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 ldc)
67 #:use-module (gnu packages linux)
68 #:use-module (gnu packages logging)
69 #:use-module (gnu packages machine-learning)
70 #:use-module (gnu packages man)
71 #:use-module (gnu packages maths)
72 #:use-module (gnu packages mpi)
73 #:use-module (gnu packages ncurses)
74 #:use-module (gnu packages pcre)
75 #:use-module (gnu packages parallel)
76 #:use-module (gnu packages pdf)
77 #:use-module (gnu packages perl)
78 #:use-module (gnu packages pkg-config)
79 #:use-module (gnu packages popt)
80 #:use-module (gnu packages protobuf)
81 #:use-module (gnu packages python)
82 #:use-module (gnu packages readline)
83 #:use-module (gnu packages ruby)
84 #:use-module (gnu packages serialization)
85 #:use-module (gnu packages statistics)
86 #:use-module (gnu packages tbb)
87 #:use-module (gnu packages tex)
88 #:use-module (gnu packages texinfo)
89 #:use-module (gnu packages textutils)
90 #:use-module (gnu packages time)
91 #:use-module (gnu packages tls)
92 #:use-module (gnu packages vim)
93 #:use-module (gnu packages web)
94 #:use-module (gnu packages xml)
95 #:use-module (gnu packages xorg)
96 #:use-module (gnu packages zip)
97 #:use-module (srfi srfi-1))
106 (uri (cran-uri "ape" version))
109 "0959fiiy11rzfzrzaknmgrx64bhszj02l0ycz79k5a6bmpfzanlk"))))
110 (build-system r-build-system)
112 `(("r-lattice" ,r-lattice)
114 (home-page "http://ape-package.ird.fr/")
115 (synopsis "Analyses of phylogenetics and evolution")
117 "This package provides functions for reading, writing, plotting, and
118 manipulating phylogenetic trees, analyses of comparative data in a
119 phylogenetic framework, ancestral character analyses, analyses of
120 diversification and macroevolution, computing distances from DNA sequences,
121 and several other tools.")
122 (license license:gpl2+)))
124 (define-public aragorn
131 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
135 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
136 (build-system gnu-build-system)
138 `(#:tests? #f ; there are no tests
140 (modify-phases %standard-phases
144 (zero? (system* "gcc"
150 (string-append "aragorn" ,version ".c")))))
152 (lambda* (#:key outputs #:allow-other-keys)
153 (let* ((out (assoc-ref outputs "out"))
154 (bin (string-append out "/bin"))
155 (man (string-append out "/share/man/man1")))
157 (install-file "aragorn" bin)
159 (install-file "aragorn.1" man))
161 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
162 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
164 "Aragorn identifies transfer RNA, mitochondrial RNA and
165 transfer-messenger RNA from nucleotide sequences, based on homology to known
166 tRNA consensus sequences and RNA structure. It also outputs the secondary
167 structure of the predicted RNA.")
168 (license license:gpl2)))
176 ;; BamM is not available on pypi.
178 "https://github.com/Ecogenomics/BamM/archive/"
180 (file-name (string-append name "-" version ".tar.gz"))
183 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
184 (modules '((guix build utils)))
187 ;; Delete bundled htslib.
188 (delete-file-recursively "c/htslib-1.3.1")
190 (build-system python-build-system)
192 `(#:python ,python-2 ; BamM is Python 2 only.
193 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
194 ;; been modified from its original form.
196 (let ((htslib (assoc-ref %build-inputs "htslib")))
197 (list "--with-libhts-lib" (string-append htslib "/lib")
198 "--with-libhts-inc" (string-append htslib "/include/htslib")))
200 (modify-phases %standard-phases
201 (add-after 'unpack 'autogen
203 (with-directory-excursion "c"
204 (let ((sh (which "sh")))
205 ;; Use autogen so that 'configure' works.
206 (substitute* "autogen.sh" (("/bin/sh") sh))
207 (setenv "CONFIG_SHELL" sh)
208 (substitute* "configure" (("/bin/sh") sh))
209 (zero? (system* "./autogen.sh"))))))
211 ;; Run tests after installation so compilation only happens once.
213 (add-after 'install 'wrap-executable
214 (lambda* (#:key outputs #:allow-other-keys)
215 (let* ((out (assoc-ref outputs "out"))
216 (path (getenv "PATH")))
217 (wrap-program (string-append out "/bin/bamm")
218 `("PATH" ":" prefix (,path))))
220 (add-after 'wrap-executable 'post-install-check
221 (lambda* (#:key inputs outputs #:allow-other-keys)
223 (string-append (assoc-ref outputs "out")
228 (assoc-ref outputs "out")
230 (string-take (string-take-right
231 (assoc-ref inputs "python") 5) 3)
233 (getenv "PYTHONPATH")))
234 ;; There are 2 errors printed, but they are safe to ignore:
235 ;; 1) [E::hts_open_format] fail to open file ...
236 ;; 2) samtools view: failed to open ...
237 (zero? (system* "nosetests")))))))
239 `(("autoconf" ,autoconf)
240 ("automake" ,automake)
243 ("python-nose" ,python2-nose)
244 ("python-pysam" ,python2-pysam)))
247 ("samtools" ,samtools)
251 ("coreutils" ,coreutils)))
253 `(("python-numpy" ,python2-numpy)))
254 (home-page "http://ecogenomics.github.io/BamM/")
255 (synopsis "Metagenomics-focused BAM file manipulator")
257 "BamM is a C library, wrapped in python, to efficiently generate and
258 parse BAM files, specifically for the analysis of metagenomic data. For
259 instance, it implements several methods to assess contig-wise read coverage.")
260 (license license:lgpl3+)))
262 (define-public bamtools
269 "https://github.com/pezmaster31/bamtools/archive/v"
271 (file-name (string-append name "-" version ".tar.gz"))
274 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
275 (build-system cmake-build-system)
277 `(#:tests? #f ;no "check" target
279 (modify-phases %standard-phases
281 'configure 'set-ldflags
282 (lambda* (#:key outputs #:allow-other-keys)
286 (assoc-ref outputs "out") "/lib/bamtools")))))))
287 (inputs `(("zlib" ,zlib)))
288 (home-page "https://github.com/pezmaster31/bamtools")
289 (synopsis "C++ API and command-line toolkit for working with BAM data")
291 "BamTools provides both a C++ API and a command-line toolkit for handling
293 (license license:expat)))
295 (define-public bcftools
302 "https://github.com/samtools/bcftools/releases/download/"
303 version "/bcftools-" version ".tar.bz2"))
306 "095ry68vmz9q5s1scjsa698dhgyvgw5aicz24c19iwfbai07mhqj"))
307 (modules '((guix build utils)))
309 ;; Delete bundled htslib.
310 '(delete-file-recursively "htslib-1.3.1"))))
311 (build-system gnu-build-system)
313 `(#:test-target "test"
317 (string-append "prefix=" (assoc-ref %outputs "out"))
318 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
319 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.a")
320 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
321 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix"))
323 (modify-phases %standard-phases
324 (add-after 'unpack 'patch-Makefile
326 (substitute* "Makefile"
327 ;; Do not attempt to build htslib.
328 (("^include \\$\\(HTSDIR\\)/htslib\\.mk") "")
329 ;; Link against GSL cblas.
330 (("-lcblas") "-lgslcblas"))
333 (add-before 'check 'patch-tests
335 (substitute* "test/test.pl"
336 (("/bin/bash") (which "bash")))
344 (home-page "https://samtools.github.io/bcftools/")
345 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
347 "BCFtools is a set of utilities that manipulate variant calls in the
348 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
349 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
350 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
351 (license (list license:gpl3+ license:expat))))
353 (define-public bedops
359 (uri (string-append "https://github.com/bedops/bedops/archive/v"
361 (file-name (string-append name "-" version ".tar.gz"))
364 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
365 (build-system gnu-build-system)
368 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
371 'unpack 'unpack-tarballs
373 ;; FIXME: Bedops includes tarballs of minimally patched upstream
374 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
375 ;; libraries because at least one of the libraries (zlib) is
376 ;; patched to add a C++ function definition (deflateInit2cpp).
377 ;; Until the Bedops developers offer a way to link against system
378 ;; libraries we have to build the in-tree copies of these three
381 ;; See upstream discussion:
382 ;; https://github.com/bedops/bedops/issues/124
384 ;; Unpack the tarballs to benefit from shebang patching.
385 (with-directory-excursion "third-party"
386 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
387 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
388 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
389 ;; Disable unpacking of tarballs in Makefile.
390 (substitute* "system.mk/Makefile.linux"
391 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
392 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
393 (substitute* "third-party/zlib-1.2.7/Makefile.in"
394 (("^SHELL=.*$") "SHELL=bash\n")))
395 (alist-delete 'configure %standard-phases))))
396 (home-page "https://github.com/bedops/bedops")
397 (synopsis "Tools for high-performance genomic feature operations")
399 "BEDOPS is a suite of tools to address common questions raised in genomic
400 studies---mostly with regard to overlap and proximity relationships between
401 data sets. It aims to be scalable and flexible, facilitating the efficient
402 and accurate analysis and management of large-scale genomic data.
404 BEDOPS provides tools that perform highly efficient and scalable Boolean and
405 other set operations, statistical calculations, archiving, conversion and
406 other management of genomic data of arbitrary scale. Tasks can be easily
407 split by chromosome for distributing whole-genome analyses across a
408 computational cluster.")
409 (license license:gpl2+)))
411 (define-public bedtools
417 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
419 (file-name (string-append name "-" version ".tar.gz"))
422 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
423 (build-system gnu-build-system)
424 (native-inputs `(("python" ,python-2)))
425 (inputs `(("samtools" ,samtools)
428 '(#:test-target "test"
430 (modify-phases %standard-phases
433 (lambda* (#:key outputs #:allow-other-keys)
434 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
435 (for-each (lambda (file)
436 (install-file file bin))
437 (find-files "bin" ".*")))
439 (home-page "https://github.com/arq5x/bedtools2")
440 (synopsis "Tools for genome analysis and arithmetic")
442 "Collectively, the bedtools utilities are a swiss-army knife of tools for
443 a wide-range of genomics analysis tasks. The most widely-used tools enable
444 genome arithmetic: that is, set theory on the genome. For example, bedtools
445 allows one to intersect, merge, count, complement, and shuffle genomic
446 intervals from multiple files in widely-used genomic file formats such as BAM,
448 (license license:gpl2)))
450 ;; Later releases of bedtools produce files with more columns than
451 ;; what Ribotaper expects.
452 (define-public bedtools-2.18
453 (package (inherit bedtools)
458 (uri (string-append "https://github.com/arq5x/bedtools2/"
459 "archive/v" version ".tar.gz"))
460 (file-name (string-append name "-" version ".tar.gz"))
463 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
465 (define-public ribotaper
471 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
472 "files/RiboTaper/RiboTaper_Version_"
476 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
477 (build-system gnu-build-system)
479 `(("bedtools" ,bedtools-2.18)
480 ("samtools" ,samtools-0.1)
481 ("r-minimal" ,r-minimal)
482 ("r-foreach" ,r-foreach)
483 ("r-xnomial" ,r-xnomial)
485 ("r-multitaper" ,r-multitaper)
486 ("r-seqinr" ,r-seqinr)))
487 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
488 (synopsis "Define translated ORFs using ribosome profiling data")
490 "Ribotaper is a method for defining translated @dfn{open reading
491 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
492 provides the Ribotaper pipeline.")
493 (license license:gpl3+)))
495 (define-public ribodiff
502 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
503 "archive/v" version ".tar.gz"))
504 (file-name (string-append name "-" version ".tar.gz"))
507 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
508 (build-system python-build-system)
512 (modify-phases %standard-phases
513 ;; Generate an installable executable script wrapper.
514 (add-after 'unpack 'patch-setup.py
516 (substitute* "setup.py"
517 (("^(.*)packages=.*" line prefix)
518 (string-append line "\n"
519 prefix "scripts=['scripts/TE.py'],\n")))
522 `(("python-numpy" ,python2-numpy)
523 ("python-matplotlib" ,python2-matplotlib)
524 ("python-scipy" ,python2-scipy)
525 ("python-statsmodels" ,python2-statsmodels)))
527 `(("python-mock" ,python2-mock)
528 ("python-nose" ,python2-nose)))
529 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
530 (synopsis "Detect translation efficiency changes from ribosome footprints")
531 (description "RiboDiff is a statistical tool that detects the protein
532 translational efficiency change from Ribo-Seq (ribosome footprinting) and
533 RNA-Seq data. It uses a generalized linear model to detect genes showing
534 difference in translational profile taking mRNA abundance into account. It
535 facilitates us to decipher the translational regulation that behave
536 independently with transcriptional regulation.")
537 (license license:gpl3+)))
539 (define-public bioawk
545 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
547 (file-name (string-append name "-" version ".tar.gz"))
549 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
550 (build-system gnu-build-system)
556 `(#:tests? #f ; There are no tests to run.
557 ;; Bison must generate files, before other targets can build.
560 (modify-phases %standard-phases
561 (delete 'configure) ; There is no configure phase.
563 (lambda* (#:key outputs #:allow-other-keys)
564 (let* ((out (assoc-ref outputs "out"))
565 (bin (string-append out "/bin"))
566 (man (string-append out "/share/man/man1")))
568 (copy-file "awk.1" (string-append man "/bioawk.1"))
569 (install-file "bioawk" bin)))))))
570 (home-page "https://github.com/lh3/bioawk")
571 (synopsis "AWK with bioinformatics extensions")
572 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
573 support of several common biological data formats, including optionally gzip'ed
574 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
575 also adds a few built-in functions and a command line option to use TAB as the
576 input/output delimiter. When the new functionality is not used, bioawk is
577 intended to behave exactly the same as the original BWK awk.")
578 (license license:x11)))
580 (define-public python2-pybedtools
582 (name "python2-pybedtools")
587 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
591 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
592 (build-system python-build-system)
593 (arguments `(#:python ,python-2)) ; no Python 3 support
595 `(("python-matplotlib" ,python2-matplotlib)))
597 `(("bedtools" ,bedtools)
598 ("samtools" ,samtools)))
600 `(("python-cython" ,python2-cython)
601 ("python-pyyaml" ,python2-pyyaml)
602 ("python-nose" ,python2-nose)))
603 (home-page "https://pythonhosted.org/pybedtools/")
604 (synopsis "Python wrapper for BEDtools programs")
606 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
607 which are widely used for genomic interval manipulation or \"genome algebra\".
608 pybedtools extends BEDTools by offering feature-level manipulations from with
610 (license license:gpl2+)))
612 (define-public python-biom-format
614 (name "python-biom-format")
619 ;; Use GitHub as source because PyPI distribution does not contain
620 ;; test data: https://github.com/biocore/biom-format/issues/693
621 (uri (string-append "https://github.com/biocore/biom-format/archive/"
623 (file-name (string-append name "-" version ".tar.gz"))
626 "1n25w3p1rixbpac8iysmzcja6m4ip5r6sz19l8y6wlwi49hxn278"))))
627 (build-system python-build-system)
629 `(("python-numpy" ,python-numpy)
630 ("python-scipy" ,python-scipy)
631 ("python-future" ,python-future)
632 ("python-click" ,python-click)
633 ("python-h5py" ,python-h5py)))
635 `(("python-nose" ,python-nose)))
636 (home-page "http://www.biom-format.org")
637 (synopsis "Biological Observation Matrix (BIOM) format utilities")
639 "The BIOM file format is designed to be a general-use format for
640 representing counts of observations e.g. operational taxonomic units, KEGG
641 orthology groups or lipid types, in one or more biological samples
642 e.g. microbiome samples, genomes, metagenomes.")
643 (license license:bsd-3)
644 (properties `((python2-variant . ,(delay python2-biom-format))))))
646 (define-public python2-biom-format
647 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
652 (modify-phases %standard-phases
653 ;; Do not require the unmaintained pyqi library.
654 (add-after 'unpack 'remove-pyqi
656 (substitute* "setup.py"
657 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
659 ,@(package-arguments base))))))
661 (define-public bioperl-minimal
662 (let* ((inputs `(("perl-module-build" ,perl-module-build)
663 ("perl-data-stag" ,perl-data-stag)
664 ("perl-libwww" ,perl-libwww)
665 ("perl-uri" ,perl-uri)))
667 (map (compose package-name cadr)
670 (map (compose package-transitive-target-inputs cadr) inputs))))))
672 (name "bioperl-minimal")
677 (uri (string-append "https://github.com/bioperl/bioperl-live/"
679 (string-map (lambda (c)
685 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
686 (build-system perl-build-system)
689 (modify-phases %standard-phases
691 'install 'wrap-programs
692 (lambda* (#:key outputs #:allow-other-keys)
693 ;; Make sure all executables in "bin" find the required Perl
694 ;; modules at runtime. As the PERL5LIB variable contains also
695 ;; the paths of native inputs, we pick the transitive target
696 ;; inputs from %build-inputs.
697 (let* ((out (assoc-ref outputs "out"))
698 (bin (string-append out "/bin/"))
700 (cons (string-append out "/lib/perl5/site_perl")
702 (assoc-ref %build-inputs name))
703 ',transitive-inputs))
705 (for-each (lambda (file)
707 `("PERL5LIB" ":" prefix (,path))))
708 (find-files bin "\\.pl$"))
712 `(("perl-test-most" ,perl-test-most)))
713 (home-page "http://search.cpan.org/dist/BioPerl")
714 (synopsis "Bioinformatics toolkit")
716 "BioPerl is the product of a community effort to produce Perl code which
717 is useful in biology. Examples include Sequence objects, Alignment objects
718 and database searching objects. These objects not only do what they are
719 advertised to do in the documentation, but they also interact - Alignment
720 objects are made from the Sequence objects, Sequence objects have access to
721 Annotation and SeqFeature objects and databases, Blast objects can be
722 converted to Alignment objects, and so on. This means that the objects
723 provide a coordinated and extensible framework to do computational biology.")
724 (license (package-license perl)))))
726 (define-public python-biopython
728 (name "python-biopython")
732 ;; use PyPi rather than biopython.org to ease updating
733 (uri (pypi-uri "biopython" version))
736 "07qc7nz0k77y8hf8s18rscvibvm91zw0kkq7ylrhisf8vp8hkp6i"))))
737 (build-system python-build-system)
740 (modify-phases %standard-phases
741 (add-before 'check 'set-home
742 ;; Some tests require a home directory to be set.
743 (lambda _ (setenv "HOME" "/tmp") #t)))))
745 `(("python-numpy" ,python-numpy)))
746 (home-page "http://biopython.org/")
747 (synopsis "Tools for biological computation in Python")
749 "Biopython is a set of tools for biological computation including parsers
750 for bioinformatics files into Python data structures; interfaces to common
751 bioinformatics programs; a standard sequence class and tools for performing
752 common operations on them; code to perform data classification; code for
753 dealing with alignments; code making it easy to split up parallelizable tasks
754 into separate processes; and more.")
755 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
757 (define-public python2-biopython
758 (package-with-python2 python-biopython))
760 ;; An outdated version of biopython is required for seqmagick, see
761 ;; https://github.com/fhcrc/seqmagick/issues/59
762 ;; When that issue has been resolved this package should be removed.
763 (define python2-biopython-1.66
765 (inherit python2-biopython)
769 (uri (pypi-uri "biopython" version))
772 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
774 (define-public bpp-core
775 ;; The last release was in 2014 and the recommended way to install from source
776 ;; is to clone the git repository, so we do this.
777 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
778 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
781 (version (string-append "2.2.0-1." (string-take commit 7)))
785 (url "http://biopp.univ-montp2.fr/git/bpp-core")
787 (file-name (string-append name "-" version "-checkout"))
790 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
791 (build-system cmake-build-system)
793 `(#:parallel-build? #f))
795 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
796 ; compile all of the bpp packages with GCC 5.
797 (home-page "http://biopp.univ-montp2.fr")
798 (synopsis "C++ libraries for Bioinformatics")
800 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
801 analysis, phylogenetics, molecular evolution and population genetics. It is
802 Object Oriented and is designed to be both easy to use and computer efficient.
803 Bio++ intends to help programmers to write computer expensive programs, by
804 providing them a set of re-usable tools.")
805 (license license:cecill-c))))
807 (define-public bpp-phyl
808 ;; The last release was in 2014 and the recommended way to install from source
809 ;; is to clone the git repository, so we do this.
810 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
811 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
814 (version (string-append "2.2.0-1." (string-take commit 7)))
818 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
820 (file-name (string-append name "-" version "-checkout"))
823 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
824 (build-system cmake-build-system)
826 `(#:parallel-build? #f
827 ;; If out-of-source, test data is not copied into the build directory
828 ;; so the tests fail.
829 #:out-of-source? #f))
831 `(("bpp-core" ,bpp-core)
833 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
836 (home-page "http://biopp.univ-montp2.fr")
837 (synopsis "Bio++ phylogenetic Library")
839 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
840 analysis, phylogenetics, molecular evolution and population genetics. This
841 library provides phylogenetics-related modules.")
842 (license license:cecill-c))))
844 (define-public bpp-popgen
845 ;; The last release was in 2014 and the recommended way to install from source
846 ;; is to clone the git repository, so we do this.
847 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
848 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
851 (version (string-append "2.2.0-1." (string-take commit 7)))
855 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
857 (file-name (string-append name "-" version "-checkout"))
860 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
861 (build-system cmake-build-system)
863 `(#:parallel-build? #f
864 #:tests? #f)) ; There are no tests.
866 `(("bpp-core" ,bpp-core)
869 (home-page "http://biopp.univ-montp2.fr")
870 (synopsis "Bio++ population genetics library")
872 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
873 analysis, phylogenetics, molecular evolution and population genetics. This
874 library provides population genetics-related modules.")
875 (license license:cecill-c))))
877 (define-public bpp-seq
878 ;; The last release was in 2014 and the recommended way to install from source
879 ;; is to clone the git repository, so we do this.
880 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
881 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
884 (version (string-append "2.2.0-1." (string-take commit 7)))
888 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
890 (file-name (string-append name "-" version "-checkout"))
893 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
894 (build-system cmake-build-system)
896 `(#:parallel-build? #f
897 ;; If out-of-source, test data is not copied into the build directory
898 ;; so the tests fail.
899 #:out-of-source? #f))
901 `(("bpp-core" ,bpp-core)
902 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
903 (home-page "http://biopp.univ-montp2.fr")
904 (synopsis "Bio++ sequence library")
906 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
907 analysis, phylogenetics, molecular evolution and population genetics. This
908 library provides sequence-related modules.")
909 (license license:cecill-c))))
911 (define-public bppsuite
912 ;; The last release was in 2014 and the recommended way to install from source
913 ;; is to clone the git repository, so we do this.
914 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
915 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
918 (version (string-append "2.2.0-1." (string-take commit 7)))
922 (url "http://biopp.univ-montp2.fr/git/bppsuite")
924 (file-name (string-append name "-" version "-checkout"))
927 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
928 (build-system cmake-build-system)
930 `(#:parallel-build? #f
931 #:tests? #f)) ; There are no tests.
935 ("texinfo" ,texinfo)))
937 `(("bpp-core" ,bpp-core)
939 ("bpp-phyl" ,bpp-phyl)
940 ("bpp-phyl" ,bpp-popgen)
942 (home-page "http://biopp.univ-montp2.fr")
943 (synopsis "Bioinformatics tools written with the Bio++ libraries")
945 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
946 analysis, phylogenetics, molecular evolution and population genetics. This
947 package provides command line tools using the Bio++ library.")
948 (license license:cecill-c))))
950 (define-public blast+
957 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
958 version "/ncbi-blast-" version "+-src.tar.gz"))
961 "14n9jik6vhiwjd3m7bach4xj1pzfn0szbsbyfxybd9l9cc43b6mb"))
962 (modules '((guix build utils)))
965 ;; Remove bundled bzip2 and zlib
966 (delete-file-recursively "c++/src/util/compress/bzip2")
967 (delete-file-recursively "c++/src/util/compress/zlib")
968 (substitute* "c++/src/util/compress/Makefile.in"
969 (("bzip2 zlib api") "api"))
970 ;; Remove useless msbuild directory
971 (delete-file-recursively
972 "c++/src/build-system/project_tree_builder/msbuild")
974 (build-system gnu-build-system)
976 `(;; There are three(!) tests for this massive library, and all fail with
977 ;; "unparsable timing stats".
978 ;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
979 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
980 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
983 #:parallel-build? #f ; not supported
985 (modify-phases %standard-phases
988 ;; $HOME needs to be set at some point during the configure phase
989 (lambda _ (setenv "HOME" "/tmp") #t))
992 (lambda _ (chdir "c++") #t))
994 'enter-dir 'fix-build-system
997 (cond ((string=? cmd "date")
998 ;; make call to "date" deterministic
1003 (format (current-error-port)
1004 "WARNING: Unable to find absolute path for ~s~%"
1008 ;; Rewrite hardcoded paths to various tools
1009 (substitute* (append '("src/build-system/configure.ac"
1010 "src/build-system/configure"
1011 "scripts/common/impl/if_diff.sh"
1012 "scripts/common/impl/run_with_lock.sh"
1013 "src/build-system/Makefile.configurables.real"
1014 "src/build-system/Makefile.in.top"
1015 "src/build-system/Makefile.meta.gmake=no"
1016 "src/build-system/Makefile.meta.in"
1017 "src/build-system/Makefile.meta_l"
1018 "src/build-system/Makefile.meta_p"
1019 "src/build-system/Makefile.meta_r"
1020 "src/build-system/Makefile.mk.in"
1021 "src/build-system/Makefile.requirements"
1022 "src/build-system/Makefile.rules_with_autodep.in")
1023 (find-files "scripts/common/check" "\\.sh$"))
1024 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1025 (or (which* cmd) all)))
1027 (substitute* (find-files "src/build-system" "^config.*")
1028 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1031 ;; rewrite "/var/tmp" in check script
1032 (substitute* "scripts/common/check/check_make_unix.sh"
1033 (("/var/tmp") "/tmp"))
1035 ;; do not reset PATH
1036 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1038 (("action=/bin/") "action=")
1039 (("export PATH") ":"))
1043 (lambda* (#:key inputs outputs #:allow-other-keys)
1044 (let ((out (assoc-ref outputs "out"))
1045 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1046 (include (string-append (assoc-ref outputs "include")
1047 "/include/ncbi-tools++")))
1048 ;; The 'configure' script doesn't recognize things like
1049 ;; '--enable-fast-install'.
1050 (zero? (system* "./configure.orig"
1051 (string-append "--with-build-root=" (getcwd) "/build")
1052 (string-append "--prefix=" out)
1053 (string-append "--libdir=" lib)
1054 (string-append "--includedir=" include)
1055 (string-append "--with-bz2="
1056 (assoc-ref inputs "bzip2"))
1057 (string-append "--with-z="
1058 (assoc-ref inputs "zlib"))
1059 ;; Each library is built twice by default, once
1060 ;; with "-static" in its name, and again
1063 "--with-dll"))))))))
1064 (outputs '("out" ; 19 MB
1072 (home-page "http://blast.ncbi.nlm.nih.gov")
1073 (synopsis "Basic local alignment search tool")
1075 "BLAST is a popular method of performing a DNA or protein sequence
1076 similarity search, using heuristics to produce results quickly. It also
1077 calculates an “expect value” that estimates how many matches would have
1078 occurred at a given score by chance, which can aid a user in judging how much
1079 confidence to have in an alignment.")
1080 ;; Most of the sources are in the public domain, with the following
1083 ;; * ./c++/include/util/bitset/
1084 ;; * ./c++/src/html/ncbi_menu*.js
1086 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1088 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1090 ;; * ./c++/src/corelib/teamcity_*
1091 (license (list license:public-domain
1097 (define-public bless
1103 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1107 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1108 (modules '((guix build utils)))
1111 ;; Remove bundled boost, pigz, zlib, and .git directory
1112 ;; FIXME: also remove bundled sources for murmurhash3 and
1113 ;; kmc once packaged.
1114 (delete-file-recursively "boost")
1115 (delete-file-recursively "pigz")
1116 (delete-file-recursively "google-sparsehash")
1117 (delete-file-recursively "zlib")
1118 (delete-file-recursively ".git")
1120 (build-system gnu-build-system)
1122 '(#:tests? #f ;no "check" target
1124 (list (string-append "ZLIB="
1125 (assoc-ref %build-inputs "zlib")
1127 (string-append "LDFLAGS="
1128 (string-join '("-lboost_filesystem"
1135 (modify-phases %standard-phases
1136 (add-after 'unpack 'do-not-build-bundled-pigz
1137 (lambda* (#:key inputs outputs #:allow-other-keys)
1138 (substitute* "Makefile"
1139 (("cd pigz/pigz-2.3.3; make") ""))
1141 (add-after 'unpack 'patch-paths-to-executables
1142 (lambda* (#:key inputs outputs #:allow-other-keys)
1143 (substitute* "parse_args.cpp"
1144 (("kmc_binary = .*")
1145 (string-append "kmc_binary = \""
1146 (assoc-ref outputs "out")
1148 (("pigz_binary = .*")
1149 (string-append "pigz_binary = \""
1150 (assoc-ref inputs "pigz")
1154 (lambda* (#:key outputs #:allow-other-keys)
1155 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1156 (for-each (lambda (file)
1157 (install-file file bin))
1158 '("bless" "kmc/bin/kmc"))
1160 (delete 'configure))))
1164 `(("openmpi" ,openmpi)
1166 ("sparsehash" ,sparsehash)
1169 (supported-systems '("x86_64-linux"))
1170 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1171 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1173 "@dfn{Bloom-filter-based error correction solution for high-throughput
1174 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1175 correction tool for genomic reads produced by @dfn{Next-generation
1176 sequencing} (NGS). BLESS produces accurate correction results with much less
1177 memory compared with previous solutions and is also able to tolerate a higher
1178 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1179 errors at the end of reads.")
1180 (license license:gpl3+)))
1182 (define-public bowtie
1188 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1190 (file-name (string-append name "-" version ".tar.gz"))
1193 "1vp5db8i7is57iwjybcdg18f5ivyzlj5g1ix1nlvxainzivhz55g"))
1194 (modules '((guix build utils)))
1196 '(substitute* "Makefile"
1197 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1198 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1199 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1200 (build-system gnu-build-system)
1201 (inputs `(("perl" ,perl)
1202 ("perl-clone" ,perl-clone)
1203 ("perl-test-deep" ,perl-test-deep)
1204 ("perl-test-simple" ,perl-test-simple)
1205 ("python" ,python-2)
1211 (string-append "prefix=" (assoc-ref %outputs "out")))
1217 (lambda* (#:key outputs #:allow-other-keys)
1219 "scripts/test/simple_tests.pl"
1220 "--bowtie2=./bowtie2"
1221 "--bowtie2-build=./bowtie2-build"))
1222 %standard-phases))))
1223 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1224 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1226 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1227 reads to long reference sequences. It is particularly good at aligning reads
1228 of about 50 up to 100s or 1,000s of characters, and particularly good at
1229 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1230 genome with an FM Index to keep its memory footprint small: for the human
1231 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1232 gapped, local, and paired-end alignment modes.")
1233 (supported-systems '("x86_64-linux"))
1234 (license license:gpl3+)))
1236 (define-public tophat
1243 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1247 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1248 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1249 (modules '((guix build utils)))
1252 ;; Remove bundled SeqAn and samtools
1253 (delete-file-recursively "src/SeqAn-1.3")
1254 (delete-file-recursively "src/samtools-0.1.18")
1256 (build-system gnu-build-system)
1258 '(#:parallel-build? #f ; not supported
1260 (modify-phases %standard-phases
1261 (add-after 'unpack 'use-system-samtools
1262 (lambda* (#:key inputs #:allow-other-keys)
1263 (substitute* "src/Makefile.in"
1264 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1265 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1266 (("SAMPROG = samtools_0\\.1\\.18") "")
1267 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1268 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1269 (substitute* '("src/common.cpp"
1271 (("samtools_0.1.18") (which "samtools")))
1272 (substitute* '("src/common.h"
1273 "src/bam2fastx.cpp")
1274 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1275 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1276 (substitute* '("src/bwt_map.h"
1278 "src/align_status.h")
1279 (("#include <bam.h>") "#include <samtools/bam.h>")
1280 (("#include <sam.h>") "#include <samtools/sam.h>"))
1285 ("samtools" ,samtools-0.1)
1286 ("ncurses" ,ncurses)
1287 ("python" ,python-2)
1291 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1292 (synopsis "Spliced read mapper for RNA-Seq data")
1294 "TopHat is a fast splice junction mapper for nucleotide sequence
1295 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1296 mammalian-sized genomes using the ultra high-throughput short read
1297 aligner Bowtie, and then analyzes the mapping results to identify
1298 splice junctions between exons.")
1299 ;; TopHat is released under the Boost Software License, Version 1.0
1300 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1301 (license license:boost1.0)))
1309 (uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
1310 version ".tar.bz2"))
1313 "1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
1314 (build-system gnu-build-system)
1316 '(#:tests? #f ;no "check" target
1320 (lambda* (#:key outputs #:allow-other-keys)
1321 (let ((bin (string-append
1322 (assoc-ref outputs "out") "/bin"))
1324 (assoc-ref outputs "out") "/share/doc/bwa"))
1326 (assoc-ref outputs "out") "/share/man/man1")))
1327 (install-file "bwa" bin)
1328 (install-file "README.md" doc)
1329 (install-file "bwa.1" man)))
1330 ;; no "configure" script
1331 (alist-delete 'configure %standard-phases))))
1332 (inputs `(("zlib" ,zlib)))
1333 ;; Non-portable SSE instructions are used so building fails on platforms
1334 ;; other than x86_64.
1335 (supported-systems '("x86_64-linux"))
1336 (home-page "http://bio-bwa.sourceforge.net/")
1337 (synopsis "Burrows-Wheeler sequence aligner")
1339 "BWA is a software package for mapping low-divergent sequences against a
1340 large reference genome, such as the human genome. It consists of three
1341 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1342 designed for Illumina sequence reads up to 100bp, while the rest two for
1343 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1344 features such as long-read support and split alignment, but BWA-MEM, which is
1345 the latest, is generally recommended for high-quality queries as it is faster
1346 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1347 70-100bp Illumina reads.")
1348 (license license:gpl3+)))
1350 (define-public bwa-pssm
1351 (package (inherit bwa)
1356 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1357 "archive/" version ".tar.gz"))
1358 (file-name (string-append name "-" version ".tar.gz"))
1361 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1362 (build-system gnu-build-system)
1367 (home-page "http://bwa-pssm.binf.ku.dk/")
1368 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1370 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1371 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1372 existing aligners it is fast and sensitive. Unlike most other aligners,
1373 however, it is also adaptible in the sense that one can direct the alignment
1374 based on known biases within the data set. It is coded as a modification of
1375 the original BWA alignment program and shares the genome index structure as
1376 well as many of the command line options.")
1377 (license license:gpl3+)))
1379 (define-public python2-bx-python
1381 (name "python2-bx-python")
1386 "https://pypi.python.org/packages/source/b/bx-python/bx-python-"
1390 "0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
1391 (modules '((guix build utils)))
1393 '(substitute* "setup.py"
1394 ;; remove dependency on outdated "distribute" module
1395 (("^from distribute_setup import use_setuptools") "")
1396 (("^use_setuptools\\(\\)") "")))))
1397 (build-system python-build-system)
1399 `(#:tests? #f ;tests fail because test data are not included
1400 #:python ,python-2))
1402 `(("python-numpy" ,python2-numpy)
1405 `(("python-nose" ,python2-nose)))
1406 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1407 (synopsis "Tools for manipulating biological data")
1409 "bx-python provides tools for manipulating biological data, particularly
1410 multiple sequence alignments.")
1411 (license license:expat)))
1413 (define-public python-pysam
1415 (name "python-pysam")
1419 ;; Test data is missing on PyPi.
1421 "https://github.com/pysam-developers/pysam/archive/v"
1423 (file-name (string-append name "-" version ".tar.gz"))
1426 "1mmvn91agr238kwz7226xq0i7k84lg2nxywn9712mzj7gvgqhfy8"))
1427 (modules '((guix build utils)))
1429 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1430 '(delete-file-recursively "htslib"))))
1431 (build-system python-build-system)
1433 `(#:modules ((ice-9 ftw)
1435 (guix build python-build-system)
1438 (modify-phases %standard-phases
1439 (add-before 'build 'set-flags
1440 (lambda* (#:key inputs #:allow-other-keys)
1441 (setenv "HTSLIB_MODE" "external")
1442 (setenv "HTSLIB_LIBRARY_DIR"
1443 (string-append (assoc-ref inputs "htslib") "/lib"))
1444 (setenv "HTSLIB_INCLUDE_DIR"
1445 (string-append (assoc-ref inputs "htslib") "/include"))
1446 (setenv "LDFLAGS" "-lncurses")
1447 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1450 (lambda* (#:key inputs outputs #:allow-other-keys)
1451 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1452 (setenv "PYTHONPATH"
1454 (getenv "PYTHONPATH")
1455 ":" (getcwd) "/build/"
1456 (car (scandir "build"
1457 (negate (cut string-prefix? "." <>))))))
1458 ;; Step out of source dir so python does not import from CWD.
1459 (with-directory-excursion "tests"
1460 (setenv "HOME" "/tmp")
1461 (and (zero? (system* "make" "-C" "pysam_data"))
1462 (zero? (system* "make" "-C" "cbcf_data"))
1463 (zero? (system* "nosetests" "-v"
1465 (number->string (parallel-job-count)))))))))))
1467 `(("htslib" ,htslib))) ; Included from installed header files.
1469 `(("ncurses" ,ncurses)
1472 `(("python-cython" ,python-cython)
1473 ;; Dependencies below are are for tests only.
1474 ("samtools" ,samtools)
1475 ("bcftools" ,bcftools)
1476 ("python-nose" ,python-nose)))
1477 (home-page "https://github.com/pysam-developers/pysam")
1478 (synopsis "Python bindings to the SAMtools C API")
1480 "Pysam is a Python module for reading and manipulating files in the
1481 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1482 also includes an interface for tabix.")
1483 (license license:expat)))
1485 (define-public python2-pysam
1486 (package-with-python2 python-pysam))
1488 (define-public python-twobitreader
1490 (name "python-twobitreader")
1494 (uri (pypi-uri "twobitreader" version))
1497 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1498 (build-system python-build-system)
1500 '(;; Tests are not distributed in the PyPi release.
1501 ;; TODO Try building from the Git repo or asking the upstream maintainer
1502 ;; to distribute the tests on PyPi.
1505 `(("python-sphinx" ,python-sphinx)))
1506 (home-page "https://github.com/benjschiller/twobitreader")
1507 (synopsis "Python library for reading .2bit files")
1509 "twobitreader is a Python library for reading .2bit files as used by the
1510 UCSC genome browser.")
1511 (license license:artistic2.0)))
1513 (define-public python2-twobitreader
1514 (package-with-python2 python-twobitreader))
1516 (define-public python-plastid
1518 (name "python-plastid")
1522 (uri (pypi-uri "plastid" version))
1525 "1sqkz5d3b9kf688mp7k771c87ins42j7j0whmkb49cb3fsg8s8lj"))))
1526 (build-system python-build-system)
1528 ;; Some test files are not included.
1531 `(("python-numpy" ,python-numpy)
1532 ("python-scipy" ,python-scipy)
1533 ("python-pandas" ,python-pandas)
1534 ("python-pysam" ,python-pysam)
1535 ("python-matplotlib" ,python-matplotlib)
1536 ("python-biopython" ,python-biopython)
1537 ("python-twobitreader" ,python-twobitreader)
1538 ("python-termcolor" ,python-termcolor)))
1540 `(("python-cython" ,python-cython)
1541 ("python-nose" ,python-nose)))
1542 (home-page "https://github.com/joshuagryphon/plastid")
1543 (synopsis "Python library for genomic analysis")
1545 "plastid is a Python library for genomic analysis – in particular,
1546 high-throughput sequencing data – with an emphasis on simplicity.")
1547 (license license:bsd-3)))
1549 (define-public python2-plastid
1550 (package-with-python2 python-plastid))
1552 (define-public cd-hit
1558 (uri (string-append "https://github.com/weizhongli/cdhit"
1559 "/releases/download/V" version
1560 "/cd-hit-v" version "-2016-0711.tar.gz"))
1563 "1w8hd4fszgg29nqiz569fldwy012la77nljcmlhglgicws56z54p"))))
1564 (build-system gnu-build-system)
1566 `(#:tests? #f ; there are no tests
1568 ;; Executables are copied directly to the PREFIX.
1569 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1571 (modify-phases %standard-phases
1572 ;; No "configure" script
1574 ;; Remove sources of non-determinism
1575 (add-after 'unpack 'be-timeless
1577 (substitute* "cdhit-utility.c++"
1578 ((" \\(built on \" __DATE__ \"\\)") ""))
1579 (substitute* "cdhit-common.c++"
1580 (("__DATE__") "\"0\"")
1581 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1583 ;; The "install" target does not create the target directory
1584 (add-before 'install 'create-target-dir
1585 (lambda* (#:key outputs #:allow-other-keys)
1586 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1590 (home-page "http://weizhongli-lab.org/cd-hit/")
1591 (synopsis "Cluster and compare protein or nucleotide sequences")
1593 "CD-HIT is a program for clustering and comparing protein or nucleotide
1594 sequences. CD-HIT is designed to be fast and handle extremely large
1596 ;; The manual says: "It can be copied under the GNU General Public License
1597 ;; version 2 (GPLv2)."
1598 (license license:gpl2)))
1600 (define-public clipper
1607 "https://github.com/YeoLab/clipper/archive/"
1609 (file-name (string-append name "-" version ".tar.gz"))
1612 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1613 (modules '((guix build utils)))
1616 ;; remove unnecessary setup dependency
1617 (substitute* "setup.py"
1618 (("setup_requires = .*") ""))
1619 (for-each delete-file
1620 '("clipper/src/peaks.so"
1621 "clipper/src/readsToWiggle.so"))
1622 (delete-file-recursively "dist/")
1624 (build-system python-build-system)
1625 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1628 ("python-pybedtools" ,python2-pybedtools)
1629 ("python-cython" ,python2-cython)
1630 ("python-scikit-learn" ,python2-scikit-learn)
1631 ("python-matplotlib" ,python2-matplotlib)
1632 ("python-pandas" ,python2-pandas)
1633 ("python-pysam" ,python2-pysam)
1634 ("python-numpy" ,python2-numpy)
1635 ("python-scipy" ,python2-scipy)))
1637 `(("python-mock" ,python2-mock) ; for tests
1638 ("python-nose" ,python2-nose) ; for tests
1639 ("python-pytz" ,python2-pytz))) ; for tests
1640 (home-page "https://github.com/YeoLab/clipper")
1641 (synopsis "CLIP peak enrichment recognition")
1643 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1644 (license license:gpl2)))
1646 (define-public codingquarry
1648 (name "codingquarry")
1653 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1657 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1658 (build-system gnu-build-system)
1660 '(#:tests? #f ; no "check" target
1662 (modify-phases %standard-phases
1665 (lambda* (#:key outputs #:allow-other-keys)
1666 (let* ((out (assoc-ref outputs "out"))
1667 (bin (string-append out "/bin"))
1668 (doc (string-append out "/share/doc/codingquarry")))
1669 (install-file "INSTRUCTIONS.pdf" doc)
1670 (copy-recursively "QuarryFiles"
1671 (string-append out "/QuarryFiles"))
1672 (install-file "CodingQuarry" bin)
1673 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1674 (inputs `(("openmpi" ,openmpi)))
1675 (native-search-paths
1676 (list (search-path-specification
1677 (variable "QUARRY_PATH")
1678 (files '("QuarryFiles")))))
1679 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1680 (synopsis "Fungal gene predictor")
1681 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1682 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1683 (home-page "https://sourceforge.net/projects/codingquarry/")
1684 (license license:gpl3+)))
1686 (define-public couger
1693 "http://couger.oit.duke.edu/static/assets/COUGER"
1697 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1698 (build-system gnu-build-system)
1702 (modify-phases %standard-phases
1707 (lambda* (#:key outputs #:allow-other-keys)
1708 (let* ((out (assoc-ref outputs "out"))
1709 (bin (string-append out "/bin")))
1710 (copy-recursively "src" (string-append out "/src"))
1712 ;; Add "src" directory to module lookup path.
1713 (substitute* "couger"
1715 (string-append "import sys\nsys.path.append(\""
1716 out "\")\nfrom argparse")))
1717 (install-file "couger" bin))
1720 'install 'wrap-program
1721 (lambda* (#:key inputs outputs #:allow-other-keys)
1722 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1723 (let* ((out (assoc-ref outputs "out"))
1724 (path (getenv "PYTHONPATH")))
1725 (wrap-program (string-append out "/bin/couger")
1726 `("PYTHONPATH" ":" prefix (,path))))
1729 `(("python" ,python-2)
1730 ("python2-pillow" ,python2-pillow)
1731 ("python2-numpy" ,python2-numpy)
1732 ("python2-scipy" ,python2-scipy)
1733 ("python2-matplotlib" ,python2-matplotlib)))
1735 `(("r-minimal" ,r-minimal)
1737 ("randomjungle" ,randomjungle)))
1739 `(("unzip" ,unzip)))
1740 (home-page "http://couger.oit.duke.edu")
1741 (synopsis "Identify co-factors in sets of genomic regions")
1743 "COUGER can be applied to any two sets of genomic regions bound by
1744 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1745 putative co-factors that provide specificity to each TF. The framework
1746 determines the genomic targets uniquely-bound by each TF, and identifies a
1747 small set of co-factors that best explain the in vivo binding differences
1748 between the two TFs.
1750 COUGER uses classification algorithms (support vector machines and random
1751 forests) with features that reflect the DNA binding specificities of putative
1752 co-factors. The features are generated either from high-throughput TF-DNA
1753 binding data (from protein binding microarray experiments), or from large
1754 collections of DNA motifs.")
1755 (license license:gpl3+)))
1757 (define-public clustal-omega
1759 (name "clustal-omega")
1764 "http://www.clustal.org/omega/clustal-omega-"
1768 "02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
1769 (build-system gnu-build-system)
1771 `(("argtable" ,argtable)))
1772 (home-page "http://www.clustal.org/omega/")
1773 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1775 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1776 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1777 of handling data-sets of hundreds of thousands of sequences in reasonable
1779 (license license:gpl2+)))
1781 (define-public crossmap
1787 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1791 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1792 ;; This patch has been sent upstream already and is available
1793 ;; for download from Sourceforge, but it has not been merged.
1794 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1795 (modules '((guix build utils)))
1796 ;; remove bundled copy of pysam
1798 '(delete-file-recursively "lib/pysam"))))
1799 (build-system python-build-system)
1801 `(#:python ,python-2
1805 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
1808 `(("python-numpy" ,python2-numpy)
1809 ("python-pysam" ,python2-pysam)
1812 `(("python-cython" ,python2-cython)
1813 ("python-nose" ,python2-nose)))
1814 (home-page "http://crossmap.sourceforge.net/")
1815 (synopsis "Convert genome coordinates between assemblies")
1817 "CrossMap is a program for conversion of genome coordinates or annotation
1818 files between different genome assemblies. It supports most commonly used
1819 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1820 (license license:gpl2+)))
1822 (define-public cufflinks
1828 (uri (string-append "http://cole-trapnell-lab.github.io/"
1829 "cufflinks/assets/downloads/cufflinks-"
1833 "1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
1834 (build-system gnu-build-system)
1838 ;; The includes for "eigen" are located in a subdirectory.
1839 (string-append "EIGEN_CPPFLAGS="
1840 "-I" (assoc-ref %build-inputs "eigen")
1842 ;; Cufflinks must be linked with various boost libraries.
1843 (string-append "LDFLAGS="
1844 (string-join '("-lboost_system"
1845 "-lboost_serialization"
1846 "-lboost_thread"))))
1848 (modify-phases %standard-phases
1849 (add-after 'unpack 'fix-search-for-bam
1851 (substitute* '("ax_bam.m4"
1854 (("<bam/sam\\.h>") "<samtools/sam.h>")
1855 (("<bam/bam\\.h>") "<samtools/bam.h>")
1856 (("<bam/version\\.hpp>") "<samtools/version.h>"))
1859 (list (string-append "--with-bam="
1860 (assoc-ref %build-inputs "samtools")))))
1863 ("samtools" ,samtools-0.1)
1866 ("python" ,python-2)
1868 (home-page "http://cole-trapnell-lab.github.io/cufflinks/")
1869 (synopsis "Transcriptome assembly and RNA-Seq expression analysis")
1871 "Cufflinks assembles RNA transcripts, estimates their abundances,
1872 and tests for differential expression and regulation in RNA-Seq
1873 samples. It accepts aligned RNA-Seq reads and assembles the
1874 alignments into a parsimonious set of transcripts. Cufflinks then
1875 estimates the relative abundances of these transcripts based on how
1876 many reads support each one, taking into account biases in library
1877 preparation protocols.")
1878 (license license:boost1.0)))
1880 (define-public cutadapt
1887 "https://github.com/marcelm/cutadapt/archive/v"
1889 (file-name (string-append name "-" version ".tar.gz"))
1892 "19smhh6444ikn4jlmyhvffw4m5aw7yg07rqsk7arg8dkwyga1i4v"))))
1893 (build-system python-build-system)
1896 (modify-phases %standard-phases
1897 ;; The tests must be run after installation.
1899 (add-after 'install 'check
1900 (lambda* (#:key inputs outputs #:allow-other-keys)
1901 (setenv "PYTHONPATH"
1903 (getenv "PYTHONPATH")
1904 ":" (assoc-ref outputs "out")
1906 (string-take (string-take-right
1907 (assoc-ref inputs "python") 5) 3)
1909 (zero? (system* "nosetests" "-P" "tests")))))))
1911 `(("python-xopen" ,python-xopen)))
1913 `(("python-cython" ,python-cython)
1914 ("python-nose" ,python-nose)))
1915 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1916 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1918 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1919 other types of unwanted sequence from high-throughput sequencing reads.")
1920 (license license:expat)))
1922 (define-public libbigwig
1928 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1929 "archive/" version ".tar.gz"))
1930 (file-name (string-append name "-" version ".tar.gz"))
1933 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1934 (build-system gnu-build-system)
1936 `(#:test-target "test"
1939 (string-append "prefix=" (assoc-ref %outputs "out")))
1941 (modify-phases %standard-phases
1943 (add-before 'check 'disable-curl-test
1945 (substitute* "Makefile"
1946 (("./test/testRemote.*") ""))
1948 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1949 ;; there has not yet been a release containing this change.
1950 (add-before 'install 'create-target-dirs
1951 (lambda* (#:key outputs #:allow-other-keys)
1952 (let ((out (assoc-ref outputs "out")))
1953 (mkdir-p (string-append out "/lib"))
1954 (mkdir-p (string-append out "/include"))
1960 `(("doxygen" ,doxygen)))
1961 (home-page "https://github.com/dpryan79/libBigWig")
1962 (synopsis "C library for handling bigWig files")
1964 "This package provides a C library for parsing local and remote BigWig
1966 (license license:expat)))
1968 (define-public python-pybigwig
1970 (name "python-pybigwig")
1974 (uri (pypi-uri "pyBigWig" version))
1977 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1978 (modules '((guix build utils)))
1981 ;; Delete bundled libBigWig sources
1982 (delete-file-recursively "libBigWig")))))
1983 (build-system python-build-system)
1986 (modify-phases %standard-phases
1987 (add-after 'unpack 'link-with-libBigWig
1988 (lambda* (#:key inputs #:allow-other-keys)
1989 (substitute* "setup.py"
1990 (("libs=\\[") "libs=[\"BigWig\", "))
1993 `(("libbigwig" ,libbigwig)
1996 (home-page "https://github.com/dpryan79/pyBigWig")
1997 (synopsis "Access bigWig files in Python using libBigWig")
1999 "This package provides Python bindings to the libBigWig library for
2000 accessing bigWig files.")
2001 (license license:expat)))
2003 (define-public python2-pybigwig
2004 (package-with-python2 python-pybigwig))
2006 (define-public python-dendropy
2008 (name "python-dendropy")
2013 (uri (pypi-uri "DendroPy" version))
2016 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
2017 (patches (search-patches "python-dendropy-fix-tests.patch"))))
2018 (build-system python-build-system)
2019 (home-page "http://packages.python.org/DendroPy/")
2020 (synopsis "Library for phylogenetics and phylogenetic computing")
2022 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2023 writing, simulation, processing and manipulation of phylogenetic
2024 trees (phylogenies) and characters.")
2025 (license license:bsd-3)
2026 (properties `((python2-variant . ,(delay python2-dendropy))))))
2028 (define-public python2-dendropy
2029 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
2033 `(#:python ,python-2
2035 (modify-phases %standard-phases
2037 ;; There is currently a test failure that only happens on some
2038 ;; systems, and only using "setup.py test"
2039 (lambda _ (zero? (system* "nosetests")))))))
2040 (native-inputs `(("python2-nose" ,python2-nose)
2041 ,@(package-native-inputs base))))))
2044 (define-public deeptools
2050 (uri (string-append "https://github.com/fidelram/deepTools/"
2051 "archive/" version ".tar.gz"))
2052 (file-name (string-append name "-" version ".tar.gz"))
2055 "1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
2056 (build-system python-build-system)
2058 `(#:python ,python-2))
2060 `(("python-scipy" ,python2-scipy)
2061 ("python-numpy" ,python2-numpy)
2062 ("python-numpydoc" ,python2-numpydoc)
2063 ("python-matplotlib" ,python2-matplotlib)
2064 ("python-bx-python" ,python2-bx-python)
2065 ("python-pysam" ,python2-pysam)
2066 ("python-pybigwig" ,python2-pybigwig)))
2068 `(("python-mock" ,python2-mock) ;for tests
2069 ("python-nose" ,python2-nose) ;for tests
2070 ("python-pytz" ,python2-pytz))) ;for tests
2071 (home-page "https://github.com/fidelram/deepTools")
2072 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2074 "DeepTools addresses the challenge of handling the large amounts of data
2075 that are now routinely generated from DNA sequencing centers. To do so,
2076 deepTools contains useful modules to process the mapped reads data to create
2077 coverage files in standard bedGraph and bigWig file formats. By doing so,
2078 deepTools allows the creation of normalized coverage files or the comparison
2079 between two files (for example, treatment and control). Finally, using such
2080 normalized and standardized files, multiple visualizations can be created to
2081 identify enrichments with functional annotations of the genome.")
2082 (license license:gpl3+)))
2084 (define-public diamond
2091 "https://github.com/bbuchfink/diamond/archive/v"
2093 (file-name (string-append name "-" version ".tar.gz"))
2096 "1zn7q8m41ayfnjvf9snrsnq00mm68alf9rhdadx5q1sk23lyvp2l"))))
2097 (build-system cmake-build-system)
2099 '(#:tests? #f ; no "check" target
2101 (modify-phases %standard-phases
2102 (add-after 'unpack 'remove-native-compilation
2104 (substitute* "CMakeLists.txt" (("-march=native") ""))
2108 (home-page "https://github.com/bbuchfink/diamond")
2109 (synopsis "Accelerated BLAST compatible local sequence aligner")
2111 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2112 translated DNA query sequences against a protein reference database (BLASTP
2113 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2114 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2115 data and settings.")
2116 ;; diamond fails to build on other platforms
2117 ;; https://github.com/bbuchfink/diamond/issues/18
2118 (supported-systems '("x86_64-linux"))
2119 (license (license:non-copyleft "file://src/COPYING"
2120 "See src/COPYING in the distribution."))))
2122 (define-public discrover
2129 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2131 (file-name (string-append name "-" version ".tar.gz"))
2134 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2135 (build-system cmake-build-system)
2137 `(#:tests? #f ; there are no tests
2139 (modify-phases %standard-phases
2140 (add-after 'unpack 'add-missing-includes
2142 (substitute* "src/executioninformation.hpp"
2143 (("#define EXECUTIONINFORMATION_HPP" line)
2144 (string-append line "\n#include <random>")))
2145 (substitute* "src/plasma/fasta.hpp"
2146 (("#define FASTA_HPP" line)
2147 (string-append line "\n#include <random>")))
2153 `(("texlive" ,texlive)
2154 ("imagemagick" ,imagemagick)))
2155 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2156 (synopsis "Discover discriminative nucleotide sequence motifs")
2157 (description "Discrover is a motif discovery method to find binding sites
2158 of nucleic acid binding proteins.")
2159 (license license:gpl3+)))
2161 (define-public eigensoft
2162 (let ((revision "1")
2163 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2166 (version (string-append "6.1.2-"
2168 (string-take commit 9)))
2173 (url "https://github.com/DReichLab/EIG.git")
2175 (file-name (string-append "eigensoft-" commit "-checkout"))
2178 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2179 (modules '((guix build utils)))
2180 ;; Remove pre-built binaries.
2182 (delete-file-recursively "bin")
2185 (build-system gnu-build-system)
2187 `(#:tests? #f ; There are no tests.
2188 #:make-flags '("CC=gcc")
2190 (modify-phases %standard-phases
2191 ;; There is no configure phase, but the Makefile is in a
2196 ;; The link flags are incomplete.
2197 (substitute* "Makefile"
2198 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2200 ;; The provided install target only copies executables to
2201 ;; the "bin" directory in the build root.
2202 (add-after 'install 'actually-install
2203 (lambda* (#:key outputs #:allow-other-keys)
2204 (let* ((out (assoc-ref outputs "out"))
2205 (bin (string-append out "/bin")))
2206 (for-each (lambda (file)
2207 (install-file file bin))
2208 (find-files "../bin" ".*"))
2213 ("openblas" ,openblas)
2215 ("gfortran" ,gfortran "lib")))
2216 (home-page "https://github.com/DReichLab/EIG")
2217 (synopsis "Tools for population genetics")
2218 (description "The EIGENSOFT package provides tools for population
2219 genetics and stratification correction. EIGENSOFT implements methods commonly
2220 used in population genetics analyses such as PCA, computation of Tracy-Widom
2221 statistics, and finding related individuals in structured populations. It
2222 comes with a built-in plotting script and supports multiple file formats and
2223 quantitative phenotypes.")
2224 ;; The license of the eigensoft tools is Expat, but since it's
2225 ;; linking with the GNU Scientific Library (GSL) the effective
2226 ;; license is the GPL.
2227 (license license:gpl3+))))
2229 (define-public edirect
2235 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2236 "versions/2016-05-03/edirect.tar.gz"))
2239 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2240 (build-system perl-build-system)
2242 `(#:tests? #f ;no "check" target
2244 (modify-phases %standard-phases
2248 (lambda* (#:key outputs #:allow-other-keys)
2249 (let ((target (string-append (assoc-ref outputs "out")
2252 (install-file "edirect.pl" target)
2255 'install 'wrap-program
2256 (lambda* (#:key inputs outputs #:allow-other-keys)
2257 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2258 (let* ((out (assoc-ref outputs "out"))
2259 (path (getenv "PERL5LIB")))
2260 (wrap-program (string-append out "/bin/edirect.pl")
2261 `("PERL5LIB" ":" prefix (,path)))))))))
2263 `(("perl-html-parser" ,perl-html-parser)
2264 ("perl-encode-locale" ,perl-encode-locale)
2265 ("perl-file-listing" ,perl-file-listing)
2266 ("perl-html-tagset" ,perl-html-tagset)
2267 ("perl-html-tree" ,perl-html-tree)
2268 ("perl-http-cookies" ,perl-http-cookies)
2269 ("perl-http-date" ,perl-http-date)
2270 ("perl-http-message" ,perl-http-message)
2271 ("perl-http-negotiate" ,perl-http-negotiate)
2272 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2273 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2274 ("perl-net-http" ,perl-net-http)
2275 ("perl-uri" ,perl-uri)
2276 ("perl-www-robotrules" ,perl-www-robotrules)
2278 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2279 (synopsis "Tools for accessing the NCBI's set of databases")
2281 "Entrez Direct (EDirect) is a method for accessing the National Center
2282 for Biotechnology Information's (NCBI) set of interconnected
2283 databases (publication, sequence, structure, gene, variation, expression,
2284 etc.) from a terminal. Functions take search terms from command-line
2285 arguments. Individual operations are combined to build multi-step queries.
2286 Record retrieval and formatting normally complete the process.
2288 EDirect also provides an argument-driven function that simplifies the
2289 extraction of data from document summaries or other results that are returned
2290 in structured XML format. This can eliminate the need for writing custom
2291 software to answer ad hoc questions.")
2292 (license license:public-domain)))
2294 (define-public exonerate
2303 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2304 "exonerate-" version ".tar.gz"))
2307 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2308 (build-system gnu-build-system)
2310 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2312 `(("pkg-config" ,pkg-config)))
2316 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2317 (synopsis "Generic tool for biological sequence alignment")
2319 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2320 the alignment of sequences using a many alignment models, either exhaustive
2321 dynamic programming or a variety of heuristics.")
2322 (license license:gpl3)))
2324 (define-public express
2332 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2333 version "/express-" version "-src.tgz"))
2336 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2337 (build-system cmake-build-system)
2339 `(#:tests? #f ;no "check" target
2342 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2343 (lambda* (#:key inputs #:allow-other-keys)
2344 (substitute* "CMakeLists.txt"
2345 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2346 "set(Boost_USE_STATIC_LIBS OFF)")
2347 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2348 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2349 (substitute* "src/CMakeLists.txt"
2350 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2351 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2356 ("bamtools" ,bamtools)
2357 ("protobuf" ,protobuf)
2359 (home-page "http://bio.math.berkeley.edu/eXpress")
2360 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2362 "eXpress is a streaming tool for quantifying the abundances of a set of
2363 target sequences from sampled subsequences. Example applications include
2364 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2365 analysis (from RNA-Seq), transcription factor binding quantification in
2366 ChIP-Seq, and analysis of metagenomic data.")
2367 (license license:artistic2.0)))
2369 (define-public express-beta-diversity
2371 (name "express-beta-diversity")
2377 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2379 (file-name (string-append name "-" version ".tar.gz"))
2382 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2383 (build-system gnu-build-system)
2386 (modify-phases %standard-phases
2388 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2390 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2392 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2394 (lambda* (#:key outputs #:allow-other-keys)
2395 (let ((bin (string-append (assoc-ref outputs "out")
2398 (install-file "scripts/convertToEBD.py" bin)
2399 (install-file "bin/ExpressBetaDiversity" bin)
2402 `(("python" ,python-2)))
2403 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2404 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2406 "Express Beta Diversity (EBD) calculates ecological beta diversity
2407 (dissimilarity) measures between biological communities. EBD implements a
2408 variety of diversity measures including those that make use of phylogenetic
2409 similarity of community members.")
2410 (license license:gpl3+)))
2412 (define-public fasttree
2419 "http://www.microbesonline.org/fasttree/FastTree-"
2423 "0ljvvw8i1als1wbfzvrf15c3ii2vw9db20a259g6pzg34xyyb97k"))))
2424 (build-system gnu-build-system)
2426 `(#:tests? #f ; no "check" target
2428 (modify-phases %standard-phases
2432 (lambda* (#:key source #:allow-other-keys)
2433 (and (zero? (system* "gcc"
2435 "-finline-functions"
2442 (zero? (system* "gcc"
2446 "-finline-functions"
2454 (lambda* (#:key outputs #:allow-other-keys)
2455 (let ((bin (string-append (assoc-ref outputs "out")
2458 (install-file "FastTree" bin)
2459 (install-file "FastTreeMP" bin)
2461 (home-page "http://www.microbesonline.org/fasttree")
2462 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2464 "FastTree can handle alignments with up to a million of sequences in a
2465 reasonable amount of time and memory. For large alignments, FastTree is
2466 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2467 (license license:gpl2+)))
2469 (define-public fastx-toolkit
2471 (name "fastx-toolkit")
2477 "https://github.com/agordon/fastx_toolkit/releases/download/"
2478 version "/fastx_toolkit-" version ".tar.bz2"))
2481 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2482 (build-system gnu-build-system)
2484 `(("libgtextutils" ,libgtextutils)))
2486 `(("pkg-config" ,pkg-config)))
2487 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2488 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2490 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2491 FASTA/FASTQ files preprocessing.
2493 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2494 containing multiple short-reads sequences. The main processing of such
2495 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2496 is sometimes more productive to preprocess the files before mapping the
2497 sequences to the genome---manipulating the sequences to produce better mapping
2498 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2499 (license license:agpl3+)))
2501 (define-public flexbar
2508 (string-append "mirror://sourceforge/flexbar/"
2509 version "/flexbar_v" version "_src.tgz"))
2512 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2513 (build-system cmake-build-system)
2515 `(#:configure-flags (list
2516 (string-append "-DFLEXBAR_BINARY_DIR="
2517 (assoc-ref %outputs "out")
2522 (lambda* (#:key outputs #:allow-other-keys)
2523 (setenv "PATH" (string-append
2524 (assoc-ref outputs "out") "/bin:"
2526 (chdir "../flexbar_v2.5_src/test")
2527 (zero? (system* "bash" "flexbar_validate.sh")))
2528 (alist-delete 'install %standard-phases))))
2533 `(("pkg-config" ,pkg-config)
2535 (home-page "http://flexbar.sourceforge.net")
2536 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2538 "Flexbar preprocesses high-throughput nucleotide sequencing data
2539 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2540 Moreover, trimming and filtering features are provided. Flexbar increases
2541 read mapping rates and improves genome and transcriptome assemblies. It
2542 supports next-generation sequencing data in fasta/q and csfasta/q format from
2543 Illumina, Roche 454, and the SOLiD platform.")
2544 (license license:gpl3)))
2546 (define-public fraggenescan
2548 (name "fraggenescan")
2554 (string-append "mirror://sourceforge/fraggenescan/"
2555 "FragGeneScan" version ".tar.gz"))
2557 (base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
2558 (build-system gnu-build-system)
2561 (modify-phases %standard-phases
2563 (add-before 'build 'patch-paths
2564 (lambda* (#:key outputs #:allow-other-keys)
2565 (let* ((out (string-append (assoc-ref outputs "out")))
2566 (share (string-append out "/share/fraggenescan/")))
2567 (substitute* "run_FragGeneScan.pl"
2569 (string-append "system(\"" (which "rm")))
2571 (string-append "system(\"" (which "mv")))
2572 ;; This script and other programs expect the training files
2573 ;; to be in the non-standard location bin/train/XXX. Change
2574 ;; this to be share/fraggenescan/train/XXX instead.
2575 (("^\\$train.file = \\$dir.*")
2576 (string-append "$train_file = \""
2578 "train/\".$FGS_train_file;")))
2579 (substitute* "run_hmm.c"
2580 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2581 (string-append " strcpy(train_dir, \"" share "/train/\");")))
2582 (substitute* "post_process.pl"
2583 (("^my \\$dir = substr.*")
2584 (string-append "my $dir = \"" share "\";"))))
2587 (lambda _ (and (zero? (system* "make" "clean"))
2588 (zero? (system* "make" "fgs")))))
2590 (lambda* (#:key outputs #:allow-other-keys)
2591 (let* ((out (string-append (assoc-ref outputs "out")))
2592 (bin (string-append out "/bin/"))
2593 (share (string-append out "/share/fraggenescan/train")))
2594 (install-file "run_FragGeneScan.pl" bin)
2595 (install-file "FragGeneScan" bin)
2596 (install-file "FGS_gff.py" bin)
2597 (install-file "post_process.pl" bin)
2598 (copy-recursively "train" share))))
2600 (add-after 'install 'post-install-check
2601 ;; In lieu of 'make check', run one of the examples and check the
2602 ;; output files gets created.
2603 (lambda* (#:key outputs #:allow-other-keys)
2604 (let* ((out (string-append (assoc-ref outputs "out")))
2605 (bin (string-append out "/bin/")))
2606 (and (zero? (system* (string-append bin "run_FragGeneScan.pl")
2607 "-genome=./example/NC_000913.fna"
2611 (file-exists? "test2.faa")
2612 (file-exists? "test2.ffn")
2613 (file-exists? "test2.gff")
2614 (file-exists? "test2.out"))))))))
2617 ("python" ,python-2))) ;not compatible with python 3.
2618 (home-page "https://sourceforge.net/projects/fraggenescan/")
2619 (synopsis "Finds potentially fragmented genes in short reads")
2621 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2622 short and error-prone DNA sequencing reads. It can also be applied to predict
2623 genes in incomplete assemblies or complete genomes.")
2624 ;; GPL3+ according to private correspondense with the authors.
2625 (license license:gpl3+)))
2627 (define-public fxtract
2628 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2636 "https://github.com/ctSkennerton/fxtract/archive/"
2638 (file-name (string-append "ctstennerton-util-"
2639 (string-take util-commit 7)
2643 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2644 (build-system gnu-build-system)
2646 `(#:make-flags (list
2647 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2649 #:test-target "fxtract_test"
2651 (modify-phases %standard-phases
2653 (add-before 'build 'copy-util
2654 (lambda* (#:key inputs #:allow-other-keys)
2656 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2658 ;; Do not use make install as this requires additional dependencies.
2660 (lambda* (#:key outputs #:allow-other-keys)
2661 (let* ((out (assoc-ref outputs "out"))
2662 (bin (string-append out"/bin")))
2663 (install-file "fxtract" bin)
2669 ;; ctskennerton-util is licensed under GPL2.
2670 `(("ctskennerton-util"
2674 (url "https://github.com/ctSkennerton/util.git")
2675 (commit util-commit)))
2676 (file-name (string-append
2677 "ctstennerton-util-" util-commit "-checkout"))
2680 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2681 (home-page "https://github.com/ctSkennerton/fxtract")
2682 (synopsis "Extract sequences from FASTA and FASTQ files")
2684 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2685 or FASTQ) file given a subsequence. It uses a simple substring search for
2686 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2687 lookups or multi-pattern searching as required. By default fxtract looks in
2688 the sequence of each record but can also be told to look in the header,
2689 comment or quality sections.")
2690 ;; 'util' requires SSE instructions.
2691 (supported-systems '("x86_64-linux"))
2692 (license license:expat))))
2701 "https://github.com/nboley/grit/archive/"
2703 (file-name (string-append name "-" version ".tar.gz"))
2706 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2707 (build-system python-build-system)
2709 `(#:python ,python-2
2712 'unpack 'generate-from-cython-sources
2713 (lambda* (#:key inputs outputs #:allow-other-keys)
2714 ;; Delete these C files to force fresh generation from pyx sources.
2715 (delete-file "grit/sparsify_support_fns.c")
2716 (delete-file "grit/call_peaks_support_fns.c")
2717 (substitute* "setup.py"
2718 (("Cython.Setup") "Cython.Build")
2719 ;; Add numpy include path to fix compilation
2721 (string-append "pyx\", ], include_dirs = ['"
2722 (assoc-ref inputs "python-numpy")
2723 "/lib/python2.7/site-packages/numpy/core/include/"
2727 `(("python-scipy" ,python2-scipy)
2728 ("python-numpy" ,python2-numpy)
2729 ("python-pysam" ,python2-pysam)
2730 ("python-networkx" ,python2-networkx)))
2732 `(("python-cython" ,python2-cython)))
2733 (home-page "http://grit-bio.org")
2734 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2736 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2737 full length transcript models. When none of these data sources are available,
2738 GRIT can be run by providing a candidate set of TES or TSS sites. In
2739 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2740 also be run in quantification mode, where it uses a provided GTF file and just
2741 estimates transcript expression.")
2742 (license license:gpl3+)))
2744 (define-public hisat
2751 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2752 version "-beta-source.zip"))
2755 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2756 (build-system gnu-build-system)
2758 `(#:tests? #f ;no check target
2759 #:make-flags '("allall"
2760 ;; Disable unsupported `popcnt' instructions on
2761 ;; architectures other than x86_64
2762 ,@(if (string-prefix? "x86_64"
2763 (or (%current-target-system)
2766 '("POPCNT_CAPABILITY=0")))
2769 'unpack 'patch-sources
2771 ;; XXX Cannot use snippet because zip files are not supported
2772 (substitute* "Makefile"
2773 (("^CC = .*$") "CC = gcc")
2774 (("^CPP = .*$") "CPP = g++")
2775 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2776 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2777 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2778 (substitute* '("hisat-build" "hisat-inspect")
2779 (("/usr/bin/env") (which "env"))))
2782 (lambda* (#:key outputs #:allow-other-keys)
2783 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2784 (for-each (lambda (file)
2785 (install-file file bin))
2788 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
2789 (alist-delete 'configure %standard-phases)))))
2791 `(("unzip" ,unzip)))
2796 ;; Non-portable SSE instructions are used so building fails on platforms
2797 ;; other than x86_64.
2798 (supported-systems '("x86_64-linux"))
2799 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2800 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2802 "HISAT is a fast and sensitive spliced alignment program for mapping
2803 RNA-seq reads. In addition to one global FM index that represents a whole
2804 genome, HISAT uses a large set of small FM indexes that collectively cover the
2805 whole genome. These small indexes (called local indexes) combined with
2806 several alignment strategies enable effective alignment of RNA-seq reads, in
2807 particular, reads spanning multiple exons.")
2808 (license license:gpl3+)))
2810 (define-public hisat2
2817 ;; FIXME: a better source URL is
2818 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2819 ;; "/downloads/hisat2-" version "-source.zip")
2820 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2821 ;; but it is currently unavailable.
2822 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2823 (file-name (string-append name "-" version ".tar.gz"))
2826 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2827 (build-system gnu-build-system)
2829 `(#:tests? #f ; no check target
2830 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2831 #:modules ((guix build gnu-build-system)
2835 (modify-phases %standard-phases
2836 (add-after 'unpack 'make-deterministic
2838 (substitute* "Makefile"
2843 (lambda* (#:key outputs #:allow-other-keys)
2844 (let* ((out (assoc-ref outputs "out"))
2845 (bin (string-append out "/bin/"))
2846 (doc (string-append out "/share/doc/hisat2/")))
2848 (cut install-file <> bin)
2850 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2852 (install-file "doc/manual.inc.html" doc))
2855 `(("unzip" ,unzip) ; needed for archive from ftp
2857 ("pandoc" ,ghc-pandoc))) ; for documentation
2858 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2859 (synopsis "Graph-based alignment of genomic sequencing reads")
2860 (description "HISAT2 is a fast and sensitive alignment program for mapping
2861 next-generation sequencing reads (both DNA and RNA) to a population of human
2862 genomes (as well as to a single reference genome). In addition to using one
2863 global @dfn{graph FM} (GFM) index that represents a population of human
2864 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2865 the whole genome. These small indexes, combined with several alignment
2866 strategies, enable rapid and accurate alignment of sequencing reads. This new
2867 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2868 ;; HISAT2 contains files from Bowtie2, which is released under
2869 ;; GPLv2 or later. The HISAT2 source files are released under
2871 (license license:gpl3+)))
2873 (define-public hmmer
2881 "http://eddylab.org/software/hmmer"
2882 (version-prefix version 1) "/"
2883 version "/hmmer-" version ".tar.gz"))
2886 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2887 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2888 (build-system gnu-build-system)
2889 (native-inputs `(("perl" ,perl)))
2890 (home-page "http://hmmer.org/")
2891 (synopsis "Biosequence analysis using profile hidden Markov models")
2893 "HMMER is used for searching sequence databases for homologs of protein
2894 sequences, and for making protein sequence alignments. It implements methods
2895 using probabilistic models called profile hidden Markov models (profile
2897 (license (list license:gpl3+
2898 ;; The bundled library 'easel' is distributed
2899 ;; under The Janelia Farm Software License.
2900 (license:non-copyleft
2901 "file://easel/LICENSE"
2902 "See easel/LICENSE in the distribution.")))))
2904 (define-public htseq
2911 "https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
2915 "1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
2916 (build-system python-build-system)
2917 (arguments `(#:python ,python-2)) ; only Python 2 is supported
2918 ;; Numpy needs to be propagated when htseq is used as a Python library.
2920 `(("python-numpy" ,python2-numpy)))
2922 `(("python-pysam" ,python2-pysam)))
2923 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2924 (synopsis "Analysing high-throughput sequencing data with Python")
2926 "HTSeq is a Python package that provides infrastructure to process data
2927 from high-throughput sequencing assays.")
2928 (license license:gpl3+)))
2930 (define-public java-htsjdk
2932 (name "java-htsjdk")
2937 "https://github.com/samtools/htsjdk/archive/"
2939 (file-name (string-append name "-" version ".tar.gz"))
2942 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2943 (modules '((guix build utils)))
2944 ;; remove build dependency on git
2945 (snippet '(substitute* "build.xml"
2946 (("failifexecutionfails=\"true\"")
2947 "failifexecutionfails=\"false\"")))))
2948 (build-system ant-build-system)
2950 `(#:tests? #f ; test require Internet access
2952 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2953 "/share/java/htsjdk/"))
2954 #:build-target "all"
2956 (modify-phases %standard-phases
2957 ;; The build phase also installs the jars
2958 (delete 'install))))
2959 (home-page "http://samtools.github.io/htsjdk/")
2960 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2962 "HTSJDK is an implementation of a unified Java library for accessing
2963 common file formats, such as SAM and VCF, used for high-throughput
2964 sequencing (HTS) data. There are also an number of useful utilities for
2965 manipulating HTS data.")
2966 (license license:expat)))
2968 (define-public htslib
2975 "https://github.com/samtools/htslib/releases/download/"
2976 version "/htslib-" version ".tar.bz2"))
2979 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))
2980 (build-system gnu-build-system)
2983 (modify-phases %standard-phases
2985 'unpack 'patch-tests
2987 (substitute* "test/test.pl"
2988 (("/bin/bash") (which "bash")))
2994 (home-page "http://www.htslib.org")
2995 (synopsis "C library for reading/writing high-throughput sequencing data")
2997 "HTSlib is a C library for reading/writing high-throughput sequencing
2998 data. It also provides the bgzip, htsfile, and tabix utilities.")
2999 ;; Files under cram/ are released under the modified BSD license;
3000 ;; the rest is released under the Expat license
3001 (license (list license:expat license:bsd-3))))
3010 "https://github.com/nboley/idr/archive/"
3012 (file-name (string-append name "-" version ".tar.gz"))
3015 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3016 (build-system python-build-system)
3018 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3020 `(("python-scipy" ,python-scipy)
3021 ("python-sympy" ,python-sympy)
3022 ("python-numpy" ,python-numpy)
3023 ("python-matplotlib" ,python-matplotlib)))
3025 `(("python-cython" ,python-cython)))
3026 (home-page "https://github.com/nboley/idr")
3027 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3029 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3030 to measure the reproducibility of findings identified from replicate
3031 experiments and provide highly stable thresholds based on reproducibility.")
3032 (license license:gpl3+)))
3034 (define-public jellyfish
3040 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3041 "releases/download/v" version
3042 "/jellyfish-" version ".tar.gz"))
3045 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3046 (build-system gnu-build-system)
3047 (outputs '("out" ;for library
3048 "ruby" ;for Ruby bindings
3049 "python")) ;for Python bindings
3052 (list (string-append "--enable-ruby-binding="
3053 (assoc-ref %outputs "ruby"))
3054 (string-append "--enable-python-binding="
3055 (assoc-ref %outputs "python")))
3057 (modify-phases %standard-phases
3058 (add-before 'check 'set-SHELL-variable
3060 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3062 (setenv "SHELL" (which "bash"))
3068 ("python" ,python-2)))
3069 (synopsis "Tool for fast counting of k-mers in DNA")
3071 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3072 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3073 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3074 is a command-line program that reads FASTA and multi-FASTA files containing
3075 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3076 translated into a human-readable text format using the @code{jellyfish dump}
3077 command, or queried for specific k-mers with @code{jellyfish query}.")
3078 (home-page "http://www.genome.umd.edu/jellyfish.html")
3079 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3080 (supported-systems '("x86_64-linux"))
3081 ;; The combined work is published under the GPLv3 or later. Individual
3082 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3083 (license (list license:gpl3+ license:expat))))
3085 (define-public khmer
3092 (uri (pypi-uri "khmer" version))
3095 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3096 (patches (search-patches "khmer-use-libraries.patch"))))
3097 (build-system python-build-system)
3100 (modify-phases %standard-phases
3101 (add-after 'unpack 'set-paths
3102 (lambda* (#:key inputs outputs #:allow-other-keys)
3103 ;; Delete bundled libraries.
3104 (delete-file-recursively "third-party/zlib")
3105 (delete-file-recursively "third-party/bzip2")
3106 ;; Replace bundled seqan.
3107 (let* ((seqan-all "third-party/seqan")
3108 (seqan-include (string-append
3109 seqan-all "/core/include")))
3110 (delete-file-recursively seqan-all)
3111 (copy-recursively (string-append (assoc-ref inputs "seqan")
3113 (string-append seqan-include "/seqan")))
3114 ;; We do not replace the bundled MurmurHash as the canonical
3115 ;; repository for this code 'SMHasher' is unsuitable for
3116 ;; providing a library. See
3117 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3119 (add-after 'unpack 'set-cc
3123 ;; It is simpler to test after installation.
3125 (add-after 'install 'post-install-check
3126 (lambda* (#:key inputs outputs #:allow-other-keys)
3127 (let ((out (assoc-ref outputs "out")))
3132 (assoc-ref outputs "out")
3134 (setenv "PYTHONPATH"
3136 (getenv "PYTHONPATH")
3140 (string-take (string-take-right
3141 (assoc-ref inputs "python") 5) 3)
3143 (with-directory-excursion "build"
3144 (zero? (system* "nosetests" "khmer" "--attr"
3145 "!known_failing")))))))))
3148 ("python-nose" ,python-nose)))
3152 ("python-screed" ,python-screed)
3153 ("python-bz2file" ,python-bz2file)
3154 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3155 ;; until the next version of khmer (likely 2.1) is released.
3157 (home-page "https://khmer.readthedocs.org/")
3158 (synopsis "K-mer counting, filtering and graph traversal library")
3159 (description "The khmer software is a set of command-line tools for
3160 working with DNA shotgun sequencing data from genomes, transcriptomes,
3161 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3162 sometimes better. Khmer can also identify and fix problems with shotgun
3164 ;; When building on i686, armhf and mips64el, we get the following error:
3165 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3166 (supported-systems '("x86_64-linux"))
3167 (license license:bsd-3)))
3172 (version "2.1.0.20151222")
3175 (uri (pypi-uri "MACS2" version))
3178 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3179 (build-system python-build-system)
3181 `(#:python ,python-2 ; only compatible with Python 2.7
3182 #:tests? #f)) ; no test target
3184 `(("python-numpy" ,python2-numpy)))
3185 (home-page "https://github.com/taoliu/MACS/")
3186 (synopsis "Model based analysis for ChIP-Seq data")
3188 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3189 identifying transcript factor binding sites named Model-based Analysis of
3190 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3191 the significance of enriched ChIP regions and it improves the spatial
3192 resolution of binding sites through combining the information of both
3193 sequencing tag position and orientation.")
3194 (license license:bsd-3)))
3196 (define-public mafft
3203 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3204 "-without-extensions-src.tgz"))
3205 (file-name (string-append name "-" version ".tgz"))
3208 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3209 (build-system gnu-build-system)
3211 `(#:tests? #f ; no automated tests, though there are tests in the read me
3212 #:make-flags (let ((out (assoc-ref %outputs "out")))
3213 (list (string-append "PREFIX=" out)
3214 (string-append "BINDIR="
3215 (string-append out "/bin"))))
3217 (modify-phases %standard-phases
3218 (add-after 'unpack 'enter-dir
3219 (lambda _ (chdir "core") #t))
3220 (add-after 'enter-dir 'patch-makefile
3222 ;; on advice from the MAFFT authors, there is no need to
3223 ;; distribute mafft-profile, mafft-distance, or
3224 ;; mafft-homologs.rb as they are too "specialised".
3225 (substitute* "Makefile"
3226 ;; remove mafft-homologs.rb from SCRIPTS
3227 (("^SCRIPTS = mafft mafft-homologs.rb")
3229 ;; remove mafft-homologs from MANPAGES
3230 (("^MANPAGES = mafft.1 mafft-homologs.1")
3231 "MANPAGES = mafft.1")
3232 ;; remove mafft-distance from PROGS
3233 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3234 "PROGS = dvtditr dndfast7 dndblast sextet5")
3235 ;; remove mafft-profile from PROGS
3236 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3237 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3238 (("^rm -f mafft-profile mafft-profile.exe") "#")
3239 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3240 ;; do not install MAN pages in libexec folder
3241 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3242 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3244 (add-after 'enter-dir 'patch-paths
3245 (lambda* (#:key inputs #:allow-other-keys)
3246 (substitute* '("pairash.c"
3248 (("perl") (which "perl"))
3249 (("([\"`| ])awk" _ prefix)
3250 (string-append prefix (which "awk")))
3251 (("grep") (which "grep")))
3254 (add-after 'install 'wrap-programs
3255 (lambda* (#:key outputs #:allow-other-keys)
3256 (let* ((out (assoc-ref outputs "out"))
3257 (bin (string-append out "/bin"))
3258 (path (string-append
3259 (assoc-ref %build-inputs "coreutils") "/bin:")))
3260 (for-each (lambda (file)
3262 `("PATH" ":" prefix (,path))))
3270 ("coreutils" ,coreutils)))
3271 (home-page "http://mafft.cbrc.jp/alignment/software/")
3272 (synopsis "Multiple sequence alignment program")
3274 "MAFFT offers a range of multiple alignment methods for nucleotide and
3275 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3276 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3278 (license (license:non-copyleft
3279 "http://mafft.cbrc.jp/alignment/software/license.txt"
3280 "BSD-3 with different formatting"))))
3289 "https://github.com/marbl/mash/archive/v"
3291 (file-name (string-append name "-" version ".tar.gz"))
3294 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3295 (modules '((guix build utils)))
3297 ;; Delete bundled kseq.
3298 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3299 '(delete-file "src/mash/kseq.h"))))
3300 (build-system gnu-build-system)
3302 `(#:tests? #f ; No tests.
3305 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3306 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3307 #:make-flags (list "CC=gcc")
3309 (modify-phases %standard-phases
3310 (add-after 'unpack 'fix-includes
3312 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3313 (("^#include \"kseq\\.h\"")
3314 "#include \"htslib/kseq.h\""))
3316 (add-before 'configure 'autoconf
3317 (lambda _ (zero? (system* "autoconf")))))))
3319 `(("autoconf" ,autoconf)
3320 ;; Capnproto and htslib are statically embedded in the final
3321 ;; application. Therefore we also list their licenses, below.
3322 ("capnproto" ,capnproto)
3323 ("htslib" ,htslib)))
3327 (supported-systems '("x86_64-linux"))
3328 (home-page "https://mash.readthedocs.io")
3329 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3330 (description "Mash is a fast sequence distance estimator that uses the
3331 MinHash algorithm and is designed to work with genomes and metagenomes in the
3332 form of assemblies or reads.")
3333 (license (list license:bsd-3 ; Mash
3334 license:expat ; HTSlib and capnproto
3335 license:public-domain ; MurmurHash 3
3336 license:cpl1.0)))) ; Open Bloom Filter
3338 (define-public metabat
3339 ;; We package from a git commit because compilation of the released version
3341 (let ((commit "cbdca756993e66ae57e50a27970595dda9cbde1b"))
3344 (version (string-append "0.32.4-1." (string-take commit 8)))
3349 (url "https://bitbucket.org/berkeleylab/metabat.git")
3351 (file-name (string-append name "-" version))
3354 "0byia8nsip6zvc4ha0qkxkxxyjf4x7jcvy48q2dvb0pzr989syzr"))
3355 (patches (search-patches "metabat-remove-compilation-date.patch"))))
3356 (build-system gnu-build-system)
3359 (modify-phases %standard-phases
3360 (add-after 'unpack 'fix-includes
3362 (substitute* "src/BamUtils.h"
3363 (("^#include \"bam/bam\\.h\"")
3364 "#include \"samtools/bam.h\"")
3365 (("^#include \"bam/sam\\.h\"")
3366 "#include \"samtools/sam.h\""))
3367 (substitute* "src/KseqReader.h"
3368 (("^#include \"bam/kseq\\.h\"")
3369 "#include \"htslib/kseq.h\""))
3371 (add-after 'unpack 'fix-scons
3372 (lambda* (#:key inputs #:allow-other-keys)
3373 (substitute* "SConstruct"
3374 (("^htslib_dir = 'samtools'")
3375 (string-append "hitslib_dir = '"
3376 (assoc-ref inputs "htslib")
3378 (("^samtools_dir = 'samtools'")
3379 (string-append "samtools_dir = '"
3380 (assoc-ref inputs "htslib")
3382 (("^findStaticOrShared\\('bam', hts_lib")
3383 (string-append "findStaticOrShared('bam', '"
3384 (assoc-ref inputs "samtools")
3386 ;; Do not distribute README.
3387 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3391 (lambda* (#:key inputs outputs #:allow-other-keys)
3392 (mkdir (assoc-ref outputs "out"))
3393 (zero? (system* "scons"
3396 (assoc-ref outputs "out"))
3399 (assoc-ref inputs "boost"))
3401 ;; Check and install are carried out during build phase.
3403 (delete 'install))))
3407 ("samtools" ,samtools)
3411 `(("scons" ,scons)))
3412 (home-page "https://bitbucket.org/berkeleylab/metabat")
3414 "Reconstruction of single genomes from complex microbial communities")
3416 "Grouping large genomic fragments assembled from shotgun metagenomic
3417 sequences to deconvolute complex microbial communities, or metagenome binning,
3418 enables the study of individual organisms and their interactions. MetaBAT is
3419 an automated metagenome binning software, which integrates empirical
3420 probabilistic distances of genome abundance and tetranucleotide frequency.")
3421 (license (license:non-copyleft "file://license.txt"
3422 "See license.txt in the distribution.")))))
3424 (define-public minced
3431 "https://github.com/ctSkennerton/minced/archive/"
3433 (file-name (string-append name "-" version ".tar.gz"))
3436 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3437 (build-system gnu-build-system)
3439 `(#:test-target "test"
3441 (modify-phases %standard-phases
3443 (add-before 'check 'fix-test
3445 ;; Fix test for latest version.
3446 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3447 (("minced:0.1.6") "minced:0.2.0"))
3449 (replace 'install ; No install target.
3450 (lambda* (#:key inputs outputs #:allow-other-keys)
3451 (let* ((out (assoc-ref outputs "out"))
3452 (bin (string-append out "/bin"))
3453 (wrapper (string-append bin "/minced")))
3454 ;; Minced comes with a wrapper script that tries to figure out where
3455 ;; it is located before running the JAR. Since these paths are known
3456 ;; to us, we build our own wrapper to avoid coreutils dependency.
3457 (install-file "minced.jar" bin)
3458 (with-output-to-file wrapper
3462 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3463 (assoc-ref inputs "jre") "/bin/java -jar "
3464 bin "/minced.jar \"$@\"\n"))))
3465 (chmod wrapper #o555)))))))
3467 `(("jdk" ,icedtea "jdk")))
3470 ("jre" ,icedtea "out")))
3471 (home-page "https://github.com/ctSkennerton/minced")
3472 (synopsis "Mining CRISPRs in Environmental Datasets")
3474 "MinCED is a program to find Clustered Regularly Interspaced Short
3475 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3476 unassembled metagenomic reads, but is mainly designed for full genomes and
3477 assembled metagenomic sequence.")
3478 (license license:gpl3+)))
3487 "https://pypi.python.org/packages/source/m/misopy/misopy-"
3491 "0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
3492 (modules '((guix build utils)))
3494 '(substitute* "setup.py"
3495 ;; Use setuptools, or else the executables are not
3497 (("distutils.core") "setuptools")
3498 ;; use "gcc" instead of "cc" for compilation
3500 "cc.set_executables(
3504 linker_so='gcc -shared'); defines")))))
3505 (build-system python-build-system)
3507 `(#:python ,python-2 ; only Python 2 is supported
3508 #:tests? #f)) ; no "test" target
3510 `(("samtools" ,samtools)
3511 ("python-numpy" ,python2-numpy)
3512 ("python-pysam" ,python2-pysam)
3513 ("python-scipy" ,python2-scipy)
3514 ("python-matplotlib" ,python2-matplotlib)))
3516 `(("python-mock" ,python2-mock) ;for tests
3517 ("python-pytz" ,python2-pytz))) ;for tests
3518 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3519 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3521 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3522 the expression level of alternatively spliced genes from RNA-Seq data, and
3523 identifies differentially regulated isoforms or exons across samples. By
3524 modeling the generative process by which reads are produced from isoforms in
3525 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3526 that a read originated from a particular isoform.")
3527 (license license:gpl2)))
3529 (define-public muscle
3532 (version "3.8.1551")
3534 (method url-fetch/tarbomb)
3536 "http://www.drive5.com/muscle/muscle_src_"
3540 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3541 (build-system gnu-build-system)
3543 `(#:make-flags (list "LDLIBS = -lm")
3545 (modify-phases %standard-phases
3548 ;; There are no tests, so just test if it runs.
3549 (lambda _ (zero? (system* "./muscle" "-version"))))
3551 (lambda* (#:key outputs #:allow-other-keys)
3552 (let* ((out (assoc-ref outputs "out"))
3553 (bin (string-append out "/bin")))
3554 (install-file "muscle" bin)))))))
3555 (home-page "http://www.drive5.com/muscle")
3556 (synopsis "Multiple sequence alignment program")
3558 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3559 program for nucleotide and protein sequences.")
3560 ;; License information found in 'muscle -h' and usage.cpp.
3561 (license license:public-domain)))
3563 (define-public newick-utils
3564 ;; There are no recent releases so we package from git.
3565 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3567 (name "newick-utils")
3568 (version (string-append "1.6-1." (string-take commit 8)))
3572 (url "https://github.com/tjunier/newick_utils.git")
3574 (file-name (string-append name "-" version "-checkout"))
3577 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3578 (build-system gnu-build-system)
3581 (modify-phases %standard-phases
3582 (add-after 'unpack 'autoconf
3583 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3585 ;; XXX: TODO: Enable Lua and Guile bindings.
3586 ;; https://github.com/tjunier/newick_utils/issues/13
3587 `(("libxml2" ,libxml2)
3591 `(("autoconf" ,autoconf)
3592 ("automake" ,automake)
3593 ("libtool" ,libtool)))
3594 (synopsis "Programs for working with newick format phylogenetic trees")
3596 "Newick-utils is a suite of utilities for processing phylogenetic trees
3597 in Newick format. Functions include re-rooting, extracting subtrees,
3598 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3599 (home-page "https://github.com/tjunier/newick_utils")
3600 (license license:bsd-3))))
3609 "https://github.com/wwood/OrfM/releases/download/v"
3610 version "/orfm-" version ".tar.gz"))
3613 "19hwp13n82isdvk16710l9m35cmzf0q3fsrcn3r8c5r67biiz39s"))))
3614 (build-system gnu-build-system)
3615 (inputs `(("zlib" ,zlib)))
3617 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3618 ("ruby-rspec" ,ruby-rspec)
3620 (synopsis "Simple and not slow open reading frame (ORF) caller")
3622 "An ORF caller finds stretches of DNA that, when translated, are not
3623 interrupted by stop codons. OrfM finds and prints these ORFs.")
3624 (home-page "https://github.com/wwood/OrfM")
3625 (license license:lgpl3+)))
3627 (define-public python2-pbcore
3629 (name "python2-pbcore")
3633 (uri (pypi-uri "pbcore" version))
3636 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3637 (build-system python-build-system)
3638 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3640 `(("python-cython" ,python2-cython)
3641 ("python-numpy" ,python2-numpy)
3642 ("python-pysam" ,python2-pysam)
3643 ("python-h5py" ,python2-h5py)))
3645 `(("python-nose" ,python2-nose)
3646 ("python-sphinx" ,python2-sphinx)
3647 ("python-pyxb" ,python2-pyxb)))
3648 (home-page "http://pacificbiosciences.github.io/pbcore/")
3649 (synopsis "Library for reading and writing PacBio data files")
3651 "The pbcore package provides Python APIs for interacting with PacBio data
3652 files and writing bioinformatics applications.")
3653 (license license:bsd-3)))
3655 (define-public python2-warpedlmm
3657 (name "python2-warpedlmm")
3663 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3667 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3668 (build-system python-build-system)
3670 `(#:python ,python-2)) ; requires Python 2.7
3672 `(("python-scipy" ,python2-scipy)
3673 ("python-numpy" ,python2-numpy)
3674 ("python-matplotlib" ,python2-matplotlib)
3675 ("python-fastlmm" ,python2-fastlmm)
3676 ("python-pandas" ,python2-pandas)
3677 ("python-pysnptools" ,python2-pysnptools)))
3679 `(("python-mock" ,python2-mock)
3680 ("python-nose" ,python2-nose)
3682 (home-page "https://github.com/PMBio/warpedLMM")
3683 (synopsis "Implementation of warped linear mixed models")
3685 "WarpedLMM is a Python implementation of the warped linear mixed model,
3686 which automatically learns an optimal warping function (or transformation) for
3687 the phenotype as it models the data.")
3688 (license license:asl2.0)))
3690 (define-public pbtranscript-tofu
3691 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3693 (name "pbtranscript-tofu")
3694 (version (string-append "2.2.3." (string-take commit 7)))
3698 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3700 (file-name (string-append name "-" version "-checkout"))
3703 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3704 (modules '((guix build utils)))
3707 ;; remove bundled Cython sources
3708 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3710 (build-system python-build-system)
3712 `(#:python ,python-2
3713 ;; FIXME: Tests fail with "No such file or directory:
3714 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3717 (modify-phases %standard-phases
3718 (add-after 'unpack 'enter-directory
3720 (chdir "pbtranscript-tofu/pbtranscript/")
3722 ;; With setuptools version 18.0 and later this setup.py hack causes
3723 ;; a build error, so we disable it.
3724 (add-after 'enter-directory 'patch-setuppy
3726 (substitute* "setup.py"
3727 (("if 'setuptools.extension' in sys.modules:")
3731 `(("python-numpy" ,python2-numpy)
3732 ("python-bx-python" ,python2-bx-python)
3733 ("python-networkx" ,python2-networkx)
3734 ("python-scipy" ,python2-scipy)
3735 ("python-pbcore" ,python2-pbcore)
3736 ("python-h5py" ,python2-h5py)))
3738 `(("python-cython" ,python2-cython)
3739 ("python-nose" ,python2-nose)))
3740 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3741 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3743 "pbtranscript-tofu contains scripts to analyze transcriptome data
3744 generated using the PacBio Iso-Seq protocol.")
3745 (license license:bsd-3))))
3747 (define-public prank
3754 "http://wasabiapp.org/download/prank/prank.source."
3758 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3759 (build-system gnu-build-system)
3762 (modify-phases %standard-phases
3763 (add-after 'unpack 'enter-src-dir
3767 (add-after 'unpack 'remove-m64-flag
3768 ;; Prank will build with the correct 'bit-ness' without this flag
3769 ;; and this allows building on 32-bit machines.
3770 (lambda _ (substitute* "src/Makefile"
3775 (lambda* (#:key outputs #:allow-other-keys)
3776 (let* ((out (assoc-ref outputs "out"))
3777 (bin (string-append out "/bin"))
3778 (man (string-append out "/share/man/man1"))
3779 (path (string-append
3780 (assoc-ref %build-inputs "mafft") "/bin:"
3781 (assoc-ref %build-inputs "exonerate") "/bin:"
3782 (assoc-ref %build-inputs "bppsuite") "/bin")))
3783 (install-file "prank" bin)
3784 (wrap-program (string-append bin "/prank")
3785 `("PATH" ":" prefix (,path)))
3786 (install-file "prank.1" man))
3790 ("exonerate" ,exonerate)
3791 ("bppsuite" ,bppsuite)))
3792 (home-page "http://wasabiapp.org/software/prank/")
3793 (synopsis "Probabilistic multiple sequence alignment program")
3795 "PRANK is a probabilistic multiple sequence alignment program for DNA,
3796 codon and amino-acid sequences. It is based on a novel algorithm that treats
3797 insertions correctly and avoids over-estimation of the number of deletion
3798 events. In addition, PRANK borrows ideas from maximum likelihood methods used
3799 in phylogenetics and correctly takes into account the evolutionary distances
3800 between sequences. Lastly, PRANK allows for defining a potential structure
3801 for sequences to be aligned and then, simultaneously with the alignment,
3802 predicts the locations of structural units in the sequences.")
3803 (license license:gpl2+)))
3805 (define-public proteinortho
3807 (name "proteinortho")
3814 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
3815 version "_src.tar.gz"))
3818 "05wacnnbx56avpcwhzlcf6b7s77swcpv3qnwz5sh1z54i51gg2ki"))))
3819 (build-system gnu-build-system)
3821 `(#:test-target "test"
3823 (modify-phases %standard-phases
3825 ;; There is no configure script, so we modify the Makefile directly.
3826 (lambda* (#:key outputs #:allow-other-keys)
3827 (substitute* "Makefile"
3830 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
3832 (add-before 'install 'make-install-directory
3833 ;; The install directory is not created during 'make install'.
3834 (lambda* (#:key outputs #:allow-other-keys)
3835 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3837 (add-after 'install 'wrap-programs
3838 (lambda* (#:key inputs outputs #:allow-other-keys)
3839 (let* ((path (getenv "PATH"))
3840 (out (assoc-ref outputs "out"))
3841 (binary (string-append out "/bin/proteinortho5.pl")))
3842 (wrap-program binary `("PATH" ":" prefix (,path))))
3846 ("python" ,python-2)
3847 ("blast+" ,blast+)))
3848 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
3849 (synopsis "Detect orthologous genes across species")
3851 "Proteinortho is a tool to detect orthologous genes across different
3852 species. For doing so, it compares similarities of given gene sequences and
3853 clusters them to find significant groups. The algorithm was designed to handle
3854 large-scale data and can be applied to hundreds of species at once.")
3855 (license license:gpl2+)))
3857 (define-public pyicoteo
3864 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
3865 "pyicoteo/get/v" version ".tar.bz2"))
3866 (file-name (string-append name "-" version ".tar.bz2"))
3869 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
3870 (build-system python-build-system)
3872 `(#:python ,python-2 ; does not work with Python 3
3873 #:tests? #f)) ; there are no tests
3875 `(("python2-matplotlib" ,python2-matplotlib)))
3876 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
3877 (synopsis "Analyze high-throughput genetic sequencing data")
3879 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
3880 sequencing data. It works with genomic coordinates. There are currently six
3881 different command-line tools:
3884 @item pyicoregion: for generating exploratory regions automatically;
3885 @item pyicoenrich: for differential enrichment between two conditions;
3886 @item pyicoclip: for calling CLIP-Seq peaks without a control;
3887 @item pyicos: for genomic coordinates manipulation;
3888 @item pyicoller: for peak calling on punctuated ChIP-Seq;
3889 @item pyicount: to count how many reads from N experiment files overlap in a
3891 @item pyicotrocol: to combine operations from pyicoteo.
3893 (license license:gpl3+)))
3895 (define-public prodigal
3902 "https://github.com/hyattpd/Prodigal/archive/v"
3904 (file-name (string-append name "-" version ".tar.gz"))
3907 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
3908 (build-system gnu-build-system)
3910 `(#:tests? #f ;no check target
3911 #:make-flags (list (string-append "INSTALLDIR="
3912 (assoc-ref %outputs "out")
3915 (modify-phases %standard-phases
3916 (delete 'configure))))
3917 (home-page "http://prodigal.ornl.gov")
3918 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
3920 "Prodigal runs smoothly on finished genomes, draft genomes, and
3921 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
3922 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
3923 partial genes, and identifies translation initiation sites.")
3924 (license license:gpl3+)))
3926 (define-public roary
3934 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
3938 "0x2hpb3nfsc6x2nq1788w0fhqfzc7cn2dp4xwyva9m3k6xlz0m43"))))
3939 (build-system perl-build-system)
3942 (modify-phases %standard-phases
3947 ;; The tests are not run by default, so we run each test file
3949 (setenv "PATH" (string-append (getcwd) "/bin" ":"
3951 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
3952 (getenv "PERL5LIB")))
3953 (zero? (length (filter (lambda (file)
3954 (display file)(display "\n")
3955 (not (zero? (system* "perl" file))))
3956 (find-files "t" ".*\\.t$"))))))
3958 ;; There is no 'install' target in the Makefile.
3959 (lambda* (#:key outputs #:allow-other-keys)
3960 (let* ((out (assoc-ref outputs "out"))
3961 (bin (string-append out "/bin"))
3962 (perl (string-append out "/lib/perl5/site_perl"))
3963 (roary-plots "contrib/roary_plots"))
3966 (copy-recursively "bin" bin)
3967 (copy-recursively "lib" perl)
3969 (add-after 'install 'wrap-programs
3970 (lambda* (#:key inputs outputs #:allow-other-keys)
3971 (let* ((out (assoc-ref outputs "out"))
3972 (perl5lib (getenv "PERL5LIB"))
3973 (path (getenv "PATH")))
3974 (for-each (lambda (prog)
3975 (let ((binary (string-append out "/" prog)))
3976 (wrap-program binary
3977 `("PERL5LIB" ":" prefix
3978 (,(string-append perl5lib ":" out
3979 "/lib/perl5/site_perl"))))
3980 (wrap-program binary
3982 (,(string-append path ":" out "/bin"))))))
3983 (find-files "bin" ".*[^R]$"))
3985 (string-append out "/bin/roary-create_pan_genome_plots.R"))
3986 (r-site-lib (getenv "R_LIBS_SITE"))
3988 (string-append (assoc-ref inputs "coreutils") "/bin")))
3990 `("R_LIBS_SITE" ":" prefix
3991 (,(string-append r-site-lib ":" out "/site-library/"))))
3994 (,(string-append coreutils-path ":" out "/bin"))))))
3997 `(("perl-env-path" ,perl-env-path)
3998 ("perl-test-files" ,perl-test-files)
3999 ("perl-test-most" ,perl-test-most)
4000 ("perl-test-output" ,perl-test-output)))
4002 `(("perl-array-utils" ,perl-array-utils)
4003 ("bioperl" ,bioperl-minimal)
4004 ("perl-exception-class" ,perl-exception-class)
4005 ("perl-file-find-rule" ,perl-file-find-rule)
4006 ("perl-file-grep" ,perl-file-grep)
4007 ("perl-file-slurper" ,perl-file-slurper)
4008 ("perl-file-which" ,perl-file-which)
4009 ("perl-graph" ,perl-graph)
4010 ("perl-graph-readwrite" ,perl-graph-readwrite)
4011 ("perl-log-log4perl" ,perl-log-log4perl)
4012 ("perl-moose" ,perl-moose)
4013 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4014 ("perl-text-csv" ,perl-text-csv)
4015 ("bedtools" ,bedtools)
4019 ("parallel" ,parallel)
4022 ("fasttree" ,fasttree)
4026 ("r-minimal" ,r-minimal)
4027 ("r-ggplot2" ,r-ggplot2)
4028 ("coreutils" ,coreutils)))
4029 (home-page "http://sanger-pathogens.github.io/Roary")
4030 (synopsis "High speed stand-alone pan genome pipeline")
4032 "Roary is a high speed stand alone pan genome pipeline, which takes
4033 annotated assemblies in GFF3 format (produced by the Prokka program) and
4034 calculates the pan genome. Using a standard desktop PC, it can analyse
4035 datasets with thousands of samples, without compromising the quality of the
4036 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4037 single processor. Roary is not intended for metagenomics or for comparing
4038 extremely diverse sets of genomes.")
4039 (license license:gpl3)))
4041 (define-public raxml
4050 "https://github.com/stamatak/standard-RAxML/archive/v"
4052 (file-name (string-append name "-" version ".tar.gz"))
4055 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4056 (build-system gnu-build-system)
4058 `(#:tests? #f ; There are no tests.
4059 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4060 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4062 (modify-phases %standard-phases
4065 (lambda* (#:key outputs #:allow-other-keys)
4066 (let* ((out (assoc-ref outputs "out"))
4067 (bin (string-append out "/bin"))
4068 (executable "raxmlHPC-HYBRID"))
4069 (install-file executable bin)
4070 (symlink (string-append bin "/" executable) "raxml"))
4073 `(("openmpi" ,openmpi)))
4074 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4075 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4077 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4079 (license license:gpl2+)))
4089 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4092 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4093 (patches (search-patches "rsem-makefile.patch"))
4094 (modules '((guix build utils)))
4097 ;; remove bundled copy of boost
4098 (delete-file-recursively "boost")
4100 (build-system gnu-build-system)
4102 `(#:tests? #f ;no "check" target
4104 (modify-phases %standard-phases
4105 ;; No "configure" script.
4106 ;; Do not build bundled samtools library.
4109 (substitute* "Makefile"
4110 (("^all : sam/libbam.a") "all : "))
4113 (lambda* (#:key outputs #:allow-other-keys)
4114 (let* ((out (string-append (assoc-ref outputs "out")))
4115 (bin (string-append out "/bin/"))
4116 (perl (string-append out "/lib/perl5/site_perl")))
4119 (for-each (lambda (file)
4120 (install-file file bin))
4121 (find-files "." "rsem-.*"))
4122 (install-file "rsem_perl_utils.pm" perl))
4125 'install 'wrap-program
4126 (lambda* (#:key outputs #:allow-other-keys)
4127 (let ((out (assoc-ref outputs "out")))
4128 (for-each (lambda (prog)
4129 (wrap-program (string-append out "/bin/" prog)
4130 `("PERL5LIB" ":" prefix
4131 (,(string-append out "/lib/perl5/site_perl")))))
4132 '("rsem-plot-transcript-wiggles"
4133 "rsem-calculate-expression"
4134 "rsem-generate-ngvector"
4136 "rsem-prepare-reference")))
4140 ("ncurses" ,ncurses)
4141 ("r-minimal" ,r-minimal)
4143 ("samtools" ,samtools-0.1)
4145 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4146 (synopsis "Estimate gene expression levels from RNA-Seq data")
4148 "RSEM is a software package for estimating gene and isoform expression
4149 levels from RNA-Seq data. The RSEM package provides a user-friendly
4150 interface, supports threads for parallel computation of the EM algorithm,
4151 single-end and paired-end read data, quality scores, variable-length reads and
4152 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4153 interval estimates for expression levels. For visualization, it can generate
4154 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4155 (license license:gpl3+)))
4157 (define-public rseqc
4165 (string-append "mirror://sourceforge/rseqc/"
4166 "RSeQC-" version ".tar.gz"))
4168 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4169 (modules '((guix build utils)))
4172 ;; remove bundled copy of pysam
4173 (delete-file-recursively "lib/pysam")
4174 (substitute* "setup.py"
4175 ;; remove dependency on outdated "distribute" module
4176 (("^from distribute_setup import use_setuptools") "")
4177 (("^use_setuptools\\(\\)") "")
4178 ;; do not use bundled copy of pysam
4179 (("^have_pysam = False") "have_pysam = True"))))))
4180 (build-system python-build-system)
4181 (arguments `(#:python ,python-2))
4183 `(("python-cython" ,python2-cython)
4184 ("python-pysam" ,python2-pysam)
4185 ("python-numpy" ,python2-numpy)
4188 `(("python-nose" ,python2-nose)))
4189 (home-page "http://rseqc.sourceforge.net/")
4190 (synopsis "RNA-seq quality control package")
4192 "RSeQC provides a number of modules that can comprehensively evaluate
4193 high throughput sequence data, especially RNA-seq data. Some basic modules
4194 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4195 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4196 distribution, coverage uniformity, strand specificity, etc.")
4197 (license license:gpl3+)))
4200 ;; There are no release tarballs. According to the installation
4201 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4202 ;; stable release is identified by this changeset ID.
4203 (let ((changeset "2329130")
4207 (version (string-append "0-" revision "." changeset))
4211 (url "https://bitbucket.org/libsleipnir/sleipnir")
4212 (changeset changeset)))
4215 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4216 (build-system gnu-build-system)
4218 `(#:modules ((srfi srfi-1)
4219 (guix build gnu-build-system)
4222 (let ((dirs '("SeekMiner"
4228 (modify-phases %standard-phases
4229 (add-before 'configure 'bootstrap
4231 (zero? (system* "bash" "gen_auto"))))
4232 (add-after 'build 'build-additional-tools
4233 (lambda* (#:key make-flags #:allow-other-keys)
4234 (every (lambda (dir)
4235 (with-directory-excursion (string-append "tools/" dir)
4236 (zero? (apply system* "make" make-flags))))
4238 (add-after 'install 'install-additional-tools
4239 (lambda* (#:key make-flags #:allow-other-keys)
4240 (fold (lambda (dir result)
4241 (with-directory-excursion (string-append "tools/" dir)
4243 (zero? (apply system*
4244 `("make" ,@make-flags "install"))))))
4250 ("readline" ,readline)
4251 ("gengetopt" ,gengetopt)
4252 ("log4cpp" ,log4cpp)))
4254 `(("autoconf" ,autoconf)
4255 ("automake" ,automake)
4257 (home-page "http://seek.princeton.edu")
4258 (synopsis "Gene co-expression search engine")
4260 "SEEK is a computational gene co-expression search engine. SEEK provides
4261 biologists with a way to navigate the massive human expression compendium that
4262 now contains thousands of expression datasets. SEEK returns a robust ranking
4263 of co-expressed genes in the biological area of interest defined by the user's
4264 query genes. It also prioritizes thousands of expression datasets according
4265 to the user's query of interest.")
4266 (license license:cc-by3.0))))
4268 (define-public samtools
4276 (string-append "mirror://sourceforge/samtools/samtools/"
4277 version "/samtools-" version ".tar.bz2"))
4280 "0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
4281 (build-system gnu-build-system)
4283 `(#:modules ((ice-9 ftw)
4285 (guix build gnu-build-system)
4287 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4288 #:configure-flags (list "--with-ncurses")
4291 'unpack 'patch-tests
4293 (substitute* "test/test.pl"
4294 ;; The test script calls out to /bin/bash
4295 (("/bin/bash") (which "bash")))
4298 'install 'install-library
4299 (lambda* (#:key outputs #:allow-other-keys)
4300 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4301 (install-file "libbam.a" lib)
4304 'install 'install-headers
4305 (lambda* (#:key outputs #:allow-other-keys)
4306 (let ((include (string-append (assoc-ref outputs "out")
4307 "/include/samtools/")))
4308 (for-each (lambda (file)
4309 (install-file file include))
4310 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4312 %standard-phases)))))
4313 (native-inputs `(("pkg-config" ,pkg-config)))
4314 (inputs `(("ncurses" ,ncurses)
4318 (home-page "http://samtools.sourceforge.net")
4319 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4321 "Samtools implements various utilities for post-processing nucleotide
4322 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4323 variant calling (in conjunction with bcftools), and a simple alignment
4325 (license license:expat)))
4327 (define-public samtools-0.1
4328 ;; This is the most recent version of the 0.1 line of samtools. The input
4329 ;; and output formats differ greatly from that used and produced by samtools
4330 ;; 1.x and is still used in many bioinformatics pipelines.
4331 (package (inherit samtools)
4337 (string-append "mirror://sourceforge/samtools/samtools/"
4338 version "/samtools-" version ".tar.bz2"))
4340 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4342 `(#:tests? #f ;no "check" target
4343 ,@(substitute-keyword-arguments (package-arguments samtools)
4344 ((#:make-flags flags)
4345 `(cons "LIBCURSES=-lncurses" ,flags))
4347 `(modify-phases ,phases
4349 (lambda* (#:key outputs #:allow-other-keys)
4350 (let ((bin (string-append
4351 (assoc-ref outputs "out") "/bin")))
4353 (install-file "samtools" bin)
4355 (delete 'patch-tests)
4356 (delete 'configure))))))))
4358 (define-public mosaik
4359 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4364 ;; There are no release tarballs nor tags.
4367 (url "https://github.com/wanpinglee/MOSAIK.git")
4369 (file-name (string-append name "-" version))
4372 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4373 (build-system gnu-build-system)
4375 `(#:tests? #f ; no tests
4376 #:make-flags (list "CC=gcc")
4378 (modify-phases %standard-phases
4380 (lambda _ (chdir "src") #t))
4382 (lambda* (#:key outputs #:allow-other-keys)
4383 (let ((bin (string-append (assoc-ref outputs "out")
4386 (copy-recursively "../bin" bin)
4391 (supported-systems '("x86_64-linux"))
4392 (home-page "https://github.com/wanpinglee/MOSAIK")
4393 (synopsis "Map nucleotide sequence reads to reference genomes")
4395 "MOSAIK is a program for mapping second and third-generation sequencing
4396 reads to a reference genome. MOSAIK can align reads generated by all the
4397 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4398 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4399 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4400 ;; code released into the public domain:
4401 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4402 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4403 (license (list license:gpl2+ license:public-domain)))))
4405 (define-public ngs-sdk
4413 (string-append "https://github.com/ncbi/ngs/archive/"
4415 (file-name (string-append name "-" version ".tar.gz"))
4418 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4419 (build-system gnu-build-system)
4421 `(#:parallel-build? #f ; not supported
4422 #:tests? #f ; no "check" target
4426 (lambda* (#:key outputs #:allow-other-keys)
4427 (let ((out (assoc-ref outputs "out")))
4428 ;; The 'configure' script doesn't recognize things like
4429 ;; '--enable-fast-install'.
4430 (zero? (system* "./configure"
4431 (string-append "--build-prefix=" (getcwd) "/build")
4432 (string-append "--prefix=" out)))))
4435 (lambda _ (chdir "ngs-sdk") #t)
4436 %standard-phases))))
4437 (native-inputs `(("perl" ,perl)))
4438 ;; According to the test
4439 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4440 ;; in ngs-sdk/setup/konfigure.perl
4441 (supported-systems '("i686-linux" "x86_64-linux"))
4442 (home-page "https://github.com/ncbi/ngs")
4443 (synopsis "API for accessing Next Generation Sequencing data")
4445 "NGS is a domain-specific API for accessing reads, alignments and pileups
4446 produced from Next Generation Sequencing. The API itself is independent from
4447 any particular back-end implementation, and supports use of multiple back-ends
4449 (license license:public-domain)))
4451 (define-public java-ngs
4452 (package (inherit ngs-sdk)
4455 `(,@(substitute-keyword-arguments
4456 `(#:modules ((guix build gnu-build-system)
4460 ,@(package-arguments ngs-sdk))
4462 `(modify-phases ,phases
4463 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4465 `(("jdk" ,icedtea "jdk")
4466 ("ngs-sdk" ,ngs-sdk)))
4467 (synopsis "Java bindings for NGS SDK")))
4469 (define-public ncbi-vdb
4477 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4479 (file-name (string-append name "-" version ".tar.gz"))
4482 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4483 (build-system gnu-build-system)
4485 `(#:parallel-build? #f ; not supported
4486 #:tests? #f ; no "check" target
4488 (modify-phases %standard-phases
4490 (lambda* (#:key inputs outputs #:allow-other-keys)
4491 (let ((out (assoc-ref outputs "out")))
4492 ;; Override include path for libmagic
4493 (substitute* "setup/package.prl"
4494 (("name => 'magic', Include => '/usr/include'")
4495 (string-append "name=> 'magic', Include => '"
4496 (assoc-ref inputs "libmagic")
4499 ;; Install kdf5 library (needed by sra-tools)
4500 (substitute* "build/Makefile.install"
4501 (("LIBRARIES_TO_INSTALL =")
4502 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4504 (substitute* "build/Makefile.env"
4505 (("CFLAGS =" prefix)
4506 (string-append prefix "-msse2 ")))
4508 ;; Override search path for ngs-java
4509 (substitute* "setup/package.prl"
4510 (("/usr/local/ngs/ngs-java")
4511 (assoc-ref inputs "java-ngs")))
4513 ;; The 'configure' script doesn't recognize things like
4514 ;; '--enable-fast-install'.
4517 (string-append "--build-prefix=" (getcwd) "/build")
4518 (string-append "--prefix=" (assoc-ref outputs "out"))
4519 (string-append "--debug")
4520 (string-append "--with-xml2-prefix="
4521 (assoc-ref inputs "libxml2"))
4522 (string-append "--with-ngs-sdk-prefix="
4523 (assoc-ref inputs "ngs-sdk"))
4524 (string-append "--with-hdf5-prefix="
4525 (assoc-ref inputs "hdf5")))))))
4526 (add-after 'install 'install-interfaces
4527 (lambda* (#:key outputs #:allow-other-keys)
4528 ;; Install interface libraries. On i686 the interface libraries
4529 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4530 ;; architecture name ("i386") instead of the target system prefix
4532 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4533 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4534 ,(system->linux-architecture
4535 (or (%current-target-system)
4538 (string-append (assoc-ref outputs "out")
4540 ;; Install interface headers
4541 (copy-recursively "interfaces"
4542 (string-append (assoc-ref outputs "out")
4545 ;; These files are needed by sra-tools.
4546 (add-after 'install 'install-configuration-files
4547 (lambda* (#:key outputs #:allow-other-keys)
4548 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4550 (install-file "libs/kfg/default.kfg" target)
4551 (install-file "libs/kfg/certs.kfg" target))
4554 `(("libxml2" ,libxml2)
4555 ("ngs-sdk" ,ngs-sdk)
4556 ("java-ngs" ,java-ngs)
4559 (native-inputs `(("perl" ,perl)))
4560 ;; NCBI-VDB requires SSE capability.
4561 (supported-systems '("i686-linux" "x86_64-linux"))
4562 (home-page "https://github.com/ncbi/ncbi-vdb")
4563 (synopsis "Database engine for genetic information")
4565 "The NCBI-VDB library implements a highly compressed columnar data
4566 warehousing engine that is most often used to store genetic information.
4567 Databases are stored in a portable image within the file system, and can be
4568 accessed/downloaded on demand across HTTP.")
4569 (license license:public-domain)))
4571 (define-public plink
4579 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4580 version "-src.zip"))
4582 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4583 (patches (search-patches "plink-1.07-unclobber-i.patch"
4584 "plink-endian-detection.patch"))))
4585 (build-system gnu-build-system)
4587 '(#:tests? #f ;no "check" target
4588 #:make-flags (list (string-append "LIB_LAPACK="
4589 (assoc-ref %build-inputs "lapack")
4590 "/lib/liblapack.so")
4593 ;; disable phoning home
4596 (modify-phases %standard-phases
4597 ;; no "configure" script
4600 (lambda* (#:key outputs #:allow-other-keys)
4601 (let ((bin (string-append (assoc-ref outputs "out")
4603 (install-file "plink" bin)
4607 ("lapack" ,lapack)))
4609 `(("unzip" ,unzip)))
4610 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4611 (synopsis "Whole genome association analysis toolset")
4613 "PLINK is a whole genome association analysis toolset, designed to
4614 perform a range of basic, large-scale analyses in a computationally efficient
4615 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4616 so there is no support for steps prior to this (e.g. study design and
4617 planning, generating genotype or CNV calls from raw data). Through
4618 integration with gPLINK and Haploview, there is some support for the
4619 subsequent visualization, annotation and storage of results.")
4620 ;; Code is released under GPLv2, except for fisher.h, which is under
4622 (license (list license:gpl2 license:lgpl2.1+))))
4624 (define-public smithlab-cpp
4625 (let ((revision "1")
4626 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4628 (name "smithlab-cpp")
4629 (version (string-append "0." revision "." (string-take commit 7)))
4633 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4635 (file-name (string-append name "-" version "-checkout"))
4638 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4639 (build-system gnu-build-system)
4641 `(#:modules ((guix build gnu-build-system)
4644 #:tests? #f ;no "check" target
4646 (modify-phases %standard-phases
4647 (add-after 'unpack 'use-samtools-headers
4649 (substitute* '("SAM.cpp"
4651 (("sam.h") "samtools/sam.h"))
4654 (lambda* (#:key outputs #:allow-other-keys)
4655 (let* ((out (assoc-ref outputs "out"))
4656 (lib (string-append out "/lib"))
4657 (include (string-append out "/include/smithlab-cpp")))
4660 (for-each (cut install-file <> lib)
4661 (find-files "." "\\.o$"))
4662 (for-each (cut install-file <> include)
4663 (find-files "." "\\.hpp$")))
4665 (delete 'configure))))
4667 `(("samtools" ,samtools-0.1)
4669 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4670 (synopsis "C++ helper library for functions used in Smith lab projects")
4672 "Smithlab CPP is a C++ library that includes functions used in many of
4673 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4674 structures, classes for genomic regions, mapped sequencing reads, etc.")
4675 (license license:gpl3+))))
4677 (define-public preseq
4683 (uri (string-append "https://github.com/smithlabcode/"
4684 "preseq/archive/v" version ".tar.gz"))
4685 (file-name (string-append name "-" version ".tar.gz"))
4687 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4688 (modules '((guix build utils)))
4690 ;; Remove bundled samtools.
4691 '(delete-file-recursively "samtools"))))
4692 (build-system gnu-build-system)
4694 `(#:tests? #f ;no "check" target
4696 (modify-phases %standard-phases
4697 (delete 'configure))
4699 (list (string-append "PREFIX="
4700 (assoc-ref %outputs "out"))
4701 (string-append "LIBBAM="
4702 (assoc-ref %build-inputs "samtools")
4704 (string-append "SMITHLAB_CPP="
4705 (assoc-ref %build-inputs "smithlab-cpp")
4708 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4711 ("samtools" ,samtools-0.1)
4712 ("smithlab-cpp" ,smithlab-cpp)
4714 (home-page "http://smithlabresearch.org/software/preseq/")
4715 (synopsis "Program for analyzing library complexity")
4717 "The preseq package is aimed at predicting and estimating the complexity
4718 of a genomic sequencing library, equivalent to predicting and estimating the
4719 number of redundant reads from a given sequencing depth and how many will be
4720 expected from additional sequencing using an initial sequencing experiment.
4721 The estimates can then be used to examine the utility of further sequencing,
4722 optimize the sequencing depth, or to screen multiple libraries to avoid low
4723 complexity samples.")
4724 (license license:gpl3+)))
4726 (define-public python-screed
4728 (name "python-screed")
4733 (uri (pypi-uri "screed" version))
4736 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4737 (build-system python-build-system)
4740 (modify-phases %standard-phases
4743 (setenv "PYTHONPATH"
4744 (string-append (getenv "PYTHONPATH") ":."))
4745 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4747 `(("python-nose" ,python-nose)))
4749 `(("python-bz2file" ,python-bz2file)))
4750 (home-page "https://github.com/dib-lab/screed/")
4751 (synopsis "Short read sequence database utilities")
4752 (description "Screed parses FASTA and FASTQ files and generates databases.
4753 Values such as sequence name, sequence description, sequence quality and the
4754 sequence itself can be retrieved from these databases.")
4755 (license license:bsd-3)))
4757 (define-public python2-screed
4758 (package-with-python2 python-screed))
4760 (define-public sra-tools
4768 (string-append "https://github.com/ncbi/sra-tools/archive/"
4770 (file-name (string-append name "-" version ".tar.gz"))
4773 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
4774 (build-system gnu-build-system)
4776 `(#:parallel-build? #f ; not supported
4777 #:tests? #f ; no "check" target
4779 (list (string-append "DEFAULT_CRT="
4780 (assoc-ref %build-inputs "ncbi-vdb")
4782 (string-append "DEFAULT_KFG="
4783 (assoc-ref %build-inputs "ncbi-vdb")
4785 (string-append "VDB_LIBDIR="
4786 (assoc-ref %build-inputs "ncbi-vdb")
4787 ,(if (string-prefix? "x86_64"
4788 (or (%current-target-system)
4793 (modify-phases %standard-phases
4795 (lambda* (#:key inputs outputs #:allow-other-keys)
4796 ;; The build system expects a directory containing the sources and
4797 ;; raw build output of ncbi-vdb, including files that are not
4798 ;; installed. Since we are building against an installed version of
4799 ;; ncbi-vdb, the following modifications are needed.
4800 (substitute* "setup/konfigure.perl"
4801 ;; Make the configure script look for the "ilib" directory of
4802 ;; "ncbi-vdb" without first checking for the existence of a
4803 ;; matching library in its "lib" directory.
4804 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
4805 "my $f = File::Spec->catdir($ilibdir, $ilib);")
4806 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
4807 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
4808 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
4811 (substitute* "tools/copycat/Makefile"
4812 (("smagic-static") "lmagic"))
4814 ;; The 'configure' script doesn't recognize things like
4815 ;; '--enable-fast-install'.
4818 (string-append "--build-prefix=" (getcwd) "/build")
4819 (string-append "--prefix=" (assoc-ref outputs "out"))
4820 (string-append "--debug")
4821 (string-append "--with-fuse-prefix="
4822 (assoc-ref inputs "fuse"))
4823 (string-append "--with-magic-prefix="
4824 (assoc-ref inputs "libmagic"))
4825 ;; TODO: building with libxml2 fails with linker errors
4826 ;; (string-append "--with-xml2-prefix="
4827 ;; (assoc-ref inputs "libxml2"))
4828 (string-append "--with-ncbi-vdb-sources="
4829 (assoc-ref inputs "ncbi-vdb"))
4830 (string-append "--with-ncbi-vdb-build="
4831 (assoc-ref inputs "ncbi-vdb"))
4832 (string-append "--with-ngs-sdk-prefix="
4833 (assoc-ref inputs "ngs-sdk"))
4834 (string-append "--with-hdf5-prefix="
4835 (assoc-ref inputs "hdf5"))))))
4836 ;; This version of sra-tools fails to build with glibc because of a
4837 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
4838 ;; contains a definition of "canonicalize", so we rename it.
4840 ;; See upstream bug report:
4841 ;; https://github.com/ncbi/sra-tools/issues/67
4842 (add-after 'unpack 'patch-away-glibc-conflict
4844 (substitute* "tools/bam-loader/bam.c"
4845 (("canonicalize\\(" line)
4846 (string-append "sra_tools_" line)))
4848 (native-inputs `(("perl" ,perl)))
4850 `(("ngs-sdk" ,ngs-sdk)
4851 ("ncbi-vdb" ,ncbi-vdb)
4856 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
4857 (synopsis "Tools and libraries for reading and writing sequencing data")
4859 "The SRA Toolkit from NCBI is a collection of tools and libraries for
4860 reading of sequencing files from the Sequence Read Archive (SRA) database and
4861 writing files into the .sra format.")
4862 (license license:public-domain)))
4864 (define-public seqan
4870 (uri (string-append "http://packages.seqan.de/seqan-library/"
4871 "seqan-library-" version ".tar.bz2"))
4874 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
4875 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
4876 ;; makes sense to split the outputs.
4877 (outputs '("out" "doc"))
4878 (build-system trivial-build-system)
4880 `(#:modules ((guix build utils))
4883 (use-modules (guix build utils))
4884 (let ((tar (assoc-ref %build-inputs "tar"))
4885 (bzip (assoc-ref %build-inputs "bzip2"))
4886 (out (assoc-ref %outputs "out"))
4887 (doc (assoc-ref %outputs "doc")))
4888 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
4889 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
4890 (chdir (string-append "seqan-library-" ,version))
4891 (copy-recursively "include" (string-append out "/include"))
4892 (copy-recursively "share" (string-append doc "/share"))))))
4894 `(("source" ,source)
4897 (home-page "http://www.seqan.de")
4898 (synopsis "Library for nucleotide sequence analysis")
4900 "SeqAn is a C++ library of efficient algorithms and data structures for
4901 the analysis of sequences with the focus on biological data. It contains
4902 algorithms and data structures for string representation and their
4903 manipulation, online and indexed string search, efficient I/O of
4904 bioinformatics file formats, sequence alignment, and more.")
4905 (license license:bsd-3)))
4907 (define-public seqmagick
4915 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
4919 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
4920 (build-system python-build-system)
4922 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
4923 `(#:python ,python-2
4925 (modify-phases %standard-phases
4926 ;; Current test in setup.py does not work as of 0.6.1,
4927 ;; so use nose to run tests instead for now. See
4928 ;; https://github.com/fhcrc/seqmagick/issues/55
4929 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
4931 ;; biopython-1.66 is required due to
4932 ;; https://github.com/fhcrc/seqmagick/issues/59
4933 ;; When that issue is resolved the 'python2-biopython-1.66' package
4934 ;; should be removed.
4935 `(("python-biopython" ,python2-biopython-1.66)))
4937 `(("python-nose" ,python2-nose)))
4938 (home-page "https://github.com/fhcrc/seqmagick")
4939 (synopsis "Tools for converting and modifying sequence files")
4941 "Bioinformaticians often have to convert sequence files between formats
4942 and do little manipulations on them, and it's not worth writing scripts for
4943 that. Seqmagick is a utility to expose the file format conversion in
4944 BioPython in a convenient way. Instead of having a big mess of scripts, there
4945 is one that takes arguments.")
4946 (license license:gpl3)))
4948 (define-public seqtk
4955 "https://github.com/lh3/seqtk/archive/v"
4957 (file-name (string-append name "-" version ".tar.gz"))
4960 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
4961 (modules '((guix build utils)))
4964 ;; Remove extraneous header files, as is done in the seqtk
4966 (for-each (lambda (file) (delete-file file))
4967 (list "ksort.h" "kstring.h" "kvec.h"))
4969 (build-system gnu-build-system)
4972 (modify-phases %standard-phases
4975 ;; There are no tests, so we just run a sanity check.
4976 (lambda _ (zero? (system* "./seqtk" "seq"))))
4978 (lambda* (#:key outputs #:allow-other-keys)
4979 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
4980 (install-file "seqtk" bin)))))))
4983 (home-page "https://github.com/lh3/seqtk")
4984 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
4986 "Seqtk is a fast and lightweight tool for processing sequences in the
4987 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
4988 optionally compressed by gzip.")
4989 (license license:expat)))
4991 (define-public snap-aligner
4993 (name "snap-aligner")
4994 (version "1.0beta.18")
4998 "https://github.com/amplab/snap/archive/v"
5000 (file-name (string-append name "-" version ".tar.gz"))
5003 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5004 (build-system gnu-build-system)
5007 (modify-phases %standard-phases
5009 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5011 (lambda* (#:key outputs #:allow-other-keys)
5012 (let* ((out (assoc-ref outputs "out"))
5013 (bin (string-append out "/bin")))
5014 (install-file "snap-aligner" bin)
5015 (install-file "SNAPCommand" bin)
5019 (home-page "http://snap.cs.berkeley.edu/")
5020 (synopsis "Short read DNA sequence aligner")
5022 "SNAP is a fast and accurate aligner for short DNA reads. It is
5023 optimized for modern read lengths of 100 bases or higher, and takes advantage
5024 of these reads to align data quickly through a hash-based indexing scheme.")
5025 ;; 32-bit systems are not supported by the unpatched code.
5026 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5027 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5028 ;; systems without a lot of memory cannot make good use of this program.
5029 (supported-systems '("x86_64-linux"))
5030 (license license:asl2.0)))
5032 (define-public sortmerna
5040 "https://github.com/biocore/sortmerna/archive/"
5042 (file-name (string-append name "-" version ".tar.gz"))
5045 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5046 (build-system gnu-build-system)
5047 (outputs '("out" ;for binaries
5048 "db")) ;for sequence databases
5051 (modify-phases %standard-phases
5053 (lambda* (#:key outputs #:allow-other-keys)
5054 (let* ((out (assoc-ref outputs "out"))
5055 (bin (string-append out "/bin"))
5056 (db (assoc-ref outputs "db"))
5058 (string-append db "/share/sortmerna/rRNA_databases")))
5059 (install-file "sortmerna" bin)
5060 (install-file "indexdb_rna" bin)
5061 (for-each (lambda (file)
5062 (install-file file share))
5063 (find-files "rRNA_databases" ".*fasta"))
5067 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5068 (synopsis "Biological sequence analysis tool for NGS reads")
5070 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5071 and operational taxonomic unit (OTU) picking of next generation
5072 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5073 allows for fast and sensitive analyses of nucleotide sequences. The main
5074 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5075 (license license:lgpl3)))
5083 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5085 (file-name (string-append name "-" version ".tar.gz"))
5088 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5089 (modules '((guix build utils)))
5092 (substitute* "source/Makefile"
5094 ;; Remove pre-built binaries and bundled htslib sources.
5095 (delete-file-recursively "bin/MacOSX_x86_64")
5096 (delete-file-recursively "bin/Linux_x86_64")
5097 (delete-file-recursively "bin/Linux_x86_64_static")
5098 (delete-file-recursively "source/htslib")
5100 (build-system gnu-build-system)
5102 '(#:tests? #f ;no check target
5103 #:make-flags '("STAR")
5105 (modify-phases %standard-phases
5106 (add-after 'unpack 'enter-source-dir
5107 (lambda _ (chdir "source") #t))
5108 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5110 (substitute* "Makefile"
5111 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5113 (substitute* '("BAMfunctions.cpp"
5118 "bamRemoveDuplicates.cpp")
5119 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5120 (string-append "#include <" header ">")))
5121 (substitute* "IncludeDefine.h"
5122 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5123 (string-append "<" header ">")))
5126 (lambda* (#:key outputs #:allow-other-keys)
5127 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5128 (install-file "STAR" bin))
5130 (delete 'configure))))
5132 `(("vim" ,vim))) ; for xxd
5134 `(("htslib" ,htslib)
5136 (home-page "https://github.com/alexdobin/STAR")
5137 (synopsis "Universal RNA-seq aligner")
5139 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5140 based on a previously undescribed RNA-seq alignment algorithm that uses
5141 sequential maximum mappable seed search in uncompressed suffix arrays followed
5142 by seed clustering and stitching procedure. In addition to unbiased de novo
5143 detection of canonical junctions, STAR can discover non-canonical splices and
5144 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5146 ;; Only 64-bit systems are supported according to the README.
5147 (supported-systems '("x86_64-linux" "mips64el-linux"))
5148 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5149 (license license:gpl3+)))
5151 (define-public subread
5157 (uri (string-append "mirror://sourceforge/subread/subread-"
5158 version "/subread-" version "-source.tar.gz"))
5161 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5162 (build-system gnu-build-system)
5164 `(#:tests? #f ;no "check" target
5165 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5166 ;; optimizations by default, so we override these flags such that x86_64
5167 ;; flags are only added when the build target is an x86_64 system.
5169 (list (let ((system ,(or (%current-target-system)
5171 (flags '("-ggdb" "-fomit-frame-pointer"
5172 "-ffast-math" "-funroll-loops"
5173 "-fmessage-length=0"
5174 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5176 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5177 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5178 (if (string-prefix? "x86_64" system)
5179 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5180 (string-append "CCFLAGS=" (string-join flags))))
5181 "-f" "Makefile.Linux"
5182 "CC=gcc ${CCFLAGS}")
5186 (lambda _ (chdir "src") #t)
5189 (lambda* (#:key outputs #:allow-other-keys)
5190 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5192 (copy-recursively "../bin" bin)))
5193 ;; no "configure" script
5194 (alist-delete 'configure %standard-phases)))))
5195 (inputs `(("zlib" ,zlib)))
5196 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5197 (synopsis "Tool kit for processing next-gen sequencing data")
5199 "The subread package contains the following tools: subread aligner, a
5200 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5201 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5202 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5203 against local background noises.")
5204 (license license:gpl3+)))
5206 (define-public stringtie
5212 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5213 "stringtie-" version ".tar.gz"))
5216 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5217 (modules '((guix build utils)))
5220 (delete-file-recursively "samtools-0.1.18")
5222 (build-system gnu-build-system)
5224 `(#:tests? #f ;no test suite
5226 (modify-phases %standard-phases
5227 ;; no configure script
5229 (add-before 'build 'use-system-samtools
5231 (substitute* "Makefile"
5232 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5234 (substitute* '("gclib/GBam.h"
5236 (("#include \"(bam|sam|kstring).h\"" _ header)
5237 (string-append "#include <samtools/" header ".h>")))
5239 (add-after 'unpack 'remove-duplicate-typedef
5241 ;; This typedef conflicts with the typedef in
5242 ;; glibc-2.25/include/bits/types.h
5243 (substitute* "gclib/GThreads.h"
5244 (("typedef long long __intmax_t;") ""))
5247 (lambda* (#:key outputs #:allow-other-keys)
5248 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5249 (install-file "stringtie" bin)
5252 `(("samtools" ,samtools-0.1)
5254 (home-page "http://ccb.jhu.edu/software/stringtie/")
5255 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5257 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5258 alignments into potential transcripts. It uses a novel network flow algorithm
5259 as well as an optional de novo assembly step to assemble and quantitate
5260 full-length transcripts representing multiple splice variants for each gene
5261 locus. Its input can include not only the alignments of raw reads used by
5262 other transcript assemblers, but also alignments of longer sequences that have
5263 been assembled from those reads. To identify differentially expressed genes
5264 between experiments, StringTie's output can be processed either by the
5265 Cuffdiff or Ballgown programs.")
5266 (license license:artistic2.0)))
5268 (define-public vcftools
5275 "https://github.com/vcftools/vcftools/releases/download/v"
5276 version "/vcftools-" version ".tar.gz"))
5279 "10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
5280 (build-system gnu-build-system)
5282 `(#:tests? #f ; no "check" target
5284 "CFLAGS=-O2" ; override "-m64" flag
5285 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5286 (string-append "MANDIR=" (assoc-ref %outputs "out")
5287 "/share/man/man1"))))
5289 `(("pkg-config" ,pkg-config)))
5293 (home-page "https://vcftools.github.io/")
5294 (synopsis "Tools for working with VCF files")
5296 "VCFtools is a program package designed for working with VCF files, such
5297 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5298 provide easily accessible methods for working with complex genetic variation
5299 data in the form of VCF files.")
5300 ;; The license is declared as LGPLv3 in the README and
5301 ;; at https://vcftools.github.io/license.html
5302 (license license:lgpl3)))
5304 (define-public infernal
5310 (uri (string-append "http://eddylab.org/software/infernal/"
5311 "infernal-" version ".tar.gz"))
5314 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5315 (build-system gnu-build-system)
5317 `(("perl" ,perl))) ; for tests
5318 (home-page "http://eddylab.org/infernal/")
5319 (synopsis "Inference of RNA alignments")
5320 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5321 searching DNA sequence databases for RNA structure and sequence similarities.
5322 It is an implementation of a special case of profile stochastic context-free
5323 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5324 profile, but it scores a combination of sequence consensus and RNA secondary
5325 structure consensus, so in many cases, it is more capable of identifying RNA
5326 homologs that conserve their secondary structure more than their primary
5328 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5329 (supported-systems '("i686-linux" "x86_64-linux"))
5330 (license license:bsd-3)))
5332 (define-public r-centipede
5334 (name "r-centipede")
5338 (uri (string-append "http://download.r-forge.r-project.org/"
5339 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5342 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5343 (build-system r-build-system)
5344 (home-page "http://centipede.uchicago.edu/")
5345 (synopsis "Predict transcription factor binding sites")
5347 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5348 of the genome that are bound by particular transcription factors. It starts
5349 by identifying a set of candidate binding sites, and then aims to classify the
5350 sites according to whether each site is bound or not bound by a transcription
5351 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5352 between two different types of motif instances using as much relevant
5353 information as possible.")
5354 (license (list license:gpl2+ license:gpl3+))))
5356 (define-public r-vegan
5363 (uri (cran-uri "vegan" version))
5366 "15zcxfix2d854897k1lr0sfmj2n00339nlsppcr3zrb238lb2mi5"))))
5367 (build-system r-build-system)
5369 `(("gfortran" ,gfortran)
5370 ("r-knitr" ,r-knitr)))
5372 `(("r-cluster" ,r-cluster)
5373 ("r-lattice" ,r-lattice)
5376 ("r-permute" ,r-permute)))
5377 (home-page "https://cran.r-project.org/web/packages/vegan")
5378 (synopsis "Functions for community ecology")
5380 "The vegan package provides tools for descriptive community ecology. It
5381 has most basic functions of diversity analysis, community ordination and
5382 dissimilarity analysis. Most of its multivariate tools can be used for other
5383 data types as well.")
5384 (license license:gpl2+)))
5386 (define-public r-annotate
5393 (uri (bioconductor-uri "annotate" version))
5396 "0yymz8qxgnbybvfhqrgkd1hh9dhwxdii1yxkhr1zicjgb35xixxb"))))
5397 (build-system r-build-system)
5399 `(("r-annotationdbi" ,r-annotationdbi)
5400 ("r-biobase" ,r-biobase)
5401 ("r-biocgenerics" ,r-biocgenerics)
5403 ("r-rcurl" ,r-rcurl)
5405 ("r-xtable" ,r-xtable)))
5407 "http://bioconductor.org/packages/annotate")
5408 (synopsis "Annotation for microarrays")
5409 (description "This package provides R environments for the annotation of
5411 (license license:artistic2.0)))
5413 (define-public r-geneplotter
5415 (name "r-geneplotter")
5420 (uri (bioconductor-uri "geneplotter" version))
5423 "1p6yvxi243irhjxwm97hp73abhwampj0myyf8z00ij166674pc7h"))))
5424 (build-system r-build-system)
5426 `(("r-annotate" ,r-annotate)
5427 ("r-annotationdbi" ,r-annotationdbi)
5428 ("r-biobase" ,r-biobase)
5429 ("r-biocgenerics" ,r-biocgenerics)
5430 ("r-lattice" ,r-lattice)
5431 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5432 (home-page "http://bioconductor.org/packages/geneplotter")
5433 (synopsis "Graphics functions for genomic data")
5435 "This package provides functions for plotting genomic data.")
5436 (license license:artistic2.0)))
5438 (define-public r-genefilter
5440 (name "r-genefilter")
5445 (uri (bioconductor-uri "genefilter" version))
5448 "1vzgciqd09csqcw9qync8blsv51ylrd86a65iadgyy6j26g01fwd"))))
5449 (build-system r-build-system)
5451 `(("gfortran" ,gfortran)))
5453 `(("r-annotate" ,r-annotate)
5454 ("r-annotationdbi" ,r-annotationdbi)
5455 ("r-biobase" ,r-biobase)
5456 ("r-s4vectors" ,r-s4vectors)
5457 ("r-survival" ,r-survival)))
5458 (home-page "http://bioconductor.org/packages/genefilter")
5459 (synopsis "Filter genes from high-throughput experiments")
5461 "This package provides basic functions for filtering genes from
5462 high-throughput sequencing experiments.")
5463 (license license:artistic2.0)))
5465 (define-public r-deseq2
5472 (uri (bioconductor-uri "DESeq2" version))
5475 "1walwkqryn1gnwz7zryr5764a0p6ia7ag4w6w9n8fskg8dkg0fqs"))))
5476 (properties `((upstream-name . "DESeq2")))
5477 (build-system r-build-system)
5479 `(("r-biobase" ,r-biobase)
5480 ("r-biocgenerics" ,r-biocgenerics)
5481 ("r-biocparallel" ,r-biocparallel)
5482 ("r-genefilter" ,r-genefilter)
5483 ("r-geneplotter" ,r-geneplotter)
5484 ("r-genomicranges" ,r-genomicranges)
5485 ("r-ggplot2" ,r-ggplot2)
5486 ("r-hmisc" ,r-hmisc)
5487 ("r-iranges" ,r-iranges)
5488 ("r-locfit" ,r-locfit)
5490 ("r-rcpparmadillo" ,r-rcpparmadillo)
5491 ("r-s4vectors" ,r-s4vectors)
5492 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5493 (home-page "http://bioconductor.org/packages/DESeq2")
5494 (synopsis "Differential gene expression analysis")
5496 "This package provides functions to estimate variance-mean dependence in
5497 count data from high-throughput nucleotide sequencing assays and test for
5498 differential expression based on a model using the negative binomial
5500 (license license:lgpl3+)))
5502 (define-public r-annotationforge
5504 (name "r-annotationforge")
5509 (uri (bioconductor-uri "AnnotationForge" version))
5512 "0l1g9hy88sh5g567svyfd8pnjvkyklkn6a3gjn8zalvh62qqjjq1"))))
5514 `((upstream-name . "AnnotationForge")))
5515 (build-system r-build-system)
5517 `(("r-annotationdbi" ,r-annotationdbi)
5518 ("r-biobase" ,r-biobase)
5519 ("r-biocgenerics" ,r-biocgenerics)
5521 ("r-rcurl" ,r-rcurl)
5522 ("r-rsqlite" ,r-rsqlite)
5523 ("r-s4vectors" ,r-s4vectors)
5525 (home-page "http://bioconductor.org/packages/AnnotationForge")
5526 (synopsis "Code for building annotation database packages")
5528 "This package provides code for generating Annotation packages and their
5529 databases. Packages produced are intended to be used with AnnotationDbi.")
5530 (license license:artistic2.0)))
5532 (define-public r-rbgl
5539 (uri (bioconductor-uri "RBGL" version))
5542 "1q14m8w6ih56v680kf3d9wh1qbgp7af33kz3cxafdf1vvzx9km08"))))
5543 (properties `((upstream-name . "RBGL")))
5544 (build-system r-build-system)
5545 (propagated-inputs `(("r-graph" ,r-graph)))
5546 (home-page "http://www.bioconductor.org/packages/RBGL")
5547 (synopsis "Interface to the Boost graph library")
5549 "This package provides a fairly extensive and comprehensive interface to
5550 the graph algorithms contained in the Boost library.")
5551 (license license:artistic2.0)))
5553 (define-public r-gseabase
5560 (uri (bioconductor-uri "GSEABase" version))
5563 "0l2x7yj7lfb0m2dmsav5ib026dikpgl4crdckrnj776yy08lgxpj"))))
5564 (properties `((upstream-name . "GSEABase")))
5565 (build-system r-build-system)
5567 `(("r-annotate" ,r-annotate)
5568 ("r-annotationdbi" ,r-annotationdbi)
5569 ("r-biobase" ,r-biobase)
5570 ("r-biocgenerics" ,r-biocgenerics)
5571 ("r-graph" ,r-graph)
5573 (home-page "http://bioconductor.org/packages/GSEABase")
5574 (synopsis "Gene set enrichment data structures and methods")
5576 "This package provides classes and methods to support @dfn{Gene Set
5577 Enrichment Analysis} (GSEA).")
5578 (license license:artistic2.0)))
5580 (define-public r-category
5587 (uri (bioconductor-uri "Category" version))
5590 "16ncwz7b4y48k0p3fvbrbmvf7nfz63li9ysgcl8kp9kl4hg7llng"))))
5591 (properties `((upstream-name . "Category")))
5592 (build-system r-build-system)
5594 `(("r-annotate" ,r-annotate)
5595 ("r-annotationdbi" ,r-annotationdbi)
5596 ("r-biobase" ,r-biobase)
5597 ("r-biocgenerics" ,r-biocgenerics)
5598 ("r-genefilter" ,r-genefilter)
5599 ("r-graph" ,r-graph)
5600 ("r-gseabase" ,r-gseabase)
5601 ("r-matrix" ,r-matrix)
5603 ("r-rsqlite" ,r-rsqlite)))
5604 (home-page "http://bioconductor.org/packages/Category")
5605 (synopsis "Category analysis")
5607 "This package provides a collection of tools for performing category
5609 (license license:artistic2.0)))
5611 (define-public r-gostats
5618 (uri (bioconductor-uri "GOstats" version))
5621 "0g2czm94zhzx92z7y2r4mjfxhwml7bhab2db6820ks8nkw1zvr9n"))))
5622 (properties `((upstream-name . "GOstats")))
5623 (build-system r-build-system)
5625 `(("r-annotate" ,r-annotate)
5626 ("r-annotationdbi" ,r-annotationdbi)
5627 ("r-annotationforge" ,r-annotationforge)
5628 ("r-biobase" ,r-biobase)
5629 ("r-category" ,r-category)
5630 ("r-go-db" ,r-go-db)
5631 ("r-graph" ,r-graph)
5632 ("r-rbgl" ,r-rbgl)))
5633 (home-page "http://bioconductor.org/packages/GOstats")
5634 (synopsis "Tools for manipulating GO and microarrays")
5636 "This package provides a set of tools for interacting with GO and
5637 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5638 testing and other simple calculations.")
5639 (license license:artistic2.0)))
5641 (define-public r-shortread
5643 (name "r-shortread")
5648 (uri (bioconductor-uri "ShortRead" version))
5651 "1m7lbfxs7xwcy9xs76zy5rky2mb96anvh457xfw60lh3kygwfpxc"))))
5652 (properties `((upstream-name . "ShortRead")))
5653 (build-system r-build-system)
5657 `(("r-biobase" ,r-biobase)
5658 ("r-biocgenerics" ,r-biocgenerics)
5659 ("r-biocparallel" ,r-biocparallel)
5660 ("r-biostrings" ,r-biostrings)
5661 ("r-genomeinfodb" ,r-genomeinfodb)
5662 ("r-genomicalignments" ,r-genomicalignments)
5663 ("r-genomicranges" ,r-genomicranges)
5664 ("r-hwriter" ,r-hwriter)
5665 ("r-iranges" ,r-iranges)
5666 ("r-lattice" ,r-lattice)
5667 ("r-latticeextra" ,r-latticeextra)
5668 ("r-rsamtools" ,r-rsamtools)
5669 ("r-s4vectors" ,r-s4vectors)
5670 ("r-xvector" ,r-xvector)
5671 ("r-zlibbioc" ,r-zlibbioc)))
5672 (home-page "http://bioconductor.org/packages/ShortRead")
5673 (synopsis "FASTQ input and manipulation tools")
5675 "This package implements sampling, iteration, and input of FASTQ files.
5676 It includes functions for filtering and trimming reads, and for generating a
5677 quality assessment report. Data are represented as
5678 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
5679 purposes. The package also contains legacy support for early single-end,
5680 ungapped alignment formats.")
5681 (license license:artistic2.0)))
5683 (define-public r-systempiper
5685 (name "r-systempiper")
5690 (uri (bioconductor-uri "systemPipeR" version))
5693 "0hyi841w8fm2yzpm6lwqi3jz5kc8ny8dy5p29dxynzaw5bpjw56d"))))
5694 (properties `((upstream-name . "systemPipeR")))
5695 (build-system r-build-system)
5697 `(("r-annotate" ,r-annotate)
5698 ("r-batchjobs" ,r-batchjobs)
5699 ("r-biocgenerics" ,r-biocgenerics)
5700 ("r-biostrings" ,r-biostrings)
5701 ("r-deseq2" ,r-deseq2)
5702 ("r-edger" ,r-edger)
5703 ("r-genomicfeatures" ,r-genomicfeatures)
5704 ("r-genomicranges" ,r-genomicranges)
5705 ("r-ggplot2" ,r-ggplot2)
5706 ("r-go-db" ,r-go-db)
5707 ("r-gostats" ,r-gostats)
5708 ("r-limma" ,r-limma)
5709 ("r-pheatmap" ,r-pheatmap)
5710 ("r-rjson" ,r-rjson)
5711 ("r-rsamtools" ,r-rsamtools)
5712 ("r-shortread" ,r-shortread)
5713 ("r-summarizedexperiment" ,r-summarizedexperiment)
5714 ("r-variantannotation" ,r-variantannotation)))
5715 (home-page "https://github.com/tgirke/systemPipeR")
5716 (synopsis "Next generation sequencing workflow and reporting environment")
5718 "This R package provides tools for building and running automated
5719 end-to-end analysis workflows for a wide range of @dfn{next generation
5720 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
5721 Important features include a uniform workflow interface across different NGS
5722 applications, automated report generation, and support for running both R and
5723 command-line software, such as NGS aligners or peak/variant callers, on local
5724 computers or compute clusters. Efficient handling of complex sample sets and
5725 experimental designs is facilitated by a consistently implemented sample
5726 annotation infrastructure.")
5727 (license license:artistic2.0)))
5729 (define-public r-grohmm
5736 (uri (bioconductor-uri "groHMM" version))
5739 "0d91nyhqbi5hv3mgmr2z0g29wg2md26g0hyv5mgapmz20cd9zi4y"))))
5740 (properties `((upstream-name . "groHMM")))
5741 (build-system r-build-system)
5743 `(("r-genomeinfodb" ,r-genomeinfodb)
5744 ("r-genomicalignments" ,r-genomicalignments)
5745 ("r-genomicranges" ,r-genomicranges)
5746 ("r-iranges" ,r-iranges)
5748 ("r-rtracklayer" ,r-rtracklayer)
5749 ("r-s4vectors" ,r-s4vectors)))
5750 (home-page "https://github.com/Kraus-Lab/groHMM")
5751 (synopsis "GRO-seq analysis pipeline")
5753 "This package provides a pipeline for the analysis of GRO-seq data.")
5754 (license license:gpl3+)))
5756 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
5758 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
5762 ;; We cannot use bioconductor-uri here because this tarball is
5763 ;; located under "data/annotation/" instead of "bioc/".
5764 (uri (string-append "http://bioconductor.org/packages/"
5765 "release/data/annotation/src/contrib"
5766 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
5770 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
5772 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
5773 (build-system r-build-system)
5774 ;; As this package provides little more than a very large data file it
5775 ;; doesn't make sense to build substitutes.
5776 (arguments `(#:substitutable? #f))
5778 `(("r-genomicfeatures" ,r-genomicfeatures)))
5780 "http://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
5781 (synopsis "Annotation package for human genome in TxDb format")
5783 "This package provides an annotation database of Homo sapiens genome
5784 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
5785 track. The database is exposed as a @code{TxDb} object.")
5786 (license license:artistic2.0)))
5788 (define-public vsearch
5796 "https://github.com/torognes/vsearch/archive/v"
5798 (file-name (string-append name "-" version ".tar.gz"))
5801 "0hc110ycqpa54nr6x173qg7190hk08qp7yz7zzqxlsypqnpc5zzp"))
5802 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
5805 ;; Remove bundled cityhash sources. The vsearch source is adjusted
5806 ;; for this in the patch.
5807 (delete-file "src/city.h")
5808 (delete-file "src/citycrc.h")
5809 (delete-file "src/city.cc")
5811 (build-system gnu-build-system)
5814 (modify-phases %standard-phases
5815 (add-before 'configure 'autogen
5816 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
5820 ("cityhash" ,cityhash)))
5822 `(("autoconf" ,autoconf)
5823 ("automake" ,automake)))
5824 (synopsis "Sequence search tools for metagenomics")
5826 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
5827 dereplication, pairwise alignment, shuffling, subsampling, sorting and
5828 masking. The tool takes advantage of parallelism in the form of SIMD
5829 vectorization as well as multiple threads to perform accurate alignments at
5830 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
5831 Needleman-Wunsch).")
5832 (home-page "https://github.com/torognes/vsearch")
5833 ;; vsearch uses non-portable SSE intrinsics so building fails on other
5835 (supported-systems '("x86_64-linux"))
5836 ;; Dual licensed; also includes public domain source.
5837 (license (list license:gpl3 license:bsd-2))))
5839 (define-public pardre
5842 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
5847 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
5851 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
5852 (build-system gnu-build-system)
5854 `(#:tests? #f ; no tests included
5856 (modify-phases %standard-phases
5859 (lambda* (#:key outputs #:allow-other-keys)
5860 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
5861 (install-file "ParDRe" bin)
5864 `(("openmpi" ,openmpi)
5866 (synopsis "Parallel tool to remove duplicate DNA reads")
5868 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
5869 Duplicate reads can be seen as identical or nearly identical sequences with
5870 some mismatches. This tool lets users avoid the analysis of unnecessary
5871 reads, reducing the time of subsequent procedures with the
5872 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
5873 in order to exploit the parallel capabilities of multicore clusters. It is
5874 faster than multithreaded counterparts (end of 2015) for the same number of
5875 cores and, thanks to the message-passing technology, it can be executed on
5877 (home-page "https://sourceforge.net/projects/pardre/")
5878 (license license:gpl3+)))
5880 (define-public ruby-bio-kseq
5882 (name "ruby-bio-kseq")
5887 (uri (rubygems-uri "bio-kseq" version))
5890 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
5891 (build-system ruby-build-system)
5893 `(#:test-target "spec"))
5895 `(("bundler" ,bundler)
5896 ("ruby-rspec" ,ruby-rspec)
5897 ("ruby-rake-compiler" ,ruby-rake-compiler)))
5900 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
5902 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
5903 FASTQ parsing code. It provides a fast iterator over sequences and their
5905 (home-page "https://github.com/gusevfe/bio-kseq")
5906 (license license:expat)))
5908 (define-public bio-locus
5915 (uri (rubygems-uri "bio-locus" version))
5918 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
5919 (build-system ruby-build-system)
5921 `(("ruby-rspec" ,ruby-rspec)))
5922 (synopsis "Tool for fast querying of genome locations")
5924 "Bio-locus is a tabix-like tool for fast querying of genome
5925 locations. Many file formats in bioinformatics contain records that
5926 start with a chromosome name and a position for a SNP, or a start-end
5927 position for indels. Bio-locus allows users to store this chr+pos or
5928 chr+pos+alt information in a database.")
5929 (home-page "https://github.com/pjotrp/bio-locus")
5930 (license license:expat)))
5932 (define-public bio-blastxmlparser
5934 (name "bio-blastxmlparser")
5938 (uri (rubygems-uri "bio-blastxmlparser" version))
5941 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
5942 (build-system ruby-build-system)
5944 `(("ruby-bio-logger" ,ruby-bio-logger)
5945 ("ruby-nokogiri" ,ruby-nokogiri)))
5947 `(("ruby-rspec" ,ruby-rspec)))
5948 (synopsis "Fast big data BLAST XML parser and library")
5950 "Very fast parallel big-data BLAST XML file parser which can be used as
5951 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
5952 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
5953 (home-page "https://github.com/pjotrp/blastxmlparser")
5954 (license license:expat)))
5956 (define-public bioruby
5963 (uri (rubygems-uri "bio" version))
5966 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
5967 (build-system ruby-build-system)
5969 `(("ruby-libxml" ,ruby-libxml)))
5971 `(("which" ,which))) ; required for test phase
5974 (modify-phases %standard-phases
5975 (add-before 'build 'patch-test-command
5977 (substitute* '("test/functional/bio/test_command.rb")
5978 (("/bin/sh") (which "sh")))
5979 (substitute* '("test/functional/bio/test_command.rb")
5980 (("/bin/ls") (which "ls")))
5981 (substitute* '("test/functional/bio/test_command.rb")
5982 (("which") (which "which")))
5983 (substitute* '("test/functional/bio/test_command.rb",
5984 "test/data/command/echoarg2.sh")
5985 (("/bin/echo") (which "echo")))
5987 (synopsis "Ruby library, shell and utilities for bioinformatics")
5988 (description "BioRuby comes with a comprehensive set of Ruby development
5989 tools and libraries for bioinformatics and molecular biology. BioRuby has
5990 components for sequence analysis, pathway analysis, protein modelling and
5991 phylogenetic analysis; it supports many widely used data formats and provides
5992 easy access to databases, external programs and public web services, including
5993 BLAST, KEGG, GenBank, MEDLINE and GO.")
5994 (home-page "http://bioruby.org/")
5995 ;; Code is released under Ruby license, except for setup
5996 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
5997 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
5999 (define-public r-acsnminer
6001 (name "r-acsnminer")
6002 (version "0.16.8.25")
6005 (uri (cran-uri "ACSNMineR" version))
6008 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6009 (properties `((upstream-name . "ACSNMineR")))
6010 (build-system r-build-system)
6012 `(("r-ggplot2" ,r-ggplot2)
6013 ("r-gridextra" ,r-gridextra)))
6014 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6015 (synopsis "Gene enrichment analysis")
6017 "This package provides tools to compute and represent gene set enrichment
6018 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6019 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6020 enrichment can be run with hypergeometric test or Fisher exact test, and can
6021 use multiple corrections. Visualization of data can be done either by
6022 barplots or heatmaps.")
6023 (license license:gpl2+)))
6025 (define-public r-biocgenerics
6027 (name "r-biocgenerics")
6031 (uri (bioconductor-uri "BiocGenerics" version))
6034 "06szdz7dfs1iyv5zdl4fjzad18nnf1zf3wvglc6c6yd9mrqlf7vk"))))
6036 `((upstream-name . "BiocGenerics")))
6037 (build-system r-build-system)
6038 (home-page "http://bioconductor.org/packages/BiocGenerics")
6039 (synopsis "S4 generic functions for Bioconductor")
6041 "This package provides S4 generic functions needed by many Bioconductor
6043 (license license:artistic2.0)))
6045 (define-public r-biocinstaller
6047 (name "r-biocinstaller")
6051 (uri (bioconductor-uri "BiocInstaller" version))
6054 "0y1y5wmy6lzjqx3hdg15n91d417ccjj8dbvdkhmp99bs5aijwcpn"))))
6056 `((upstream-name . "BiocInstaller")))
6057 (build-system r-build-system)
6058 (home-page "http://bioconductor.org/packages/BiocInstaller")
6059 (synopsis "Install Bioconductor packages")
6060 (description "This package is used to install and update R packages from
6061 Bioconductor, CRAN, and Github.")
6062 (license license:artistic2.0)))
6064 (define-public r-biocviews
6066 (name "r-biocviews")
6070 (uri (bioconductor-uri "biocViews" version))
6073 "07rjk10b91pkriyq297w86199r2d3sfji3ggs9mq2gyalsa8y4b6"))))
6075 `((upstream-name . "biocViews")))
6076 (build-system r-build-system)
6078 `(("r-biobase" ,r-biobase)
6079 ("r-graph" ,r-graph)
6081 ("r-rcurl" ,r-rcurl)
6083 ("r-knitr" ,r-knitr)
6084 ("r-runit" ,r-runit)))
6085 (home-page "http://bioconductor.org/packages/biocViews")
6086 (synopsis "Bioconductor package categorization helper")
6087 (description "The purpose of biocViews is to create HTML pages that
6088 categorize packages in a Bioconductor package repository according to keywords,
6089 also known as views, in a controlled vocabulary.")
6090 (license license:artistic2.0)))
6092 (define-public r-biocstyle
6094 (name "r-biocstyle")
6098 (uri (bioconductor-uri "BiocStyle" version))
6101 "0sl99xw940ixrm6v24lgaw3ljh56g59a6rdz7g160hx84z9f8n2n"))))
6103 `((upstream-name . "BiocStyle")))
6104 (build-system r-build-system)
6105 (home-page "http://bioconductor.org/packages/BiocStyle")
6106 (synopsis "Bioconductor formatting styles")
6107 (description "This package provides standard formatting styles for
6108 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6110 (license license:artistic2.0)))
6112 (define-public r-bioccheck
6114 (name "r-bioccheck")
6118 (uri (bioconductor-uri "BiocCheck" version))
6121 "197kpiycyl3qawm6801fxyxj81d2g57a00qxaqprapsf1d140l52"))))
6123 `((upstream-name . "BiocCheck")))
6124 (build-system r-build-system)
6127 (modify-phases %standard-phases
6128 ;; This package can be used by calling BiocCheck(<package>) from
6129 ;; within R, or by running R CMD BiocCheck <package>. This phase
6130 ;; makes sure the latter works. For this to work, the BiocCheck
6131 ;; script must be somewhere on the PATH (not the R bin directory).
6132 (add-after 'install 'install-bioccheck-subcommand
6133 (lambda* (#:key outputs #:allow-other-keys)
6134 (let* ((out (assoc-ref outputs "out"))
6135 (dest-dir (string-append out "/bin"))
6137 (string-append out "/site-library/BiocCheck/script/")))
6139 (symlink (string-append script-dir "/checkBadDeps.R")
6140 (string-append dest-dir "/checkBadDeps.R"))
6141 (symlink (string-append script-dir "/BiocCheck")
6142 (string-append dest-dir "/BiocCheck")))
6145 `(("which" ,which)))
6147 `(("r-codetools" ,r-codetools)
6148 ("r-graph" ,r-graph)
6150 ("r-optparse" ,r-optparse)
6151 ("r-biocinstaller" ,r-biocinstaller)
6152 ("r-biocviews" ,r-biocviews)))
6153 (home-page "http://bioconductor.org/packages/BiocCheck")
6154 (synopsis "Executes Bioconductor-specific package checks")
6155 (description "This package contains tools to perform additional quality
6156 checks on R packages that are to be submitted to the Bioconductor repository.")
6157 (license license:artistic2.0)))
6159 (define-public r-getopt
6166 (uri (cran-uri "getopt" version))
6169 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6170 (build-system r-build-system)
6171 (home-page "https://github.com/trevorld/getopt")
6172 (synopsis "Command-line option processor for R")
6174 "This package is designed to be used with Rscript to write shebang
6175 scripts that accept short and long options. Many users will prefer to
6176 use the packages @code{optparse} or @code{argparse} which add extra
6177 features like automatically generated help options and usage texts,
6178 support for default values, positional argument support, etc.")
6179 (license license:gpl2+)))
6181 (define-public r-optparse
6188 (uri (cran-uri "optparse" version))
6191 "1g8as89r91xxi5j5azsd6vrfrhg84mnfx2683j7pacdp8s33radw"))))
6192 (build-system r-build-system)
6194 `(("r-getopt" ,r-getopt)))
6196 "https://github.com/trevorld/optparse")
6197 (synopsis "Command line option parser")
6199 "This package provides a command line parser inspired by Python's
6200 @code{optparse} library to be used with Rscript to write shebang scripts
6201 that accept short and long options.")
6202 (license license:gpl2+)))
6204 (define-public r-dnacopy
6210 (uri (bioconductor-uri "DNAcopy" version))
6213 "1idyvfvy7xx8k9vk00y4k3819qmip8iqm809j3vpxabmsn7r9zyh"))))
6215 `((upstream-name . "DNAcopy")))
6216 (build-system r-build-system)
6218 `(("gfortran" ,gfortran)))
6219 (home-page "https://bioconductor.org/packages/DNAcopy")
6220 (synopsis "Implementation of a circular binary segmentation algorithm")
6221 (description "This package implements the circular binary segmentation (CBS)
6222 algorithm to segment DNA copy number data and identify genomic regions with
6223 abnormal copy number.")
6224 (license license:gpl2+)))
6226 (define-public r-s4vectors
6228 (name "r-s4vectors")
6232 (uri (bioconductor-uri "S4Vectors" version))
6235 "0syx0qgipx97zsp3b8afhzamsr30835a2a99yb9wnq7b50g3v3p1"))))
6237 `((upstream-name . "S4Vectors")))
6238 (build-system r-build-system)
6240 `(("r-biocgenerics" ,r-biocgenerics)))
6241 (home-page "http://bioconductor.org/packages/S4Vectors")
6242 (synopsis "S4 implementation of vectors and lists")
6244 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6245 classes and a set of generic functions that extend the semantic of ordinary
6246 vectors and lists in R. Package developers can easily implement vector-like
6247 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6248 In addition, a few low-level concrete subclasses of general interest (e.g.
6249 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6250 S4Vectors package itself.")
6251 (license license:artistic2.0)))
6253 (define-public r-seqinr
6260 (uri (cran-uri "seqinr" version))
6263 "13d0qxm2244wgdl2dy2s8vnrnf5fx4n47if9gkb49dqx6c0sx8s2"))))
6264 (build-system r-build-system)
6266 `(("r-ade4" ,r-ade4)
6267 ("r-segmented" ,r-segmented)))
6270 (home-page "http://seqinr.r-forge.r-project.org/")
6271 (synopsis "Biological sequences retrieval and analysis")
6273 "This package provides tools for exploratory data analysis and data
6274 visualization of biological sequence (DNA and protein) data. It also includes
6275 utilities for sequence data management under the ACNUC system.")
6276 (license license:gpl2+)))
6278 (define-public r-iranges
6284 (uri (bioconductor-uri "IRanges" version))
6287 "0x8h74ik3xwdnwrkn89hq5ll0qa1lp9jgzlbmpa02dpws7snfwyr"))))
6289 `((upstream-name . "IRanges")))
6290 (build-system r-build-system)
6292 `(("r-biocgenerics" ,r-biocgenerics)
6293 ("r-s4vectors" ,r-s4vectors)))
6294 (home-page "http://bioconductor.org/packages/IRanges")
6295 (synopsis "Infrastructure for manipulating intervals on sequences")
6297 "This package provides efficient low-level and highly reusable S4 classes
6298 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6299 generally, data that can be organized sequentially (formally defined as
6300 @code{Vector} objects), as well as views on these @code{Vector} objects.
6301 Efficient list-like classes are also provided for storing big collections of
6302 instances of the basic classes. All classes in the package use consistent
6303 naming and share the same rich and consistent \"Vector API\" as much as
6305 (license license:artistic2.0)))
6307 (define-public r-genomeinfodb
6309 (name "r-genomeinfodb")
6313 (uri (bioconductor-uri "GenomeInfoDb" version))
6316 "18g24cf6b3vi13w85ki2mam6i2gl4yxr1zchyga34xc3dkdngzrw"))))
6318 `((upstream-name . "GenomeInfoDb")))
6319 (build-system r-build-system)
6321 `(("r-biocgenerics" ,r-biocgenerics)
6322 ("r-iranges" ,r-iranges)
6323 ("r-rcurl" ,r-rcurl)
6324 ("r-s4vectors" ,r-s4vectors)))
6325 (home-page "http://bioconductor.org/packages/GenomeInfoDb")
6326 (synopsis "Utilities for manipulating chromosome identifiers")
6328 "This package contains data and functions that define and allow
6329 translation between different chromosome sequence naming conventions (e.g.,
6330 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6331 names in their natural, rather than lexicographic, order.")
6332 (license license:artistic2.0)))
6334 (define-public r-edger
6340 (uri (bioconductor-uri "edgeR" version))
6343 "04vpa0a6dkkjyvvfbkmfjyaxf2ldkagi66g028qpaszd8jsk8yiv"))))
6344 (properties `((upstream-name . "edgeR")))
6345 (build-system r-build-system)
6347 `(("r-limma" ,r-limma)
6348 ("r-locfit" ,r-locfit)
6349 ("r-statmod" ,r-statmod))) ;for estimateDisp
6350 (home-page "http://bioinf.wehi.edu.au/edgeR")
6351 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6352 (description "This package can do differential expression analysis of
6353 RNA-seq expression profiles with biological replication. It implements a range
6354 of statistical methodology based on the negative binomial distributions,
6355 including empirical Bayes estimation, exact tests, generalized linear models
6356 and quasi-likelihood tests. It be applied to differential signal analysis of
6357 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6359 (license license:gpl2+)))
6361 (define-public r-variantannotation
6363 (name "r-variantannotation")
6367 (uri (bioconductor-uri "VariantAnnotation" version))
6370 "10v8apgfw57nd4dxmdxdrijxpw135jpp2p8wrk3wjpb3hhfjp1qj"))))
6372 `((upstream-name . "VariantAnnotation")))
6376 `(("r-annotationdbi" ,r-annotationdbi)
6377 ("r-biobase" ,r-biobase)
6378 ("r-biocgenerics" ,r-biocgenerics)
6379 ("r-biostrings" ,r-biostrings)
6380 ("r-bsgenome" ,r-bsgenome)
6382 ("r-genomeinfodb" ,r-genomeinfodb)
6383 ("r-genomicfeatures" ,r-genomicfeatures)
6384 ("r-genomicranges" ,r-genomicranges)
6385 ("r-iranges" ,r-iranges)
6386 ("r-summarizedexperiment" ,r-summarizedexperiment)
6387 ("r-rsamtools" ,r-rsamtools)
6388 ("r-rtracklayer" ,r-rtracklayer)
6389 ("r-s4vectors" ,r-s4vectors)
6390 ("r-xvector" ,r-xvector)
6391 ("r-zlibbioc" ,r-zlibbioc)))
6392 (build-system r-build-system)
6393 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6394 (synopsis "Package for annotation of genetic variants")
6395 (description "This R package can annotate variants, compute amino acid
6396 coding changes and predict coding outcomes.")
6397 (license license:artistic2.0)))
6399 (define-public r-limma
6405 (uri (bioconductor-uri "limma" version))
6408 "1ji8kb19anwq2505zii2kzqlrnk75mk1mpz8vy4s1mckzs1cz4m0"))))
6409 (build-system r-build-system)
6410 (home-page "http://bioinf.wehi.edu.au/limma")
6411 (synopsis "Package for linear models for microarray and RNA-seq data")
6412 (description "This package can be used for the analysis of gene expression
6413 studies, especially the use of linear models for analysing designed experiments
6414 and the assessment of differential expression. The analysis methods apply to
6415 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6416 (license license:gpl2+)))
6418 (define-public r-xvector
6424 (uri (bioconductor-uri "XVector" version))
6427 "1j14ip4c260kdp3zcmgfa2v8ky88csa0gfdg6a1xsb64s03hdbm6"))))
6429 `((upstream-name . "XVector")))
6430 (build-system r-build-system)
6433 (modify-phases %standard-phases
6434 (add-after 'unpack 'use-system-zlib
6436 (substitute* "DESCRIPTION"
6437 (("zlibbioc, ") ""))
6438 (substitute* "NAMESPACE"
6439 (("import\\(zlibbioc\\)") ""))
6444 `(("r-biocgenerics" ,r-biocgenerics)
6445 ("r-iranges" ,r-iranges)
6446 ("r-s4vectors" ,r-s4vectors)))
6447 (home-page "http://bioconductor.org/packages/XVector")
6448 (synopsis "Representation and manpulation of external sequences")
6450 "This package provides memory efficient S4 classes for storing sequences
6451 \"externally\" (behind an R external pointer, or on disk).")
6452 (license license:artistic2.0)))
6454 (define-public r-genomicranges
6456 (name "r-genomicranges")
6460 (uri (bioconductor-uri "GenomicRanges" version))
6463 "1789ycqzv20d8p1axkxrhsz9v0ww6w1dk2mfvm85p8j53zd1f67c"))))
6465 `((upstream-name . "GenomicRanges")))
6466 (build-system r-build-system)
6468 `(("r-biocgenerics" ,r-biocgenerics)
6469 ("r-genomeinfodb" ,r-genomeinfodb)
6470 ("r-iranges" ,r-iranges)
6471 ("r-s4vectors" ,r-s4vectors)
6472 ("r-xvector" ,r-xvector)))
6473 (home-page "http://bioconductor.org/packages/GenomicRanges")
6474 (synopsis "Representation and manipulation of genomic intervals")
6476 "This package provides tools to efficiently represent and manipulate
6477 genomic annotations and alignments is playing a central role when it comes to
6478 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6479 GenomicRanges package defines general purpose containers for storing and
6480 manipulating genomic intervals and variables defined along a genome.")
6481 (license license:artistic2.0)))
6483 (define-public r-biobase
6489 (uri (bioconductor-uri "Biobase" version))
6492 "0js9j9wqls8f571ifl9ylllbb9a9hwf7b7drf2grwb1fl31ldazl"))))
6494 `((upstream-name . "Biobase")))
6495 (build-system r-build-system)
6497 `(("r-biocgenerics" ,r-biocgenerics)))
6498 (home-page "http://bioconductor.org/packages/Biobase")
6499 (synopsis "Base functions for Bioconductor")
6501 "This package provides functions that are needed by many other packages
6502 on Bioconductor or which replace R functions.")
6503 (license license:artistic2.0)))
6505 (define-public r-annotationdbi
6507 (name "r-annotationdbi")
6511 (uri (bioconductor-uri "AnnotationDbi" version))
6514 "0574lmyisn3nv9aicz9x3iivx990da4q2j4i0f1jz0mpj9v3vc2w"))))
6516 `((upstream-name . "AnnotationDbi")))
6517 (build-system r-build-system)
6519 `(("r-biobase" ,r-biobase)
6520 ("r-biocgenerics" ,r-biocgenerics)
6522 ("r-iranges" ,r-iranges)
6523 ("r-rsqlite" ,r-rsqlite)
6524 ("r-s4vectors" ,r-s4vectors)))
6525 (home-page "http://bioconductor.org/packages/AnnotationDbi")
6526 (synopsis "Annotation database interface")
6528 "This package provides user interface and database connection code for
6529 annotation data packages using SQLite data storage.")
6530 (license license:artistic2.0)))
6532 (define-public r-biomart
6538 (uri (bioconductor-uri "biomaRt" version))
6541 "1x0flcghq71784q2l02j0g4f9jkmyb14f6i307n6c59d6ji7h7x6"))))
6543 `((upstream-name . "biomaRt")))
6544 (build-system r-build-system)
6546 `(("r-annotationdbi" ,r-annotationdbi)
6547 ("r-rcurl" ,r-rcurl)
6549 (home-page "http://bioconductor.org/packages/biomaRt")
6550 (synopsis "Interface to BioMart databases")
6552 "biomaRt provides an interface to a growing collection of databases
6553 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6554 package enables retrieval of large amounts of data in a uniform way without
6555 the need to know the underlying database schemas or write complex SQL queries.
6556 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6557 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6558 users direct access to a diverse set of data and enable a wide range of
6559 powerful online queries from gene annotation to database mining.")
6560 (license license:artistic2.0)))
6562 (define-public r-biocparallel
6564 (name "r-biocparallel")
6568 (uri (bioconductor-uri "BiocParallel" version))
6571 "18zpa0vl375n9pvxsgbid1k96m17nqqgv1g1sfnlmm7kj34jxg6v"))))
6573 `((upstream-name . "BiocParallel")))
6574 (build-system r-build-system)
6576 `(("r-futile-logger" ,r-futile-logger)
6577 ("r-snow" ,r-snow)))
6578 (home-page "http://bioconductor.org/packages/BiocParallel")
6579 (synopsis "Bioconductor facilities for parallel evaluation")
6581 "This package provides modified versions and novel implementation of
6582 functions for parallel evaluation, tailored to use with Bioconductor
6584 (license (list license:gpl2+ license:gpl3+))))
6586 (define-public r-biostrings
6588 (name "r-biostrings")
6592 (uri (bioconductor-uri "Biostrings" version))
6595 "0vqgd9i6y3wj4zviqwgvwgd4qj6033fg01rmx1cw9bw5i8ans42d"))))
6597 `((upstream-name . "Biostrings")))
6598 (build-system r-build-system)
6600 `(("r-biocgenerics" ,r-biocgenerics)
6601 ("r-iranges" ,r-iranges)
6602 ("r-s4vectors" ,r-s4vectors)
6603 ("r-xvector" ,r-xvector)))
6604 (home-page "http://bioconductor.org/packages/Biostrings")
6605 (synopsis "String objects and algorithms for biological sequences")
6607 "This package provides memory efficient string containers, string
6608 matching algorithms, and other utilities, for fast manipulation of large
6609 biological sequences or sets of sequences.")
6610 (license license:artistic2.0)))
6612 (define-public r-rsamtools
6614 (name "r-rsamtools")
6618 (uri (bioconductor-uri "Rsamtools" version))
6621 "118nsajgghi4cy3h0wi7777kc70a5j1fdyxv5n1dy01glix2z4qk"))))
6623 `((upstream-name . "Rsamtools")))
6624 (build-system r-build-system)
6627 (modify-phases %standard-phases
6628 (add-after 'unpack 'use-system-zlib
6630 (substitute* "DESCRIPTION"
6631 (("zlibbioc, ") ""))
6632 (substitute* "NAMESPACE"
6633 (("import\\(zlibbioc\\)") ""))
6638 `(("r-biocgenerics" ,r-biocgenerics)
6639 ("r-biocparallel" ,r-biocparallel)
6640 ("r-biostrings" ,r-biostrings)
6641 ("r-bitops" ,r-bitops)
6642 ("r-genomeinfodb" ,r-genomeinfodb)
6643 ("r-genomicranges" ,r-genomicranges)
6644 ("r-iranges" ,r-iranges)
6645 ("r-s4vectors" ,r-s4vectors)
6646 ("r-xvector" ,r-xvector)))
6647 (home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
6648 (synopsis "Interface to samtools, bcftools, and tabix")
6650 "This package provides an interface to the 'samtools', 'bcftools', and
6651 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
6652 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
6654 (license license:expat)))
6656 (define-public r-summarizedexperiment
6658 (name "r-summarizedexperiment")
6662 (uri (bioconductor-uri "SummarizedExperiment" version))
6665 "1kbj8sg2ik9f8d6g95wz0py62jldg01qy5rsdpg1cxw95nf7dzi3"))))
6667 `((upstream-name . "SummarizedExperiment")))
6668 (build-system r-build-system)
6670 `(("r-biobase" ,r-biobase)
6671 ("r-biocgenerics" ,r-biocgenerics)
6672 ("r-genomeinfodb" ,r-genomeinfodb)
6673 ("r-genomicranges" ,r-genomicranges)
6674 ("r-iranges" ,r-iranges)
6675 ("r-matrix" ,r-matrix)
6676 ("r-s4vectors" ,r-s4vectors)))
6677 (home-page "http://bioconductor.org/packages/SummarizedExperiment")
6678 (synopsis "Container for representing genomic ranges by sample")
6680 "The SummarizedExperiment container contains one or more assays, each
6681 represented by a matrix-like object of numeric or other mode. The rows
6682 typically represent genomic ranges of interest and the columns represent
6684 (license license:artistic2.0)))
6686 (define-public r-genomicalignments
6688 (name "r-genomicalignments")
6692 (uri (bioconductor-uri "GenomicAlignments" version))
6695 "1dilghbsyf64iz5c0kib2c7if72x7almd5w3ali09a2b2ff2mcjk"))))
6697 `((upstream-name . "GenomicAlignments")))
6698 (build-system r-build-system)
6700 `(("r-biocgenerics" ,r-biocgenerics)
6701 ("r-biocparallel" ,r-biocparallel)
6702 ("r-biostrings" ,r-biostrings)
6703 ("r-genomeinfodb" ,r-genomeinfodb)
6704 ("r-genomicranges" ,r-genomicranges)
6705 ("r-iranges" ,r-iranges)
6706 ("r-rsamtools" ,r-rsamtools)
6707 ("r-s4vectors" ,r-s4vectors)
6708 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6709 (home-page "http://bioconductor.org/packages/GenomicAlignments")
6710 (synopsis "Representation and manipulation of short genomic alignments")
6712 "This package provides efficient containers for storing and manipulating
6713 short genomic alignments (typically obtained by aligning short reads to a
6714 reference genome). This includes read counting, computing the coverage,
6715 junction detection, and working with the nucleotide content of the
6717 (license license:artistic2.0)))
6719 (define-public r-rtracklayer
6721 (name "r-rtracklayer")
6725 (uri (bioconductor-uri "rtracklayer" version))
6728 "1j3cyvg1wg1d9l0lkcjk3jn7pb96zi17nd1qsa5lglsimja19mpl"))))
6729 (build-system r-build-system)
6732 (modify-phases %standard-phases
6733 (add-after 'unpack 'use-system-zlib
6735 (substitute* "DESCRIPTION"
6736 (("zlibbioc, ") ""))
6737 (substitute* "NAMESPACE"
6738 (("import\\(zlibbioc\\)") ""))
6743 `(("r-biocgenerics" ,r-biocgenerics)
6744 ("r-biostrings" ,r-biostrings)
6745 ("r-genomeinfodb" ,r-genomeinfodb)
6746 ("r-genomicalignments" ,r-genomicalignments)
6747 ("r-genomicranges" ,r-genomicranges)
6748 ("r-iranges" ,r-iranges)
6749 ("r-rcurl" ,r-rcurl)
6750 ("r-rsamtools" ,r-rsamtools)
6751 ("r-s4vectors" ,r-s4vectors)
6753 ("r-xvector" ,r-xvector)))
6754 (home-page "http://bioconductor.org/packages/rtracklayer")
6755 (synopsis "R interface to genome browsers and their annotation tracks")
6757 "rtracklayer is an extensible framework for interacting with multiple
6758 genome browsers (currently UCSC built-in) and manipulating annotation tracks
6759 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
6760 built-in). The user may export/import tracks to/from the supported browsers,
6761 as well as query and modify the browser state, such as the current viewport.")
6762 (license license:artistic2.0)))
6764 (define-public r-genomicfeatures
6766 (name "r-genomicfeatures")
6770 (uri (bioconductor-uri "GenomicFeatures" version))
6773 "1y16lqach0v3ym5zhdhj4r2imfi0kpa0djlb51hj85yf7xkzwdlb"))))
6775 `((upstream-name . "GenomicFeatures")))
6776 (build-system r-build-system)
6778 `(("r-annotationdbi" ,r-annotationdbi)
6779 ("r-biobase" ,r-biobase)
6780 ("r-biocgenerics" ,r-biocgenerics)
6781 ("r-biomart" ,r-biomart)
6782 ("r-biostrings" ,r-biostrings)
6784 ("r-genomeinfodb" ,r-genomeinfodb)
6785 ("r-genomicranges" ,r-genomicranges)
6786 ("r-iranges" ,r-iranges)
6787 ("r-rcurl" ,r-rcurl)
6788 ("r-rsqlite" ,r-rsqlite)
6789 ("r-rtracklayer" ,r-rtracklayer)
6790 ("r-s4vectors" ,r-s4vectors)
6791 ("r-xvector" ,r-xvector)))
6792 (home-page "http://bioconductor.org/packages/GenomicFeatures")
6793 (synopsis "Tools for working with transcript centric annotations")
6795 "This package provides a set of tools and methods for making and
6796 manipulating transcript centric annotations. With these tools the user can
6797 easily download the genomic locations of the transcripts, exons and cds of a
6798 given organism, from either the UCSC Genome Browser or a BioMart
6799 database (more sources will be supported in the future). This information is
6800 then stored in a local database that keeps track of the relationship between
6801 transcripts, exons, cds and genes. Flexible methods are provided for
6802 extracting the desired features in a convenient format.")
6803 (license license:artistic2.0)))
6805 (define-public r-go-db
6811 (uri (string-append "http://www.bioconductor.org/packages/"
6812 "release/data/annotation/src/contrib/GO.db_"
6816 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
6818 `((upstream-name . "GO.db")))
6819 (build-system r-build-system)
6821 `(("r-annotationdbi" ,r-annotationdbi)))
6822 (home-page "http://bioconductor.org/packages/GO.db")
6823 (synopsis "Annotation maps describing the entire Gene Ontology")
6825 "The purpose of this GO.db annotation package is to provide detailed
6826 information about the latest version of the Gene Ontologies.")
6827 (license license:artistic2.0)))
6829 (define-public r-graph
6835 (uri (bioconductor-uri "graph" version))
6838 "0g3dk5vsdp489fmyg8mifczmzgqrjlakkkr8i96dj15gghp3l135"))))
6839 (build-system r-build-system)
6841 `(("r-biocgenerics" ,r-biocgenerics)))
6842 (home-page "http://bioconductor.org/packages/graph")
6843 (synopsis "Handle graph data structures in R")
6845 "This package implements some simple graph handling capabilities for R.")
6846 (license license:artistic2.0)))
6848 (define-public r-topgo
6854 (uri (bioconductor-uri "topGO" version))
6857 "0j6sgvam4lk9348ag6pypcbkv93x4fk0di8ivhr23mz2s2yqzwrx"))))
6859 `((upstream-name . "topGO")))
6860 (build-system r-build-system)
6862 `(("r-annotationdbi" ,r-annotationdbi)
6864 ("r-biobase" ,r-biobase)
6865 ("r-biocgenerics" ,r-biocgenerics)
6866 ("r-go-db" ,r-go-db)
6867 ("r-graph" ,r-graph)
6868 ("r-lattice" ,r-lattice)
6869 ("r-matrixstats" ,r-matrixstats)
6870 ("r-sparsem" ,r-sparsem)))
6871 (home-page "http://bioconductor.org/packages/topGO")
6872 (synopsis "Enrichment analysis for gene ontology")
6874 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
6875 terms while accounting for the topology of the GO graph. Different test
6876 statistics and different methods for eliminating local similarities and
6877 dependencies between GO terms can be implemented and applied.")
6878 ;; Any version of the LGPL applies.
6879 (license license:lgpl2.1+)))
6881 (define-public r-bsgenome
6887 (uri (bioconductor-uri "BSgenome" version))
6890 "0hxwc02h5mzhkrk60d1jmlsfjf0ai9jxdc0128kj1sg4r2k1q94y"))))
6892 `((upstream-name . "BSgenome")))
6893 (build-system r-build-system)
6895 `(("r-biocgenerics" ,r-biocgenerics)
6896 ("r-biostrings" ,r-biostrings)
6897 ("r-genomeinfodb" ,r-genomeinfodb)
6898 ("r-genomicranges" ,r-genomicranges)
6899 ("r-iranges" ,r-iranges)
6900 ("r-rsamtools" ,r-rsamtools)
6901 ("r-rtracklayer" ,r-rtracklayer)
6902 ("r-s4vectors" ,r-s4vectors)
6903 ("r-xvector" ,r-xvector)))
6904 (home-page "http://bioconductor.org/packages/BSgenome")
6905 (synopsis "Infrastructure for Biostrings-based genome data packages")
6907 "This package provides infrastructure shared by all Biostrings-based
6908 genome data packages and support for efficient SNP representation.")
6909 (license license:artistic2.0)))
6911 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
6913 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
6917 ;; We cannot use bioconductor-uri here because this tarball is
6918 ;; located under "data/annotation/" instead of "bioc/".
6919 (uri (string-append "http://www.bioconductor.org/packages/"
6920 "release/data/annotation/src/contrib/"
6921 "BSgenome.Hsapiens.1000genomes.hs37d5_"
6925 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
6927 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
6928 (build-system r-build-system)
6929 ;; As this package provides little more than a very large data file it
6930 ;; doesn't make sense to build substitutes.
6931 (arguments `(#:substitutable? #f))
6933 `(("r-bsgenome" ,r-bsgenome)))
6935 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
6936 (synopsis "Full genome sequences for Homo sapiens")
6938 "This package provides full genome sequences for Homo sapiens from
6939 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
6940 (license license:artistic2.0)))
6942 (define-public r-impute
6948 (uri (bioconductor-uri "impute" version))
6951 "1164zvnikbjd0ybdn9xwn520rlmdjd824vmhnl83zgv3v9lzp9bm"))))
6953 `(("gfortran" ,gfortran)))
6954 (build-system r-build-system)
6955 (home-page "http://bioconductor.org/packages/impute")
6956 (synopsis "Imputation for microarray data")
6958 "This package provides a function to impute missing gene expression
6959 microarray data, using nearest neighbor averaging.")
6960 (license license:gpl2+)))
6962 (define-public r-seqpattern
6964 (name "r-seqpattern")
6968 (uri (bioconductor-uri "seqPattern" version))
6971 "0lsa5pz36xapi3yiv78k3z286a5md5sm5g21pgfyg8zmhmkxr7y8"))))
6973 `((upstream-name . "seqPattern")))
6974 (build-system r-build-system)
6976 `(("r-biostrings" ,r-biostrings)
6977 ("r-genomicranges" ,r-genomicranges)
6978 ("r-iranges" ,r-iranges)
6979 ("r-kernsmooth" ,r-kernsmooth)
6980 ("r-plotrix" ,r-plotrix)))
6981 (home-page "http://bioconductor.org/packages/seqPattern")
6982 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
6984 "This package provides tools to visualize oligonucleotide patterns and
6985 sequence motif occurrences across a large set of sequences centred at a common
6986 reference point and sorted by a user defined feature.")
6987 (license license:gpl3+)))
6989 (define-public r-genomation
6991 (name "r-genomation")
6995 (uri (bioconductor-uri "genomation" version))
6998 "1m4mz7wihj8yqivwkzw68div8ybk4rjsai3ffki7xp7sh21ax03y"))))
6999 (build-system r-build-system)
7001 `(("r-biostrings" ,r-biostrings)
7002 ("r-bsgenome" ,r-bsgenome)
7003 ("r-data-table" ,r-data-table)
7004 ("r-genomeinfodb" ,r-genomeinfodb)
7005 ("r-genomicalignments" ,r-genomicalignments)
7006 ("r-genomicranges" ,r-genomicranges)
7007 ("r-ggplot2" ,r-ggplot2)
7008 ("r-gridbase" ,r-gridbase)
7009 ("r-impute" ,r-impute)
7010 ("r-iranges" ,r-iranges)
7011 ("r-matrixstats" ,r-matrixstats)
7012 ("r-plotrix" ,r-plotrix)
7015 ("r-readr" ,r-readr)
7016 ("r-reshape2" ,r-reshape2)
7017 ("r-rhtslib" ,r-rhtslib)
7018 ("r-rsamtools" ,r-rsamtools)
7019 ("r-rtracklayer" ,r-rtracklayer)
7020 ("r-runit" ,r-runit)
7021 ("r-s4vectors" ,r-s4vectors)
7022 ("r-seqpattern" ,r-seqpattern)))
7025 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7026 (synopsis "Summary, annotation and visualization of genomic data")
7028 "This package provides a package for summary and annotation of genomic
7029 intervals. Users can visualize and quantify genomic intervals over
7030 pre-defined functional regions, such as promoters, exons, introns, etc. The
7031 genomic intervals represent regions with a defined chromosome position, which
7032 may be associated with a score, such as aligned reads from HT-seq experiments,
7033 TF binding sites, methylation scores, etc. The package can use any tabular
7034 genomic feature data as long as it has minimal information on the locations of
7035 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7036 (license license:artistic2.0)))
7038 (define-public r-genomationdata
7040 (name "r-genomationdata")
7044 ;; We cannot use bioconductor-uri here because this tarball is
7045 ;; located under "data/annotation/" instead of "bioc/".
7046 (uri (string-append "https://bioconductor.org/packages/"
7047 "release/data/experiment/src/contrib/"
7048 "genomationData_" version ".tar.gz"))
7051 "16dqwb7wx1igx77zdbcskx5m1hs4g4gp2hl56zzm70hcagnlkz8y"))))
7052 (build-system r-build-system)
7053 ;; As this package provides little more than large data files, it doesn't
7054 ;; make sense to build substitutes.
7055 (arguments `(#:substitutable? #f))
7057 `(("r-knitr" ,r-knitr)))
7058 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7059 (synopsis "Experimental data for use with the genomation package")
7061 "This package contains experimental genetic data for use with the
7062 genomation package. Included are Chip Seq, Methylation and Cage data,
7063 downloaded from Encode.")
7064 (license license:gpl3+)))
7066 (define-public r-org-hs-eg-db
7068 (name "r-org-hs-eg-db")
7072 ;; We cannot use bioconductor-uri here because this tarball is
7073 ;; located under "data/annotation/" instead of "bioc/".
7074 (uri (string-append "http://www.bioconductor.org/packages/"
7075 "release/data/annotation/src/contrib/"
7076 "org.Hs.eg.db_" version ".tar.gz"))
7079 "19mg64pw8zcvb9yxzzyf7caz1kvdrkfsj1hd84bzq7crrh8kc4y6"))))
7081 `((upstream-name . "org.Hs.eg.db")))
7082 (build-system r-build-system)
7084 `(("r-annotationdbi" ,r-annotationdbi)))
7085 (home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
7086 (synopsis "Genome wide annotation for Human")
7088 "This package provides mappings from Entrez gene identifiers to various
7089 annotations for the human genome.")
7090 (license license:artistic2.0)))
7092 (define-public r-org-ce-eg-db
7094 (name "r-org-ce-eg-db")
7098 ;; We cannot use bioconductor-uri here because this tarball is
7099 ;; located under "data/annotation/" instead of "bioc/".
7100 (uri (string-append "http://www.bioconductor.org/packages/"
7101 "release/data/annotation/src/contrib/"
7102 "org.Ce.eg.db_" version ".tar.gz"))
7105 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7107 `((upstream-name . "org.Ce.eg.db")))
7108 (build-system r-build-system)
7110 `(("r-annotationdbi" ,r-annotationdbi)))
7111 (home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
7112 (synopsis "Genome wide annotation for Worm")
7114 "This package provides mappings from Entrez gene identifiers to various
7115 annotations for the genome of the model worm Caenorhabditis elegans.")
7116 (license license:artistic2.0)))
7118 (define-public r-org-dm-eg-db
7120 (name "r-org-dm-eg-db")
7124 ;; We cannot use bioconductor-uri here because this tarball is
7125 ;; located under "data/annotation/" instead of "bioc/".
7126 (uri (string-append "http://www.bioconductor.org/packages/"
7127 "release/data/annotation/src/contrib/"
7128 "org.Dm.eg.db_" version ".tar.gz"))
7131 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7133 `((upstream-name . "org.Dm.eg.db")))
7134 (build-system r-build-system)
7136 `(("r-annotationdbi" ,r-annotationdbi)))
7137 (home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
7138 (synopsis "Genome wide annotation for Fly")
7140 "This package provides mappings from Entrez gene identifiers to various
7141 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7142 (license license:artistic2.0)))
7144 (define-public r-org-mm-eg-db
7146 (name "r-org-mm-eg-db")
7150 ;; We cannot use bioconductor-uri here because this tarball is
7151 ;; located under "data/annotation/" instead of "bioc/".
7152 (uri (string-append "http://www.bioconductor.org/packages/"
7153 "release/data/annotation/src/contrib/"
7154 "org.Mm.eg.db_" version ".tar.gz"))
7157 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7159 `((upstream-name . "org.Mm.eg.db")))
7160 (build-system r-build-system)
7162 `(("r-annotationdbi" ,r-annotationdbi)))
7163 (home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
7164 (synopsis "Genome wide annotation for Mouse")
7166 "This package provides mappings from Entrez gene identifiers to various
7167 annotations for the genome of the model mouse Mus musculus.")
7168 (license license:artistic2.0)))
7170 (define-public r-seqlogo
7177 (uri (bioconductor-uri "seqLogo" version))
7180 "18bajdl75h3039559d81rgllqqvnq8ygsfxfx081xphxs0v6xggy"))))
7181 (properties `((upstream-name . "seqLogo")))
7182 (build-system r-build-system)
7183 (home-page "http://bioconductor.org/packages/seqLogo")
7184 (synopsis "Sequence logos for DNA sequence alignments")
7186 "seqLogo takes the position weight matrix of a DNA sequence motif and
7187 plots the corresponding sequence logo as introduced by Schneider and
7189 (license license:lgpl2.0+)))
7191 (define-public r-bsgenome-hsapiens-ucsc-hg19
7193 (name "r-bsgenome-hsapiens-ucsc-hg19")
7197 ;; We cannot use bioconductor-uri here because this tarball is
7198 ;; located under "data/annotation/" instead of "bioc/".
7199 (uri (string-append "http://www.bioconductor.org/packages/"
7200 "release/data/annotation/src/contrib/"
7201 "BSgenome.Hsapiens.UCSC.hg19_"
7205 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7207 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7208 (build-system r-build-system)
7209 ;; As this package provides little more than a very large data file it
7210 ;; doesn't make sense to build substitutes.
7211 (arguments `(#:substitutable? #f))
7213 `(("r-bsgenome" ,r-bsgenome)))
7215 "http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7216 (synopsis "Full genome sequences for Homo sapiens")
7218 "This package provides full genome sequences for Homo sapiens as provided
7219 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7220 (license license:artistic2.0)))
7222 (define-public r-bsgenome-mmusculus-ucsc-mm9
7224 (name "r-bsgenome-mmusculus-ucsc-mm9")
7228 ;; We cannot use bioconductor-uri here because this tarball is
7229 ;; located under "data/annotation/" instead of "bioc/".
7230 (uri (string-append "http://www.bioconductor.org/packages/"
7231 "release/data/annotation/src/contrib/"
7232 "BSgenome.Mmusculus.UCSC.mm9_"
7236 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7238 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7239 (build-system r-build-system)
7240 ;; As this package provides little more than a very large data file it
7241 ;; doesn't make sense to build substitutes.
7242 (arguments `(#:substitutable? #f))
7244 `(("r-bsgenome" ,r-bsgenome)))
7246 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7247 (synopsis "Full genome sequences for Mouse")
7249 "This package provides full genome sequences for Mus musculus (Mouse) as
7250 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7251 (license license:artistic2.0)))
7253 (define-public r-bsgenome-mmusculus-ucsc-mm10
7255 (name "r-bsgenome-mmusculus-ucsc-mm10")
7259 ;; We cannot use bioconductor-uri here because this tarball is
7260 ;; located under "data/annotation/" instead of "bioc/".
7261 (uri (string-append "http://www.bioconductor.org/packages/"
7262 "release/data/annotation/src/contrib/"
7263 "BSgenome.Mmusculus.UCSC.mm10_"
7267 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7269 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7270 (build-system r-build-system)
7271 ;; As this package provides little more than a very large data file it
7272 ;; doesn't make sense to build substitutes.
7273 (arguments `(#:substitutable? #f))
7275 `(("r-bsgenome" ,r-bsgenome)))
7277 "http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7278 (synopsis "Full genome sequences for Mouse")
7280 "This package provides full genome sequences for Mus
7281 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7282 in Biostrings objects.")
7283 (license license:artistic2.0)))
7285 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7287 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7291 ;; We cannot use bioconductor-uri here because this tarball is
7292 ;; located under "data/annotation/" instead of "bioc/".
7293 (uri (string-append "http://www.bioconductor.org/packages/"
7294 "release/data/annotation/src/contrib/"
7295 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7299 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7301 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7302 (build-system r-build-system)
7303 ;; As this package provides little more than a very large data file it
7304 ;; doesn't make sense to build substitutes.
7305 (arguments `(#:substitutable? #f))
7307 `(("r-bsgenome" ,r-bsgenome)
7308 ("r-genomicfeatures" ,r-genomicfeatures)
7309 ("r-annotationdbi" ,r-annotationdbi)))
7311 "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7312 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7314 "This package loads a TxDb object, which is an R interface to
7315 prefabricated databases contained in this package. This package provides
7316 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7317 based on the knownGene track.")
7318 (license license:artistic2.0)))
7320 (define-public r-bsgenome-celegans-ucsc-ce6
7322 (name "r-bsgenome-celegans-ucsc-ce6")
7326 ;; We cannot use bioconductor-uri here because this tarball is
7327 ;; located under "data/annotation/" instead of "bioc/".
7328 (uri (string-append "http://www.bioconductor.org/packages/"
7329 "release/data/annotation/src/contrib/"
7330 "BSgenome.Celegans.UCSC.ce6_"
7334 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7336 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7337 (build-system r-build-system)
7338 ;; As this package provides little more than a very large data file it
7339 ;; doesn't make sense to build substitutes.
7340 (arguments `(#:substitutable? #f))
7342 `(("r-bsgenome" ,r-bsgenome)))
7344 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7345 (synopsis "Full genome sequences for Worm")
7347 "This package provides full genome sequences for Caenorhabditis
7348 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7350 (license license:artistic2.0)))
7352 (define-public r-bsgenome-celegans-ucsc-ce10
7354 (name "r-bsgenome-celegans-ucsc-ce10")
7358 ;; We cannot use bioconductor-uri here because this tarball is
7359 ;; located under "data/annotation/" instead of "bioc/".
7360 (uri (string-append "http://www.bioconductor.org/packages/"
7361 "release/data/annotation/src/contrib/"
7362 "BSgenome.Celegans.UCSC.ce10_"
7366 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7368 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7369 (build-system r-build-system)
7370 ;; As this package provides little more than a very large data file it
7371 ;; doesn't make sense to build substitutes.
7372 (arguments `(#:substitutable? #f))
7374 `(("r-bsgenome" ,r-bsgenome)))
7376 "http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7377 (synopsis "Full genome sequences for Worm")
7379 "This package provides full genome sequences for Caenorhabditis
7380 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7382 (license license:artistic2.0)))
7384 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7386 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7390 ;; We cannot use bioconductor-uri here because this tarball is
7391 ;; located under "data/annotation/" instead of "bioc/".
7392 (uri (string-append "http://www.bioconductor.org/packages/"
7393 "release/data/annotation/src/contrib/"
7394 "BSgenome.Dmelanogaster.UCSC.dm3_"
7398 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7400 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7401 (build-system r-build-system)
7402 ;; As this package provides little more than a very large data file it
7403 ;; doesn't make sense to build substitutes.
7404 (arguments `(#:substitutable? #f))
7406 `(("r-bsgenome" ,r-bsgenome)))
7408 "http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7409 (synopsis "Full genome sequences for Fly")
7411 "This package provides full genome sequences for Drosophila
7412 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7413 Biostrings objects.")
7414 (license license:artistic2.0)))
7416 (define-public r-motifrg
7423 (uri (bioconductor-uri "motifRG" version))
7426 "1pa97aj6c5f3gx4bgriw110764dj3m9h104ddi8rv2bpy41yd98d"))))
7427 (properties `((upstream-name . "motifRG")))
7428 (build-system r-build-system)
7430 `(("r-biostrings" ,r-biostrings)
7431 ("r-bsgenome" ,r-bsgenome)
7432 ("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7433 ("r-iranges" ,r-iranges)
7434 ("r-seqlogo" ,r-seqlogo)
7435 ("r-xvector" ,r-xvector)))
7436 (home-page "http://bioconductor.org/packages/motifRG")
7437 (synopsis "Discover motifs in high throughput sequencing data")
7439 "This package provides tools for discriminative motif discovery in high
7440 throughput genetic sequencing data sets using regression methods.")
7441 (license license:artistic2.0)))
7443 (define-public r-qtl
7450 (uri (string-append "mirror://cran/src/contrib/qtl_"
7454 "05bj1x2ry0i7yqiydlswb3d2h4pxg70z8w1072az1mrv1m54k8sp"))))
7455 (build-system r-build-system)
7456 (home-page "http://rqtl.org/")
7457 (synopsis "R package for analyzing QTL experiments in genetics")
7458 (description "R/qtl is an extension library for the R statistics
7459 system. It is used to analyze experimental crosses for identifying
7460 genes contributing to variation in quantitative traits (so-called
7461 quantitative trait loci, QTLs).
7463 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7464 identify genotyping errors, and to perform single-QTL and two-QTL,
7465 two-dimensional genome scans.")
7466 (license license:gpl3)))
7468 (define-public r-zlibbioc
7474 (uri (bioconductor-uri "zlibbioc" version))
7477 "0hbk90q5hl0fycfvy5nxxa4hxgglag9lzp7i0fg849bqygg5nbyq"))))
7479 `((upstream-name . "zlibbioc")))
7480 (build-system r-build-system)
7481 (home-page "https://bioconductor.org/packages/zlibbioc")
7482 (synopsis "Provider for zlib-1.2.5 to R packages")
7483 (description "This package uses the source code of zlib-1.2.5 to create
7484 libraries for systems that do not have these available via other means.")
7485 (license license:artistic2.0)))
7487 (define-public r-r4rna
7494 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7498 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7499 (build-system r-build-system)
7501 `(("r-optparse" ,r-optparse)
7502 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7503 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7504 (synopsis "Analysis framework for RNA secondary structure")
7506 "The R4RNA package aims to be a general framework for the analysis of RNA
7507 secondary structure and comparative analysis in R.")
7508 (license license:gpl3+)))
7510 (define-public r-rhtslib
7517 (uri (bioconductor-uri "Rhtslib" version))
7520 "1vk3ng61dhi3pbia1lp3gl3mlr3i1vb2lkq83qb53i9dzz128wh9"))))
7521 (properties `((upstream-name . "Rhtslib")))
7522 (build-system r-build-system)
7524 `(("r-zlibbioc" ,r-zlibbioc)))
7528 `(("autoconf" ,autoconf)))
7529 (home-page "https://github.com/nhayden/Rhtslib")
7530 (synopsis "High-throughput sequencing library as an R package")
7532 "This package provides the HTSlib C library for high-throughput
7533 nucleotide sequence analysis. The package is primarily useful to developers
7534 of other R packages who wish to make use of HTSlib.")
7535 (license license:lgpl2.0+)))
7537 (define-public r-bamsignals
7539 (name "r-bamsignals")
7544 (uri (bioconductor-uri "bamsignals" version))
7547 "1k42gvk5mgq4la1fp0in3an2zfdz69h6522jsqhmk0f6i75kg4mb"))))
7548 (build-system r-build-system)
7550 `(("r-biocgenerics" ,r-biocgenerics)
7551 ("r-genomicranges" ,r-genomicranges)
7552 ("r-iranges" ,r-iranges)
7554 ("r-rhtslib" ,r-rhtslib)
7555 ("r-zlibbioc" ,r-zlibbioc)))
7558 (home-page "http://bioconductor.org/packages/bamsignals")
7559 (synopsis "Extract read count signals from bam files")
7561 "This package allows to efficiently obtain count vectors from indexed bam
7562 files. It counts the number of nucleotide sequence reads in given genomic
7563 ranges and it computes reads profiles and coverage profiles. It also handles
7565 (license license:gpl2+)))
7567 (define-public r-rcas
7573 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
7575 (file-name (string-append name "-" version ".tar.gz"))
7578 "1hd0r66556bxbdd82ksjklq7nfli36l4k6y88ic7kkg9873wa1nw"))))
7579 (build-system r-build-system)
7581 `(("r-knitr" ,r-knitr)
7582 ("r-testthat" ,r-testthat)
7583 ;; During vignette building knitr checks that "pandoc-citeproc"
7585 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
7587 `(("r-data-table" ,r-data-table)
7588 ("r-biomart" ,r-biomart)
7589 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
7590 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
7591 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
7592 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
7593 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7594 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
7595 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
7596 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
7597 ("r-topgo" ,r-topgo)
7599 ("r-plotly" ,r-plotly)
7600 ("r-plotrix" ,r-plotrix)
7601 ("r-motifrg" ,r-motifrg)
7602 ("r-genomation" ,r-genomation)
7603 ("r-genomicfeatures" ,r-genomicfeatures)
7604 ("r-rtracklayer" ,r-rtracklayer)
7605 ("r-rmarkdown" ,r-rmarkdown)))
7606 (synopsis "RNA-centric annotation system")
7608 "RCAS aims to be a standalone RNA-centric annotation system that provides
7609 intuitive reports and publication-ready graphics. This package provides the R
7610 library implementing most of the pipeline's features.")
7611 (home-page "https://github.com/BIMSBbioinfo/RCAS")
7612 (license license:expat)))
7614 (define-public rcas-web
7621 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
7622 "releases/download/v" version
7623 "/rcas-web-" version ".tar.gz"))
7626 "0d3my0g8i7js59n184zzzjdki7hgmhpi4rhfvk7i6jsw01ba04qq"))))
7627 (build-system gnu-build-system)
7630 (modify-phases %standard-phases
7631 (add-after 'install 'wrap-executable
7632 (lambda* (#:key inputs outputs #:allow-other-keys)
7633 (let* ((out (assoc-ref outputs "out"))
7634 (json (assoc-ref inputs "guile-json"))
7635 (redis (assoc-ref inputs "guile-redis"))
7636 (path (string-append
7637 json "/share/guile/site/2.2:"
7638 redis "/share/guile/site/2.2")))
7639 (wrap-program (string-append out "/bin/rcas-web")
7640 `("GUILE_LOAD_PATH" ":" = (,path))
7641 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
7642 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
7645 `(("r-minimal" ,r-minimal)
7647 ("guile-next" ,guile-2.2)
7648 ("guile-json" ,guile2.2-json)
7649 ("guile-redis" ,guile2.2-redis)))
7651 `(("pkg-config" ,pkg-config)))
7652 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
7653 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
7654 (description "This package provides a simple web interface for the
7655 @dfn{RNA-centric annotation system} (RCAS).")
7656 (license license:agpl3+)))
7658 (define-public r-mutationalpatterns
7660 (name "r-mutationalpatterns")
7665 (uri (bioconductor-uri "MutationalPatterns" version))
7668 "1a3c2bm0xx0q4gf98jiw74msmdf2fr8rbsdysd5ww9kqlzmsbr17"))))
7669 (build-system r-build-system)
7671 `(("r-biocgenerics" ,r-biocgenerics)
7672 ("r-biostrings" ,r-biostrings)
7673 ("r-genomicranges" ,r-genomicranges)
7674 ("r-genomeinfodb" ,r-genomeinfodb)
7675 ("r-ggplot2" ,r-ggplot2)
7676 ("r-gridextra" ,r-gridextra)
7677 ("r-iranges" ,r-iranges)
7680 ("r-pracma" ,r-pracma)
7681 ("r-reshape2" ,r-reshape2)
7682 ("r-summarizedexperiment" ,r-summarizedexperiment)
7683 ("r-variantannotation" ,r-variantannotation)))
7684 (home-page "http://bioconductor.org/packages/MutationalPatterns/")
7685 (synopsis "Extract and visualize mutational patterns in genomic data")
7686 (description "This package provides an extensive toolset for the
7687 characterization and visualization of a wide range of mutational patterns
7688 in SNV base substitution data.")
7689 (license license:expat)))
7691 (define-public r-wgcna
7698 (uri (cran-uri "WGCNA" version))
7701 "0hzvnhw76vwg8bl8x368f0c5szpwb8323bmrb3bir93i5bmfjsxx"))))
7702 (properties `((upstream-name . "WGCNA")))
7703 (build-system r-build-system)
7705 `(("r-annotationdbi" ,r-annotationdbi)
7706 ("r-doparallel" ,r-doparallel)
7707 ("r-dynamictreecut" ,r-dynamictreecut)
7708 ("r-fastcluster" ,r-fastcluster)
7709 ("r-foreach" ,r-foreach)
7710 ("r-go-db" ,r-go-db)
7711 ("r-hmisc" ,r-hmisc)
7712 ("r-impute" ,r-impute)
7713 ("r-matrixstats" ,r-matrixstats)
7714 ("r-preprocesscore" ,r-preprocesscore)))
7716 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
7717 (synopsis "Weighted correlation network analysis")
7719 "This package provides functions necessary to perform Weighted
7720 Correlation Network Analysis on high-dimensional data. It includes functions
7721 for rudimentary data cleaning, construction and summarization of correlation
7722 networks, module identification and functions for relating both variables and
7723 modules to sample traits. It also includes a number of utility functions for
7724 data manipulation and visualization.")
7725 (license license:gpl2+)))
7727 (define-public r-chipkernels
7728 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
7731 (name "r-chipkernels")
7732 (version (string-append "1.1-" revision "." (string-take commit 9)))
7737 (url "https://github.com/ManuSetty/ChIPKernels.git")
7739 (file-name (string-append name "-" version))
7742 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
7743 (build-system r-build-system)
7745 `(("r-iranges" ,r-iranges)
7746 ("r-xvector" ,r-xvector)
7747 ("r-biostrings" ,r-biostrings)
7748 ("r-bsgenome" ,r-bsgenome)
7749 ("r-gtools" ,r-gtools)
7750 ("r-genomicranges" ,r-genomicranges)
7751 ("r-sfsmisc" ,r-sfsmisc)
7752 ("r-kernlab" ,r-kernlab)
7753 ("r-s4vectors" ,r-s4vectors)
7754 ("r-biocgenerics" ,r-biocgenerics)))
7755 (home-page "https://github.com/ManuSetty/ChIPKernels")
7756 (synopsis "Build string kernels for DNA Sequence analysis")
7757 (description "ChIPKernels is an R package for building different string
7758 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
7759 must be built and this dictionary can be used for determining kernels for DNA
7761 (license license:gpl2+))))
7763 (define-public r-seqgl
7770 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
7771 "archive/" version ".tar.gz"))
7772 (file-name (string-append name "-" version ".tar.gz"))
7775 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
7776 (build-system r-build-system)
7778 `(("r-biostrings" ,r-biostrings)
7779 ("r-chipkernels" ,r-chipkernels)
7780 ("r-genomicranges" ,r-genomicranges)
7781 ("r-spams" ,r-spams)
7782 ("r-wgcna" ,r-wgcna)
7783 ("r-fastcluster" ,r-fastcluster)))
7784 (home-page "https://github.com/ManuSetty/SeqGL")
7785 (synopsis "Group lasso for Dnase/ChIP-seq data")
7786 (description "SeqGL is a group lasso based algorithm to extract
7787 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
7788 This package presents a method which uses group lasso to discriminate between
7789 bound and non bound genomic regions to accurately identify transcription
7790 factors bound at the specific regions.")
7791 (license license:gpl2+)))
7793 (define-public r-gkmsvm
7800 (uri (cran-uri "gkmSVM" version))
7803 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
7804 (properties `((upstream-name . "gkmSVM")))
7805 (build-system r-build-system)
7807 `(("r-biocgenerics" ,r-biocgenerics)
7808 ("r-biostrings" ,r-biostrings)
7809 ("r-genomeinfodb" ,r-genomeinfodb)
7810 ("r-genomicranges" ,r-genomicranges)
7811 ("r-iranges" ,r-iranges)
7812 ("r-kernlab" ,r-kernlab)
7815 ("r-rtracklayer" ,r-rtracklayer)
7816 ("r-s4vectors" ,r-s4vectors)
7817 ("r-seqinr" ,r-seqinr)))
7818 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
7819 (synopsis "Gapped-kmer support vector machine")
7821 "This R package provides tools for training gapped-kmer SVM classifiers
7822 for DNA and protein sequences. This package supports several sequence
7823 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
7824 (license license:gpl2+)))
7826 (define-public r-tximport
7832 (uri (bioconductor-uri "tximport" version))
7835 "1k5a7dad6zqg936s17f6cmwgqp11x24z9zhxndsgwbscgpyhpcb0"))))
7836 (build-system r-build-system)
7837 (home-page "http://bioconductor.org/packages/tximport")
7838 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
7840 "This package provides tools to import transcript-level abundance,
7841 estimated counts and transcript lengths, and to summarize them into matrices
7842 for use with downstream gene-level analysis packages. Average transcript
7843 length, weighted by sample-specific transcript abundance estimates, is
7844 provided as a matrix which can be used as an offset for different expression
7845 of gene-level counts.")
7846 (license license:gpl2+)))
7848 (define-public r-rhdf5
7854 (uri (bioconductor-uri "rhdf5" version))
7857 "0pb04li55ysag30s7rap7nnivc0rqmgsmpj43kin0rxdabfn1w0k"))))
7858 (build-system r-build-system)
7861 (modify-phases %standard-phases
7862 (add-after 'unpack 'unpack-smallhdf5
7863 (lambda* (#:key outputs #:allow-other-keys)
7864 (system* "tar" "-xzvf"
7865 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
7866 (substitute* "src/Makevars"
7867 (("^.*cd hdf5source &&.*$") "")
7868 (("^.*gunzip -dc hdf5small.tgz.*$") "")
7869 (("^.*rm -rf hdf5.*$") "")
7870 (("^.*mv hdf5source/hdf5 ..*$") ""))
7871 (substitute* "src/hdf5/configure"
7875 `(("r-zlibbioc" ,r-zlibbioc)))
7879 (home-page "http://bioconductor.org/packages/rhdf5")
7880 (synopsis "HDF5 interface to R")
7882 "This R/Bioconductor package provides an interface between HDF5 and R.
7883 HDF5's main features are the ability to store and access very large and/or
7884 complex datasets and a wide variety of metadata on mass storage (disk) through
7885 a completely portable file format. The rhdf5 package is thus suited for the
7886 exchange of large and/or complex datasets between R and other software
7887 package, and for letting R applications work on datasets that are larger than
7888 the available RAM.")
7889 (license license:artistic2.0)))
7891 (define-public emboss
7897 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
7898 (version-major+minor version) ".0/"
7899 "EMBOSS-" version ".tar.gz"))
7902 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
7903 (build-system gnu-build-system)
7906 (list (string-append "--with-hpdf="
7907 (assoc-ref %build-inputs "libharu")))
7909 (modify-phases %standard-phases
7910 (add-after 'unpack 'fix-checks
7912 ;; The PNGDRIVER tests check for the presence of libgd, libpng
7913 ;; and zlib, but assume that they are all found at the same
7915 (substitute* "configure.in"
7916 (("CHECK_PNGDRIVER")
7917 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
7918 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
7919 AM_CONDITIONAL(AMPNG, true)"))
7921 (add-after 'unpack 'disable-update-check
7923 ;; At build time there is no connection to the Internet, so
7924 ;; looking for updates will not work.
7925 (substitute* "Makefile.am"
7926 (("\\$\\(bindir\\)/embossupdate") ""))
7928 (add-before 'configure 'autogen
7929 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
7935 ("libharu" ,libharu)
7938 `(("autoconf" ,autoconf)
7939 ("automake" ,automake)
7940 ("libtool" ,libtool)
7941 ("pkg-config" ,pkg-config)))
7942 (home-page "http://emboss.sourceforge.net")
7943 (synopsis "Molecular biology analysis suite")
7944 (description "EMBOSS is the \"European Molecular Biology Open Software
7945 Suite\". EMBOSS is an analysis package specially developed for the needs of
7946 the molecular biology (e.g. EMBnet) user community. The software
7947 automatically copes with data in a variety of formats and even allows
7948 transparent retrieval of sequence data from the web. It also provides a
7949 number of libraries for the development of software in the field of molecular
7950 biology. EMBOSS also integrates a range of currently available packages and
7951 tools for sequence analysis into a seamless whole.")
7952 (license license:gpl2+)))
7955 (let ((revision "1")
7956 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
7959 ;; The version is 2.13.0 even though no release archives have been
7960 ;; published as yet.
7961 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
7965 (url "https://github.com/arq5x/bits.git")
7967 (file-name (string-append name "-" version "-checkout"))
7970 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
7971 (build-system gnu-build-system)
7973 `(#:tests? #f ;no tests included
7975 (modify-phases %standard-phases
7977 (add-after 'unpack 'remove-cuda
7979 (substitute* "Makefile"
7981 (("(bits_test_intersections) \\\\" _ match) match))
7984 (lambda* (#:key outputs #:allow-other-keys)
7986 "bin" (string-append (assoc-ref outputs "out") "/bin"))
7991 (home-page "https://github.com/arq5x/bits")
7992 (synopsis "Implementation of binary interval search algorithm")
7993 (description "This package provides an implementation of the
7994 BITS (Binary Interval Search) algorithm, an approach to interval set
7995 intersection. It is especially suited for the comparison of diverse genomic
7996 datasets and the exploration of large datasets of genome
7997 intervals (e.g. genes, sequence alignments).")
7998 (license license:gpl2))))
8000 (define-public piranha
8001 ;; There is no release tarball for the latest version. The latest commit is
8002 ;; older than one year at the time of this writing.
8003 (let ((revision "1")
8004 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8007 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8011 (url "https://github.com/smithlabcode/piranha.git")
8015 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8016 (build-system gnu-build-system)
8018 `(#:test-target "test"
8020 (modify-phases %standard-phases
8021 (add-after 'unpack 'copy-smithlab-cpp
8022 (lambda* (#:key inputs #:allow-other-keys)
8023 (for-each (lambda (file)
8024 (install-file file "./src/smithlab_cpp/"))
8025 (find-files (assoc-ref inputs "smithlab-cpp")))
8027 (add-after 'install 'install-to-store
8028 (lambda* (#:key outputs #:allow-other-keys)
8029 (let* ((out (assoc-ref outputs "out"))
8030 (bin (string-append out "/bin")))
8031 (for-each (lambda (file)
8032 (install-file file bin))
8033 (find-files "bin" ".*")))
8036 (list (string-append "--with-bam_tools_headers="
8037 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8038 (string-append "--with-bam_tools_library="
8039 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8041 `(("bamtools" ,bamtools)
8042 ("samtools" ,samtools-0.1)
8045 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8049 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8051 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8054 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8056 `(("python" ,python-2)))
8057 (home-page "https://github.com/smithlabcode/piranha")
8058 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8060 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8061 RIP-seq experiments. It takes input in BED or BAM format and identifies
8062 regions of statistically significant read enrichment. Additional covariates
8063 may optionally be provided to further inform the peak-calling process.")
8064 (license license:gpl3+))))
8072 (uri (string-append "https://pypi.python.org/packages/source/P"
8073 "/PePr/PePr-" version ".tar.gz"))
8076 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8077 (build-system python-build-system)
8079 `(#:python ,python-2 ; python2 only
8080 #:tests? #f)) ; no tests included
8082 `(("python2-numpy" ,python2-numpy)
8083 ("python2-scipy" ,python2-scipy)
8084 ("python2-pysam" ,python2-pysam)))
8085 (home-page "https://github.com/shawnzhangyx/PePr")
8086 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8088 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8089 that is primarily designed for data with biological replicates. It uses a
8090 negative binomial distribution to model the read counts among the samples in
8091 the same group, and look for consistent differences between ChIP and control
8092 group or two ChIP groups run under different conditions.")
8093 (license license:gpl3+)))
8095 (define-public filevercmp
8096 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8099 (version (string-append "0-1." (string-take commit 7)))
8102 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8104 (file-name (string-append name "-" version ".tar.gz"))
8106 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8107 (build-system gnu-build-system)
8109 `(#:tests? #f ; There are no tests to run.
8111 (modify-phases %standard-phases
8112 (delete 'configure) ; There is no configure phase.
8114 (lambda* (#:key outputs #:allow-other-keys)
8115 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8116 (install-file "filevercmp" bin)))))))
8117 (home-page "https://github.com/ekg/filevercmp")
8118 (synopsis "This program compares version strings")
8119 (description "This program compares version strings. It intends to be a
8120 replacement for strverscmp.")
8121 (license license:gpl3+))))
8123 (define-public multiqc
8130 (uri (pypi-uri "multiqc" version))
8133 "12gs1jw2jrxrij529rnl5kaqxfcqn15yzcsggxkfhdx634ml0cny"))
8134 (patches (search-patches "multiqc-fix-git-subprocess-error.patch"))))
8135 (build-system python-build-system)
8137 ;; Tests are to be introduced in the next version, see
8138 ;; https://github.com/ewels/MultiQC/issues/376
8141 `(("python-jinja2" ,python-jinja2)
8142 ("python-simplejson" ,python-simplejson)
8143 ("python-pyyaml" ,python-pyyaml)
8144 ("python-click" ,python-click)
8145 ("python-matplotlib" ,python-matplotlib)
8146 ("python-numpy" ,python-numpy)
8147 ;; MultQC checks for the presence of nose at runtime.
8148 ("python-nose" ,python-nose)))
8149 (home-page "http://multiqc.info")
8150 (synopsis "Aggregate bioinformatics analysis reports")
8152 "MultiQC is a tool to aggregate bioinformatics results across many
8153 samples into a single report. It contains modules for a large number of
8154 common bioinformatics tools.")
8155 (license license:gpl3)))
8157 (define-public r-chipseq
8164 (uri (bioconductor-uri "chipseq" version))
8167 "115ayp82rs99iaswrx45skw1i5iacgwzz5k8rzijbp5qic0554n0"))))
8168 (build-system r-build-system)
8170 `(("r-biocgenerics" ,r-biocgenerics)
8171 ("r-genomicranges" ,r-genomicranges)
8172 ("r-iranges" ,r-iranges)
8173 ("r-s4vectors" ,r-s4vectors)
8174 ("r-shortread" ,r-shortread)))
8175 (home-page "http://bioconductor.org/packages/chipseq")
8176 (synopsis "Package for analyzing ChIPseq data")
8178 "This package provides tools for processing short read data from ChIPseq
8180 (license license:artistic2.0)))
8182 (define-public r-copyhelper
8184 (name "r-copyhelper")
8189 (uri (string-append "http://bioconductor.org/packages/release/"
8190 "data/experiment/src/contrib/CopyhelpeR_"
8194 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8195 (properties `((upstream-name . "CopyhelpeR")))
8196 (build-system r-build-system)
8197 (home-page "http://bioconductor.org/packages/CopyhelpeR/")
8198 (synopsis "Helper files for CopywriteR")
8200 "This package contains the helper files that are required to run the
8201 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8202 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8203 mm10. In addition, it contains a blacklist filter to remove regions that
8204 display copy number variation. Files are stored as GRanges objects from the
8205 GenomicRanges Bioconductor package.")
8206 (license license:gpl2)))
8208 (define-public r-copywriter
8210 (name "r-copywriter")
8215 (uri (bioconductor-uri "CopywriteR" version))
8218 "1bwwnsyk7cpgwkagsnn5mv6fv233b0rkhjvbadrh70h8m4anawfj"))))
8219 (properties `((upstream-name . "CopywriteR")))
8220 (build-system r-build-system)
8222 `(("r-biocparallel" ,r-biocparallel)
8223 ("r-chipseq" ,r-chipseq)
8224 ("r-copyhelper" ,r-copyhelper)
8225 ("r-data-table" ,r-data-table)
8226 ("r-dnacopy" ,r-dnacopy)
8227 ("r-futile-logger" ,r-futile-logger)
8228 ("r-genomeinfodb" ,r-genomeinfodb)
8229 ("r-genomicalignments" ,r-genomicalignments)
8230 ("r-genomicranges" ,r-genomicranges)
8231 ("r-gtools" ,r-gtools)
8232 ("r-iranges" ,r-iranges)
8233 ("r-matrixstats" ,r-matrixstats)
8234 ("r-rsamtools" ,r-rsamtools)
8235 ("r-s4vectors" ,r-s4vectors)))
8236 (home-page "https://github.com/PeeperLab/CopywriteR")
8237 (synopsis "Copy number information from targeted sequencing")
8239 "CopywriteR extracts DNA copy number information from targeted sequencing
8240 by utilizing off-target reads. It allows for extracting uniformly distributed
8241 copy number information, can be used without reference, and can be applied to
8242 sequencing data obtained from various techniques including chromatin
8243 immunoprecipitation and target enrichment on small gene panels. Thereby,
8244 CopywriteR constitutes a widely applicable alternative to available copy
8245 number detection tools.")
8246 (license license:gpl2)))
8248 (define-public r-sva
8255 (uri (bioconductor-uri "sva" version))
8258 "1wc1fjm6dzlsqqagm43y57w8jh8nsh0r0m8z1p6ximcb5gxqh7hn"))))
8259 (build-system r-build-system)
8261 `(("r-genefilter" ,r-genefilter)
8262 ("r-mgcv" ,r-mgcv)))
8263 (home-page "http://bioconductor.org/packages/sva")
8264 (synopsis "Surrogate variable analysis")
8266 "This package contains functions for removing batch effects and other
8267 unwanted variation in high-throughput experiment. It also contains functions
8268 for identifying and building surrogate variables for high-dimensional data
8269 sets. Surrogate variables are covariates constructed directly from
8270 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8271 imaging data that can be used in subsequent analyses to adjust for unknown,
8272 unmodeled, or latent sources of noise.")
8273 (license license:artistic2.0)))
8275 (define-public r-seqminer
8282 (uri (cran-uri "seqminer" version))
8285 "0p75wyl70cvp36mwg5y74nv573j1gdqi15ac2a7xf61jmsq7ycpy"))))
8286 (build-system r-build-system)
8289 (home-page "http://seqminer.genomic.codes")
8290 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8292 "This package provides tools to integrate nucleotide sequencing
8293 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8294 ;; Any version of the GPL is acceptable
8295 (license (list license:gpl2+ license:gpl3+))))
8297 (define-public r-raremetals2
8299 (name "r-raremetals2")
8304 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8305 "b/b7/RareMETALS2_" version ".tar.gz"))
8308 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8309 (properties `((upstream-name . "RareMETALS2")))
8310 (build-system r-build-system)
8312 `(("r-seqminer" ,r-seqminer)
8313 ("r-mvtnorm" ,r-mvtnorm)
8315 ("r-compquadform" ,r-compquadform)
8316 ("r-getopt" ,r-getopt)))
8317 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8318 (synopsis "Analyze gene-level association tests for binary trait")
8320 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8321 It was designed to meta-analyze gene-level association tests for binary trait.
8322 While rareMETALS offers a near-complete solution for meta-analysis of
8323 gene-level tests for quantitative trait, it does not offer the optimal
8324 solution for binary trait. The package rareMETALS2 offers improved features
8325 for analyzing gene-level association tests in meta-analyses for binary
8327 (license license:gpl3)))
8329 (define-public r-maldiquant
8331 (name "r-maldiquant")
8336 (uri (cran-uri "MALDIquant" version))
8339 "0z5srzsfgsgi4bssr4chls4ry6d18y2g9143znqmraylppwrrqzr"))))
8340 (properties `((upstream-name . "MALDIquant")))
8341 (build-system r-build-system)
8342 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8343 (synopsis "Quantitative analysis of mass spectrometry data")
8345 "This package provides a complete analysis pipeline for matrix-assisted
8346 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8347 two-dimensional mass spectrometry data. In addition to commonly used plotting
8348 and processing methods it includes distinctive features, namely baseline
8349 subtraction methods such as morphological filters (TopHat) or the
8350 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8351 alignment using warping functions, handling of replicated measurements as well
8352 as allowing spectra with different resolutions.")
8353 (license license:gpl3+)))
8355 (define-public r-protgenerics
8357 (name "r-protgenerics")
8362 (uri (bioconductor-uri "ProtGenerics" version))
8365 "0hb3vrrvfx6lcfalmjxm8dmigfmi5nba0pzjfgsrzd35c8mbfc6f"))))
8366 (properties `((upstream-name . "ProtGenerics")))
8367 (build-system r-build-system)
8368 (home-page "https://github.com/lgatto/ProtGenerics")
8369 (synopsis "S4 generic functions for proteomics infrastructure")
8371 "This package provides S4 generic functions needed by Bioconductor
8372 proteomics packages.")
8373 (license license:artistic2.0)))
8375 (define-public r-mzr
8382 (uri (bioconductor-uri "mzR" version))
8385 "0ipmhg6l3pf648rdx5g2ha7l5ppd3cja6afxhdw76x8ga3633x0r"))))
8386 (properties `((upstream-name . "mzR")))
8387 (build-system r-build-system)
8389 `(("netcdf" ,netcdf)))
8391 `(("r-biobase" ,r-biobase)
8392 ("r-biocgenerics" ,r-biocgenerics)
8393 ("r-protgenerics" ,r-protgenerics)
8395 ("r-zlibbioc" ,r-zlibbioc)))
8396 (home-page "https://github.com/sneumann/mzR/")
8397 (synopsis "Parser for mass spectrometry data files")
8399 "The mzR package provides a unified API to the common file formats and
8400 parsers available for mass spectrometry data. It comes with a wrapper for the
8401 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8402 The package contains the original code written by the ISB, and a subset of the
8403 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8404 previously been used in XCMS.")
8405 (license license:artistic2.0)))
8407 (define-public r-affyio
8414 (uri (bioconductor-uri "affyio" version))
8417 "1svsl4mpk06xm505pap913x69ywks99262krag8y4ygpllj7dfyy"))))
8418 (build-system r-build-system)
8420 `(("r-zlibbioc" ,r-zlibbioc)))
8423 (home-page "https://github.com/bmbolstad/affyio")
8424 (synopsis "Tools for parsing Affymetrix data files")
8426 "This package provides routines for parsing Affymetrix data files based
8427 upon file format information. The primary focus is on accessing the CEL and
8429 (license license:lgpl2.0+)))
8431 (define-public r-affy
8438 (uri (bioconductor-uri "affy" version))
8441 "1snq71ligf0wvaxa6zfrl13ydw0zfhspmhdyfk8q3ba3np4cz344"))))
8442 (build-system r-build-system)
8444 `(("r-affyio" ,r-affyio)
8445 ("r-biobase" ,r-biobase)
8446 ("r-biocgenerics" ,r-biocgenerics)
8447 ("r-biocinstaller" ,r-biocinstaller)
8448 ("r-preprocesscore" ,r-preprocesscore)
8449 ("r-zlibbioc" ,r-zlibbioc)))
8450 (home-page "http://bioconductor.org/packages/affy")
8451 (synopsis "Methods for affymetrix oligonucleotide arrays")
8453 "This package contains functions for exploratory oligonucleotide array
8455 (license license:lgpl2.0+)))
8457 (define-public r-vsn
8464 (uri (bioconductor-uri "vsn" version))
8467 "0mgl0azys2g90simf8wx6jdwd7gyg3m4pf12n6w6507jixm2cg97"))))
8468 (build-system r-build-system)
8470 `(("r-affy" ,r-affy)
8471 ("r-biobase" ,r-biobase)
8472 ("r-ggplot2" ,r-ggplot2)
8473 ("r-lattice" ,r-lattice)
8474 ("r-limma" ,r-limma)))
8475 (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
8476 (synopsis "Variance stabilization and calibration for microarray data")
8478 "The package implements a method for normalising microarray intensities,
8479 and works for single- and multiple-color arrays. It can also be used for data
8480 from other technologies, as long as they have similar format. The method uses
8481 a robust variant of the maximum-likelihood estimator for an
8482 additive-multiplicative error model and affine calibration. The model
8483 incorporates data calibration step (a.k.a. normalization), a model for the
8484 dependence of the variance on the mean intensity and a variance stabilizing
8485 data transformation. Differences between transformed intensities are
8486 analogous to \"normalized log-ratios\". However, in contrast to the latter,
8487 their variance is independent of the mean, and they are usually more sensitive
8488 and specific in detecting differential transcription.")
8489 (license license:artistic2.0)))
8491 (define-public r-mzid
8498 (uri (bioconductor-uri "mzID" version))
8501 "1zn896cpfvqp1qmq5c4vcj933hb8rxwb6gkck1wqvr7393rpqy1q"))))
8502 (properties `((upstream-name . "mzID")))
8503 (build-system r-build-system)
8505 `(("r-doparallel" ,r-doparallel)
8506 ("r-foreach" ,r-foreach)
8507 ("r-iterators" ,r-iterators)
8509 ("r-protgenerics" ,r-protgenerics)
8512 (home-page "http://bioconductor.org/packages/mzID")
8513 (synopsis "Parser for mzIdentML files")
8515 "This package provides a parser for mzIdentML files implemented using the
8516 XML package. The parser tries to be general and able to handle all types of
8517 mzIdentML files with the drawback of having less pretty output than a vendor
8519 (license license:gpl2+)))
8521 (define-public r-pcamethods
8523 (name "r-pcamethods")
8528 (uri (bioconductor-uri "pcaMethods" version))
8531 "18mawhxw57pgpn87qha4mwki24gqja7wpqha8q496476vyap11xw"))))
8532 (properties `((upstream-name . "pcaMethods")))
8533 (build-system r-build-system)
8535 `(("r-biobase" ,r-biobase)
8536 ("r-biocgenerics" ,r-biocgenerics)
8538 ("r-rcpp" ,r-rcpp)))
8539 (home-page "https://github.com/hredestig/pcamethods")
8540 (synopsis "Collection of PCA methods")
8542 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
8543 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
8544 for missing value estimation is included for comparison. BPCA, PPCA and
8545 NipalsPCA may be used to perform PCA on incomplete data as well as for
8546 accurate missing value estimation. A set of methods for printing and plotting
8547 the results is also provided. All PCA methods make use of the same data
8548 structure (pcaRes) to provide a common interface to the PCA results.")
8549 (license license:gpl3+)))
8551 (define-public r-msnbase
8558 (uri (bioconductor-uri "MSnbase" version))
8561 "0jjjs29dcwsjaxzfqxy98ycpg3rwxzzchkj77my3cjgdc00sm66n"))))
8562 (properties `((upstream-name . "MSnbase")))
8563 (build-system r-build-system)
8565 `(("r-affy" ,r-affy)
8566 ("r-biobase" ,r-biobase)
8567 ("r-biocgenerics" ,r-biocgenerics)
8568 ("r-biocparallel" ,r-biocparallel)
8569 ("r-digest" ,r-digest)
8570 ("r-ggplot2" ,r-ggplot2)
8571 ("r-impute" ,r-impute)
8572 ("r-iranges" ,r-iranges)
8573 ("r-maldiquant" ,r-maldiquant)
8576 ("r-pcamethods" ,r-pcamethods)
8578 ("r-preprocesscore" ,r-preprocesscore)
8579 ("r-protgenerics" ,r-protgenerics)
8581 ("r-reshape2" ,r-reshape2)
8582 ("r-s4vectors" ,r-s4vectors)
8585 (home-page "https://github.com/lgatto/MSnbase")
8586 (synopsis "Base functions and classes for MS-based proteomics")
8588 "This package provides basic plotting, data manipulation and processing
8589 of mass spectrometry based proteomics data.")
8590 (license license:artistic2.0)))
8592 (define-public r-msnid
8599 (uri (bioconductor-uri "MSnID" version))
8602 "0fkk3za39cxi0jyxmagmycjdslr2xf6vg3ylz14jyffqi0blw9d5"))))
8603 (properties `((upstream-name . "MSnID")))
8604 (build-system r-build-system)
8606 `(("r-biobase" ,r-biobase)
8607 ("r-data-table" ,r-data-table)
8608 ("r-doparallel" ,r-doparallel)
8609 ("r-dplyr" ,r-dplyr)
8610 ("r-foreach" ,r-foreach)
8611 ("r-iterators" ,r-iterators)
8612 ("r-msnbase" ,r-msnbase)
8615 ("r-protgenerics" ,r-protgenerics)
8616 ("r-r-cache" ,r-r-cache)
8618 ("r-reshape2" ,r-reshape2)))
8619 (home-page "http://bioconductor.org/packages/MSnID")
8620 (synopsis "Utilities for LC-MSn proteomics identifications")
8622 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
8623 from mzIdentML (leveraging the mzID package) or text files. After collating
8624 the search results from multiple datasets it assesses their identification
8625 quality and optimize filtering criteria to achieve the maximum number of
8626 identifications while not exceeding a specified false discovery rate. It also
8627 contains a number of utilities to explore the MS/MS results and assess missed
8628 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
8629 (license license:artistic2.0)))
8631 (define-public r-seurat
8632 ;; Source releases are only made for new x.0 versions. All newer versions
8633 ;; are only released as pre-built binaries. At the time of this writing the
8634 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
8635 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
8639 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
8643 (url "https://github.com/satijalab/seurat")
8645 (file-name (string-append name "-" version "-checkout"))
8648 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
8649 ;; Delete pre-built jar.
8651 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
8653 (build-system r-build-system)
8656 (modify-phases %standard-phases
8657 (add-after 'unpack 'build-jar
8658 (lambda* (#:key inputs #:allow-other-keys)
8659 (let ((classesdir "tmp-classes"))
8660 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
8662 (and (zero? (apply system* `("javac" "-d" ,classesdir
8663 ,@(find-files "java" "\\.java$"))))
8664 (zero? (system* "jar"
8665 "-cf" "inst/java/ModularityOptimizer.jar"
8666 "-C" classesdir ".")))))))))
8668 `(("jdk" ,icedtea "jdk")))
8671 ("r-caret" ,r-caret)
8672 ("r-cowplot" ,r-cowplot)
8673 ("r-dplyr" ,r-dplyr)
8674 ("r-fastica" ,r-fastica)
8677 ("r-gdata" ,r-gdata)
8678 ("r-ggplot2" ,r-ggplot2)
8679 ("r-gplots" ,r-gplots)
8680 ("r-gridextra" ,r-gridextra)
8681 ("r-igraph" ,r-igraph)
8682 ("r-irlba" ,r-irlba)
8684 ("r-mixtools" ,r-mixtools)
8685 ("r-pbapply" ,r-pbapply)
8687 ("r-ranger" ,r-ranger)
8688 ("r-rcolorbrewer" ,r-rcolorbrewer)
8690 ("r-rcppeigen" ,r-rcppeigen)
8691 ("r-rcppprogress" ,r-rcppprogress)
8692 ("r-reshape2" ,r-reshape2)
8694 ("r-rtsne" ,r-rtsne)
8695 ("r-stringr" ,r-stringr)
8696 ("r-tclust" ,r-tclust)
8698 ("r-vgam" ,r-vgam)))
8699 (home-page "http://www.satijalab.org/seurat")
8700 (synopsis "Seurat is an R toolkit for single cell genomics")
8702 "This package is an R package designed for QC, analysis, and
8703 exploration of single cell RNA-seq data. It easily enables widely-used
8704 analytical techniques, including the identification of highly variable genes,
8705 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
8706 algorithms; density clustering, hierarchical clustering, k-means, and the
8707 discovery of differentially expressed genes and markers.")
8708 (license license:gpl3))))
8710 (define htslib-for-sambamba
8711 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
8714 (name "htslib-for-sambamba")
8715 (version (string-append "1.3.1-1." (string-take commit 9)))
8720 (url "https://github.com/lomereiter/htslib.git")
8722 (file-name (string-append "htslib-" version "-checkout"))
8725 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
8727 (substitute-keyword-arguments (package-arguments htslib)
8729 `(modify-phases ,phases
8730 (add-before 'configure 'bootstrap
8732 (zero? (system* "autoreconf" "-vif"))))))))
8734 `(("autoconf" ,autoconf)
8735 ("automake" ,automake)
8736 ,@(package-native-inputs htslib))))))
8738 (define-public sambamba
8745 (uri (string-append "https://github.com/lomereiter/sambamba/"
8746 "archive/v" version ".tar.gz"))
8747 (file-name (string-append name "-" version ".tar.gz"))
8750 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
8751 (build-system gnu-build-system)
8753 `(#:tests? #f ; there is no test target
8756 ;; Override "--compiler" flag only.
8757 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
8758 "sambamba-ldmd2-64")
8760 (modify-phases %standard-phases
8762 (add-after 'unpack 'place-biod
8763 (lambda* (#:key inputs #:allow-other-keys)
8764 (copy-recursively (assoc-ref inputs "biod") "BioD")
8766 (add-after 'unpack 'unbundle-prerequisites
8768 (substitute* "Makefile"
8769 ((" htslib-static lz4-static") ""))
8772 (lambda* (#:key outputs #:allow-other-keys)
8773 (let* ((out (assoc-ref outputs "out"))
8774 (bin (string-append out "/bin")))
8776 (install-file "build/sambamba" bin)
8782 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
8786 (url "https://github.com/biod/BioD.git")
8788 (file-name (string-append "biod-"
8789 (string-take commit 9)
8793 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
8796 ("htslib" ,htslib-for-sambamba)))
8797 (home-page "http://lomereiter.github.io/sambamba")
8798 (synopsis "Tools for working with SAM/BAM data")
8799 (description "Sambamba is a high performance modern robust and
8800 fast tool (and library), written in the D programming language, for
8801 working with SAM and BAM files. Current parallelised functionality is
8802 an important subset of samtools functionality, including view, index,
8803 sort, markdup, and depth.")
8804 (license license:gpl2+)))