1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017 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>
9 ;;; Copyright © 2016 Raoul Bonnal <ilpuccio.febo@gmail.com>
11 ;;; This file is part of GNU Guix.
13 ;;; GNU Guix is free software; you can redistribute it and/or modify it
14 ;;; under the terms of the GNU General Public License as published by
15 ;;; the Free Software Foundation; either version 3 of the License, or (at
16 ;;; your option) any later version.
18 ;;; GNU Guix is distributed in the hope that it will be useful, but
19 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
20 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21 ;;; GNU General Public License for more details.
23 ;;; You should have received a copy of the GNU General Public License
24 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
26 (define-module (gnu packages bioinformatics)
27 #:use-module ((guix licenses) #:prefix license:)
28 #:use-module (guix packages)
29 #:use-module (guix utils)
30 #:use-module (guix download)
31 #:use-module (guix git-download)
32 #:use-module (guix hg-download)
33 #:use-module (guix build-system ant)
34 #:use-module (guix build-system gnu)
35 #:use-module (guix build-system cmake)
36 #:use-module (guix build-system perl)
37 #:use-module (guix build-system python)
38 #:use-module (guix build-system r)
39 #:use-module (guix build-system ruby)
40 #:use-module (guix build-system trivial)
41 #:use-module (gnu packages)
42 #:use-module (gnu packages autotools)
43 #:use-module (gnu packages algebra)
44 #:use-module (gnu packages base)
45 #:use-module (gnu packages bash)
46 #:use-module (gnu packages bison)
47 #:use-module (gnu packages boost)
48 #:use-module (gnu packages compression)
49 #:use-module (gnu packages cpio)
50 #:use-module (gnu packages curl)
51 #:use-module (gnu packages documentation)
52 #:use-module (gnu packages datastructures)
53 #:use-module (gnu packages file)
54 #:use-module (gnu packages flex)
55 #:use-module (gnu packages gawk)
56 #:use-module (gnu packages gcc)
57 #:use-module (gnu packages gd)
58 #:use-module (gnu packages gtk)
59 #:use-module (gnu packages glib)
60 #:use-module (gnu packages groff)
61 #:use-module (gnu packages guile)
62 #:use-module (gnu packages haskell)
63 #:use-module (gnu packages image)
64 #:use-module (gnu packages imagemagick)
65 #:use-module (gnu packages java)
66 #:use-module (gnu packages linux)
67 #:use-module (gnu packages logging)
68 #:use-module (gnu packages machine-learning)
69 #:use-module (gnu packages man)
70 #:use-module (gnu packages maths)
71 #:use-module (gnu packages mpi)
72 #:use-module (gnu packages ncurses)
73 #:use-module (gnu packages pcre)
74 #:use-module (gnu packages parallel)
75 #:use-module (gnu packages pdf)
76 #:use-module (gnu packages perl)
77 #:use-module (gnu packages pkg-config)
78 #:use-module (gnu packages popt)
79 #:use-module (gnu packages protobuf)
80 #:use-module (gnu packages python)
81 #:use-module (gnu packages readline)
82 #:use-module (gnu packages ruby)
83 #:use-module (gnu packages serialization)
84 #:use-module (gnu packages statistics)
85 #:use-module (gnu packages tbb)
86 #:use-module (gnu packages tex)
87 #:use-module (gnu packages texinfo)
88 #:use-module (gnu packages textutils)
89 #:use-module (gnu packages time)
90 #:use-module (gnu packages tls)
91 #:use-module (gnu packages vim)
92 #:use-module (gnu packages web)
93 #:use-module (gnu packages xml)
94 #:use-module (gnu packages xorg)
95 #:use-module (gnu packages zip)
96 #:use-module (srfi srfi-1))
98 (define-public aragorn
105 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
109 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
110 (build-system gnu-build-system)
112 `(#:tests? #f ; there are no tests
114 (modify-phases %standard-phases
118 (zero? (system* "gcc"
124 (string-append "aragorn" ,version ".c")))))
126 (lambda* (#:key outputs #:allow-other-keys)
127 (let* ((out (assoc-ref outputs "out"))
128 (bin (string-append out "/bin"))
129 (man (string-append out "/share/man/man1")))
132 (string-append bin "/aragorn"))
134 (copy-file "aragorn.1"
135 (string-append man "/aragorn.1")))
137 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
138 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
140 "Aragorn identifies transfer RNA, mitochondrial RNA and
141 transfer-messenger RNA from nucleotide sequences, based on homology to known
142 tRNA consensus sequences and RNA structure. It also outputs the secondary
143 structure of the predicted RNA.")
144 (license license:gpl2)))
152 ;; BamM is not available on pypi.
154 "https://github.com/Ecogenomics/BamM/archive/"
156 (file-name (string-append name "-" version ".tar.gz"))
159 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
160 (modules '((guix build utils)))
163 ;; Delete bundled htslib.
164 (delete-file-recursively "c/htslib-1.3.1")
166 (build-system python-build-system)
168 `(#:python ,python-2 ; BamM is Python 2 only.
169 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
170 ;; been modified from its original form.
172 (let ((htslib (assoc-ref %build-inputs "htslib")))
173 (list "--with-libhts-lib" (string-append htslib "/lib")
174 "--with-libhts-inc" (string-append htslib "/include/htslib")))
176 (modify-phases %standard-phases
177 (add-after 'unpack 'autogen
179 (with-directory-excursion "c"
180 (let ((sh (which "sh")))
181 ;; Use autogen so that 'configure' works.
182 (substitute* "autogen.sh" (("/bin/sh") sh))
183 (setenv "CONFIG_SHELL" sh)
184 (substitute* "configure" (("/bin/sh") sh))
185 (zero? (system* "./autogen.sh"))))))
187 ;; Run tests after installation so compilation only happens once.
189 (add-after 'install 'wrap-executable
190 (lambda* (#:key outputs #:allow-other-keys)
191 (let* ((out (assoc-ref outputs "out"))
192 (path (getenv "PATH")))
193 (wrap-program (string-append out "/bin/bamm")
194 `("PATH" ":" prefix (,path))))
196 (add-after 'wrap-executable 'post-install-check
197 (lambda* (#:key inputs outputs #:allow-other-keys)
199 (string-append (assoc-ref outputs "out")
204 (assoc-ref outputs "out")
206 (string-take (string-take-right
207 (assoc-ref inputs "python") 5) 3)
209 (getenv "PYTHONPATH")))
210 ;; There are 2 errors printed, but they are safe to ignore:
211 ;; 1) [E::hts_open_format] fail to open file ...
212 ;; 2) samtools view: failed to open ...
213 (zero? (system* "nosetests")))))))
215 `(("autoconf" ,autoconf)
216 ("automake" ,automake)
219 ("python-nose" ,python2-nose)
220 ("python-pysam" ,python2-pysam)))
223 ("samtools" ,samtools)
227 ("coreutils" ,coreutils)))
229 `(("python-numpy" ,python2-numpy)))
230 (home-page "http://ecogenomics.github.io/BamM/")
231 (synopsis "Metagenomics-focused BAM file manipulator")
233 "BamM is a C library, wrapped in python, to efficiently generate and
234 parse BAM files, specifically for the analysis of metagenomic data. For
235 instance, it implements several methods to assess contig-wise read coverage.")
236 (license license:lgpl3+)))
238 (define-public bamtools
245 "https://github.com/pezmaster31/bamtools/archive/v"
247 (file-name (string-append name "-" version ".tar.gz"))
250 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
251 (build-system cmake-build-system)
253 `(#:tests? #f ;no "check" target
255 (modify-phases %standard-phases
257 'configure 'set-ldflags
258 (lambda* (#:key outputs #:allow-other-keys)
262 (assoc-ref outputs "out") "/lib/bamtools")))))))
263 (inputs `(("zlib" ,zlib)))
264 (home-page "https://github.com/pezmaster31/bamtools")
265 (synopsis "C++ API and command-line toolkit for working with BAM data")
267 "BamTools provides both a C++ API and a command-line toolkit for handling
269 (license license:expat)))
271 (define-public bcftools
278 "https://github.com/samtools/bcftools/releases/download/"
279 version "/bcftools-" version ".tar.bz2"))
282 "095ry68vmz9q5s1scjsa698dhgyvgw5aicz24c19iwfbai07mhqj"))
283 (modules '((guix build utils)))
285 ;; Delete bundled htslib.
286 '(delete-file-recursively "htslib-1.3.1"))))
287 (build-system gnu-build-system)
289 `(#:test-target "test"
293 (string-append "prefix=" (assoc-ref %outputs "out"))
294 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
295 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.a")
296 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
297 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix"))
299 (modify-phases %standard-phases
300 (add-after 'unpack 'patch-Makefile
302 (substitute* "Makefile"
303 ;; Do not attempt to build htslib.
304 (("^include \\$\\(HTSDIR\\)/htslib\\.mk") "")
305 ;; Link against GSL cblas.
306 (("-lcblas") "-lgslcblas"))
309 (add-before 'check 'patch-tests
311 (substitute* "test/test.pl"
312 (("/bin/bash") (which "bash")))
320 (home-page "https://samtools.github.io/bcftools/")
321 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
323 "BCFtools is a set of utilities that manipulate variant calls in the
324 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
325 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
326 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
327 (license (list license:gpl3+ license:expat))))
329 (define-public bedops
335 (uri (string-append "https://github.com/bedops/bedops/archive/v"
337 (file-name (string-append name "-" version ".tar.gz"))
340 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
341 (build-system gnu-build-system)
344 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
347 'unpack 'unpack-tarballs
349 ;; FIXME: Bedops includes tarballs of minimally patched upstream
350 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
351 ;; libraries because at least one of the libraries (zlib) is
352 ;; patched to add a C++ function definition (deflateInit2cpp).
353 ;; Until the Bedops developers offer a way to link against system
354 ;; libraries we have to build the in-tree copies of these three
357 ;; See upstream discussion:
358 ;; https://github.com/bedops/bedops/issues/124
360 ;; Unpack the tarballs to benefit from shebang patching.
361 (with-directory-excursion "third-party"
362 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
363 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
364 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
365 ;; Disable unpacking of tarballs in Makefile.
366 (substitute* "system.mk/Makefile.linux"
367 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
368 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
369 (substitute* "third-party/zlib-1.2.7/Makefile.in"
370 (("^SHELL=.*$") "SHELL=bash\n")))
371 (alist-delete 'configure %standard-phases))))
372 (home-page "https://github.com/bedops/bedops")
373 (synopsis "Tools for high-performance genomic feature operations")
375 "BEDOPS is a suite of tools to address common questions raised in genomic
376 studies---mostly with regard to overlap and proximity relationships between
377 data sets. It aims to be scalable and flexible, facilitating the efficient
378 and accurate analysis and management of large-scale genomic data.
380 BEDOPS provides tools that perform highly efficient and scalable Boolean and
381 other set operations, statistical calculations, archiving, conversion and
382 other management of genomic data of arbitrary scale. Tasks can be easily
383 split by chromosome for distributing whole-genome analyses across a
384 computational cluster.")
385 (license license:gpl2+)))
387 (define-public bedtools
393 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
395 (file-name (string-append name "-" version ".tar.gz"))
398 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
399 (build-system gnu-build-system)
400 (native-inputs `(("python" ,python-2)))
401 (inputs `(("samtools" ,samtools)
404 '(#:test-target "test"
406 (modify-phases %standard-phases
409 (lambda* (#:key outputs #:allow-other-keys)
410 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
411 (for-each (lambda (file)
412 (install-file file bin))
413 (find-files "bin" ".*")))
415 (home-page "https://github.com/arq5x/bedtools2")
416 (synopsis "Tools for genome analysis and arithmetic")
418 "Collectively, the bedtools utilities are a swiss-army knife of tools for
419 a wide-range of genomics analysis tasks. The most widely-used tools enable
420 genome arithmetic: that is, set theory on the genome. For example, bedtools
421 allows one to intersect, merge, count, complement, and shuffle genomic
422 intervals from multiple files in widely-used genomic file formats such as BAM,
424 (license license:gpl2)))
426 ;; Later releases of bedtools produce files with more columns than
427 ;; what Ribotaper expects.
428 (define-public bedtools-2.18
429 (package (inherit bedtools)
434 (uri (string-append "https://github.com/arq5x/bedtools2/"
435 "archive/v" version ".tar.gz"))
436 (file-name (string-append name "-" version ".tar.gz"))
439 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
441 (define-public ribotaper
447 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
448 "files/RiboTaper/RiboTaper_Version_"
452 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
453 (build-system gnu-build-system)
455 `(("bedtools" ,bedtools-2.18)
456 ("samtools" ,samtools-0.1)
458 ("r-foreach" ,r-foreach)
459 ("r-xnomial" ,r-xnomial)
461 ("r-multitaper" ,r-multitaper)
462 ("r-seqinr" ,r-seqinr)))
463 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
464 (synopsis "Define translated ORFs using ribosome profiling data")
466 "Ribotaper is a method for defining translated @dfn{open reading
467 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
468 provides the Ribotaper pipeline.")
469 (license license:gpl3+)))
471 (define-public ribodiff
478 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
479 "archive/v" version ".tar.gz"))
480 (file-name (string-append name "-" version ".tar.gz"))
483 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
484 (build-system python-build-system)
488 (modify-phases %standard-phases
489 ;; Generate an installable executable script wrapper.
490 (add-after 'unpack 'patch-setup.py
492 (substitute* "setup.py"
493 (("^(.*)packages=.*" line prefix)
494 (string-append line "\n"
495 prefix "scripts=['scripts/TE.py'],\n")))
498 `(("python-numpy" ,python2-numpy)
499 ("python-matplotlib" ,python2-matplotlib)
500 ("python-scipy" ,python2-scipy)
501 ("python-statsmodels" ,python2-statsmodels)))
503 `(("python-mock" ,python2-mock)
504 ("python-nose" ,python2-nose)))
505 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
506 (synopsis "Detect translation efficiency changes from ribosome footprints")
507 (description "RiboDiff is a statistical tool that detects the protein
508 translational efficiency change from Ribo-Seq (ribosome footprinting) and
509 RNA-Seq data. It uses a generalized linear model to detect genes showing
510 difference in translational profile taking mRNA abundance into account. It
511 facilitates us to decipher the translational regulation that behave
512 independently with transcriptional regulation.")
513 (license license:gpl3+)))
515 (define-public bioawk
521 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
523 (file-name (string-append name "-" version ".tar.gz"))
525 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
526 (build-system gnu-build-system)
532 `(#:tests? #f ; There are no tests to run.
533 ;; Bison must generate files, before other targets can build.
536 (modify-phases %standard-phases
537 (delete 'configure) ; There is no configure phase.
539 (lambda* (#:key outputs #:allow-other-keys)
540 (let* ((out (assoc-ref outputs "out"))
541 (bin (string-append out "/bin"))
542 (man (string-append out "/share/man/man1")))
544 (copy-file "awk.1" (string-append man "/bioawk.1"))
545 (install-file "bioawk" bin)))))))
546 (home-page "https://github.com/lh3/bioawk")
547 (synopsis "AWK with bioinformatics extensions")
548 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
549 support of several common biological data formats, including optionally gzip'ed
550 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
551 also adds a few built-in functions and a command line option to use TAB as the
552 input/output delimiter. When the new functionality is not used, bioawk is
553 intended to behave exactly the same as the original BWK awk.")
554 (license license:x11)))
556 (define-public python2-pybedtools
558 (name "python2-pybedtools")
563 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
567 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
568 (build-system python-build-system)
569 (arguments `(#:python ,python-2)) ; no Python 3 support
571 `(("python-matplotlib" ,python2-matplotlib)))
573 `(("bedtools" ,bedtools)
574 ("samtools" ,samtools)))
576 `(("python-cython" ,python2-cython)
577 ("python-pyyaml" ,python2-pyyaml)
578 ("python-nose" ,python2-nose)))
579 (home-page "https://pythonhosted.org/pybedtools/")
580 (synopsis "Python wrapper for BEDtools programs")
582 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
583 which are widely used for genomic interval manipulation or \"genome algebra\".
584 pybedtools extends BEDTools by offering feature-level manipulations from with
586 (license license:gpl2+)))
588 (define-public python-biom-format
590 (name "python-biom-format")
595 ;; Use GitHub as source because PyPI distribution does not contain
596 ;; test data: https://github.com/biocore/biom-format/issues/693
597 (uri (string-append "https://github.com/biocore/biom-format/archive/"
599 (file-name (string-append name "-" version ".tar.gz"))
602 "1n25w3p1rixbpac8iysmzcja6m4ip5r6sz19l8y6wlwi49hxn278"))))
603 (build-system python-build-system)
605 `(("python-numpy" ,python-numpy)
606 ("python-scipy" ,python-scipy)
607 ("python-future" ,python-future)
608 ("python-click" ,python-click)
609 ("python-h5py" ,python-h5py)))
611 `(("python-nose" ,python-nose)))
612 (home-page "http://www.biom-format.org")
613 (synopsis "Biological Observation Matrix (BIOM) format utilities")
615 "The BIOM file format is designed to be a general-use format for
616 representing counts of observations e.g. operational taxonomic units, KEGG
617 orthology groups or lipid types, in one or more biological samples
618 e.g. microbiome samples, genomes, metagenomes.")
619 (license license:bsd-3)
620 (properties `((python2-variant . ,(delay python2-biom-format))))))
622 (define-public python2-biom-format
623 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
628 (modify-phases %standard-phases
629 ;; Do not require the unmaintained pyqi library.
630 (add-after 'unpack 'remove-pyqi
632 (substitute* "setup.py"
633 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
635 ,@(package-arguments base))))))
637 (define-public bioperl-minimal
638 (let* ((inputs `(("perl-module-build" ,perl-module-build)
639 ("perl-data-stag" ,perl-data-stag)
640 ("perl-libwww" ,perl-libwww)
641 ("perl-uri" ,perl-uri)))
643 (map (compose package-name cadr)
646 (map (compose package-transitive-target-inputs cadr) inputs))))))
648 (name "bioperl-minimal")
653 (uri (string-append "https://github.com/bioperl/bioperl-live/"
655 (string-map (lambda (c)
661 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
662 (build-system perl-build-system)
665 (modify-phases %standard-phases
667 'install 'wrap-programs
668 (lambda* (#:key outputs #:allow-other-keys)
669 ;; Make sure all executables in "bin" find the required Perl
670 ;; modules at runtime. As the PERL5LIB variable contains also
671 ;; the paths of native inputs, we pick the transitive target
672 ;; inputs from %build-inputs.
673 (let* ((out (assoc-ref outputs "out"))
674 (bin (string-append out "/bin/"))
676 (cons (string-append out "/lib/perl5/site_perl")
678 (assoc-ref %build-inputs name))
679 ',transitive-inputs))
681 (for-each (lambda (file)
683 `("PERL5LIB" ":" prefix (,path))))
684 (find-files bin "\\.pl$"))
688 `(("perl-test-most" ,perl-test-most)))
689 (home-page "http://search.cpan.org/dist/BioPerl")
690 (synopsis "Bioinformatics toolkit")
692 "BioPerl is the product of a community effort to produce Perl code which
693 is useful in biology. Examples include Sequence objects, Alignment objects
694 and database searching objects. These objects not only do what they are
695 advertised to do in the documentation, but they also interact - Alignment
696 objects are made from the Sequence objects, Sequence objects have access to
697 Annotation and SeqFeature objects and databases, Blast objects can be
698 converted to Alignment objects, and so on. This means that the objects
699 provide a coordinated and extensible framework to do computational biology.")
700 (license (package-license perl)))))
702 (define-public python-biopython
704 (name "python-biopython")
708 ;; use PyPi rather than biopython.org to ease updating
709 (uri (pypi-uri "biopython" version))
712 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
713 (build-system python-build-system)
716 (modify-phases %standard-phases
717 (add-before 'check 'set-home
718 ;; Some tests require a home directory to be set.
719 (lambda _ (setenv "HOME" "/tmp") #t)))))
721 `(("python-numpy" ,python-numpy)))
722 (home-page "http://biopython.org/")
723 (synopsis "Tools for biological computation in Python")
725 "Biopython is a set of tools for biological computation including parsers
726 for bioinformatics files into Python data structures; interfaces to common
727 bioinformatics programs; a standard sequence class and tools for performing
728 common operations on them; code to perform data classification; code for
729 dealing with alignments; code making it easy to split up parallelizable tasks
730 into separate processes; and more.")
731 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
733 (define-public python2-biopython
734 (package-with-python2 python-biopython))
736 ;; An outdated version of biopython is required for seqmagick, see
737 ;; https://github.com/fhcrc/seqmagick/issues/59
738 ;; When that issue has been resolved this package should be removed.
739 (define python2-biopython-1.66
741 (inherit python2-biopython)
745 (uri (pypi-uri "biopython" version))
748 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
750 (define-public bpp-core
751 ;; The last release was in 2014 and the recommended way to install from source
752 ;; is to clone the git repository, so we do this.
753 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
754 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
757 (version (string-append "2.2.0-1." (string-take commit 7)))
761 (url "http://biopp.univ-montp2.fr/git/bpp-core")
763 (file-name (string-append name "-" version "-checkout"))
766 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
767 (build-system cmake-build-system)
769 `(#:parallel-build? #f))
771 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
772 ; compile all of the bpp packages with GCC 5.
773 (home-page "http://biopp.univ-montp2.fr")
774 (synopsis "C++ libraries for Bioinformatics")
776 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
777 analysis, phylogenetics, molecular evolution and population genetics. It is
778 Object Oriented and is designed to be both easy to use and computer efficient.
779 Bio++ intends to help programmers to write computer expensive programs, by
780 providing them a set of re-usable tools.")
781 (license license:cecill-c))))
783 (define-public bpp-phyl
784 ;; The last release was in 2014 and the recommended way to install from source
785 ;; is to clone the git repository, so we do this.
786 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
787 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
790 (version (string-append "2.2.0-1." (string-take commit 7)))
794 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
796 (file-name (string-append name "-" version "-checkout"))
799 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
800 (build-system cmake-build-system)
802 `(#:parallel-build? #f
803 ;; If out-of-source, test data is not copied into the build directory
804 ;; so the tests fail.
805 #:out-of-source? #f))
807 `(("bpp-core" ,bpp-core)
809 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
812 (home-page "http://biopp.univ-montp2.fr")
813 (synopsis "Bio++ phylogenetic Library")
815 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
816 analysis, phylogenetics, molecular evolution and population genetics. This
817 library provides phylogenetics-related modules.")
818 (license license:cecill-c))))
820 (define-public bpp-popgen
821 ;; The last release was in 2014 and the recommended way to install from source
822 ;; is to clone the git repository, so we do this.
823 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
824 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
827 (version (string-append "2.2.0-1." (string-take commit 7)))
831 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
833 (file-name (string-append name "-" version "-checkout"))
836 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
837 (build-system cmake-build-system)
839 `(#:parallel-build? #f
840 #:tests? #f)) ; There are no tests.
842 `(("bpp-core" ,bpp-core)
845 (home-page "http://biopp.univ-montp2.fr")
846 (synopsis "Bio++ population genetics library")
848 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
849 analysis, phylogenetics, molecular evolution and population genetics. This
850 library provides population genetics-related modules.")
851 (license license:cecill-c))))
853 (define-public bpp-seq
854 ;; The last release was in 2014 and the recommended way to install from source
855 ;; is to clone the git repository, so we do this.
856 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
857 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
860 (version (string-append "2.2.0-1." (string-take commit 7)))
864 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
866 (file-name (string-append name "-" version "-checkout"))
869 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
870 (build-system cmake-build-system)
872 `(#:parallel-build? #f
873 ;; If out-of-source, test data is not copied into the build directory
874 ;; so the tests fail.
875 #:out-of-source? #f))
877 `(("bpp-core" ,bpp-core)
878 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
879 (home-page "http://biopp.univ-montp2.fr")
880 (synopsis "Bio++ sequence library")
882 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
883 analysis, phylogenetics, molecular evolution and population genetics. This
884 library provides sequence-related modules.")
885 (license license:cecill-c))))
887 (define-public bppsuite
888 ;; The last release was in 2014 and the recommended way to install from source
889 ;; is to clone the git repository, so we do this.
890 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
891 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
894 (version (string-append "2.2.0-1." (string-take commit 7)))
898 (url "http://biopp.univ-montp2.fr/git/bppsuite")
900 (file-name (string-append name "-" version "-checkout"))
903 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
904 (build-system cmake-build-system)
906 `(#:parallel-build? #f
907 #:tests? #f)) ; There are no tests.
911 ("texinfo" ,texinfo)))
913 `(("bpp-core" ,bpp-core)
915 ("bpp-phyl" ,bpp-phyl)
916 ("bpp-phyl" ,bpp-popgen)
918 (home-page "http://biopp.univ-montp2.fr")
919 (synopsis "Bioinformatics tools written with the Bio++ libraries")
921 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
922 analysis, phylogenetics, molecular evolution and population genetics. This
923 package provides command line tools using the Bio++ library.")
924 (license license:cecill-c))))
926 (define-public blast+
933 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
934 version "/ncbi-blast-" version "+-src.tar.gz"))
937 "14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
938 (modules '((guix build utils)))
941 ;; Remove bundled bzip2 and zlib
942 (delete-file-recursively "c++/src/util/compress/bzip2")
943 (delete-file-recursively "c++/src/util/compress/zlib")
944 (substitute* "c++/src/util/compress/Makefile.in"
945 (("bzip2 zlib api") "api"))
946 ;; Remove useless msbuild directory
947 (delete-file-recursively
948 "c++/src/build-system/project_tree_builder/msbuild")
950 (build-system gnu-build-system)
952 `(;; There are three(!) tests for this massive library, and all fail with
953 ;; "unparsable timing stats".
954 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
955 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
956 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
959 #:parallel-build? #f ; not supported
961 (modify-phases %standard-phases
964 ;; $HOME needs to be set at some point during the configure phase
965 (lambda _ (setenv "HOME" "/tmp") #t))
968 (lambda _ (chdir "c++") #t))
970 'enter-dir 'fix-build-system
973 (cond ((string=? cmd "date")
974 ;; make call to "date" deterministic
979 (format (current-error-port)
980 "WARNING: Unable to find absolute path for ~s~%"
984 ;; Rewrite hardcoded paths to various tools
985 (substitute* (append '("src/build-system/configure.ac"
986 "src/build-system/configure"
987 "scripts/common/impl/if_diff.sh"
988 "scripts/common/impl/run_with_lock.sh"
989 "src/build-system/Makefile.configurables.real"
990 "src/build-system/Makefile.in.top"
991 "src/build-system/Makefile.meta.gmake=no"
992 "src/build-system/Makefile.meta.in"
993 "src/build-system/Makefile.meta_l"
994 "src/build-system/Makefile.meta_p"
995 "src/build-system/Makefile.meta_r"
996 "src/build-system/Makefile.mk.in"
997 "src/build-system/Makefile.requirements"
998 "src/build-system/Makefile.rules_with_autodep.in")
999 (find-files "scripts/common/check" "\\.sh$"))
1000 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1001 (or (which* cmd) all)))
1003 (substitute* (find-files "src/build-system" "^config.*")
1004 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1007 ;; rewrite "/var/tmp" in check script
1008 (substitute* "scripts/common/check/check_make_unix.sh"
1009 (("/var/tmp") "/tmp"))
1011 ;; do not reset PATH
1012 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1014 (("action=/bin/") "action=")
1015 (("export PATH") ":"))
1019 (lambda* (#:key inputs outputs #:allow-other-keys)
1020 (let ((out (assoc-ref outputs "out"))
1021 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1022 (include (string-append (assoc-ref outputs "include")
1023 "/include/ncbi-tools++")))
1024 ;; The 'configure' script doesn't recognize things like
1025 ;; '--enable-fast-install'.
1026 (zero? (system* "./configure.orig"
1027 (string-append "--with-build-root=" (getcwd) "/build")
1028 (string-append "--prefix=" out)
1029 (string-append "--libdir=" lib)
1030 (string-append "--includedir=" include)
1031 (string-append "--with-bz2="
1032 (assoc-ref inputs "bzip2"))
1033 (string-append "--with-z="
1034 (assoc-ref inputs "zlib"))
1035 ;; Each library is built twice by default, once
1036 ;; with "-static" in its name, and again
1039 "--with-dll"))))))))
1040 (outputs '("out" ; 19 MB
1048 (home-page "http://blast.ncbi.nlm.nih.gov")
1049 (synopsis "Basic local alignment search tool")
1051 "BLAST is a popular method of performing a DNA or protein sequence
1052 similarity search, using heuristics to produce results quickly. It also
1053 calculates an “expect value” that estimates how many matches would have
1054 occurred at a given score by chance, which can aid a user in judging how much
1055 confidence to have in an alignment.")
1056 ;; Most of the sources are in the public domain, with the following
1059 ;; * ./c++/include/util/bitset/
1060 ;; * ./c++/src/html/ncbi_menu*.js
1062 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1064 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1066 ;; * ./c++/src/corelib/teamcity_*
1067 (license (list license:public-domain
1073 (define-public bless
1079 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1083 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1084 (modules '((guix build utils)))
1087 ;; Remove bundled boost, pigz, zlib, and .git directory
1088 ;; FIXME: also remove bundled sources for murmurhash3 and
1089 ;; kmc once packaged.
1090 (delete-file-recursively "boost")
1091 (delete-file-recursively "pigz")
1092 (delete-file-recursively "google-sparsehash")
1093 (delete-file-recursively "zlib")
1094 (delete-file-recursively ".git")
1096 (build-system gnu-build-system)
1098 '(#:tests? #f ;no "check" target
1100 (list (string-append "ZLIB="
1101 (assoc-ref %build-inputs "zlib")
1103 (string-append "LDFLAGS="
1104 (string-join '("-lboost_filesystem"
1111 (modify-phases %standard-phases
1112 (add-after 'unpack 'do-not-build-bundled-pigz
1113 (lambda* (#:key inputs outputs #:allow-other-keys)
1114 (substitute* "Makefile"
1115 (("cd pigz/pigz-2.3.3; make") ""))
1117 (add-after 'unpack 'patch-paths-to-executables
1118 (lambda* (#:key inputs outputs #:allow-other-keys)
1119 (substitute* "parse_args.cpp"
1120 (("kmc_binary = .*")
1121 (string-append "kmc_binary = \""
1122 (assoc-ref outputs "out")
1124 (("pigz_binary = .*")
1125 (string-append "pigz_binary = \""
1126 (assoc-ref inputs "pigz")
1130 (lambda* (#:key outputs #:allow-other-keys)
1131 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1132 (for-each (lambda (file)
1133 (install-file file bin))
1134 '("bless" "kmc/bin/kmc"))
1136 (delete 'configure))))
1140 `(("openmpi" ,openmpi)
1142 ("sparsehash" ,sparsehash)
1145 (supported-systems '("x86_64-linux"))
1146 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1147 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1149 "@dfn{Bloom-filter-based error correction solution for high-throughput
1150 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1151 correction tool for genomic reads produced by @dfn{Next-generation
1152 sequencing} (NGS). BLESS produces accurate correction results with much less
1153 memory compared with previous solutions and is also able to tolerate a higher
1154 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1155 errors at the end of reads.")
1156 (license license:gpl3+)))
1158 (define-public bowtie
1164 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1166 (file-name (string-append name "-" version ".tar.gz"))
1169 "1vp5db8i7is57iwjybcdg18f5ivyzlj5g1ix1nlvxainzivhz55g"))
1170 (modules '((guix build utils)))
1172 '(substitute* "Makefile"
1173 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1174 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1175 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1176 (build-system gnu-build-system)
1177 (inputs `(("perl" ,perl)
1178 ("perl-clone" ,perl-clone)
1179 ("perl-test-deep" ,perl-test-deep)
1180 ("perl-test-simple" ,perl-test-simple)
1181 ("python" ,python-2)
1187 (string-append "prefix=" (assoc-ref %outputs "out")))
1193 (lambda* (#:key outputs #:allow-other-keys)
1195 "scripts/test/simple_tests.pl"
1196 "--bowtie2=./bowtie2"
1197 "--bowtie2-build=./bowtie2-build"))
1198 %standard-phases))))
1199 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1200 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1202 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1203 reads to long reference sequences. It is particularly good at aligning reads
1204 of about 50 up to 100s or 1,000s of characters, and particularly good at
1205 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1206 genome with an FM Index to keep its memory footprint small: for the human
1207 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1208 gapped, local, and paired-end alignment modes.")
1209 (supported-systems '("x86_64-linux"))
1210 (license license:gpl3+)))
1212 (define-public tophat
1219 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1223 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1224 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1225 (modules '((guix build utils)))
1228 ;; Remove bundled SeqAn and samtools
1229 (delete-file-recursively "src/SeqAn-1.3")
1230 (delete-file-recursively "src/samtools-0.1.18")
1232 (build-system gnu-build-system)
1234 '(#:parallel-build? #f ; not supported
1236 (modify-phases %standard-phases
1237 (add-after 'unpack 'use-system-samtools
1238 (lambda* (#:key inputs #:allow-other-keys)
1239 (substitute* "src/Makefile.in"
1240 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1241 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1242 (("SAMPROG = samtools_0\\.1\\.18") "")
1243 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1244 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1245 (substitute* '("src/common.cpp"
1247 (("samtools_0.1.18") (which "samtools")))
1248 (substitute* '("src/common.h"
1249 "src/bam2fastx.cpp")
1250 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1251 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1252 (substitute* '("src/bwt_map.h"
1254 "src/align_status.h")
1255 (("#include <bam.h>") "#include <samtools/bam.h>")
1256 (("#include <sam.h>") "#include <samtools/sam.h>"))
1261 ("samtools" ,samtools-0.1)
1262 ("ncurses" ,ncurses)
1263 ("python" ,python-2)
1267 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1268 (synopsis "Spliced read mapper for RNA-Seq data")
1270 "TopHat is a fast splice junction mapper for nucleotide sequence
1271 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1272 mammalian-sized genomes using the ultra high-throughput short read
1273 aligner Bowtie, and then analyzes the mapping results to identify
1274 splice junctions between exons.")
1275 ;; TopHat is released under the Boost Software License, Version 1.0
1276 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1277 (license license:boost1.0)))
1285 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1286 version ".tar.bz2"))
1289 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
1290 (build-system gnu-build-system)
1292 '(#:tests? #f ;no "check" target
1296 (lambda* (#:key outputs #:allow-other-keys)
1297 (let ((bin (string-append
1298 (assoc-ref outputs "out") "/bin"))
1300 (assoc-ref outputs "out") "/share/doc/bwa"))
1302 (assoc-ref outputs "out") "/share/man/man1")))
1303 (install-file "bwa" bin)
1304 (install-file "README.md" doc)
1305 (install-file "bwa.1" man)))
1306 ;; no "configure" script
1307 (alist-delete 'configure %standard-phases))))
1308 (inputs `(("zlib" ,zlib)))
1309 ;; Non-portable SSE instructions are used so building fails on platforms
1310 ;; other than x86_64.
1311 (supported-systems '("x86_64-linux"))
1312 (home-page "http://bio-bwa.sourceforge.net/")
1313 (synopsis "Burrows-Wheeler sequence aligner")
1315 "BWA is a software package for mapping low-divergent sequences against a
1316 large reference genome, such as the human genome. It consists of three
1317 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1318 designed for Illumina sequence reads up to 100bp, while the rest two for
1319 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1320 features such as long-read support and split alignment, but BWA-MEM, which is
1321 the latest, is generally recommended for high-quality queries as it is faster
1322 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1323 70-100bp Illumina reads.")
1324 (license license:gpl3+)))
1326 (define-public bwa-pssm
1327 (package (inherit bwa)
1332 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1333 "archive/" version ".tar.gz"))
1334 (file-name (string-append name "-" version ".tar.gz"))
1337 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1338 (build-system gnu-build-system)
1343 (home-page "http://bwa-pssm.binf.ku.dk/")
1344 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1346 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1347 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1348 existing aligners it is fast and sensitive. Unlike most other aligners,
1349 however, it is also adaptible in the sense that one can direct the alignment
1350 based on known biases within the data set. It is coded as a modification of
1351 the original BWA alignment program and shares the genome index structure as
1352 well as many of the command line options.")
1353 (license license:gpl3+)))
1355 (define-public python2-bx-python
1357 (name "python2-bx-python")
1362 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
1366 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
1367 (modules '((guix build utils)))
1369 '(substitute* "setup.py"
1370 ;; remove dependency on outdated "distribute" module
1371 (("^from distribute_setup import use_setuptools") "")
1372 (("^use_setuptools\\(\\)") "")))))
1373 (build-system python-build-system)
1375 `(#:tests? #f ;tests fail because test data are not included
1376 #:python ,python-2))
1378 `(("python-numpy" ,python2-numpy)
1381 `(("python-nose" ,python2-nose)))
1382 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1383 (synopsis "Tools for manipulating biological data")
1385 "bx-python provides tools for manipulating biological data, particularly
1386 multiple sequence alignments.")
1387 (license license:expat)))
1389 (define-public python-pysam
1391 (name "python-pysam")
1395 ;; Test data is missing on PyPi.
1397 "https://github.com/pysam-developers/pysam/archive/v"
1399 (file-name (string-append name "-" version ".tar.gz"))
1402 "0y41ssbg6nvn2jgcbnrvkzblpjcwszaiv1rgyd8dwzjkrbfsgsmc"))
1403 (modules '((guix build utils)))
1405 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1406 '(delete-file-recursively "htslib"))))
1407 (build-system python-build-system)
1410 (modify-phases %standard-phases
1411 (add-before 'build 'set-flags
1412 (lambda* (#:key inputs #:allow-other-keys)
1413 (setenv "HTSLIB_MODE" "external")
1414 (setenv "HTSLIB_LIBRARY_DIR"
1415 (string-append (assoc-ref inputs "htslib") "/lib"))
1416 (setenv "HTSLIB_INCLUDE_DIR"
1417 (string-append (assoc-ref inputs "htslib") "/include"))
1418 (setenv "LDFLAGS" "-lncurses")
1419 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1422 (add-after 'install 'check
1423 (lambda* (#:key inputs outputs #:allow-other-keys)
1424 (setenv "PYTHONPATH"
1426 (getenv "PYTHONPATH")
1427 ":" (assoc-ref outputs "out")
1429 (string-take (string-take-right
1430 (assoc-ref inputs "python") 5) 3)
1432 ;; Step out of source dir so python does not import from CWD.
1434 (setenv "HOME" "/tmp")
1435 (and (zero? (system* "make" "-C" "pysam_data"))
1436 (zero? (system* "make" "-C" "cbcf_data"))
1437 (zero? (system* "nosetests" "-v"))))))))
1439 `(("htslib" ,htslib))) ; Included from installed header files.
1441 `(("ncurses" ,ncurses)
1444 `(("python-cython" ,python-cython)
1445 ;; Dependencies below are are for tests only.
1446 ("samtools" ,samtools)
1447 ("bcftools" ,bcftools)
1448 ("python-nose" ,python-nose)))
1449 (home-page "https://github.com/pysam-developers/pysam")
1450 (synopsis "Python bindings to the SAMtools C API")
1452 "Pysam is a Python module for reading and manipulating files in the
1453 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1454 also includes an interface for tabix.")
1455 (license license:expat)))
1457 (define-public python2-pysam
1458 (package-with-python2 python-pysam))
1460 (define-public python-twobitreader
1462 (name "python-twobitreader")
1466 (uri (pypi-uri "twobitreader" version))
1469 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1470 (build-system python-build-system)
1472 '(;; Tests are not distributed in the PyPi release.
1473 ;; TODO Try building from the Git repo or asking the upstream maintainer
1474 ;; to distribute the tests on PyPi.
1477 `(("python-sphinx" ,python-sphinx)))
1478 (home-page "https://github.com/benjschiller/twobitreader")
1479 (synopsis "Python library for reading .2bit files")
1481 "twobitreader is a Python library for reading .2bit files as used by the
1482 UCSC genome browser.")
1483 (license license:artistic2.0)))
1485 (define-public python2-twobitreader
1486 (package-with-python2 python-twobitreader))
1488 (define-public python-plastid
1490 (name "python-plastid")
1494 (uri (pypi-uri "plastid" version))
1497 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
1498 (build-system python-build-system)
1500 ;; Some test files are not included.
1503 `(("python-numpy" ,python-numpy)
1504 ("python-scipy" ,python-scipy)
1505 ("python-pandas" ,python-pandas)
1506 ("python-pysam" ,python-pysam)
1507 ("python-matplotlib" ,python-matplotlib)
1508 ("python-biopython" ,python-biopython)
1509 ("python-twobitreader" ,python-twobitreader)
1510 ("python-termcolor" ,python-termcolor)))
1512 `(("python-cython" ,python-cython)
1513 ("python-nose" ,python-nose)))
1514 (home-page "https://github.com/joshuagryphon/plastid")
1515 (synopsis "Python library for genomic analysis")
1517 "plastid is a Python library for genomic analysis – in particular,
1518 high-throughput sequencing data – with an emphasis on simplicity.")
1519 (license license:bsd-3)))
1521 (define-public python2-plastid
1522 (package-with-python2 python-plastid))
1524 (define-public cd-hit
1530 (uri (string-append "https://github.com/weizhongli/cdhit"
1531 "/releases/download/V" version
1532 "/cd-hit-v" version "-2016-0711.tar.gz"))
1535 "1w8hd4fszgg29nqiz569fldwy012la77nljcmlhglgicws56z54p"))))
1536 (build-system gnu-build-system)
1538 `(#:tests? #f ; there are no tests
1540 ;; Executables are copied directly to the PREFIX.
1541 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1543 (modify-phases %standard-phases
1544 ;; No "configure" script
1546 ;; Remove sources of non-determinism
1547 (add-after 'unpack 'be-timeless
1549 (substitute* "cdhit-utility.c++"
1550 ((" \\(built on \" __DATE__ \"\\)") ""))
1551 (substitute* "cdhit-common.c++"
1552 (("__DATE__") "\"0\"")
1553 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1555 ;; The "install" target does not create the target directory
1556 (add-before 'install 'create-target-dir
1557 (lambda* (#:key outputs #:allow-other-keys)
1558 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1562 (home-page "http://weizhongli-lab.org/cd-hit/")
1563 (synopsis "Cluster and compare protein or nucleotide sequences")
1565 "CD-HIT is a program for clustering and comparing protein or nucleotide
1566 sequences. CD-HIT is designed to be fast and handle extremely large
1568 ;; The manual says: "It can be copied under the GNU General Public License
1569 ;; version 2 (GPLv2)."
1570 (license license:gpl2)))
1572 (define-public clipper
1579 "https://github.com/YeoLab/clipper/archive/"
1581 (file-name (string-append name "-" version ".tar.gz"))
1584 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1585 (modules '((guix build utils)))
1588 ;; remove unnecessary setup dependency
1589 (substitute* "setup.py"
1590 (("setup_requires = .*") ""))
1591 (for-each delete-file
1592 '("clipper/src/peaks.so"
1593 "clipper/src/readsToWiggle.so"))
1594 (delete-file-recursively "dist/")
1596 (build-system python-build-system)
1597 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1600 ("python-pybedtools" ,python2-pybedtools)
1601 ("python-cython" ,python2-cython)
1602 ("python-scikit-learn" ,python2-scikit-learn)
1603 ("python-matplotlib" ,python2-matplotlib)
1604 ("python-pandas" ,python2-pandas)
1605 ("python-pysam" ,python2-pysam)
1606 ("python-numpy" ,python2-numpy)
1607 ("python-scipy" ,python2-scipy)))
1609 `(("python-mock" ,python2-mock) ; for tests
1610 ("python-nose" ,python2-nose) ; for tests
1611 ("python-pytz" ,python2-pytz))) ; for tests
1612 (home-page "https://github.com/YeoLab/clipper")
1613 (synopsis "CLIP peak enrichment recognition")
1615 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1616 (license license:gpl2)))
1618 (define-public codingquarry
1620 (name "codingquarry")
1625 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1629 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1630 (build-system gnu-build-system)
1632 '(#:tests? #f ; no "check" target
1634 (modify-phases %standard-phases
1637 (lambda* (#:key outputs #:allow-other-keys)
1638 (let* ((out (assoc-ref outputs "out"))
1639 (bin (string-append out "/bin"))
1640 (doc (string-append out "/share/doc/codingquarry")))
1641 (install-file "INSTRUCTIONS.pdf" doc)
1642 (copy-recursively "QuarryFiles"
1643 (string-append out "/QuarryFiles"))
1644 (install-file "CodingQuarry" bin)
1645 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1646 (inputs `(("openmpi" ,openmpi)))
1647 (native-search-paths
1648 (list (search-path-specification
1649 (variable "QUARRY_PATH")
1650 (files '("QuarryFiles")))))
1651 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1652 (synopsis "Fungal gene predictor")
1653 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1654 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1655 (home-page "https://sourceforge.net/projects/codingquarry/")
1656 (license license:gpl3+)))
1658 (define-public couger
1665 "http://couger.oit.duke.edu/static/assets/COUGER"
1669 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1670 (build-system gnu-build-system)
1674 (modify-phases %standard-phases
1679 (lambda* (#:key outputs #:allow-other-keys)
1680 (let ((out (assoc-ref outputs "out")))
1681 (copy-recursively "src" (string-append out "/src"))
1682 (mkdir (string-append out "/bin"))
1683 ;; Add "src" directory to module lookup path.
1684 (substitute* "couger"
1686 (string-append "import sys\nsys.path.append(\""
1687 out "\")\nfrom argparse")))
1688 (copy-file "couger" (string-append out "/bin/couger")))
1691 'install 'wrap-program
1692 (lambda* (#:key inputs outputs #:allow-other-keys)
1693 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1694 (let* ((out (assoc-ref outputs "out"))
1695 (path (getenv "PYTHONPATH")))
1696 (wrap-program (string-append out "/bin/couger")
1697 `("PYTHONPATH" ":" prefix (,path))))
1700 `(("python" ,python-2)
1701 ("python2-pillow" ,python2-pillow)
1702 ("python2-numpy" ,python2-numpy)
1703 ("python2-scipy" ,python2-scipy)
1704 ("python2-matplotlib" ,python2-matplotlib)))
1708 ("randomjungle" ,randomjungle)))
1710 `(("unzip" ,unzip)))
1711 (home-page "http://couger.oit.duke.edu")
1712 (synopsis "Identify co-factors in sets of genomic regions")
1714 "COUGER can be applied to any two sets of genomic regions bound by
1715 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1716 putative co-factors that provide specificity to each TF. The framework
1717 determines the genomic targets uniquely-bound by each TF, and identifies a
1718 small set of co-factors that best explain the in vivo binding differences
1719 between the two TFs.
1721 COUGER uses classification algorithms (support vector machines and random
1722 forests) with features that reflect the DNA binding specificities of putative
1723 co-factors. The features are generated either from high-throughput TF-DNA
1724 binding data (from protein binding microarray experiments), or from large
1725 collections of DNA motifs.")
1726 (license license:gpl3+)))
1728 (define-public clustal-omega
1730 (name "clustal-omega")
1735 "http://www.clustal.org/omega/clustal-omega-"
1739 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1740 (build-system gnu-build-system)
1742 `(("argtable" ,argtable)))
1743 (home-page "http://www.clustal.org/omega/")
1744 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1746 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1747 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1748 of handling data-sets of hundreds of thousands of sequences in reasonable
1750 (license license:gpl2+)))
1752 (define-public crossmap
1758 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1762 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1763 ;; This patch has been sent upstream already and is available
1764 ;; for download from Sourceforge, but it has not been merged.
1765 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1766 (modules '((guix build utils)))
1767 ;; remove bundled copy of pysam
1769 '(delete-file-recursively "lib/pysam"))))
1770 (build-system python-build-system)
1772 `(#:python ,python-2
1776 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1779 `(("python-numpy" ,python2-numpy)
1780 ("python-pysam" ,python2-pysam)
1783 `(("python-cython" ,python2-cython)
1784 ("python-nose" ,python2-nose)))
1785 (home-page "http://crossmap.sourceforge.net/")
1786 (synopsis "Convert genome coordinates between assemblies")
1788 "CrossMap is a program for conversion of genome coordinates or annotation
1789 files between different genome assemblies. It supports most commonly used
1790 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1791 (license license:gpl2+)))
1793 (define-public cufflinks
1799 (uri (string-append "http://cole-trapnell-lab.github.io/"
1800 "cufflinks/assets/downloads/cufflinks-"
1804 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1805 (build-system gnu-build-system)
1809 ;; The includes for "eigen" are located in a subdirectory.
1810 (string-append "EIGEN_CPPFLAGS="
1811 "-I" (assoc-ref %build-inputs "eigen")
1813 ;; Cufflinks must be linked with various boost libraries.
1814 (string-append "LDFLAGS="
1815 (string-join '("-lboost_system"
1816 "-lboost_serialization"
1817 "-lboost_thread"))))
1819 (modify-phases %standard-phases
1820 (add-after 'unpack 'fix-search-for-bam
1822 (substitute* '("ax_bam.m4"
1825 (("<bam/sam\\.h>") "<samtools/sam.h>")
1826 (("<bam/bam\\.h>") "<samtools/bam.h>")
1827 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1830 (list (string-append "--with-bam="
1831 (assoc-ref %build-inputs "samtools")))))
1834 ("samtools" ,samtools-0.1)
1837 ("python" ,python-2)
1839 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1840 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1842 "Cufflinks assembles RNA transcripts, estimates their abundances,
1843 and tests for differential expression and regulation in RNA-Seq
1844 samples. It accepts aligned RNA-Seq reads and assembles the
1845 alignments into a parsimonious set of transcripts. Cufflinks then
1846 estimates the relative abundances of these transcripts based on how
1847 many reads support each one, taking into account biases in library
1848 preparation protocols.")
1849 (license license:boost1.0)))
1851 (define-public cutadapt
1858 "https://github.com/marcelm/cutadapt/archive/v"
1860 (file-name (string-append name "-" version ".tar.gz"))
1863 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1864 (build-system python-build-system)
1867 (modify-phases %standard-phases
1868 ;; The tests must be run after installation.
1870 (add-after 'install 'check
1871 (lambda* (#:key inputs outputs #:allow-other-keys)
1872 (setenv "PYTHONPATH"
1874 (getenv "PYTHONPATH")
1875 ":" (assoc-ref outputs "out")
1877 (string-take (string-take-right
1878 (assoc-ref inputs "python") 5) 3)
1880 (zero? (system* "nosetests" "-P" "tests")))))))
1882 `(("python-xopen" ,python-xopen)))
1884 `(("python-cython" ,python-cython)
1885 ("python-nose" ,python-nose)))
1886 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1887 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1889 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1890 other types of unwanted sequence from high-throughput sequencing reads.")
1891 (license license:expat)))
1893 (define-public libbigwig
1899 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1900 "archive/" version ".tar.gz"))
1901 (file-name (string-append name "-" version ".tar.gz"))
1904 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1905 (build-system gnu-build-system)
1907 `(#:test-target "test"
1910 (string-append "prefix=" (assoc-ref %outputs "out")))
1912 (modify-phases %standard-phases
1914 (add-before 'check 'disable-curl-test
1916 (substitute* "Makefile"
1917 (("./test/testRemote.*") ""))
1919 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1920 ;; there has not yet been a release containing this change.
1921 (add-before 'install 'create-target-dirs
1922 (lambda* (#:key outputs #:allow-other-keys)
1923 (let ((out (assoc-ref outputs "out")))
1924 (mkdir-p (string-append out "/lib"))
1925 (mkdir-p (string-append out "/include"))
1931 `(("doxygen" ,doxygen)))
1932 (home-page "https://github.com/dpryan79/libBigWig")
1933 (synopsis "C library for handling bigWig files")
1935 "This package provides a C library for parsing local and remote BigWig
1937 (license license:expat)))
1939 (define-public python-pybigwig
1941 (name "python-pybigwig")
1945 (uri (pypi-uri "pyBigWig" version))
1948 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1949 (modules '((guix build utils)))
1952 ;; Delete bundled libBigWig sources
1953 (delete-file-recursively "libBigWig")))))
1954 (build-system python-build-system)
1957 (modify-phases %standard-phases
1958 (add-after 'unpack 'link-with-libBigWig
1959 (lambda* (#:key inputs #:allow-other-keys)
1960 (substitute* "setup.py"
1961 (("libs=\\[") "libs=[\"BigWig\", "))
1964 `(("libbigwig" ,libbigwig)
1967 (home-page "https://github.com/dpryan79/pyBigWig")
1968 (synopsis "Access bigWig files in Python using libBigWig")
1970 "This package provides Python bindings to the libBigWig library for
1971 accessing bigWig files.")
1972 (license license:expat)))
1974 (define-public python2-pybigwig
1975 (package-with-python2 python-pybigwig))
1977 (define-public python-dendropy
1979 (name "python-dendropy")
1984 (uri (pypi-uri "DendroPy" version))
1987 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1988 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1989 (build-system python-build-system)
1990 (home-page "http://packages.python.org/DendroPy/")
1991 (synopsis "Library for phylogenetics and phylogenetic computing")
1993 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1994 writing, simulation, processing and manipulation of phylogenetic
1995 trees (phylogenies) and characters.")
1996 (license license:bsd-3)
1997 (properties `((python2-variant . ,(delay python2-dendropy))))))
1999 (define-public python2-dendropy
2000 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2004 `(#:python ,python-2
2006 (modify-phases %standard-phases
2008 ;; There is currently a test failure that only happens on some
2009 ;; systems, and only using "setup.py test"
2010 (lambda _ (zero? (system* "nosetests")))))))
2011 (native-inputs `(("python2-nose" ,python2-nose)
2012 ,@(package-native-inputs base))))))
2015 (define-public deeptools
2021 (uri (string-append "https://github.com/fidelram/deepTools/"
2022 "archive/" version ".tar.gz"))
2023 (file-name (string-append name "-" version ".tar.gz"))
2026 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
2027 (build-system python-build-system)
2029 `(#:python ,python-2))
2031 `(("python-scipy" ,python2-scipy)
2032 ("python-numpy" ,python2-numpy)
2033 ("python-numpydoc" ,python2-numpydoc)
2034 ("python-matplotlib" ,python2-matplotlib)
2035 ("python-bx-python" ,python2-bx-python)
2036 ("python-pysam" ,python2-pysam)
2037 ("python-pybigwig" ,python2-pybigwig)))
2039 `(("python-mock" ,python2-mock) ;for tests
2040 ("python-nose" ,python2-nose) ;for tests
2041 ("python-pytz" ,python2-pytz))) ;for tests
2042 (home-page "https://github.com/fidelram/deepTools")
2043 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2045 "DeepTools addresses the challenge of handling the large amounts of data
2046 that are now routinely generated from DNA sequencing centers. To do so,
2047 deepTools contains useful modules to process the mapped reads data to create
2048 coverage files in standard bedGraph and bigWig file formats. By doing so,
2049 deepTools allows the creation of normalized coverage files or the comparison
2050 between two files (for example, treatment and control). Finally, using such
2051 normalized and standardized files, multiple visualizations can be created to
2052 identify enrichments with functional annotations of the genome.")
2053 (license license:gpl3+)))
2055 (define-public diamond
2062 "https://github.com/bbuchfink/diamond/archive/v"
2064 (file-name (string-append name "-" version ".tar.gz"))
2067 "092smzzjcg51n3x4h84k52ijpz9m40ri838j9k2i463ribc3c8rh"))))
2068 (build-system cmake-build-system)
2070 '(#:tests? #f ; no "check" target
2072 (modify-phases %standard-phases
2073 (add-after 'unpack 'remove-native-compilation
2075 (substitute* "CMakeLists.txt" (("-march=native") ""))
2079 (home-page "https://github.com/bbuchfink/diamond")
2080 (synopsis "Accelerated BLAST compatible local sequence aligner")
2082 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2083 translated DNA query sequences against a protein reference database (BLASTP
2084 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2085 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2086 data and settings.")
2087 ;; diamond fails to build on other platforms
2088 ;; https://github.com/bbuchfink/diamond/issues/18
2089 (supported-systems '("x86_64-linux"))
2090 (license (license:non-copyleft "file://src/COPYING"
2091 "See src/COPYING in the distribution."))))
2093 (define-public discrover
2100 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2102 (file-name (string-append name "-" version ".tar.gz"))
2105 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2106 (build-system cmake-build-system)
2107 (arguments `(#:tests? #f)) ; there are no tests
2112 `(("texlive" ,texlive)
2113 ("imagemagick" ,imagemagick)))
2114 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2115 (synopsis "Discover discriminative nucleotide sequence motifs")
2116 (description "Discrover is a motif discovery method to find binding sites
2117 of nucleic acid binding proteins.")
2118 (license license:gpl3+)))
2120 (define-public eigensoft
2121 (let ((revision "1")
2122 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2125 (version (string-append "6.1.2-"
2127 (string-take commit 9)))
2132 (url "https://github.com/DReichLab/EIG.git")
2134 (file-name (string-append "eigensoft-" commit "-checkout"))
2137 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2138 (modules '((guix build utils)))
2139 ;; Remove pre-built binaries.
2141 (delete-file-recursively "bin")
2144 (build-system gnu-build-system)
2146 `(#:tests? #f ; There are no tests.
2147 #:make-flags '("CC=gcc")
2149 (modify-phases %standard-phases
2150 ;; There is no configure phase, but the Makefile is in a
2155 ;; The link flags are incomplete.
2156 (substitute* "Makefile"
2157 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2159 ;; The provided install target only copies executables to
2160 ;; the "bin" directory in the build root.
2161 (add-after 'install 'actually-install
2162 (lambda* (#:key outputs #:allow-other-keys)
2163 (let* ((out (assoc-ref outputs "out"))
2164 (bin (string-append out "/bin")))
2165 (for-each (lambda (file)
2166 (install-file file bin))
2167 (find-files "../bin" ".*"))
2172 ("openblas" ,openblas)
2174 ("gfortran" ,gfortran "lib")))
2175 (home-page "https://github.com/DReichLab/EIG")
2176 (synopsis "Tools for population genetics")
2177 (description "The EIGENSOFT package provides tools for population
2178 genetics and stratification correction. EIGENSOFT implements methods commonly
2179 used in population genetics analyses such as PCA, computation of Tracy-Widom
2180 statistics, and finding related individuals in structured populations. It
2181 comes with a built-in plotting script and supports multiple file formats and
2182 quantitative phenotypes.")
2183 ;; The license of the eigensoft tools is Expat, but since it's
2184 ;; linking with the GNU Scientific Library (GSL) the effective
2185 ;; license is the GPL.
2186 (license license:gpl3+))))
2188 (define-public edirect
2194 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2195 "versions/2016-05-03/edirect.tar.gz"))
2198 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2199 (build-system perl-build-system)
2201 `(#:tests? #f ;no "check" target
2203 (modify-phases %standard-phases
2207 (lambda* (#:key outputs #:allow-other-keys)
2208 (let ((target (string-append (assoc-ref outputs "out")
2211 (copy-file "edirect.pl"
2212 (string-append target "/edirect.pl"))
2215 'install 'wrap-program
2216 (lambda* (#:key inputs outputs #:allow-other-keys)
2217 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2218 (let* ((out (assoc-ref outputs "out"))
2219 (path (getenv "PERL5LIB")))
2220 (wrap-program (string-append out "/bin/edirect.pl")
2221 `("PERL5LIB" ":" prefix (,path)))))))))
2223 `(("perl-html-parser" ,perl-html-parser)
2224 ("perl-encode-locale" ,perl-encode-locale)
2225 ("perl-file-listing" ,perl-file-listing)
2226 ("perl-html-tagset" ,perl-html-tagset)
2227 ("perl-html-tree" ,perl-html-tree)
2228 ("perl-http-cookies" ,perl-http-cookies)
2229 ("perl-http-date" ,perl-http-date)
2230 ("perl-http-message" ,perl-http-message)
2231 ("perl-http-negotiate" ,perl-http-negotiate)
2232 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2233 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2234 ("perl-net-http" ,perl-net-http)
2235 ("perl-uri" ,perl-uri)
2236 ("perl-www-robotrules" ,perl-www-robotrules)
2238 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2239 (synopsis "Tools for accessing the NCBI's set of databases")
2241 "Entrez Direct (EDirect) is a method for accessing the National Center
2242 for Biotechnology Information's (NCBI) set of interconnected
2243 databases (publication, sequence, structure, gene, variation, expression,
2244 etc.) from a terminal. Functions take search terms from command-line
2245 arguments. Individual operations are combined to build multi-step queries.
2246 Record retrieval and formatting normally complete the process.
2248 EDirect also provides an argument-driven function that simplifies the
2249 extraction of data from document summaries or other results that are returned
2250 in structured XML format. This can eliminate the need for writing custom
2251 software to answer ad hoc questions.")
2252 (license license:public-domain)))
2254 (define-public exonerate
2263 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2264 "exonerate-" version ".tar.gz"))
2267 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2268 (build-system gnu-build-system)
2270 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2272 `(("pkg-config" ,pkg-config)))
2276 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2277 (synopsis "Generic tool for biological sequence alignment")
2279 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2280 the alignment of sequences using a many alignment models, either exhaustive
2281 dynamic programming or a variety of heuristics.")
2282 (license license:gpl3)))
2284 (define-public express
2292 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2293 version "/express-" version "-src.tgz"))
2296 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2297 (build-system cmake-build-system)
2299 `(#:tests? #f ;no "check" target
2302 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2303 (lambda* (#:key inputs #:allow-other-keys)
2304 (substitute* "CMakeLists.txt"
2305 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2306 "set(Boost_USE_STATIC_LIBS OFF)")
2307 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2308 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2309 (substitute* "src/CMakeLists.txt"
2310 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2311 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2316 ("bamtools" ,bamtools)
2317 ("protobuf" ,protobuf)
2319 (home-page "http://bio.math.berkeley.edu/eXpress")
2320 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2322 "eXpress is a streaming tool for quantifying the abundances of a set of
2323 target sequences from sampled subsequences. Example applications include
2324 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2325 analysis (from RNA-Seq), transcription factor binding quantification in
2326 ChIP-Seq, and analysis of metagenomic data.")
2327 (license license:artistic2.0)))
2329 (define-public express-beta-diversity
2331 (name "express-beta-diversity")
2337 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2339 (file-name (string-append name "-" version ".tar.gz"))
2342 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2343 (build-system gnu-build-system)
2346 (modify-phases %standard-phases
2348 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2350 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2352 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2354 (lambda* (#:key outputs #:allow-other-keys)
2355 (let ((bin (string-append (assoc-ref outputs "out")
2358 (copy-file "scripts/convertToEBD.py"
2359 (string-append bin "/convertToEBD.py"))
2360 (copy-file "bin/ExpressBetaDiversity"
2361 (string-append bin "/ExpressBetaDiversity"))
2364 `(("python" ,python-2)))
2365 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2366 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2368 "Express Beta Diversity (EBD) calculates ecological beta diversity
2369 (dissimilarity) measures between biological communities. EBD implements a
2370 variety of diversity measures including those that make use of phylogenetic
2371 similarity of community members.")
2372 (license license:gpl3+)))
2374 (define-public fasttree
2381 "http://www.microbesonline.org/fasttree/FastTree-"
2385 "0ljvvw8i1als1wbfzvrf15c3ii2vw9db20a259g6pzg34xyyb97k"))))
2386 (build-system gnu-build-system)
2388 `(#:tests? #f ; no "check" target
2390 (modify-phases %standard-phases
2394 (lambda* (#:key source #:allow-other-keys)
2395 (and (zero? (system* "gcc"
2397 "-finline-functions"
2404 (zero? (system* "gcc"
2408 "-finline-functions"
2416 (lambda* (#:key outputs #:allow-other-keys)
2417 (let ((bin (string-append (assoc-ref outputs "out")
2420 (copy-file "FastTree"
2421 (string-append bin "/FastTree"))
2422 (copy-file "FastTreeMP"
2423 (string-append bin "/FastTreeMP"))
2425 (home-page "http://www.microbesonline.org/fasttree")
2426 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2428 "FastTree can handle alignments with up to a million of sequences in a
2429 reasonable amount of time and memory. For large alignments, FastTree is
2430 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2431 (license license:gpl2+)))
2433 (define-public fastx-toolkit
2435 (name "fastx-toolkit")
2441 "https://github.com/agordon/fastx_toolkit/releases/download/"
2442 version "/fastx_toolkit-" version ".tar.bz2"))
2445 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2446 (build-system gnu-build-system)
2448 `(("libgtextutils" ,libgtextutils)))
2450 `(("pkg-config" ,pkg-config)))
2451 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2452 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2454 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2455 FASTA/FASTQ files preprocessing.
2457 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2458 containing multiple short-reads sequences. The main processing of such
2459 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2460 is sometimes more productive to preprocess the files before mapping the
2461 sequences to the genome---manipulating the sequences to produce better mapping
2462 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2463 (license license:agpl3+)))
2465 (define-public flexbar
2472 (string-append "mirror://sourceforge/flexbar/"
2473 version "/flexbar_v" version "_src.tgz"))
2476 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2477 (build-system cmake-build-system)
2479 `(#:configure-flags (list
2480 (string-append "-DFLEXBAR_BINARY_DIR="
2481 (assoc-ref %outputs "out")
2486 (lambda* (#:key outputs #:allow-other-keys)
2487 (setenv "PATH" (string-append
2488 (assoc-ref outputs "out") "/bin:"
2490 (chdir "../flexbar_v2.5_src/test")
2491 (zero? (system* "bash" "flexbar_validate.sh")))
2492 (alist-delete 'install %standard-phases))))
2497 `(("pkg-config" ,pkg-config)
2499 (home-page "http://flexbar.sourceforge.net")
2500 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2502 "Flexbar preprocesses high-throughput nucleotide sequencing data
2503 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2504 Moreover, trimming and filtering features are provided. Flexbar increases
2505 read mapping rates and improves genome and transcriptome assemblies. It
2506 supports next-generation sequencing data in fasta/q and csfasta/q format from
2507 Illumina, Roche 454, and the SOLiD platform.")
2508 (license license:gpl3)))
2510 (define-public fraggenescan
2512 (name "fraggenescan")
2518 (string-append "mirror://sourceforge/fraggenescan/"
2519 "FragGeneScan" version ".tar.gz"))
2521 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
2522 (build-system gnu-build-system)
2525 (modify-phases %standard-phases
2527 (add-before 'build 'patch-paths
2528 (lambda* (#:key outputs #:allow-other-keys)
2529 (let* ((out (string-append (assoc-ref outputs "out")))
2530 (share (string-append out "/share/fraggenescan/")))
2531 (substitute* "run_FragGeneScan.pl"
2533 (string-append "system(\"" (which "rm")))
2535 (string-append "system(\"" (which "mv")))
2536 ;; This script and other programs expect the training files
2537 ;; to be in the non-standard location bin/train/XXX. Change
2538 ;; this to be share/fraggenescan/train/XXX instead.
2539 (("^\\$train.file = \\$dir.*")
2540 (string-append "$train_file = \""
2542 "train/\".$FGS_train_file;")))
2543 (substitute* "run_hmm.c"
2544 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2545 (string-append " strcpy(train_dir, \"" share "/train/\");")))
2546 (substitute* "post_process.pl"
2547 (("^my \\$dir = substr.*")
2548 (string-append "my $dir = \"" share "\";"))))
2551 (lambda _ (and (zero? (system* "make" "clean"))
2552 (zero? (system* "make" "fgs")))))
2554 (lambda* (#:key outputs #:allow-other-keys)
2555 (let* ((out (string-append (assoc-ref outputs "out")))
2556 (bin (string-append out "/bin/"))
2557 (share (string-append out "/share/fraggenescan/train")))
2558 (install-file "run_FragGeneScan.pl" bin)
2559 (install-file "FragGeneScan" bin)
2560 (install-file "FGS_gff.py" bin)
2561 (install-file "post_process.pl" bin)
2562 (copy-recursively "train" share))))
2564 (add-after 'install 'post-install-check
2565 ;; In lieu of 'make check', run one of the examples and check the
2566 ;; output files gets created.
2567 (lambda* (#:key outputs #:allow-other-keys)
2568 (let* ((out (string-append (assoc-ref outputs "out")))
2569 (bin (string-append out "/bin/")))
2570 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
2571 "-genome=./example/NC_000913.fna"
2575 (file-exists? "test2.faa")
2576 (file-exists? "test2.ffn")
2577 (file-exists? "test2.gff")
2578 (file-exists? "test2.out"))))))))
2581 ("python" ,python-2))) ;not compatible with python 3.
2582 (home-page "https://sourceforge.net/projects/fraggenescan/")
2583 (synopsis "Finds potentially fragmented genes in short reads")
2585 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2586 short and error-prone DNA sequencing reads. It can also be applied to predict
2587 genes in incomplete assemblies or complete genomes.")
2588 ;; GPL3+ according to private correspondense with the authors.
2589 (license license:gpl3+)))
2591 (define-public fxtract
2592 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2600 "https://github.com/ctSkennerton/fxtract/archive/"
2602 (file-name (string-append "ctstennerton-util-"
2603 (string-take util-commit 7)
2607 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2608 (build-system gnu-build-system)
2610 `(#:make-flags (list
2611 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2613 #:test-target "fxtract_test"
2615 (modify-phases %standard-phases
2617 (add-before 'build 'copy-util
2618 (lambda* (#:key inputs #:allow-other-keys)
2620 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2622 ;; Do not use make install as this requires additional dependencies.
2624 (lambda* (#:key outputs #:allow-other-keys)
2625 (let* ((out (assoc-ref outputs "out"))
2626 (bin (string-append out"/bin")))
2627 (install-file "fxtract" bin)
2633 ;; ctskennerton-util is licensed under GPL2.
2634 `(("ctskennerton-util"
2638 (url "https://github.com/ctSkennerton/util.git")
2639 (commit util-commit)))
2640 (file-name (string-append
2641 "ctstennerton-util-" util-commit "-checkout"))
2644 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2645 (home-page "https://github.com/ctSkennerton/fxtract")
2646 (synopsis "Extract sequences from FASTA and FASTQ files")
2648 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2649 or FASTQ) file given a subsequence. It uses a simple substring search for
2650 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2651 lookups or multi-pattern searching as required. By default fxtract looks in
2652 the sequence of each record but can also be told to look in the header,
2653 comment or quality sections.")
2654 ;; 'util' requires SSE instructions.
2655 (supported-systems '("x86_64-linux"))
2656 (license license:expat))))
2665 "https://github.com/nboley/grit/archive/"
2667 (file-name (string-append name "-" version ".tar.gz"))
2670 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2671 (build-system python-build-system)
2673 `(#:python ,python-2
2676 'unpack 'generate-from-cython-sources
2677 (lambda* (#:key inputs outputs #:allow-other-keys)
2678 ;; Delete these C files to force fresh generation from pyx sources.
2679 (delete-file "grit/sparsify_support_fns.c")
2680 (delete-file "grit/call_peaks_support_fns.c")
2681 (substitute* "setup.py"
2682 (("Cython.Setup") "Cython.Build")
2683 ;; Add numpy include path to fix compilation
2685 (string-append "pyx\", ], include_dirs = ['"
2686 (assoc-ref inputs "python-numpy")
2687 "/lib/python2.7/site-packages/numpy/core/include/"
2691 `(("python-scipy" ,python2-scipy)
2692 ("python-numpy" ,python2-numpy)
2693 ("python-pysam" ,python2-pysam)
2694 ("python-networkx" ,python2-networkx)))
2696 `(("python-cython" ,python2-cython)))
2697 (home-page "http://grit-bio.org")
2698 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2700 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2701 full length transcript models. When none of these data sources are available,
2702 GRIT can be run by providing a candidate set of TES or TSS sites. In
2703 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2704 also be run in quantification mode, where it uses a provided GTF file and just
2705 estimates transcript expression.")
2706 (license license:gpl3+)))
2708 (define-public hisat
2715 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2716 version "-beta-source.zip"))
2719 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2720 (build-system gnu-build-system)
2722 `(#:tests? #f ;no check target
2723 #:make-flags '("allall"
2724 ;; Disable unsupported `popcnt' instructions on
2725 ;; architectures other than x86_64
2726 ,@(if (string-prefix? "x86_64"
2727 (or (%current-target-system)
2730 '("POPCNT_CAPABILITY=0")))
2733 'unpack 'patch-sources
2735 ;; XXX Cannot use snippet because zip files are not supported
2736 (substitute* "Makefile"
2737 (("^CC = .*$") "CC = gcc")
2738 (("^CPP = .*$") "CPP = g++")
2739 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2740 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2741 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2742 (substitute* '("hisat-build" "hisat-inspect")
2743 (("/usr/bin/env") (which "env"))))
2746 (lambda* (#:key outputs #:allow-other-keys)
2747 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2748 (for-each (lambda (file)
2749 (install-file file bin))
2752 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2753 (alist-delete 'configure %standard-phases)))))
2755 `(("unzip" ,unzip)))
2760 ;; Non-portable SSE instructions are used so building fails on platforms
2761 ;; other than x86_64.
2762 (supported-systems '("x86_64-linux"))
2763 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2764 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2766 "HISAT is a fast and sensitive spliced alignment program for mapping
2767 RNA-seq reads. In addition to one global FM index that represents a whole
2768 genome, HISAT uses a large set of small FM indexes that collectively cover the
2769 whole genome. These small indexes (called local indexes) combined with
2770 several alignment strategies enable effective alignment of RNA-seq reads, in
2771 particular, reads spanning multiple exons.")
2772 (license license:gpl3+)))
2774 (define-public hisat2
2781 ;; FIXME: a better source URL is
2782 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2783 ;; "/downloads/hisat2-" version "-source.zip")
2784 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2785 ;; but it is currently unavailable.
2786 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2787 (file-name (string-append name "-" version ".tar.gz"))
2790 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2791 (build-system gnu-build-system)
2793 `(#:tests? #f ; no check target
2794 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2795 #:modules ((guix build gnu-build-system)
2799 (modify-phases %standard-phases
2800 (add-after 'unpack 'make-deterministic
2802 (substitute* "Makefile"
2807 (lambda* (#:key outputs #:allow-other-keys)
2808 (let* ((out (assoc-ref outputs "out"))
2809 (bin (string-append out "/bin/"))
2810 (doc (string-append out "/share/doc/hisat2/")))
2812 (cut install-file <> bin)
2814 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2816 (install-file "doc/manual.inc.html" doc))
2819 `(("unzip" ,unzip) ; needed for archive from ftp
2821 ("pandoc" ,ghc-pandoc))) ; for documentation
2822 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2823 (synopsis "Graph-based alignment of genomic sequencing reads")
2824 (description "HISAT2 is a fast and sensitive alignment program for mapping
2825 next-generation sequencing reads (both DNA and RNA) to a population of human
2826 genomes (as well as to a single reference genome). In addition to using one
2827 global @dfn{graph FM} (GFM) index that represents a population of human
2828 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2829 the whole genome. These small indexes, combined with several alignment
2830 strategies, enable rapid and accurate alignment of sequencing reads. This new
2831 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2832 ;; HISAT2 contains files from Bowtie2, which is released under
2833 ;; GPLv2 or later. The HISAT2 source files are released under
2835 (license license:gpl3+)))
2837 (define-public hmmer
2844 "http://eddylab.org/software/hmmer"
2845 (version-prefix version 1) "/"
2846 version "/hmmer-" version ".tar.gz"))
2849 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
2850 (build-system gnu-build-system)
2851 (native-inputs `(("perl" ,perl)))
2852 (home-page "http://hmmer.org/")
2853 (synopsis "Biosequence analysis using profile hidden Markov models")
2855 "HMMER is used for searching sequence databases for homologs of protein
2856 sequences, and for making protein sequence alignments. It implements methods
2857 using probabilistic models called profile hidden Markov models (profile
2859 (license (list license:gpl3+
2860 ;; The bundled library 'easel' is distributed
2861 ;; under The Janelia Farm Software License.
2862 (license:non-copyleft
2863 "file://easel/LICENSE"
2864 "See easel/LICENSE in the distribution.")))))
2866 (define-public htseq
2873 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2877 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2878 (build-system python-build-system)
2879 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2880 ;; Numpy needs to be propagated when htseq is used as a Python library.
2882 `(("python-numpy" ,python2-numpy)))
2884 `(("python-pysam" ,python2-pysam)))
2885 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2886 (synopsis "Analysing high-throughput sequencing data with Python")
2888 "HTSeq is a Python package that provides infrastructure to process data
2889 from high-throughput sequencing assays.")
2890 (license license:gpl3+)))
2892 (define-public java-htsjdk
2894 (name "java-htsjdk")
2899 "https://github.com/samtools/htsjdk/archive/"
2901 (file-name (string-append name "-" version ".tar.gz"))
2904 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2905 (modules '((guix build utils)))
2906 ;; remove build dependency on git
2907 (snippet '(substitute* "build.xml"
2908 (("failifexecutionfails=\"true\"")
2909 "failifexecutionfails=\"false\"")))))
2910 (build-system ant-build-system)
2912 `(#:tests? #f ; test require Internet access
2914 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2915 "/share/java/htsjdk/"))
2916 #:build-target "all"
2918 (modify-phases %standard-phases
2919 ;; The build phase also installs the jars
2920 (delete 'install))))
2921 (home-page "http://samtools.github.io/htsjdk/")
2922 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2924 "HTSJDK is an implementation of a unified Java library for accessing
2925 common file formats, such as SAM and VCF, used for high-throughput
2926 sequencing (HTS) data. There are also an number of useful utilities for
2927 manipulating HTS data.")
2928 (license license:expat)))
2930 (define-public htslib
2937 "https://github.com/samtools/htslib/releases/download/"
2938 version "/htslib-" version ".tar.bz2"))
2941 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
2942 (build-system gnu-build-system)
2945 (modify-phases %standard-phases
2947 'unpack 'patch-tests
2949 (substitute* "test/test.pl"
2950 (("/bin/bash") (which "bash")))
2956 (home-page "http://www.htslib.org")
2957 (synopsis "C library for reading/writing high-throughput sequencing data")
2959 "HTSlib is a C library for reading/writing high-throughput sequencing
2960 data. It also provides the bgzip, htsfile, and tabix utilities.")
2961 ;; Files under cram/ are released under the modified BSD license;
2962 ;; the rest is released under the Expat license
2963 (license (list license:expat license:bsd-3))))
2972 "https://github.com/nboley/idr/archive/"
2974 (file-name (string-append name "-" version ".tar.gz"))
2977 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
2978 (build-system python-build-system)
2980 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
2982 `(("python-scipy" ,python-scipy)
2983 ("python-sympy" ,python-sympy)
2984 ("python-numpy" ,python-numpy)
2985 ("python-matplotlib" ,python-matplotlib)))
2987 `(("python-cython" ,python-cython)))
2988 (home-page "https://github.com/nboley/idr")
2989 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
2991 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
2992 to measure the reproducibility of findings identified from replicate
2993 experiments and provide highly stable thresholds based on reproducibility.")
2994 (license license:gpl3+)))
2996 (define-public jellyfish
3002 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3003 "releases/download/v" version
3004 "/jellyfish-" version ".tar.gz"))
3007 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3008 (build-system gnu-build-system)
3009 (outputs '("out" ;for library
3010 "ruby" ;for Ruby bindings
3011 "python")) ;for Python bindings
3014 (list (string-append "--enable-ruby-binding="
3015 (assoc-ref %outputs "ruby"))
3016 (string-append "--enable-python-binding="
3017 (assoc-ref %outputs "python")))
3019 (modify-phases %standard-phases
3020 (add-before 'check 'set-SHELL-variable
3022 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3024 (setenv "SHELL" (which "bash"))
3030 ("python" ,python-2)))
3031 (synopsis "Tool for fast counting of k-mers in DNA")
3033 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3034 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3035 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3036 is a command-line program that reads FASTA and multi-FASTA files containing
3037 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3038 translated into a human-readable text format using the @code{jellyfish dump}
3039 command, or queried for specific k-mers with @code{jellyfish query}.")
3040 (home-page "http://www.genome.umd.edu/jellyfish.html")
3041 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3042 (supported-systems '("x86_64-linux"))
3043 ;; The combined work is published under the GPLv3 or later. Individual
3044 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3045 (license (list license:gpl3+ license:expat))))
3047 (define-public khmer
3054 (uri (pypi-uri "khmer" version))
3057 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3058 (patches (search-patches "khmer-use-libraries.patch"))))
3059 (build-system python-build-system)
3062 (modify-phases %standard-phases
3063 (add-after 'unpack 'set-paths
3064 (lambda* (#:key inputs outputs #:allow-other-keys)
3065 ;; Delete bundled libraries.
3066 (delete-file-recursively "third-party/zlib")
3067 (delete-file-recursively "third-party/bzip2")
3068 ;; Replace bundled seqan.
3069 (let* ((seqan-all "third-party/seqan")
3070 (seqan-include (string-append
3071 seqan-all "/core/include")))
3072 (delete-file-recursively seqan-all)
3073 (copy-recursively (string-append (assoc-ref inputs "seqan")
3075 (string-append seqan-include "/seqan")))
3076 ;; We do not replace the bundled MurmurHash as the canonical
3077 ;; repository for this code 'SMHasher' is unsuitable for
3078 ;; providing a library. See
3079 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3081 (add-after 'unpack 'set-cc
3085 ;; It is simpler to test after installation.
3087 (add-after 'install 'post-install-check
3088 (lambda* (#:key inputs outputs #:allow-other-keys)
3089 (let ((out (assoc-ref outputs "out")))
3094 (assoc-ref outputs "out")
3096 (setenv "PYTHONPATH"
3098 (getenv "PYTHONPATH")
3102 (string-take (string-take-right
3103 (assoc-ref inputs "python") 5) 3)
3105 (with-directory-excursion "build"
3106 (zero? (system* "nosetests" "khmer" "--attr"
3107 "!known_failing")))))))))
3110 ("python-nose" ,python-nose)))
3114 ("python-screed" ,python-screed)
3115 ("python-bz2file" ,python-bz2file)))
3116 (home-page "https://khmer.readthedocs.org/")
3117 (synopsis "K-mer counting, filtering and graph traversal library")
3118 (description "The khmer software is a set of command-line tools for
3119 working with DNA shotgun sequencing data from genomes, transcriptomes,
3120 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3121 sometimes better. Khmer can also identify and fix problems with shotgun
3123 ;; When building on i686, armhf and mips64el, we get the following error:
3124 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3125 (supported-systems '("x86_64-linux"))
3126 (license license:bsd-3)))
3131 (version "2.1.0.20151222")
3134 (uri (pypi-uri "MACS2" version))
3137 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3138 (build-system python-build-system)
3140 `(#:python ,python-2 ; only compatible with Python 2.7
3141 #:tests? #f)) ; no test target
3143 `(("python-numpy" ,python2-numpy)))
3144 (home-page "http://github.com/taoliu/MACS/")
3145 (synopsis "Model based analysis for ChIP-Seq data")
3147 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3148 identifying transcript factor binding sites named Model-based Analysis of
3149 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3150 the significance of enriched ChIP regions and it improves the spatial
3151 resolution of binding sites through combining the information of both
3152 sequencing tag position and orientation.")
3153 (license license:bsd-3)))
3155 (define-public mafft
3162 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3163 "-without-extensions-src.tgz"))
3164 (file-name (string-append name "-" version ".tgz"))
3167 "0ziim7g58n3z8gppsa713f5fxprl60ldj3xck186z0n9dpp06i8r"))))
3168 (build-system gnu-build-system)
3170 `(#:tests? #f ; no automated tests, though there are tests in the read me
3171 #:make-flags (let ((out (assoc-ref %outputs "out")))
3172 (list (string-append "PREFIX=" out)
3173 (string-append "BINDIR="
3174 (string-append out "/bin"))))
3176 (modify-phases %standard-phases
3177 (add-after 'unpack 'enter-dir
3178 (lambda _ (chdir "core") #t))
3179 (add-after 'enter-dir 'patch-makefile
3181 ;; on advice from the MAFFT authors, there is no need to
3182 ;; distribute mafft-profile, mafft-distance, or
3183 ;; mafft-homologs.rb as they are too "specialised".
3184 (substitute* "Makefile"
3185 ;; remove mafft-homologs.rb from SCRIPTS
3186 (("^SCRIPTS = mafft mafft-homologs.rb")
3188 ;; remove mafft-homologs from MANPAGES
3189 (("^MANPAGES = mafft.1 mafft-homologs.1")
3190 "MANPAGES = mafft.1")
3191 ;; remove mafft-distance from PROGS
3192 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3193 "PROGS = dvtditr dndfast7 dndblast sextet5")
3194 ;; remove mafft-profile from PROGS
3195 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3196 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3197 (("^rm -f mafft-profile mafft-profile.exe") "#")
3198 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3199 ;; do not install MAN pages in libexec folder
3200 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3201 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3203 (add-after 'enter-dir 'patch-paths
3204 (lambda* (#:key inputs #:allow-other-keys)
3205 (substitute* '("pairash.c"
3207 (("perl") (which "perl"))
3208 (("([\"`| ])awk" _ prefix)
3209 (string-append prefix (which "awk")))
3210 (("grep") (which "grep")))
3213 (add-after 'install 'wrap-programs
3214 (lambda* (#:key outputs #:allow-other-keys)
3215 (let* ((out (assoc-ref outputs "out"))
3216 (bin (string-append out "/bin"))
3217 (path (string-append
3218 (assoc-ref %build-inputs "coreutils") "/bin:")))
3219 (for-each (lambda (file)
3221 `("PATH" ":" prefix (,path))))
3229 ("coreutils" ,coreutils)))
3230 (home-page "http://mafft.cbrc.jp/alignment/software/")
3231 (synopsis "Multiple sequence alignment program")
3233 "MAFFT offers a range of multiple alignment methods for nucleotide and
3234 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3235 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3237 (license (license:non-copyleft
3238 "http://mafft.cbrc.jp/alignment/software/license.txt"
3239 "BSD-3 with different formatting"))))
3248 "https://github.com/marbl/mash/archive/v"
3250 (file-name (string-append name "-" version ".tar.gz"))
3253 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3254 (modules '((guix build utils)))
3256 ;; Delete bundled kseq.
3257 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3258 '(delete-file "src/mash/kseq.h"))))
3259 (build-system gnu-build-system)
3261 `(#:tests? #f ; No tests.
3264 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3265 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3266 #:make-flags (list "CC=gcc")
3268 (modify-phases %standard-phases
3269 (add-after 'unpack 'fix-includes
3271 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3272 (("^#include \"kseq\\.h\"")
3273 "#include \"htslib/kseq.h\""))
3275 (add-before 'configure 'autoconf
3276 (lambda _ (zero? (system* "autoconf")))))))
3278 `(("autoconf" ,autoconf)
3279 ;; Capnproto and htslib are statically embedded in the final
3280 ;; application. Therefore we also list their licenses, below.
3281 ("capnproto" ,capnproto)
3282 ("htslib" ,htslib)))
3286 (supported-systems '("x86_64-linux"))
3287 (home-page "https://mash.readthedocs.io")
3288 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3289 (description "Mash is a fast sequence distance estimator that uses the
3290 MinHash algorithm and is designed to work with genomes and metagenomes in the
3291 form of assemblies or reads.")
3292 (license (list license:bsd-3 ; Mash
3293 license:expat ; HTSlib and capnproto
3294 license:public-domain ; MurmurHash 3
3295 license:cpl1.0)))) ; Open Bloom Filter
3297 (define-public metabat
3298 ;; We package from a git commit because compilation of the released version
3300 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3303 (version (string-append "0.32.4-1." (string-take commit 8)))
3308 (url "https://bitbucket.org/berkeleylab/metabat.git")
3310 (file-name (string-append name "-" version))
3313 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3314 (patches (search-patches "metabat-remove-compilation-date.patch"))))
3315 (build-system gnu-build-system)
3318 (modify-phases %standard-phases
3319 (add-after 'unpack 'fix-includes
3321 (substitute* "src/BamUtils.h"
3322 (("^#include \"bam/bam\\.h\"")
3323 "#include \"samtools/bam.h\"")
3324 (("^#include \"bam/sam\\.h\"")
3325 "#include \"samtools/sam.h\""))
3326 (substitute* "src/KseqReader.h"
3327 (("^#include \"bam/kseq\\.h\"")
3328 "#include \"htslib/kseq.h\""))
3330 (add-after 'unpack 'fix-scons
3331 (lambda* (#:key inputs #:allow-other-keys)
3332 (substitute* "SConstruct"
3333 (("^htslib_dir = 'samtools'")
3334 (string-append "hitslib_dir = '"
3335 (assoc-ref inputs "htslib")
3337 (("^samtools_dir = 'samtools'")
3338 (string-append "samtools_dir = '"
3339 (assoc-ref inputs "htslib")
3341 (("^findStaticOrShared\\('bam', hts_lib")
3342 (string-append "findStaticOrShared('bam', '"
3343 (assoc-ref inputs "samtools")
3345 ;; Do not distribute README.
3346 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3350 (lambda* (#:key inputs outputs #:allow-other-keys)
3351 (mkdir (assoc-ref outputs "out"))
3352 (zero? (system* "scons"
3355 (assoc-ref outputs "out"))
3358 (assoc-ref inputs "boost"))
3360 ;; Check and install are carried out during build phase.
3362 (delete 'install))))
3366 ("samtools" ,samtools)
3370 `(("scons" ,scons)))
3371 (home-page "https://bitbucket.org/berkeleylab/metabat")
3373 "Reconstruction of single genomes from complex microbial communities")
3375 "Grouping large genomic fragments assembled from shotgun metagenomic
3376 sequences to deconvolute complex microbial communities, or metagenome binning,
3377 enables the study of individual organisms and their interactions. MetaBAT is
3378 an automated metagenome binning software, which integrates empirical
3379 probabilistic distances of genome abundance and tetranucleotide frequency.")
3380 (license (license:non-copyleft "file://license.txt"
3381 "See license.txt in the distribution.")))))
3383 (define-public minced
3390 "https://github.com/ctSkennerton/minced/archive/"
3392 (file-name (string-append name "-" version ".tar.gz"))
3395 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3396 (build-system gnu-build-system)
3398 `(#:test-target "test"
3400 (modify-phases %standard-phases
3402 (add-before 'check 'fix-test
3404 ;; Fix test for latest version.
3405 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3406 (("minced:0.1.6") "minced:0.2.0"))
3408 (replace 'install ; No install target.
3409 (lambda* (#:key inputs outputs #:allow-other-keys)
3410 (let* ((out (assoc-ref outputs "out"))
3411 (bin (string-append out "/bin"))
3412 (wrapper (string-append bin "/minced")))
3413 ;; Minced comes with a wrapper script that tries to figure out where
3414 ;; it is located before running the JAR. Since these paths are known
3415 ;; to us, we build our own wrapper to avoid coreutils dependency.
3416 (install-file "minced.jar" bin)
3417 (with-output-to-file wrapper
3421 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3422 (assoc-ref inputs "jre") "/bin/java -jar "
3423 bin "/minced.jar \"$@\"\n"))))
3424 (chmod wrapper #o555)))))))
3426 `(("jdk" ,icedtea "jdk")))
3429 ("jre" ,icedtea "out")))
3430 (home-page "https://github.com/ctSkennerton/minced")
3431 (synopsis "Mining CRISPRs in Environmental Datasets")
3433 "MinCED is a program to find Clustered Regularly Interspaced Short
3434 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3435 unassembled metagenomic reads, but is mainly designed for full genomes and
3436 assembled metagenomic sequence.")
3437 (license license:gpl3+)))
3446 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3450 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3451 (modules '((guix build utils)))
3453 '(substitute* "setup.py"
3454 ;; Use setuptools, or else the executables are not
3456 (("distutils.core") "setuptools")
3457 ;; use "gcc" instead of "cc" for compilation
3459 "cc.set_executables(
3463 linker_so='gcc -shared'); defines")))))
3464 (build-system python-build-system)
3466 `(#:python ,python-2 ; only Python 2 is supported
3467 #:tests? #f)) ; no "test" target
3469 `(("samtools" ,samtools)
3470 ("python-numpy" ,python2-numpy)
3471 ("python-pysam" ,python2-pysam)
3472 ("python-scipy" ,python2-scipy)
3473 ("python-matplotlib" ,python2-matplotlib)))
3475 `(("python-mock" ,python2-mock) ;for tests
3476 ("python-pytz" ,python2-pytz))) ;for tests
3477 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3478 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3480 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3481 the expression level of alternatively spliced genes from RNA-Seq data, and
3482 identifies differentially regulated isoforms or exons across samples. By
3483 modeling the generative process by which reads are produced from isoforms in
3484 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3485 that a read originated from a particular isoform.")
3486 (license license:gpl2)))
3488 (define-public muscle
3491 (version "3.8.1551")
3493 (method url-fetch/tarbomb)
3495 "http://www.drive5.com/muscle/muscle_src_"
3499 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3500 (build-system gnu-build-system)
3502 `(#:make-flags (list "LDLIBS = -lm")
3504 (modify-phases %standard-phases
3507 ;; There are no tests, so just test if it runs.
3508 (lambda _ (zero? (system* "./muscle" "-version"))))
3510 (lambda* (#:key outputs #:allow-other-keys)
3511 (let* ((out (assoc-ref outputs "out"))
3512 (bin (string-append out "/bin")))
3513 (install-file "muscle" bin)))))))
3514 (home-page "http://www.drive5.com/muscle")
3515 (synopsis "Multiple sequence alignment program")
3517 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3518 program for nucleotide and protein sequences.")
3519 ;; License information found in 'muscle -h' and usage.cpp.
3520 (license license:public-domain)))
3522 (define-public newick-utils
3523 ;; There are no recent releases so we package from git.
3524 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3526 (name "newick-utils")
3527 (version (string-append "1.6-1." (string-take commit 8)))
3531 (url "https://github.com/tjunier/newick_utils.git")
3533 (file-name (string-append name "-" version "-checkout"))
3536 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3537 (build-system gnu-build-system)
3540 (modify-phases %standard-phases
3541 (add-after 'unpack 'autoconf
3542 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3544 ;; XXX: TODO: Enable Lua and Guile bindings.
3545 ;; https://github.com/tjunier/newick_utils/issues/13
3546 `(("libxml2" ,libxml2)
3550 `(("autoconf" ,autoconf)
3551 ("automake" ,automake)
3552 ("libtool" ,libtool)))
3553 (synopsis "Programs for working with newick format phylogenetic trees")
3555 "Newick-utils is a suite of utilities for processing phylogenetic trees
3556 in Newick format. Functions include re-rooting, extracting subtrees,
3557 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3558 (home-page "https://github.com/tjunier/newick_utils")
3559 (license license:bsd-3))))
3568 "https://github.com/wwood/OrfM/releases/download/v"
3569 version "/orfm-" version ".tar.gz"))
3572 "19hwp13n82isdvk16710l9m35cmzf0q3fsrcn3r8c5r67biiz39s"))))
3573 (build-system gnu-build-system)
3574 (inputs `(("zlib" ,zlib)))
3576 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3577 ("ruby-rspec" ,ruby-rspec)
3579 (synopsis "Simple and not slow open reading frame (ORF) caller")
3581 "An ORF caller finds stretches of DNA that, when translated, are not
3582 interrupted by stop codons. OrfM finds and prints these ORFs.")
3583 (home-page "https://github.com/wwood/OrfM")
3584 (license license:lgpl3+)))
3586 (define-public python2-pbcore
3588 (name "python2-pbcore")
3592 (uri (pypi-uri "pbcore" version))
3595 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3596 (build-system python-build-system)
3597 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3599 `(("python-cython" ,python2-cython)
3600 ("python-numpy" ,python2-numpy)
3601 ("python-pysam" ,python2-pysam)
3602 ("python-h5py" ,python2-h5py)))
3604 `(("python-nose" ,python2-nose)
3605 ("python-sphinx" ,python2-sphinx)
3606 ("python-pyxb" ,python2-pyxb)))
3607 (home-page "http://pacificbiosciences.github.io/pbcore/")
3608 (synopsis "Library for reading and writing PacBio data files")
3610 "The pbcore package provides Python APIs for interacting with PacBio data
3611 files and writing bioinformatics applications.")
3612 (license license:bsd-3)))
3614 (define-public python2-warpedlmm
3616 (name "python2-warpedlmm")
3622 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3626 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3627 (build-system python-build-system)
3629 `(#:python ,python-2)) ; requires Python 2.7
3631 `(("python-scipy" ,python2-scipy)
3632 ("python-numpy" ,python2-numpy)
3633 ("python-matplotlib" ,python2-matplotlib)
3634 ("python-fastlmm" ,python2-fastlmm)
3635 ("python-pandas" ,python2-pandas)
3636 ("python-pysnptools" ,python2-pysnptools)))
3638 `(("python-mock" ,python2-mock)
3639 ("python-nose" ,python2-nose)
3641 (home-page "https://github.com/PMBio/warpedLMM")
3642 (synopsis "Implementation of warped linear mixed models")
3644 "WarpedLMM is a Python implementation of the warped linear mixed model,
3645 which automatically learns an optimal warping function (or transformation) for
3646 the phenotype as it models the data.")
3647 (license license:asl2.0)))
3649 (define-public pbtranscript-tofu
3650 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3652 (name "pbtranscript-tofu")
3653 (version (string-append "2.2.3." (string-take commit 7)))
3657 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3659 (file-name (string-append name "-" version "-checkout"))
3662 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3663 (modules '((guix build utils)))
3666 ;; remove bundled Cython sources
3667 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3669 (build-system python-build-system)
3671 `(#:python ,python-2
3672 ;; FIXME: Tests fail with "No such file or directory:
3673 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3676 (modify-phases %standard-phases
3677 (add-after 'unpack 'enter-directory
3679 (chdir "pbtranscript-tofu/pbtranscript/")
3681 ;; With setuptools version 18.0 and later this setup.py hack causes
3682 ;; a build error, so we disable it.
3683 (add-after 'enter-directory 'patch-setuppy
3685 (substitute* "setup.py"
3686 (("if 'setuptools.extension' in sys.modules:")
3690 `(("python-numpy" ,python2-numpy)
3691 ("python-bx-python" ,python2-bx-python)
3692 ("python-networkx" ,python2-networkx)
3693 ("python-scipy" ,python2-scipy)
3694 ("python-pbcore" ,python2-pbcore)
3695 ("python-h5py" ,python2-h5py)))
3697 `(("python-cython" ,python2-cython)
3698 ("python-nose" ,python2-nose)))
3699 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3700 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3702 "pbtranscript-tofu contains scripts to analyze transcriptome data
3703 generated using the PacBio Iso-Seq protocol.")
3704 (license license:bsd-3))))
3706 (define-public prank
3713 "http://wasabiapp.org/download/prank/prank.source."
3717 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3718 (build-system gnu-build-system)
3721 (modify-phases %standard-phases
3722 (add-after 'unpack 'enter-src-dir
3726 (add-after 'unpack 'remove-m64-flag
3727 ;; Prank will build with the correct 'bit-ness' without this flag
3728 ;; and this allows building on 32-bit machines.
3729 (lambda _ (substitute* "src/Makefile"
3734 (lambda* (#:key outputs #:allow-other-keys)
3735 (let* ((out (assoc-ref outputs "out"))
3736 (bin (string-append out "/bin"))
3737 (man (string-append out "/share/man/man1"))
3738 (path (string-append
3739 (assoc-ref %build-inputs "mafft") "/bin:"
3740 (assoc-ref %build-inputs "exonerate") "/bin:"
3741 (assoc-ref %build-inputs "bppsuite") "/bin")))
3742 (install-file "prank" bin)
3743 (wrap-program (string-append bin "/prank")
3744 `("PATH" ":" prefix (,path)))
3745 (install-file "prank.1" man))
3749 ("exonerate" ,exonerate)
3750 ("bppsuite" ,bppsuite)))
3751 (home-page "http://wasabiapp.org/software/prank/")
3752 (synopsis "Probabilistic multiple sequence alignment program")
3754 "PRANK is a probabilistic multiple sequence alignment program for DNA,
3755 codon and amino-acid sequences. It is based on a novel algorithm that treats
3756 insertions correctly and avoids over-estimation of the number of deletion
3757 events. In addition, PRANK borrows ideas from maximum likelihood methods used
3758 in phylogenetics and correctly takes into account the evolutionary distances
3759 between sequences. Lastly, PRANK allows for defining a potential structure
3760 for sequences to be aligned and then, simultaneously with the alignment,
3761 predicts the locations of structural units in the sequences.")
3762 (license license:gpl2+)))
3764 (define-public proteinortho
3766 (name "proteinortho")
3773 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
3774 version "_src.tar.gz"))
3777 "05wacnnbx56avpcwhzlcf6b7s77swcpv3qnwz5sh1z54i51gg2ki"))))
3778 (build-system gnu-build-system)
3780 `(#:test-target "test"
3782 (modify-phases %standard-phases
3784 ;; There is no configure script, so we modify the Makefile directly.
3785 (lambda* (#:key outputs #:allow-other-keys)
3786 (substitute* "Makefile"
3789 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
3791 (add-before 'install 'make-install-directory
3792 ;; The install directory is not created during 'make install'.
3793 (lambda* (#:key outputs #:allow-other-keys)
3794 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3796 (add-after 'install 'wrap-programs
3797 (lambda* (#:key inputs outputs #:allow-other-keys)
3798 (let* ((path (getenv "PATH"))
3799 (out (assoc-ref outputs "out"))
3800 (binary (string-append out "/bin/proteinortho5.pl")))
3801 (wrap-program binary `("PATH" ":" prefix (,path))))
3805 ("python" ,python-2)
3806 ("blast+" ,blast+)))
3807 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
3808 (synopsis "Detect orthologous genes across species")
3810 "Proteinortho is a tool to detect orthologous genes across different
3811 species. For doing so, it compares similarities of given gene sequences and
3812 clusters them to find significant groups. The algorithm was designed to handle
3813 large-scale data and can be applied to hundreds of species at once.")
3814 (license license:gpl2+)))
3816 (define-public pyicoteo
3823 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
3824 "pyicoteo/get/v" version ".tar.bz2"))
3825 (file-name (string-append name "-" version ".tar.bz2"))
3828 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
3829 (build-system python-build-system)
3831 `(#:python ,python-2 ; does not work with Python 3
3832 #:tests? #f)) ; there are no tests
3834 `(("python2-matplotlib" ,python2-matplotlib)))
3835 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
3836 (synopsis "Analyze high-throughput genetic sequencing data")
3838 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
3839 sequencing data. It works with genomic coordinates. There are currently six
3840 different command-line tools:
3843 @item pyicoregion: for generating exploratory regions automatically;
3844 @item pyicoenrich: for differential enrichment between two conditions;
3845 @item pyicoclip: for calling CLIP-Seq peaks without a control;
3846 @item pyicos: for genomic coordinates manipulation;
3847 @item pyicoller: for peak calling on punctuated ChIP-Seq;
3848 @item pyicount: to count how many reads from N experiment files overlap in a
3850 @item pyicotrocol: to combine operations from pyicoteo.
3852 (license license:gpl3+)))
3854 (define-public prodigal
3861 "https://github.com/hyattpd/Prodigal/archive/v"
3863 (file-name (string-append name "-" version ".tar.gz"))
3866 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
3867 (build-system gnu-build-system)
3869 `(#:tests? #f ;no check target
3870 #:make-flags (list (string-append "INSTALLDIR="
3871 (assoc-ref %outputs "out")
3874 (modify-phases %standard-phases
3875 (delete 'configure))))
3876 (home-page "http://prodigal.ornl.gov")
3877 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
3879 "Prodigal runs smoothly on finished genomes, draft genomes, and
3880 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
3881 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
3882 partial genes, and identifies translation initiation sites.")
3883 (license license:gpl3+)))
3885 (define-public roary
3893 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
3897 "0x2hpb3nfsc6x2nq1788w0fhqfzc7cn2dp4xwyva9m3k6xlz0m43"))))
3898 (build-system perl-build-system)
3901 (modify-phases %standard-phases
3906 ;; The tests are not run by default, so we run each test file
3908 (setenv "PATH" (string-append (getcwd) "/bin" ":"
3910 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
3911 (getenv "PERL5LIB")))
3912 (zero? (length (filter (lambda (file)
3913 (display file)(display "\n")
3914 (not (zero? (system* "perl" file))))
3915 (find-files "t" ".*\\.t$"))))))
3917 ;; There is no 'install' target in the Makefile.
3918 (lambda* (#:key outputs #:allow-other-keys)
3919 (let* ((out (assoc-ref outputs "out"))
3920 (bin (string-append out "/bin"))
3921 (perl (string-append out "/lib/perl5/site_perl"))
3922 (roary-plots "contrib/roary_plots"))
3925 (copy-recursively "bin" bin)
3926 (copy-recursively "lib" perl)
3928 (add-after 'install 'wrap-programs
3929 (lambda* (#:key inputs outputs #:allow-other-keys)
3930 (let* ((out (assoc-ref outputs "out"))
3931 (perl5lib (getenv "PERL5LIB"))
3932 (path (getenv "PATH")))
3933 (for-each (lambda (prog)
3934 (let ((binary (string-append out "/" prog)))
3935 (wrap-program binary
3936 `("PERL5LIB" ":" prefix
3937 (,(string-append perl5lib ":" out
3938 "/lib/perl5/site_perl"))))
3939 (wrap-program binary
3941 (,(string-append path ":" out "/bin"))))))
3942 (find-files "bin" ".*[^R]$"))
3944 (string-append out "/bin/roary-create_pan_genome_plots.R"))
3945 (r-site-lib (getenv "R_LIBS_SITE"))
3947 (string-append (assoc-ref inputs "coreutils") "/bin")))
3949 `("R_LIBS_SITE" ":" prefix
3950 (,(string-append r-site-lib ":" out "/site-library/"))))
3953 (,(string-append coreutils-path ":" out "/bin"))))))
3956 `(("perl-env-path" ,perl-env-path)
3957 ("perl-test-files" ,perl-test-files)
3958 ("perl-test-most" ,perl-test-most)
3959 ("perl-test-output" ,perl-test-output)))
3961 `(("perl-array-utils" ,perl-array-utils)
3962 ("bioperl" ,bioperl-minimal)
3963 ("perl-exception-class" ,perl-exception-class)
3964 ("perl-file-find-rule" ,perl-file-find-rule)
3965 ("perl-file-grep" ,perl-file-grep)
3966 ("perl-file-slurper" ,perl-file-slurper)
3967 ("perl-file-which" ,perl-file-which)
3968 ("perl-graph" ,perl-graph)
3969 ("perl-graph-readwrite" ,perl-graph-readwrite)
3970 ("perl-log-log4perl" ,perl-log-log4perl)
3971 ("perl-moose" ,perl-moose)
3972 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
3973 ("perl-text-csv" ,perl-text-csv)
3974 ("bedtools" ,bedtools)
3978 ("parallel" ,parallel)
3981 ("fasttree" ,fasttree)
3986 ("r-ggplot2" ,r-ggplot2)
3987 ("coreutils" ,coreutils)))
3988 (home-page "http://sanger-pathogens.github.io/Roary")
3989 (synopsis "High speed stand-alone pan genome pipeline")
3991 "Roary is a high speed stand alone pan genome pipeline, which takes
3992 annotated assemblies in GFF3 format (produced by the Prokka program) and
3993 calculates the pan genome. Using a standard desktop PC, it can analyse
3994 datasets with thousands of samples, without compromising the quality of the
3995 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
3996 single processor. Roary is not intended for metagenomics or for comparing
3997 extremely diverse sets of genomes.")
3998 (license license:gpl3)))
4000 (define-public raxml
4009 "https://github.com/stamatak/standard-RAxML/archive/v"
4011 (file-name (string-append name "-" version ".tar.gz"))
4014 "1pv8p2fy67y21a9y4cm7xpvxqjwz2v4201flfjshdq1p8j52rqf7"))))
4015 (build-system gnu-build-system)
4017 `(#:tests? #f ; There are no tests.
4018 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4019 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4021 (modify-phases %standard-phases
4024 (lambda* (#:key outputs #:allow-other-keys)
4025 (let* ((out (assoc-ref outputs "out"))
4026 (bin (string-append out "/bin"))
4027 (executable "raxmlHPC-HYBRID"))
4028 (install-file executable bin)
4029 (symlink (string-append bin "/" executable) "raxml"))
4032 `(("openmpi" ,openmpi)))
4033 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4034 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4036 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4038 (license license:gpl2+)))
4048 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4051 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4052 (patches (search-patches "rsem-makefile.patch"))
4053 (modules '((guix build utils)))
4056 ;; remove bundled copy of boost
4057 (delete-file-recursively "boost")
4059 (build-system gnu-build-system)
4061 `(#:tests? #f ;no "check" target
4063 (modify-phases %standard-phases
4064 ;; No "configure" script.
4065 ;; Do not build bundled samtools library.
4068 (substitute* "Makefile"
4069 (("^all : sam/libbam.a") "all : "))
4072 (lambda* (#:key outputs #:allow-other-keys)
4073 (let* ((out (string-append (assoc-ref outputs "out")))
4074 (bin (string-append out "/bin/"))
4075 (perl (string-append out "/lib/perl5/site_perl")))
4078 (for-each (lambda (file)
4080 (string-append bin (basename file))))
4081 (find-files "." "rsem-.*"))
4082 (copy-file "rsem_perl_utils.pm"
4083 (string-append perl "/rsem_perl_utils.pm")))
4086 'install 'wrap-program
4087 (lambda* (#:key outputs #:allow-other-keys)
4088 (let ((out (assoc-ref outputs "out")))
4089 (for-each (lambda (prog)
4090 (wrap-program (string-append out "/bin/" prog)
4091 `("PERL5LIB" ":" prefix
4092 (,(string-append out "/lib/perl5/site_perl")))))
4093 '("rsem-plot-transcript-wiggles"
4094 "rsem-calculate-expression"
4095 "rsem-generate-ngvector"
4097 "rsem-prepare-reference")))
4101 ("ncurses" ,ncurses)
4104 ("samtools" ,samtools-0.1)
4106 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4107 (synopsis "Estimate gene expression levels from RNA-Seq data")
4109 "RSEM is a software package for estimating gene and isoform expression
4110 levels from RNA-Seq data. The RSEM package provides a user-friendly
4111 interface, supports threads for parallel computation of the EM algorithm,
4112 single-end and paired-end read data, quality scores, variable-length reads and
4113 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4114 interval estimates for expression levels. For visualization, it can generate
4115 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4116 (license license:gpl3+)))
4118 (define-public rseqc
4126 (string-append "mirror://sourceforge/rseqc/"
4127 "RSeQC-" version ".tar.gz"))
4129 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4130 (modules '((guix build utils)))
4133 ;; remove bundled copy of pysam
4134 (delete-file-recursively "lib/pysam")
4135 (substitute* "setup.py"
4136 ;; remove dependency on outdated "distribute" module
4137 (("^from distribute_setup import use_setuptools") "")
4138 (("^use_setuptools\\(\\)") "")
4139 ;; do not use bundled copy of pysam
4140 (("^have_pysam = False") "have_pysam = True"))))))
4141 (build-system python-build-system)
4142 (arguments `(#:python ,python-2))
4144 `(("python-cython" ,python2-cython)
4145 ("python-pysam" ,python2-pysam)
4146 ("python-numpy" ,python2-numpy)
4149 `(("python-nose" ,python2-nose)))
4150 (home-page "http://rseqc.sourceforge.net/")
4151 (synopsis "RNA-seq quality control package")
4153 "RSeQC provides a number of modules that can comprehensively evaluate
4154 high throughput sequence data, especially RNA-seq data. Some basic modules
4155 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4156 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4157 distribution, coverage uniformity, strand specificity, etc.")
4158 (license license:gpl3+)))
4161 ;; There are no release tarballs. According to the installation
4162 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4163 ;; stable release is identified by this changeset ID.
4164 (let ((changeset "2329130")
4168 (version (string-append "0-" revision "." changeset))
4172 (url "https://bitbucket.org/libsleipnir/sleipnir")
4173 (changeset changeset)))
4176 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4177 (build-system gnu-build-system)
4179 `(#:modules ((srfi srfi-1)
4180 (guix build gnu-build-system)
4183 (let ((dirs '("SeekMiner"
4189 (modify-phases %standard-phases
4190 (add-before 'configure 'bootstrap
4192 (zero? (system* "bash" "gen_auto"))))
4193 (add-after 'build 'build-additional-tools
4194 (lambda* (#:key make-flags #:allow-other-keys)
4195 (every (lambda (dir)
4196 (with-directory-excursion (string-append "tools/" dir)
4197 (zero? (apply system* "make" make-flags))))
4199 (add-after 'install 'install-additional-tools
4200 (lambda* (#:key make-flags #:allow-other-keys)
4201 (fold (lambda (dir result)
4202 (with-directory-excursion (string-append "tools/" dir)
4204 (zero? (apply system*
4205 `("make" ,@make-flags "install"))))))
4211 ("readline" ,readline)
4212 ("gengetopt" ,gengetopt)
4213 ("log4cpp" ,log4cpp)))
4215 `(("autoconf" ,autoconf)
4216 ("automake" ,automake)
4218 (home-page "http://seek.princeton.edu")
4219 (synopsis "Gene co-expression search engine")
4221 "SEEK is a computational gene co-expression search engine. SEEK provides
4222 biologists with a way to navigate the massive human expression compendium that
4223 now contains thousands of expression datasets. SEEK returns a robust ranking
4224 of co-expressed genes in the biological area of interest defined by the user's
4225 query genes. It also prioritizes thousands of expression datasets according
4226 to the user's query of interest.")
4227 (license license:cc-by3.0))))
4229 (define-public samtools
4237 (string-append "mirror://sourceforge/samtools/samtools/"
4238 version "/samtools-" version ".tar.bz2"))
4241 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4242 (build-system gnu-build-system)
4244 `(#:modules ((ice-9 ftw)
4246 (guix build gnu-build-system)
4248 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4249 #:configure-flags (list "--with-ncurses")
4252 'unpack 'patch-tests
4254 (substitute* "test/test.pl"
4255 ;; The test script calls out to /bin/bash
4256 (("/bin/bash") (which "bash")))
4259 'install 'install-library
4260 (lambda* (#:key outputs #:allow-other-keys)
4261 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4262 (install-file "libbam.a" lib)))
4264 'install 'install-headers
4265 (lambda* (#:key outputs #:allow-other-keys)
4266 (let ((include (string-append (assoc-ref outputs "out")
4267 "/include/samtools/")))
4268 (for-each (lambda (file)
4269 (install-file file include))
4270 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4272 %standard-phases)))))
4273 (native-inputs `(("pkg-config" ,pkg-config)))
4274 (inputs `(("ncurses" ,ncurses)
4278 (home-page "http://samtools.sourceforge.net")
4279 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4281 "Samtools implements various utilities for post-processing nucleotide
4282 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4283 variant calling (in conjunction with bcftools), and a simple alignment
4285 (license license:expat)))
4287 (define-public samtools-0.1
4288 ;; This is the most recent version of the 0.1 line of samtools. The input
4289 ;; and output formats differ greatly from that used and produced by samtools
4290 ;; 1.x and is still used in many bioinformatics pipelines.
4291 (package (inherit samtools)
4297 (string-append "mirror://sourceforge/samtools/samtools/"
4298 version "/samtools-" version ".tar.bz2"))
4300 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4302 `(#:tests? #f ;no "check" target
4303 ,@(substitute-keyword-arguments (package-arguments samtools)
4304 ((#:make-flags flags)
4305 `(cons "LIBCURSES=-lncurses" ,flags))
4307 `(modify-phases ,phases
4309 (lambda* (#:key outputs #:allow-other-keys)
4310 (let ((bin (string-append
4311 (assoc-ref outputs "out") "/bin")))
4313 (copy-file "samtools"
4314 (string-append bin "/samtools")))))
4315 (delete 'patch-tests)
4316 (delete 'configure))))))))
4318 (define-public mosaik
4319 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4324 ;; There are no release tarballs nor tags.
4327 (url "https://github.com/wanpinglee/MOSAIK.git")
4329 (file-name (string-append name "-" version))
4332 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4333 (build-system gnu-build-system)
4335 `(#:tests? #f ; no tests
4336 #:make-flags (list "CC=gcc")
4338 (modify-phases %standard-phases
4340 (lambda _ (chdir "src") #t))
4342 (lambda* (#:key outputs #:allow-other-keys)
4343 (let ((bin (string-append (assoc-ref outputs "out")
4346 (copy-recursively "../bin" bin)
4351 (supported-systems '("x86_64-linux"))
4352 (home-page "https://github.com/wanpinglee/MOSAIK")
4353 (synopsis "Map nucleotide sequence reads to reference genomes")
4355 "MOSAIK is a program for mapping second and third-generation sequencing
4356 reads to a reference genome. MOSAIK can align reads generated by all the
4357 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4358 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4359 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4360 ;; code released into the public domain:
4361 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4362 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4363 (license (list license:gpl2+ license:public-domain)))))
4365 (define-public ngs-sdk
4373 (string-append "https://github.com/ncbi/ngs/archive/"
4375 (file-name (string-append name "-" version ".tar.gz"))
4378 "04y1fsmdnb5y86m3gg6f5g9wcscr6r25n7m8mdlcxy0i2q6w6cia"))))
4379 (build-system gnu-build-system)
4381 `(#:parallel-build? #f ; not supported
4382 #:tests? #f ; no "check" target
4386 (lambda* (#:key outputs #:allow-other-keys)
4387 (let ((out (assoc-ref outputs "out")))
4388 ;; The 'configure' script doesn't recognize things like
4389 ;; '--enable-fast-install'.
4390 (zero? (system* "./configure"
4391 (string-append "--build-prefix=" (getcwd) "/build")
4392 (string-append "--prefix=" out)))))
4395 (lambda _ (chdir "ngs-sdk") #t)
4396 %standard-phases))))
4397 (native-inputs `(("perl" ,perl)))
4398 ;; According to the test
4399 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4400 ;; in ngs-sdk/setup/konfigure.perl
4401 (supported-systems '("i686-linux" "x86_64-linux"))
4402 (home-page "https://github.com/ncbi/ngs")
4403 (synopsis "API for accessing Next Generation Sequencing data")
4405 "NGS is a domain-specific API for accessing reads, alignments and pileups
4406 produced from Next Generation Sequencing. The API itself is independent from
4407 any particular back-end implementation, and supports use of multiple back-ends
4409 (license license:public-domain)))
4411 (define-public java-ngs
4412 (package (inherit ngs-sdk)
4415 `(,@(substitute-keyword-arguments
4416 `(#:modules ((guix build gnu-build-system)
4420 ,@(package-arguments ngs-sdk))
4422 `(modify-phases ,phases
4423 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4425 `(("jdk" ,icedtea "jdk")
4426 ("ngs-sdk" ,ngs-sdk)))
4427 (synopsis "Java bindings for NGS SDK")))
4429 (define-public ncbi-vdb
4437 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4439 (file-name (string-append name "-" version ".tar.gz"))
4442 "0x1cg1x8vy0yjlkp0snc1533zcjhxqzqsaiwqk598n7vvw37n8lf"))))
4443 (build-system gnu-build-system)
4445 `(#:parallel-build? #f ; not supported
4446 #:tests? #f ; no "check" target
4450 (lambda* (#:key inputs outputs #:allow-other-keys)
4451 (let ((out (assoc-ref outputs "out")))
4452 ;; Override include path for libmagic
4453 (substitute* "setup/package.prl"
4454 (("name => 'magic', Include => '/usr/include'")
4455 (string-append "name=> 'magic', Include => '"
4456 (assoc-ref inputs "libmagic")
4459 ;; Install kdf5 library (needed by sra-tools)
4460 (substitute* "build/Makefile.install"
4461 (("LIBRARIES_TO_INSTALL =")
4462 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4464 (substitute* "build/Makefile.env"
4465 (("CFLAGS =" prefix)
4466 (string-append prefix "-msse2 ")))
4468 ;; The 'configure' script doesn't recognize things like
4469 ;; '--enable-fast-install'.
4472 (string-append "--build-prefix=" (getcwd) "/build")
4473 (string-append "--prefix=" (assoc-ref outputs "out"))
4474 (string-append "--debug")
4475 (string-append "--with-xml2-prefix="
4476 (assoc-ref inputs "libxml2"))
4477 (string-append "--with-ngs-sdk-prefix="
4478 (assoc-ref inputs "ngs-sdk"))
4479 (string-append "--with-ngs-java-prefix="
4480 (assoc-ref inputs "java-ngs"))
4481 (string-append "--with-hdf5-prefix="
4482 (assoc-ref inputs "hdf5"))))))
4484 'install 'install-interfaces
4485 (lambda* (#:key outputs #:allow-other-keys)
4486 ;; Install interface libraries. On i686 the interface libraries
4487 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4488 ;; architecture name ("i386") instead of the target system prefix
4490 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4491 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4492 ,(system->linux-architecture
4493 (or (%current-target-system)
4496 (string-append (assoc-ref outputs "out")
4498 ;; Install interface headers
4499 (copy-recursively "interfaces"
4500 (string-append (assoc-ref outputs "out")
4502 %standard-phases))))
4504 `(("libxml2" ,libxml2)
4505 ("ngs-sdk" ,ngs-sdk)
4506 ("java-ngs" ,java-ngs)
4509 (native-inputs `(("perl" ,perl)))
4510 ;; NCBI-VDB requires SSE capability.
4511 (supported-systems '("i686-linux" "x86_64-linux"))
4512 (home-page "https://github.com/ncbi/ncbi-vdb")
4513 (synopsis "Database engine for genetic information")
4515 "The NCBI-VDB library implements a highly compressed columnar data
4516 warehousing engine that is most often used to store genetic information.
4517 Databases are stored in a portable image within the file system, and can be
4518 accessed/downloaded on demand across HTTP.")
4519 (license license:public-domain)))
4521 (define-public plink
4529 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4530 version "-src.zip"))
4532 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4533 (patches (search-patches "plink-1.07-unclobber-i.patch"
4534 "plink-endian-detection.patch"))))
4535 (build-system gnu-build-system)
4537 '(#:tests? #f ;no "check" target
4538 #:make-flags (list (string-append "LIB_LAPACK="
4539 (assoc-ref %build-inputs "lapack")
4540 "/lib/liblapack.so")
4543 ;; disable phoning home
4546 (modify-phases %standard-phases
4547 ;; no "configure" script
4550 (lambda* (#:key outputs #:allow-other-keys)
4551 (let ((bin (string-append (assoc-ref outputs "out")
4553 (install-file "plink" bin)
4557 ("lapack" ,lapack)))
4559 `(("unzip" ,unzip)))
4560 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4561 (synopsis "Whole genome association analysis toolset")
4563 "PLINK is a whole genome association analysis toolset, designed to
4564 perform a range of basic, large-scale analyses in a computationally efficient
4565 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4566 so there is no support for steps prior to this (e.g. study design and
4567 planning, generating genotype or CNV calls from raw data). Through
4568 integration with gPLINK and Haploview, there is some support for the
4569 subsequent visualization, annotation and storage of results.")
4570 ;; Code is released under GPLv2, except for fisher.h, which is under
4572 (license (list license:gpl2 license:lgpl2.1+))))
4574 (define-public smithlab-cpp
4575 (let ((revision "1")
4576 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4578 (name "smithlab-cpp")
4579 (version (string-append "0." revision "." (string-take commit 7)))
4583 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4585 (file-name (string-append name "-" version "-checkout"))
4588 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4589 (build-system gnu-build-system)
4591 `(#:modules ((guix build gnu-build-system)
4594 #:tests? #f ;no "check" target
4596 (modify-phases %standard-phases
4597 (add-after 'unpack 'use-samtools-headers
4599 (substitute* '("SAM.cpp"
4601 (("sam.h") "samtools/sam.h"))
4604 (lambda* (#:key outputs #:allow-other-keys)
4605 (let* ((out (assoc-ref outputs "out"))
4606 (lib (string-append out "/lib"))
4607 (include (string-append out "/include/smithlab-cpp")))
4610 (for-each (cut install-file <> lib)
4611 (find-files "." "\\.o$"))
4612 (for-each (cut install-file <> include)
4613 (find-files "." "\\.hpp$")))
4615 (delete 'configure))))
4617 `(("samtools" ,samtools-0.1)
4619 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4620 (synopsis "C++ helper library for functions used in Smith lab projects")
4622 "Smithlab CPP is a C++ library that includes functions used in many of
4623 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4624 structures, classes for genomic regions, mapped sequencing reads, etc.")
4625 (license license:gpl3+))))
4627 (define-public preseq
4633 (uri (string-append "https://github.com/smithlabcode/"
4634 "preseq/archive/v" version ".tar.gz"))
4635 (file-name (string-append name "-" version ".tar.gz"))
4637 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4638 (modules '((guix build utils)))
4640 ;; Remove bundled samtools.
4641 '(delete-file-recursively "samtools"))))
4642 (build-system gnu-build-system)
4644 `(#:tests? #f ;no "check" target
4646 (modify-phases %standard-phases
4647 (delete 'configure))
4649 (list (string-append "PREFIX="
4650 (assoc-ref %outputs "out"))
4651 (string-append "LIBBAM="
4652 (assoc-ref %build-inputs "samtools")
4654 (string-append "SMITHLAB_CPP="
4655 (assoc-ref %build-inputs "smithlab-cpp")
4658 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4661 ("samtools" ,samtools-0.1)
4662 ("smithlab-cpp" ,smithlab-cpp)
4664 (home-page "http://smithlabresearch.org/software/preseq/")
4665 (synopsis "Program for analyzing library complexity")
4667 "The preseq package is aimed at predicting and estimating the complexity
4668 of a genomic sequencing library, equivalent to predicting and estimating the
4669 number of redundant reads from a given sequencing depth and how many will be
4670 expected from additional sequencing using an initial sequencing experiment.
4671 The estimates can then be used to examine the utility of further sequencing,
4672 optimize the sequencing depth, or to screen multiple libraries to avoid low
4673 complexity samples.")
4674 (license license:gpl3+)))
4676 (define-public python-screed
4678 (name "python-screed")
4683 (uri (pypi-uri "screed" version))
4686 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4687 (build-system python-build-system)
4690 (modify-phases %standard-phases
4693 (setenv "PYTHONPATH"
4694 (string-append (getenv "PYTHONPATH") ":."))
4695 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4697 `(("python-nose" ,python-nose)))
4699 `(("python-bz2file" ,python-bz2file)))
4700 (home-page "http://github.com/dib-lab/screed/")
4701 (synopsis "Short read sequence database utilities")
4702 (description "Screed parses FASTA and FASTQ files and generates databases.
4703 Values such as sequence name, sequence description, sequence quality and the
4704 sequence itself can be retrieved from these databases.")
4705 (license license:bsd-3)))
4707 (define-public python2-screed
4708 (package-with-python2 python-screed))
4710 (define-public sra-tools
4718 (string-append "https://github.com/ncbi/sra-tools/archive/"
4720 (file-name (string-append name "-" version ".tar.gz"))
4723 "13paw7bq6y47d2pl0ac5gpgcqp1xsy1g7v1fwysm3hr8lb2dck17"))))
4724 (build-system gnu-build-system)
4726 `(#:parallel-build? #f ; not supported
4727 #:tests? #f ; no "check" target
4729 (list (string-append "VDB_LIBDIR="
4730 (assoc-ref %build-inputs "ncbi-vdb")
4731 ,(if (string-prefix? "x86_64"
4732 (or (%current-target-system)
4739 (lambda* (#:key inputs outputs #:allow-other-keys)
4740 ;; The build system expects a directory containing the sources and
4741 ;; raw build output of ncbi-vdb, including files that are not
4742 ;; installed. Since we are building against an installed version of
4743 ;; ncbi-vdb, the following modifications are needed.
4744 (substitute* "setup/konfigure.perl"
4745 ;; Make the configure script look for the "ilib" directory of
4746 ;; "ncbi-vdb" without first checking for the existence of a
4747 ;; matching library in its "lib" directory.
4748 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
4749 "my $f = File::Spec->catdir($ilibdir, $ilib);")
4750 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
4751 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
4752 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
4755 (substitute* "tools/copycat/Makefile"
4756 (("smagic-static") "lmagic"))
4758 ;; The 'configure' script doesn't recognize things like
4759 ;; '--enable-fast-install'.
4762 (string-append "--build-prefix=" (getcwd) "/build")
4763 (string-append "--prefix=" (assoc-ref outputs "out"))
4764 (string-append "--debug")
4765 (string-append "--with-fuse-prefix="
4766 (assoc-ref inputs "fuse"))
4767 (string-append "--with-magic-prefix="
4768 (assoc-ref inputs "libmagic"))
4769 ;; TODO: building with libxml2 fails with linker errors
4770 ;; (string-append "--with-xml2-prefix="
4771 ;; (assoc-ref inputs "libxml2"))
4772 (string-append "--with-ncbi-vdb-sources="
4773 (assoc-ref inputs "ncbi-vdb"))
4774 (string-append "--with-ncbi-vdb-build="
4775 (assoc-ref inputs "ncbi-vdb"))
4776 (string-append "--with-ngs-sdk-prefix="
4777 (assoc-ref inputs "ngs-sdk"))
4778 (string-append "--with-hdf5-prefix="
4779 (assoc-ref inputs "hdf5")))))
4781 (native-inputs `(("perl" ,perl)))
4783 `(("ngs-sdk" ,ngs-sdk)
4784 ("ncbi-vdb" ,ncbi-vdb)
4789 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
4790 (synopsis "Tools and libraries for reading and writing sequencing data")
4792 "The SRA Toolkit from NCBI is a collection of tools and libraries for
4793 reading of sequencing files from the Sequence Read Archive (SRA) database and
4794 writing files into the .sra format.")
4795 (license license:public-domain)))
4797 (define-public seqan
4803 (uri (string-append "http://packages.seqan.de/seqan-library/"
4804 "seqan-library-" version ".tar.bz2"))
4807 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
4808 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
4809 ;; makes sense to split the outputs.
4810 (outputs '("out" "doc"))
4811 (build-system trivial-build-system)
4813 `(#:modules ((guix build utils))
4816 (use-modules (guix build utils))
4817 (let ((tar (assoc-ref %build-inputs "tar"))
4818 (bzip (assoc-ref %build-inputs "bzip2"))
4819 (out (assoc-ref %outputs "out"))
4820 (doc (assoc-ref %outputs "doc")))
4821 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
4822 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
4823 (chdir (string-append "seqan-library-" ,version))
4824 (copy-recursively "include" (string-append out "/include"))
4825 (copy-recursively "share" (string-append doc "/share"))))))
4827 `(("source" ,source)
4830 (home-page "http://www.seqan.de")
4831 (synopsis "Library for nucleotide sequence analysis")
4833 "SeqAn is a C++ library of efficient algorithms and data structures for
4834 the analysis of sequences with the focus on biological data. It contains
4835 algorithms and data structures for string representation and their
4836 manipulation, online and indexed string search, efficient I/O of
4837 bioinformatics file formats, sequence alignment, and more.")
4838 (license license:bsd-3)))
4840 (define-public seqmagick
4848 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
4852 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
4853 (build-system python-build-system)
4855 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
4856 `(#:python ,python-2
4858 (modify-phases %standard-phases
4859 ;; Current test in setup.py does not work as of 0.6.1,
4860 ;; so use nose to run tests instead for now. See
4861 ;; https://github.com/fhcrc/seqmagick/issues/55
4862 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
4864 ;; biopython-1.66 is required due to
4865 ;; https://github.com/fhcrc/seqmagick/issues/59
4866 ;; When that issue is resolved the 'python2-biopython-1.66' package
4867 ;; should be removed.
4868 `(("python-biopython" ,python2-biopython-1.66)))
4870 `(("python-nose" ,python2-nose)))
4871 (home-page "http://github.com/fhcrc/seqmagick")
4872 (synopsis "Tools for converting and modifying sequence files")
4874 "Bioinformaticians often have to convert sequence files between formats
4875 and do little manipulations on them, and it's not worth writing scripts for
4876 that. Seqmagick is a utility to expose the file format conversion in
4877 BioPython in a convenient way. Instead of having a big mess of scripts, there
4878 is one that takes arguments.")
4879 (license license:gpl3)))
4881 (define-public seqtk
4888 "https://github.com/lh3/seqtk/archive/v"
4890 (file-name (string-append name "-" version ".tar.gz"))
4893 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
4894 (modules '((guix build utils)))
4897 ;; Remove extraneous header files, as is done in the seqtk
4899 (for-each (lambda (file) (delete-file file))
4900 (list "ksort.h" "kstring.h" "kvec.h"))
4902 (build-system gnu-build-system)
4905 (modify-phases %standard-phases
4908 ;; There are no tests, so we just run a sanity check.
4909 (lambda _ (zero? (system* "./seqtk" "seq"))))
4911 (lambda* (#:key outputs #:allow-other-keys)
4912 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4913 (install-file "seqtk" bin)))))))
4916 (home-page "https://github.com/lh3/seqtk")
4917 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
4919 "Seqtk is a fast and lightweight tool for processing sequences in the
4920 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
4921 optionally compressed by gzip.")
4922 (license license:expat)))
4924 (define-public snap-aligner
4926 (name "snap-aligner")
4927 (version "1.0beta.18")
4931 "https://github.com/amplab/snap/archive/v"
4933 (file-name (string-append name "-" version ".tar.gz"))
4936 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
4937 (build-system gnu-build-system)
4940 (modify-phases %standard-phases
4942 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
4944 (lambda* (#:key outputs #:allow-other-keys)
4945 (let* ((out (assoc-ref outputs "out"))
4946 (bin (string-append out "/bin")))
4947 (install-file "snap-aligner" bin)
4948 (install-file "SNAPCommand" bin)
4952 (home-page "http://snap.cs.berkeley.edu/")
4953 (synopsis "Short read DNA sequence aligner")
4955 "SNAP is a fast and accurate aligner for short DNA reads. It is
4956 optimized for modern read lengths of 100 bases or higher, and takes advantage
4957 of these reads to align data quickly through a hash-based indexing scheme.")
4958 ;; 32-bit systems are not supported by the unpatched code.
4959 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
4960 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
4961 ;; systems without a lot of memory cannot make good use of this program.
4962 (supported-systems '("x86_64-linux"))
4963 (license license:asl2.0)))
4965 (define-public sortmerna
4973 "https://github.com/biocore/sortmerna/archive/"
4975 (file-name (string-append name "-" version ".tar.gz"))
4978 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
4979 (build-system gnu-build-system)
4980 (outputs '("out" ;for binaries
4981 "db")) ;for sequence databases
4984 (modify-phases %standard-phases
4986 (lambda* (#:key outputs #:allow-other-keys)
4987 (let* ((out (assoc-ref outputs "out"))
4988 (bin (string-append out "/bin"))
4989 (db (assoc-ref outputs "db"))
4991 (string-append db "/share/sortmerna/rRNA_databases")))
4992 (install-file "sortmerna" bin)
4993 (install-file "indexdb_rna" bin)
4994 (for-each (lambda (file)
4995 (install-file file share))
4996 (find-files "rRNA_databases" ".*fasta"))
5000 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5001 (synopsis "Biological sequence analysis tool for NGS reads")
5003 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5004 and operational taxonomic unit (OTU) picking of next generation
5005 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5006 allows for fast and sensitive analyses of nucleotide sequences. The main
5007 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5008 (license license:lgpl3)))
5016 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5018 (file-name (string-append name "-" version ".tar.gz"))
5021 "1na6np880r1zaamiy00hy8bid5anpy0kgf63587v2yl080krk2zq"))
5022 (modules '((guix build utils)))
5025 (substitute* "source/Makefile"
5027 ;; Remove pre-built binaries and bundled htslib sources.
5028 (delete-file-recursively "bin/MacOSX_x86_64")
5029 (delete-file-recursively "bin/Linux_x86_64")
5030 (delete-file-recursively "bin/Linux_x86_64_static")
5031 (delete-file-recursively "source/htslib")
5033 (build-system gnu-build-system)
5035 '(#:tests? #f ;no check target
5036 #:make-flags '("STAR")
5038 (modify-phases %standard-phases
5039 (add-after 'unpack 'enter-source-dir
5040 (lambda _ (chdir "source") #t))
5041 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5043 (substitute* "Makefile"
5044 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5046 (substitute* '("BAMfunctions.cpp"
5051 "bamRemoveDuplicates.cpp")
5052 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5053 (string-append "#include <" header ">")))
5054 (substitute* "IncludeDefine.h"
5055 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5056 (string-append "<" header ">")))
5059 (lambda* (#:key outputs #:allow-other-keys)
5060 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5061 (install-file "STAR" bin))
5063 (delete 'configure))))
5065 `(("vim" ,vim))) ; for xxd
5067 `(("htslib" ,htslib)
5069 (home-page "https://github.com/alexdobin/STAR")
5070 (synopsis "Universal RNA-seq aligner")
5072 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5073 based on a previously undescribed RNA-seq alignment algorithm that uses
5074 sequential maximum mappable seed search in uncompressed suffix arrays followed
5075 by seed clustering and stitching procedure. In addition to unbiased de novo
5076 detection of canonical junctions, STAR can discover non-canonical splices and
5077 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5079 ;; Only 64-bit systems are supported according to the README.
5080 (supported-systems '("x86_64-linux" "mips64el-linux"))
5081 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5082 (license license:gpl3+)))
5084 (define-public subread
5090 (uri (string-append "mirror://sourceforge/subread/subread-"
5091 version "/subread-" version "-source.tar.gz"))
5094 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5095 (build-system gnu-build-system)
5097 `(#:tests? #f ;no "check" target
5098 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5099 ;; optimizations by default, so we override these flags such that x86_64
5100 ;; flags are only added when the build target is an x86_64 system.
5102 (list (let ((system ,(or (%current-target-system)
5104 (flags '("-ggdb" "-fomit-frame-pointer"
5105 "-ffast-math" "-funroll-loops"
5106 "-fmessage-length=0"
5107 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5109 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5110 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5111 (if (string-prefix? "x86_64" system)
5112 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5113 (string-append "CCFLAGS=" (string-join flags))))
5114 "-f" "Makefile.Linux"
5115 "CC=gcc ${CCFLAGS}")
5119 (lambda _ (chdir "src") #t)
5122 (lambda* (#:key outputs #:allow-other-keys)
5123 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5125 (copy-recursively "../bin" bin)))
5126 ;; no "configure" script
5127 (alist-delete 'configure %standard-phases)))))
5128 (inputs `(("zlib" ,zlib)))
5129 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5130 (synopsis "Tool kit for processing next-gen sequencing data")
5132 "The subread package contains the following tools: subread aligner, a
5133 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5134 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5135 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5136 against local background noises.")
5137 (license license:gpl3+)))
5139 (define-public stringtie
5145 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5146 "stringtie-" version ".tar.gz"))
5149 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5150 (modules '((guix build utils)))
5153 (delete-file-recursively "samtools-0.1.18")
5155 (build-system gnu-build-system)
5157 `(#:tests? #f ;no test suite
5159 (modify-phases %standard-phases
5160 ;; no configure script
5162 (add-before 'build 'use-system-samtools
5164 (substitute* "Makefile"
5165 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5167 (substitute* '("gclib/GBam.h"
5169 (("#include \"(bam|sam|kstring).h\"" _ header)
5170 (string-append "#include <samtools/" header ".h>")))
5173 (lambda* (#:key outputs #:allow-other-keys)
5174 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5175 (install-file "stringtie" bin)
5178 `(("samtools" ,samtools-0.1)
5180 (home-page "http://ccb.jhu.edu/software/stringtie/")
5181 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5183 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5184 alignments into potential transcripts. It uses a novel network flow algorithm
5185 as well as an optional de novo assembly step to assemble and quantitate
5186 full-length transcripts representing multiple splice variants for each gene
5187 locus. Its input can include not only the alignments of raw reads used by
5188 other transcript assemblers, but also alignments of longer sequences that have
5189 been assembled from those reads. To identify differentially expressed genes
5190 between experiments, StringTie's output can be processed either by the
5191 Cuffdiff or Ballgown programs.")
5192 (license license:artistic2.0)))
5194 (define-public vcftools
5201 "https://github.com/vcftools/vcftools/releases/download/v"
5202 version "/vcftools-" version ".tar.gz"))
5205 "10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
5206 (build-system gnu-build-system)
5208 `(#:tests? #f ; no "check" target
5210 "CFLAGS=-O2" ; override "-m64" flag
5211 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5212 (string-append "MANDIR=" (assoc-ref %outputs "out")
5213 "/share/man/man1"))))
5215 `(("pkg-config" ,pkg-config)))
5219 (home-page "https://vcftools.github.io/")
5220 (synopsis "Tools for working with VCF files")
5222 "VCFtools is a program package designed for working with VCF files, such
5223 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5224 provide easily accessible methods for working with complex genetic variation
5225 data in the form of VCF files.")
5226 ;; The license is declared as LGPLv3 in the README and
5227 ;; at https://vcftools.github.io/license.html
5228 (license license:lgpl3)))
5230 (define-public infernal
5236 (uri (string-append "http://eddylab.org/software/infernal/"
5237 "infernal-" version ".tar.gz"))
5240 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5241 (build-system gnu-build-system)
5243 `(("perl" ,perl))) ; for tests
5244 (home-page "http://eddylab.org/infernal/")
5245 (synopsis "Inference of RNA alignments")
5246 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5247 searching DNA sequence databases for RNA structure and sequence similarities.
5248 It is an implementation of a special case of profile stochastic context-free
5249 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5250 profile, but it scores a combination of sequence consensus and RNA secondary
5251 structure consensus, so in many cases, it is more capable of identifying RNA
5252 homologs that conserve their secondary structure more than their primary
5254 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5255 (supported-systems '("i686-linux" "x86_64-linux"))
5256 (license license:bsd-3)))
5258 (define-public r-centipede
5260 (name "r-centipede")
5264 (uri (string-append "http://download.r-forge.r-project.org/"
5265 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5268 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5269 (build-system r-build-system)
5270 (home-page "http://centipede.uchicago.edu/")
5271 (synopsis "Predict transcription factor binding sites")
5273 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5274 of the genome that are bound by particular transcription factors. It starts
5275 by identifying a set of candidate binding sites, and then aims to classify the
5276 sites according to whether each site is bound or not bound by a transcription
5277 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5278 between two different types of motif instances using as much relevant
5279 information as possible.")
5280 (license (list license:gpl2+ license:gpl3+))))
5282 (define-public r-vegan
5289 (uri (cran-uri "vegan" version))
5292 "12wf64izrpq9z3ix7mgm5421mq0xsm8dw5qblvcrz452nfhjf5w9"))))
5293 (build-system r-build-system)
5296 (modify-phases %standard-phases
5297 (add-after 'unpack 'revert-test-deletion
5298 ;; The distributed sources do not include tests with the CRAN
5299 ;; package. Here we revert the commit
5300 ;; `591d0e8ba1deaaf82445474ec6619c0b43db4e63' which deletes these
5301 ;; tests. There are plans to not delete tests in future as
5302 ;; documented at https://github.com/vegandevs/vegan/issues/181.
5303 (lambda* (#:key inputs #:allow-other-keys)
5305 (system* "patch" "-R" "-p1" "-i"
5306 (assoc-ref inputs "r-vegan-delete-tests-patch"))))))))
5308 `(("gfortran" ,gfortran)
5309 ("r-knitr" ,r-knitr)
5310 ("r-vegan-delete-tests-patch"
5314 "https://github.com/vegandevs/vegan/commit/"
5315 "591d0e8ba1deaaf82445474ec6619c0b43db4e63.patch"))
5318 "0b1bi7y4jjdl3ph721vm9apm51dr2z9piwvhy4355sf2b4kyyj5a"))))))
5320 `(("r-cluster" ,r-cluster)
5321 ("r-lattice" ,r-lattice)
5323 ("r-permute" ,r-permute)))
5324 (home-page "https://cran.r-project.org/web/packages/vegan")
5325 (synopsis "Functions for community ecology")
5327 "The vegan package provides tools for descriptive community ecology. It
5328 has most basic functions of diversity analysis, community ordination and
5329 dissimilarity analysis. Most of its multivariate tools can be used for other
5330 data types as well.")
5331 (license license:gpl2+)))
5333 (define-public r-annotate
5340 (uri (bioconductor-uri "annotate" version))
5343 "0yymz8qxgnbybvfhqrgkd1hh9dhwxdii1yxkhr1zicjgb35xixxb"))))
5344 (build-system r-build-system)
5346 `(("r-annotationdbi" ,r-annotationdbi)
5347 ("r-biobase" ,r-biobase)
5348 ("r-biocgenerics" ,r-biocgenerics)
5350 ("r-rcurl" ,r-rcurl)
5352 ("r-xtable" ,r-xtable)))
5354 "http://bioconductor.org/packages/annotate")
5355 (synopsis "Annotation for microarrays")
5356 (description "This package provides R enviroments for the annotation of
5358 (license license:artistic2.0)))
5360 (define-public r-geneplotter
5362 (name "r-geneplotter")
5367 (uri (bioconductor-uri "geneplotter" version))
5370 "1p6yvxi243irhjxwm97hp73abhwampj0myyf8z00ij166674pc7h"))))
5371 (build-system r-build-system)
5373 `(("r-annotate" ,r-annotate)
5374 ("r-annotationdbi" ,r-annotationdbi)
5375 ("r-biobase" ,r-biobase)
5376 ("r-biocgenerics" ,r-biocgenerics)
5377 ("r-lattice" ,r-lattice)
5378 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5379 (home-page "http://bioconductor.org/packages/geneplotter")
5380 (synopsis "Graphics functions for genomic data")
5382 "This package provides functions for plotting genomic data.")
5383 (license license:artistic2.0)))
5385 (define-public r-genefilter
5387 (name "r-genefilter")
5392 (uri (bioconductor-uri "genefilter" version))
5395 "1vzgciqd09csqcw9qync8blsv51ylrd86a65iadgyy6j26g01fwd"))))
5396 (build-system r-build-system)
5398 `(("gfortran" ,gfortran)))
5400 `(("r-annotate" ,r-annotate)
5401 ("r-annotationdbi" ,r-annotationdbi)
5402 ("r-biobase" ,r-biobase)
5403 ("r-s4vectors" ,r-s4vectors)))
5404 (home-page "http://bioconductor.org/packages/genefilter")
5405 (synopsis "Filter genes from high-throughput experiments")
5407 "This package provides basic functions for filtering genes from
5408 high-throughput sequencing experiments.")
5409 (license license:artistic2.0)))
5411 (define-public r-deseq2
5418 (uri (bioconductor-uri "DESeq2" version))
5421 "1walwkqryn1gnwz7zryr5764a0p6ia7ag4w6w9n8fskg8dkg0fqs"))))
5422 (properties `((upstream-name . "DESeq2")))
5423 (build-system r-build-system)
5426 (modify-phases %standard-phases
5427 (add-after 'unpack 'link-against-armadillo
5429 (substitute* "src/Makevars"
5430 (("PKG_LIBS =" prefix)
5431 (string-append prefix "-larmadillo"))))))))
5433 `(("r-biobase" ,r-biobase)
5434 ("r-biocgenerics" ,r-biocgenerics)
5435 ("r-biocparallel" ,r-biocparallel)
5436 ("r-genefilter" ,r-genefilter)
5437 ("r-geneplotter" ,r-geneplotter)
5438 ("r-genomicranges" ,r-genomicranges)
5439 ("r-ggplot2" ,r-ggplot2)
5440 ("r-hmisc" ,r-hmisc)
5441 ("r-iranges" ,r-iranges)
5442 ("r-locfit" ,r-locfit)
5444 ("r-rcpparmadillo" ,r-rcpparmadillo)
5445 ("r-s4vectors" ,r-s4vectors)
5446 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5447 (home-page "http://bioconductor.org/packages/DESeq2")
5448 (synopsis "Differential gene expression analysis")
5450 "This package provides functions to estimate variance-mean dependence in
5451 count data from high-throughput nucleotide sequencing assays and test for
5452 differential expression based on a model using the negative binomial
5454 (license license:lgpl3+)))
5456 (define-public r-annotationforge
5458 (name "r-annotationforge")
5463 (uri (bioconductor-uri "AnnotationForge" version))
5466 "02msyb9p3hywrryx00zpjkjl126mrv827i1ah1092s0cplm6xxvf"))))
5468 `((upstream-name . "AnnotationForge")))
5469 (build-system r-build-system)
5471 `(("r-annotationdbi" ,r-annotationdbi)
5472 ("r-biobase" ,r-biobase)
5473 ("r-biocgenerics" ,r-biocgenerics)
5475 ("r-rcurl" ,r-rcurl)
5476 ("r-rsqlite" ,r-rsqlite)
5477 ("r-s4vectors" ,r-s4vectors)
5479 (home-page "http://bioconductor.org/packages/AnnotationForge")
5480 (synopsis "Code for building annotation database packages")
5482 "This package provides code for generating Annotation packages and their
5483 databases. Packages produced are intended to be used with AnnotationDbi.")
5484 (license license:artistic2.0)))
5486 (define-public r-rbgl
5493 (uri (bioconductor-uri "RBGL" version))
5496 "1q14m8w6ih56v680kf3d9wh1qbgp7af33kz3cxafdf1vvzx9km08"))))
5497 (properties `((upstream-name . "RBGL")))
5498 (build-system r-build-system)
5499 (propagated-inputs `(("r-graph" ,r-graph)))
5500 (home-page "http://www.bioconductor.org/packages/RBGL")
5501 (synopsis "Interface to the Boost graph library")
5503 "This package provides a fairly extensive and comprehensive interface to
5504 the graph algorithms contained in the Boost library.")
5505 (license license:artistic2.0)))
5507 (define-public r-gseabase
5514 (uri (bioconductor-uri "GSEABase" version))
5517 "0l2x7yj7lfb0m2dmsav5ib026dikpgl4crdckrnj776yy08lgxpj"))))
5518 (properties `((upstream-name . "GSEABase")))
5519 (build-system r-build-system)
5521 `(("r-annotate" ,r-annotate)
5522 ("r-annotationdbi" ,r-annotationdbi)
5523 ("r-biobase" ,r-biobase)
5524 ("r-biocgenerics" ,r-biocgenerics)
5525 ("r-graph" ,r-graph)
5527 (home-page "http://bioconductor.org/packages/GSEABase")
5528 (synopsis "Gene set enrichment data structures and methods")
5530 "This package provides classes and methods to support @dfn{Gene Set
5531 Enrichment Analysis} (GSEA).")
5532 (license license:artistic2.0)))
5534 (define-public r-category
5541 (uri (bioconductor-uri "Category" version))
5544 "16ncwz7b4y48k0p3fvbrbmvf7nfz63li9ysgcl8kp9kl4hg7llng"))))
5545 (properties `((upstream-name . "Category")))
5546 (build-system r-build-system)
5548 `(("r-annotate" ,r-annotate)
5549 ("r-annotationdbi" ,r-annotationdbi)
5550 ("r-biobase" ,r-biobase)
5551 ("r-biocgenerics" ,r-biocgenerics)
5552 ("r-genefilter" ,r-genefilter)
5553 ("r-graph" ,r-graph)
5554 ("r-gseabase" ,r-gseabase)
5555 ("r-matrix" ,r-matrix)
5557 ("r-rsqlite" ,r-rsqlite)))
5558 (home-page "http://bioconductor.org/packages/Category")
5559 (synopsis "Category analysis")
5561 "This package provides a collection of tools for performing category
5563 (license license:artistic2.0)))
5565 (define-public r-gostats
5572 (uri (bioconductor-uri "GOstats" version))
5575 "0g2czm94zhzx92z7y2r4mjfxhwml7bhab2db6820ks8nkw1zvr9n"))))
5576 (properties `((upstream-name . "GOstats")))
5577 (build-system r-build-system)
5579 `(("r-annotate" ,r-annotate)
5580 ("r-annotationdbi" ,r-annotationdbi)
5581 ("r-annotationforge" ,r-annotationforge)
5582 ("r-biobase" ,r-biobase)
5583 ("r-category" ,r-category)
5584 ("r-go-db" ,r-go-db)
5585 ("r-graph" ,r-graph)
5586 ("r-rbgl" ,r-rbgl)))
5587 (home-page "http://bioconductor.org/packages/GOstats")
5588 (synopsis "Tools for manipulating GO and microarrays")
5590 "This package provides a set of tools for interacting with GO and
5591 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5592 testing and other simple calculations.")
5593 (license license:artistic2.0)))
5595 (define-public r-shortread
5597 (name "r-shortread")
5602 (uri (bioconductor-uri "ShortRead" version))
5605 "0mjdlg92x5qw4x2djc4dv5lxwl7ai6ix56nnf86zr07jk8vc7yls"))))
5606 (properties `((upstream-name . "ShortRead")))
5607 (build-system r-build-system)
5611 `(("r-biobase" ,r-biobase)
5612 ("r-biocgenerics" ,r-biocgenerics)
5613 ("r-biocparallel" ,r-biocparallel)
5614 ("r-biostrings" ,r-biostrings)
5615 ("r-genomeinfodb" ,r-genomeinfodb)
5616 ("r-genomicalignments" ,r-genomicalignments)
5617 ("r-genomicranges" ,r-genomicranges)
5618 ("r-hwriter" ,r-hwriter)
5619 ("r-iranges" ,r-iranges)
5620 ("r-lattice" ,r-lattice)
5621 ("r-latticeextra" ,r-latticeextra)
5622 ("r-rsamtools" ,r-rsamtools)
5623 ("r-s4vectors" ,r-s4vectors)
5624 ("r-xvector" ,r-xvector)
5625 ("r-zlibbioc" ,r-zlibbioc)))
5626 (home-page "http://bioconductor.org/packages/ShortRead")
5627 (synopsis "FASTQ input and manipulation tools")
5629 "This package implements sampling, iteration, and input of FASTQ files.
5630 It includes functions for filtering and trimming reads, and for generating a
5631 quality assessment report. Data are represented as
5632 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5633 purposes. The package also contains legacy support for early single-end,
5634 ungapped alignment formats.")
5635 (license license:artistic2.0)))
5637 (define-public r-systempiper
5639 (name "r-systempiper")
5644 (uri (bioconductor-uri "systemPipeR" version))
5647 "0hyi841w8fm2yzpm6lwqi3jz5kc8ny8dy5p29dxynzaw5bpjw56d"))))
5648 (properties `((upstream-name . "systemPipeR")))
5649 (build-system r-build-system)
5651 `(("r-annotate" ,r-annotate)
5652 ("r-batchjobs" ,r-batchjobs)
5653 ("r-biocgenerics" ,r-biocgenerics)
5654 ("r-biostrings" ,r-biostrings)
5655 ("r-deseq2" ,r-deseq2)
5656 ("r-edger" ,r-edger)
5657 ("r-genomicfeatures" ,r-genomicfeatures)
5658 ("r-genomicranges" ,r-genomicranges)
5659 ("r-ggplot2" ,r-ggplot2)
5660 ("r-go-db" ,r-go-db)
5661 ("r-gostats" ,r-gostats)
5662 ("r-limma" ,r-limma)
5663 ("r-pheatmap" ,r-pheatmap)
5664 ("r-rjson" ,r-rjson)
5665 ("r-rsamtools" ,r-rsamtools)
5666 ("r-shortread" ,r-shortread)
5667 ("r-summarizedexperiment" ,r-summarizedexperiment)
5668 ("r-variantannotation" ,r-variantannotation)))
5669 (home-page "https://github.com/tgirke/systemPipeR")
5670 (synopsis "Next generation sequencing workflow and reporting environment")
5672 "This R package provides tools for building and running automated
5673 end-to-end analysis workflows for a wide range of @dfn{next generation
5674 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5675 Important features include a uniform workflow interface across different NGS
5676 applications, automated report generation, and support for running both R and
5677 command-line software, such as NGS aligners or peak/variant callers, on local
5678 computers or compute clusters. Efficient handling of complex sample sets and
5679 experimental designs is facilitated by a consistently implemented sample
5680 annotation infrastructure.")
5681 (license license:artistic2.0)))
5683 (define-public r-grohmm
5690 (uri (bioconductor-uri "groHMM" version))
5693 "0d91nyhqbi5hv3mgmr2z0g29wg2md26g0hyv5mgapmz20cd9zi4y"))))
5694 (properties `((upstream-name . "groHMM")))
5695 (build-system r-build-system)
5697 `(("r-genomeinfodb" ,r-genomeinfodb)
5698 ("r-genomicalignments" ,r-genomicalignments)
5699 ("r-genomicranges" ,r-genomicranges)
5700 ("r-iranges" ,r-iranges)
5701 ("r-rtracklayer" ,r-rtracklayer)
5702 ("r-s4vectors" ,r-s4vectors)))
5703 (home-page "https://github.com/Kraus-Lab/groHMM")
5704 (synopsis "GRO-seq analysis pipeline")
5706 "This package provides a pipeline for the analysis of GRO-seq data.")
5707 (license license:gpl3+)))
5709 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
5711 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
5715 ;; We cannot use bioconductor-uri here because this tarball is
5716 ;; located under "data/annotation/" instead of "bioc/".
5717 (uri (string-append "http://bioconductor.org/packages/"
5718 "release/data/annotation/src/contrib"
5719 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
5723 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
5725 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
5726 (build-system r-build-system)
5727 ;; As this package provides little more than a very large data file it
5728 ;; doesn't make sense to build substitutes.
5729 (arguments `(#:substitutable? #f))
5731 `(("r-genomicfeatures" ,r-genomicfeatures)))
5733 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
5734 (synopsis "Annotation package for human genome in TxDb format")
5736 "This package provides an annotation database of Homo sapiens genome
5737 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
5738 track. The database is exposed as a @code{TxDb} object.")
5739 (license license:artistic2.0)))
5741 (define-public vsearch
5749 "https://github.com/torognes/vsearch/archive/v"
5751 (file-name (string-append name "-" version ".tar.gz"))
5754 "007q9a50hdw4vs2iajabvbw7qccml4r8cbqzyi5ipkkf42jk3vnr"))
5755 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
5758 ;; Remove bundled cityhash sources. The vsearch source is adjusted
5759 ;; for this in the patch.
5760 (delete-file "src/city.h")
5761 (delete-file "src/citycrc.h")
5762 (delete-file "src/city.cc")
5764 (build-system gnu-build-system)
5767 (modify-phases %standard-phases
5768 (add-before 'configure 'autogen
5769 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
5773 ("cityhash" ,cityhash)))
5775 `(("autoconf" ,autoconf)
5776 ("automake" ,automake)))
5777 (synopsis "Sequence search tools for metagenomics")
5779 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
5780 dereplication, pairwise alignment, shuffling, subsampling, sorting and
5781 masking. The tool takes advantage of parallelism in the form of SIMD
5782 vectorization as well as multiple threads to perform accurate alignments at
5783 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
5784 Needleman-Wunsch).")
5785 (home-page "https://github.com/torognes/vsearch")
5786 ;; vsearch uses non-portable SSE intrinsics so building fails on other
5788 (supported-systems '("x86_64-linux"))
5789 ;; Dual licensed; also includes public domain source.
5790 (license (list license:gpl3 license:bsd-2))))
5792 (define-public pardre
5795 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
5800 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
5804 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
5805 (build-system gnu-build-system)
5807 `(#:tests? #f ; no tests included
5809 (modify-phases %standard-phases
5812 (lambda* (#:key outputs #:allow-other-keys)
5813 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
5814 (install-file "ParDRe" bin)
5817 `(("openmpi" ,openmpi)
5819 (synopsis "Parallel tool to remove duplicate DNA reads")
5821 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
5822 Duplicate reads can be seen as identical or nearly identical sequences with
5823 some mismatches. This tool lets users avoid the analysis of unnecessary
5824 reads, reducing the time of subsequent procedures with the
5825 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
5826 in order to exploit the parallel capabilities of multicore clusters. It is
5827 faster than multithreaded counterparts (end of 2015) for the same number of
5828 cores and, thanks to the message-passing technology, it can be executed on
5830 (home-page "https://sourceforge.net/projects/pardre/")
5831 (license license:gpl3+)))
5833 (define-public ruby-bio-kseq
5835 (name "ruby-bio-kseq")
5840 (uri (rubygems-uri "bio-kseq" version))
5843 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
5844 (build-system ruby-build-system)
5846 `(#:test-target "spec"))
5848 `(("bundler" ,bundler)
5849 ("ruby-rspec" ,ruby-rspec)
5850 ("ruby-rake-compiler" ,ruby-rake-compiler)))
5853 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
5855 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
5856 FASTQ parsing code. It provides a fast iterator over sequences and their
5858 (home-page "https://github.com/gusevfe/bio-kseq")
5859 (license license:expat)))
5861 (define-public bio-locus
5868 (uri (rubygems-uri "bio-locus" version))
5871 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
5872 (build-system ruby-build-system)
5874 `(("ruby-rspec" ,ruby-rspec)))
5875 (synopsis "Tool for fast querying of genome locations")
5877 "Bio-locus is a tabix-like tool for fast querying of genome
5878 locations. Many file formats in bioinformatics contain records that
5879 start with a chromosome name and a position for a SNP, or a start-end
5880 position for indels. Bio-locus allows users to store this chr+pos or
5881 chr+pos+alt information in a database.")
5882 (home-page "https://github.com/pjotrp/bio-locus")
5883 (license license:expat)))
5885 (define-public bio-blastxmlparser
5887 (name "bio-blastxmlparser")
5891 (uri (rubygems-uri "bio-blastxmlparser" version))
5894 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
5895 (build-system ruby-build-system)
5897 `(("ruby-bio-logger" ,ruby-bio-logger)
5898 ("ruby-nokogiri" ,ruby-nokogiri)))
5900 `(("ruby-rspec" ,ruby-rspec)))
5901 (synopsis "Fast big data BLAST XML parser and library")
5903 "Very fast parallel big-data BLAST XML file parser which can be used as
5904 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
5905 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
5906 (home-page "http://github.com/pjotrp/blastxmlparser")
5907 (license license:expat)))
5909 (define-public bioruby
5916 (uri (rubygems-uri "bio" version))
5919 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
5920 (build-system ruby-build-system)
5922 `(("ruby-libxml" ,ruby-libxml)))
5924 `(("which" ,which))) ; required for test phase
5927 (modify-phases %standard-phases
5928 (add-before 'build 'patch-test-command
5930 (substitute* '("test/functional/bio/test_command.rb")
5931 (("/bin/sh") (which "sh")))
5932 (substitute* '("test/functional/bio/test_command.rb")
5933 (("/bin/ls") (which "ls")))
5934 (substitute* '("test/functional/bio/test_command.rb")
5935 (("which") (which "which")))
5936 (substitute* '("test/functional/bio/test_command.rb",
5937 "test/data/command/echoarg2.sh")
5938 (("/bin/echo") (which "echo")))
5940 (synopsis "Ruby library, shell and utilities for bioinformatics")
5941 (description "BioRuby comes with a comprehensive set of Ruby development
5942 tools and libraries for bioinformatics and molecular biology. BioRuby has
5943 components for sequence analysis, pathway analysis, protein modelling and
5944 phylogenetic analysis; it supports many widely used data formats and provides
5945 easy access to databases, external programs and public web services, including
5946 BLAST, KEGG, GenBank, MEDLINE and GO.")
5947 (home-page "http://bioruby.org/")
5948 ;; Code is released under Ruby license, except for setup
5949 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
5950 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
5952 (define-public r-acsnminer
5954 (name "r-acsnminer")
5955 (version "0.16.8.25")
5958 (uri (cran-uri "ACSNMineR" version))
5961 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
5962 (properties `((upstream-name . "ACSNMineR")))
5963 (build-system r-build-system)
5965 `(("r-ggplot2" ,r-ggplot2)
5966 ("r-gridextra" ,r-gridextra)))
5967 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
5968 (synopsis "Gene enrichment analysis")
5970 "This package provides tools to compute and represent gene set enrichment
5971 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
5972 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
5973 enrichment can be run with hypergeometric test or Fisher exact test, and can
5974 use multiple corrections. Visualization of data can be done either by
5975 barplots or heatmaps.")
5976 (license license:gpl2+)))
5978 (define-public r-biocgenerics
5980 (name "r-biocgenerics")
5984 (uri (bioconductor-uri "BiocGenerics" version))
5987 "06szdz7dfs1iyv5zdl4fjzad18nnf1zf3wvglc6c6yd9mrqlf7vk"))))
5989 `((upstream-name . "BiocGenerics")))
5990 (build-system r-build-system)
5991 (home-page "http://bioconductor.org/packages/BiocGenerics")
5992 (synopsis "S4 generic functions for Bioconductor")
5994 "This package provides S4 generic functions needed by many Bioconductor
5996 (license license:artistic2.0)))
5998 (define-public r-biocinstaller
6000 (name "r-biocinstaller")
6004 (uri (bioconductor-uri "BiocInstaller" version))
6007 "0y1y5wmy6lzjqx3hdg15n91d417ccjj8dbvdkhmp99bs5aijwcpn"))))
6009 `((upstream-name . "BiocInstaller")))
6010 (build-system r-build-system)
6011 (home-page "http://bioconductor.org/packages/BiocInstaller")
6012 (synopsis "Install Bioconductor packages")
6013 (description "This package is used to install and update R packages from
6014 Bioconductor, CRAN, and Github.")
6015 (license license:artistic2.0)))
6017 (define-public r-biocviews
6019 (name "r-biocviews")
6023 (uri (bioconductor-uri "biocViews" version))
6026 "07rjk10b91pkriyq297w86199r2d3sfji3ggs9mq2gyalsa8y4b6"))))
6028 `((upstream-name . "biocViews")))
6029 (build-system r-build-system)
6031 `(("r-biobase" ,r-biobase)
6032 ("r-graph" ,r-graph)
6034 ("r-rcurl" ,r-rcurl)
6036 ("r-knitr" ,r-knitr)
6037 ("r-runit" ,r-runit)))
6038 (home-page "http://bioconductor.org/packages/biocViews")
6039 (synopsis "Bioconductor package categorization helper")
6040 (description "The purpose of biocViews is to create HTML pages that
6041 categorize packages in a Bioconductor package repository according to keywords,
6042 also known as views, in a controlled vocabulary.")
6043 (license license:artistic2.0)))
6045 (define-public r-biocstyle
6047 (name "r-biocstyle")
6051 (uri (bioconductor-uri "BiocStyle" version))
6054 "0sl99xw940ixrm6v24lgaw3ljh56g59a6rdz7g160hx84z9f8n2n"))))
6056 `((upstream-name . "BiocStyle")))
6057 (build-system r-build-system)
6058 (home-page "http://bioconductor.org/packages/BiocStyle")
6059 (synopsis "Bioconductor formatting styles")
6060 (description "This package provides standard formatting styles for
6061 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6063 (license license:artistic2.0)))
6065 (define-public r-bioccheck
6067 (name "r-bioccheck")
6071 (uri (bioconductor-uri "BiocCheck" version))
6074 "1rfy37xg1nc2cmgbclvzsi7sgmdcdjiahsx9crgx3yaw7kxgiack"))))
6076 `((upstream-name . "BiocCheck")))
6077 (build-system r-build-system)
6080 (modify-phases %standard-phases
6081 ;; This package can be used by calling BiocCheck(<package>) from
6082 ;; within R, or by running R CMD BiocCheck <package>. This phase
6083 ;; makes sure the latter works. For this to work, the BiocCheck
6084 ;; script must be somewhere on the PATH (not the R bin directory).
6085 (add-after 'install 'install-bioccheck-subcommand
6086 (lambda* (#:key outputs #:allow-other-keys)
6087 (let* ((out (assoc-ref outputs "out"))
6088 (dest-dir (string-append out "/bin"))
6090 (string-append out "/site-library/BiocCheck/script/")))
6092 (symlink (string-append script-dir "/checkBadDeps.R")
6093 (string-append dest-dir "/checkBadDeps.R"))
6094 (symlink (string-append script-dir "/BiocCheck")
6095 (string-append dest-dir "/BiocCheck")))
6098 `(("which" ,which)))
6100 `(("r-graph" ,r-graph)
6101 ("r-knitr" ,r-knitr)
6103 ("r-optparse" ,r-optparse)
6104 ("r-devtools" ,r-devtools)
6105 ("r-biocinstaller" ,r-biocinstaller)
6106 ("r-biocviews" ,r-biocviews)))
6107 (home-page "http://bioconductor.org/packages/BiocCheck")
6108 (synopsis "Executes Bioconductor-specific package checks")
6109 (description "This package contains tools to perform additional quality
6110 checks on R packages that are to be submitted to the Bioconductor repository.")
6111 (license license:artistic2.0)))
6113 (define-public r-getopt
6120 (uri (cran-uri "getopt" version))
6123 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6124 (build-system r-build-system)
6125 (home-page "https://github.com/trevorld/getopt")
6126 (synopsis "Command-line option processor for R")
6128 "This package is designed to be used with Rscript to write shebang
6129 scripts that accept short and long options. Many users will prefer to
6130 use the packages @code{optparse} or @code{argparse} which add extra
6131 features like automatically generated help options and usage texts,
6132 support for default values, positional argument support, etc.")
6133 (license license:gpl2+)))
6135 (define-public r-optparse
6142 (uri (cran-uri "optparse" version))
6145 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6146 (build-system r-build-system)
6148 `(("r-getopt" ,r-getopt)))
6150 "https://github.com/trevorld/optparse")
6151 (synopsis "Command line option parser")
6153 "This package provides a command line parser inspired by Python's
6154 @code{optparse} library to be used with Rscript to write shebang scripts
6155 that accept short and long options.")
6156 (license license:gpl2+)))
6158 (define-public r-dnacopy
6164 (uri (bioconductor-uri "DNAcopy" version))
6167 "1idyvfvy7xx8k9vk00y4k3819qmip8iqm809j3vpxabmsn7r9zyh"))))
6169 `((upstream-name . "DNAcopy")))
6170 (build-system r-build-system)
6172 `(("gfortran" ,gfortran)))
6173 (home-page "https://bioconductor.org/packages/DNAcopy")
6174 (synopsis "Implementation of a circular binary segmentation algorithm")
6175 (description "This package implements the circular binary segmentation (CBS)
6176 algorithm to segment DNA copy number data and identify genomic regions with
6177 abnormal copy number.")
6178 (license license:gpl2+)))
6180 (define-public r-s4vectors
6182 (name "r-s4vectors")
6186 (uri (bioconductor-uri "S4Vectors" version))
6189 "0i36y3w36h3d8rmazxcrip4gvn54rd9av1wz4lygsprrjmylfhcc"))))
6191 `((upstream-name . "S4Vectors")))
6192 (build-system r-build-system)
6194 `(("r-biocgenerics" ,r-biocgenerics)))
6195 (home-page "http://bioconductor.org/packages/S4Vectors")
6196 (synopsis "S4 implementation of vectors and lists")
6198 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6199 classes and a set of generic functions that extend the semantic of ordinary
6200 vectors and lists in R. Package developers can easily implement vector-like
6201 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6202 In addition, a few low-level concrete subclasses of general interest (e.g.
6203 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6204 S4Vectors package itself.")
6205 (license license:artistic2.0)))
6207 (define-public r-seqinr
6214 (uri (cran-uri "seqinr" version))
6217 "0rk4yba8km26c0rh1f4h474zsb5n6kjmqsi55bnzr6p8pymp18hj"))))
6218 (build-system r-build-system)
6220 `(("r-ade4" ,r-ade4)
6221 ("r-segmented" ,r-segmented)))
6224 (home-page "http://seqinr.r-forge.r-project.org/")
6225 (synopsis "Biological sequences retrieval and analysis")
6227 "This package provides tools for exploratory data analysis and data
6228 visualization of biological sequence (DNA and protein) data. It also includes
6229 utilities for sequence data management under the ACNUC system.")
6230 (license license:gpl2+)))
6232 (define-public r-iranges
6238 (uri (bioconductor-uri "IRanges" version))
6241 "0cryqnpqb3p6l9jjw27hyqd550sxlljls3ka7b9rb38hkji7b5hw"))))
6243 `((upstream-name . "IRanges")))
6244 (build-system r-build-system)
6246 `(("r-biocgenerics" ,r-biocgenerics)
6247 ("r-s4vectors" ,r-s4vectors)))
6248 (home-page "http://bioconductor.org/packages/IRanges")
6249 (synopsis "Infrastructure for manipulating intervals on sequences")
6251 "This package provides efficient low-level and highly reusable S4 classes
6252 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6253 generally, data that can be organized sequentially (formally defined as
6254 @code{Vector} objects), as well as views on these @code{Vector} objects.
6255 Efficient list-like classes are also provided for storing big collections of
6256 instances of the basic classes. All classes in the package use consistent
6257 naming and share the same rich and consistent \"Vector API\" as much as
6259 (license license:artistic2.0)))
6261 (define-public r-genomeinfodb
6263 (name "r-genomeinfodb")
6267 (uri (bioconductor-uri "GenomeInfoDb" version))
6270 "0zh894qd1sgpjbn0wfvq6hs2dzn7y1pyicvzk2aa48y3zbidanv7"))))
6272 `((upstream-name . "GenomeInfoDb")))
6273 (build-system r-build-system)
6275 `(("r-biocgenerics" ,r-biocgenerics)
6276 ("r-iranges" ,r-iranges)
6277 ("r-s4vectors" ,r-s4vectors)))
6278 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6279 (synopsis "Utilities for manipulating chromosome identifiers")
6281 "This package contains data and functions that define and allow
6282 translation between different chromosome sequence naming conventions (e.g.,
6283 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6284 names in their natural, rather than lexicographic, order.")
6285 (license license:artistic2.0)))
6287 (define-public r-edger
6293 (uri (bioconductor-uri "edgeR" version))
6296 "04vpa0a6dkkjyvvfbkmfjyaxf2ldkagi66g028qpaszd8jsk8yiv"))))
6297 (properties `((upstream-name . "edgeR")))
6298 (build-system r-build-system)
6300 `(("r-limma" ,r-limma)
6301 ("r-locfit" ,r-locfit)
6302 ("r-statmod" ,r-statmod))) ;for estimateDisp
6303 (home-page "http://bioinf.wehi.edu.au/edgeR")
6304 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6305 (description "This package can do differential expression analysis of
6306 RNA-seq expression profiles with biological replication. It implements a range
6307 of statistical methodology based on the negative binomial distributions,
6308 including empirical Bayes estimation, exact tests, generalized linear models
6309 and quasi-likelihood tests. It be applied to differential signal analysis of
6310 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6312 (license license:gpl2+)))
6314 (define-public r-variantannotation
6316 (name "r-variantannotation")
6320 (uri (bioconductor-uri "VariantAnnotation" version))
6323 "165wda1d2jagd907pnra4m3sla66icyqxvd60xpv09jl5agd5mn9"))))
6325 `((upstream-name . "VariantAnnotation")))
6329 `(("r-annotationdbi" ,r-annotationdbi)
6330 ("r-biobase" ,r-biobase)
6331 ("r-biocgenerics" ,r-biocgenerics)
6332 ("r-biostrings" ,r-biostrings)
6333 ("r-bsgenome" ,r-bsgenome)
6335 ("r-genomeinfodb" ,r-genomeinfodb)
6336 ("r-genomicfeatures" ,r-genomicfeatures)
6337 ("r-genomicranges" ,r-genomicranges)
6338 ("r-iranges" ,r-iranges)
6339 ("r-summarizedexperiment" ,r-summarizedexperiment)
6340 ("r-rsamtools" ,r-rsamtools)
6341 ("r-rtracklayer" ,r-rtracklayer)
6342 ("r-s4vectors" ,r-s4vectors)
6343 ("r-xvector" ,r-xvector)
6344 ("r-zlibbioc" ,r-zlibbioc)))
6345 (build-system r-build-system)
6346 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6347 (synopsis "Package for annotation of genetic variants")
6348 (description "This R package can annotate variants, compute amino acid
6349 coding changes and predict coding outcomes.")
6350 (license license:artistic2.0)))
6352 (define-public r-limma
6358 (uri (bioconductor-uri "limma" version))
6361 "1xg9w4lmn9n4hwyflxiwi6g969lcy569cg4z1x47crwwg7z7qdka"))))
6362 (build-system r-build-system)
6363 (home-page "http://bioinf.wehi.edu.au/limma")
6364 (synopsis "Package for linear models for microarray and RNA-seq data")
6365 (description "This package can be used for the analysis of gene expression
6366 studies, especially the use of linear models for analysing designed experiments
6367 and the assessment of differential expression. The analysis methods apply to
6368 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6369 (license license:gpl2+)))
6371 (define-public r-xvector
6377 (uri (bioconductor-uri "XVector" version))
6380 "09lbqxpqr80g0kw77mpz0p1a8cq706j33kz8194wp71il67cdzi7"))))
6382 `((upstream-name . "XVector")))
6383 (build-system r-build-system)
6386 (modify-phases %standard-phases
6387 (add-after 'unpack 'use-system-zlib
6389 (substitute* "DESCRIPTION"
6390 (("zlibbioc, ") ""))
6391 (substitute* "NAMESPACE"
6392 (("import\\(zlibbioc\\)") ""))
6397 `(("r-biocgenerics" ,r-biocgenerics)
6398 ("r-iranges" ,r-iranges)
6399 ("r-s4vectors" ,r-s4vectors)))
6400 (home-page "http://bioconductor.org/packages/XVector")
6401 (synopsis "Representation and manpulation of external sequences")
6403 "This package provides memory efficient S4 classes for storing sequences
6404 \"externally\" (behind an R external pointer, or on disk).")
6405 (license license:artistic2.0)))
6407 (define-public r-genomicranges
6409 (name "r-genomicranges")
6413 (uri (bioconductor-uri "GenomicRanges" version))
6416 "0if5dswkp77lyqppd0z2iyvnwag9h1gsr03707s8npcx13mzpsia"))))
6418 `((upstream-name . "GenomicRanges")))
6419 (build-system r-build-system)
6421 `(("r-biocgenerics" ,r-biocgenerics)
6422 ("r-genomeinfodb" ,r-genomeinfodb)
6423 ("r-iranges" ,r-iranges)
6424 ("r-s4vectors" ,r-s4vectors)
6425 ("r-xvector" ,r-xvector)))
6426 (home-page "http://bioconductor.org/packages/GenomicRanges")
6427 (synopsis "Representation and manipulation of genomic intervals")
6429 "This package provides tools to efficiently represent and manipulate
6430 genomic annotations and alignments is playing a central role when it comes to
6431 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6432 GenomicRanges package defines general purpose containers for storing and
6433 manipulating genomic intervals and variables defined along a genome.")
6434 (license license:artistic2.0)))
6436 (define-public r-biobase
6442 (uri (bioconductor-uri "Biobase" version))
6445 "0js9j9wqls8f571ifl9ylllbb9a9hwf7b7drf2grwb1fl31ldazl"))))
6447 `((upstream-name . "Biobase")))
6448 (build-system r-build-system)
6450 `(("r-biocgenerics" ,r-biocgenerics)))
6451 (home-page "http://bioconductor.org/packages/Biobase")
6452 (synopsis "Base functions for Bioconductor")
6454 "This package provides functions that are needed by many other packages
6455 on Bioconductor or which replace R functions.")
6456 (license license:artistic2.0)))
6458 (define-public r-annotationdbi
6460 (name "r-annotationdbi")
6464 (uri (bioconductor-uri "AnnotationDbi" version))
6467 "0ydrqw1k1j5p6w76bwc753cx545c055x88q87wzya93858synj6r"))))
6469 `((upstream-name . "AnnotationDbi")))
6470 (build-system r-build-system)
6472 `(("r-biobase" ,r-biobase)
6473 ("r-biocgenerics" ,r-biocgenerics)
6475 ("r-iranges" ,r-iranges)
6476 ("r-rsqlite" ,r-rsqlite)
6477 ("r-s4vectors" ,r-s4vectors)))
6478 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6479 (synopsis "Annotation database interface")
6481 "This package provides user interface and database connection code for
6482 annotation data packages using SQLite data storage.")
6483 (license license:artistic2.0)))
6485 (define-public r-biomart
6491 (uri (bioconductor-uri "biomaRt" version))
6494 "1x0flcghq71784q2l02j0g4f9jkmyb14f6i307n6c59d6ji7h7x6"))))
6496 `((upstream-name . "biomaRt")))
6497 (build-system r-build-system)
6499 `(("r-annotationdbi" ,r-annotationdbi)
6500 ("r-rcurl" ,r-rcurl)
6502 (home-page "http://bioconductor.org/packages/biomaRt")
6503 (synopsis "Interface to BioMart databases")
6505 "biomaRt provides an interface to a growing collection of databases
6506 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6507 package enables retrieval of large amounts of data in a uniform way without
6508 the need to know the underlying database schemas or write complex SQL queries.
6509 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6510 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6511 users direct access to a diverse set of data and enable a wide range of
6512 powerful online queries from gene annotation to database mining.")
6513 (license license:artistic2.0)))
6515 (define-public r-biocparallel
6517 (name "r-biocparallel")
6521 (uri (bioconductor-uri "BiocParallel" version))
6524 "123i928rwi4h4sy4fpysv6pinw5nns0sm3myxi2ghqhm34ws8gyl"))))
6526 `((upstream-name . "BiocParallel")))
6527 (build-system r-build-system)
6529 `(("r-futile-logger" ,r-futile-logger)
6530 ("r-snow" ,r-snow)))
6531 (home-page "http://bioconductor.org/packages/BiocParallel")
6532 (synopsis "Bioconductor facilities for parallel evaluation")
6534 "This package provides modified versions and novel implementation of
6535 functions for parallel evaluation, tailored to use with Bioconductor
6537 (license (list license:gpl2+ license:gpl3+))))
6539 (define-public r-biostrings
6541 (name "r-biostrings")
6545 (uri (bioconductor-uri "Biostrings" version))
6548 "0vqgd9i6y3wj4zviqwgvwgd4qj6033fg01rmx1cw9bw5i8ans42d"))))
6550 `((upstream-name . "Biostrings")))
6551 (build-system r-build-system)
6553 `(("r-biocgenerics" ,r-biocgenerics)
6554 ("r-iranges" ,r-iranges)
6555 ("r-s4vectors" ,r-s4vectors)
6556 ("r-xvector" ,r-xvector)))
6557 (home-page "http://bioconductor.org/packages/Biostrings")
6558 (synopsis "String objects and algorithms for biological sequences")
6560 "This package provides memory efficient string containers, string
6561 matching algorithms, and other utilities, for fast manipulation of large
6562 biological sequences or sets of sequences.")
6563 (license license:artistic2.0)))
6565 (define-public r-rsamtools
6567 (name "r-rsamtools")
6571 (uri (bioconductor-uri "Rsamtools" version))
6574 "0pf4f6brf4bl5zgjrah0f38qslazrs49ayqgyh0xfqgrh63yx4ck"))))
6576 `((upstream-name . "Rsamtools")))
6577 (build-system r-build-system)
6580 (modify-phases %standard-phases
6581 (add-after 'unpack 'use-system-zlib
6583 (substitute* "DESCRIPTION"
6584 (("zlibbioc, ") ""))
6585 (substitute* "NAMESPACE"
6586 (("import\\(zlibbioc\\)") ""))
6591 `(("r-biocgenerics" ,r-biocgenerics)
6592 ("r-biocparallel" ,r-biocparallel)
6593 ("r-biostrings" ,r-biostrings)
6594 ("r-bitops" ,r-bitops)
6595 ("r-genomeinfodb" ,r-genomeinfodb)
6596 ("r-genomicranges" ,r-genomicranges)
6597 ("r-iranges" ,r-iranges)
6598 ("r-s4vectors" ,r-s4vectors)
6599 ("r-xvector" ,r-xvector)))
6600 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6601 (synopsis "Interface to samtools, bcftools, and tabix")
6603 "This package provides an interface to the 'samtools', 'bcftools', and
6604 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6605 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6607 (license license:expat)))
6609 (define-public r-summarizedexperiment
6611 (name "r-summarizedexperiment")
6615 (uri (bioconductor-uri "SummarizedExperiment" version))
6618 "1kbj8sg2ik9f8d6g95wz0py62jldg01qy5rsdpg1cxw95nf7dzi3"))))
6620 `((upstream-name . "SummarizedExperiment")))
6621 (build-system r-build-system)
6623 `(("r-biobase" ,r-biobase)
6624 ("r-biocgenerics" ,r-biocgenerics)
6625 ("r-genomeinfodb" ,r-genomeinfodb)
6626 ("r-genomicranges" ,r-genomicranges)
6627 ("r-iranges" ,r-iranges)
6628 ("r-s4vectors" ,r-s4vectors)))
6629 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
6630 (synopsis "Container for representing genomic ranges by sample")
6632 "The SummarizedExperiment container contains one or more assays, each
6633 represented by a matrix-like object of numeric or other mode. The rows
6634 typically represent genomic ranges of interest and the columns represent
6636 (license license:artistic2.0)))
6638 (define-public r-genomicalignments
6640 (name "r-genomicalignments")
6644 (uri (bioconductor-uri "GenomicAlignments" version))
6647 "11vb0a0zd36i4yhg4mfijv787v0nihn6pkjj6q7rfy19gwy61xlc"))))
6649 `((upstream-name . "GenomicAlignments")))
6650 (build-system r-build-system)
6652 `(("r-biocgenerics" ,r-biocgenerics)
6653 ("r-biocparallel" ,r-biocparallel)
6654 ("r-biostrings" ,r-biostrings)
6655 ("r-genomeinfodb" ,r-genomeinfodb)
6656 ("r-genomicranges" ,r-genomicranges)
6657 ("r-iranges" ,r-iranges)
6658 ("r-rsamtools" ,r-rsamtools)
6659 ("r-s4vectors" ,r-s4vectors)
6660 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6661 (home-page "http://bioconductor.org/packages/GenomicAlignments")
6662 (synopsis "Representation and manipulation of short genomic alignments")
6664 "This package provides efficient containers for storing and manipulating
6665 short genomic alignments (typically obtained by aligning short reads to a
6666 reference genome). This includes read counting, computing the coverage,
6667 junction detection, and working with the nucleotide content of the
6669 (license license:artistic2.0)))
6671 (define-public r-rtracklayer
6673 (name "r-rtracklayer")
6677 (uri (bioconductor-uri "rtracklayer" version))
6680 "0x59k2fd0iaqi93gy6bm58p2j2z90z1b7a6w5b4c098y98n096rc"))))
6681 (build-system r-build-system)
6684 (modify-phases %standard-phases
6685 (add-after 'unpack 'use-system-zlib
6687 (substitute* "DESCRIPTION"
6688 (("zlibbioc, ") ""))
6689 (substitute* "NAMESPACE"
6690 (("import\\(zlibbioc\\)") ""))
6695 `(("r-biocgenerics" ,r-biocgenerics)
6696 ("r-biostrings" ,r-biostrings)
6697 ("r-genomeinfodb" ,r-genomeinfodb)
6698 ("r-genomicalignments" ,r-genomicalignments)
6699 ("r-genomicranges" ,r-genomicranges)
6700 ("r-iranges" ,r-iranges)
6701 ("r-rcurl" ,r-rcurl)
6702 ("r-rsamtools" ,r-rsamtools)
6703 ("r-s4vectors" ,r-s4vectors)
6705 ("r-xvector" ,r-xvector)))
6706 (home-page "http://bioconductor.org/packages/rtracklayer")
6707 (synopsis "R interface to genome browsers and their annotation tracks")
6709 "rtracklayer is an extensible framework for interacting with multiple
6710 genome browsers (currently UCSC built-in) and manipulating annotation tracks
6711 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
6712 built-in). The user may export/import tracks to/from the supported browsers,
6713 as well as query and modify the browser state, such as the current viewport.")
6714 (license license:artistic2.0)))
6716 (define-public r-genomicfeatures
6718 (name "r-genomicfeatures")
6722 (uri (bioconductor-uri "GenomicFeatures" version))
6725 "1ybi6r3bax07wlv2qcd34y5qjdvcqcfayfvlrjc39ifrkk65wv4f"))))
6727 `((upstream-name . "GenomicFeatures")))
6728 (build-system r-build-system)
6730 `(("r-annotationdbi" ,r-annotationdbi)
6731 ("r-biobase" ,r-biobase)
6732 ("r-biocgenerics" ,r-biocgenerics)
6733 ("r-biomart" ,r-biomart)
6734 ("r-biostrings" ,r-biostrings)
6736 ("r-genomeinfodb" ,r-genomeinfodb)
6737 ("r-genomicranges" ,r-genomicranges)
6738 ("r-iranges" ,r-iranges)
6739 ("r-rcurl" ,r-rcurl)
6740 ("r-rsqlite" ,r-rsqlite)
6741 ("r-rtracklayer" ,r-rtracklayer)
6742 ("r-s4vectors" ,r-s4vectors)
6743 ("r-xvector" ,r-xvector)))
6744 (home-page "http://bioconductor.org/packages/GenomicFeatures")
6745 (synopsis "Tools for working with transcript centric annotations")
6747 "This package provides a set of tools and methods for making and
6748 manipulating transcript centric annotations. With these tools the user can
6749 easily download the genomic locations of the transcripts, exons and cds of a
6750 given organism, from either the UCSC Genome Browser or a BioMart
6751 database (more sources will be supported in the future). This information is
6752 then stored in a local database that keeps track of the relationship between
6753 transcripts, exons, cds and genes. Flexible methods are provided for
6754 extracting the desired features in a convenient format.")
6755 (license license:artistic2.0)))
6757 (define-public r-go-db
6763 (uri (string-append "http://www.bioconductor.org/packages/"
6764 "release/data/annotation/src/contrib/GO.db_"
6768 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
6770 `((upstream-name . "GO.db")))
6771 (build-system r-build-system)
6773 `(("r-annotationdbi" ,r-annotationdbi)))
6774 (home-page "http://bioconductor.org/packages/GO.db")
6775 (synopsis "Annotation maps describing the entire Gene Ontology")
6777 "The purpose of this GO.db annotation package is to provide detailed
6778 information about the latest version of the Gene Ontologies.")
6779 (license license:artistic2.0)))
6781 (define-public r-graph
6787 (uri (bioconductor-uri "graph" version))
6790 "0g3dk5vsdp489fmyg8mifczmzgqrjlakkkr8i96dj15gghp3l135"))))
6791 (build-system r-build-system)
6793 `(("r-biocgenerics" ,r-biocgenerics)))
6794 (home-page "http://bioconductor.org/packages/graph")
6795 (synopsis "Handle graph data structures in R")
6797 "This package implements some simple graph handling capabilities for R.")
6798 (license license:artistic2.0)))
6800 (define-public r-topgo
6806 (uri (bioconductor-uri "topGO" version))
6809 "0j6sgvam4lk9348ag6pypcbkv93x4fk0di8ivhr23mz2s2yqzwrx"))))
6811 `((upstream-name . "topGO")))
6812 (build-system r-build-system)
6814 `(("r-annotationdbi" ,r-annotationdbi)
6816 ("r-biobase" ,r-biobase)
6817 ("r-biocgenerics" ,r-biocgenerics)
6818 ("r-go-db" ,r-go-db)
6819 ("r-matrixstats" ,r-matrixstats)
6820 ("r-graph" ,r-graph)
6821 ("r-sparsem" ,r-sparsem)))
6822 (home-page "http://bioconductor.org/packages/topGO")
6823 (synopsis "Enrichment analysis for gene ontology")
6825 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
6826 terms while accounting for the topology of the GO graph. Different test
6827 statistics and different methods for eliminating local similarities and
6828 dependencies between GO terms can be implemented and applied.")
6829 ;; Any version of the LGPL applies.
6830 (license license:lgpl2.1+)))
6832 (define-public r-bsgenome
6838 (uri (bioconductor-uri "BSgenome" version))
6841 "0hxwc02h5mzhkrk60d1jmlsfjf0ai9jxdc0128kj1sg4r2k1q94y"))))
6843 `((upstream-name . "BSgenome")))
6844 (build-system r-build-system)
6846 `(("r-biocgenerics" ,r-biocgenerics)
6847 ("r-biostrings" ,r-biostrings)
6848 ("r-genomeinfodb" ,r-genomeinfodb)
6849 ("r-genomicranges" ,r-genomicranges)
6850 ("r-iranges" ,r-iranges)
6851 ("r-rsamtools" ,r-rsamtools)
6852 ("r-rtracklayer" ,r-rtracklayer)
6853 ("r-s4vectors" ,r-s4vectors)
6854 ("r-xvector" ,r-xvector)))
6855 (home-page "http://bioconductor.org/packages/BSgenome")
6856 (synopsis "Infrastructure for Biostrings-based genome data packages")
6858 "This package provides infrastructure shared by all Biostrings-based
6859 genome data packages and support for efficient SNP representation.")
6860 (license license:artistic2.0)))
6862 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
6864 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
6868 ;; We cannot use bioconductor-uri here because this tarball is
6869 ;; located under "data/annotation/" instead of "bioc/".
6870 (uri (string-append "http://www.bioconductor.org/packages/"
6871 "release/data/annotation/src/contrib/"
6872 "BSgenome.Hsapiens.1000genomes.hs37d5_"
6876 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
6878 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
6879 (build-system r-build-system)
6880 ;; As this package provides little more than a very large data file it
6881 ;; doesn't make sense to build substitutes.
6882 (arguments `(#:substitutable? #f))
6884 `(("r-bsgenome" ,r-bsgenome)))
6886 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
6887 (synopsis "Full genome sequences for Homo sapiens")
6889 "This package provides full genome sequences for Homo sapiens from
6890 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
6891 (license license:artistic2.0)))
6893 (define-public r-impute
6899 (uri (bioconductor-uri "impute" version))
6902 "1164zvnikbjd0ybdn9xwn520rlmdjd824vmhnl83zgv3v9lzp9bm"))))
6904 `(("gfortran" ,gfortran)))
6905 (build-system r-build-system)
6906 (home-page "http://bioconductor.org/packages/impute")
6907 (synopsis "Imputation for microarray data")
6909 "This package provides a function to impute missing gene expression
6910 microarray data, using nearest neighbor averaging.")
6911 (license license:gpl2+)))
6913 (define-public r-seqpattern
6915 (name "r-seqpattern")
6919 (uri (bioconductor-uri "seqPattern" version))
6922 "0lsa5pz36xapi3yiv78k3z286a5md5sm5g21pgfyg8zmhmkxr7y8"))))
6924 `((upstream-name . "seqPattern")))
6925 (build-system r-build-system)
6927 `(("r-biostrings" ,r-biostrings)
6928 ("r-genomicranges" ,r-genomicranges)
6929 ("r-iranges" ,r-iranges)
6930 ("r-kernsmooth" ,r-kernsmooth)
6931 ("r-plotrix" ,r-plotrix)))
6932 (home-page "http://bioconductor.org/packages/seqPattern")
6933 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
6935 "This package provides tools to visualize oligonucleotide patterns and
6936 sequence motif occurrences across a large set of sequences centred at a common
6937 reference point and sorted by a user defined feature.")
6938 (license license:gpl3+)))
6940 (define-public r-genomation
6942 (name "r-genomation")
6946 (uri (bioconductor-uri "genomation" version))
6949 "1m4mz7wihj8yqivwkzw68div8ybk4rjsai3ffki7xp7sh21ax03y"))))
6950 (build-system r-build-system)
6952 `(("r-biostrings" ,r-biostrings)
6953 ("r-bsgenome" ,r-bsgenome)
6954 ("r-data-table" ,r-data-table)
6955 ("r-genomeinfodb" ,r-genomeinfodb)
6956 ("r-genomicalignments" ,r-genomicalignments)
6957 ("r-genomicranges" ,r-genomicranges)
6958 ("r-ggplot2" ,r-ggplot2)
6959 ("r-gridbase" ,r-gridbase)
6960 ("r-impute" ,r-impute)
6961 ("r-iranges" ,r-iranges)
6962 ("r-matrixstats" ,r-matrixstats)
6963 ("r-plotrix" ,r-plotrix)
6966 ("r-readr" ,r-readr)
6967 ("r-reshape2" ,r-reshape2)
6968 ("r-rhtslib" ,r-rhtslib)
6969 ("r-rsamtools" ,r-rsamtools)
6970 ("r-rtracklayer" ,r-rtracklayer)
6971 ("r-runit" ,r-runit)
6972 ("r-s4vectors" ,r-s4vectors)
6973 ("r-seqpattern" ,r-seqpattern)))
6976 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
6977 (synopsis "Summary, annotation and visualization of genomic data")
6979 "This package provides a package for summary and annotation of genomic
6980 intervals. Users can visualize and quantify genomic intervals over
6981 pre-defined functional regions, such as promoters, exons, introns, etc. The
6982 genomic intervals represent regions with a defined chromosome position, which
6983 may be associated with a score, such as aligned reads from HT-seq experiments,
6984 TF binding sites, methylation scores, etc. The package can use any tabular
6985 genomic feature data as long as it has minimal information on the locations of
6986 genomic intervals. In addition, it can use BAM or BigWig files as input.")
6987 (license license:artistic2.0)))
6989 (define-public r-genomationdata
6991 (name "r-genomationdata")
6995 ;; We cannot use bioconductor-uri here because this tarball is
6996 ;; located under "data/annotation/" instead of "bioc/".
6997 (uri (string-append "https://bioconductor.org/packages/"
6998 "release/data/experiment/src/contrib/"
6999 "genomationData_" version ".tar.gz"))
7002 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7003 (build-system r-build-system)
7004 ;; As this package provides little more than large data files, it doesn't
7005 ;; make sense to build substitutes.
7006 (arguments `(#:substitutable? #f))
7008 `(("r-knitr" ,r-knitr)))
7009 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7010 (synopsis "Experimental data for use with the genomation package")
7012 "This package contains experimental genetic data for use with the
7013 genomation package. Included are Chip Seq, Methylation and Cage data,
7014 downloaded from Encode.")
7015 (license license:gpl3+)))
7017 (define-public r-org-hs-eg-db
7019 (name "r-org-hs-eg-db")
7023 ;; We cannot use bioconductor-uri here because this tarball is
7024 ;; located under "data/annotation/" instead of "bioc/".
7025 (uri (string-append "http://www.bioconductor.org/packages/"
7026 "release/data/annotation/src/contrib/"
7027 "org.Hs.eg.db_" version ".tar.gz"))
7030 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7032 `((upstream-name . "org.Hs.eg.db")))
7033 (build-system r-build-system)
7035 `(("r-annotationdbi" ,r-annotationdbi)))
7036 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
7037 (synopsis "Genome wide annotation for Human")
7039 "This package provides mappings from Entrez gene identifiers to various
7040 annotations for the human genome.")
7041 (license license:artistic2.0)))
7043 (define-public r-org-ce-eg-db
7045 (name "r-org-ce-eg-db")
7049 ;; We cannot use bioconductor-uri here because this tarball is
7050 ;; located under "data/annotation/" instead of "bioc/".
7051 (uri (string-append "http://www.bioconductor.org/packages/"
7052 "release/data/annotation/src/contrib/"
7053 "org.Ce.eg.db_" version ".tar.gz"))
7056 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7058 `((upstream-name . "org.Ce.eg.db")))
7059 (build-system r-build-system)
7061 `(("r-annotationdbi" ,r-annotationdbi)))
7062 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
7063 (synopsis "Genome wide annotation for Worm")
7065 "This package provides mappings from Entrez gene identifiers to various
7066 annotations for the genome of the model worm Caenorhabditis elegans.")
7067 (license license:artistic2.0)))
7069 (define-public r-org-dm-eg-db
7071 (name "r-org-dm-eg-db")
7075 ;; We cannot use bioconductor-uri here because this tarball is
7076 ;; located under "data/annotation/" instead of "bioc/".
7077 (uri (string-append "http://www.bioconductor.org/packages/"
7078 "release/data/annotation/src/contrib/"
7079 "org.Dm.eg.db_" version ".tar.gz"))
7082 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7084 `((upstream-name . "org.Dm.eg.db")))
7085 (build-system r-build-system)
7087 `(("r-annotationdbi" ,r-annotationdbi)))
7088 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
7089 (synopsis "Genome wide annotation for Fly")
7091 "This package provides mappings from Entrez gene identifiers to various
7092 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7093 (license license:artistic2.0)))
7095 (define-public r-org-mm-eg-db
7097 (name "r-org-mm-eg-db")
7101 ;; We cannot use bioconductor-uri here because this tarball is
7102 ;; located under "data/annotation/" instead of "bioc/".
7103 (uri (string-append "http://www.bioconductor.org/packages/"
7104 "release/data/annotation/src/contrib/"
7105 "org.Mm.eg.db_" version ".tar.gz"))
7108 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7110 `((upstream-name . "org.Mm.eg.db")))
7111 (build-system r-build-system)
7113 `(("r-annotationdbi" ,r-annotationdbi)))
7114 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
7115 (synopsis "Genome wide annotation for Mouse")
7117 "This package provides mappings from Entrez gene identifiers to various
7118 annotations for the genome of the model mouse Mus musculus.")
7119 (license license:artistic2.0)))
7121 (define-public r-seqlogo
7128 (uri (bioconductor-uri "seqLogo" version))
7131 "18bajdl75h3039559d81rgllqqvnq8ygsfxfx081xphxs0v6xggy"))))
7132 (properties `((upstream-name . "seqLogo")))
7133 (build-system r-build-system)
7134 (home-page "http://bioconductor.org/packages/seqLogo")
7135 (synopsis "Sequence logos for DNA sequence alignments")
7137 "seqLogo takes the position weight matrix of a DNA sequence motif and
7138 plots the corresponding sequence logo as introduced by Schneider and
7140 (license license:lgpl2.0+)))
7142 (define-public r-bsgenome-hsapiens-ucsc-hg19
7144 (name "r-bsgenome-hsapiens-ucsc-hg19")
7148 ;; We cannot use bioconductor-uri here because this tarball is
7149 ;; located under "data/annotation/" instead of "bioc/".
7150 (uri (string-append "http://www.bioconductor.org/packages/"
7151 "release/data/annotation/src/contrib/"
7152 "BSgenome.Hsapiens.UCSC.hg19_"
7156 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7158 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7159 (build-system r-build-system)
7160 ;; As this package provides little more than a very large data file it
7161 ;; doesn't make sense to build substitutes.
7162 (arguments `(#:substitutable? #f))
7164 `(("r-bsgenome" ,r-bsgenome)))
7166 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7167 (synopsis "Full genome sequences for Homo sapiens")
7169 "This package provides full genome sequences for Homo sapiens as provided
7170 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7171 (license license:artistic2.0)))
7173 (define-public r-bsgenome-mmusculus-ucsc-mm9
7175 (name "r-bsgenome-mmusculus-ucsc-mm9")
7179 ;; We cannot use bioconductor-uri here because this tarball is
7180 ;; located under "data/annotation/" instead of "bioc/".
7181 (uri (string-append "http://www.bioconductor.org/packages/"
7182 "release/data/annotation/src/contrib/"
7183 "BSgenome.Mmusculus.UCSC.mm9_"
7187 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7189 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7190 (build-system r-build-system)
7191 ;; As this package provides little more than a very large data file it
7192 ;; doesn't make sense to build substitutes.
7193 (arguments `(#:substitutable? #f))
7195 `(("r-bsgenome" ,r-bsgenome)))
7197 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7198 (synopsis "Full genome sequences for Mouse")
7200 "This package provides full genome sequences for Mus musculus (Mouse) as
7201 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7202 (license license:artistic2.0)))
7204 (define-public r-bsgenome-mmusculus-ucsc-mm10
7206 (name "r-bsgenome-mmusculus-ucsc-mm10")
7210 ;; We cannot use bioconductor-uri here because this tarball is
7211 ;; located under "data/annotation/" instead of "bioc/".
7212 (uri (string-append "http://www.bioconductor.org/packages/"
7213 "release/data/annotation/src/contrib/"
7214 "BSgenome.Mmusculus.UCSC.mm10_"
7218 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7220 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7221 (build-system r-build-system)
7222 ;; As this package provides little more than a very large data file it
7223 ;; doesn't make sense to build substitutes.
7224 (arguments `(#:substitutable? #f))
7226 `(("r-bsgenome" ,r-bsgenome)))
7228 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7229 (synopsis "Full genome sequences for Mouse")
7231 "This package provides full genome sequences for Mus
7232 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7233 in Biostrings objects.")
7234 (license license:artistic2.0)))
7236 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7238 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7242 ;; We cannot use bioconductor-uri here because this tarball is
7243 ;; located under "data/annotation/" instead of "bioc/".
7244 (uri (string-append "http://www.bioconductor.org/packages/"
7245 "release/data/annotation/src/contrib/"
7246 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7250 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7252 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7253 (build-system r-build-system)
7254 ;; As this package provides little more than a very large data file it
7255 ;; doesn't make sense to build substitutes.
7256 (arguments `(#:substitutable? #f))
7258 `(("r-bsgenome" ,r-bsgenome)
7259 ("r-genomicfeatures" ,r-genomicfeatures)
7260 ("r-annotationdbi" ,r-annotationdbi)))
7262 "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7263 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7265 "This package loads a TxDb object, which is an R interface to
7266 prefabricated databases contained in this package. This package provides
7267 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7268 based on the knownGene track.")
7269 (license license:artistic2.0)))
7271 (define-public r-bsgenome-celegans-ucsc-ce6
7273 (name "r-bsgenome-celegans-ucsc-ce6")
7277 ;; We cannot use bioconductor-uri here because this tarball is
7278 ;; located under "data/annotation/" instead of "bioc/".
7279 (uri (string-append "http://www.bioconductor.org/packages/"
7280 "release/data/annotation/src/contrib/"
7281 "BSgenome.Celegans.UCSC.ce6_"
7285 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7287 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7288 (build-system r-build-system)
7289 ;; As this package provides little more than a very large data file it
7290 ;; doesn't make sense to build substitutes.
7291 (arguments `(#:substitutable? #f))
7293 `(("r-bsgenome" ,r-bsgenome)))
7295 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7296 (synopsis "Full genome sequences for Worm")
7298 "This package provides full genome sequences for Caenorhabditis
7299 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7301 (license license:artistic2.0)))
7303 (define-public r-bsgenome-celegans-ucsc-ce10
7305 (name "r-bsgenome-celegans-ucsc-ce10")
7309 ;; We cannot use bioconductor-uri here because this tarball is
7310 ;; located under "data/annotation/" instead of "bioc/".
7311 (uri (string-append "http://www.bioconductor.org/packages/"
7312 "release/data/annotation/src/contrib/"
7313 "BSgenome.Celegans.UCSC.ce10_"
7317 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7319 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7320 (build-system r-build-system)
7321 ;; As this package provides little more than a very large data file it
7322 ;; doesn't make sense to build substitutes.
7323 (arguments `(#:substitutable? #f))
7325 `(("r-bsgenome" ,r-bsgenome)))
7327 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7328 (synopsis "Full genome sequences for Worm")
7330 "This package provides full genome sequences for Caenorhabditis
7331 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7333 (license license:artistic2.0)))
7335 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7337 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7341 ;; We cannot use bioconductor-uri here because this tarball is
7342 ;; located under "data/annotation/" instead of "bioc/".
7343 (uri (string-append "http://www.bioconductor.org/packages/"
7344 "release/data/annotation/src/contrib/"
7345 "BSgenome.Dmelanogaster.UCSC.dm3_"
7349 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7351 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7352 (build-system r-build-system)
7353 ;; As this package provides little more than a very large data file it
7354 ;; doesn't make sense to build substitutes.
7355 (arguments `(#:substitutable? #f))
7357 `(("r-bsgenome" ,r-bsgenome)))
7359 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7360 (synopsis "Full genome sequences for Fly")
7362 "This package provides full genome sequences for Drosophila
7363 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7364 Biostrings objects.")
7365 (license license:artistic2.0)))
7367 (define-public r-motifrg
7374 (uri (bioconductor-uri "motifRG" version))
7377 "1pa97aj6c5f3gx4bgriw110764dj3m9h104ddi8rv2bpy41yd98d"))))
7378 (properties `((upstream-name . "motifRG")))
7379 (build-system r-build-system)
7381 `(("r-biostrings" ,r-biostrings)
7382 ("r-bsgenome" ,r-bsgenome)
7383 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7384 ("r-iranges" ,r-iranges)
7385 ("r-seqlogo" ,r-seqlogo)
7386 ("r-xvector" ,r-xvector)))
7387 (home-page "http://bioconductor.org/packages/motifRG")
7388 (synopsis "Discover motifs in high throughput sequencing data")
7390 "This package provides tools for discriminative motif discovery in high
7391 throughput genetic sequencing data sets using regression methods.")
7392 (license license:artistic2.0)))
7394 (define-public r-qtl
7401 (uri (string-append "mirror://cran/src/contrib/qtl_"
7405 "05bj1x2ry0i7yqiydlswb3d2h4pxg70z8w1072az1mrv1m54k8sp"))))
7406 (build-system r-build-system)
7407 (home-page "http://rqtl.org/")
7408 (synopsis "R package for analyzing QTL experiments in genetics")
7409 (description "R/qtl is an extension library for the R statistics
7410 system. It is used to analyze experimental crosses for identifying
7411 genes contributing to variation in quantitative traits (so-called
7412 quantitative trait loci, QTLs).
7414 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7415 identify genotyping errors, and to perform single-QTL and two-QTL,
7416 two-dimensional genome scans.")
7417 (license license:gpl3)))
7419 (define-public r-zlibbioc
7425 (uri (bioconductor-uri "zlibbioc" version))
7428 "0hbk90q5hl0fycfvy5nxxa4hxgglag9lzp7i0fg849bqygg5nbyq"))))
7430 `((upstream-name . "zlibbioc")))
7431 (build-system r-build-system)
7432 (home-page "https://bioconductor.org/packages/zlibbioc")
7433 (synopsis "Provider for zlib-1.2.5 to R packages")
7434 (description "This package uses the source code of zlib-1.2.5 to create
7435 libraries for systems that do not have these available via other means.")
7436 (license license:artistic2.0)))
7438 (define-public r-r4rna
7445 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7449 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7450 (build-system r-build-system)
7452 `(("r-optparse" ,r-optparse)
7453 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7454 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7455 (synopsis "Analysis framework for RNA secondary structure")
7457 "The R4RNA package aims to be a general framework for the analysis of RNA
7458 secondary structure and comparative analysis in R.")
7459 (license license:gpl3+)))
7461 (define-public r-rhtslib
7468 (uri (bioconductor-uri "Rhtslib" version))
7471 "1vk3ng61dhi3pbia1lp3gl3mlr3i1vb2lkq83qb53i9dzz128wh9"))))
7472 (properties `((upstream-name . "Rhtslib")))
7473 (build-system r-build-system)
7475 `(("r-zlibbioc" ,r-zlibbioc)))
7479 `(("autoconf" ,autoconf)))
7480 (home-page "https://github.com/nhayden/Rhtslib")
7481 (synopsis "High-throughput sequencing library as an R package")
7483 "This package provides the HTSlib C library for high-throughput
7484 nucleotide sequence analysis. The package is primarily useful to developers
7485 of other R packages who wish to make use of HTSlib.")
7486 (license license:lgpl2.0+)))
7488 (define-public r-bamsignals
7490 (name "r-bamsignals")
7495 (uri (bioconductor-uri "bamsignals" version))
7498 "1k42gvk5mgq4la1fp0in3an2zfdz69h6522jsqhmk0f6i75kg4mb"))))
7499 (build-system r-build-system)
7501 `(("r-biocgenerics" ,r-biocgenerics)
7502 ("r-genomicranges" ,r-genomicranges)
7503 ("r-iranges" ,r-iranges)
7505 ("r-rhtslib" ,r-rhtslib)
7506 ("r-zlibbioc" ,r-zlibbioc)))
7509 (home-page "http://bioconductor.org/packages/bamsignals")
7510 (synopsis "Extract read count signals from bam files")
7512 "This package allows to efficiently obtain count vectors from indexed bam
7513 files. It counts the number of nucleotide sequence reads in given genomic
7514 ranges and it computes reads profiles and coverage profiles. It also handles
7516 (license license:gpl2+)))
7518 (define-public r-rcas
7524 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7526 (file-name (string-append name "-" version ".tar.gz"))
7529 "1hd0r66556bxbdd82ksjklq7nfli36l4k6y88ic7kkg9873wa1nw"))))
7530 (build-system r-build-system)
7532 `(("r-knitr" ,r-knitr)
7533 ("r-testthat" ,r-testthat)
7534 ;; During vignette building knitr checks that "pandoc-citeproc"
7536 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7538 `(("r-data-table" ,r-data-table)
7539 ("r-biomart" ,r-biomart)
7540 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7541 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7542 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7543 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7544 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7545 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7546 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7547 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7548 ("r-topgo" ,r-topgo)
7550 ("r-plotly" ,r-plotly)
7551 ("r-plotrix" ,r-plotrix)
7552 ("r-motifrg" ,r-motifrg)
7553 ("r-genomation" ,r-genomation)
7554 ("r-genomicfeatures" ,r-genomicfeatures)
7555 ("r-rtracklayer" ,r-rtracklayer)
7556 ("r-rmarkdown" ,r-rmarkdown)))
7557 (synopsis "RNA-centric annotation system")
7559 "RCAS aims to be a standalone RNA-centric annotation system that provides
7560 intuitive reports and publication-ready graphics. This package provides the R
7561 library implementing most of the pipeline's features.")
7562 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7563 (license license:expat)))
7565 (define-public rcas-web
7572 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7573 "releases/download/v" version
7574 "/rcas-web-" version ".tar.gz"))
7577 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7578 (build-system gnu-build-system)
7581 (modify-phases %standard-phases
7582 (add-after 'install 'wrap-executable
7583 (lambda* (#:key inputs outputs #:allow-other-keys)
7584 (let* ((out (assoc-ref outputs "out"))
7585 (json (assoc-ref inputs "guile-json"))
7586 (redis (assoc-ref inputs "guile-redis"))
7587 (path (string-append
7588 json "/share/guile/site/2.2:"
7589 redis "/share/guile/site/2.2")))
7590 (wrap-program (string-append out "/bin/rcas-web")
7591 `("GUILE_LOAD_PATH" ":" = (,path))
7592 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
7593 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
7598 ("guile-next" ,guile-next)
7599 ("guile-json" ,guile2.2-json)
7600 ("guile-redis" ,guile2.2-redis)))
7602 `(("pkg-config" ,pkg-config)))
7603 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
7604 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
7605 (description "This package provides a simple web interface for the
7606 @dfn{RNA-centric annotation system} (RCAS).")
7607 (license license:agpl3+)))
7609 (define-public r-mutationalpatterns
7611 (name "r-mutationalpatterns")
7616 (uri (bioconductor-uri "MutationalPatterns" version))
7619 "1a3c2bm0xx0q4gf98jiw74msmdf2fr8rbsdysd5ww9kqlzmsbr17"))))
7620 (build-system r-build-system)
7622 `(("r-biocgenerics" ,r-biocgenerics)
7623 ("r-biostrings" ,r-biostrings)
7624 ("r-genomicranges" ,r-genomicranges)
7625 ("r-genomeinfodb" ,r-genomeinfodb)
7626 ("r-ggplot2" ,r-ggplot2)
7627 ("r-gridextra" ,r-gridextra)
7628 ("r-iranges" ,r-iranges)
7631 ("r-pracma" ,r-pracma)
7632 ("r-reshape2" ,r-reshape2)
7633 ("r-summarizedexperiment" ,r-summarizedexperiment)
7634 ("r-variantannotation" ,r-variantannotation)))
7635 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
7636 (synopsis "Extract and visualize mutational patterns in genomic data")
7637 (description "This package provides an extensive toolset for the
7638 characterization and visualization of a wide range of mutational patterns
7639 in SNV base substitution data.")
7640 (license license:expat)))
7642 (define-public r-wgcna
7649 (uri (cran-uri "WGCNA" version))
7652 "0hzvnhw76vwg8bl8x368f0c5szpwb8323bmrb3bir93i5bmfjsxx"))))
7653 (properties `((upstream-name . "WGCNA")))
7654 (build-system r-build-system)
7656 `(("r-annotationdbi" ,r-annotationdbi)
7657 ("r-doparallel" ,r-doparallel)
7658 ("r-dynamictreecut" ,r-dynamictreecut)
7659 ("r-fastcluster" ,r-fastcluster)
7660 ("r-foreach" ,r-foreach)
7661 ("r-go-db" ,r-go-db)
7662 ("r-hmisc" ,r-hmisc)
7663 ("r-impute" ,r-impute)
7664 ("r-matrixstats" ,r-matrixstats)
7665 ("r-preprocesscore" ,r-preprocesscore)))
7667 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
7668 (synopsis "Weighted correlation network analysis")
7670 "This package provides functions necessary to perform Weighted
7671 Correlation Network Analysis on high-dimensional data. It includes functions
7672 for rudimentary data cleaning, construction and summarization of correlation
7673 networks, module identification and functions for relating both variables and
7674 modules to sample traits. It also includes a number of utility functions for
7675 data manipulation and visualization.")
7676 (license license:gpl2+)))
7678 (define-public r-chipkernels
7679 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
7682 (name "r-chipkernels")
7683 (version (string-append "1.1-" revision "." (string-take commit 9)))
7688 (url "https://github.com/ManuSetty/ChIPKernels.git")
7690 (file-name (string-append name "-" version))
7693 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
7694 (build-system r-build-system)
7696 `(("r-iranges" ,r-iranges)
7697 ("r-xvector" ,r-xvector)
7698 ("r-biostrings" ,r-biostrings)
7699 ("r-bsgenome" ,r-bsgenome)
7700 ("r-gtools" ,r-gtools)
7701 ("r-genomicranges" ,r-genomicranges)
7702 ("r-sfsmisc" ,r-sfsmisc)
7703 ("r-kernlab" ,r-kernlab)
7704 ("r-s4vectors" ,r-s4vectors)
7705 ("r-biocgenerics" ,r-biocgenerics)))
7706 (home-page "https://github.com/ManuSetty/ChIPKernels")
7707 (synopsis "Build string kernels for DNA Sequence analysis")
7708 (description "ChIPKernels is an R package for building different string
7709 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
7710 must be built and this dictionary can be used for determining kernels for DNA
7712 (license license:gpl2+))))
7714 (define-public r-seqgl
7721 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
7722 "archive/" version ".tar.gz"))
7723 (file-name (string-append name "-" version ".tar.gz"))
7726 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
7727 (build-system r-build-system)
7729 `(("r-biostrings" ,r-biostrings)
7730 ("r-chipkernels" ,r-chipkernels)
7731 ("r-genomicranges" ,r-genomicranges)
7732 ("r-spams" ,r-spams)
7733 ("r-wgcna" ,r-wgcna)
7734 ("r-fastcluster" ,r-fastcluster)))
7735 (home-page "https://github.com/ManuSetty/SeqGL")
7736 (synopsis "Group lasso for Dnase/ChIP-seq data")
7737 (description "SeqGL is a group lasso based algorithm to extract
7738 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
7739 This package presents a method which uses group lasso to discriminate between
7740 bound and non bound genomic regions to accurately identify transcription
7741 factors bound at the specific regions.")
7742 (license license:gpl2+)))
7744 (define-public r-gkmsvm
7751 (uri (cran-uri "gkmSVM" version))
7754 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
7755 (properties `((upstream-name . "gkmSVM")))
7756 (build-system r-build-system)
7758 `(("r-biocgenerics" ,r-biocgenerics)
7759 ("r-biostrings" ,r-biostrings)
7760 ("r-genomeinfodb" ,r-genomeinfodb)
7761 ("r-genomicranges" ,r-genomicranges)
7762 ("r-iranges" ,r-iranges)
7763 ("r-kernlab" ,r-kernlab)
7766 ("r-rtracklayer" ,r-rtracklayer)
7767 ("r-s4vectors" ,r-s4vectors)
7768 ("r-seqinr" ,r-seqinr)))
7769 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
7770 (synopsis "Gapped-kmer support vector machine")
7772 "This R package provides tools for training gapped-kmer SVM classifiers
7773 for DNA and protein sequences. This package supports several sequence
7774 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
7775 (license license:gpl2+)))
7777 (define-public r-tximport
7783 (uri (bioconductor-uri "tximport" version))
7786 "1k5a7dad6zqg936s17f6cmwgqp11x24z9zhxndsgwbscgpyhpcb0"))))
7787 (build-system r-build-system)
7788 (home-page "http://bioconductor.org/packages/tximport")
7789 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
7791 "This package provides tools to import transcript-level abundance,
7792 estimated counts and transcript lengths, and to summarize them into matrices
7793 for use with downstream gene-level analysis packages. Average transcript
7794 length, weighted by sample-specific transcript abundance estimates, is
7795 provided as a matrix which can be used as an offset for different expression
7796 of gene-level counts.")
7797 (license license:gpl2+)))
7799 (define-public r-rhdf5
7805 (uri (bioconductor-uri "rhdf5" version))
7808 "0pb04li55ysag30s7rap7nnivc0rqmgsmpj43kin0rxdabfn1w0k"))))
7809 (build-system r-build-system)
7812 (modify-phases %standard-phases
7813 (add-after 'unpack 'unpack-smallhdf5
7814 (lambda* (#:key outputs #:allow-other-keys)
7815 (system* "tar" "-xzvf"
7816 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
7817 (substitute* "src/Makevars"
7818 (("^.*cd hdf5source &&.*$") "")
7819 (("^.*gunzip -dc hdf5small.tgz.*$") "")
7820 (("^.*rm -rf hdf5.*$") "")
7821 (("^.*mv hdf5source/hdf5 ..*$") ""))
7822 (substitute* "src/hdf5/configure"
7826 `(("r-zlibbioc" ,r-zlibbioc)))
7830 (home-page "http://bioconductor.org/packages/rhdf5")
7831 (synopsis "HDF5 interface to R")
7833 "This R/Bioconductor package provides an interface between HDF5 and R.
7834 HDF5's main features are the ability to store and access very large and/or
7835 complex datasets and a wide variety of metadata on mass storage (disk) through
7836 a completely portable file format. The rhdf5 package is thus suited for the
7837 exchange of large and/or complex datasets between R and other software
7838 package, and for letting R applications work on datasets that are larger than
7839 the available RAM.")
7840 (license license:artistic2.0)))
7842 (define-public emboss
7848 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
7849 (version-major+minor version) ".0/"
7850 "EMBOSS-" version ".tar.gz"))
7853 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
7854 (build-system gnu-build-system)
7857 (list (string-append "--with-hpdf="
7858 (assoc-ref %build-inputs "libharu")))
7860 (modify-phases %standard-phases
7861 (add-after 'unpack 'fix-checks
7863 ;; The PNGDRIVER tests check for the presence of libgd, libpng
7864 ;; and zlib, but assume that they are all found at the same
7866 (substitute* "configure.in"
7867 (("CHECK_PNGDRIVER")
7868 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
7869 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
7870 AM_CONDITIONAL(AMPNG, true)"))
7872 (add-after 'unpack 'disable-update-check
7874 ;; At build time there is no connection to the Internet, so
7875 ;; looking for updates will not work.
7876 (substitute* "Makefile.am"
7877 (("\\$\\(bindir\\)/embossupdate") ""))
7879 (add-before 'configure 'autogen
7880 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
7886 ("libharu" ,libharu)
7889 `(("autoconf" ,autoconf)
7890 ("automake" ,automake)
7891 ("libtool" ,libtool)
7892 ("pkg-config" ,pkg-config)))
7893 (home-page "http://emboss.sourceforge.net")
7894 (synopsis "Molecular biology analysis suite")
7895 (description "EMBOSS is the \"European Molecular Biology Open Software
7896 Suite\". EMBOSS is an analysis package specially developed for the needs of
7897 the molecular biology (e.g. EMBnet) user community. The software
7898 automatically copes with data in a variety of formats and even allows
7899 transparent retrieval of sequence data from the web. It also provides a
7900 number of libraries for the development of software in the field of molecular
7901 biology. EMBOSS also integrates a range of currently available packages and
7902 tools for sequence analysis into a seamless whole.")
7903 (license license:gpl2+)))
7906 (let ((revision "1")
7907 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
7910 ;; The version is 2.13.0 even though no release archives have been
7911 ;; published as yet.
7912 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
7916 (url "https://github.com/arq5x/bits.git")
7918 (file-name (string-append name "-" version "-checkout"))
7921 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
7922 (build-system gnu-build-system)
7924 `(#:tests? #f ;no tests included
7926 (modify-phases %standard-phases
7928 (add-after 'unpack 'remove-cuda
7930 (substitute* "Makefile"
7932 (("(bits_test_intersections) \\\\" _ match) match))
7935 (lambda* (#:key outputs #:allow-other-keys)
7937 "bin" (string-append (assoc-ref outputs "out") "/bin"))
7942 (home-page "https://github.com/arq5x/bits")
7943 (synopsis "Implementation of binary interval search algorithm")
7944 (description "This package provides an implementation of the
7945 BITS (Binary Interval Search) algorithm, an approach to interval set
7946 intersection. It is especially suited for the comparison of diverse genomic
7947 datasets and the exploration of large datasets of genome
7948 intervals (e.g. genes, sequence alignments).")
7949 (license license:gpl2))))
7951 (define-public piranha
7952 ;; There is no release tarball for the latest version. The latest commit is
7953 ;; older than one year at the time of this writing.
7954 (let ((revision "1")
7955 (commit "0466d364b71117d01e4471b74c514436cc281233"))
7958 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
7962 (url "https://github.com/smithlabcode/piranha.git")
7966 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
7967 (build-system gnu-build-system)
7969 `(#:test-target "test"
7971 (modify-phases %standard-phases
7972 (add-after 'unpack 'copy-smithlab-cpp
7973 (lambda* (#:key inputs #:allow-other-keys)
7974 (for-each (lambda (file)
7975 (install-file file "./src/smithlab_cpp/"))
7976 (find-files (assoc-ref inputs "smithlab-cpp")))
7978 (add-after 'install 'install-to-store
7979 (lambda* (#:key outputs #:allow-other-keys)
7980 (let* ((out (assoc-ref outputs "out"))
7981 (bin (string-append out "/bin")))
7982 (for-each (lambda (file)
7983 (install-file file bin))
7984 (find-files "bin" ".*")))
7987 (list (string-append "--with-bam_tools_headers="
7988 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
7989 (string-append "--with-bam_tools_library="
7990 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
7992 `(("bamtools" ,bamtools)
7993 ("samtools" ,samtools-0.1)
7996 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8000 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8002 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8005 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8007 `(("python" ,python-2)))
8008 (home-page "https://github.com/smithlabcode/piranha")
8009 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8011 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8012 RIP-seq experiments. It takes input in BED or BAM format and identifies
8013 regions of statistically significant read enrichment. Additional covariates
8014 may optionally be provided to further inform the peak-calling process.")
8015 (license license:gpl3+))))
8023 (uri (string-append "https://pypi.python.org/packages/source/P"
8024 "/PePr/PePr-" version ".tar.gz"))
8027 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8028 (build-system python-build-system)
8030 `(#:python ,python-2 ; python2 only
8031 #:tests? #f)) ; no tests included
8033 `(("python2-numpy" ,python2-numpy)
8034 ("python2-scipy" ,python2-scipy)
8035 ("python2-pysam" ,python2-pysam)))
8036 (home-page "https://github.com/shawnzhangyx/PePr")
8037 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8039 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8040 that is primarily designed for data with biological replicates. It uses a
8041 negative binomial distribution to model the read counts among the samples in
8042 the same group, and look for consistent differences between ChIP and control
8043 group or two ChIP groups run under different conditions.")
8044 (license license:gpl3+)))
8046 (define-public filevercmp
8047 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8050 (version (string-append "0-1." (string-take commit 7)))
8053 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8055 (file-name (string-append name "-" version ".tar.gz"))
8057 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8058 (build-system gnu-build-system)
8060 `(#:tests? #f ; There are no tests to run.
8062 (modify-phases %standard-phases
8063 (delete 'configure) ; There is no configure phase.
8065 (lambda* (#:key outputs #:allow-other-keys)
8066 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8067 (install-file "filevercmp" bin)))))))
8068 (home-page "https://github.com/ekg/filevercmp")
8069 (synopsis "This program compares version strings")
8070 (description "This program compares version strings. It intends to be a
8071 replacement for strverscmp.")
8072 (license license:gpl3+))))
8074 (define-public multiqc
8081 (uri (pypi-uri "multiqc" version))
8084 "12gs1jw2jrxrij529rnl5kaqxfcqn15yzcsggxkfhdx634ml0cny"))
8085 (patches (search-patches "multiqc-fix-git-subprocess-error.patch"))))
8086 (build-system python-build-system)
8088 ;; Tests are to be introduced in the next version, see
8089 ;; https://github.com/ewels/MultiQC/issues/376
8092 `(("python-jinja2" ,python-jinja2)
8093 ("python-simplejson" ,python-simplejson)
8094 ("python-pyyaml" ,python-pyyaml)
8095 ("python-click" ,python-click)
8096 ("python-matplotlib" ,python-matplotlib)
8097 ("python-numpy" ,python-numpy)
8098 ;; MultQC checks for the presence of nose at runtime.
8099 ("python-nose" ,python-nose)))
8100 (home-page "http://multiqc.info")
8101 (synopsis "Aggregate bioinformatics analysis reports")
8103 "MultiQC is a tool to aggregate bioinformatics results across many
8104 samples into a single report. It contains modules for a large number of
8105 common bioinformatics tools.")
8106 (license license:gpl3)))
8108 (define-public r-chipseq
8115 (uri (bioconductor-uri "chipseq" version))
8118 "115ayp82rs99iaswrx45skw1i5iacgwzz5k8rzijbp5qic0554n0"))))
8119 (build-system r-build-system)
8121 `(("r-biocgenerics" ,r-biocgenerics)
8122 ("r-genomicranges" ,r-genomicranges)
8123 ("r-iranges" ,r-iranges)
8124 ("r-s4vectors" ,r-s4vectors)
8125 ("r-shortread" ,r-shortread)))
8126 (home-page "http://bioconductor.org/packages/chipseq")
8127 (synopsis "Package for analyzing ChIPseq data")
8129 "This package provides tools for processing short read data from ChIPseq
8131 (license license:artistic2.0)))
8133 (define-public r-copyhelper
8135 (name "r-copyhelper")
8140 (uri (string-append "http://bioconductor.org/packages/release/"
8141 "data/experiment/src/contrib/CopyhelpeR_"
8145 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8146 (properties `((upstream-name . "CopyhelpeR")))
8147 (build-system r-build-system)
8148 (home-page "http://bioconductor.org/packages/CopyhelpeR/")
8149 (synopsis "Helper files for CopywriteR")
8151 "This package contains the helper files that are required to run the
8152 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8153 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8154 mm10. In addition, it contains a blacklist filter to remove regions that
8155 display copy number variation. Files are stored as GRanges objects from the
8156 GenomicRanges Bioconductor package.")
8157 (license license:gpl2)))
8159 (define-public r-copywriter
8161 (name "r-copywriter")
8166 (uri (bioconductor-uri "CopywriteR" version))
8169 "1bwwnsyk7cpgwkagsnn5mv6fv233b0rkhjvbadrh70h8m4anawfj"))))
8170 (properties `((upstream-name . "CopywriteR")))
8171 (build-system r-build-system)
8173 `(("r-biocparallel" ,r-biocparallel)
8174 ("r-chipseq" ,r-chipseq)
8175 ("r-copyhelper" ,r-copyhelper)
8176 ("r-data-table" ,r-data-table)
8177 ("r-dnacopy" ,r-dnacopy)
8178 ("r-futile-logger" ,r-futile-logger)
8179 ("r-genomeinfodb" ,r-genomeinfodb)
8180 ("r-genomicalignments" ,r-genomicalignments)
8181 ("r-genomicranges" ,r-genomicranges)
8182 ("r-gtools" ,r-gtools)
8183 ("r-iranges" ,r-iranges)
8184 ("r-matrixstats" ,r-matrixstats)
8185 ("r-rsamtools" ,r-rsamtools)
8186 ("r-s4vectors" ,r-s4vectors)))
8187 (home-page "https://github.com/PeeperLab/CopywriteR")
8188 (synopsis "Copy number information from targeted sequencing")
8190 "CopywriteR extracts DNA copy number information from targeted sequencing
8191 by utilizing off-target reads. It allows for extracting uniformly distributed
8192 copy number information, can be used without reference, and can be applied to
8193 sequencing data obtained from various techniques including chromatin
8194 immunoprecipitation and target enrichment on small gene panels. Thereby,
8195 CopywriteR constitutes a widely applicable alternative to available copy
8196 number detection tools.")
8197 (license license:gpl2)))
8199 (define-public r-sva
8206 (uri (bioconductor-uri "sva" version))
8209 "1wc1fjm6dzlsqqagm43y57w8jh8nsh0r0m8z1p6ximcb5gxqh7hn"))))
8210 (build-system r-build-system)
8212 `(("r-genefilter" ,r-genefilter)))
8213 (home-page "http://bioconductor.org/packages/sva")
8214 (synopsis "Surrogate variable analysis")
8216 "This package contains functions for removing batch effects and other
8217 unwanted variation in high-throughput experiment. It also contains functions
8218 for identifying and building surrogate variables for high-dimensional data
8219 sets. Surrogate variables are covariates constructed directly from
8220 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8221 imaging data that can be used in subsequent analyses to adjust for unknown,
8222 unmodeled, or latent sources of noise.")
8223 (license license:artistic2.0)))
8225 (define-public r-seqminer
8232 (uri (cran-uri "seqminer" version))
8235 "0y0gc5lws3hdxasjb84m532ics6imb7qg9sl1zy62h503jh4j9gw"))))
8236 (build-system r-build-system)
8239 (home-page "http://seqminer.genomic.codes")
8240 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8242 "This package provides tools to integrate nucleotide sequencing
8243 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8244 ;; Any version of the GPL is acceptable
8245 (license (list license:gpl2+ license:gpl3+))))
8247 (define-public r-raremetals2
8249 (name "r-raremetals2")
8254 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8255 "b/b7/RareMETALS2_" version ".tar.gz"))
8258 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8259 (properties `((upstream-name . "RareMETALS2")))
8260 (build-system r-build-system)
8262 `(("r-seqminer" ,r-seqminer)
8263 ("r-mvtnorm" ,r-mvtnorm)
8264 ("r-compquadform" ,r-compquadform)
8265 ("r-getopt" ,r-getopt)))
8266 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8267 (synopsis "Analyze gene-level association tests for binary trait")
8269 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8270 It was designed to meta-analyze gene-level association tests for binary trait.
8271 While rareMETALS offers a near-complete solution for meta-analysis of
8272 gene-level tests for quantitative trait, it does not offer the optimal
8273 solution for binary trait. The package rareMETALS2 offers improved features
8274 for analyzing gene-level association tests in meta-analyses for binary
8276 (license license:gpl3)))
8278 (define-public r-maldiquant
8280 (name "r-maldiquant")
8285 (uri (cran-uri "MALDIquant" version))
8288 "067xbmy10mpsvmv77g62chd7wwhdhcfn5hmp5fisbnz2h5rq0q60"))))
8289 (properties `((upstream-name . "MALDIquant")))
8290 (build-system r-build-system)
8291 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8292 (synopsis "Quantitative analysis of mass spectrometry data")
8294 "This package provides a complete analysis pipeline for matrix-assisted
8295 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8296 two-dimensional mass spectrometry data. In addition to commonly used plotting
8297 and processing methods it includes distinctive features, namely baseline
8298 subtraction methods such as morphological filters (TopHat) or the
8299 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8300 alignment using warping functions, handling of replicated measurements as well
8301 as allowing spectra with different resolutions.")
8302 (license license:gpl3+)))
8304 (define-public r-protgenerics
8306 (name "r-protgenerics")
8311 (uri (bioconductor-uri "ProtGenerics" version))
8314 "0hb3vrrvfx6lcfalmjxm8dmigfmi5nba0pzjfgsrzd35c8mbfc6f"))))
8315 (properties `((upstream-name . "ProtGenerics")))
8316 (build-system r-build-system)
8317 (home-page "https://github.com/lgatto/ProtGenerics")
8318 (synopsis "S4 generic functions for proteomics infrastructure")
8320 "This package provides S4 generic functions needed by Bioconductor
8321 proteomics packages.")
8322 (license license:artistic2.0)))
8324 (define-public r-mzr
8331 (uri (bioconductor-uri "mzR" version))
8334 "0ipmhg6l3pf648rdx5g2ha7l5ppd3cja6afxhdw76x8ga3633x0r"))))
8335 (properties `((upstream-name . "mzR")))
8336 (build-system r-build-system)
8338 `(("netcdf" ,netcdf)))
8340 `(("r-biobase" ,r-biobase)
8341 ("r-biocgenerics" ,r-biocgenerics)
8342 ("r-protgenerics" ,r-protgenerics)
8344 ("r-zlibbioc" ,r-zlibbioc)))
8345 (home-page "https://github.com/sneumann/mzR/")
8346 (synopsis "Parser for mass spectrometry data files")
8348 "The mzR package provides a unified API to the common file formats and
8349 parsers available for mass spectrometry data. It comes with a wrapper for the
8350 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8351 The package contains the original code written by the ISB, and a subset of the
8352 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8353 previously been used in XCMS.")
8354 (license license:artistic2.0)))
8356 (define-public r-affyio
8363 (uri (bioconductor-uri "affyio" version))
8366 "1svsl4mpk06xm505pap913x69ywks99262krag8y4ygpllj7dfyy"))))
8367 (build-system r-build-system)
8369 `(("r-zlibbioc" ,r-zlibbioc)))
8372 (home-page "https://github.com/bmbolstad/affyio")
8373 (synopsis "Tools for parsing Affymetrix data files")
8375 "This package provides routines for parsing Affymetrix data files based
8376 upon file format information. The primary focus is on accessing the CEL and
8378 (license license:lgpl2.0+)))
8380 (define-public r-affy
8387 (uri (bioconductor-uri "affy" version))
8390 "1snq71ligf0wvaxa6zfrl13ydw0zfhspmhdyfk8q3ba3np4cz344"))))
8391 (build-system r-build-system)
8393 `(("r-affyio" ,r-affyio)
8394 ("r-biobase" ,r-biobase)
8395 ("r-biocgenerics" ,r-biocgenerics)
8396 ("r-biocinstaller" ,r-biocinstaller)
8397 ("r-preprocesscore" ,r-preprocesscore)
8398 ("r-zlibbioc" ,r-zlibbioc)))
8399 (home-page "http://bioconductor.org/packages/affy")
8400 (synopsis "Methods for affymetrix oligonucleotide arrays")
8402 "This package contains functions for exploratory oligonucleotide array
8404 (license license:lgpl2.0+)))
8406 (define-public r-vsn
8413 (uri (bioconductor-uri "vsn" version))
8416 "0mgl0azys2g90simf8wx6jdwd7gyg3m4pf12n6w6507jixm2cg97"))))
8417 (build-system r-build-system)
8419 `(("r-affy" ,r-affy)
8420 ("r-biobase" ,r-biobase)
8421 ("r-ggplot2" ,r-ggplot2)
8422 ("r-limma" ,r-limma)))
8423 (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
8424 (synopsis "Variance stabilization and calibration for microarray data")
8426 "The package implements a method for normalising microarray intensities,
8427 and works for single- and multiple-color arrays. It can also be used for data
8428 from other technologies, as long as they have similar format. The method uses
8429 a robust variant of the maximum-likelihood estimator for an
8430 additive-multiplicative error model and affine calibration. The model
8431 incorporates data calibration step (a.k.a. normalization), a model for the
8432 dependence of the variance on the mean intensity and a variance stabilizing
8433 data transformation. Differences between transformed intensities are
8434 analogous to \"normalized log-ratios\". However, in contrast to the latter,
8435 their variance is independent of the mean, and they are usually more sensitive
8436 and specific in detecting differential transcription.")
8437 (license license:artistic2.0)))
8439 (define-public r-mzid
8446 (uri (bioconductor-uri "mzID" version))
8449 "1zn896cpfvqp1qmq5c4vcj933hb8rxwb6gkck1wqvr7393rpqy1q"))))
8450 (properties `((upstream-name . "mzID")))
8451 (build-system r-build-system)
8453 `(("r-doparallel" ,r-doparallel)
8454 ("r-foreach" ,r-foreach)
8455 ("r-iterators" ,r-iterators)
8457 ("r-protgenerics" ,r-protgenerics)
8460 (home-page "http://bioconductor.org/packages/mzID")
8461 (synopsis "Parser for mzIdentML files")
8463 "This package provides a parser for mzIdentML files implemented using the
8464 XML package. The parser tries to be general and able to handle all types of
8465 mzIdentML files with the drawback of having less pretty output than a vendor
8467 (license license:gpl2+)))
8469 (define-public r-pcamethods
8471 (name "r-pcamethods")
8476 (uri (bioconductor-uri "pcaMethods" version))
8479 "18mawhxw57pgpn87qha4mwki24gqja7wpqha8q496476vyap11xw"))))
8480 (properties `((upstream-name . "pcaMethods")))
8481 (build-system r-build-system)
8483 `(("r-biobase" ,r-biobase)
8484 ("r-biocgenerics" ,r-biocgenerics)
8485 ("r-rcpp" ,r-rcpp)))
8486 (home-page "https://github.com/hredestig/pcamethods")
8487 (synopsis "Collection of PCA methods")
8489 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
8490 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
8491 for missing value estimation is included for comparison. BPCA, PPCA and
8492 NipalsPCA may be used to perform PCA on incomplete data as well as for
8493 accurate missing value estimation. A set of methods for printing and plotting
8494 the results is also provided. All PCA methods make use of the same data
8495 structure (pcaRes) to provide a common interface to the PCA results.")
8496 (license license:gpl3+)))
8498 (define-public r-msnbase
8505 (uri (bioconductor-uri "MSnbase" version))
8508 "0jjjs29dcwsjaxzfqxy98ycpg3rwxzzchkj77my3cjgdc00sm66n"))))
8509 (properties `((upstream-name . "MSnbase")))
8510 (build-system r-build-system)
8512 `(("r-affy" ,r-affy)
8513 ("r-biobase" ,r-biobase)
8514 ("r-biocgenerics" ,r-biocgenerics)
8515 ("r-biocparallel" ,r-biocparallel)
8516 ("r-digest" ,r-digest)
8517 ("r-ggplot2" ,r-ggplot2)
8518 ("r-impute" ,r-impute)
8519 ("r-iranges" ,r-iranges)
8520 ("r-maldiquant" ,r-maldiquant)
8523 ("r-pcamethods" ,r-pcamethods)
8525 ("r-preprocesscore" ,r-preprocesscore)
8526 ("r-protgenerics" ,r-protgenerics)
8528 ("r-reshape2" ,r-reshape2)
8529 ("r-s4vectors" ,r-s4vectors)
8532 (home-page "https://github.com/lgatto/MSnbase")
8533 (synopsis "Base functions and classes for MS-based proteomics")
8535 "This package provides basic plotting, data manipulation and processing
8536 of mass spectrometry based proteomics data.")
8537 (license license:artistic2.0)))
8539 (define-public r-msnid
8546 (uri (bioconductor-uri "MSnID" version))
8549 "0fkk3za39cxi0jyxmagmycjdslr2xf6vg3ylz14jyffqi0blw9d5"))))
8550 (properties `((upstream-name . "MSnID")))
8551 (build-system r-build-system)
8553 `(("r-biobase" ,r-biobase)
8554 ("r-data-table" ,r-data-table)
8555 ("r-doparallel" ,r-doparallel)
8556 ("r-dplyr" ,r-dplyr)
8557 ("r-foreach" ,r-foreach)
8558 ("r-iterators" ,r-iterators)
8559 ("r-msnbase" ,r-msnbase)
8562 ("r-protgenerics" ,r-protgenerics)
8563 ("r-r-cache" ,r-r-cache)
8565 ("r-reshape2" ,r-reshape2)))
8566 (home-page "http://bioconductor.org/packages/MSnID")
8567 (synopsis "Utilities for LC-MSn proteomics identifications")
8569 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
8570 from mzIdentML (leveraging the mzID package) or text files. After collating
8571 the search results from multiple datasets it assesses their identification
8572 quality and optimize filtering criteria to achieve the maximum number of
8573 identifications while not exceeding a specified false discovery rate. It also
8574 contains a number of utilities to explore the MS/MS results and assess missed
8575 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
8576 (license license:artistic2.0)))