phases
3549 'install 'remove-bin-directory
3550 (lambda* (#:key outputs #:allow-other-keys)
3551 ;; The "bin" directory only contains wrappers for running
3552 ;; the module tests. They are not needed after the
3554 (delete-file-recursively
3555 (string-append (assoc-ref outputs "out") "/bin"))
3558 `(("python-scipy" ,python2-scipy)
3559 ("python-numpy" ,python2-numpy)
3560 ("python-matplotlib" ,python2-matplotlib)
3561 ("python-fastlmm" ,python2-fastlmm)
3562 ("python-pandas" ,python2-pandas)
3563 ("python-pysnptools" ,python2-pysnptools)))
3565 `(("python-setuptools" ,python2-setuptools)
3566 ("python-mock" ,python2-mock)
3567 ("python-nose" ,python2-nose)
3569 (home-page "https://github.com/PMBio/warpedLMM")
3570 (synopsis "Implementation of warped linear mixed models")
3572 "WarpedLMM is a Python implementation of the warped linear mixed model,
3573 which automatically learns an optimal warping function (or transformation) for
3574 the phenotype as it models the data.")
3575 (license license:asl2.0)))
3577 (define-public pbtranscript-tofu
3578 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3580 (name "pbtranscript-tofu")
3581 (version (string-append "2.2.3." (string-take commit 7)))
3585 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3587 (file-name (string-append name "-" version "-checkout"))
3590 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3591 (modules '((guix build utils)))
3594 ;; remove bundled Cython sources
3595 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3597 (build-system python-build-system)
3599 `(#:python ,python-2
3600 ;; With standard flags, the install phase attempts to create a zip'd
3601 ;; egg file, and fails with an error: 'ZIP does not support timestamps
3603 #:configure-flags '("--single-version-externally-managed"
3604 "--record=pbtranscript-tofu.txt")
3606 (modify-phases %standard-phases
3607 (add-after 'unpack 'enter-directory
3609 (chdir "pbtranscript-tofu/pbtranscript/")
3611 ;; With setuptools version 18.0 and later this setup.py hack causes
3612 ;; a build error, so we disable it.
3613 (add-after 'enter-directory 'patch-setuppy
3615 (substitute* "setup.py"
3616 (("if 'setuptools.extension' in sys.modules:")
3620 `(("python-numpy" ,python2-numpy)
3621 ("python-bx-python" ,python2-bx-python)
3622 ("python-networkx" ,python2-networkx)
3623 ("python-scipy" ,python2-scipy)
3624 ("python-pbcore" ,python2-pbcore)
3625 ("python-h5py" ,python2-h5py)))
3627 `(("python-cython" ,python2-cython)
3628 ("python-nose" ,python2-nose)
3629 ("python-setuptools" ,python2-setuptools)))
3630 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3631 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3633 "pbtranscript-tofu contains scripts to analyze transcriptome data
3634 generated using the PacBio Iso-Seq protocol.")
3635 (license license:bsd-3))))
3637 (define-public prank
3644 "http://wasabiapp.org/download/prank/prank.source."
3648 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3649 (build-system gnu-build-system)
3652 (modify-phases %standard-phases
3653 (add-after 'unpack 'enter-src-dir
3657 (add-after 'unpack 'remove-m64-flag
3658 ;; Prank will build with the correct 'bit-ness' without this flag
3659 ;; and this allows building on 32-bit machines.
3660 (lambda _ (substitute* "src/Makefile"
3665 (lambda* (#:key outputs #:allow-other-keys)
3666 (let* ((out (assoc-ref outputs "out"))
3667 (bin (string-append out "/bin"))
3668 (man (string-append out "/share/man/man1"))
3669 (path (string-append
3670 (assoc-ref %build-inputs "mafft") "/bin:"
3671 (assoc-ref %build-inputs "exonerate") "/bin:"
3672 (assoc-ref %build-inputs "bppsuite") "/bin")))
3673 (install-file "prank" bin)
3674 (wrap-program (string-append bin "/prank")
3675 `("PATH" ":" prefix (,path)))
3676 (install-file "prank.1" man))
3680 ("exonerate" ,exonerate)
3681 ("bppsuite" ,bppsuite)))
3682 (home-page "http://wasabiapp.org/software/prank/")
3683 (synopsis "Probabilistic multiple sequence alignment program")
3685 "PRANK is a probabilistic multiple sequence alignment program for DNA,
3686 codon and amino-acid sequences. It is based on a novel algorithm that treats
3687 insertions correctly and avoids over-estimation of the number of deletion
3688 events. In addition, PRANK borrows ideas from maximum likelihood methods used
3689 in phylogenetics and correctly takes into account the evolutionary distances
3690 between sequences. Lastly, PRANK allows for defining a potential structure
3691 for sequences to be aligned and then, simultaneously with the alignment,
3692 predicts the locations of structural units in the sequences.")
3693 (license license:gpl2+)))
3695 (define-public pyicoteo
3702 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
3703 "pyicoteo/get/v" version ".tar.bz2"))
3704 (file-name (string-append name "-" version ".tar.bz2"))
3707 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
3708 (build-system python-build-system)
3710 `(#:python ,python-2 ; does not work with Python 3
3711 #:tests? #f)) ; there are no tests
3713 `(("python2-matplotlib" ,python2-matplotlib)))
3714 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
3715 (synopsis "Analyze high-throughput genetic sequencing data")
3717 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
3718 sequencing data. It works with genomic coordinates. There are currently six
3719 different command-line tools:
3722 @item pyicoregion: for generating exploratory regions automatically;
3723 @item pyicoenrich: for differential enrichment between two conditions;
3724 @item pyicoclip: for calling CLIP-Seq peaks without a control;
3725 @item pyicos: for genomic coordinates manipulation;
3726 @item pyicoller: for peak calling on punctuated ChIP-Seq;
3727 @item pyicount: to count how many reads from N experiment files overlap in a
3729 @item pyicotrocol: to combine operations from pyicoteo.
3731 (license license:gpl3+)))
3733 (define-public prodigal
3740 "https://github.com/hyattpd/Prodigal/archive/v"
3742 (file-name (string-append name "-" version ".tar.gz"))
3745 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
3746 (build-system gnu-build-system)
3748 `(#:tests? #f ;no check target
3749 #:make-flags (list (string-append "INSTALLDIR="
3750 (assoc-ref %outputs "out")
3753 (modify-phases %standard-phases
3754 (delete 'configure))))
3755 (home-page "http://prodigal.ornl.gov")
3756 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
3758 "Prodigal runs smoothly on finished genomes, draft genomes, and
3759 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
3760 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
3761 partial genes, and identifies translation initiation sites.")
3762 (license license:gpl3+)))
3764 (define-public roary
3772 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
3776 "0g0pzcv8y7n2w8q7c9q0a7s2ghkwci6w8smg9mjw4agad5cd7yaw"))))
3777 (build-system perl-build-system)
3780 (modify-phases %standard-phases
3785 ;; The tests are not run by default, so we run each test file
3787 (setenv "PATH" (string-append (getcwd) "/bin" ":"
3789 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
3790 (getenv "PERL5LIB")))
3791 (zero? (length (filter (lambda (file)
3792 (display file)(display "\n")
3793 (not (zero? (system* "perl" file))))
3794 (find-files "t" ".*\\.t$"))))))
3796 ;; There is no 'install' target in the Makefile.
3797 (lambda* (#:key outputs #:allow-other-keys)
3798 (let* ((out (assoc-ref outputs "out"))
3799 (bin (string-append out "/bin"))
3800 (perl (string-append out "/lib/perl5/site_perl"))
3801 (roary-plots "contrib/roary_plots"))
3804 (copy-recursively "bin" bin)
3805 (copy-recursively "lib" perl)
3807 (add-after 'install 'wrap-programs
3808 (lambda* (#:key inputs outputs #:allow-other-keys)
3809 (let* ((out (assoc-ref outputs "out"))
3810 (perl5lib (getenv "PERL5LIB"))
3811 (path (getenv "PATH")))
3812 (for-each (lambda (prog)
3813 (let ((binary (string-append out "/" prog)))
3814 (wrap-program binary
3815 `("PERL5LIB" ":" prefix
3816 (,(string-append perl5lib ":" out
3817 "/lib/perl5/site_perl"))))
3818 (wrap-program binary
3820 (,(string-append path ":" out "/bin"))))))
3821 (find-files "bin" ".*[^R]$"))
3823 (string-append out "/bin/roary-create_pan_genome_plots.R"))
3824 (r-site-lib (getenv "R_LIBS_SITE"))
3826 (string-append (assoc-ref inputs "coreutils") "/bin")))
3828 `("R_LIBS_SITE" ":" prefix
3829 (,(string-append r-site-lib ":" out "/site-library/"))))
3832 (,(string-append coreutils-path ":" out "/bin"))))))
3835 `(("perl-env-path" ,perl-env-path)
3836 ("perl-test-files" ,perl-test-files)
3837 ("perl-test-most" ,perl-test-most)
3838 ("perl-test-output" ,perl-test-output)))
3840 `(("perl-array-utils" ,perl-array-utils)
3841 ("bioperl" ,bioperl-minimal)
3842 ("perl-exception-class" ,perl-exception-class)
3843 ("perl-file-find-rule" ,perl-file-find-rule)
3844 ("perl-file-grep" ,perl-file-grep)
3845 ("perl-file-slurper" ,perl-file-slurper)
3846 ("perl-file-which" ,perl-file-which)
3847 ("perl-graph" ,perl-graph)
3848 ("perl-graph-readwrite" ,perl-graph-readwrite)
3849 ("perl-log-log4perl" ,perl-log-log4perl)
3850 ("perl-moose" ,perl-moose)
3851 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
3852 ("perl-text-csv" ,perl-text-csv)
3853 ("bedtools" ,bedtools)
3857 ("parallel" ,parallel)
3860 ("fasttree" ,fasttree)
3865 ("r-ggplot2" ,r-ggplot2)
3866 ("coreutils" ,coreutils)))
3867 (home-page "http://sanger-pathogens.github.io/Roary")
3868 (synopsis "High speed stand-alone pan genome pipeline")
3870 "Roary is a high speed stand alone pan genome pipeline, which takes
3871 annotated assemblies in GFF3 format (produced by the Prokka program) and
3872 calculates the pan genome. Using a standard desktop PC, it can analyse
3873 datasets with thousands of samples, without compromising the quality of the
3874 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
3875 single processor. Roary is not intended for metagenomics or for comparing
3876 extremely diverse sets of genomes.")
3877 (license license:gpl3)))
3879 (define-public raxml
3888 "https://github.com/stamatak/standard-RAxML/archive/v"
3890 (file-name (string-append name "-" version ".tar.gz"))
3893 "1pv8p2fy67y21a9y4cm7xpvxqjwz2v4201flfjshdq1p8j52rqf7"))))
3894 (build-system gnu-build-system)
3896 `(#:tests? #f ; There are no tests.
3897 ;; Use 'standard' Makefile rather than SSE or AVX ones.
3898 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
3900 (modify-phases %standard-phases
3903 (lambda* (#:key outputs #:allow-other-keys)
3904 (let* ((out (assoc-ref outputs "out"))
3905 (bin (string-append out "/bin"))
3906 (executable "raxmlHPC-HYBRID"))
3907 (install-file executable bin)
3908 (symlink (string-append bin "/" executable) "raxml"))
3911 `(("openmpi" ,openmpi)))
3912 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
3913 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
3915 "RAxML is a tool for phylogenetic analysis and post-analysis of large
3917 (license license:gpl2+)))
3927 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
3930 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
3931 (patches (search-patches "rsem-makefile.patch"))
3932 (modules '((guix build utils)))
3935 ;; remove bundled copy of boost
3936 (delete-file-recursively "boost")
3938 (build-system gnu-build-system)
3940 `(#:tests? #f ;no "check" target
3942 (modify-phases %standard-phases
3943 ;; No "configure" script.
3944 ;; Do not build bundled samtools library.
3947 (substitute* "Makefile"
3948 (("^all : sam/libbam.a") "all : "))
3951 (lambda* (#:key outputs #:allow-other-keys)
3952 (let* ((out (string-append (assoc-ref outputs "out")))
3953 (bin (string-append out "/bin/"))
3954 (perl (string-append out "/lib/perl5/site_perl")))
3957 (for-each (lambda (file)
3959 (string-append bin (basename file))))
3960 (find-files "." "rsem-.*"))
3961 (copy-file "rsem_perl_utils.pm"
3962 (string-append perl "/rsem_perl_utils.pm")))
3965 'install 'wrap-program
3966 (lambda* (#:key outputs #:allow-other-keys)
3967 (let ((out (assoc-ref outputs "out")))
3968 (for-each (lambda (prog)
3969 (wrap-program (string-append out "/bin/" prog)
3970 `("PERL5LIB" ":" prefix
3971 (,(string-append out "/lib/perl5/site_perl")))))
3972 '("rsem-plot-transcript-wiggles"
3973 "rsem-calculate-expression"
3974 "rsem-generate-ngvector"
3976 "rsem-prepare-reference")))
3980 ("ncurses" ,ncurses)
3983 ("samtools" ,samtools-0.1)
3985 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
3986 (synopsis "Estimate gene expression levels from RNA-Seq data")
3988 "RSEM is a software package for estimating gene and isoform expression
3989 levels from RNA-Seq data. The RSEM package provides a user-friendly
3990 interface, supports threads for parallel computation of the EM algorithm,
3991 single-end and paired-end read data, quality scores, variable-length reads and
3992 RSPD estimation. In addition, it provides posterior mean and 95% credibility
3993 interval estimates for expression levels. For visualization, it can generate
3994 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
3995 (license license:gpl3+)))
3997 (define-public rseqc
4005 (string-append "mirror://sourceforge/rseqc/"
4006 "RSeQC-" version ".tar.gz"))
4008 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4009 (modules '((guix build utils)))
4012 ;; remove bundled copy of pysam
4013 (delete-file-recursively "lib/pysam")
4014 (substitute* "setup.py"
4015 ;; remove dependency on outdated "distribute" module
4016 (("^from distribute_setup import use_setuptools") "")
4017 (("^use_setuptools\\(\\)") "")
4018 ;; do not use bundled copy of pysam
4019 (("^have_pysam = False") "have_pysam = True"))))))
4020 (build-system python-build-system)
4021 (arguments `(#:python ,python-2))
4023 `(("python-cython" ,python2-cython)
4024 ("python-pysam" ,python2-pysam)
4025 ("python-numpy" ,python2-numpy)
4026 ("python-setuptools" ,python2-setuptools)
4029 `(("python-nose" ,python2-nose)))
4030 (home-page "http://rseqc.sourceforge.net/")
4031 (synopsis "RNA-seq quality control package")
4033 "RSeQC provides a number of modules that can comprehensively evaluate
4034 high throughput sequence data, especially RNA-seq data. Some basic modules
4035 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4036 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4037 distribution, coverage uniformity, strand specificity, etc.")
4038 (license license:gpl3+)))
4041 ;; There are no release tarballs. According to the installation
4042 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4043 ;; stable release is identified by this changeset ID.
4044 (let ((changeset "2329130")
4048 (version (string-append "0-" revision "." changeset))
4052 (url "https://bitbucket.org/libsleipnir/sleipnir")
4053 (changeset changeset)))
4056 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4057 (build-system gnu-build-system)
4059 `(#:modules ((srfi srfi-1)
4060 (guix build gnu-build-system)
4063 (let ((dirs '("SeekMiner"
4069 (modify-phases %standard-phases
4070 (add-before 'configure 'bootstrap
4072 (zero? (system* "bash" "gen_auto"))))
4073 (add-after 'build 'build-additional-tools
4074 (lambda* (#:key make-flags #:allow-other-keys)
4075 (every (lambda (dir)
4076 (with-directory-excursion (string-append "tools/" dir)
4077 (zero? (apply system* "make" make-flags))))
4079 (add-after 'install 'install-additional-tools
4080 (lambda* (#:key make-flags #:allow-other-keys)
4081 (fold (lambda (dir result)
4082 (with-directory-excursion (string-append "tools/" dir)
4084 (zero? (apply system*
4085 `("make" ,@make-flags "install"))))))
4091 ("readline" ,readline)
4092 ("gengetopt" ,gengetopt)
4093 ("log4cpp" ,log4cpp)))
4095 `(("autoconf" ,autoconf)
4096 ("automake" ,automake)
4098 (home-page "http://seek.princeton.edu")
4099 (synopsis "Gene co-expression search engine")
4101 "SEEK is a computational gene co-expression search engine. SEEK provides
4102 biologists with a way to navigate the massive human expression compendium that
4103 now contains thousands of expression datasets. SEEK returns a robust ranking
4104 of co-expressed genes in the biological area of interest defined by the user's
4105 query genes. It also prioritizes thousands of expression datasets according
4106 to the user's query of interest.")
4107 (license license:cc-by3.0))))
4109 (define-public samtools
4117 (string-append "mirror://sourceforge/samtools/samtools/"
4118 version "/samtools-" version ".tar.bz2"))
4121 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4122 (build-system gnu-build-system)
4124 `(#:modules ((ice-9 ftw)
4126 (guix build gnu-build-system)
4128 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4129 #:configure-flags (list "--with-ncurses")
4132 'unpack 'patch-tests
4134 (substitute* "test/test.pl"
4135 ;; The test script calls out to /bin/bash
4136 (("/bin/bash") (which "bash")))
4139 'install 'install-library
4140 (lambda* (#:key outputs #:allow-other-keys)
4141 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4142 (install-file "libbam.a" lib)))
4144 'install 'install-headers
4145 (lambda* (#:key outputs #:allow-other-keys)
4146 (let ((include (string-append (assoc-ref outputs "out")
4147 "/include/samtools/")))
4148 (for-each (lambda (file)
4149 (install-file file include))
4150 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4152 %standard-phases)))))
4153 (native-inputs `(("pkg-config" ,pkg-config)))
4154 (inputs `(("ncurses" ,ncurses)
4158 (home-page "http://samtools.sourceforge.net")
4159 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4161 "Samtools implements various utilities for post-processing nucleotide
4162 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4163 variant calling (in conjunction with bcftools), and a simple alignment
4165 (license license:expat)))
4167 (define-public samtools-0.1
4168 ;; This is the most recent version of the 0.1 line of samtools. The input
4169 ;; and output formats differ greatly from that used and produced by samtools
4170 ;; 1.x and is still used in many bioinformatics pipelines.
4171 (package (inherit samtools)
4177 (string-append "mirror://sourceforge/samtools/samtools/"
4178 version "/samtools-" version ".tar.bz2"))
4180 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4182 `(#:tests? #f ;no "check" target
4183 ,@(substitute-keyword-arguments (package-arguments samtools)
4184 ((#:make-flags flags)
4185 `(cons "LIBCURSES=-lncurses" ,flags))
4187 `(modify-phases ,phases
4189 (lambda* (#:key outputs #:allow-other-keys)
4190 (let ((bin (string-append
4191 (assoc-ref outputs "out") "/bin")))
4193 (copy-file "samtools"
4194 (string-append bin "/samtools")))))
4195 (delete 'patch-tests)
4196 (delete 'configure))))))))
4198 (define-public mosaik
4199 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4204 ;; There are no release tarballs nor tags.
4207 (url "https://github.com/wanpinglee/MOSAIK.git")
4209 (file-name (string-append name "-" version))
4212 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4213 (build-system gnu-build-system)
4215 `(#:tests? #f ; no tests
4216 #:make-flags (list "CC=gcc")
4218 (modify-phases %standard-phases
4220 (lambda _ (chdir "src") #t))
4222 (lambda* (#:key outputs #:allow-other-keys)
4223 (let ((bin (string-append (assoc-ref outputs "out")
4226 (copy-recursively "../bin" bin)
4231 (supported-systems '("x86_64-linux"))
4232 (home-page "https://code.google.com/p/mosaik-aligner/")
4233 (synopsis "Map nucleotide sequence reads to reference genomes")
4235 "MOSAIK is a program for mapping second and third-generation sequencing
4236 reads to a reference genome. MOSAIK can align reads generated by all the
4237 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4238 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4239 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4240 ;; code released into the public domain:
4241 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4242 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4243 (license (list license:gpl2+ license:public-domain)))))
4245 (define-public ngs-sdk
4253 (string-append "https://github.com/ncbi/ngs/archive/"
4255 (file-name (string-append name "-" version ".tar.gz"))
4258 "04y1fsmdnb5y86m3gg6f5g9wcscr6r25n7m8mdlcxy0i2q6w6cia"))))
4259 (build-system gnu-build-system)
4261 `(#:parallel-build? #f ; not supported
4262 #:tests? #f ; no "check" target
4266 (lambda* (#:key outputs #:allow-other-keys)
4267 (let ((out (assoc-ref outputs "out")))
4268 ;; The 'configure' script doesn't recognize things like
4269 ;; '--enable-fast-install'.
4270 (zero? (system* "./configure"
4271 (string-append "--build-prefix=" (getcwd) "/build")
4272 (string-append "--prefix=" out)))))
4275 (lambda _ (chdir "ngs-sdk") #t)
4276 %standard-phases))))
4277 (native-inputs `(("perl" ,perl)))
4278 ;; According to the test
4279 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4280 ;; in ngs-sdk/setup/konfigure.perl
4281 (supported-systems '("i686-linux" "x86_64-linux"))
4282 (home-page "https://github.com/ncbi/ngs")
4283 (synopsis "API for accessing Next Generation Sequencing data")
4285 "NGS is a domain-specific API for accessing reads, alignments and pileups
4286 produced from Next Generation Sequencing. The API itself is independent from
4287 any particular back-end implementation, and supports use of multiple back-ends
4289 (license license:public-domain)))
4291 (define-public java-ngs
4292 (package (inherit ngs-sdk)
4295 `(,@(substitute-keyword-arguments
4296 `(#:modules ((guix build gnu-build-system)
4300 ,@(package-arguments ngs-sdk))
4302 `(modify-phases ,phases
4303 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4305 `(("jdk" ,icedtea "jdk")
4306 ("ngs-sdk" ,ngs-sdk)))
4307 (synopsis "Java bindings for NGS SDK")))
4309 (define-public ncbi-vdb
4317 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4319 (file-name (string-append name "-" version ".tar.gz"))
4322 "0x1cg1x8vy0yjlkp0snc1533zcjhxqzqsaiwqk598n7vvw37n8lf"))))
4323 (build-system gnu-build-system)
4325 `(#:parallel-build? #f ; not supported
4326 #:tests? #f ; no "check" target
4330 (lambda* (#:key inputs outputs #:allow-other-keys)
4331 (let ((out (assoc-ref outputs "out")))
4332 ;; Override include path for libmagic
4333 (substitute* "setup/package.prl"
4334 (("name => 'magic', Include => '/usr/include'")
4335 (string-append "name=> 'magic', Include => '"
4336 (assoc-ref inputs "libmagic")
4339 ;; Install kdf5 library (needed by sra-tools)
4340 (substitute* "build/Makefile.install"
4341 (("LIBRARIES_TO_INSTALL =")
4342 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4344 (substitute* "build/Makefile.env"
4345 (("CFLAGS =" prefix)
4346 (string-append prefix "-msse2 ")))
4348 ;; The 'configure' script doesn't recognize things like
4349 ;; '--enable-fast-install'.
4352 (string-append "--build-prefix=" (getcwd) "/build")
4353 (string-append "--prefix=" (assoc-ref outputs "out"))
4354 (string-append "--debug")
4355 (string-append "--with-xml2-prefix="
4356 (assoc-ref inputs "libxml2"))
4357 (string-append "--with-ngs-sdk-prefix="
4358 (assoc-ref inputs "ngs-sdk"))
4359 (string-append "--with-ngs-java-prefix="
4360 (assoc-ref inputs "java-ngs"))
4361 (string-append "--with-hdf5-prefix="
4362 (assoc-ref inputs "hdf5"))))))
4364 'install 'install-interfaces
4365 (lambda* (#:key outputs #:allow-other-keys)
4366 ;; Install interface libraries. On i686 the interface libraries
4367 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4368 ;; architecture name ("i386") instead of the target system prefix
4370 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4371 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4372 ,(system->linux-architecture
4373 (or (%current-target-system)
4376 (string-append (assoc-ref outputs "out")
4378 ;; Install interface headers
4379 (copy-recursively "interfaces"
4380 (string-append (assoc-ref outputs "out")
4382 %standard-phases))))
4384 `(("libxml2" ,libxml2)
4385 ("ngs-sdk" ,ngs-sdk)
4386 ("java-ngs" ,java-ngs)
4389 (native-inputs `(("perl" ,perl)))
4390 ;; NCBI-VDB requires SSE capability.
4391 (supported-systems '("i686-linux" "x86_64-linux"))
4392 (home-page "https://github.com/ncbi/ncbi-vdb")
4393 (synopsis "Database engine for genetic information")
4395 "The NCBI-VDB library implements a highly compressed columnar data
4396 warehousing engine that is most often used to store genetic information.
4397 Databases are stored in a portable image within the file system, and can be
4398 accessed/downloaded on demand across HTTP.")
4399 (license license:public-domain)))
4401 (define-public plink
4409 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4410 version "-src.zip"))
4412 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4413 (patches (search-patches "plink-1.07-unclobber-i.patch"
4414 "plink-endian-detection.patch"))))
4415 (build-system gnu-build-system)
4417 '(#:tests? #f ;no "check" target
4418 #:make-flags (list (string-append "LIB_LAPACK="
4419 (assoc-ref %build-inputs "lapack")
4420 "/lib/liblapack.so")
4423 ;; disable phoning home
4426 (modify-phases %standard-phases
4427 ;; no "configure" script
4430 (lambda* (#:key outputs #:allow-other-keys)
4431 (let ((bin (string-append (assoc-ref outputs "out")
4433 (install-file "plink" bin)
4437 ("lapack" ,lapack)))
4439 `(("unzip" ,unzip)))
4440 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4441 (synopsis "Whole genome association analysis toolset")
4443 "PLINK is a whole genome association analysis toolset, designed to
4444 perform a range of basic, large-scale analyses in a computationally efficient
4445 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4446 so there is no support for steps prior to this (e.g. study design and
4447 planning, generating genotype or CNV calls from raw data). Through
4448 integration with gPLINK and Haploview, there is some support for the
4449 subsequent visualization, annotation and storage of results.")
4450 ;; Code is released under GPLv2, except for fisher.h, which is under
4452 (license (list license:gpl2 license:lgpl2.1+))))
4454 (define-public smithlab-cpp
4455 (let ((revision "1")
4456 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4458 (name "smithlab-cpp")
4459 (version (string-append "0." revision "." (string-take commit 7)))
4463 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4465 (file-name (string-append name "-" version "-checkout"))
4468 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4469 (build-system gnu-build-system)
4471 `(#:modules ((guix build gnu-build-system)
4474 #:tests? #f ;no "check" target
4476 (modify-phases %standard-phases
4477 (add-after 'unpack 'use-samtools-headers
4479 (substitute* '("SAM.cpp"
4481 (("sam.h") "samtools/sam.h"))
4484 (lambda* (#:key outputs #:allow-other-keys)
4485 (let* ((out (assoc-ref outputs "out"))
4486 (lib (string-append out "/lib"))
4487 (include (string-append out "/include/smithlab-cpp")))
4490 (for-each (cut install-file <> lib)
4491 (find-files "." "\\.o$"))
4492 (for-each (cut install-file <> include)
4493 (find-files "." "\\.hpp$")))
4495 (delete 'configure))))
4497 `(("samtools" ,samtools-0.1)
4499 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4500 (synopsis "C++ helper library for functions used in Smith lab projects")
4502 "Smithlab CPP is a C++ library that includes functions used in many of
4503 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4504 structures, classes for genomic regions, mapped sequencing reads, etc.")
4505 (license license:gpl3+))))
4507 (define-public preseq
4513 (uri (string-append "https://github.com/smithlabcode/"
4514 "preseq/archive/v" version ".tar.gz"))
4515 (file-name (string-append name "-" version ".tar.gz"))
4517 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4518 (modules '((guix build utils)))
4520 ;; Remove bundled samtools.
4521 '(delete-file-recursively "samtools"))))
4522 (build-system gnu-build-system)
4524 `(#:tests? #f ;no "check" target
4526 (modify-phases %standard-phases
4527 (delete 'configure))
4529 (list (string-append "PREFIX="
4530 (assoc-ref %outputs "out"))
4531 (string-append "LIBBAM="
4532 (assoc-ref %build-inputs "samtools")
4534 (string-append "SMITHLAB_CPP="
4535 (assoc-ref %build-inputs "smithlab-cpp")
4538 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4541 ("samtools" ,samtools-0.1)
4542 ("smithlab-cpp" ,smithlab-cpp)
4544 (home-page "http://smithlabresearch.org/software/preseq/")
4545 (synopsis "Program for analyzing library complexity")
4547 "The preseq package is aimed at predicting and estimating the complexity
4548 of a genomic sequencing library, equivalent to predicting and estimating the
4549 number of redundant reads from a given sequencing depth and how many will be
4550 expected from additional sequencing using an initial sequencing experiment.
4551 The estimates can then be used to examine the utility of further sequencing,
4552 optimize the sequencing depth, or to screen multiple libraries to avoid low
4553 complexity samples.")
4554 (license license:gpl3+)))
4556 (define-public python-screed
4558 (name "python-screed")
4563 (uri (pypi-uri "screed" version))
4566 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4567 (build-system python-build-system)
4570 (modify-phases %standard-phases
4573 (setenv "PYTHONPATH"
4574 (string-append (getenv "PYTHONPATH") ":."))
4575 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4577 `(("python-nose" ,python-nose)))
4579 `(("python-bz2file" ,python-bz2file)))
4580 (home-page "http://github.com/dib-lab/screed/")
4581 (synopsis "Short read sequence database utilities")
4582 (description "Screed parses FASTA and FASTQ files and generates databases.
4583 Values such as sequence name, sequence description, sequence quality and the
4584 sequence itself can be retrieved from these databases.")
4585 (license license:bsd-3)))
4587 (define-public python2-screed
4588 (let ((base (package-with-python2 (strip-python2-variant python-screed))))
4591 (native-inputs `(("python2-setuptools" ,python2-setuptools)
4592 ,@(package-native-inputs base))))))
4594 (define-public sra-tools
4602 (string-append "https://github.com/ncbi/sra-tools/archive/"
4604 (file-name (string-append name "-" version ".tar.gz"))
4607 "13paw7bq6y47d2pl0ac5gpgcqp1xsy1g7v1fwysm3hr8lb2dck17"))))
4608 (build-system gnu-build-system)
4610 `(#:parallel-build? #f ; not supported
4611 #:tests? #f ; no "check" target
4613 (list (string-append "VDB_LIBDIR="
4614 (assoc-ref %build-inputs "ncbi-vdb")
4615 ,(if (string-prefix? "x86_64"
4616 (or (%current-target-system)
4623 (lambda* (#:key inputs outputs #:allow-other-keys)
4624 ;; The build system expects a directory containing the sources and
4625 ;; raw build output of ncbi-vdb, including files that are not
4626 ;; installed. Since we are building against an installed version of
4627 ;; ncbi-vdb, the following modifications are needed.
4628 (substitute* "setup/konfigure.perl"
4629 ;; Make the configure script look for the "ilib" directory of
4630 ;; "ncbi-vdb" without first checking for the existence of a
4631 ;; matching library in its "lib" directory.
4632 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
4633 "my $f = File::Spec->catdir($ilibdir, $ilib);")
4634 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
4635 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
4636 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
4639 (substitute* "tools/copycat/Makefile"
4640 (("smagic-static") "lmagic"))
4642 ;; The 'configure' script doesn't recognize things like
4643 ;; '--enable-fast-install'.
4646 (string-append "--build-prefix=" (getcwd) "/build")
4647 (string-append "--prefix=" (assoc-ref outputs "out"))
4648 (string-append "--debug")
4649 (string-append "--with-fuse-prefix="
4650 (assoc-ref inputs "fuse"))
4651 (string-append "--with-magic-prefix="
4652 (assoc-ref inputs "libmagic"))
4653 ;; TODO: building with libxml2 fails with linker errors
4654 ;; (string-append "--with-xml2-prefix="
4655 ;; (assoc-ref inputs "libxml2"))
4656 (string-append "--with-ncbi-vdb-sources="
4657 (assoc-ref inputs "ncbi-vdb"))
4658 (string-append "--with-ncbi-vdb-build="
4659 (assoc-ref inputs "ncbi-vdb"))
4660 (string-append "--with-ngs-sdk-prefix="
4661 (assoc-ref inputs "ngs-sdk"))
4662 (string-append "--with-hdf5-prefix="
4663 (assoc-ref inputs "hdf5")))))
4665 (native-inputs `(("perl" ,perl)))
4667 `(("ngs-sdk" ,ngs-sdk)
4668 ("ncbi-vdb" ,ncbi-vdb)
4673 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
4674 (synopsis "Tools and libraries for reading and writing sequencing data")
4676 "The SRA Toolkit from NCBI is a collection of tools and libraries for
4677 reading of sequencing files from the Sequence Read Archive (SRA) database and
4678 writing files into the .sra format.")
4679 (license license:public-domain)))
4681 (define-public seqan
4687 (uri (string-append "http://packages.seqan.de/seqan-library/"
4688 "seqan-library-" version ".tar.bz2"))
4691 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
4692 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
4693 ;; makes sense to split the outputs.
4694 (outputs '("out" "doc"))
4695 (build-system trivial-build-system)
4697 `(#:modules ((guix build utils))
4700 (use-modules (guix build utils))
4701 (let ((tar (assoc-ref %build-inputs "tar"))
4702 (bzip (assoc-ref %build-inputs "bzip2"))
4703 (out (assoc-ref %outputs "out"))
4704 (doc (assoc-ref %outputs "doc")))
4705 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
4706 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
4707 (chdir (string-append "seqan-library-" ,version))
4708 (copy-recursively "include" (string-append out "/include"))
4709 (copy-recursively "share" (string-append doc "/share"))))))
4711 `(("source" ,source)
4714 (home-page "http://www.seqan.de")
4715 (synopsis "Library for nucleotide sequence analysis")
4717 "SeqAn is a C++ library of efficient algorithms and data structures for
4718 the analysis of sequences with the focus on biological data. It contains
4719 algorithms and data structures for string representation and their
4720 manipulation, online and indexed string search, efficient I/O of
4721 bioinformatics file formats, sequence alignment, and more.")
4722 (license license:bsd-3)))
4724 (define-public seqmagick
4732 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
4736 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
4737 (build-system python-build-system)
4739 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
4740 `(#:python ,python-2
4742 (modify-phases %standard-phases
4743 ;; Current test in setup.py does not work as of 0.6.1,
4744 ;; so use nose to run tests instead for now. See
4745 ;; https://github.com/fhcrc/seqmagick/issues/55
4746 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
4748 ;; biopython-1.66 is required due to
4749 ;; https://github.com/fhcrc/seqmagick/issues/59
4750 ;; When that issue is resolved the 'python2-biopython-1.66' package
4751 ;; should be removed.
4752 `(("python-biopython" ,python2-biopython-1.66)))
4754 `(("python-setuptools" ,python2-setuptools)
4755 ("python-nose" ,python2-nose)))
4756 (home-page "http://github.com/fhcrc/seqmagick")
4757 (synopsis "Tools for converting and modifying sequence files")
4759 "Bioinformaticians often have to convert sequence files between formats
4760 and do little manipulations on them, and it's not worth writing scripts for
4761 that. Seqmagick is a utility to expose the file format conversion in
4762 BioPython in a convenient way. Instead of having a big mess of scripts, there
4763 is one that takes arguments.")
4764 (license license:gpl3)))
4766 (define-public seqtk
4773 "https://github.com/lh3/seqtk/archive/v"
4775 (file-name (string-append name "-" version ".tar.gz"))
4778 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
4779 (modules '((guix build utils)))
4782 ;; Remove extraneous header files, as is done in the seqtk
4784 (for-each (lambda (file) (delete-file file))
4785 (list "ksort.h" "kstring.h" "kvec.h"))
4787 (build-system gnu-build-system)
4790 (modify-phases %standard-phases
4793 ;; There are no tests, so we just run a sanity check.
4794 (lambda _ (zero? (system* "./seqtk" "seq"))))
4796 (lambda* (#:key outputs #:allow-other-keys)
4797 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4798 (install-file "seqtk" bin)))))))
4801 (home-page "https://github.com/lh3/seqtk")
4802 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
4804 "Seqtk is a fast and lightweight tool for processing sequences in the
4805 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
4806 optionally compressed by gzip.")
4807 (license license:expat)))
4809 (define-public snap-aligner
4811 (name "snap-aligner")
4812 (version "1.0beta.18")
4816 "https://github.com/amplab/snap/archive/v"
4818 (file-name (string-append name "-" version ".tar.gz"))
4821 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
4822 (build-system gnu-build-system)
4825 (modify-phases %standard-phases
4827 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
4829 (lambda* (#:key outputs #:allow-other-keys)
4830 (let* ((out (assoc-ref outputs "out"))
4831 (bin (string-append out "/bin")))
4833 (install-file "snap-aligner" bin)
4834 (install-file "SNAPCommand" bin)
4838 (home-page "http://snap.cs.berkeley.edu/")
4839 (synopsis "Short read DNA sequence aligner")
4841 "SNAP is a fast and accurate aligner for short DNA reads. It is
4842 optimized for modern read lengths of 100 bases or higher, and takes advantage
4843 of these reads to align data quickly through a hash-based indexing scheme.")
4844 ;; 32-bit systems are not supported by the unpatched code.
4845 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
4846 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
4847 ;; systems without a lot of memory cannot make good use of this program.
4848 (supported-systems '("x86_64-linux"))
4849 (license license:asl2.0)))
4851 (define-public sortmerna
4859 "https://github.com/biocore/sortmerna/archive/"
4861 (file-name (string-append name "-" version ".tar.gz"))
4864 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
4865 (build-system gnu-build-system)
4866 (outputs '("out" ;for binaries
4867 "db")) ;for sequence databases
4870 (modify-phases %standard-phases
4872 (lambda* (#:key outputs #:allow-other-keys)
4873 (let* ((out (assoc-ref outputs "out"))
4874 (bin (string-append out "/bin"))
4875 (db (assoc-ref outputs "db"))
4877 (string-append db "/share/sortmerna/rRNA_databases")))
4878 (install-file "sortmerna" bin)
4879 (install-file "indexdb_rna" bin)
4880 (for-each (lambda (file)
4881 (install-file file share))
4882 (find-files "rRNA_databases" ".*fasta"))
4886 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
4887 (synopsis "Biological sequence analysis tool for NGS reads")
4889 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
4890 and operational taxonomic unit (OTU) picking of next generation
4891 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
4892 allows for fast and sensitive analyses of nucleotide sequences. The main
4893 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
4894 (license license:lgpl3)))
4902 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
4904 (file-name (string-append name "-" version ".tar.gz"))
4907 "0xjlsm4p9flln111hv4xx7xy94c2nl53zvdvbk9winmiradjsdra"))
4908 (modules '((guix build utils)))
4911 (substitute* "source/Makefile"
4913 ;; Remove pre-built binaries and bundled htslib sources.
4914 (delete-file-recursively "bin/MacOSX_x86_64")
4915 (delete-file-recursively "bin/Linux_x86_64")
4916 (delete-file-recursively "source/htslib")
4918 (build-system gnu-build-system)
4920 '(#:tests? #f ;no check target
4921 #:make-flags '("STAR")
4923 (modify-phases %standard-phases
4924 (add-after 'unpack 'enter-source-dir
4925 (lambda _ (chdir "source") #t))
4926 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
4928 (substitute* "Makefile"
4929 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
4931 (substitute* '("BAMfunctions.cpp"
4936 "bamRemoveDuplicates.cpp")
4937 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
4938 (string-append "#include <" header ">")))
4939 (substitute* "IncludeDefine.h"
4940 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
4941 (string-append "<" header ">")))
4944 (lambda* (#:key outputs #:allow-other-keys)
4945 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4946 (install-file "STAR" bin))
4948 (delete 'configure))))
4950 `(("vim" ,vim))) ; for xxd
4952 `(("htslib" ,htslib)
4954 (home-page "https://github.com/alexdobin/STAR")
4955 (synopsis "Universal RNA-seq aligner")
4957 "The Spliced Transcripts Alignment to a Reference (STAR) software is
4958 based on a previously undescribed RNA-seq alignment algorithm that uses
4959 sequential maximum mappable seed search in uncompressed suffix arrays followed
4960 by seed clustering and stitching procedure. In addition to unbiased de novo
4961 detection of canonical junctions, STAR can discover non-canonical splices and
4962 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
4964 ;; Only 64-bit systems are supported according to the README.
4965 (supported-systems '("x86_64-linux" "mips64el-linux"))
4966 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
4967 (license license:gpl3+)))
4969 (define-public subread
4975 (uri (string-append "mirror://sourceforge/subread/subread-"
4976 version "/subread-" version "-source.tar.gz"))
4979 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
4980 (build-system gnu-build-system)
4982 `(#:tests? #f ;no "check" target
4983 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
4984 ;; optimizations by default, so we override these flags such that x86_64
4985 ;; flags are only added when the build target is an x86_64 system.
4987 (list (let ((system ,(or (%current-target-system)
4989 (flags '("-ggdb" "-fomit-frame-pointer"
4990 "-ffast-math" "-funroll-loops"
4991 "-fmessage-length=0"
4992 "-O9" "-Wall" "-DMAKE_FOR_EXON"
4994 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
4995 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
4996 (if (string-prefix? "x86_64" system)
4997 (string-append "CCFLAGS=" (string-join (append flags flags64)))
4998 (string-append "CCFLAGS=" (string-join flags))))
4999 "-f" "Makefile.Linux"
5000 "CC=gcc ${CCFLAGS}")
5004 (lambda _ (chdir "src") #t)
5007 (lambda* (#:key outputs #:allow-other-keys)
5008 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5010 (copy-recursively "../bin" bin)))
5011 ;; no "configure" script
5012 (alist-delete 'configure %standard-phases)))))
5013 (inputs `(("zlib" ,zlib)))
5014 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5015 (synopsis "Tool kit for processing next-gen sequencing data")
5017 "The subread package contains the following tools: subread aligner, a
5018 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5019 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5020 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5021 against local background noises.")
5022 (license license:gpl3+)))
5024 (define-public stringtie
5030 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5031 "stringtie-" version ".tar.gz"))
5034 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5035 (modules '((guix build utils)))
5038 (delete-file-recursively "samtools-0.1.18")
5040 (build-system gnu-build-system)
5042 `(#:tests? #f ;no test suite
5044 (modify-phases %standard-phases
5045 ;; no configure script
5047 (add-before 'build 'use-system-samtools
5049 (substitute* "Makefile"
5050 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5052 (substitute* '("gclib/GBam.h"
5054 (("#include \"(bam|sam|kstring).h\"" _ header)
5055 (string-append "#include <samtools/" header ".h>")))
5058 (lambda* (#:key outputs #:allow-other-keys)
5059 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5060 (install-file "stringtie" bin)
5063 `(("samtools" ,samtools-0.1)
5065 (home-page "http://ccb.jhu.edu/software/stringtie/")
5066 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5068 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5069 alignments into potential transcripts. It uses a novel network flow algorithm
5070 as well as an optional de novo assembly step to assemble and quantitate
5071 full-length transcripts representing multiple splice variants for each gene
5072 locus. Its input can include not only the alignments of raw reads used by
5073 other transcript assemblers, but also alignments of longer sequences that have
5074 been assembled from those reads. To identify differentially expressed genes
5075 between experiments, StringTie's output can be processed either by the
5076 Cuffdiff or Ballgown programs.")
5077 (license license:artistic2.0)))
5079 (define-public vcftools
5086 "https://github.com/vcftools/vcftools/releases/download/v"
5087 version "/vcftools-" version ".tar.gz"))
5090 "10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
5091 (build-system gnu-build-system)
5093 `(#:tests? #f ; no "check" target
5095 "CFLAGS=-O2" ; override "-m64" flag
5096 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5097 (string-append "MANDIR=" (assoc-ref %outputs "out")
5098 "/share/man/man1"))))
5100 `(("pkg-config" ,pkg-config)))
5104 (home-page "https://vcftools.github.io/")
5105 (synopsis "Tools for working with VCF files")
5107 "VCFtools is a program package designed for working with VCF files, such
5108 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5109 provide easily accessible methods for working with complex genetic variation
5110 data in the form of VCF files.")
5111 ;; The license is declared as LGPLv3 in the README and
5112 ;; at https://vcftools.github.io/license.html
5113 (license license:lgpl3)))
5115 (define-public infernal
5121 (uri (string-append "http://eddylab.org/software/infernal/"
5122 "infernal-" version ".tar.gz"))
5125 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5126 (build-system gnu-build-system)
5128 `(("perl" ,perl))) ; for tests
5129 (home-page "http://eddylab.org/infernal/")
5130 (synopsis "Inference of RNA alignments")
5131 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5132 searching DNA sequence databases for RNA structure and sequence similarities.
5133 It is an implementation of a special case of profile stochastic context-free
5134 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5135 profile, but it scores a combination of sequence consensus and RNA secondary
5136 structure consensus, so in many cases, it is more capable of identifying RNA
5137 homologs that conserve their secondary structure more than their primary
5139 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5140 (supported-systems '("i686-linux" "x86_64-linux"))
5141 (license license:bsd-3)))
5143 (define-public r-vegan
5150 (uri (cran-uri "vegan" version))
5153 "0i0c7rc0nzgbysd1nlxzxd2rvy75qcnw3yc7nggzqjzzj5d7yzsd"))))
5154 (build-system r-build-system)
5157 (modify-phases %standard-phases
5158 (add-after 'unpack 'revert-test-deletion
5159 ;; The distributed sources do not include tests with the CRAN
5160 ;; package. Here we revert the commit
5161 ;; `591d0e8ba1deaaf82445474ec6619c0b43db4e63' which deletes these
5162 ;; tests. There are plans to not delete tests in future as
5163 ;; documented at https://github.com/vegandevs/vegan/issues/181.
5164 (lambda* (#:key inputs #:allow-other-keys)
5166 (system* "patch" "-R" "-p1" "-i"
5167 (assoc-ref inputs "r-vegan-delete-tests-patch"))))))))
5169 `(("gfortran" ,gfortran)
5170 ("r-knitr" ,r-knitr)
5171 ("r-vegan-delete-tests-patch"
5175 "https://github.com/vegandevs/vegan/commit/"
5176 "591d0e8ba1deaaf82445474ec6619c0b43db4e63.patch"))
5179 "0b1bi7y4jjdl3ph721vm9apm51dr2z9piwvhy4355sf2b4kyyj5a"))))))
5181 `(("r-cluster" ,r-cluster)
5182 ("r-lattice" ,r-lattice)
5184 ("r-permute" ,r-permute)))
5185 (home-page "https://cran.r-project.org/web/packages/vegan")
5186 (synopsis "Functions for community ecology")
5188 "The vegan package provides tools for descriptive community ecology. It
5189 has most basic functions of diversity analysis, community ordination and
5190 dissimilarity analysis. Most of its multivariate tools can be used for other
5191 data types as well.")
5192 (license license:gpl2+)))
5194 (define-public r-annotate
5201 (uri (bioconductor-uri "annotate" version))
5204 "1fd2csq7dcs2gwndgwdx2nwkymz8gsmlnqqzv3p0vjjsvvq5n2a8"))))
5205 (build-system r-build-system)
5207 `(("r-annotationdbi" ,r-annotationdbi)
5208 ("r-biobase" ,r-biobase)
5209 ("r-biocgenerics" ,r-biocgenerics)
5212 ("r-xtable" ,r-xtable)))
5214 "http://bioconductor.org/packages/annotate")
5215 (synopsis "Annotation for microarrays")
5216 (description "This package provides R enviroments for the annotation of
5218 (license license:artistic2.0)))
5220 (define-public r-geneplotter
5222 (name "r-geneplotter")
5227 (uri (bioconductor-uri "geneplotter" version))
5230 "1p6yvxi243irhjxwm97hp73abhwampj0myyf8z00ij166674pc7h"))))
5231 (build-system r-build-system)
5233 `(("r-annotate" ,r-annotate)
5234 ("r-annotationdbi" ,r-annotationdbi)
5235 ("r-biobase" ,r-biobase)
5236 ("r-biocgenerics" ,r-biocgenerics)
5237 ("r-lattice" ,r-lattice)
5238 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5239 (home-page "http://bioconductor.org/packages/geneplotter")
5240 (synopsis "Graphics functions for genomic data")
5242 "This package provides functions for plotting genomic data.")
5243 (license license:artistic2.0)))
5245 (define-public r-genefilter
5247 (name "r-genefilter")
5252 (uri (bioconductor-uri "genefilter" version))
5255 "1vzgciqd09csqcw9qync8blsv51ylrd86a65iadgyy6j26g01fwd"))))
5256 (build-system r-build-system)
5258 `(("gfortran" ,gfortran)))
5260 `(("r-annotate" ,r-annotate)
5261 ("r-annotationdbi" ,r-annotationdbi)
5262 ("r-biobase" ,r-biobase)
5263 ("r-s4vectors" ,r-s4vectors)))
5264 (home-page "http://bioconductor.org/packages/genefilter")
5265 (synopsis "Filter genes from high-throughput experiments")
5267 "This package provides basic functions for filtering genes from
5268 high-throughput sequencing experiments.")
5269 (license license:artistic2.0)))
5271 (define-public r-deseq2
5278 (uri (bioconductor-uri "DESeq2" version))
5281 "0kq06jy4xg5ii3a9l62f17kirsfx0gsiwq6mhiy985cqzpdn893g"))))
5282 (properties `((upstream-name . "DESeq2")))
5283 (build-system r-build-system)
5286 (modify-phases %standard-phases
5287 (add-after 'unpack 'link-against-armadillo
5289 (substitute* "src/Makevars"
5290 (("PKG_LIBS =" prefix)
5291 (string-append prefix "-larmadillo"))))))))
5293 `(("r-biobase" ,r-biobase)
5294 ("r-biocgenerics" ,r-biocgenerics)
5295 ("r-biocparallel" ,r-biocparallel)
5296 ("r-genefilter" ,r-genefilter)
5297 ("r-geneplotter" ,r-geneplotter)
5298 ("r-genomicranges" ,r-genomicranges)
5299 ("r-ggplot2" ,r-ggplot2)
5300 ("r-hmisc" ,r-hmisc)
5301 ("r-iranges" ,r-iranges)
5302 ("r-locfit" ,r-locfit)
5304 ("r-rcpparmadillo" ,r-rcpparmadillo)
5305 ("r-s4vectors" ,r-s4vectors)
5306 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5307 (home-page "http://bioconductor.org/packages/DESeq2")
5308 (synopsis "Differential gene expression analysis")
5310 "This package provides functions to estimate variance-mean dependence in
5311 count data from high-throughput nucleotide sequencing assays and test for
5312 differential expression based on a model using the negative binomial
5314 (license license:lgpl3+)))
5316 (define-public r-annotationforge
5318 (name "r-annotationforge")
5323 (uri (bioconductor-uri "AnnotationForge" version))
5326 "02msyb9p3hywrryx00zpjkjl126mrv827i1ah1092s0cplm6xxvf"))))
5328 `((upstream-name . "AnnotationForge")))
5329 (build-system r-build-system)
5331 `(("r-annotationdbi" ,r-annotationdbi)
5332 ("r-biobase" ,r-biobase)
5333 ("r-biocgenerics" ,r-biocgenerics)
5335 ("r-rcurl" ,r-rcurl)
5336 ("r-rsqlite" ,r-rsqlite)
5337 ("r-s4vectors" ,r-s4vectors)
5339 (home-page "http://bioconductor.org/packages/AnnotationForge")
5340 (synopsis "Code for building annotation database packages")
5342 "This package provides code for generating Annotation packages and their
5343 databases. Packages produced are intended to be used with AnnotationDbi.")
5344 (license license:artistic2.0)))
5346 (define-public r-rbgl
5353 (uri (bioconductor-uri "RBGL" version))
5356 "1q14m8w6ih56v680kf3d9wh1qbgp7af33kz3cxafdf1vvzx9km08"))))
5357 (properties `((upstream-name . "RBGL")))
5358 (build-system r-build-system)
5359 (propagated-inputs `(("r-graph" ,r-graph)))
5360 (home-page "http://www.bioconductor.org/packages/RBGL")
5361 (synopsis "Interface to the Boost graph library")
5363 "This package provides a fairly extensive and comprehensive interface to
5364 the graph algorithms contained in the Boost library.")
5365 (license license:artistic2.0)))
5367 (define-public r-gseabase
5374 (uri (bioconductor-uri "GSEABase" version))
5377 "0l2x7yj7lfb0m2dmsav5ib026dikpgl4crdckrnj776yy08lgxpj"))))
5378 (properties `((upstream-name . "GSEABase")))
5379 (build-system r-build-system)
5381 `(("r-annotate" ,r-annotate)
5382 ("r-annotationdbi" ,r-annotationdbi)
5383 ("r-biobase" ,r-biobase)
5384 ("r-biocgenerics" ,r-biocgenerics)
5385 ("r-graph" ,r-graph)
5387 (home-page "http://bioconductor.org/packages/GSEABase")
5388 (synopsis "Gene set enrichment data structures and methods")
5390 "This package provides classes and methods to support @dfn{Gene Set
5391 Enrichment Analysis} (GSEA).")
5392 (license license:artistic2.0)))
5394 (define-public r-category
5401 (uri (bioconductor-uri "Category" version))
5404 "16ncwz7b4y48k0p3fvbrbmvf7nfz63li9ysgcl8kp9kl4hg7llng"))))
5405 (properties `((upstream-name . "Category")))
5406 (build-system r-build-system)
5408 `(("r-annotate" ,r-annotate)
5409 ("r-annotationdbi" ,r-annotationdbi)
5410 ("r-biobase" ,r-biobase)
5411 ("r-biocgenerics" ,r-biocgenerics)
5412 ("r-genefilter" ,r-genefilter)
5413 ("r-graph" ,r-graph)
5414 ("r-gseabase" ,r-gseabase)
5415 ("r-matrix" ,r-matrix)
5417 ("r-rsqlite" ,r-rsqlite)))
5418 (home-page "http://bioconductor.org/packages/Category")
5419 (synopsis "Category analysis")
5421 "This package provides a collection of tools for performing category
5423 (license license:artistic2.0)))
5425 (define-public r-gostats
5432 (uri (bioconductor-uri "GOstats" version))
5435 "0g2czm94zhzx92z7y2r4mjfxhwml7bhab2db6820ks8nkw1zvr9n"))))
5436 (properties `((upstream-name . "GOstats")))
5437 (build-system r-build-system)
5439 `(("r-annotate" ,r-annotate)
5440 ("r-annotationdbi" ,r-annotationdbi)
5441 ("r-annotationforge" ,r-annotationforge)
5442 ("r-biobase" ,r-biobase)
5443 ("r-category" ,r-category)
5444 ("r-go-db" ,r-go-db)
5445 ("r-graph" ,r-graph)
5446 ("r-rbgl" ,r-rbgl)))
5447 (home-page "http://bioconductor.org/packages/GOstats")
5448 (synopsis "Tools for manipulating GO and microarrays")
5450 "This package provides a set of tools for interacting with GO and
5451 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5452 testing and other simple calculations.")
5453 (license license:artistic2.0)))
5455 (define-public r-shortread
5457 (name "r-shortread")
5462 (uri (bioconductor-uri "ShortRead" version))
5465 "0mjdlg92x5qw4x2djc4dv5lxwl7ai6ix56nnf86zr07jk8vc7yls"))))
5466 (properties `((upstream-name . "ShortRead")))
5467 (build-system r-build-system)
5471 `(("r-biobase" ,r-biobase)
5472 ("r-biocgenerics" ,r-biocgenerics)
5473 ("r-biocparallel" ,r-biocparallel)
5474 ("r-biostrings" ,r-biostrings)
5475 ("r-genomeinfodb" ,r-genomeinfodb)
5476 ("r-genomicalignments" ,r-genomicalignments)
5477 ("r-genomicranges" ,r-genomicranges)
5478 ("r-hwriter" ,r-hwriter)
5479 ("r-iranges" ,r-iranges)
5480 ("r-lattice" ,r-lattice)
5481 ("r-latticeextra" ,r-latticeextra)
5482 ("r-rsamtools" ,r-rsamtools)
5483 ("r-s4vectors" ,r-s4vectors)
5484 ("r-xvector" ,r-xvector)
5485 ("r-zlibbioc" ,r-zlibbioc)))
5486 (home-page "http://bioconductor.org/packages/ShortRead")
5487 (synopsis "FASTQ input and manipulation tools")
5489 "This package implements sampling, iteration, and input of FASTQ files.
5490 It includes functions for filtering and trimming reads, and for generating a
5491 quality assessment report. Data are represented as
5492 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5493 purposes. The package also contains legacy support for early single-end,
5494 ungapped alignment formats.")
5495 (license license:artistic2.0)))
5497 (define-public r-systempiper
5499 (name "r-systempiper")
5504 (uri (bioconductor-uri "systemPipeR" version))
5507 "0hyi841w8fm2yzpm6lwqi3jz5kc8ny8dy5p29dxynzaw5bpjw56d"))))
5508 (properties `((upstream-name . "systemPipeR")))
5509 (build-system r-build-system)
5511 `(("r-annotate" ,r-annotate)
5512 ("r-batchjobs" ,r-batchjobs)
5513 ("r-biocgenerics" ,r-biocgenerics)
5514 ("r-biostrings" ,r-biostrings)
5515 ("r-deseq2" ,r-deseq2)
5516 ("r-edger" ,r-edger)
5517 ("r-genomicfeatures" ,r-genomicfeatures)
5518 ("r-genomicranges" ,r-genomicranges)
5519 ("r-ggplot2" ,r-ggplot2)
5520 ("r-go-db" ,r-go-db)
5521 ("r-gostats" ,r-gostats)
5522 ("r-limma" ,r-limma)
5523 ("r-pheatmap" ,r-pheatmap)
5524 ("r-rjson" ,r-rjson)
5525 ("r-rsamtools" ,r-rsamtools)
5526 ("r-shortread" ,r-shortread)
5527 ("r-summarizedexperiment" ,r-summarizedexperiment)
5528 ("r-variantannotation" ,r-variantannotation)))
5529 (home-page "https://github.com/tgirke/systemPipeR")
5530 (synopsis "Next generation sequencing workflow and reporting environment")
5532 "This R package provides tools for building and running automated
5533 end-to-end analysis workflows for a wide range of @dfn{next generation
5534 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5535 Important features include a uniform workflow interface across different NGS
5536 applications, automated report generation, and support for running both R and
5537 command-line software, such as NGS aligners or peak/variant callers, on local
5538 computers or compute clusters. Efficient handling of complex sample sets and
5539 experimental designs is facilitated by a consistently implemented sample
5540 annotation infrastructure.")
5541 (license license:artistic2.0)))
5543 (define-public r-grohmm
5550 (uri (bioconductor-uri "groHMM" version))
5553 "0d91nyhqbi5hv3mgmr2z0g29wg2md26g0hyv5mgapmz20cd9zi4y"))))
5554 (properties `((upstream-name . "groHMM")))
5555 (build-system r-build-system)
5557 `(("r-genomeinfodb" ,r-genomeinfodb)
5558 ("r-genomicalignments" ,r-genomicalignments)
5559 ("r-genomicranges" ,r-genomicranges)
5560 ("r-iranges" ,r-iranges)
5561 ("r-rtracklayer" ,r-rtracklayer)
5562 ("r-s4vectors" ,r-s4vectors)))
5563 (home-page "https://github.com/Kraus-Lab/groHMM")
5564 (synopsis "GRO-seq analysis pipeline")
5566 "This package provides a pipeline for the analysis of GRO-seq data.")
5567 (license license:gpl3+)))
5569 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
5571 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
5575 ;; We cannot use bioconductor-uri here because this tarball is
5576 ;; located under "data/annotation/" instead of "bioc/".
5577 (uri (string-append "http://bioconductor.org/packages/"
5578 "release/data/annotation/src/contrib"
5579 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
5583 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
5585 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
5586 (build-system r-build-system)
5587 ;; As this package provides little more than a very large data file it
5588 ;; doesn't make sense to build substitutes.
5589 (arguments `(#:substitutable? #f))
5591 `(("r-genomicfeatures" ,r-genomicfeatures)))
5593 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
5594 (synopsis "Annotation package for human genome in TxDb format")
5596 "This package provides an annotation database of Homo sapiens genome
5597 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
5598 track. The database is exposed as a @code{TxDb} object.")
5599 (license license:artistic2.0)))
5601 (define-public vsearch
5609 "https://github.com/torognes/vsearch/archive/v"
5611 (file-name (string-append name "-" version ".tar.gz"))
5614 "1r8fk3whkil348y5hfsd4r56qjmchhq4nxm6s7ra5rlisw0mf9fy"))
5615 (modules '((guix build utils)))
5618 ;; Remove bundled cityhash and '-mtune=native'.
5619 (substitute* "src/Makefile.am"
5620 (("^AM_CXXFLAGS=-I\\$\\{srcdir\\}/cityhash \
5621 -O3 -mtune=native -Wall -Wsign-compare")
5622 (string-append "AM_CXXFLAGS=-lcityhash"
5623 " -O3 -Wall -Wsign-compare"))
5624 (("^__top_builddir__bin_vsearch_SOURCES = city.h \\\\")
5625 "__top_builddir__bin_vsearch_SOURCES = \\")
5626 (("^city.h \\\\") "\\")
5627 (("^citycrc.h \\\\") "\\")
5628 (("^libcityhash_a.*") "")
5629 (("noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a \
5631 "noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a")
5632 (("__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
5633 libcpu_sse2.a libcityhash.a")
5634 "__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
5635 libcpu_sse2.a -lcityhash"))
5636 (substitute* "src/vsearch.h"
5637 (("^\\#include \"city.h\"") "#include <city.h>")
5638 (("^\\#include \"citycrc.h\"") "#include <citycrc.h>"))
5639 (delete-file "src/city.h")
5640 (delete-file "src/citycrc.h")
5641 (delete-file "src/city.cc")
5643 (build-system gnu-build-system)
5646 (modify-phases %standard-phases
5647 (add-before 'configure 'autogen
5648 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
5652 ("cityhash" ,cityhash)))
5654 `(("autoconf" ,autoconf)
5655 ("automake" ,automake)))
5656 (synopsis "Sequence search tools for metagenomics")
5658 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
5659 dereplication, pairwise alignment, shuffling, subsampling, sorting and
5660 masking. The tool takes advantage of parallelism in the form of SIMD
5661 vectorization as well as multiple threads to perform accurate alignments at
5662 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
5663 Needleman-Wunsch).")
5664 (home-page "https://github.com/torognes/vsearch")
5665 ;; vsearch uses non-portable SSE intrinsics so building fails on other
5667 (supported-systems '("x86_64-linux"))
5668 ;; Dual licensed; also includes public domain source.
5669 (license (list license:gpl3 license:bsd-2))))
5671 (define-public pardre
5678 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
5682 "0zkyjzv4s8q2h5npalhirbk17r5b1h0n2a42mh7njzlf047h9bhy"))))
5683 (build-system gnu-build-system)
5685 `(#:tests? #f ; no tests included
5687 (modify-phases %standard-phases
5690 (lambda* (#:key outputs #:allow-other-keys)
5691 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
5693 (install-file "ParDRe" bin)
5696 `(("openmpi" ,openmpi)
5698 (synopsis "Parallel tool to remove duplicate DNA reads")
5700 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
5701 Duplicate reads can be seen as identical or nearly identical sequences with
5702 some mismatches. This tool lets users avoid the analysis of unnecessary
5703 reads, reducing the time of subsequent procedures with the
5704 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
5705 in order to exploit the parallel capabilities of multicore clusters. It is
5706 faster than multithreaded counterparts (end of 2015) for the same number of
5707 cores and, thanks to the message-passing technology, it can be executed on
5709 (home-page "https://sourceforge.net/projects/pardre/")
5710 (license license:gpl3+)))
5712 (define-public ruby-bio-kseq
5714 (name "ruby-bio-kseq")
5719 (uri (rubygems-uri "bio-kseq" version))
5722 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
5723 (build-system ruby-build-system)
5725 `(#:test-target "spec"))
5727 `(("bundler" ,bundler)
5728 ("ruby-rspec" ,ruby-rspec)
5729 ("ruby-rake-compiler" ,ruby-rake-compiler)))
5732 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
5734 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
5735 FASTQ parsing code. It provides a fast iterator over sequences and their
5737 (home-page "https://github.com/gusevfe/bio-kseq")
5738 (license license:expat)))
5740 (define-public bio-locus
5747 (uri (rubygems-uri "bio-locus" version))
5750 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
5751 (build-system ruby-build-system)
5753 `(("ruby-rspec" ,ruby-rspec)))
5754 (synopsis "Tool for fast querying of genome locations")
5756 "Bio-locus is a tabix-like tool for fast querying of genome
5757 locations. Many file formats in bioinformatics contain records that
5758 start with a chromosome name and a position for a SNP, or a start-end
5759 position for indels. Bio-locus allows users to store this chr+pos or
5760 chr+pos+alt information in a database.")
5761 (home-page "https://github.com/pjotrp/bio-locus")
5762 (license license:expat)))
5764 (define-public bio-blastxmlparser
5766 (name "bio-blastxmlparser")
5770 (uri (rubygems-uri "bio-blastxmlparser" version))
5773 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
5774 (build-system ruby-build-system)
5776 `(("ruby-bio-logger" ,ruby-bio-logger)
5777 ("ruby-nokogiri" ,ruby-nokogiri)))
5779 `(("ruby-rspec" ,ruby-rspec)))
5780 (synopsis "Fast big data BLAST XML parser and library")
5782 "Very fast parallel big-data BLAST XML file parser which can be used as
5783 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
5784 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
5785 (home-page "http://github.com/pjotrp/blastxmlparser")
5786 (license license:expat)))
5788 (define-public bioruby
5795 (uri (rubygems-uri "bio" version))
5798 "01k2fyjl5fpx4zn8g6gqiqvsg2j1fgixrs9p03vzxckynxdq3wmc"))))
5799 (build-system ruby-build-system)
5801 `(("ruby-libxml" ,ruby-libxml)))
5803 `(("which" ,which))) ; required for test phase
5806 (modify-phases %standard-phases
5807 (add-before 'build 'patch-test-command
5809 (substitute* '("test/functional/bio/test_command.rb")
5810 (("/bin/sh") (which "sh")))
5811 (substitute* '("test/functional/bio/test_command.rb")
5812 (("/bin/ls") (which "ls")))
5813 (substitute* '("test/functional/bio/test_command.rb")
5814 (("which") (which "which")))
5815 (substitute* '("test/functional/bio/test_command.rb",
5816 "test/data/command/echoarg2.sh")
5817 (("/bin/echo") (which "echo")))
5819 (synopsis "Ruby library, shell and utilities for bioinformatics")
5820 (description "BioRuby comes with a comprehensive set of Ruby development
5821 tools and libraries for bioinformatics and molecular biology. BioRuby has
5822 components for sequence analysis, pathway analysis, protein modelling and
5823 phylogenetic analysis; it supports many widely used data formats and provides
5824 easy access to databases, external programs and public web services, including
5825 BLAST, KEGG, GenBank, MEDLINE and GO.")
5826 (home-page "http://bioruby.org/")
5827 ;; Code is released under Ruby license, except for setup
5828 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
5829 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
5831 (define-public r-acsnminer
5833 (name "r-acsnminer")
5834 (version "0.16.8.25")
5837 (uri (cran-uri "ACSNMineR" version))
5840 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
5841 (properties `((upstream-name . "ACSNMineR")))
5842 (build-system r-build-system)
5844 `(("r-ggplot2" ,r-ggplot2)
5845 ("r-gridextra" ,r-gridextra)))
5846 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
5847 (synopsis "Gene enrichment analysis")
5849 "This package provides tools to compute and represent gene set enrichment
5850 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
5851 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
5852 enrichment can be run with hypergeometric test or Fisher exact test, and can
5853 use multiple corrections. Visualization of data can be done either by
5854 barplots or heatmaps.")
5855 (license license:gpl2+)))
5857 (define-public r-biocgenerics
5859 (name "r-biocgenerics")
5863 (uri (bioconductor-uri "BiocGenerics" version))
5866 "06szdz7dfs1iyv5zdl4fjzad18nnf1zf3wvglc6c6yd9mrqlf7vk"))))
5868 `((upstream-name . "BiocGenerics")))
5869 (build-system r-build-system)
5870 (home-page "http://bioconductor.org/packages/BiocGenerics")
5871 (synopsis "S4 generic functions for Bioconductor")
5873 "This package provides S4 generic functions needed by many Bioconductor
5875 (license license:artistic2.0)))
5877 (define-public r-biocinstaller
5879 (name "r-biocinstaller")
5883 (uri (bioconductor-uri "BiocInstaller" version))
5886 "0y1y5wmy6lzjqx3hdg15n91d417ccjj8dbvdkhmp99bs5aijwcpn"))))
5888 `((upstream-name . "BiocInstaller")))
5889 (build-system r-build-system)
5890 (home-page "http://bioconductor.org/packages/BiocInstaller")
5891 (synopsis "Install Bioconductor packages")
5892 (description "This package is used to install and update R packages from
5893 Bioconductor, CRAN, and Github.")
5894 (license license:artistic2.0)))
5896 (define-public r-biocviews
5898 (name "r-biocviews")
5902 (uri (bioconductor-uri "biocViews" version))
5905 "07rjk10b91pkriyq297w86199r2d3sfji3ggs9mq2gyalsa8y4b6"))))
5907 `((upstream-name . "biocViews")))
5908 (build-system r-build-system)
5910 `(("r-biobase" ,r-biobase)
5911 ("r-graph" ,r-graph)
5913 ("r-rcurl" ,r-rcurl)
5915 ("r-knitr" ,r-knitr)
5916 ("r-runit" ,r-runit)))
5917 (home-page "http://bioconductor.org/packages/biocViews")
5918 (synopsis "Bioconductor package categorization helper")
5919 (description "The purpose of biocViews is to create HTML pages that
5920 categorize packages in a Bioconductor package repository according to keywords,
5921 also known as views, in a controlled vocabulary.")
5922 (license license:artistic2.0)))
5924 (define-public r-biocstyle
5926 (name "r-biocstyle")
5930 (uri (bioconductor-uri "BiocStyle" version))
5933 "0qbk23fz8cn260isd9xlh9lxfj4adar6iqzai01c4kz0p31f45za"))))
5935 `((upstream-name . "BiocStyle")))
5936 (build-system r-build-system)
5937 (home-page "http://bioconductor.org/packages/BiocStyle")
5938 (synopsis "Bioconductor formatting styles")
5939 (description "This package provides standard formatting styles for
5940 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
5942 (license license:artistic2.0)))
5944 (define-public r-bioccheck
5946 (name "r-bioccheck")
5950 (uri (bioconductor-uri "BiocCheck" version))
5953 "1rfy37xg1nc2cmgbclvzsi7sgmdcdjiahsx9crgx3yaw7kxgiack"))))
5955 `((upstream-name . "BiocCheck")))
5956 (build-system r-build-system)
5959 (modify-phases %standard-phases
5960 ;; This package can be used by calling BiocCheck(<package>) from
5961 ;; within R, or by running R CMD BiocCheck <package>. This phase
5962 ;; makes sure the latter works. For this to work, the BiocCheck
5963 ;; script must be somewhere on the PATH (not the R bin directory).
5964 (add-after 'install 'install-bioccheck-subcommand
5965 (lambda* (#:key outputs #:allow-other-keys)
5966 (let* ((out (assoc-ref outputs "out"))
5967 (dest-dir (string-append out "/bin"))
5969 (string-append out "/site-library/BiocCheck/script/")))
5971 (symlink (string-append script-dir "/checkBadDeps.R")
5972 (string-append dest-dir "/checkBadDeps.R"))
5973 (symlink (string-append script-dir "/BiocCheck")
5974 (string-append dest-dir "/BiocCheck")))
5977 `(("which" ,which)))
5979 `(("r-graph" ,r-graph)
5980 ("r-knitr" ,r-knitr)
5982 ("r-optparse" ,r-optparse)
5983 ("r-devtools" ,r-devtools)
5984 ("r-biocinstaller" ,r-biocinstaller)
5985 ("r-biocviews" ,r-biocviews)))
5986 (home-page "http://bioconductor.org/packages/BiocCheck")
5987 (synopsis "Executes Bioconductor-specific package checks")
5988 (description "This package contains tools to perform additional quality
5989 checks on R packages that are to be submitted to the Bioconductor repository.")
5990 (license license:artistic2.0)))
5992 (define-public r-getopt
5999 (uri (cran-uri "getopt" version))
6002 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6003 (build-system r-build-system)
6004 (home-page "https://github.com/trevorld/getopt")
6005 (synopsis "Command-line option processor for R")
6007 "This package is designed to be used with Rscript to write shebang
6008 scripts that accept short and long options. Many users will prefer to
6009 use the packages @code{optparse} or @code{argparse} which add extra
6010 features like automatically generated help options and usage texts,
6011 support for default values, positional argument support, etc.")
6012 (license license:gpl2+)))
6014 (define-public r-optparse
6021 (uri (cran-uri "optparse" version))
6024 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6025 (build-system r-build-system)
6027 `(("r-getopt" ,r-getopt)))
6029 "https://github.com/trevorld/optparse")
6030 (synopsis "Command line option parser")
6032 "This package provides a command line parser inspired by Python's
6033 @code{optparse} library to be used with Rscript to write shebang scripts
6034 that accept short and long options.")
6035 (license license:gpl2+)))
6037 (define-public r-dnacopy
6043 (uri (bioconductor-uri "DNAcopy" version))
6046 "1idyvfvy7xx8k9vk00y4k3819qmip8iqm809j3vpxabmsn7r9zyh"))))
6048 `((upstream-name . "DNAcopy")))
6049 (build-system r-build-system)
6051 `(("gfortran" ,gfortran)))
6052 (home-page "https://bioconductor.org/packages/DNAcopy")
6053 (synopsis "Implementation of a circular binary segmentation algorithm")
6054 (description "This package implements the circular binary segmentation (CBS)
6055 algorithm to segment DNA copy number data and identify genomic regions with
6056 abnormal copy number.")
6057 (license license:gpl2+)))
6059 (define-public r-s4vectors
6061 (name "r-s4vectors")
6065 (uri (bioconductor-uri "S4Vectors" version))
6068 "0m0npc0vhmcwcxws7v2f8k4hvvrjvnlrsr94klxf4a8m4xw2xzzk"))))
6070 `((upstream-name . "S4Vectors")))
6071 (build-system r-build-system)
6073 `(("r-biocgenerics" ,r-biocgenerics)))
6074 (home-page "http://bioconductor.org/packages/S4Vectors")
6075 (synopsis "S4 implementation of vectors and lists")
6077 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6078 classes and a set of generic functions that extend the semantic of ordinary
6079 vectors and lists in R. Package developers can easily implement vector-like
6080 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6081 In addition, a few low-level concrete subclasses of general interest (e.g.
6082 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6083 S4Vectors package itself.")
6084 (license license:artistic2.0)))
6086 (define-public r-seqinr
6093 (uri (cran-uri "seqinr" version))
6096 "0rk4yba8km26c0rh1f4h474zsb5n6kjmqsi55bnzr6p8pymp18hj"))))
6097 (build-system r-build-system)
6099 `(("r-ade4" ,r-ade4)
6100 ("r-segmented" ,r-segmented)))
6103 (home-page "http://seqinr.r-forge.r-project.org/")
6104 (synopsis "Biological sequences retrieval and analysis")
6106 "This package provides tools for exploratory data analysis and data
6107 visualization of biological sequence (DNA and protein) data. It also includes
6108 utilities for sequence data management under the ACNUC system.")
6109 (license license:gpl2+)))
6111 (define-public r-iranges
6117 (uri (bioconductor-uri "IRanges" version))
6120 "0cdl1sfd3cvf93lnz91fdk64fbg1mnd5g958dwh1il8r358hqq3f"))))
6122 `((upstream-name . "IRanges")))
6123 (build-system r-build-system)
6125 `(("r-biocgenerics" ,r-biocgenerics)
6126 ("r-s4vectors" ,r-s4vectors)))
6127 (home-page "http://bioconductor.org/packages/IRanges")
6128 (synopsis "Infrastructure for manipulating intervals on sequences")
6130 "This package provides efficient low-level and highly reusable S4 classes
6131 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6132 generally, data that can be organized sequentially (formally defined as
6133 @code{Vector} objects), as well as views on these @code{Vector} objects.
6134 Efficient list-like classes are also provided for storing big collections of
6135 instances of the basic classes. All classes in the package use consistent
6136 naming and share the same rich and consistent \"Vector API\" as much as
6138 (license license:artistic2.0)))
6140 (define-public r-genomeinfodb
6142 (name "r-genomeinfodb")
6146 (uri (bioconductor-uri "GenomeInfoDb" version))
6149 "0nhg4bk38gzvf3mvnbqgisbbhfv1kzjld27z1z9knnlkplkiyyyv"))))
6151 `((upstream-name . "GenomeInfoDb")))
6152 (build-system r-build-system)
6154 `(("r-biocgenerics" ,r-biocgenerics)
6155 ("r-iranges" ,r-iranges)
6156 ("r-s4vectors" ,r-s4vectors)))
6157 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6158 (synopsis "Utilities for manipulating chromosome identifiers")
6160 "This package contains data and functions that define and allow
6161 translation between different chromosome sequence naming conventions (e.g.,
6162 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6163 names in their natural, rather than lexicographic, order.")
6164 (license license:artistic2.0)))
6166 (define-public r-edger
6172 (uri (bioconductor-uri "edgeR" version))
6175 "1qr20j55m35dwzqyzzmla69gk5bzff8v1v2qjh7yd3362wq1ch49"))))
6176 (properties `((upstream-name . "edgeR")))
6177 (build-system r-build-system)
6179 `(("r-limma" ,r-limma)
6180 ("r-locfit" ,r-locfit)))
6181 (home-page "http://bioinf.wehi.edu.au/edgeR")
6182 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6183 (description "This package can do differential expression analysis of
6184 RNA-seq expression profiles with biological replication. It implements a range
6185 of statistical methodology based on the negative binomial distributions,
6186 including empirical Bayes estimation, exact tests, generalized linear models
6187 and quasi-likelihood tests. It be applied to differential signal analysis of
6188 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6190 (license license:gpl2+)))
6192 (define-public r-variantannotation
6194 (name "r-variantannotation")
6198 (uri (bioconductor-uri "VariantAnnotation" version))
6201 "1lwzfgahz8ipwli73kcfqb18y6adi129hap1gnycnj3980m54i8q"))))
6203 `((upstream-name . "VariantAnnotation")))
6207 `(("r-annotationdbi" ,r-annotationdbi)
6208 ("r-biobase" ,r-biobase)
6209 ("r-biocgenerics" ,r-biocgenerics)
6210 ("r-biostrings" ,r-biostrings)
6211 ("r-bsgenome" ,r-bsgenome)
6213 ("r-genomeinfodb" ,r-genomeinfodb)
6214 ("r-genomicfeatures" ,r-genomicfeatures)
6215 ("r-genomicranges" ,r-genomicranges)
6216 ("r-iranges" ,r-iranges)
6217 ("r-summarizedexperiment" ,r-summarizedexperiment)
6218 ("r-rsamtools" ,r-rsamtools)
6219 ("r-rtracklayer" ,r-rtracklayer)
6220 ("r-s4vectors" ,r-s4vectors)
6221 ("r-xvector" ,r-xvector)
6222 ("r-zlibbioc" ,r-zlibbioc)))
6223 (build-system r-build-system)
6224 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6225 (synopsis "Package for annotation of genetic variants")
6226 (description "This R package can annotate variants, compute amino acid
6227 coding changes and predict coding outcomes.")
6228 (license license:artistic2.0)))
6230 (define-public r-limma
6236 (uri (bioconductor-uri "limma" version))
6239 "0d8wp7b7nymawf4czwsg27k4c61i4ij2lhv7phi6cb3hdd8c76yf"))))
6240 (build-system r-build-system)
6241 (home-page "http://bioinf.wehi.edu.au/limma")
6242 (synopsis "Package for linear models for microarray and RNA-seq data")
6243 (description "This package can be used for the analysis of gene expression
6244 studies, especially the use of linear models for analysing designed experiments
6245 and the assessment of differential expression. The analysis methods apply to
6246 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6247 (license license:gpl2+)))
6249 (define-public r-xvector
6255 (uri (bioconductor-uri "XVector" version))
6258 "09lbqxpqr80g0kw77mpz0p1a8cq706j33kz8194wp71il67cdzi7"))))
6260 `((upstream-name . "XVector")))
6261 (build-system r-build-system)
6264 (modify-phases %standard-phases
6265 (add-after 'unpack 'use-system-zlib
6267 (substitute* "DESCRIPTION"
6268 (("zlibbioc, ") ""))
6269 (substitute* "NAMESPACE"
6270 (("import\\(zlibbioc\\)") ""))
6275 `(("r-biocgenerics" ,r-biocgenerics)
6276 ("r-iranges" ,r-iranges)
6277 ("r-s4vectors" ,r-s4vectors)))
6278 (home-page "http://bioconductor.org/packages/XVector")
6279 (synopsis "Representation and manpulation of external sequences")
6281 "This package provides memory efficient S4 classes for storing sequences
6282 \"externally\" (behind an R external pointer, or on disk).")
6283 (license license:artistic2.0)))
6285 (define-public r-genomicranges
6287 (name "r-genomicranges")
6291 (uri (bioconductor-uri "GenomicRanges" version))
6294 "039nxccg9i2an8q2wni79x8dr9p1fcfcqvih9hg9w243pczg2g3c"))))
6296 `((upstream-name . "GenomicRanges")))
6297 (build-system r-build-system)
6299 `(("r-biocgenerics" ,r-biocgenerics)
6300 ("r-genomeinfodb" ,r-genomeinfodb)
6301 ("r-iranges" ,r-iranges)
6302 ("r-s4vectors" ,r-s4vectors)
6303 ("r-xvector" ,r-xvector)))
6304 (home-page "http://bioconductor.org/packages/GenomicRanges")
6305 (synopsis "Representation and manipulation of genomic intervals")
6307 "This package provides tools to efficiently represent and manipulate
6308 genomic annotations and alignments is playing a central role when it comes to
6309 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6310 GenomicRanges package defines general purpose containers for storing and
6311 manipulating genomic intervals and variables defined along a genome.")
6312 (license license:artistic2.0)))
6314 (define-public r-biobase
6320 (uri (bioconductor-uri "Biobase" version))
6323 "0js9j9wqls8f571ifl9ylllbb9a9hwf7b7drf2grwb1fl31ldazl"))))
6325 `((upstream-name . "Biobase")))
6326 (build-system r-build-system)
6328 `(("r-biocgenerics" ,r-biocgenerics)))
6329 (home-page "http://bioconductor.org/packages/Biobase")
6330 (synopsis "Base functions for Bioconductor")
6332 "This package provides functions that are needed by many other packages
6333 on Bioconductor or which replace R functions.")
6334 (license license:artistic2.0)))
6336 (define-public r-annotationdbi
6338 (name "r-annotationdbi")
6342 (uri (bioconductor-uri "AnnotationDbi" version))
6345 "0ydrqw1k1j5p6w76bwc753cx545c055x88q87wzya93858synj6r"))))
6347 `((upstream-name . "AnnotationDbi")))
6348 (build-system r-build-system)
6350 `(("r-biobase" ,r-biobase)
6351 ("r-biocgenerics" ,r-biocgenerics)
6353 ("r-iranges" ,r-iranges)
6354 ("r-rsqlite" ,r-rsqlite)
6355 ("r-s4vectors" ,r-s4vectors)))
6356 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6357 (synopsis "Annotation database interface")
6359 "This package provides user interface and database connection code for
6360 annotation data packages using SQLite data storage.")
6361 (license license:artistic2.0)))
6363 (define-public r-biomart
6369 (uri (bioconductor-uri "biomaRt" version))
6372 "1x0flcghq71784q2l02j0g4f9jkmyb14f6i307n6c59d6ji7h7x6"))))
6374 `((upstream-name . "biomaRt")))
6375 (build-system r-build-system)
6377 `(("r-annotationdbi" ,r-annotationdbi)
6378 ("r-rcurl" ,r-rcurl)
6380 (home-page "http://bioconductor.org/packages/biomaRt")
6381 (synopsis "Interface to BioMart databases")
6383 "biomaRt provides an interface to a growing collection of databases
6384 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6385 package enables retrieval of large amounts of data in a uniform way without
6386 the need to know the underlying database schemas or write complex SQL queries.
6387 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6388 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6389 users direct access to a diverse set of data and enable a wide range of
6390 powerful online queries from gene annotation to database mining.")
6391 (license license:artistic2.0)))
6393 (define-public r-biocparallel
6395 (name "r-biocparallel")
6399 (uri (bioconductor-uri "BiocParallel" version))
6402 "0vz23i14f7wjygr5d4y1hp8ki6l6igwcsjscfpr6dcigmknyi55c"))))
6404 `((upstream-name . "BiocParallel")))
6405 (build-system r-build-system)
6407 `(("r-futile-logger" ,r-futile-logger)
6408 ("r-snow" ,r-snow)))
6409 (home-page "http://bioconductor.org/packages/BiocParallel")
6410 (synopsis "Bioconductor facilities for parallel evaluation")
6412 "This package provides modified versions and novel implementation of
6413 functions for parallel evaluation, tailored to use with Bioconductor
6415 (license (list license:gpl2+ license:gpl3+))))
6417 (define-public r-biostrings
6419 (name "r-biostrings")
6423 (uri (bioconductor-uri "Biostrings" version))
6426 "08z8lkz3axa94wkf144a931ry6vf6cc25avi1ywr84ln2k5czz9f"))))
6428 `((upstream-name . "Biostrings")))
6429 (build-system r-build-system)
6431 `(("r-biocgenerics" ,r-biocgenerics)
6432 ("r-iranges" ,r-iranges)
6433 ("r-s4vectors" ,r-s4vectors)
6434 ("r-xvector" ,r-xvector)))
6435 (home-page "http://bioconductor.org/packages/Biostrings")
6436 (synopsis "String objects and algorithms for biological sequences")
6438 "This package provides memory efficient string containers, string
6439 matching algorithms, and other utilities, for fast manipulation of large
6440 biological sequences or sets of sequences.")
6441 (license license:artistic2.0)))
6443 (define-public r-rsamtools
6445 (name "r-rsamtools")
6449 (uri (bioconductor-uri "Rsamtools" version))
6452 "0pf4f6brf4bl5zgjrah0f38qslazrs49ayqgyh0xfqgrh63yx4ck"))))
6454 `((upstream-name . "Rsamtools")))
6455 (build-system r-build-system)
6458 (modify-phases %standard-phases
6459 (add-after 'unpack 'use-system-zlib
6461 (substitute* "DESCRIPTION"
6462 (("zlibbioc, ") ""))
6463 (substitute* "NAMESPACE"
6464 (("import\\(zlibbioc\\)") ""))
6469 `(("r-biocgenerics" ,r-biocgenerics)
6470 ("r-biocparallel" ,r-biocparallel)
6471 ("r-biostrings" ,r-biostrings)
6472 ("r-bitops" ,r-bitops)
6473 ("r-genomeinfodb" ,r-genomeinfodb)
6474 ("r-genomicranges" ,r-genomicranges)
6475 ("r-iranges" ,r-iranges)
6476 ("r-s4vectors" ,r-s4vectors)
6477 ("r-xvector" ,r-xvector)))
6478 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6479 (synopsis "Interface to samtools, bcftools, and tabix")
6481 "This package provides an interface to the 'samtools', 'bcftools', and
6482 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6483 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6485 (license license:expat)))
6487 (define-public r-summarizedexperiment
6489 (name "r-summarizedexperiment")
6493 (uri (bioconductor-uri "SummarizedExperiment" version))
6496 "1kbj8sg2ik9f8d6g95wz0py62jldg01qy5rsdpg1cxw95nf7dzi3"))))
6498 `((upstream-name . "SummarizedExperiment")))
6499 (build-system r-build-system)
6501 `(("r-biobase" ,r-biobase)
6502 ("r-biocgenerics" ,r-biocgenerics)
6503 ("r-genomeinfodb" ,r-genomeinfodb)
6504 ("r-genomicranges" ,r-genomicranges)
6505 ("r-iranges" ,r-iranges)
6506 ("r-s4vectors" ,r-s4vectors)))
6507 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
6508 (synopsis "Container for representing genomic ranges by sample")
6510 "The SummarizedExperiment container contains one or more assays, each
6511 represented by a matrix-like object of numeric or other mode. The rows
6512 typically represent genomic ranges of interest and the columns represent
6514 (license license:artistic2.0)))
6516 (define-public r-genomicalignments
6518 (name "r-genomicalignments")
6522 (uri (bioconductor-uri "GenomicAlignments" version))
6525 "11vb0a0zd36i4yhg4mfijv787v0nihn6pkjj6q7rfy19gwy61xlc"))))
6527 `((upstream-name . "GenomicAlignments")))
6528 (build-system r-build-system)
6530 `(("r-biocgenerics" ,r-biocgenerics)
6531 ("r-biocparallel" ,r-biocparallel)
6532 ("r-biostrings" ,r-biostrings)
6533 ("r-genomeinfodb" ,r-genomeinfodb)
6534 ("r-genomicranges" ,r-genomicranges)
6535 ("r-iranges" ,r-iranges)
6536 ("r-rsamtools" ,r-rsamtools)
6537 ("r-s4vectors" ,r-s4vectors)
6538 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6539 (home-page "http://bioconductor.org/packages/GenomicAlignments")
6540 (synopsis "Representation and manipulation of short genomic alignments")
6542 "This package provides efficient containers for storing and manipulating
6543 short genomic alignments (typically obtained by aligning short reads to a
6544 reference genome). This includes read counting, computing the coverage,
6545 junction detection, and working with the nucleotide content of the
6547 (license license:artistic2.0)))
6549 (define-public r-rtracklayer
6551 (name "r-rtracklayer")
6555 (uri (bioconductor-uri "rtracklayer" version))
6558 "0mix5k75j70mwplbdipqw71n8qic75ny6y8w2f5jj0pqg1k0327d"))))
6559 (build-system r-build-system)
6562 (modify-phases %standard-phases
6563 (add-after 'unpack 'use-system-zlib
6565 (substitute* "DESCRIPTION"
6566 (("zlibbioc, ") ""))
6567 (substitute* "NAMESPACE"
6568 (("import\\(zlibbioc\\)") ""))
6573 `(("r-biocgenerics" ,r-biocgenerics)
6574 ("r-biostrings" ,r-biostrings)
6575 ("r-genomeinfodb" ,r-genomeinfodb)
6576 ("r-genomicalignments" ,r-genomicalignments)
6577 ("r-genomicranges" ,r-genomicranges)
6578 ("r-iranges" ,r-iranges)
6579 ("r-rcurl" ,r-rcurl)
6580 ("r-rsamtools" ,r-rsamtools)
6581 ("r-s4vectors" ,r-s4vectors)
6583 ("r-xvector" ,r-xvector)))
6584 (home-page "http://bioconductor.org/packages/rtracklayer")
6585 (synopsis "R interface to genome browsers and their annotation tracks")
6587 "rtracklayer is an extensible framework for interacting with multiple
6588 genome browsers (currently UCSC built-in) and manipulating annotation tracks
6589 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
6590 built-in). The user may export/import tracks to/from the supported browsers,
6591 as well as query and modify the browser state, such as the current viewport.")
6592 (license license:artistic2.0)))
6594 (define-public r-genomicfeatures
6596 (name "r-genomicfeatures")
6600 (uri (bioconductor-uri "GenomicFeatures" version))
6603 "0z8spi2knwzwi10c38vr7xlvi3ah9faj7m1lka880mmxkl9cai4k"))))
6605 `((upstream-name . "GenomicFeatures")))
6606 (build-system r-build-system)
6608 `(("r-annotationdbi" ,r-annotationdbi)
6609 ("r-biobase" ,r-biobase)
6610 ("r-biocgenerics" ,r-biocgenerics)
6611 ("r-biomart" ,r-biomart)
6612 ("r-biostrings" ,r-biostrings)
6614 ("r-genomeinfodb" ,r-genomeinfodb)
6615 ("r-genomicranges" ,r-genomicranges)
6616 ("r-iranges" ,r-iranges)
6617 ("r-rcurl" ,r-rcurl)
6618 ("r-rsqlite" ,r-rsqlite)
6619 ("r-rtracklayer" ,r-rtracklayer)
6620 ("r-s4vectors" ,r-s4vectors)
6621 ("r-xvector" ,r-xvector)))
6622 (home-page "http://bioconductor.org/packages/GenomicFeatures")
6623 (synopsis "Tools for working with transcript centric annotations")
6625 "This package provides a set of tools and methods for making and
6626 manipulating transcript centric annotations. With these tools the user can
6627 easily download the genomic locations of the transcripts, exons and cds of a
6628 given organism, from either the UCSC Genome Browser or a BioMart
6629 database (more sources will be supported in the future). This information is
6630 then stored in a local database that keeps track of the relationship between
6631 transcripts, exons, cds and genes. Flexible methods are provided for
6632 extracting the desired features in a convenient format.")
6633 (license license:artistic2.0)))
6635 (define-public r-go-db
6641 (uri (string-append "http://www.bioconductor.org/packages/"
6642 "release/data/annotation/src/contrib/GO.db_"
6646 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
6648 `((upstream-name . "GO.db")))
6649 (build-system r-build-system)
6651 `(("r-annotationdbi" ,r-annotationdbi)))
6652 (home-page "http://bioconductor.org/packages/GO.db")
6653 (synopsis "Annotation maps describing the entire Gene Ontology")
6655 "The purpose of this GO.db annotation package is to provide detailed
6656 information about the latest version of the Gene Ontologies.")
6657 (license license:artistic2.0)))
6659 (define-public r-graph
6665 (uri (bioconductor-uri "graph" version))
6668 "0g3dk5vsdp489fmyg8mifczmzgqrjlakkkr8i96dj15gghp3l135"))))
6669 (build-system r-build-system)
6671 `(("r-biocgenerics" ,r-biocgenerics)))
6672 (home-page "http://bioconductor.org/packages/graph")
6673 (synopsis "Handle graph data structures in R")
6675 "This package implements some simple graph handling capabilities for R.")
6676 (license license:artistic2.0)))
6678 (define-public r-topgo
6684 (uri (bioconductor-uri "topGO" version))
6687 "0j6sgvam4lk9348ag6pypcbkv93x4fk0di8ivhr23mz2s2yqzwrx"))))
6689 `((upstream-name . "topGO")))
6690 (build-system r-build-system)
6692 `(("r-annotationdbi" ,r-annotationdbi)
6694 ("r-biobase" ,r-biobase)
6695 ("r-biocgenerics" ,r-biocgenerics)
6696 ("r-go-db" ,r-go-db)
6697 ("r-matrixstats" ,r-matrixstats)
6698 ("r-graph" ,r-graph)
6699 ("r-sparsem" ,r-sparsem)))
6700 (home-page "http://bioconductor.org/packages/topGO")
6701 (synopsis "Enrichment analysis for gene ontology")
6703 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
6704 terms while accounting for the topology of the GO graph. Different test
6705 statistics and different methods for eliminating local similarities and
6706 dependencies between GO terms can be implemented and applied.")
6707 ;; Any version of the LGPL applies.
6708 (license license:lgpl2.1+)))
6710 (define-public r-bsgenome
6716 (uri (bioconductor-uri "BSgenome" version))
6719 "0hxwc02h5mzhkrk60d1jmlsfjf0ai9jxdc0128kj1sg4r2k1q94y"))))
6721 `((upstream-name . "BSgenome")))
6722 (build-system r-build-system)
6724 `(("r-biocgenerics" ,r-biocgenerics)
6725 ("r-biostrings" ,r-biostrings)
6726 ("r-genomeinfodb" ,r-genomeinfodb)
6727 ("r-genomicranges" ,r-genomicranges)
6728 ("r-iranges" ,r-iranges)
6729 ("r-rsamtools" ,r-rsamtools)
6730 ("r-rtracklayer" ,r-rtracklayer)
6731 ("r-s4vectors" ,r-s4vectors)
6732 ("r-xvector" ,r-xvector)))
6733 (home-page "http://bioconductor.org/packages/BSgenome")
6734 (synopsis "Infrastructure for Biostrings-based genome data packages")
6736 "This package provides infrastructure shared by all Biostrings-based
6737 genome data packages and support for efficient SNP representation.")
6738 (license license:artistic2.0)))
6740 (define-public r-impute
6746 (uri (bioconductor-uri "impute" version))
6749 "1164zvnikbjd0ybdn9xwn520rlmdjd824vmhnl83zgv3v9lzp9bm"))))
6751 `(("gfortran" ,gfortran)))
6752 (build-system r-build-system)
6753 (home-page "http://bioconductor.org/packages/impute")
6754 (synopsis "Imputation for microarray data")
6756 "This package provides a function to impute missing gene expression
6757 microarray data, using nearest neighbor averaging.")
6758 (license license:gpl2+)))
6760 (define-public r-seqpattern
6762 (name "r-seqpattern")
6766 (uri (bioconductor-uri "seqPattern" version))
6769 "0lsa5pz36xapi3yiv78k3z286a5md5sm5g21pgfyg8zmhmkxr7y8"))))
6771 `((upstream-name . "seqPattern")))
6772 (build-system r-build-system)
6774 `(("r-biostrings" ,r-biostrings)
6775 ("r-genomicranges" ,r-genomicranges)
6776 ("r-iranges" ,r-iranges)
6777 ("r-kernsmooth" ,r-kernsmooth)
6778 ("r-plotrix" ,r-plotrix)))
6779 (home-page "http://bioconductor.org/packages/seqPattern")
6780 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
6782 "This package provides tools to visualize oligonucleotide patterns and
6783 sequence motif occurrences across a large set of sequences centred at a common
6784 reference point and sorted by a user defined feature.")
6785 (license license:gpl3+)))
6787 (define-public r-genomation
6789 (name "r-genomation")
6793 (uri (bioconductor-uri "genomation" version))
6796 "1m4mz7wihj8yqivwkzw68div8ybk4rjsai3ffki7xp7sh21ax03y"))))
6797 (build-system r-build-system)
6799 `(("r-biostrings" ,r-biostrings)
6800 ("r-bsgenome" ,r-bsgenome)
6801 ("r-data-table" ,r-data-table)
6802 ("r-genomeinfodb" ,r-genomeinfodb)
6803 ("r-genomicalignments" ,r-genomicalignments)
6804 ("r-genomicranges" ,r-genomicranges)
6805 ("r-ggplot2" ,r-ggplot2)
6806 ("r-gridbase" ,r-gridbase)
6807 ("r-impute" ,r-impute)
6808 ("r-iranges" ,r-iranges)
6809 ("r-matrixstats" ,r-matrixstats)
6810 ("r-plotrix" ,r-plotrix)
6813 ("r-readr" ,r-readr)
6814 ("r-reshape2" ,r-reshape2)
6815 ("r-rhtslib" ,r-rhtslib)
6816 ("r-rsamtools" ,r-rsamtools)
6817 ("r-rtracklayer" ,r-rtracklayer)
6818 ("r-runit" ,r-runit)
6819 ("r-s4vectors" ,r-s4vectors)
6820 ("r-seqpattern" ,r-seqpattern)))
6823 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
6824 (synopsis "Summary, annotation and visualization of genomic data")
6826 "This package provides a package for summary and annotation of genomic
6827 intervals. Users can visualize and quantify genomic intervals over
6828 pre-defined functional regions, such as promoters, exons, introns, etc. The
6829 genomic intervals represent regions with a defined chromosome position, which
6830 may be associated with a score, such as aligned reads from HT-seq experiments,
6831 TF binding sites, methylation scores, etc. The package can use any tabular
6832 genomic feature data as long as it has minimal information on the locations of
6833 genomic intervals. In addition, it can use BAM or BigWig files as input.")
6834 (license license:artistic2.0)))
6836 (define-public r-genomationdata
6838 (name "r-genomationdata")
6842 ;; We cannot use bioconductor-uri here because this tarball is
6843 ;; located under "data/annotation/" instead of "bioc/".
6844 (uri (string-append "https://bioconductor.org/packages/"
6845 "release/data/experiment/src/contrib/"
6846 "genomationData_" version ".tar.gz"))
6849 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
6850 (build-system r-build-system)
6851 ;; As this package provides little more than large data files, it doesn't
6852 ;; make sense to build substitutes.
6853 (arguments `(#:substitutable? #f))
6855 `(("r-knitr" ,r-knitr)))
6856 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
6857 (synopsis "Experimental data for use with the genomation package")
6859 "This package contains experimental genetic data for use with the
6860 genomation package. Included are Chip Seq, Methylation and Cage data,
6861 downloaded from Encode.")
6862 (license license:gpl3+)))
6864 (define-public r-org-hs-eg-db
6866 (name "r-org-hs-eg-db")
6870 ;; We cannot use bioconductor-uri here because this tarball is
6871 ;; located under "data/annotation/" instead of "bioc/".
6872 (uri (string-append "http://www.bioconductor.org/packages/"
6873 "release/data/annotation/src/contrib/"
6874 "org.Hs.eg.db_" version ".tar.gz"))
6877 "09zb43yjd82ny210n5a0wsrji4w56l2r6ana6d9lx0nn9mzd7rzp"))))
6879 `((upstream-name . "org.Hs.eg.db")))
6880 (build-system r-build-system)
6882 `(("r-annotationdbi" ,r-annotationdbi)))
6883 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
6884 (synopsis "Genome wide annotation for Human")
6886 "This package provides mappings from Entrez gene identifiers to various
6887 annotations for the human genome.")
6888 (license license:artistic2.0)))
6890 (define-public r-org-ce-eg-db
6892 (name "r-org-ce-eg-db")
6896 ;; We cannot use bioconductor-uri here because this tarball is
6897 ;; located under "data/annotation/" instead of "bioc/".
6898 (uri (string-append "http://www.bioconductor.org/packages/"
6899 "release/data/annotation/src/contrib/"
6900 "org.Ce.eg.db_" version ".tar.gz"))
6903 "17mvb2ci2jgac3zi420cbf70n4zswqinzxlk1v2fjnp8vvydl2fw"))))
6905 `((upstream-name . "org.Ce.eg.db")))
6906 (build-system r-build-system)
6908 `(("r-annotationdbi" ,r-annotationdbi)))
6909 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
6910 (synopsis "Genome wide annotation for Worm")
6912 "This package provides mappings from Entrez gene identifiers to various
6913 annotations for the genome of the model worm Caenorhabditis elegans.")
6914 (license license:artistic2.0)))
6916 (define-public r-org-dm-eg-db
6918 (name "r-org-dm-eg-db")
6922 ;; We cannot use bioconductor-uri here because this tarball is
6923 ;; located under "data/annotation/" instead of "bioc/".
6924 (uri (string-append "http://www.bioconductor.org/packages/"
6925 "release/data/annotation/src/contrib/"
6926 "org.Dm.eg.db_" version ".tar.gz"))
6929 "15kzvw78xwa54yk1d69l6pmgny4726ydpdkk8lic26vr0yiwicla"))))
6931 `((upstream-name . "org.Dm.eg.db")))
6932 (build-system r-build-system)
6934 `(("r-annotationdbi" ,r-annotationdbi)))
6935 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
6936 (synopsis "Genome wide annotation for Fly")
6938 "This package provides mappings from Entrez gene identifiers to various
6939 annotations for the genome of the model fruit fly Drosophila melanogaster.")
6940 (license license:artistic2.0)))
6942 (define-public r-org-mm-eg-db
6944 (name "r-org-mm-eg-db")
6948 ;; We cannot use bioconductor-uri here because this tarball is
6949 ;; located under "data/annotation/" instead of "bioc/".
6950 (uri (string-append "http://www.bioconductor.org/packages/"
6951 "release/data/annotation/src/contrib/"
6952 "org.Mm.eg.db_" version ".tar.gz"))
6955 "0r939vfmsqqdwfimix1nv0bkhnixawy9c6avbclrncfanw3kgjax"))))
6957 `((upstream-name . "org.Mm.eg.db")))
6958 (build-system r-build-system)
6960 `(("r-annotationdbi" ,r-annotationdbi)))
6961 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
6962 (synopsis "Genome wide annotation for Mouse")
6964 "This package provides mappings from Entrez gene identifiers to various
6965 annotations for the genome of the model mouse Mus musculus.")
6966 (license license:artistic2.0)))
6968 (define-public r-seqlogo
6975 (uri (bioconductor-uri "seqLogo" version))
6978 "18bajdl75h3039559d81rgllqqvnq8ygsfxfx081xphxs0v6xggy"))))
6979 (properties `((upstream-name . "seqLogo")))
6980 (build-system r-build-system)
6981 (home-page "http://bioconductor.org/packages/seqLogo")
6982 (synopsis "Sequence logos for DNA sequence alignments")
6984 "seqLogo takes the position weight matrix of a DNA sequence motif and
6985 plots the corresponding sequence logo as introduced by Schneider and
6987 (license license:lgpl2.0+)))
6989 (define-public r-bsgenome-hsapiens-ucsc-hg19
6991 (name "r-bsgenome-hsapiens-ucsc-hg19")
6995 ;; We cannot use bioconductor-uri here because this tarball is
6996 ;; located under "data/annotation/" instead of "bioc/".
6997 (uri (string-append "http://www.bioconductor.org/packages/"
6998 "release/data/annotation/src/contrib/"
6999 "BSgenome.Hsapiens.UCSC.hg19_"
7003 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7005 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7006 (build-system r-build-system)
7007 ;; As this package provides little more than a very large data file it
7008 ;; doesn't make sense to build substitutes.
7009 (arguments `(#:substitutable? #f))
7011 `(("r-bsgenome" ,r-bsgenome)))
7013 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7014 (synopsis "Full genome sequences for Homo sapiens")
7016 "This package provides full genome sequences for Homo sapiens as provided
7017 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7018 (license license:artistic2.0)))
7020 (define-public r-bsgenome-mmusculus-ucsc-mm9
7022 (name "r-bsgenome-mmusculus-ucsc-mm9")
7026 ;; We cannot use bioconductor-uri here because this tarball is
7027 ;; located under "data/annotation/" instead of "bioc/".
7028 (uri (string-append "http://www.bioconductor.org/packages/"
7029 "release/data/annotation/src/contrib/"
7030 "BSgenome.Mmusculus.UCSC.mm9_"
7034 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7036 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7037 (build-system r-build-system)
7038 ;; As this package provides little more than a very large data file it
7039 ;; doesn't make sense to build substitutes.
7040 (arguments `(#:substitutable? #f))
7042 `(("r-bsgenome" ,r-bsgenome)))
7044 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7045 (synopsis "Full genome sequences for Mouse")
7047 "This package provides full genome sequences for Mus musculus (Mouse) as
7048 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7049 (license license:artistic2.0)))
7051 (define-public r-bsgenome-mmusculus-ucsc-mm10
7053 (name "r-bsgenome-mmusculus-ucsc-mm10")
7057 ;; We cannot use bioconductor-uri here because this tarball is
7058 ;; located under "data/annotation/" instead of "bioc/".
7059 (uri (string-append "http://www.bioconductor.org/packages/"
7060 "release/data/annotation/src/contrib/"
7061 "BSgenome.Mmusculus.UCSC.mm10_"
7065 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7067 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7068 (build-system r-build-system)
7069 ;; As this package provides little more than a very large data file it
7070 ;; doesn't make sense to build substitutes.
7071 (arguments `(#:substitutable? #f))
7073 `(("r-bsgenome" ,r-bsgenome)))
7075 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7076 (synopsis "Full genome sequences for Mouse")
7078 "This package provides full genome sequences for Mus
7079 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7080 in Biostrings objects.")
7081 (license license:artistic2.0)))
7083 (define-public r-bsgenome-celegans-ucsc-ce6
7085 (name "r-bsgenome-celegans-ucsc-ce6")
7089 ;; We cannot use bioconductor-uri here because this tarball is
7090 ;; located under "data/annotation/" instead of "bioc/".
7091 (uri (string-append "http://www.bioconductor.org/packages/"
7092 "release/data/annotation/src/contrib/"
7093 "BSgenome.Celegans.UCSC.ce6_"
7097 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7099 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7100 (build-system r-build-system)
7101 ;; As this package provides little more than a very large data file it
7102 ;; doesn't make sense to build substitutes.
7103 (arguments `(#:substitutable? #f))
7105 `(("r-bsgenome" ,r-bsgenome)))
7107 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7108 (synopsis "Full genome sequences for Worm")
7110 "This package provides full genome sequences for Caenorhabditis
7111 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7113 (license license:artistic2.0)))
7115 (define-public r-bsgenome-celegans-ucsc-ce10
7117 (name "r-bsgenome-celegans-ucsc-ce10")
7121 ;; We cannot use bioconductor-uri here because this tarball is
7122 ;; located under "data/annotation/" instead of "bioc/".
7123 (uri (string-append "http://www.bioconductor.org/packages/"
7124 "release/data/annotation/src/contrib/"
7125 "BSgenome.Celegans.UCSC.ce10_"
7129 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7131 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7132 (build-system r-build-system)
7133 ;; As this package provides little more than a very large data file it
7134 ;; doesn't make sense to build substitutes.
7135 (arguments `(#:substitutable? #f))
7137 `(("r-bsgenome" ,r-bsgenome)))
7139 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7140 (synopsis "Full genome sequences for Worm")
7142 "This package provides full genome sequences for Caenorhabditis
7143 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7145 (license license:artistic2.0)))
7147 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7149 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7153 ;; We cannot use bioconductor-uri here because this tarball is
7154 ;; located under "data/annotation/" instead of "bioc/".
7155 (uri (string-append "http://www.bioconductor.org/packages/"
7156 "release/data/annotation/src/contrib/"
7157 "BSgenome.Dmelanogaster.UCSC.dm3_"
7161 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7163 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7164 (build-system r-build-system)
7165 ;; As this package provides little more than a very large data file it
7166 ;; doesn't make sense to build substitutes.
7167 (arguments `(#:substitutable? #f))
7169 `(("r-bsgenome" ,r-bsgenome)))
7171 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7172 (synopsis "Full genome sequences for Fly")
7174 "This package provides full genome sequences for Drosophila
7175 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7176 Biostrings objects.")
7177 (license license:artistic2.0)))
7179 (define-public r-motifrg
7186 (uri (bioconductor-uri "motifRG" version))
7189 "1pa97aj6c5f3gx4bgriw110764dj3m9h104ddi8rv2bpy41yd98d"))))
7190 (properties `((upstream-name . "motifRG")))
7191 (build-system r-build-system)
7193 `(("r-biostrings" ,r-biostrings)
7194 ("r-bsgenome" ,r-bsgenome)
7195 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7196 ("r-iranges" ,r-iranges)
7197 ("r-seqlogo" ,r-seqlogo)
7198 ("r-xvector" ,r-xvector)))
7199 (home-page "http://bioconductor.org/packages/motifRG")
7200 (synopsis "Discover motifs in high throughput sequencing data")
7202 "This package provides tools for discriminative motif discovery in high
7203 throughput genetic sequencing data sets using regression methods.")
7204 (license license:artistic2.0)))
7206 (define-public r-qtl
7213 (uri (string-append "mirror://cran/src/contrib/qtl_"
7217 "1grwgvyv7x0dgay1858bg7qf4wk47gpnq7qkqpcda9cn0h970d6f"))))
7218 (build-system r-build-system)
7219 (home-page "http://rqtl.org/")
7220 (synopsis "R package for analyzing QTL experiments in genetics")
7221 (description "R/qtl is an extension library for the R statistics
7222 system. It is used to analyze experimental crosses for identifying
7223 genes contributing to variation in quantitative traits (so-called
7224 quantitative trait loci, QTLs).
7226 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7227 identify genotyping errors, and to perform single-QTL and two-QTL,
7228 two-dimensional genome scans.")
7229 (license license:gpl3)))
7231 (define-public r-zlibbioc
7237 (uri (bioconductor-uri "zlibbioc" version))
7240 "0hbk90q5hl0fycfvy5nxxa4hxgglag9lzp7i0fg849bqygg5nbyq"))))
7242 `((upstream-name . "zlibbioc")))
7243 (build-system r-build-system)
7244 (home-page "https://bioconductor.org/packages/zlibbioc")
7245 (synopsis "Provider for zlib-1.2.5 to R packages")
7246 (description "This package uses the source code of zlib-1.2.5 to create
7247 libraries for systems that do not have these available via other means.")
7248 (license license:artistic2.0)))
7250 (define-public r-rhtslib
7257 (uri (bioconductor-uri "Rhtslib" version))
7260 "1vk3ng61dhi3pbia1lp3gl3mlr3i1vb2lkq83qb53i9dzz128wh9"))))
7261 (properties `((upstream-name . "Rhtslib")))
7262 (build-system r-build-system)
7264 `(("r-zlibbioc" ,r-zlibbioc)))
7268 `(("autoconf" ,autoconf)))
7269 (home-page "https://github.com/nhayden/Rhtslib")
7270 (synopsis "High-throughput sequencing library as an R package")
7272 "This package provides the HTSlib C library for high-throughput
7273 nucleotide sequence analysis. The package is primarily useful to developers
7274 of other R packages who wish to make use of HTSlib.")
7275 (license license:lgpl2.0+)))
7277 (define-public r-bamsignals
7279 (name "r-bamsignals")
7284 (uri (bioconductor-uri "bamsignals" version))
7287 "1k42gvk5mgq4la1fp0in3an2zfdz69h6522jsqhmk0f6i75kg4mb"))))
7288 (build-system r-build-system)
7290 `(("r-biocgenerics" ,r-biocgenerics)
7291 ("r-genomicranges" ,r-genomicranges)
7292 ("r-iranges" ,r-iranges)
7294 ("r-rhtslib" ,r-rhtslib)
7295 ("r-zlibbioc" ,r-zlibbioc)))
7298 (home-page "http://bioconductor.org/packages/bamsignals")
7299 (synopsis "Extract read count signals from bam files")
7301 "This package allows to efficiently obtain count vectors from indexed bam
7302 files. It counts the number of nucleotide sequence reads in given genomic
7303 ranges and it computes reads profiles and coverage profiles. It also handles
7305 (license license:gpl2+)))
7307 (define-public r-rcas
7313 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7315 (file-name (string-append name "-" version ".tar.gz"))
7318 "1ljgl2b4r6w2n0i9i04d9xaphajsvhfkjdj2i2z830nha4m3w8f0"))))
7319 (build-system r-build-system)
7321 `(("r-knitr" ,r-knitr)
7322 ("r-testthat" ,r-testthat)
7323 ;; During vignette building knitr checks that "pandoc-citeproc"
7325 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7327 `(("r-data-table" ,r-data-table)
7328 ("r-biomart" ,r-biomart)
7329 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7330 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7331 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7332 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7333 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7334 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7335 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7336 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7337 ("r-topgo" ,r-topgo)
7339 ("r-plotly" ,r-plotly)
7340 ("r-motifrg" ,r-motifrg)
7341 ("r-genomation" ,r-genomation)
7342 ("r-genomicfeatures" ,r-genomicfeatures)
7343 ("r-rtracklayer" ,r-rtracklayer)
7344 ("r-rmarkdown" ,r-rmarkdown)))
7345 (synopsis "RNA-centric annotation system")
7347 "RCAS aims to be a standalone RNA-centric annotation system that provides
7348 intuitive reports and publication-ready graphics. This package provides the R
7349 library implementing most of the pipeline's features.")
7350 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7351 (license license:expat)))
7353 (define-public rcas-web
7360 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7361 "releases/download/v" version
7362 "/rcas-web-" version ".tar.gz"))
7365 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7366 (build-system gnu-build-system)
7369 (modify-phases %standard-phases
7370 (add-after 'install 'wrap-executable
7371 (lambda* (#:key inputs outputs #:allow-other-keys)
7372 (let* ((out (assoc-ref outputs "out"))
7373 (json (assoc-ref inputs "guile-json"))
7374 (redis (assoc-ref inputs "guile-redis"))
7375 (path (string-append
7376 json "/share/guile/site/2.2:"
7377 redis "/share/guile/site/2.2")))
7378 (wrap-program (string-append out "/bin/rcas-web")
7379 `("GUILE_LOAD_PATH" ":" = (,path))
7380 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
7381 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
7386 ("guile-next" ,guile-next)
7387 ("guile-json" ,guile2.2-json)
7388 ("guile-redis" ,guile2.2-redis)))
7390 `(("pkg-config" ,pkg-config)))
7391 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
7392 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
7393 (description "This package provides a simple web interface for the
7394 @dfn{RNA-centric annotation system} (RCAS).")
7395 (license license:agpl3+)))
7397 (define-public emboss
7403 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
7404 (version-major+minor version) ".0/"
7405 "EMBOSS-" version ".tar.gz"))
7408 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
7409 (build-system gnu-build-system)
7412 (list (string-append "--with-hpdf="
7413 (assoc-ref %build-inputs "libharu")))
7415 (modify-phases %standard-phases
7416 (add-after 'unpack 'fix-checks
7418 ;; The PNGDRIVER tests check for the presence of libgd, libpng
7419 ;; and zlib, but assume that they are all found at the same
7421 (substitute* "configure.in"
7422 (("CHECK_PNGDRIVER")
7423 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
7424 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
7425 AM_CONDITIONAL(AMPNG, true)"))
7427 (add-after 'unpack 'disable-update-check
7429 ;; At build time there is no connection to the Internet, so
7430 ;; looking for updates will not work.
7431 (substitute* "Makefile.am"
7432 (("\\$\\(bindir\\)/embossupdate") ""))
7434 (add-before 'configure 'autogen
7435 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
7441 ("libharu" ,libharu)
7444 `(("autoconf" ,autoconf)
7445 ("automake" ,automake)
7446 ("libtool" ,libtool)
7447 ("pkg-config" ,pkg-config)))
7448 (home-page "http://emboss.sourceforge.net")
7449 (synopsis "Molecular biology analysis suite")
7450 (description "EMBOSS is the \"European Molecular Biology Open Software
7451 Suite\". EMBOSS is an analysis package specially developed for the needs of
7452 the molecular biology (e.g. EMBnet) user community. The software
7453 automatically copes with data in a variety of formats and even allows
7454 transparent retrieval of sequence data from the web. It also provides a
7455 number of libraries for the development of software in the field of molecular
7456 biology. EMBOSS also integrates a range of currently available packages and
7457 tools for sequence analysis into a seamless whole.")
7458 (license license:gpl2+)))
7461 (let ((revision "1")
7462 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
7465 ;; The version is 2.13.0 even though no release archives have been
7466 ;; published as yet.
7467 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
7471 (url "https://github.com/arq5x/bits.git")
7473 (file-name (string-append name "-" version "-checkout"))
7476 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
7477 (build-system gnu-build-system)
7479 `(#:tests? #f ;no tests included
7481 (modify-phases %standard-phases
7483 (add-after 'unpack 'remove-cuda
7485 (substitute* "Makefile"
7487 (("(bits_test_intersections) \\\\" _ match) match))
7490 (lambda* (#:key outputs #:allow-other-keys)
7492 "bin" (string-append (assoc-ref outputs "out") "/bin"))
7497 (home-page "https://github.com/arq5x/bits")
7498 (synopsis "Implementation of binary interval search algorithm")
7499 (description "This package provides an implementation of the
7500 BITS (Binary Interval Search) algorithm, an approach to interval set
7501 intersection. It is especially suited for the comparison of diverse genomic
7502 datasets and the exploration of large datasets of genome
7503 intervals (e.g. genes, sequence alignments).")
7504 (license license:gpl2))))
7506 (define-public piranha
7507 ;; There is no release tarball for the latest version. The latest commit is
7508 ;; older than one year at the time of this writing.
7509 (let ((revision "1")
7510 (commit "0466d364b71117d01e4471b74c514436cc281233"))
7513 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
7517 (url "https://github.com/smithlabcode/piranha.git")
7521 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
7522 (build-system gnu-build-system)
7524 `(#:test-target "test"
7526 (modify-phases %standard-phases
7527 (add-after 'unpack 'copy-smithlab-cpp
7528 (lambda* (#:key inputs #:allow-other-keys)
7529 (for-each (lambda (file)
7530 (install-file file "./src/smithlab_cpp/"))
7531 (find-files (assoc-ref inputs "smithlab-cpp")))
7533 (add-after 'install 'install-to-store
7534 (lambda* (#:key outputs #:allow-other-keys)
7535 (let* ((out (assoc-ref outputs "out"))
7536 (bin (string-append out "/bin")))
7538 (for-each (lambda (file)
7539 (install-file file bin))
7540 (find-files "bin" ".*")))
7543 (list (string-append "--with-bam_tools_headers="
7544 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
7545 (string-append "--with-bam_tools_library="
7546 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
7548 `(("bamtools" ,bamtools)
7549 ("samtools" ,samtools-0.1)
7552 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
7556 (url "https://github.com/smithlabcode/smithlab_cpp.git")
7558 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
7561 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
7563 `(("python" ,python-2)))
7564 (home-page "https://github.com/smithlabcode/piranha")
7565 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
7567 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
7568 RIP-seq experiments. It takes input in BED or BAM format and identifies
7569 regions of statistically significant read enrichment. Additional covariates
7570 may optionally be provided to further inform the peak-calling process.")
7571 (license license:gpl3+))))
7579 (uri (string-append "https://pypi.python.org/packages/source/P"
7580 "/PePr/PePr-" version ".tar.gz"))
7583 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
7584 (build-system python-build-system)
7586 `(#:python ,python-2 ; python2 only
7587 #:tests? #f ; no tests included
7589 (modify-phases %standard-phases
7590 ;; When setuptools is used a ".egg" archive is generated and
7591 ;; installed. This makes it hard to actually run PePr. This issue
7592 ;; has been reported upstream:
7593 ;; https://github.com/shawnzhangyx/PePr/issues/9
7594 (add-after 'unpack 'disable-egg-generation
7596 (substitute* "setup.py"
7597 (("from setuptools import setup")
7598 "from distutils.core import setup"))
7601 `(("python2-numpy" ,python2-numpy)
7602 ("python2-scipy" ,python2-scipy)
7603 ("python2-pysam" ,python2-pysam)))
7604 (home-page "https://code.google.com/p/pepr-chip-seq/")
7605 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
7607 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
7608 that is primarily designed for data with biological replicates. It uses a
7609 negative binomial distribution to model the read counts among the samples in
7610 the same group, and look for consistent differences between ChIP and control
7611 group or two ChIP groups run under different conditions.")
7612 (license license:gpl3+)))
7614 (define-public filevercmp
7615 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
7618 (version (string-append "0-1." (string-take commit 7)))
7621 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
7623 (file-name (string-append name "-" version ".tar.gz"))
7625 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
7626 (build-system gnu-build-system)
7628 `(#:tests? #f ; There are no tests to run.
7630 (modify-phases %standard-phases
7631 (delete 'configure) ; There is no configure phase.
7633 (lambda* (#:key outputs #:allow-other-keys)
7634 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7635 (install-file "filevercmp" bin)))))))
7636 (home-page "https://github.com/ekg/filevercmp")
7637 (synopsis "This program compares version strings")
7638 (description "This program compares version strings. It intends to be a
7639 replacement for strverscmp.")
7640 (license license:gpl3+))))
7642 (define-public multiqc
7649 (uri (pypi-uri "multiqc" version))
7652 "0avw11h63ldpxy5pizc3wl1wa01ha7q10wb240nggsjz3jaqvyiy"))))
7653 (build-system python-build-system)
7655 `(("python-jinja2" ,python-jinja2)
7656 ("python-simplejson" ,python-simplejson)
7657 ("python-pyyaml" ,python-pyyaml)
7658 ("python-click" ,python-click)
7659 ("python-matplotlib" ,python-matplotlib)
7660 ("python-numpy" ,python-numpy)))
7662 `(("python-setuptools" ,python-setuptools)))
7663 (home-page "http://multiqc.info")
7664 (synopsis "Aggregate bioinformatics analysis reports")
7666 "MultiQC is a tool to aggregate bioinformatics results across many
7667 samples into a single report. It contains modules for a large number of
7668 common bioinformatics tools.")
7669 (license license:gpl3)))