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, 2017 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017 Tobias Geerinckx-Rice <me@tobias.gr>
12 ;;; This file is part of GNU Guix.
14 ;;; GNU Guix is free software; you can redistribute it and/or modify it
15 ;;; under the terms of the GNU General Public License as published by
16 ;;; the Free Software Foundation; either version 3 of the License, or (at
17 ;;; your option) any later version.
19 ;;; GNU Guix is distributed in the hope that it will be useful, but
20 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
21 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
22 ;;; GNU General Public License for more details.
24 ;;; You should have received a copy of the GNU General Public License
25 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
27 (define-module (gnu packages bioinformatics)
28 #:use-module ((guix licenses) #:prefix license:)
29 #:use-module (guix packages)
30 #:use-module (guix utils)
31 #:use-module (guix download)
32 #:use-module (guix git-download)
33 #:use-module (guix hg-download)
34 #:use-module (guix build-system ant)
35 #:use-module (guix build-system gnu)
36 #:use-module (guix build-system cmake)
37 #:use-module (guix build-system ocaml)
38 #:use-module (guix build-system perl)
39 #:use-module (guix build-system python)
40 #:use-module (guix build-system r)
41 #:use-module (guix build-system ruby)
42 #:use-module (guix build-system trivial)
43 #:use-module (gnu packages)
44 #:use-module (gnu packages autotools)
45 #:use-module (gnu packages algebra)
46 #:use-module (gnu packages base)
47 #:use-module (gnu packages bash)
48 #:use-module (gnu packages bison)
49 #:use-module (gnu packages boost)
50 #:use-module (gnu packages check)
51 #:use-module (gnu packages compression)
52 #:use-module (gnu packages cpio)
53 #:use-module (gnu packages cran)
54 #:use-module (gnu packages curl)
55 #:use-module (gnu packages documentation)
56 #:use-module (gnu packages databases)
57 #:use-module (gnu packages datastructures)
58 #:use-module (gnu packages file)
59 #:use-module (gnu packages flex)
60 #:use-module (gnu packages gawk)
61 #:use-module (gnu packages gcc)
62 #:use-module (gnu packages gd)
63 #:use-module (gnu packages gtk)
64 #:use-module (gnu packages glib)
65 #:use-module (gnu packages graph)
66 #:use-module (gnu packages groff)
67 #:use-module (gnu packages guile)
68 #:use-module (gnu packages haskell)
69 #:use-module (gnu packages image)
70 #:use-module (gnu packages imagemagick)
71 #:use-module (gnu packages java)
72 #:use-module (gnu packages ldc)
73 #:use-module (gnu packages linux)
74 #:use-module (gnu packages logging)
75 #:use-module (gnu packages machine-learning)
76 #:use-module (gnu packages man)
77 #:use-module (gnu packages maths)
78 #:use-module (gnu packages mpi)
79 #:use-module (gnu packages ncurses)
80 #:use-module (gnu packages ocaml)
81 #:use-module (gnu packages pcre)
82 #:use-module (gnu packages parallel)
83 #:use-module (gnu packages pdf)
84 #:use-module (gnu packages perl)
85 #:use-module (gnu packages perl-check)
86 #:use-module (gnu packages pkg-config)
87 #:use-module (gnu packages popt)
88 #:use-module (gnu packages protobuf)
89 #:use-module (gnu packages python)
90 #:use-module (gnu packages python-web)
91 #:use-module (gnu packages readline)
92 #:use-module (gnu packages ruby)
93 #:use-module (gnu packages serialization)
94 #:use-module (gnu packages shells)
95 #:use-module (gnu packages statistics)
96 #:use-module (gnu packages swig)
97 #:use-module (gnu packages tbb)
98 #:use-module (gnu packages tex)
99 #:use-module (gnu packages texinfo)
100 #:use-module (gnu packages textutils)
101 #:use-module (gnu packages time)
102 #:use-module (gnu packages tls)
103 #:use-module (gnu packages vim)
104 #:use-module (gnu packages web)
105 #:use-module (gnu packages xml)
106 #:use-module (gnu packages xorg)
107 #:use-module (srfi srfi-1)
108 #:use-module (ice-9 match))
117 (uri (cran-uri "ape" version))
120 "0q59pmxawz498cb9mv5m49lhiwxib8ak94yyydz7qg8b6lpd4bn3"))))
121 (build-system r-build-system)
123 `(("r-lattice" ,r-lattice)
126 (home-page "http://ape-package.ird.fr/")
127 (synopsis "Analyses of phylogenetics and evolution")
129 "This package provides functions for reading, writing, plotting, and
130 manipulating phylogenetic trees, analyses of comparative data in a
131 phylogenetic framework, ancestral character analyses, analyses of
132 diversification and macroevolution, computing distances from DNA sequences,
133 and several other tools.")
134 (license license:gpl2+)))
136 (define-public aragorn
143 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
147 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
148 (build-system gnu-build-system)
150 `(#:tests? #f ; there are no tests
152 (modify-phases %standard-phases
156 (zero? (system* "gcc"
162 (string-append "aragorn" ,version ".c")))))
164 (lambda* (#:key outputs #:allow-other-keys)
165 (let* ((out (assoc-ref outputs "out"))
166 (bin (string-append out "/bin"))
167 (man (string-append out "/share/man/man1")))
169 (install-file "aragorn" bin)
171 (install-file "aragorn.1" man))
173 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
174 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
176 "Aragorn identifies transfer RNA, mitochondrial RNA and
177 transfer-messenger RNA from nucleotide sequences, based on homology to known
178 tRNA consensus sequences and RNA structure. It also outputs the secondary
179 structure of the predicted RNA.")
180 (license license:gpl2)))
188 ;; BamM is not available on pypi.
190 "https://github.com/Ecogenomics/BamM/archive/"
192 (file-name (string-append name "-" version ".tar.gz"))
195 "1f35yxp4pc8aadsvbpg6r4kg2jh4fkjci0iby4iyljm6980sac0s"))
196 (modules '((guix build utils)))
199 ;; Delete bundled htslib.
200 (delete-file-recursively "c/htslib-1.3.1")
202 (build-system python-build-system)
204 `(#:python ,python-2 ; BamM is Python 2 only.
205 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
206 ;; been modified from its original form.
208 (let ((htslib (assoc-ref %build-inputs "htslib")))
209 (list "--with-libhts-lib" (string-append htslib "/lib")
210 "--with-libhts-inc" (string-append htslib "/include/htslib")))
212 (modify-phases %standard-phases
213 (add-after 'unpack 'autogen
215 (with-directory-excursion "c"
216 (let ((sh (which "sh")))
217 ;; Use autogen so that 'configure' works.
218 (substitute* "autogen.sh" (("/bin/sh") sh))
219 (setenv "CONFIG_SHELL" sh)
220 (substitute* "configure" (("/bin/sh") sh))
221 (zero? (system* "./autogen.sh"))))))
223 ;; Run tests after installation so compilation only happens once.
225 (add-after 'install 'wrap-executable
226 (lambda* (#:key outputs #:allow-other-keys)
227 (let* ((out (assoc-ref outputs "out"))
228 (path (getenv "PATH")))
229 (wrap-program (string-append out "/bin/bamm")
230 `("PATH" ":" prefix (,path))))
232 (add-after 'wrap-executable 'post-install-check
233 (lambda* (#:key inputs outputs #:allow-other-keys)
235 (string-append (assoc-ref outputs "out")
240 (assoc-ref outputs "out")
242 (string-take (string-take-right
243 (assoc-ref inputs "python") 5) 3)
245 (getenv "PYTHONPATH")))
246 ;; There are 2 errors printed, but they are safe to ignore:
247 ;; 1) [E::hts_open_format] fail to open file ...
248 ;; 2) samtools view: failed to open ...
249 (zero? (system* "nosetests")))))))
251 `(("autoconf" ,autoconf)
252 ("automake" ,automake)
255 ("python-nose" ,python2-nose)
256 ("python-pysam" ,python2-pysam)))
258 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
259 ("samtools" ,samtools)
263 ("coreutils" ,coreutils)))
265 `(("python-numpy" ,python2-numpy)))
266 (home-page "http://ecogenomics.github.io/BamM/")
267 (synopsis "Metagenomics-focused BAM file manipulator")
269 "BamM is a C library, wrapped in python, to efficiently generate and
270 parse BAM files, specifically for the analysis of metagenomic data. For
271 instance, it implements several methods to assess contig-wise read coverage.")
272 (license license:lgpl3+)))
274 (define-public bamtools
281 "https://github.com/pezmaster31/bamtools/archive/v"
283 (file-name (string-append name "-" version ".tar.gz"))
286 "0jr024kcrhjb82cm69i7p5fcg5375zlc1h3qh2n1v368hcd0qflk"))))
287 (build-system cmake-build-system)
289 `(#:tests? #f ;no "check" target
291 (modify-phases %standard-phases
293 'configure 'set-ldflags
294 (lambda* (#:key outputs #:allow-other-keys)
298 (assoc-ref outputs "out") "/lib/bamtools")))))))
299 (inputs `(("zlib" ,zlib)))
300 (home-page "https://github.com/pezmaster31/bamtools")
301 (synopsis "C++ API and command-line toolkit for working with BAM data")
303 "BamTools provides both a C++ API and a command-line toolkit for handling
305 (license license:expat)))
307 (define-public bcftools
314 "https://github.com/samtools/bcftools/releases/download/"
315 version "/bcftools-" version ".tar.bz2"))
318 "0093hkkvxmbwfaa7905s6185jymynvg42kq6sxv7fili11l5mxwz"))
319 (patches (search-patches "bcftools-regidx-unsigned-char.patch"))
320 (modules '((guix build utils)))
322 ;; Delete bundled htslib.
323 '(delete-file-recursively "htslib-1.5"))))
324 (build-system gnu-build-system)
326 `(#:test-target "test"
327 #:configure-flags (list "--with-htslib=system")
331 "LIBS=-lgsl -lgslcblas"
332 (string-append "prefix=" (assoc-ref %outputs "out"))
333 (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
334 (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.so")
335 (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
336 (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix")
337 (string-append "PACKAGE_VERSION=" ,version))
339 (modify-phases %standard-phases
340 (add-before 'check 'patch-tests
342 (substitute* "test/test.pl"
343 (("/bin/bash") (which "bash")))
351 (home-page "https://samtools.github.io/bcftools/")
352 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
354 "BCFtools is a set of utilities that manipulate variant calls in the
355 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
356 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
357 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
358 (license (list license:gpl3+ license:expat))))
360 (define-public bedops
366 (uri (string-append "https://github.com/bedops/bedops/archive/v"
368 (file-name (string-append name "-" version ".tar.gz"))
371 "1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
372 (build-system gnu-build-system)
375 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
377 (modify-phases %standard-phases
378 (add-after 'unpack 'unpack-tarballs
380 ;; FIXME: Bedops includes tarballs of minimally patched upstream
381 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
382 ;; libraries because at least one of the libraries (zlib) is
383 ;; patched to add a C++ function definition (deflateInit2cpp).
384 ;; Until the Bedops developers offer a way to link against system
385 ;; libraries we have to build the in-tree copies of these three
388 ;; See upstream discussion:
389 ;; https://github.com/bedops/bedops/issues/124
391 ;; Unpack the tarballs to benefit from shebang patching.
392 (with-directory-excursion "third-party"
393 (and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
394 (zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
395 (zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
396 ;; Disable unpacking of tarballs in Makefile.
397 (substitute* "system.mk/Makefile.linux"
398 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
399 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
400 (substitute* "third-party/zlib-1.2.7/Makefile.in"
401 (("^SHELL=.*$") "SHELL=bash\n"))
403 (delete 'configure))))
404 (home-page "https://github.com/bedops/bedops")
405 (synopsis "Tools for high-performance genomic feature operations")
407 "BEDOPS is a suite of tools to address common questions raised in genomic
408 studies---mostly with regard to overlap and proximity relationships between
409 data sets. It aims to be scalable and flexible, facilitating the efficient
410 and accurate analysis and management of large-scale genomic data.
412 BEDOPS provides tools that perform highly efficient and scalable Boolean and
413 other set operations, statistical calculations, archiving, conversion and
414 other management of genomic data of arbitrary scale. Tasks can be easily
415 split by chromosome for distributing whole-genome analyses across a
416 computational cluster.")
417 (license license:gpl2+)))
419 (define-public bedtools
425 (uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
427 (file-name (string-append name "-" version ".tar.gz"))
430 "0xvri5hnp2iim1cx6mcd5d9f102p5ql41x69rd6106x1c17pinqm"))))
431 (build-system gnu-build-system)
432 (native-inputs `(("python" ,python-2)))
433 (inputs `(("samtools" ,samtools)
436 '(#:test-target "test"
438 (modify-phases %standard-phases
441 (lambda* (#:key outputs #:allow-other-keys)
442 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
443 (for-each (lambda (file)
444 (install-file file bin))
445 (find-files "bin" ".*")))
447 (home-page "https://github.com/arq5x/bedtools2")
448 (synopsis "Tools for genome analysis and arithmetic")
450 "Collectively, the bedtools utilities are a swiss-army knife of tools for
451 a wide-range of genomics analysis tasks. The most widely-used tools enable
452 genome arithmetic: that is, set theory on the genome. For example, bedtools
453 allows one to intersect, merge, count, complement, and shuffle genomic
454 intervals from multiple files in widely-used genomic file formats such as BAM,
456 (license license:gpl2)))
458 ;; Later releases of bedtools produce files with more columns than
459 ;; what Ribotaper expects.
460 (define-public bedtools-2.18
461 (package (inherit bedtools)
466 (uri (string-append "https://github.com/arq5x/bedtools2/"
467 "archive/v" version ".tar.gz"))
468 (file-name (string-append name "-" version ".tar.gz"))
471 "05vrnr8yp7swfagshzpgqmzk1blnwnq8pq5pckzi1m26w98d63vf"))))))
473 (define-public ribotaper
479 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
480 "files/RiboTaper/RiboTaper_Version_"
484 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
485 (build-system gnu-build-system)
487 `(("bedtools" ,bedtools-2.18)
488 ("samtools" ,samtools-0.1)
489 ("r-minimal" ,r-minimal)
490 ("r-foreach" ,r-foreach)
491 ("r-xnomial" ,r-xnomial)
493 ("r-multitaper" ,r-multitaper)
494 ("r-seqinr" ,r-seqinr)))
495 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
496 (synopsis "Define translated ORFs using ribosome profiling data")
498 "Ribotaper is a method for defining translated @dfn{open reading
499 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
500 provides the Ribotaper pipeline.")
501 (license license:gpl3+)))
503 (define-public ribodiff
510 (uri (string-append "https://github.com/ratschlab/RiboDiff/"
511 "archive/v" version ".tar.gz"))
512 (file-name (string-append name "-" version ".tar.gz"))
515 "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
516 (build-system python-build-system)
520 (modify-phases %standard-phases
521 ;; Generate an installable executable script wrapper.
522 (add-after 'unpack 'patch-setup.py
524 (substitute* "setup.py"
525 (("^(.*)packages=.*" line prefix)
526 (string-append line "\n"
527 prefix "scripts=['scripts/TE.py'],\n")))
530 `(("python-numpy" ,python2-numpy)
531 ("python-matplotlib" ,python2-matplotlib)
532 ("python-scipy" ,python2-scipy)
533 ("python-statsmodels" ,python2-statsmodels)))
535 `(("python-mock" ,python2-mock)
536 ("python-nose" ,python2-nose)))
537 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
538 (synopsis "Detect translation efficiency changes from ribosome footprints")
539 (description "RiboDiff is a statistical tool that detects the protein
540 translational efficiency change from Ribo-Seq (ribosome footprinting) and
541 RNA-Seq data. It uses a generalized linear model to detect genes showing
542 difference in translational profile taking mRNA abundance into account. It
543 facilitates us to decipher the translational regulation that behave
544 independently with transcriptional regulation.")
545 (license license:gpl3+)))
547 (define-public bioawk
553 (uri (string-append "https://github.com/lh3/bioawk/archive/v"
555 (file-name (string-append name "-" version ".tar.gz"))
557 (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
558 (build-system gnu-build-system)
564 `(#:tests? #f ; There are no tests to run.
565 ;; Bison must generate files, before other targets can build.
568 (modify-phases %standard-phases
569 (delete 'configure) ; There is no configure phase.
571 (lambda* (#:key outputs #:allow-other-keys)
572 (let* ((out (assoc-ref outputs "out"))
573 (bin (string-append out "/bin"))
574 (man (string-append out "/share/man/man1")))
576 (copy-file "awk.1" (string-append man "/bioawk.1"))
577 (install-file "bioawk" bin)))))))
578 (home-page "https://github.com/lh3/bioawk")
579 (synopsis "AWK with bioinformatics extensions")
580 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
581 support of several common biological data formats, including optionally gzip'ed
582 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
583 also adds a few built-in functions and a command line option to use TAB as the
584 input/output delimiter. When the new functionality is not used, bioawk is
585 intended to behave exactly the same as the original BWK awk.")
586 (license license:x11)))
588 (define-public python2-pybedtools
590 (name "python2-pybedtools")
595 "https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
599 "1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
600 (build-system python-build-system)
601 (arguments `(#:python ,python-2)) ; no Python 3 support
603 `(("python-matplotlib" ,python2-matplotlib)))
605 `(("bedtools" ,bedtools)
606 ("samtools" ,samtools)))
608 `(("python-cython" ,python2-cython)
609 ("python-pyyaml" ,python2-pyyaml)
610 ("python-nose" ,python2-nose)))
611 (home-page "https://pythonhosted.org/pybedtools/")
612 (synopsis "Python wrapper for BEDtools programs")
614 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
615 which are widely used for genomic interval manipulation or \"genome algebra\".
616 pybedtools extends BEDTools by offering feature-level manipulations from with
618 (license license:gpl2+)))
620 (define-public python-biom-format
622 (name "python-biom-format")
627 ;; Use GitHub as source because PyPI distribution does not contain
628 ;; test data: https://github.com/biocore/biom-format/issues/693
629 (uri (string-append "https://github.com/biocore/biom-format/archive/"
631 (file-name (string-append name "-" version ".tar.gz"))
634 "08cr7wpahk6zb31h4bs7jmzpvxcqv9s13xz40h6y2h656jvdvnpj"))))
635 (build-system python-build-system)
637 `(("python-numpy" ,python-numpy)
638 ("python-scipy" ,python-scipy)
639 ("python-future" ,python-future)
640 ("python-click" ,python-click)
641 ("python-h5py" ,python-h5py)
642 ("python-pandas" ,python-pandas)))
644 `(("python-nose" ,python-nose)))
645 (home-page "http://www.biom-format.org")
646 (synopsis "Biological Observation Matrix (BIOM) format utilities")
648 "The BIOM file format is designed to be a general-use format for
649 representing counts of observations e.g. operational taxonomic units, KEGG
650 orthology groups or lipid types, in one or more biological samples
651 e.g. microbiome samples, genomes, metagenomes.")
652 (license license:bsd-3)
653 (properties `((python2-variant . ,(delay python2-biom-format))))))
655 (define-public python2-biom-format
656 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
661 (modify-phases %standard-phases
662 ;; Do not require the unmaintained pyqi library.
663 (add-after 'unpack 'remove-pyqi
665 (substitute* "setup.py"
666 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
668 ,@(package-arguments base))))))
670 (define-public bioperl-minimal
671 (let* ((inputs `(("perl-module-build" ,perl-module-build)
672 ("perl-data-stag" ,perl-data-stag)
673 ("perl-libwww" ,perl-libwww)
674 ("perl-uri" ,perl-uri)))
676 (map (compose package-name cadr)
679 (map (compose package-transitive-target-inputs cadr) inputs))))))
681 (name "bioperl-minimal")
686 (uri (string-append "https://github.com/bioperl/bioperl-live/"
688 (string-map (lambda (c)
694 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
695 (build-system perl-build-system)
698 (modify-phases %standard-phases
700 'install 'wrap-programs
701 (lambda* (#:key outputs #:allow-other-keys)
702 ;; Make sure all executables in "bin" find the required Perl
703 ;; modules at runtime. As the PERL5LIB variable contains also
704 ;; the paths of native inputs, we pick the transitive target
705 ;; inputs from %build-inputs.
706 (let* ((out (assoc-ref outputs "out"))
707 (bin (string-append out "/bin/"))
709 (cons (string-append out "/lib/perl5/site_perl")
711 (assoc-ref %build-inputs name))
712 ',transitive-inputs))
714 (for-each (lambda (file)
716 `("PERL5LIB" ":" prefix (,path))))
717 (find-files bin "\\.pl$"))
721 `(("perl-test-most" ,perl-test-most)))
722 (home-page "http://search.cpan.org/dist/BioPerl")
723 (synopsis "Bioinformatics toolkit")
725 "BioPerl is the product of a community effort to produce Perl code which
726 is useful in biology. Examples include Sequence objects, Alignment objects
727 and database searching objects. These objects not only do what they are
728 advertised to do in the documentation, but they also interact - Alignment
729 objects are made from the Sequence objects, Sequence objects have access to
730 Annotation and SeqFeature objects and databases, Blast objects can be
731 converted to Alignment objects, and so on. This means that the objects
732 provide a coordinated and extensible framework to do computational biology.")
733 (license license:perl-license))))
735 (define-public python-biopython
737 (name "python-biopython")
741 ;; use PyPi rather than biopython.org to ease updating
742 (uri (pypi-uri "biopython" version))
745 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
746 (build-system python-build-system)
749 (modify-phases %standard-phases
750 (add-before 'check 'set-home
751 ;; Some tests require a home directory to be set.
752 (lambda _ (setenv "HOME" "/tmp") #t)))))
754 `(("python-numpy" ,python-numpy)))
755 (home-page "http://biopython.org/")
756 (synopsis "Tools for biological computation in Python")
758 "Biopython is a set of tools for biological computation including parsers
759 for bioinformatics files into Python data structures; interfaces to common
760 bioinformatics programs; a standard sequence class and tools for performing
761 common operations on them; code to perform data classification; code for
762 dealing with alignments; code making it easy to split up parallelizable tasks
763 into separate processes; and more.")
764 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
766 (define-public python2-biopython
767 (package-with-python2 python-biopython))
769 ;; An outdated version of biopython is required for seqmagick, see
770 ;; https://github.com/fhcrc/seqmagick/issues/59
771 ;; When that issue has been resolved this package should be removed.
772 (define python2-biopython-1.66
774 (inherit python2-biopython)
778 (uri (pypi-uri "biopython" version))
781 "1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))))
783 (define-public bpp-core
784 ;; The last release was in 2014 and the recommended way to install from source
785 ;; is to clone the git repository, so we do this.
786 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
787 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
790 (version (string-append "2.2.0-1." (string-take commit 7)))
794 (url "http://biopp.univ-montp2.fr/git/bpp-core")
796 (file-name (string-append name "-" version "-checkout"))
799 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
800 (build-system cmake-build-system)
802 `(#:parallel-build? #f))
804 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
805 ; compile all of the bpp packages with GCC 5.
806 (home-page "http://biopp.univ-montp2.fr")
807 (synopsis "C++ libraries for Bioinformatics")
809 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
810 analysis, phylogenetics, molecular evolution and population genetics. It is
811 Object Oriented and is designed to be both easy to use and computer efficient.
812 Bio++ intends to help programmers to write computer expensive programs, by
813 providing them a set of re-usable tools.")
814 (license license:cecill-c))))
816 (define-public bpp-phyl
817 ;; The last release was in 2014 and the recommended way to install from source
818 ;; is to clone the git repository, so we do this.
819 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
820 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
823 (version (string-append "2.2.0-1." (string-take commit 7)))
827 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
829 (file-name (string-append name "-" version "-checkout"))
832 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
833 (build-system cmake-build-system)
835 `(#:parallel-build? #f
836 ;; If out-of-source, test data is not copied into the build directory
837 ;; so the tests fail.
838 #:out-of-source? #f))
840 `(("bpp-core" ,bpp-core)
842 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
845 (home-page "http://biopp.univ-montp2.fr")
846 (synopsis "Bio++ phylogenetic Library")
848 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
849 analysis, phylogenetics, molecular evolution and population genetics. This
850 library provides phylogenetics-related modules.")
851 (license license:cecill-c))))
853 (define-public bpp-popgen
854 ;; The last release was in 2014 and the recommended way to install from source
855 ;; is to clone the git repository, so we do this.
856 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
857 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
860 (version (string-append "2.2.0-1." (string-take commit 7)))
864 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
866 (file-name (string-append name "-" version "-checkout"))
869 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
870 (build-system cmake-build-system)
872 `(#:parallel-build? #f
873 #:tests? #f)) ; There are no tests.
875 `(("bpp-core" ,bpp-core)
878 (home-page "http://biopp.univ-montp2.fr")
879 (synopsis "Bio++ population genetics library")
881 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
882 analysis, phylogenetics, molecular evolution and population genetics. This
883 library provides population genetics-related modules.")
884 (license license:cecill-c))))
886 (define-public bpp-seq
887 ;; The last release was in 2014 and the recommended way to install from source
888 ;; is to clone the git repository, so we do this.
889 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
890 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
893 (version (string-append "2.2.0-1." (string-take commit 7)))
897 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
899 (file-name (string-append name "-" version "-checkout"))
902 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
903 (build-system cmake-build-system)
905 `(#:parallel-build? #f
906 ;; If out-of-source, test data is not copied into the build directory
907 ;; so the tests fail.
908 #:out-of-source? #f))
910 `(("bpp-core" ,bpp-core)
911 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
912 (home-page "http://biopp.univ-montp2.fr")
913 (synopsis "Bio++ sequence library")
915 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
916 analysis, phylogenetics, molecular evolution and population genetics. This
917 library provides sequence-related modules.")
918 (license license:cecill-c))))
920 (define-public bppsuite
921 ;; The last release was in 2014 and the recommended way to install from source
922 ;; is to clone the git repository, so we do this.
923 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
924 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
927 (version (string-append "2.2.0-1." (string-take commit 7)))
931 (url "http://biopp.univ-montp2.fr/git/bppsuite")
933 (file-name (string-append name "-" version "-checkout"))
936 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
937 (build-system cmake-build-system)
939 `(#:parallel-build? #f
940 #:tests? #f)) ; There are no tests.
944 ("texinfo" ,texinfo)))
946 `(("bpp-core" ,bpp-core)
948 ("bpp-phyl" ,bpp-phyl)
949 ("bpp-phyl" ,bpp-popgen)
951 (home-page "http://biopp.univ-montp2.fr")
952 (synopsis "Bioinformatics tools written with the Bio++ libraries")
954 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
955 analysis, phylogenetics, molecular evolution and population genetics. This
956 package provides command line tools using the Bio++ library.")
957 (license license:cecill-c))))
959 (define-public blast+
966 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
967 version "/ncbi-blast-" version "+-src.tar.gz"))
970 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
971 (patches (search-patches "blast+-fix-makefile.patch"))
972 (modules '((guix build utils)))
975 ;; Remove bundled bzip2, zlib and pcre.
976 (delete-file-recursively "c++/src/util/compress/bzip2")
977 (delete-file-recursively "c++/src/util/compress/zlib")
978 (delete-file-recursively "c++/src/util/regexp")
979 (substitute* "c++/src/util/compress/Makefile.in"
980 (("bzip2 zlib api") "api"))
981 ;; Remove useless msbuild directory
982 (delete-file-recursively
983 "c++/src/build-system/project_tree_builder/msbuild")
985 (build-system gnu-build-system)
987 `(;; There are two(!) tests for this massive library, and both fail with
988 ;; "unparsable timing stats".
989 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
990 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
993 #:parallel-build? #f ; not supported
995 (modify-phases %standard-phases
998 ;; $HOME needs to be set at some point during the configure phase
999 (lambda _ (setenv "HOME" "/tmp") #t))
1002 (lambda _ (chdir "c++") #t))
1004 'enter-dir 'fix-build-system
1006 (define (which* cmd)
1007 (cond ((string=? cmd "date")
1008 ;; make call to "date" deterministic
1013 (format (current-error-port)
1014 "WARNING: Unable to find absolute path for ~s~%"
1018 ;; Rewrite hardcoded paths to various tools
1019 (substitute* (append '("src/build-system/configure.ac"
1020 "src/build-system/configure"
1021 "src/build-system/helpers/run_with_lock.c"
1022 "scripts/common/impl/if_diff.sh"
1023 "scripts/common/impl/run_with_lock.sh"
1024 "src/build-system/Makefile.configurables.real"
1025 "src/build-system/Makefile.in.top"
1026 "src/build-system/Makefile.meta.gmake=no"
1027 "src/build-system/Makefile.meta.in"
1028 "src/build-system/Makefile.meta_l"
1029 "src/build-system/Makefile.meta_p"
1030 "src/build-system/Makefile.meta_r"
1031 "src/build-system/Makefile.mk.in"
1032 "src/build-system/Makefile.requirements"
1033 "src/build-system/Makefile.rules_with_autodep.in")
1034 (find-files "scripts/common/check" "\\.sh$"))
1035 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1036 (or (which* cmd) all)))
1038 (substitute* (find-files "src/build-system" "^config.*")
1039 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1042 ;; rewrite "/var/tmp" in check script
1043 (substitute* "scripts/common/check/check_make_unix.sh"
1044 (("/var/tmp") "/tmp"))
1046 ;; do not reset PATH
1047 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1049 (("action=/bin/") "action=")
1050 (("export PATH") ":"))
1054 (lambda* (#:key inputs outputs #:allow-other-keys)
1055 (let ((out (assoc-ref outputs "out"))
1056 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1057 (include (string-append (assoc-ref outputs "include")
1058 "/include/ncbi-tools++")))
1059 ;; The 'configure' script doesn't recognize things like
1060 ;; '--enable-fast-install'.
1061 (zero? (system* "./configure.orig"
1062 (string-append "--with-build-root=" (getcwd) "/build")
1063 (string-append "--prefix=" out)
1064 (string-append "--libdir=" lib)
1065 (string-append "--includedir=" include)
1066 (string-append "--with-bz2="
1067 (assoc-ref inputs "bzip2"))
1068 (string-append "--with-z="
1069 (assoc-ref inputs "zlib"))
1070 (string-append "--with-pcre="
1071 (assoc-ref inputs "pcre"))
1072 ;; Each library is built twice by default, once
1073 ;; with "-static" in its name, and again
1076 "--with-dll"))))))))
1077 (outputs '("out" ; 21 MB
1085 ("python" ,python-wrapper)))
1088 (home-page "http://blast.ncbi.nlm.nih.gov")
1089 (synopsis "Basic local alignment search tool")
1091 "BLAST is a popular method of performing a DNA or protein sequence
1092 similarity search, using heuristics to produce results quickly. It also
1093 calculates an “expect value” that estimates how many matches would have
1094 occurred at a given score by chance, which can aid a user in judging how much
1095 confidence to have in an alignment.")
1096 ;; Most of the sources are in the public domain, with the following
1099 ;; * ./c++/include/util/bitset/
1100 ;; * ./c++/src/html/ncbi_menu*.js
1102 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1104 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1106 ;; * ./c++/src/corelib/teamcity_*
1107 (license (list license:public-domain
1113 (define-public bless
1119 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1123 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1124 (modules '((guix build utils)))
1127 ;; Remove bundled boost, pigz, zlib, and .git directory
1128 ;; FIXME: also remove bundled sources for murmurhash3 and
1129 ;; kmc once packaged.
1130 (delete-file-recursively "boost")
1131 (delete-file-recursively "pigz")
1132 (delete-file-recursively "google-sparsehash")
1133 (delete-file-recursively "zlib")
1134 (delete-file-recursively ".git")
1136 (build-system gnu-build-system)
1138 '(#:tests? #f ;no "check" target
1140 (list (string-append "ZLIB="
1141 (assoc-ref %build-inputs "zlib")
1143 (string-append "LDFLAGS="
1144 (string-join '("-lboost_filesystem"
1151 (modify-phases %standard-phases
1152 (add-after 'unpack 'do-not-build-bundled-pigz
1153 (lambda* (#:key inputs outputs #:allow-other-keys)
1154 (substitute* "Makefile"
1155 (("cd pigz/pigz-2.3.3; make") ""))
1157 (add-after 'unpack 'patch-paths-to-executables
1158 (lambda* (#:key inputs outputs #:allow-other-keys)
1159 (substitute* "parse_args.cpp"
1160 (("kmc_binary = .*")
1161 (string-append "kmc_binary = \""
1162 (assoc-ref outputs "out")
1164 (("pigz_binary = .*")
1165 (string-append "pigz_binary = \""
1166 (assoc-ref inputs "pigz")
1170 (lambda* (#:key outputs #:allow-other-keys)
1171 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1172 (for-each (lambda (file)
1173 (install-file file bin))
1174 '("bless" "kmc/bin/kmc"))
1176 (delete 'configure))))
1180 `(("openmpi" ,openmpi)
1182 ("sparsehash" ,sparsehash)
1185 (supported-systems '("x86_64-linux"))
1186 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1187 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1189 "@dfn{Bloom-filter-based error correction solution for high-throughput
1190 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1191 correction tool for genomic reads produced by @dfn{Next-generation
1192 sequencing} (NGS). BLESS produces accurate correction results with much less
1193 memory compared with previous solutions and is also able to tolerate a higher
1194 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1195 errors at the end of reads.")
1196 (license license:gpl3+)))
1198 (define-public bowtie
1204 (uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
1206 (file-name (string-append name "-" version ".tar.gz"))
1209 "0hwa5r9qbglppb7sz5z79rlmmddr3n51n468jb3wh8rwjgn3yr90"))
1210 (modules '((guix build utils)))
1212 '(substitute* "Makefile"
1213 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1214 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1215 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1216 (build-system gnu-build-system)
1219 ("perl-clone" ,perl-clone)
1220 ("perl-test-deep" ,perl-test-deep)
1221 ("perl-test-simple" ,perl-test-simple)
1222 ("python" ,python-2)
1229 (string-append "prefix=" (assoc-ref %outputs "out")))
1231 (modify-phases %standard-phases
1234 (lambda* (#:key outputs #:allow-other-keys)
1235 (zero? (system* "perl"
1236 "scripts/test/simple_tests.pl"
1237 "--bowtie2=./bowtie2"
1238 "--bowtie2-build=./bowtie2-build")))))))
1239 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1240 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1242 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1243 reads to long reference sequences. It is particularly good at aligning reads
1244 of about 50 up to 100s or 1,000s of characters, and particularly good at
1245 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1246 genome with an FM Index to keep its memory footprint small: for the human
1247 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1248 gapped, local, and paired-end alignment modes.")
1249 (supported-systems '("x86_64-linux"))
1250 (license license:gpl3+)))
1252 (define-public tophat
1259 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1263 "168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
1264 (patches (search-patches "tophat-build-with-later-seqan.patch"))
1265 (modules '((guix build utils)))
1268 ;; Remove bundled SeqAn and samtools
1269 (delete-file-recursively "src/SeqAn-1.3")
1270 (delete-file-recursively "src/samtools-0.1.18")
1272 (build-system gnu-build-system)
1274 '(#:parallel-build? #f ; not supported
1276 (modify-phases %standard-phases
1277 (add-after 'unpack 'use-system-samtools
1278 (lambda* (#:key inputs #:allow-other-keys)
1279 (substitute* "src/Makefile.in"
1280 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1281 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1282 (("SAMPROG = samtools_0\\.1\\.18") "")
1283 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1284 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1285 (substitute* '("src/common.cpp"
1287 (("samtools_0.1.18") (which "samtools")))
1288 (substitute* '("src/common.h"
1289 "src/bam2fastx.cpp")
1290 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1291 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1292 (substitute* '("src/bwt_map.h"
1294 "src/align_status.h")
1295 (("#include <bam.h>") "#include <samtools/bam.h>")
1296 (("#include <sam.h>") "#include <samtools/sam.h>"))
1301 ("samtools" ,samtools-0.1)
1302 ("ncurses" ,ncurses)
1303 ("python" ,python-2)
1307 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1308 (synopsis "Spliced read mapper for RNA-Seq data")
1310 "TopHat is a fast splice junction mapper for nucleotide sequence
1311 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1312 mammalian-sized genomes using the ultra high-throughput short read
1313 aligner Bowtie, and then analyzes the mapping results to identify
1314 splice junctions between exons.")
1315 ;; TopHat is released under the Boost Software License, Version 1.0
1316 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1317 (license license:boost1.0)))
1326 "https://github.com/lh3/bwa/releases/download/v"
1327 version "/bwa-" version ".tar.bz2"))
1330 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1331 (build-system gnu-build-system)
1333 '(#:tests? #f ;no "check" target
1335 (modify-phases %standard-phases
1337 (lambda* (#:key outputs #:allow-other-keys)
1338 (let ((bin (string-append
1339 (assoc-ref outputs "out") "/bin"))
1341 (assoc-ref outputs "out") "/share/doc/bwa"))
1343 (assoc-ref outputs "out") "/share/man/man1")))
1344 (install-file "bwa" bin)
1345 (install-file "README.md" doc)
1346 (install-file "bwa.1" man))
1348 ;; no "configure" script
1349 (delete 'configure))))
1350 (inputs `(("zlib" ,zlib)))
1351 ;; Non-portable SSE instructions are used so building fails on platforms
1352 ;; other than x86_64.
1353 (supported-systems '("x86_64-linux"))
1354 (home-page "http://bio-bwa.sourceforge.net/")
1355 (synopsis "Burrows-Wheeler sequence aligner")
1357 "BWA is a software package for mapping low-divergent sequences against a
1358 large reference genome, such as the human genome. It consists of three
1359 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1360 designed for Illumina sequence reads up to 100bp, while the rest two for
1361 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1362 features such as long-read support and split alignment, but BWA-MEM, which is
1363 the latest, is generally recommended for high-quality queries as it is faster
1364 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1365 70-100bp Illumina reads.")
1366 (license license:gpl3+)))
1368 (define-public bwa-pssm
1369 (package (inherit bwa)
1374 (uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
1375 "archive/" version ".tar.gz"))
1376 (file-name (string-append name "-" version ".tar.gz"))
1379 "02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
1380 (build-system gnu-build-system)
1385 (home-page "http://bwa-pssm.binf.ku.dk/")
1386 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1388 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1389 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1390 existing aligners it is fast and sensitive. Unlike most other aligners,
1391 however, it is also adaptible in the sense that one can direct the alignment
1392 based on known biases within the data set. It is coded as a modification of
1393 the original BWA alignment program and shares the genome index structure as
1394 well as many of the command line options.")
1395 (license license:gpl3+)))
1397 (define-public python2-bx-python
1399 (name "python2-bx-python")
1403 (uri (pypi-uri "bx-python" version))
1406 "15z2w3bvnc0n4qmb9bd6d8ylc2h2nj883x2w9iixf4x3vki9b22i"))
1407 (modules '((guix build utils)))
1409 '(substitute* "setup.py"
1410 ;; remove dependency on outdated "distribute" module
1411 (("^from distribute_setup import use_setuptools") "")
1412 (("^use_setuptools\\(\\)") "")))))
1413 (build-system python-build-system)
1415 `(#:tests? #f ;tests fail because test data are not included
1416 #:python ,python-2))
1418 `(("python-numpy" ,python2-numpy)
1421 `(("python-nose" ,python2-nose)))
1422 (home-page "http://bitbucket.org/james_taylor/bx-python/")
1423 (synopsis "Tools for manipulating biological data")
1425 "bx-python provides tools for manipulating biological data, particularly
1426 multiple sequence alignments.")
1427 (license license:expat)))
1429 (define-public python-pysam
1431 (name "python-pysam")
1432 (version "0.11.2.2")
1435 ;; Test data is missing on PyPi.
1437 "https://github.com/pysam-developers/pysam/archive/v"
1439 (file-name (string-append name "-" version ".tar.gz"))
1442 "1cfqdxsqs3xhacns9n0271ck6wkc76px66ddjm91wfw2jxxfklvc"))
1443 (modules '((guix build utils)))
1445 ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
1446 '(delete-file-recursively "htslib"))))
1447 (build-system python-build-system)
1449 `(#:modules ((ice-9 ftw)
1451 (guix build python-build-system)
1454 (modify-phases %standard-phases
1455 (add-before 'build 'set-flags
1456 (lambda* (#:key inputs #:allow-other-keys)
1457 (setenv "HTSLIB_MODE" "external")
1458 (setenv "HTSLIB_LIBRARY_DIR"
1459 (string-append (assoc-ref inputs "htslib") "/lib"))
1460 (setenv "HTSLIB_INCLUDE_DIR"
1461 (string-append (assoc-ref inputs "htslib") "/include"))
1462 (setenv "LDFLAGS" "-lncurses")
1463 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1466 (lambda* (#:key inputs outputs #:allow-other-keys)
1467 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1468 (setenv "PYTHONPATH"
1470 (getenv "PYTHONPATH")
1471 ":" (getcwd) "/build/"
1472 (car (scandir "build"
1473 (negate (cut string-prefix? "." <>))))))
1474 ;; Step out of source dir so python does not import from CWD.
1475 (with-directory-excursion "tests"
1476 (setenv "HOME" "/tmp")
1477 (and (zero? (system* "make" "-C" "pysam_data"))
1478 (zero? (system* "make" "-C" "cbcf_data"))
1479 ;; Running nosetests without explicitly asking for a
1480 ;; single process leads to a crash. Running with multiple
1481 ;; processes fails because the tests are not designed to
1484 ;; FIXME: tests keep timing out on some systems.
1485 ;; (zero? (system* "nosetests" "-v"
1486 ;; "--processes" "1"))
1489 `(("htslib" ,htslib))) ; Included from installed header files.
1491 `(("ncurses" ,ncurses)
1494 `(("python-cython" ,python-cython)
1495 ;; Dependencies below are are for tests only.
1496 ("samtools" ,samtools)
1497 ("bcftools" ,bcftools)
1498 ("python-nose" ,python-nose)))
1499 (home-page "https://github.com/pysam-developers/pysam")
1500 (synopsis "Python bindings to the SAMtools C API")
1502 "Pysam is a Python module for reading and manipulating files in the
1503 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1504 also includes an interface for tabix.")
1505 (license license:expat)))
1507 (define-public python2-pysam
1508 (package-with-python2 python-pysam))
1510 (define-public python-twobitreader
1512 (name "python-twobitreader")
1516 (uri (pypi-uri "twobitreader" version))
1519 "1q8wnj2kga9nz1lwc4w7qv52smfm536hp6mc8w6s53lhyj0mpi22"))))
1520 (build-system python-build-system)
1522 '(;; Tests are not distributed in the PyPi release.
1523 ;; TODO Try building from the Git repo or asking the upstream maintainer
1524 ;; to distribute the tests on PyPi.
1527 `(("python-sphinx" ,python-sphinx)))
1528 (home-page "https://github.com/benjschiller/twobitreader")
1529 (synopsis "Python library for reading .2bit files")
1531 "twobitreader is a Python library for reading .2bit files as used by the
1532 UCSC genome browser.")
1533 (license license:artistic2.0)))
1535 (define-public python2-twobitreader
1536 (package-with-python2 python-twobitreader))
1538 (define-public python-plastid
1540 (name "python-plastid")
1544 (uri (pypi-uri "plastid" version))
1547 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1548 (build-system python-build-system)
1550 ;; Some test files are not included.
1553 `(("python-numpy" ,python-numpy)
1554 ("python-scipy" ,python-scipy)
1555 ("python-pandas" ,python-pandas)
1556 ("python-pysam" ,python-pysam)
1557 ("python-matplotlib" ,python-matplotlib)
1558 ("python-biopython" ,python-biopython)
1559 ("python-twobitreader" ,python-twobitreader)
1560 ("python-termcolor" ,python-termcolor)))
1562 `(("python-cython" ,python-cython)
1563 ("python-nose" ,python-nose)))
1564 (home-page "https://github.com/joshuagryphon/plastid")
1565 (synopsis "Python library for genomic analysis")
1567 "plastid is a Python library for genomic analysis – in particular,
1568 high-throughput sequencing data – with an emphasis on simplicity.")
1569 (license license:bsd-3)))
1571 (define-public python2-plastid
1572 (package-with-python2 python-plastid))
1574 (define-public cd-hit
1580 (uri (string-append "https://github.com/weizhongli/cdhit"
1581 "/releases/download/V" version
1583 "-2017-0621-source.tar.gz"))
1586 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1587 (build-system gnu-build-system)
1589 `(#:tests? #f ; there are no tests
1591 ;; Executables are copied directly to the PREFIX.
1592 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
1594 (modify-phases %standard-phases
1595 ;; No "configure" script
1597 ;; Remove sources of non-determinism
1598 (add-after 'unpack 'be-timeless
1600 (substitute* "cdhit-utility.c++"
1601 ((" \\(built on \" __DATE__ \"\\)") ""))
1602 (substitute* "cdhit-common.c++"
1603 (("__DATE__") "\"0\"")
1604 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1606 ;; The "install" target does not create the target directory.
1607 (add-before 'install 'create-target-dir
1608 (lambda* (#:key outputs #:allow-other-keys)
1609 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1613 (home-page "http://weizhongli-lab.org/cd-hit/")
1614 (synopsis "Cluster and compare protein or nucleotide sequences")
1616 "CD-HIT is a program for clustering and comparing protein or nucleotide
1617 sequences. CD-HIT is designed to be fast and handle extremely large
1619 ;; The manual says: "It can be copied under the GNU General Public License
1620 ;; version 2 (GPLv2)."
1621 (license license:gpl2)))
1623 (define-public clipper
1630 "https://github.com/YeoLab/clipper/archive/"
1632 (file-name (string-append name "-" version ".tar.gz"))
1635 "0pflmsvhbf8izbgwhbhj1i7349sw1f55qpqj8ljmapp16hb0p0qi"))
1636 (modules '((guix build utils)))
1639 ;; remove unnecessary setup dependency
1640 (substitute* "setup.py"
1641 (("setup_requires = .*") ""))
1642 (for-each delete-file
1643 '("clipper/src/peaks.so"
1644 "clipper/src/readsToWiggle.so"))
1645 (delete-file-recursively "dist/")
1647 (build-system python-build-system)
1648 (arguments `(#:python ,python-2)) ; only Python 2 is supported
1650 `(("htseq" ,python2-htseq)
1651 ("python-pybedtools" ,python2-pybedtools)
1652 ("python-cython" ,python2-cython)
1653 ("python-scikit-learn" ,python2-scikit-learn)
1654 ("python-matplotlib" ,python2-matplotlib)
1655 ("python-pandas" ,python2-pandas)
1656 ("python-pysam" ,python2-pysam)
1657 ("python-numpy" ,python2-numpy)
1658 ("python-scipy" ,python2-scipy)))
1660 `(("python-mock" ,python2-mock) ; for tests
1661 ("python-nose" ,python2-nose) ; for tests
1662 ("python-pytz" ,python2-pytz))) ; for tests
1663 (home-page "https://github.com/YeoLab/clipper")
1664 (synopsis "CLIP peak enrichment recognition")
1666 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1667 (license license:gpl2)))
1669 (define-public codingquarry
1671 (name "codingquarry")
1676 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1680 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1681 (build-system gnu-build-system)
1683 '(#:tests? #f ; no "check" target
1685 (modify-phases %standard-phases
1688 (lambda* (#:key outputs #:allow-other-keys)
1689 (let* ((out (assoc-ref outputs "out"))
1690 (bin (string-append out "/bin"))
1691 (doc (string-append out "/share/doc/codingquarry")))
1692 (install-file "INSTRUCTIONS.pdf" doc)
1693 (copy-recursively "QuarryFiles"
1694 (string-append out "/QuarryFiles"))
1695 (install-file "CodingQuarry" bin)
1696 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
1697 (inputs `(("openmpi" ,openmpi)))
1698 (native-search-paths
1699 (list (search-path-specification
1700 (variable "QUARRY_PATH")
1701 (files '("QuarryFiles")))))
1702 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1703 (synopsis "Fungal gene predictor")
1704 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1705 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1706 (home-page "https://sourceforge.net/projects/codingquarry/")
1707 (license license:gpl3+)))
1709 (define-public couger
1716 "http://couger.oit.duke.edu/static/assets/COUGER"
1720 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1721 (build-system gnu-build-system)
1725 (modify-phases %standard-phases
1730 (lambda* (#:key outputs #:allow-other-keys)
1731 (let* ((out (assoc-ref outputs "out"))
1732 (bin (string-append out "/bin")))
1733 (copy-recursively "src" (string-append out "/src"))
1735 ;; Add "src" directory to module lookup path.
1736 (substitute* "couger"
1738 (string-append "import sys\nsys.path.append(\""
1739 out "\")\nfrom argparse")))
1740 (install-file "couger" bin))
1743 'install 'wrap-program
1744 (lambda* (#:key inputs outputs #:allow-other-keys)
1745 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1746 (let* ((out (assoc-ref outputs "out"))
1747 (path (getenv "PYTHONPATH")))
1748 (wrap-program (string-append out "/bin/couger")
1749 `("PYTHONPATH" ":" prefix (,path))))
1752 `(("python" ,python-2)
1753 ("python2-pillow" ,python2-pillow)
1754 ("python2-numpy" ,python2-numpy)
1755 ("python2-scipy" ,python2-scipy)
1756 ("python2-matplotlib" ,python2-matplotlib)))
1758 `(("r-minimal" ,r-minimal)
1760 ("randomjungle" ,randomjungle)))
1762 `(("unzip" ,unzip)))
1763 (home-page "http://couger.oit.duke.edu")
1764 (synopsis "Identify co-factors in sets of genomic regions")
1766 "COUGER can be applied to any two sets of genomic regions bound by
1767 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1768 putative co-factors that provide specificity to each TF. The framework
1769 determines the genomic targets uniquely-bound by each TF, and identifies a
1770 small set of co-factors that best explain the in vivo binding differences
1771 between the two TFs.
1773 COUGER uses classification algorithms (support vector machines and random
1774 forests) with features that reflect the DNA binding specificities of putative
1775 co-factors. The features are generated either from high-throughput TF-DNA
1776 binding data (from protein binding microarray experiments), or from large
1777 collections of DNA motifs.")
1778 (license license:gpl3+)))
1780 (define-public clustal-omega
1782 (name "clustal-omega")
1786 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1790 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1791 (build-system gnu-build-system)
1793 `(("argtable" ,argtable)))
1794 (home-page "http://www.clustal.org/omega/")
1795 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1797 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1798 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1799 of handling data-sets of hundreds of thousands of sequences in reasonable
1801 (license license:gpl2+)))
1803 (define-public crossmap
1809 (uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
1813 "07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
1814 ;; This patch has been sent upstream already and is available
1815 ;; for download from Sourceforge, but it has not been merged.
1816 (patches (search-patches "crossmap-allow-system-pysam.patch"))
1817 (modules '((guix build utils)))
1818 ;; remove bundled copy of pysam
1820 '(delete-file-recursively "lib/pysam"))))
1821 (build-system python-build-system)
1823 `(#:python ,python-2
1825 (modify-phases %standard-phases
1826 (add-after 'unpack 'set-env
1827 (lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1") #t)))))
1829 `(("python-numpy" ,python2-numpy)
1830 ("python-pysam" ,python2-pysam)
1833 `(("python-cython" ,python2-cython)
1834 ("python-nose" ,python2-nose)))
1835 (home-page "http://crossmap.sourceforge.net/")
1836 (synopsis "Convert genome coordinates between assemblies")
1838 "CrossMap is a program for conversion of genome coordinates or annotation
1839 files between different genome assemblies. It supports most commonly used
1840 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
1841 (license license:gpl2+)))
1843 (define-public cutadapt
1850 "https://github.com/marcelm/cutadapt/archive/v"
1852 (file-name (string-append name "-" version ".tar.gz"))
1855 "16gbpiwy4m48vq2h5wqar3i8vr6vcj9gcl2qvqim19x6ya9dp8kd"))))
1856 (build-system python-build-system)
1859 (modify-phases %standard-phases
1860 ;; The tests must be run after installation.
1862 (add-after 'install 'check
1863 (lambda* (#:key inputs outputs #:allow-other-keys)
1864 (setenv "PYTHONPATH"
1866 (getenv "PYTHONPATH")
1867 ":" (assoc-ref outputs "out")
1869 (string-take (string-take-right
1870 (assoc-ref inputs "python") 5) 3)
1872 (zero? (system* "nosetests" "-P" "tests")))))))
1874 `(("python-xopen" ,python-xopen)))
1876 `(("python-cython" ,python-cython)
1877 ("python-nose" ,python-nose)))
1878 (home-page "https://cutadapt.readthedocs.io/en/stable/")
1879 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
1881 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
1882 other types of unwanted sequence from high-throughput sequencing reads.")
1883 (license license:expat)))
1885 (define-public libbigwig
1891 (uri (string-append "https://github.com/dpryan79/libBigWig/"
1892 "archive/" version ".tar.gz"))
1893 (file-name (string-append name "-" version ".tar.gz"))
1896 "098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
1897 (build-system gnu-build-system)
1899 `(#:test-target "test"
1902 (string-append "prefix=" (assoc-ref %outputs "out")))
1904 (modify-phases %standard-phases
1906 (add-before 'check 'disable-curl-test
1908 (substitute* "Makefile"
1909 (("./test/testRemote.*") ""))
1911 ;; This has been fixed with the upstream commit 4ff6959cd8a0, but
1912 ;; there has not yet been a release containing this change.
1913 (add-before 'install 'create-target-dirs
1914 (lambda* (#:key outputs #:allow-other-keys)
1915 (let ((out (assoc-ref outputs "out")))
1916 (mkdir-p (string-append out "/lib"))
1917 (mkdir-p (string-append out "/include"))
1923 `(("doxygen" ,doxygen)))
1924 (home-page "https://github.com/dpryan79/libBigWig")
1925 (synopsis "C library for handling bigWig files")
1927 "This package provides a C library for parsing local and remote BigWig
1929 (license license:expat)))
1931 (define-public python-pybigwig
1933 (name "python-pybigwig")
1937 (uri (pypi-uri "pyBigWig" version))
1940 "0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
1941 (modules '((guix build utils)))
1944 ;; Delete bundled libBigWig sources
1945 (delete-file-recursively "libBigWig")))))
1946 (build-system python-build-system)
1949 (modify-phases %standard-phases
1950 (add-after 'unpack 'link-with-libBigWig
1951 (lambda* (#:key inputs #:allow-other-keys)
1952 (substitute* "setup.py"
1953 (("libs=\\[") "libs=[\"BigWig\", "))
1956 `(("libbigwig" ,libbigwig)
1959 (home-page "https://github.com/dpryan79/pyBigWig")
1960 (synopsis "Access bigWig files in Python using libBigWig")
1962 "This package provides Python bindings to the libBigWig library for
1963 accessing bigWig files.")
1964 (license license:expat)))
1966 (define-public python2-pybigwig
1967 (package-with-python2 python-pybigwig))
1969 (define-public python-dendropy
1971 (name "python-dendropy")
1976 (uri (pypi-uri "DendroPy" version))
1979 "15c7s3d5gf19ljsxvq5advaa752wfi7pwrdjyhzmg85hccyvp47p"))
1980 (patches (search-patches "python-dendropy-fix-tests.patch"))))
1981 (build-system python-build-system)
1982 (home-page "http://packages.python.org/DendroPy/")
1983 (synopsis "Library for phylogenetics and phylogenetic computing")
1985 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
1986 writing, simulation, processing and manipulation of phylogenetic
1987 trees (phylogenies) and characters.")
1988 (license license:bsd-3)
1989 (properties `((python2-variant . ,(delay python2-dendropy))))))
1991 (define-public python2-dendropy
1992 (let ((base (package-with-python2 (strip-python2-variant python-dendropy))))
1996 `(#:python ,python-2
1998 (modify-phases %standard-phases
2000 ;; There is currently a test failure that only happens on some
2001 ;; systems, and only using "setup.py test"
2002 (lambda _ (zero? (system* "nosetests")))))))
2003 (native-inputs `(("python2-nose" ,python2-nose)
2004 ,@(package-native-inputs base))))))
2006 (define-public python-py2bit
2008 (name "python-py2bit")
2013 (uri (pypi-uri "py2bit" version))
2016 "1cdf4qlmgwsh1f4k0wdv2sr8x9qn4366p0k3614vbd0fpqiarxrl"))))
2017 (build-system python-build-system)
2018 (home-page "https://github.com/dpryan79/py2bit")
2019 (synopsis "Access 2bit files using lib2bit")
2021 "This package provides Python bindings for lib2bit to access 2bit files
2023 (license license:expat)))
2025 (define-public deeptools
2031 (uri (string-append "https://github.com/fidelram/deepTools/"
2032 "archive/" version ".tar.gz"))
2033 (file-name (string-append name "-" version ".tar.gz"))
2036 "1q8i12l2gvk4n2s8lhyzwhh9g4qbc8lrk5l7maz00yvd5g6z5540"))))
2037 (build-system python-build-system)
2039 `(("python-scipy" ,python-scipy)
2040 ("python-numpy" ,python-numpy)
2041 ("python-numpydoc" ,python-numpydoc)
2042 ("python-matplotlib" ,python-matplotlib)
2043 ("python-pysam" ,python-pysam)
2044 ("python-py2bit" ,python-py2bit)
2045 ("python-pybigwig" ,python-pybigwig)))
2047 `(("python-mock" ,python-mock) ;for tests
2048 ("python-nose" ,python-nose) ;for tests
2049 ("python-pytz" ,python-pytz))) ;for tests
2050 (home-page "https://github.com/fidelram/deepTools")
2051 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2053 "DeepTools addresses the challenge of handling the large amounts of data
2054 that are now routinely generated from DNA sequencing centers. To do so,
2055 deepTools contains useful modules to process the mapped reads data to create
2056 coverage files in standard bedGraph and bigWig file formats. By doing so,
2057 deepTools allows the creation of normalized coverage files or the comparison
2058 between two files (for example, treatment and control). Finally, using such
2059 normalized and standardized files, multiple visualizations can be created to
2060 identify enrichments with functional annotations of the genome.")
2061 (license license:gpl3+)))
2063 (define-public diamond
2070 "https://github.com/bbuchfink/diamond/archive/v"
2072 (file-name (string-append name "-" version ".tar.gz"))
2075 "1pi5ncqwmynqpmmp3j3lhnqrjhj34sr6wpmsgrpkv3wyxx22fv86"))))
2076 (build-system cmake-build-system)
2078 '(#:tests? #f ; no "check" target
2080 (modify-phases %standard-phases
2081 (add-after 'unpack 'remove-native-compilation
2083 (substitute* "CMakeLists.txt" (("-march=native") ""))
2087 (home-page "https://github.com/bbuchfink/diamond")
2088 (synopsis "Accelerated BLAST compatible local sequence aligner")
2090 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2091 translated DNA query sequences against a protein reference database (BLASTP
2092 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2093 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2094 data and settings.")
2095 (license license:agpl3+)))
2097 (define-public discrover
2104 (uri (string-append "https://github.com/maaskola/discrover/archive/"
2106 (file-name (string-append name "-" version ".tar.gz"))
2109 "0rah9ja4m0rl5mldd6vag9rwrivw1zrqxssfq8qx64m7961fp68k"))))
2110 (build-system cmake-build-system)
2112 `(#:tests? #f ; there are no tests
2114 (modify-phases %standard-phases
2115 (add-after 'unpack 'add-missing-includes
2117 (substitute* "src/executioninformation.hpp"
2118 (("#define EXECUTIONINFORMATION_HPP" line)
2119 (string-append line "\n#include <random>")))
2120 (substitute* "src/plasma/fasta.hpp"
2121 (("#define FASTA_HPP" line)
2122 (string-append line "\n#include <random>")))
2128 `(("texlive" ,texlive)
2129 ("imagemagick" ,imagemagick)))
2130 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2131 (synopsis "Discover discriminative nucleotide sequence motifs")
2132 (description "Discrover is a motif discovery method to find binding sites
2133 of nucleic acid binding proteins.")
2134 (license license:gpl3+)))
2136 (define-public eigensoft
2137 (let ((revision "1")
2138 (commit "b14d1e202e21e532536ff8004f0419cd5e259dc7"))
2141 (version (string-append "6.1.2-"
2143 (string-take commit 9)))
2148 (url "https://github.com/DReichLab/EIG.git")
2150 (file-name (string-append "eigensoft-" commit "-checkout"))
2153 "0f5m6k2j5c16xc3xbywcs989xyc26ncy1zfzp9j9n55n9r4xcaiq"))
2154 (modules '((guix build utils)))
2155 ;; Remove pre-built binaries.
2157 (delete-file-recursively "bin")
2160 (build-system gnu-build-system)
2162 `(#:tests? #f ; There are no tests.
2163 #:make-flags '("CC=gcc")
2165 (modify-phases %standard-phases
2166 ;; There is no configure phase, but the Makefile is in a
2171 ;; The link flags are incomplete.
2172 (substitute* "Makefile"
2173 (("-lgsl") "-lgsl -lm -llapack -llapacke -lpthread"))
2175 ;; The provided install target only copies executables to
2176 ;; the "bin" directory in the build root.
2177 (add-after 'install 'actually-install
2178 (lambda* (#:key outputs #:allow-other-keys)
2179 (let* ((out (assoc-ref outputs "out"))
2180 (bin (string-append out "/bin")))
2181 (for-each (lambda (file)
2182 (install-file file bin))
2183 (find-files "../bin" ".*"))
2188 ("openblas" ,openblas)
2190 ("gfortran" ,gfortran "lib")))
2191 (home-page "https://github.com/DReichLab/EIG")
2192 (synopsis "Tools for population genetics")
2193 (description "The EIGENSOFT package provides tools for population
2194 genetics and stratification correction. EIGENSOFT implements methods commonly
2195 used in population genetics analyses such as PCA, computation of Tracy-Widom
2196 statistics, and finding related individuals in structured populations. It
2197 comes with a built-in plotting script and supports multiple file formats and
2198 quantitative phenotypes.")
2199 ;; The license of the eigensoft tools is Expat, but since it's
2200 ;; linking with the GNU Scientific Library (GSL) the effective
2201 ;; license is the GPL.
2202 (license license:gpl3+))))
2204 (define-public edirect
2210 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
2211 "versions/2016-05-03/edirect.tar.gz"))
2214 "15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
2215 (build-system perl-build-system)
2217 `(#:tests? #f ;no "check" target
2219 (modify-phases %standard-phases
2223 (lambda* (#:key outputs #:allow-other-keys)
2224 (let ((target (string-append (assoc-ref outputs "out")
2227 (install-file "edirect.pl" target)
2230 'install 'wrap-program
2231 (lambda* (#:key inputs outputs #:allow-other-keys)
2232 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2233 (let* ((out (assoc-ref outputs "out"))
2234 (path (getenv "PERL5LIB")))
2235 (wrap-program (string-append out "/bin/edirect.pl")
2236 `("PERL5LIB" ":" prefix (,path)))))))))
2238 `(("perl-html-parser" ,perl-html-parser)
2239 ("perl-encode-locale" ,perl-encode-locale)
2240 ("perl-file-listing" ,perl-file-listing)
2241 ("perl-html-tagset" ,perl-html-tagset)
2242 ("perl-html-tree" ,perl-html-tree)
2243 ("perl-http-cookies" ,perl-http-cookies)
2244 ("perl-http-date" ,perl-http-date)
2245 ("perl-http-message" ,perl-http-message)
2246 ("perl-http-negotiate" ,perl-http-negotiate)
2247 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2248 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2249 ("perl-net-http" ,perl-net-http)
2250 ("perl-uri" ,perl-uri)
2251 ("perl-www-robotrules" ,perl-www-robotrules)
2253 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2254 (synopsis "Tools for accessing the NCBI's set of databases")
2256 "Entrez Direct (EDirect) is a method for accessing the National Center
2257 for Biotechnology Information's (NCBI) set of interconnected
2258 databases (publication, sequence, structure, gene, variation, expression,
2259 etc.) from a terminal. Functions take search terms from command-line
2260 arguments. Individual operations are combined to build multi-step queries.
2261 Record retrieval and formatting normally complete the process.
2263 EDirect also provides an argument-driven function that simplifies the
2264 extraction of data from document summaries or other results that are returned
2265 in structured XML format. This can eliminate the need for writing custom
2266 software to answer ad hoc questions.")
2267 (license license:public-domain)))
2269 (define-public exonerate
2278 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2279 "exonerate-" version ".tar.gz"))
2282 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2283 (build-system gnu-build-system)
2285 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2287 `(("pkg-config" ,pkg-config)))
2291 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2292 (synopsis "Generic tool for biological sequence alignment")
2294 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2295 the alignment of sequences using a many alignment models, either exhaustive
2296 dynamic programming or a variety of heuristics.")
2297 (license license:gpl3)))
2299 (define-public express
2307 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2308 version "/express-" version "-src.tgz"))
2311 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2312 (build-system cmake-build-system)
2314 `(#:tests? #f ;no "check" target
2316 (modify-phases %standard-phases
2317 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2318 (lambda* (#:key inputs #:allow-other-keys)
2319 (substitute* "CMakeLists.txt"
2320 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2321 "set(Boost_USE_STATIC_LIBS OFF)")
2322 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2323 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2324 (substitute* "src/CMakeLists.txt"
2325 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2326 (string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
2330 ("bamtools" ,bamtools)
2331 ("protobuf" ,protobuf)
2333 (home-page "http://bio.math.berkeley.edu/eXpress")
2334 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2336 "eXpress is a streaming tool for quantifying the abundances of a set of
2337 target sequences from sampled subsequences. Example applications include
2338 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2339 analysis (from RNA-Seq), transcription factor binding quantification in
2340 ChIP-Seq, and analysis of metagenomic data.")
2341 (license license:artistic2.0)))
2343 (define-public express-beta-diversity
2345 (name "express-beta-diversity")
2351 "https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
2353 (file-name (string-append name "-" version ".tar.gz"))
2356 "1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
2357 (build-system gnu-build-system)
2360 (modify-phases %standard-phases
2362 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2364 (lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
2366 (add-after 'check 'exit-source (lambda _ (chdir "..") #t))
2368 (lambda* (#:key outputs #:allow-other-keys)
2369 (let ((bin (string-append (assoc-ref outputs "out")
2372 (install-file "scripts/convertToEBD.py" bin)
2373 (install-file "bin/ExpressBetaDiversity" bin)
2376 `(("python" ,python-2)))
2377 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2378 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2380 "Express Beta Diversity (EBD) calculates ecological beta diversity
2381 (dissimilarity) measures between biological communities. EBD implements a
2382 variety of diversity measures including those that make use of phylogenetic
2383 similarity of community members.")
2384 (license license:gpl3+)))
2386 (define-public fasttree
2393 "http://www.microbesonline.org/fasttree/FastTree-"
2397 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2398 (build-system gnu-build-system)
2400 `(#:tests? #f ; no "check" target
2402 (modify-phases %standard-phases
2406 (lambda* (#:key source #:allow-other-keys)
2407 (and (zero? (system* "gcc"
2409 "-finline-functions"
2416 (zero? (system* "gcc"
2420 "-finline-functions"
2428 (lambda* (#:key outputs #:allow-other-keys)
2429 (let ((bin (string-append (assoc-ref outputs "out")
2432 (install-file "FastTree" bin)
2433 (install-file "FastTreeMP" bin)
2435 (home-page "http://www.microbesonline.org/fasttree")
2436 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2438 "FastTree can handle alignments with up to a million of sequences in a
2439 reasonable amount of time and memory. For large alignments, FastTree is
2440 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2441 (license license:gpl2+)))
2443 (define-public fastx-toolkit
2445 (name "fastx-toolkit")
2451 "https://github.com/agordon/fastx_toolkit/releases/download/"
2452 version "/fastx_toolkit-" version ".tar.bz2"))
2455 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2456 (build-system gnu-build-system)
2458 `(("libgtextutils" ,libgtextutils)))
2460 `(("pkg-config" ,pkg-config)))
2461 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2462 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2464 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2465 FASTA/FASTQ files preprocessing.
2467 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2468 containing multiple short-reads sequences. The main processing of such
2469 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2470 is sometimes more productive to preprocess the files before mapping the
2471 sequences to the genome---manipulating the sequences to produce better mapping
2472 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2473 (license license:agpl3+)))
2475 (define-public flexbar
2482 (string-append "mirror://sourceforge/flexbar/"
2483 version "/flexbar_v" version "_src.tgz"))
2486 "13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
2487 (build-system cmake-build-system)
2489 `(#:configure-flags (list
2490 (string-append "-DFLEXBAR_BINARY_DIR="
2491 (assoc-ref %outputs "out")
2494 (modify-phases %standard-phases
2496 (lambda* (#:key outputs #:allow-other-keys)
2497 (setenv "PATH" (string-append
2498 (assoc-ref outputs "out") "/bin:"
2500 (chdir "../flexbar_v2.5_src/test")
2501 (zero? (system* "bash" "flexbar_validate.sh"))))
2502 (delete 'install))))
2507 `(("pkg-config" ,pkg-config)
2509 (home-page "http://flexbar.sourceforge.net")
2510 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2512 "Flexbar preprocesses high-throughput nucleotide sequencing data
2513 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2514 Moreover, trimming and filtering features are provided. Flexbar increases
2515 read mapping rates and improves genome and transcriptome assemblies. It
2516 supports next-generation sequencing data in fasta/q and csfasta/q format from
2517 Illumina, Roche 454, and the SOLiD platform.")
2518 (license license:gpl3)))
2520 (define-public fraggenescan
2522 (name "fraggenescan")
2528 (string-append "mirror://sourceforge/fraggenescan/"
2529 "FragGeneScan" version ".tar.gz"))
2531 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2532 (build-system gnu-build-system)
2535 (modify-phases %standard-phases
2537 (add-before 'build 'patch-paths
2538 (lambda* (#:key outputs #:allow-other-keys)
2539 (let* ((out (string-append (assoc-ref outputs "out")))
2540 (share (string-append out "/share/fraggenescan/")))
2541 (substitute* "run_FragGeneScan.pl"
2543 (string-append "system(\"" (which "rm")))
2545 (string-append "system(\"" (which "mv")))
2546 (("\\\"awk") (string-append "\"" (which "awk")))
2547 ;; This script and other programs expect the training files
2548 ;; to be in the non-standard location bin/train/XXX. Change
2549 ;; this to be share/fraggenescan/train/XXX instead.
2550 (("^\\$train.file = \\$dir.*")
2551 (string-append "$train_file = \""
2553 "train/\".$FGS_train_file;")))
2554 (substitute* "run_hmm.c"
2555 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2556 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2559 (lambda _ (and (zero? (system* "make" "clean"))
2560 (zero? (system* "make" "fgs")))))
2562 (lambda* (#:key outputs #:allow-other-keys)
2563 (let* ((out (string-append (assoc-ref outputs "out")))
2564 (bin (string-append out "/bin/"))
2565 (share (string-append out "/share/fraggenescan/train")))
2566 (install-file "run_FragGeneScan.pl" bin)
2567 (install-file "FragGeneScan" bin)
2568 (copy-recursively "train" share))))
2570 (add-after 'install 'post-install-check
2571 ;; In lieu of 'make check', run one of the examples and check the
2572 ;; output files gets created.
2573 (lambda* (#:key outputs #:allow-other-keys)
2574 (let* ((out (string-append (assoc-ref outputs "out")))
2575 (bin (string-append out "/bin/"))
2576 (frag (string-append bin "run_FragGeneScan.pl")))
2577 (and (zero? (system* frag ; Test complete genome.
2578 "-genome=./example/NC_000913.fna"
2582 (file-exists? "test2.faa")
2583 (file-exists? "test2.ffn")
2584 (file-exists? "test2.gff")
2585 (file-exists? "test2.out")
2586 (zero? (system* ; Test incomplete sequences.
2588 "-genome=./example/NC_000913-fgs.ffn"
2591 "-train=454_30")))))))))
2594 ("python" ,python-2))) ;not compatible with python 3.
2595 (home-page "https://sourceforge.net/projects/fraggenescan/")
2596 (synopsis "Finds potentially fragmented genes in short reads")
2598 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2599 short and error-prone DNA sequencing reads. It can also be applied to predict
2600 genes in incomplete assemblies or complete genomes.")
2601 ;; GPL3+ according to private correspondense with the authors.
2602 (license license:gpl3+)))
2604 (define-public fxtract
2605 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2613 "https://github.com/ctSkennerton/fxtract/archive/"
2615 (file-name (string-append "ctstennerton-util-"
2616 (string-take util-commit 7)
2620 "0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
2621 (build-system gnu-build-system)
2623 `(#:make-flags (list
2624 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2626 #:test-target "fxtract_test"
2628 (modify-phases %standard-phases
2630 (add-before 'build 'copy-util
2631 (lambda* (#:key inputs #:allow-other-keys)
2633 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2635 ;; Do not use make install as this requires additional dependencies.
2637 (lambda* (#:key outputs #:allow-other-keys)
2638 (let* ((out (assoc-ref outputs "out"))
2639 (bin (string-append out"/bin")))
2640 (install-file "fxtract" bin)
2646 ;; ctskennerton-util is licensed under GPL2.
2647 `(("ctskennerton-util"
2651 (url "https://github.com/ctSkennerton/util.git")
2652 (commit util-commit)))
2653 (file-name (string-append
2654 "ctstennerton-util-" util-commit "-checkout"))
2657 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2658 (home-page "https://github.com/ctSkennerton/fxtract")
2659 (synopsis "Extract sequences from FASTA and FASTQ files")
2661 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2662 or FASTQ) file given a subsequence. It uses a simple substring search for
2663 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2664 lookups or multi-pattern searching as required. By default fxtract looks in
2665 the sequence of each record but can also be told to look in the header,
2666 comment or quality sections.")
2667 ;; 'util' requires SSE instructions.
2668 (supported-systems '("x86_64-linux"))
2669 (license license:expat))))
2671 (define-public gemma
2677 (uri (string-append "https://github.com/xiangzhou/GEMMA/archive/v"
2679 (file-name (string-append name "-" version ".tar.gz"))
2682 "055ynn16gd12pf78n4vr2a9jlwsbwzajpdnf2y2yilg1krfff222"))
2683 (patches (search-patches "gemma-intel-compat.patch"))))
2688 (build-system gnu-build-system)
2691 '(,@(match (%current-system)
2693 '("FORCE_DYNAMIC=1"))
2695 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2697 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2699 (modify-phases %standard-phases
2701 (add-before 'build 'bin-mkdir
2706 (lambda* (#:key outputs #:allow-other-keys)
2707 (let ((out (assoc-ref outputs "out")))
2708 (install-file "bin/gemma"
2712 #:tests? #f)) ; no tests included yet
2713 (home-page "https://github.com/xiangzhou/GEMMA")
2714 (synopsis "Tool for genome-wide efficient mixed model association")
2716 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
2717 standard linear mixed model resolver with application in genome-wide
2718 association studies (GWAS).")
2719 (license license:gpl3)))
2728 "https://github.com/nboley/grit/archive/"
2730 (file-name (string-append name "-" version ".tar.gz"))
2733 "157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
2734 (build-system python-build-system)
2736 `(#:python ,python-2
2738 (modify-phases %standard-phases
2739 (add-after 'unpack 'generate-from-cython-sources
2740 (lambda* (#:key inputs outputs #:allow-other-keys)
2741 ;; Delete these C files to force fresh generation from pyx sources.
2742 (delete-file "grit/sparsify_support_fns.c")
2743 (delete-file "grit/call_peaks_support_fns.c")
2744 (substitute* "setup.py"
2745 (("Cython.Setup") "Cython.Build")
2746 ;; Add numpy include path to fix compilation
2748 (string-append "pyx\", ], include_dirs = ['"
2749 (assoc-ref inputs "python-numpy")
2750 "/lib/python2.7/site-packages/numpy/core/include/"
2754 `(("python-scipy" ,python2-scipy)
2755 ("python-numpy" ,python2-numpy)
2756 ("python-pysam" ,python2-pysam)
2757 ("python-networkx" ,python2-networkx)))
2759 `(("python-cython" ,python2-cython)))
2760 (home-page "http://grit-bio.org")
2761 (synopsis "Tool for integrative analysis of RNA-seq type assays")
2763 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
2764 full length transcript models. When none of these data sources are available,
2765 GRIT can be run by providing a candidate set of TES or TSS sites. In
2766 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
2767 also be run in quantification mode, where it uses a provided GTF file and just
2768 estimates transcript expression.")
2769 (license license:gpl3+)))
2771 (define-public hisat
2778 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
2779 version "-beta-source.zip"))
2782 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
2783 (build-system gnu-build-system)
2785 `(#:tests? #f ;no check target
2786 #:make-flags '("allall"
2787 ;; Disable unsupported `popcnt' instructions on
2788 ;; architectures other than x86_64
2789 ,@(if (string-prefix? "x86_64"
2790 (or (%current-target-system)
2793 '("POPCNT_CAPABILITY=0")))
2795 (modify-phases %standard-phases
2796 (add-after 'unpack 'patch-sources
2798 ;; XXX Cannot use snippet because zip files are not supported
2799 (substitute* "Makefile"
2800 (("^CC = .*$") "CC = gcc")
2801 (("^CPP = .*$") "CPP = g++")
2802 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
2803 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
2804 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
2805 (substitute* '("hisat-build" "hisat-inspect")
2806 (("/usr/bin/env") (which "env")))
2809 (lambda* (#:key outputs #:allow-other-keys)
2810 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
2811 (for-each (lambda (file)
2812 (install-file file bin))
2815 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
2817 (delete 'configure))))
2819 `(("unzip" ,unzip)))
2824 ;; Non-portable SSE instructions are used so building fails on platforms
2825 ;; other than x86_64.
2826 (supported-systems '("x86_64-linux"))
2827 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
2828 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
2830 "HISAT is a fast and sensitive spliced alignment program for mapping
2831 RNA-seq reads. In addition to one global FM index that represents a whole
2832 genome, HISAT uses a large set of small FM indexes that collectively cover the
2833 whole genome. These small indexes (called local indexes) combined with
2834 several alignment strategies enable effective alignment of RNA-seq reads, in
2835 particular, reads spanning multiple exons.")
2836 (license license:gpl3+)))
2838 (define-public hisat2
2845 ;; FIXME: a better source URL is
2846 ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
2847 ;; "/downloads/hisat2-" version "-source.zip")
2848 ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
2849 ;; but it is currently unavailable.
2850 (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
2851 (file-name (string-append name "-" version ".tar.gz"))
2854 "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
2855 (build-system gnu-build-system)
2857 `(#:tests? #f ; no check target
2858 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
2859 #:modules ((guix build gnu-build-system)
2863 (modify-phases %standard-phases
2864 (add-after 'unpack 'make-deterministic
2866 (substitute* "Makefile"
2871 (lambda* (#:key outputs #:allow-other-keys)
2872 (let* ((out (assoc-ref outputs "out"))
2873 (bin (string-append out "/bin/"))
2874 (doc (string-append out "/share/doc/hisat2/")))
2876 (cut install-file <> bin)
2878 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
2880 (install-file "doc/manual.inc.html" doc))
2883 `(("unzip" ,unzip) ; needed for archive from ftp
2885 ("pandoc" ,ghc-pandoc))) ; for documentation
2886 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
2887 (synopsis "Graph-based alignment of genomic sequencing reads")
2888 (description "HISAT2 is a fast and sensitive alignment program for mapping
2889 next-generation sequencing reads (both DNA and RNA) to a population of human
2890 genomes (as well as to a single reference genome). In addition to using one
2891 global @dfn{graph FM} (GFM) index that represents a population of human
2892 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
2893 the whole genome. These small indexes, combined with several alignment
2894 strategies, enable rapid and accurate alignment of sequencing reads. This new
2895 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
2896 ;; HISAT2 contains files from Bowtie2, which is released under
2897 ;; GPLv2 or later. The HISAT2 source files are released under
2899 (license license:gpl3+)))
2901 (define-public hmmer
2909 "http://eddylab.org/software/hmmer"
2910 (version-prefix version 1) "/"
2911 version "/hmmer-" version ".tar.gz"))
2914 "0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))
2915 (patches (search-patches "hmmer-remove-cpu-specificity.patch"))))
2916 (build-system gnu-build-system)
2917 (native-inputs `(("perl" ,perl)))
2918 (home-page "http://hmmer.org/")
2919 (synopsis "Biosequence analysis using profile hidden Markov models")
2921 "HMMER is used for searching sequence databases for homologs of protein
2922 sequences, and for making protein sequence alignments. It implements methods
2923 using probabilistic models called profile hidden Markov models (profile
2925 (license (list license:gpl3+
2926 ;; The bundled library 'easel' is distributed
2927 ;; under The Janelia Farm Software License.
2928 (license:non-copyleft
2929 "file://easel/LICENSE"
2930 "See easel/LICENSE in the distribution.")))))
2932 (define-public htseq
2938 (uri (pypi-uri "HTSeq" version))
2941 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
2942 (build-system python-build-system)
2944 `(("python-cython" ,python-cython)))
2945 ;; Numpy needs to be propagated when htseq is used as a Python library.
2947 `(("python-numpy" ,python-numpy)))
2949 `(("python-pysam" ,python-pysam)
2950 ("python-matplotlib" ,python-matplotlib)))
2951 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
2952 (synopsis "Analysing high-throughput sequencing data with Python")
2954 "HTSeq is a Python package that provides infrastructure to process data
2955 from high-throughput sequencing assays.")
2956 (license license:gpl3+)))
2958 (define-public python2-htseq
2959 (package-with-python2 htseq))
2961 (define-public java-htsjdk
2963 (name "java-htsjdk")
2968 "https://github.com/samtools/htsjdk/archive/"
2970 (file-name (string-append name "-" version ".tar.gz"))
2973 "0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
2974 (modules '((guix build utils)))
2975 ;; remove build dependency on git
2976 (snippet '(substitute* "build.xml"
2977 (("failifexecutionfails=\"true\"")
2978 "failifexecutionfails=\"false\"")))))
2979 (build-system ant-build-system)
2981 `(#:tests? #f ; test require Internet access
2983 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
2984 "/share/java/htsjdk/"))
2985 #:build-target "all"
2987 (modify-phases %standard-phases
2988 ;; The build phase also installs the jars
2989 (delete 'install))))
2990 (home-page "http://samtools.github.io/htsjdk/")
2991 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
2993 "HTSJDK is an implementation of a unified Java library for accessing
2994 common file formats, such as SAM and VCF, used for high-throughput
2995 sequencing (HTS) data. There are also an number of useful utilities for
2996 manipulating HTS data.")
2997 (license license:expat)))
2999 (define-public htslib
3006 "https://github.com/samtools/htslib/releases/download/"
3007 version "/htslib-" version ".tar.bz2"))
3010 "0bcjmnbwp2bib1z1bkrp95w9v2syzdwdfqww10mkb1hxlmg52ax0"))))
3011 (build-system gnu-build-system)
3014 (modify-phases %standard-phases
3016 'unpack 'patch-tests
3018 (substitute* "test/test.pl"
3019 (("/bin/bash") (which "bash")))
3022 `(("openssl" ,openssl)
3027 (home-page "http://www.htslib.org")
3028 (synopsis "C library for reading/writing high-throughput sequencing data")
3030 "HTSlib is a C library for reading/writing high-throughput sequencing
3031 data. It also provides the bgzip, htsfile, and tabix utilities.")
3032 ;; Files under cram/ are released under the modified BSD license;
3033 ;; the rest is released under the Expat license
3034 (license (list license:expat license:bsd-3))))
3036 ;; This package should be removed once no packages rely upon it.
3044 "https://github.com/samtools/htslib/releases/download/"
3045 version "/htslib-" version ".tar.bz2"))
3048 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3057 "https://github.com/nboley/idr/archive/"
3059 (file-name (string-append name "-" version ".tar.gz"))
3062 "1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
3063 (build-system python-build-system)
3065 `(#:tests? #f)) ; FIXME: "ImportError: No module named 'utility'"
3067 `(("python-scipy" ,python-scipy)
3068 ("python-sympy" ,python-sympy)
3069 ("python-numpy" ,python-numpy)
3070 ("python-matplotlib" ,python-matplotlib)))
3072 `(("python-cython" ,python-cython)))
3073 (home-page "https://github.com/nboley/idr")
3074 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3076 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3077 to measure the reproducibility of findings identified from replicate
3078 experiments and provide highly stable thresholds based on reproducibility.")
3079 (license license:gpl3+)))
3081 (define-public jellyfish
3087 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3088 "releases/download/v" version
3089 "/jellyfish-" version ".tar.gz"))
3092 "0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
3093 (build-system gnu-build-system)
3094 (outputs '("out" ;for library
3095 "ruby" ;for Ruby bindings
3096 "python")) ;for Python bindings
3099 (list (string-append "--enable-ruby-binding="
3100 (assoc-ref %outputs "ruby"))
3101 (string-append "--enable-python-binding="
3102 (assoc-ref %outputs "python")))
3104 (modify-phases %standard-phases
3105 (add-before 'check 'set-SHELL-variable
3107 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3109 (setenv "SHELL" (which "bash"))
3115 ("python" ,python-2)))
3116 (synopsis "Tool for fast counting of k-mers in DNA")
3118 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3119 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3120 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3121 is a command-line program that reads FASTA and multi-FASTA files containing
3122 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3123 translated into a human-readable text format using the @code{jellyfish dump}
3124 command, or queried for specific k-mers with @code{jellyfish query}.")
3125 (home-page "http://www.genome.umd.edu/jellyfish.html")
3126 ;; From their website: JELLYFISH runs on 64-bit Intel-compatible processors
3127 (supported-systems '("x86_64-linux"))
3128 ;; The combined work is published under the GPLv3 or later. Individual
3129 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3130 (license (list license:gpl3+ license:expat))))
3132 (define-public khmer
3139 (uri (pypi-uri "khmer" version))
3142 "0wb05shqh77v00256qlm68vbbx3kl76fyzihszbz5nhanl4ni33a"))
3143 (patches (search-patches "khmer-use-libraries.patch"))))
3144 (build-system python-build-system)
3147 (modify-phases %standard-phases
3148 (add-after 'unpack 'set-paths
3149 (lambda* (#:key inputs outputs #:allow-other-keys)
3150 ;; Delete bundled libraries.
3151 (delete-file-recursively "third-party/zlib")
3152 (delete-file-recursively "third-party/bzip2")
3153 ;; Replace bundled seqan.
3154 (let* ((seqan-all "third-party/seqan")
3155 (seqan-include (string-append
3156 seqan-all "/core/include")))
3157 (delete-file-recursively seqan-all)
3158 (copy-recursively (string-append (assoc-ref inputs "seqan")
3160 (string-append seqan-include "/seqan")))
3161 ;; We do not replace the bundled MurmurHash as the canonical
3162 ;; repository for this code 'SMHasher' is unsuitable for
3163 ;; providing a library. See
3164 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3166 (add-after 'unpack 'set-cc
3170 ;; It is simpler to test after installation.
3172 (add-after 'install 'post-install-check
3173 (lambda* (#:key inputs outputs #:allow-other-keys)
3174 (let ((out (assoc-ref outputs "out")))
3179 (assoc-ref outputs "out")
3181 (setenv "PYTHONPATH"
3183 (getenv "PYTHONPATH")
3187 (string-take (string-take-right
3188 (assoc-ref inputs "python") 5) 3)
3190 (with-directory-excursion "build"
3191 (zero? (system* "nosetests" "khmer" "--attr"
3192 "!known_failing")))))))))
3195 ("python-nose" ,python-nose)))
3199 ("python-screed" ,python-screed)
3200 ("python-bz2file" ,python-bz2file)
3201 ;; Tests fail when gcc-5 is used for compilation. Use gcc-4.9 at least
3202 ;; until the next version of khmer (likely 2.1) is released.
3204 (home-page "https://khmer.readthedocs.org/")
3205 (synopsis "K-mer counting, filtering and graph traversal library")
3206 (description "The khmer software is a set of command-line tools for
3207 working with DNA shotgun sequencing data from genomes, transcriptomes,
3208 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3209 sometimes better. Khmer can also identify and fix problems with shotgun
3211 ;; When building on i686, armhf and mips64el, we get the following error:
3212 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3213 (supported-systems '("x86_64-linux"))
3214 (license license:bsd-3)))
3216 (define-public kaiju
3223 "https://github.com/bioinformatics-centre/kaiju/archive/v"
3225 (file-name (string-append name "-" version ".tar.gz"))
3228 "0afbfalfw9y39bkwnqjrh9bghs118ws1pzj5h8l0nblgn3mbjdks"))))
3229 (build-system gnu-build-system)
3231 `(#:tests? #f ; There are no tests.
3233 (modify-phases %standard-phases
3235 (add-before 'build 'move-to-src-dir
3236 (lambda _ (chdir "src") #t))
3238 (lambda* (#:key inputs outputs #:allow-other-keys)
3239 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3242 (copy-recursively "bin" bin)
3243 (copy-recursively "util" bin))
3247 (home-page "http://kaiju.binf.ku.dk/")
3248 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3249 (description "Kaiju is a program for sensitive taxonomic classification
3250 of high-throughput sequencing reads from metagenomic whole genome sequencing
3252 (license license:gpl3+)))
3257 (version "2.1.0.20151222")
3260 (uri (pypi-uri "MACS2" version))
3263 "1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
3264 (build-system python-build-system)
3266 `(#:python ,python-2 ; only compatible with Python 2.7
3267 #:tests? #f)) ; no test target
3269 `(("python-numpy" ,python2-numpy)))
3270 (home-page "https://github.com/taoliu/MACS/")
3271 (synopsis "Model based analysis for ChIP-Seq data")
3273 "MACS is an implementation of a ChIP-Seq analysis algorithm for
3274 identifying transcript factor binding sites named Model-based Analysis of
3275 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
3276 the significance of enriched ChIP regions and it improves the spatial
3277 resolution of binding sites through combining the information of both
3278 sequencing tag position and orientation.")
3279 (license license:bsd-3)))
3281 (define-public mafft
3288 "http://mafft.cbrc.jp/alignment/software/mafft-" version
3289 "-without-extensions-src.tgz"))
3290 (file-name (string-append name "-" version ".tgz"))
3293 "0gbsaz6z2qa307kd7wfb06c3y4ikmv1hsdvlns11f6zq4w1z9pwc"))))
3294 (build-system gnu-build-system)
3296 `(#:tests? #f ; no automated tests, though there are tests in the read me
3297 #:make-flags (let ((out (assoc-ref %outputs "out")))
3298 (list (string-append "PREFIX=" out)
3299 (string-append "BINDIR="
3300 (string-append out "/bin"))))
3302 (modify-phases %standard-phases
3303 (add-after 'unpack 'enter-dir
3304 (lambda _ (chdir "core") #t))
3305 (add-after 'enter-dir 'patch-makefile
3307 ;; on advice from the MAFFT authors, there is no need to
3308 ;; distribute mafft-profile, mafft-distance, or
3309 ;; mafft-homologs.rb as they are too "specialised".
3310 (substitute* "Makefile"
3311 ;; remove mafft-homologs.rb from SCRIPTS
3312 (("^SCRIPTS = mafft mafft-homologs.rb")
3314 ;; remove mafft-homologs from MANPAGES
3315 (("^MANPAGES = mafft.1 mafft-homologs.1")
3316 "MANPAGES = mafft.1")
3317 ;; remove mafft-distance from PROGS
3318 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
3319 "PROGS = dvtditr dndfast7 dndblast sextet5")
3320 ;; remove mafft-profile from PROGS
3321 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
3322 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
3323 (("^rm -f mafft-profile mafft-profile.exe") "#")
3324 (("^rm -f mafft-distance mafft-distance.exe") ")#")
3325 ;; do not install MAN pages in libexec folder
3326 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
3327 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
3329 (add-after 'enter-dir 'patch-paths
3330 (lambda* (#:key inputs #:allow-other-keys)
3331 (substitute* '("pairash.c"
3333 (("perl") (which "perl"))
3334 (("([\"`| ])awk" _ prefix)
3335 (string-append prefix (which "awk")))
3336 (("grep") (which "grep")))
3339 (add-after 'install 'wrap-programs
3340 (lambda* (#:key outputs #:allow-other-keys)
3341 (let* ((out (assoc-ref outputs "out"))
3342 (bin (string-append out "/bin"))
3343 (path (string-append
3344 (assoc-ref %build-inputs "coreutils") "/bin:")))
3345 (for-each (lambda (file)
3347 `("PATH" ":" prefix (,path))))
3355 ("coreutils" ,coreutils)))
3356 (home-page "http://mafft.cbrc.jp/alignment/software/")
3357 (synopsis "Multiple sequence alignment program")
3359 "MAFFT offers a range of multiple alignment methods for nucleotide and
3360 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
3361 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
3363 (license (license:non-copyleft
3364 "http://mafft.cbrc.jp/alignment/software/license.txt"
3365 "BSD-3 with different formatting"))))
3374 "https://github.com/marbl/mash/archive/v"
3376 (file-name (string-append name "-" version ".tar.gz"))
3379 "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
3380 (modules '((guix build utils)))
3382 ;; Delete bundled kseq.
3383 ;; TODO: Also delete bundled murmurhash and open bloom filter.
3384 '(delete-file "src/mash/kseq.h"))))
3385 (build-system gnu-build-system)
3387 `(#:tests? #f ; No tests.
3390 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
3391 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
3392 #:make-flags (list "CC=gcc")
3394 (modify-phases %standard-phases
3395 (add-after 'unpack 'fix-includes
3397 (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
3398 (("^#include \"kseq\\.h\"")
3399 "#include \"htslib/kseq.h\""))
3401 (add-after 'fix-includes 'autoconf
3402 (lambda _ (zero? (system* "autoconf")))))))
3404 `(("autoconf" ,autoconf)
3405 ;; Capnproto and htslib are statically embedded in the final
3406 ;; application. Therefore we also list their licenses, below.
3407 ("capnproto" ,capnproto)
3408 ("htslib" ,htslib)))
3412 (supported-systems '("x86_64-linux"))
3413 (home-page "https://mash.readthedocs.io")
3414 (synopsis "Fast genome and metagenome distance estimation using MinHash")
3415 (description "Mash is a fast sequence distance estimator that uses the
3416 MinHash algorithm and is designed to work with genomes and metagenomes in the
3417 form of assemblies or reads.")
3418 (license (list license:bsd-3 ; Mash
3419 license:expat ; HTSlib and capnproto
3420 license:public-domain ; MurmurHash 3
3421 license:cpl1.0)))) ; Open Bloom Filter
3423 (define-public metabat
3430 (uri (string-append "https://bitbucket.org/berkeleylab/metabat/get/v"
3432 (file-name (string-append name "-" version ".tar.gz"))
3435 "1hmvdalz3zj5sqqklg0l4npjdv37cv2hsdi1al9iby2ndxjs1b73"))
3436 (patches (search-patches "metabat-fix-compilation.patch"))))
3437 (build-system gnu-build-system)
3440 (modify-phases %standard-phases
3441 (add-after 'unpack 'fix-includes
3443 (substitute* "src/BamUtils.h"
3444 (("^#include \"bam/bam\\.h\"")
3445 "#include \"samtools/bam.h\"")
3446 (("^#include \"bam/sam\\.h\"")
3447 "#include \"samtools/sam.h\""))
3448 (substitute* "src/KseqReader.h"
3449 (("^#include \"bam/kseq\\.h\"")
3450 "#include \"htslib/kseq.h\""))
3452 (add-after 'unpack 'fix-scons
3453 (lambda* (#:key inputs #:allow-other-keys)
3454 (substitute* "SConstruct"
3455 (("^htslib_dir += 'samtools'")
3456 (string-append "htslib_dir = '"
3457 (assoc-ref inputs "htslib")
3459 (("^samtools_dir = 'samtools'")
3460 (string-append "samtools_dir = '"
3461 (assoc-ref inputs "samtools")
3463 (("^findStaticOrShared\\('bam', hts_lib")
3464 (string-append "findStaticOrShared('bam', '"
3465 (assoc-ref inputs "samtools")
3467 ;; Do not distribute README.
3468 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
3472 (lambda* (#:key inputs outputs #:allow-other-keys)
3473 (mkdir (assoc-ref outputs "out"))
3474 (zero? (system* "scons"
3477 (assoc-ref outputs "out"))
3480 (assoc-ref inputs "boost"))
3482 ;; Check and install are carried out during build phase.
3484 (delete 'install))))
3488 ("samtools" ,samtools)
3492 `(("scons" ,scons)))
3493 (home-page "https://bitbucket.org/berkeleylab/metabat")
3495 "Reconstruction of single genomes from complex microbial communities")
3497 "Grouping large genomic fragments assembled from shotgun metagenomic
3498 sequences to deconvolute complex microbial communities, or metagenome binning,
3499 enables the study of individual organisms and their interactions. MetaBAT is
3500 an automated metagenome binning software, which integrates empirical
3501 probabilistic distances of genome abundance and tetranucleotide frequency.")
3502 ;; The source code contains inline assembly.
3503 (supported-systems '("x86_64-linux" "i686-linux"))
3504 (license (license:non-copyleft "file://license.txt"
3505 "See license.txt in the distribution."))))
3507 (define-public minced
3514 "https://github.com/ctSkennerton/minced/archive/"
3516 (file-name (string-append name "-" version ".tar.gz"))
3519 "0wxmlsapxfpxfd3ps9636h7i2xy6la8i42mwh0j2lsky63h63jp1"))))
3520 (build-system gnu-build-system)
3522 `(#:test-target "test"
3524 (modify-phases %standard-phases
3526 (add-before 'check 'fix-test
3528 ;; Fix test for latest version.
3529 (substitute* "t/Aquifex_aeolicus_VF5.expected"
3530 (("minced:0.1.6") "minced:0.2.0"))
3532 (replace 'install ; No install target.
3533 (lambda* (#:key inputs outputs #:allow-other-keys)
3534 (let* ((out (assoc-ref outputs "out"))
3535 (bin (string-append out "/bin"))
3536 (wrapper (string-append bin "/minced")))
3537 ;; Minced comes with a wrapper script that tries to figure out where
3538 ;; it is located before running the JAR. Since these paths are known
3539 ;; to us, we build our own wrapper to avoid coreutils dependency.
3540 (install-file "minced.jar" bin)
3541 (with-output-to-file wrapper
3545 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
3546 (assoc-ref inputs "jre") "/bin/java -jar "
3547 bin "/minced.jar \"$@\"\n"))))
3548 (chmod wrapper #o555)))))))
3550 `(("jdk" ,icedtea "jdk")))
3553 ("jre" ,icedtea "out")))
3554 (home-page "https://github.com/ctSkennerton/minced")
3555 (synopsis "Mining CRISPRs in Environmental Datasets")
3557 "MinCED is a program to find Clustered Regularly Interspaced Short
3558 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
3559 unassembled metagenomic reads, but is mainly designed for full genomes and
3560 assembled metagenomic sequence.")
3561 (license license:gpl3+)))
3569 (uri (pypi-uri "misopy" version))
3572 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
3573 (modules '((guix build utils)))
3575 '(substitute* "setup.py"
3576 ;; Use setuptools, or else the executables are not
3578 (("distutils.core") "setuptools")
3579 ;; use "gcc" instead of "cc" for compilation
3581 "cc.set_executables(
3585 linker_so='gcc -shared'); defines")))))
3586 (build-system python-build-system)
3588 `(#:python ,python-2 ; only Python 2 is supported
3589 #:tests? #f)) ; no "test" target
3591 `(("samtools" ,samtools)
3592 ("python-numpy" ,python2-numpy)
3593 ("python-pysam" ,python2-pysam)
3594 ("python-scipy" ,python2-scipy)
3595 ("python-matplotlib" ,python2-matplotlib)))
3597 `(("python-mock" ,python2-mock) ;for tests
3598 ("python-pytz" ,python2-pytz))) ;for tests
3599 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
3600 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
3602 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
3603 the expression level of alternatively spliced genes from RNA-Seq data, and
3604 identifies differentially regulated isoforms or exons across samples. By
3605 modeling the generative process by which reads are produced from isoforms in
3606 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
3607 that a read originated from a particular isoform.")
3608 (license license:gpl2)))
3610 (define-public muscle
3613 (version "3.8.1551")
3615 (method url-fetch/tarbomb)
3617 "http://www.drive5.com/muscle/muscle_src_"
3621 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
3622 (build-system gnu-build-system)
3624 `(#:make-flags (list "LDLIBS = -lm")
3626 (modify-phases %standard-phases
3629 ;; There are no tests, so just test if it runs.
3630 (lambda _ (zero? (system* "./muscle" "-version"))))
3632 (lambda* (#:key outputs #:allow-other-keys)
3633 (let* ((out (assoc-ref outputs "out"))
3634 (bin (string-append out "/bin")))
3635 (install-file "muscle" bin)))))))
3636 (home-page "http://www.drive5.com/muscle")
3637 (synopsis "Multiple sequence alignment program")
3639 "MUSCLE aims to be a fast and accurate multiple sequence alignment
3640 program for nucleotide and protein sequences.")
3641 ;; License information found in 'muscle -h' and usage.cpp.
3642 (license license:public-domain)))
3644 (define-public newick-utils
3645 ;; There are no recent releases so we package from git.
3646 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
3648 (name "newick-utils")
3649 (version (string-append "1.6-1." (string-take commit 8)))
3653 (url "https://github.com/tjunier/newick_utils.git")
3655 (file-name (string-append name "-" version "-checkout"))
3658 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
3659 (build-system gnu-build-system)
3662 (modify-phases %standard-phases
3663 (add-after 'unpack 'autoconf
3664 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
3666 ;; XXX: TODO: Enable Lua and Guile bindings.
3667 ;; https://github.com/tjunier/newick_utils/issues/13
3668 `(("libxml2" ,libxml2)
3672 `(("autoconf" ,autoconf)
3673 ("automake" ,automake)
3674 ("libtool" ,libtool)))
3675 (synopsis "Programs for working with newick format phylogenetic trees")
3677 "Newick-utils is a suite of utilities for processing phylogenetic trees
3678 in Newick format. Functions include re-rooting, extracting subtrees,
3679 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
3680 (home-page "https://github.com/tjunier/newick_utils")
3681 (license license:bsd-3))))
3690 "https://github.com/wwood/OrfM/releases/download/v"
3691 version "/orfm-" version ".tar.gz"))
3694 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
3695 (build-system gnu-build-system)
3696 (inputs `(("zlib" ,zlib)))
3698 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
3699 ("ruby-rspec" ,ruby-rspec)
3701 (synopsis "Simple and not slow open reading frame (ORF) caller")
3703 "An ORF caller finds stretches of DNA that, when translated, are not
3704 interrupted by stop codons. OrfM finds and prints these ORFs.")
3705 (home-page "https://github.com/wwood/OrfM")
3706 (license license:lgpl3+)))
3708 (define-public pplacer
3709 (let ((commit "g807f6f3"))
3712 ;; The commit should be updated with each version change.
3713 (version "1.1.alpha19")
3717 (uri (string-append "https://github.com/matsen/pplacer/archive/v"
3719 (file-name (string-append name "-" version ".tar.gz"))
3721 (base32 "0z1lnd2s8sh6kpzg106wzbh2szw7h0hvq8syd5a6wv4rmyyz6x0f"))))
3722 (build-system ocaml-build-system)
3724 `(#:ocaml ,ocaml-4.01
3725 #:findlib ,ocaml4.01-findlib
3726 #:modules ((guix build ocaml-build-system)
3730 (modify-phases %standard-phases
3732 (add-after 'unpack 'replace-bundled-cddlib
3733 (lambda* (#:key inputs #:allow-other-keys)
3734 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
3735 (local-dir "cddlib_guix"))
3737 (with-directory-excursion local-dir
3738 (system* "tar" "xvf" cddlib-src))
3739 (let ((cddlib-src-folder
3740 (string-append local-dir "/"
3741 (list-ref (scandir local-dir) 2)
3746 (string-append "cdd_src/" (basename file))))
3747 (find-files cddlib-src-folder ".*[ch]$")))
3749 (add-after 'unpack 'fix-makefile
3751 ;; Remove system calls to 'git'.
3752 (substitute* "Makefile"
3753 (("^DESCRIPT:=pplacer-.*")
3755 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
3756 (substitute* "myocamlbuild.ml"
3757 (("git describe --tags --long .*\\\" with")
3759 "echo -n v" ,version "-" ,commit "\" with")))
3762 (lambda* (#:key outputs #:allow-other-keys)
3763 (let* ((out (assoc-ref outputs "out"))
3764 (bin (string-append out "/bin")))
3765 (copy-recursively "bin" bin))
3770 ("ocaml-ounit" ,ocaml4.01-ounit)
3771 ("ocaml-batteries" ,ocaml4.01-batteries)
3772 ("ocaml-camlzip" ,ocaml4.01-camlzip)
3773 ("ocaml-csv" ,ocaml4.01-csv)
3774 ("ocaml-sqlite3" ,ocaml4.01-sqlite3)
3775 ("ocaml-xmlm" ,ocaml4.01-xmlm)
3776 ("ocaml-mcl" ,ocaml4.01-mcl)
3777 ("ocaml-gsl" ,ocaml4.01-gsl)
3778 ("cddlib-src" ,(package-source cddlib))))
3780 `(("pplacer-scripts" ,pplacer-scripts)))
3781 (synopsis "Phylogenetic placement of biological sequences")
3783 "Pplacer places query sequences on a fixed reference phylogenetic tree
3784 to maximize phylogenetic likelihood or posterior probability according to a
3785 reference alignment. Pplacer is designed to be fast, to give useful
3786 information about uncertainty, and to offer advanced visualization and
3787 downstream analysis.")
3788 (home-page "http://matsen.fhcrc.org/pplacer")
3789 (license license:gpl3))))
3791 ;; This package is installed alongside 'pplacer'. It is a separate package so
3792 ;; that it can use the python-build-system for the scripts that are
3793 ;; distributed alongside the main OCaml binaries.
3794 (define pplacer-scripts
3797 (name "pplacer-scripts")
3798 (build-system python-build-system)
3800 `(#:python ,python-2
3802 (modify-phases %standard-phases
3803 (add-after 'unpack 'enter-scripts-dir
3804 (lambda _ (chdir "scripts")))
3807 (zero? (system* "python" "-m" "unittest" "discover" "-v"))))
3808 (add-after 'install 'wrap-executables
3809 (lambda* (#:key inputs outputs #:allow-other-keys)
3810 (let* ((out (assoc-ref outputs "out"))
3811 (bin (string-append out "/bin")))
3812 (let ((path (string-append
3813 (assoc-ref inputs "hmmer") "/bin:"
3814 (assoc-ref inputs "infernal") "/bin")))
3816 (wrap-program (string-append bin "/refpkg_align.py")
3817 `("PATH" ":" prefix (,path))))
3818 (let ((path (string-append
3819 (assoc-ref inputs "hmmer") "/bin")))
3820 (wrap-program (string-append bin "/hrefpkg_query.py")
3821 `("PATH" ":" prefix (,path)))))
3824 `(("infernal" ,infernal)
3827 `(("python-biopython" ,python2-biopython)
3828 ("taxtastic" ,taxtastic)))
3829 (synopsis "Pplacer Python scripts")))
3831 (define-public python2-pbcore
3833 (name "python2-pbcore")
3837 (uri (pypi-uri "pbcore" version))
3840 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
3841 (build-system python-build-system)
3842 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
3844 `(("python-cython" ,python2-cython)
3845 ("python-numpy" ,python2-numpy)
3846 ("python-pysam" ,python2-pysam)
3847 ("python-h5py" ,python2-h5py)))
3849 `(("python-nose" ,python2-nose)
3850 ("python-sphinx" ,python2-sphinx)
3851 ("python-pyxb" ,python2-pyxb)))
3852 (home-page "http://pacificbiosciences.github.io/pbcore/")
3853 (synopsis "Library for reading and writing PacBio data files")
3855 "The pbcore package provides Python APIs for interacting with PacBio data
3856 files and writing bioinformatics applications.")
3857 (license license:bsd-3)))
3859 (define-public python2-warpedlmm
3861 (name "python2-warpedlmm")
3867 "https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
3871 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
3872 (build-system python-build-system)
3874 `(#:python ,python-2)) ; requires Python 2.7
3876 `(("python-scipy" ,python2-scipy)
3877 ("python-numpy" ,python2-numpy)
3878 ("python-matplotlib" ,python2-matplotlib)
3879 ("python-fastlmm" ,python2-fastlmm)
3880 ("python-pandas" ,python2-pandas)
3881 ("python-pysnptools" ,python2-pysnptools)))
3883 `(("python-mock" ,python2-mock)
3884 ("python-nose" ,python2-nose)
3886 (home-page "https://github.com/PMBio/warpedLMM")
3887 (synopsis "Implementation of warped linear mixed models")
3889 "WarpedLMM is a Python implementation of the warped linear mixed model,
3890 which automatically learns an optimal warping function (or transformation) for
3891 the phenotype as it models the data.")
3892 (license license:asl2.0)))
3894 (define-public pbtranscript-tofu
3895 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
3897 (name "pbtranscript-tofu")
3898 (version (string-append "2.2.3." (string-take commit 7)))
3902 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
3904 (file-name (string-append name "-" version "-checkout"))
3907 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
3908 (modules '((guix build utils)))
3911 ;; remove bundled Cython sources
3912 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
3914 (build-system python-build-system)
3916 `(#:python ,python-2
3917 ;; FIXME: Tests fail with "No such file or directory:
3918 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
3921 (modify-phases %standard-phases
3922 (add-after 'unpack 'enter-directory
3924 (chdir "pbtranscript-tofu/pbtranscript/")
3926 ;; With setuptools version 18.0 and later this setup.py hack causes
3927 ;; a build error, so we disable it.
3928 (add-after 'enter-directory 'patch-setuppy
3930 (substitute* "setup.py"
3931 (("if 'setuptools.extension' in sys.modules:")
3935 `(("python-numpy" ,python2-numpy)
3936 ("python-bx-python" ,python2-bx-python)
3937 ("python-networkx" ,python2-networkx)
3938 ("python-scipy" ,python2-scipy)
3939 ("python-pbcore" ,python2-pbcore)
3940 ("python-h5py" ,python2-h5py)))
3942 `(("python-cython" ,python2-cython)
3943 ("python-nose" ,python2-nose)))
3944 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
3945 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
3947 "pbtranscript-tofu contains scripts to analyze transcriptome data
3948 generated using the PacBio Iso-Seq protocol.")
3949 (license license:bsd-3))))
3951 (define-public prank
3958 "http://wasabiapp.org/download/prank/prank.source."
3962 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
3963 (build-system gnu-build-system)
3966 (modify-phases %standard-phases
3967 (add-after 'unpack 'enter-src-dir
3971 (add-after 'unpack 'remove-m64-flag
3972 ;; Prank will build with the correct 'bit-ness' without this flag
3973 ;; and this allows building on 32-bit machines.
3974 (lambda _ (substitute* "src/Makefile"
3979 (lambda* (#:key outputs #:allow-other-keys)
3980 (let* ((out (assoc-ref outputs "out"))
3981 (bin (string-append out "/bin"))
3982 (man (string-append out "/share/man/man1"))
3983 (path (string-append
3984 (assoc-ref %build-inputs "mafft") "/bin:"
3985 (assoc-ref %build-inputs "exonerate") "/bin:"
3986 (assoc-ref %build-inputs "bppsuite") "/bin")))
3987 (install-file "prank" bin)
3988 (wrap-program (string-append bin "/prank")
3989 `("PATH" ":" prefix (,path)))
3990 (install-file "prank.1" man))
3994 ("exonerate" ,exonerate)
3995 ("bppsuite" ,bppsuite)))
3996 (home-page "http://wasabiapp.org/software/prank/")
3997 (synopsis "Probabilistic multiple sequence alignment program")
3999 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4000 codon and amino-acid sequences. It is based on a novel algorithm that treats
4001 insertions correctly and avoids over-estimation of the number of deletion
4002 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4003 in phylogenetics and correctly takes into account the evolutionary distances
4004 between sequences. Lastly, PRANK allows for defining a potential structure
4005 for sequences to be aligned and then, simultaneously with the alignment,
4006 predicts the locations of structural units in the sequences.")
4007 (license license:gpl2+)))
4009 (define-public proteinortho
4011 (name "proteinortho")
4018 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4019 version "_src.tar.gz"))
4022 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4023 (build-system gnu-build-system)
4025 `(#:test-target "test"
4027 (modify-phases %standard-phases
4029 ;; There is no configure script, so we modify the Makefile directly.
4030 (lambda* (#:key outputs #:allow-other-keys)
4031 (substitute* "Makefile"
4034 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4036 (add-before 'install 'make-install-directory
4037 ;; The install directory is not created during 'make install'.
4038 (lambda* (#:key outputs #:allow-other-keys)
4039 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4041 (add-after 'install 'wrap-programs
4042 (lambda* (#:key inputs outputs #:allow-other-keys)
4043 (let* ((path (getenv "PATH"))
4044 (out (assoc-ref outputs "out"))
4045 (binary (string-append out "/bin/proteinortho5.pl")))
4046 (wrap-program binary `("PATH" ":" prefix (,path))))
4050 ("python" ,python-2)
4051 ("blast+" ,blast+)))
4052 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4053 (synopsis "Detect orthologous genes across species")
4055 "Proteinortho is a tool to detect orthologous genes across different
4056 species. For doing so, it compares similarities of given gene sequences and
4057 clusters them to find significant groups. The algorithm was designed to handle
4058 large-scale data and can be applied to hundreds of species at once.")
4059 (license license:gpl2+)))
4061 (define-public pyicoteo
4068 (uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
4069 "pyicoteo/get/v" version ".tar.bz2"))
4070 (file-name (string-append name "-" version ".tar.bz2"))
4073 "0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
4074 (build-system python-build-system)
4076 `(#:python ,python-2 ; does not work with Python 3
4077 #:tests? #f)) ; there are no tests
4079 `(("python2-matplotlib" ,python2-matplotlib)))
4080 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4081 (synopsis "Analyze high-throughput genetic sequencing data")
4083 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4084 sequencing data. It works with genomic coordinates. There are currently six
4085 different command-line tools:
4088 @item pyicoregion: for generating exploratory regions automatically;
4089 @item pyicoenrich: for differential enrichment between two conditions;
4090 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4091 @item pyicos: for genomic coordinates manipulation;
4092 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4093 @item pyicount: to count how many reads from N experiment files overlap in a
4095 @item pyicotrocol: to combine operations from pyicoteo.
4097 (license license:gpl3+)))
4099 (define-public prodigal
4106 "https://github.com/hyattpd/Prodigal/archive/v"
4108 (file-name (string-append name "-" version ".tar.gz"))
4111 "17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
4112 (build-system gnu-build-system)
4114 `(#:tests? #f ;no check target
4115 #:make-flags (list (string-append "INSTALLDIR="
4116 (assoc-ref %outputs "out")
4119 (modify-phases %standard-phases
4120 (delete 'configure))))
4121 (home-page "http://prodigal.ornl.gov")
4122 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4124 "Prodigal runs smoothly on finished genomes, draft genomes, and
4125 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4126 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4127 partial genes, and identifies translation initiation sites.")
4128 (license license:gpl3+)))
4130 (define-public roary
4138 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4142 "10lw78x1xzvn7xzvnmh4bm3cak3ah5cssapl0yidvhaj1f44h29i"))))
4143 (build-system perl-build-system)
4146 (modify-phases %standard-phases
4151 ;; The tests are not run by default, so we run each test file
4153 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4155 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4156 (getenv "PERL5LIB")))
4157 (zero? (length (filter (lambda (file)
4158 (display file)(display "\n")
4159 (not (zero? (system* "perl" file))))
4160 (find-files "t" ".*\\.t$"))))))
4162 ;; There is no 'install' target in the Makefile.
4163 (lambda* (#:key outputs #:allow-other-keys)
4164 (let* ((out (assoc-ref outputs "out"))
4165 (bin (string-append out "/bin"))
4166 (perl (string-append out "/lib/perl5/site_perl"))
4167 (roary-plots "contrib/roary_plots"))
4170 (copy-recursively "bin" bin)
4171 (copy-recursively "lib" perl)
4173 (add-after 'install 'wrap-programs
4174 (lambda* (#:key inputs outputs #:allow-other-keys)
4175 (let* ((out (assoc-ref outputs "out"))
4176 (perl5lib (getenv "PERL5LIB"))
4177 (path (getenv "PATH")))
4178 (for-each (lambda (prog)
4179 (let ((binary (string-append out "/" prog)))
4180 (wrap-program binary
4181 `("PERL5LIB" ":" prefix
4182 (,(string-append perl5lib ":" out
4183 "/lib/perl5/site_perl"))))
4184 (wrap-program binary
4186 (,(string-append path ":" out "/bin"))))))
4187 (find-files "bin" ".*[^R]$"))
4189 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4190 (r-site-lib (getenv "R_LIBS_SITE"))
4192 (string-append (assoc-ref inputs "coreutils") "/bin")))
4194 `("R_LIBS_SITE" ":" prefix
4195 (,(string-append r-site-lib ":" out "/site-library/"))))
4198 (,(string-append coreutils-path ":" out "/bin"))))))
4201 `(("perl-env-path" ,perl-env-path)
4202 ("perl-test-files" ,perl-test-files)
4203 ("perl-test-most" ,perl-test-most)
4204 ("perl-test-output" ,perl-test-output)))
4206 `(("perl-array-utils" ,perl-array-utils)
4207 ("bioperl" ,bioperl-minimal)
4208 ("perl-digest-md5-file" ,perl-digest-md5-file)
4209 ("perl-exception-class" ,perl-exception-class)
4210 ("perl-file-find-rule" ,perl-file-find-rule)
4211 ("perl-file-grep" ,perl-file-grep)
4212 ("perl-file-slurper" ,perl-file-slurper)
4213 ("perl-file-which" ,perl-file-which)
4214 ("perl-graph" ,perl-graph)
4215 ("perl-graph-readwrite" ,perl-graph-readwrite)
4216 ("perl-log-log4perl" ,perl-log-log4perl)
4217 ("perl-moose" ,perl-moose)
4218 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4219 ("perl-text-csv" ,perl-text-csv)
4220 ("bedtools" ,bedtools)
4224 ("parallel" ,parallel)
4227 ("fasttree" ,fasttree)
4231 ("r-minimal" ,r-minimal)
4232 ("r-ggplot2" ,r-ggplot2)
4233 ("coreutils" ,coreutils)))
4234 (home-page "http://sanger-pathogens.github.io/Roary")
4235 (synopsis "High speed stand-alone pan genome pipeline")
4237 "Roary is a high speed stand alone pan genome pipeline, which takes
4238 annotated assemblies in GFF3 format (produced by the Prokka program) and
4239 calculates the pan genome. Using a standard desktop PC, it can analyse
4240 datasets with thousands of samples, without compromising the quality of the
4241 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4242 single processor. Roary is not intended for metagenomics or for comparing
4243 extremely diverse sets of genomes.")
4244 (license license:gpl3)))
4246 (define-public raxml
4255 "https://github.com/stamatak/standard-RAxML/archive/v"
4257 (file-name (string-append name "-" version ".tar.gz"))
4260 "13s7aspfdcfr6asynwdg1x6vznys6pzap5f8wsffbnnwpkkg9ya8"))))
4261 (build-system gnu-build-system)
4263 `(#:tests? #f ; There are no tests.
4264 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4265 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4267 (modify-phases %standard-phases
4270 (lambda* (#:key outputs #:allow-other-keys)
4271 (let* ((out (assoc-ref outputs "out"))
4272 (bin (string-append out "/bin"))
4273 (executable "raxmlHPC-HYBRID"))
4274 (install-file executable bin)
4275 (symlink (string-append bin "/" executable) "raxml"))
4278 `(("openmpi" ,openmpi)))
4279 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4280 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4282 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4284 ;; The source includes x86 specific code
4285 (supported-systems '("x86_64-linux" "i686-linux"))
4286 (license license:gpl2+)))
4296 (string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
4299 (base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
4300 (patches (search-patches "rsem-makefile.patch"))
4301 (modules '((guix build utils)))
4304 ;; remove bundled copy of boost
4305 (delete-file-recursively "boost")
4307 (build-system gnu-build-system)
4309 `(#:tests? #f ;no "check" target
4311 (modify-phases %standard-phases
4312 ;; No "configure" script.
4313 ;; Do not build bundled samtools library.
4316 (substitute* "Makefile"
4317 (("^all : sam/libbam.a") "all : "))
4320 (lambda* (#:key outputs #:allow-other-keys)
4321 (let* ((out (string-append (assoc-ref outputs "out")))
4322 (bin (string-append out "/bin/"))
4323 (perl (string-append out "/lib/perl5/site_perl")))
4326 (for-each (lambda (file)
4327 (install-file file bin))
4328 (find-files "." "rsem-.*"))
4329 (install-file "rsem_perl_utils.pm" perl))
4332 'install 'wrap-program
4333 (lambda* (#:key outputs #:allow-other-keys)
4334 (let ((out (assoc-ref outputs "out")))
4335 (for-each (lambda (prog)
4336 (wrap-program (string-append out "/bin/" prog)
4337 `("PERL5LIB" ":" prefix
4338 (,(string-append out "/lib/perl5/site_perl")))))
4339 '("rsem-plot-transcript-wiggles"
4340 "rsem-calculate-expression"
4341 "rsem-generate-ngvector"
4343 "rsem-prepare-reference")))
4347 ("ncurses" ,ncurses)
4348 ("r-minimal" ,r-minimal)
4350 ("samtools" ,samtools-0.1)
4352 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4353 (synopsis "Estimate gene expression levels from RNA-Seq data")
4355 "RSEM is a software package for estimating gene and isoform expression
4356 levels from RNA-Seq data. The RSEM package provides a user-friendly
4357 interface, supports threads for parallel computation of the EM algorithm,
4358 single-end and paired-end read data, quality scores, variable-length reads and
4359 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4360 interval estimates for expression levels. For visualization, it can generate
4361 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4362 (license license:gpl3+)))
4364 (define-public rseqc
4372 (string-append "mirror://sourceforge/rseqc/"
4373 "RSeQC-" version ".tar.gz"))
4375 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4376 (modules '((guix build utils)))
4379 ;; remove bundled copy of pysam
4380 (delete-file-recursively "lib/pysam")
4381 (substitute* "setup.py"
4382 ;; remove dependency on outdated "distribute" module
4383 (("^from distribute_setup import use_setuptools") "")
4384 (("^use_setuptools\\(\\)") "")
4385 ;; do not use bundled copy of pysam
4386 (("^have_pysam = False") "have_pysam = True"))))))
4387 (build-system python-build-system)
4388 (arguments `(#:python ,python-2))
4390 `(("python-cython" ,python2-cython)
4391 ("python-pysam" ,python2-pysam)
4392 ("python-numpy" ,python2-numpy)
4395 `(("python-nose" ,python2-nose)))
4396 (home-page "http://rseqc.sourceforge.net/")
4397 (synopsis "RNA-seq quality control package")
4399 "RSeQC provides a number of modules that can comprehensively evaluate
4400 high throughput sequence data, especially RNA-seq data. Some basic modules
4401 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
4402 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
4403 distribution, coverage uniformity, strand specificity, etc.")
4404 (license license:gpl3+)))
4407 ;; There are no release tarballs. According to the installation
4408 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
4409 ;; stable release is identified by this changeset ID.
4410 (let ((changeset "2329130")
4414 (version (string-append "0-" revision "." changeset))
4418 (url "https://bitbucket.org/libsleipnir/sleipnir")
4419 (changeset changeset)))
4422 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
4423 (build-system gnu-build-system)
4425 `(#:modules ((srfi srfi-1)
4426 (guix build gnu-build-system)
4429 (let ((dirs '("SeekMiner"
4435 (modify-phases %standard-phases
4436 (add-before 'configure 'bootstrap
4438 (zero? (system* "bash" "gen_auto"))))
4439 (add-after 'build 'build-additional-tools
4440 (lambda* (#:key make-flags #:allow-other-keys)
4441 (every (lambda (dir)
4442 (with-directory-excursion (string-append "tools/" dir)
4443 (zero? (apply system* "make" make-flags))))
4445 (add-after 'install 'install-additional-tools
4446 (lambda* (#:key make-flags #:allow-other-keys)
4447 (fold (lambda (dir result)
4448 (with-directory-excursion (string-append "tools/" dir)
4450 (zero? (apply system*
4451 `("make" ,@make-flags "install"))))))
4457 ("readline" ,readline)
4458 ("gengetopt" ,gengetopt)
4459 ("log4cpp" ,log4cpp)))
4461 `(("autoconf" ,autoconf)
4462 ("automake" ,automake)
4464 (home-page "http://seek.princeton.edu")
4465 (synopsis "Gene co-expression search engine")
4467 "SEEK is a computational gene co-expression search engine. SEEK provides
4468 biologists with a way to navigate the massive human expression compendium that
4469 now contains thousands of expression datasets. SEEK returns a robust ranking
4470 of co-expressed genes in the biological area of interest defined by the user's
4471 query genes. It also prioritizes thousands of expression datasets according
4472 to the user's query of interest.")
4473 (license license:cc-by3.0))))
4475 (define-public samtools
4483 (string-append "mirror://sourceforge/samtools/samtools/"
4484 version "/samtools-" version ".tar.bz2"))
4487 "1xidmv0jmfy7l0kb32hdnlshcxgzi1hmygvig0cqrq1fhckdlhl5"))))
4488 (build-system gnu-build-system)
4490 `(#:modules ((ice-9 ftw)
4492 (guix build gnu-build-system)
4494 #:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
4495 #:configure-flags (list "--with-ncurses" "--with-htslib=system")
4497 (modify-phases %standard-phases
4498 (add-after 'unpack 'patch-tests
4500 (substitute* "test/test.pl"
4501 ;; The test script calls out to /bin/bash
4502 (("/bin/bash") (which "bash")))
4504 (add-after 'install 'install-library
4505 (lambda* (#:key outputs #:allow-other-keys)
4506 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
4507 (install-file "libbam.a" lib)
4509 (add-after 'install 'install-headers
4510 (lambda* (#:key outputs #:allow-other-keys)
4511 (let ((include (string-append (assoc-ref outputs "out")
4512 "/include/samtools/")))
4513 (for-each (lambda (file)
4514 (install-file file include))
4515 (scandir "." (lambda (name) (string-match "\\.h$" name))))
4517 (native-inputs `(("pkg-config" ,pkg-config)))
4519 `(("htslib" ,htslib)
4520 ("ncurses" ,ncurses)
4524 (home-page "http://samtools.sourceforge.net")
4525 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
4527 "Samtools implements various utilities for post-processing nucleotide
4528 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
4529 variant calling (in conjunction with bcftools), and a simple alignment
4531 (license license:expat)))
4533 (define-public samtools-0.1
4534 ;; This is the most recent version of the 0.1 line of samtools. The input
4535 ;; and output formats differ greatly from that used and produced by samtools
4536 ;; 1.x and is still used in many bioinformatics pipelines.
4537 (package (inherit samtools)
4543 (string-append "mirror://sourceforge/samtools/samtools/"
4544 version "/samtools-" version ".tar.bz2"))
4546 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
4548 `(#:tests? #f ;no "check" target
4549 ,@(substitute-keyword-arguments (package-arguments samtools)
4550 ((#:make-flags flags)
4551 `(cons "LIBCURSES=-lncurses" ,flags))
4553 `(modify-phases ,phases
4555 (lambda* (#:key outputs #:allow-other-keys)
4556 (let ((bin (string-append
4557 (assoc-ref outputs "out") "/bin")))
4559 (install-file "samtools" bin)
4561 (delete 'patch-tests)
4562 (delete 'configure))))))))
4564 (define-public mosaik
4565 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
4570 ;; There are no release tarballs nor tags.
4573 (url "https://github.com/wanpinglee/MOSAIK.git")
4575 (file-name (string-append name "-" version))
4578 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
4579 (build-system gnu-build-system)
4581 `(#:tests? #f ; no tests
4582 #:make-flags (list "CC=gcc")
4584 (modify-phases %standard-phases
4586 (lambda _ (chdir "src") #t))
4588 (lambda* (#:key outputs #:allow-other-keys)
4589 (let ((bin (string-append (assoc-ref outputs "out")
4592 (copy-recursively "../bin" bin)
4597 (supported-systems '("x86_64-linux"))
4598 (home-page "https://github.com/wanpinglee/MOSAIK")
4599 (synopsis "Map nucleotide sequence reads to reference genomes")
4601 "MOSAIK is a program for mapping second and third-generation sequencing
4602 reads to a reference genome. MOSAIK can align reads generated by all the
4603 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
4604 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
4605 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
4606 ;; code released into the public domain:
4607 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
4608 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
4609 (license (list license:gpl2+ license:public-domain)))))
4611 (define-public ngs-sdk
4619 (string-append "https://github.com/ncbi/ngs/archive/"
4621 (file-name (string-append name "-" version ".tar.gz"))
4624 "1wiyf4c6nm2j87pv015cbi0qny5byf3pbvcw3likifz5dl56ag40"))))
4625 (build-system gnu-build-system)
4627 `(#:parallel-build? #f ; not supported
4628 #:tests? #f ; no "check" target
4630 (modify-phases %standard-phases
4632 (lambda* (#:key outputs #:allow-other-keys)
4633 (let ((out (assoc-ref outputs "out")))
4634 ;; Allow 'konfigure.perl' to find 'package.prl'.
4636 (string-append ".:" (getenv "PERL5LIB")))
4638 ;; The 'configure' script doesn't recognize things like
4639 ;; '--enable-fast-install'.
4640 (zero? (system* "./configure"
4641 (string-append "--build-prefix=" (getcwd) "/build")
4642 (string-append "--prefix=" out))))))
4643 (add-after 'unpack 'enter-dir
4644 (lambda _ (chdir "ngs-sdk") #t)))))
4645 (native-inputs `(("perl" ,perl)))
4646 ;; According to the test
4647 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
4648 ;; in ngs-sdk/setup/konfigure.perl
4649 (supported-systems '("i686-linux" "x86_64-linux"))
4650 (home-page "https://github.com/ncbi/ngs")
4651 (synopsis "API for accessing Next Generation Sequencing data")
4653 "NGS is a domain-specific API for accessing reads, alignments and pileups
4654 produced from Next Generation Sequencing. The API itself is independent from
4655 any particular back-end implementation, and supports use of multiple back-ends
4657 (license license:public-domain)))
4659 (define-public java-ngs
4660 (package (inherit ngs-sdk)
4663 `(,@(substitute-keyword-arguments
4664 `(#:modules ((guix build gnu-build-system)
4668 ,@(package-arguments ngs-sdk))
4670 `(modify-phases ,phases
4671 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
4673 `(("jdk" ,icedtea "jdk")
4674 ("ngs-sdk" ,ngs-sdk)))
4675 (synopsis "Java bindings for NGS SDK")))
4677 (define-public ncbi-vdb
4685 (string-append "https://github.com/ncbi/ncbi-vdb/archive/"
4687 (file-name (string-append name "-" version ".tar.gz"))
4690 "1acn4bv81mfl137qnbn9995mjjhwd36pm0b7qli1iw5skrxa9j8m"))))
4691 (build-system gnu-build-system)
4693 `(#:parallel-build? #f ; not supported
4694 #:tests? #f ; no "check" target
4696 (modify-phases %standard-phases
4697 (add-before 'configure 'set-perl-search-path
4699 ;; Work around "dotless @INC" build failure.
4701 (string-append (getcwd) "/setup:"
4702 (getenv "PERL5LIB")))
4705 (lambda* (#:key inputs outputs #:allow-other-keys)
4706 (let ((out (assoc-ref outputs "out")))
4707 ;; Override include path for libmagic
4708 (substitute* "setup/package.prl"
4709 (("name => 'magic', Include => '/usr/include'")
4710 (string-append "name=> 'magic', Include => '"
4711 (assoc-ref inputs "libmagic")
4714 ;; Install kdf5 library (needed by sra-tools)
4715 (substitute* "build/Makefile.install"
4716 (("LIBRARIES_TO_INSTALL =")
4717 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
4719 (substitute* "build/Makefile.env"
4720 (("CFLAGS =" prefix)
4721 (string-append prefix "-msse2 ")))
4723 ;; Override search path for ngs-java
4724 (substitute* "setup/package.prl"
4725 (("/usr/local/ngs/ngs-java")
4726 (assoc-ref inputs "java-ngs")))
4728 ;; The 'configure' script doesn't recognize things like
4729 ;; '--enable-fast-install'.
4732 (string-append "--build-prefix=" (getcwd) "/build")
4733 (string-append "--prefix=" (assoc-ref outputs "out"))
4734 (string-append "--debug")
4735 (string-append "--with-xml2-prefix="
4736 (assoc-ref inputs "libxml2"))
4737 (string-append "--with-ngs-sdk-prefix="
4738 (assoc-ref inputs "ngs-sdk"))
4739 (string-append "--with-hdf5-prefix="
4740 (assoc-ref inputs "hdf5")))))))
4741 (add-after 'install 'install-interfaces
4742 (lambda* (#:key outputs #:allow-other-keys)
4743 ;; Install interface libraries. On i686 the interface libraries
4744 ;; are installed to "linux/gcc/i386", so we need to use the Linux
4745 ;; architecture name ("i386") instead of the target system prefix
4747 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
4748 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
4749 ,(system->linux-architecture
4750 (or (%current-target-system)
4753 (string-append (assoc-ref outputs "out")
4755 ;; Install interface headers
4756 (copy-recursively "interfaces"
4757 (string-append (assoc-ref outputs "out")
4760 ;; These files are needed by sra-tools.
4761 (add-after 'install 'install-configuration-files
4762 (lambda* (#:key outputs #:allow-other-keys)
4763 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
4765 (install-file "libs/kfg/default.kfg" target)
4766 (install-file "libs/kfg/certs.kfg" target))
4769 `(("libxml2" ,libxml2)
4770 ("ngs-sdk" ,ngs-sdk)
4771 ("java-ngs" ,java-ngs)
4774 (native-inputs `(("perl" ,perl)))
4775 ;; NCBI-VDB requires SSE capability.
4776 (supported-systems '("i686-linux" "x86_64-linux"))
4777 (home-page "https://github.com/ncbi/ncbi-vdb")
4778 (synopsis "Database engine for genetic information")
4780 "The NCBI-VDB library implements a highly compressed columnar data
4781 warehousing engine that is most often used to store genetic information.
4782 Databases are stored in a portable image within the file system, and can be
4783 accessed/downloaded on demand across HTTP.")
4784 (license license:public-domain)))
4786 (define-public plink
4794 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
4795 version "-src.zip"))
4797 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
4798 (patches (search-patches "plink-1.07-unclobber-i.patch"
4799 "plink-endian-detection.patch"))))
4800 (build-system gnu-build-system)
4802 '(#:tests? #f ;no "check" target
4803 #:make-flags (list (string-append "LIB_LAPACK="
4804 (assoc-ref %build-inputs "lapack")
4805 "/lib/liblapack.so")
4808 ;; disable phoning home
4811 (modify-phases %standard-phases
4812 ;; no "configure" script
4815 (lambda* (#:key outputs #:allow-other-keys)
4816 (let ((bin (string-append (assoc-ref outputs "out")
4818 (install-file "plink" bin)
4822 ("lapack" ,lapack)))
4824 `(("unzip" ,unzip)))
4825 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
4826 (synopsis "Whole genome association analysis toolset")
4828 "PLINK is a whole genome association analysis toolset, designed to
4829 perform a range of basic, large-scale analyses in a computationally efficient
4830 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
4831 so there is no support for steps prior to this (e.g. study design and
4832 planning, generating genotype or CNV calls from raw data). Through
4833 integration with gPLINK and Haploview, there is some support for the
4834 subsequent visualization, annotation and storage of results.")
4835 ;; Code is released under GPLv2, except for fisher.h, which is under
4837 (license (list license:gpl2 license:lgpl2.1+))))
4839 (define-public plink-ng
4840 (package (inherit plink)
4846 (uri (string-append "https://github.com/chrchang/plink-ng/archive/v"
4848 (file-name (string-append name "-" version ".tar.gz"))
4850 (base32 "09ixrds009aczjswxr2alcb774mksq5g0v78dgjjn1h4dky0kf9a"))))
4851 (build-system gnu-build-system)
4853 '(#:tests? #f ;no "check" target
4854 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
4855 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
4857 "-f" "Makefile.std")
4859 (modify-phases %standard-phases
4860 (add-after 'unpack 'chdir
4861 (lambda _ (chdir "1.9") #t))
4862 (delete 'configure) ; no "configure" script
4864 (lambda* (#:key outputs #:allow-other-keys)
4865 (let ((bin (string-append (assoc-ref outputs "out")
4867 (install-file "plink" bin)
4872 ("openblas" ,openblas)))
4873 (home-page "https://www.cog-genomics.org/plink/")
4874 (license license:gpl3+)))
4876 (define-public smithlab-cpp
4877 (let ((revision "1")
4878 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
4880 (name "smithlab-cpp")
4881 (version (string-append "0." revision "." (string-take commit 7)))
4885 (url "https://github.com/smithlabcode/smithlab_cpp.git")
4887 (file-name (string-append name "-" version "-checkout"))
4890 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
4891 (build-system gnu-build-system)
4893 `(#:modules ((guix build gnu-build-system)
4896 #:tests? #f ;no "check" target
4898 (modify-phases %standard-phases
4899 (add-after 'unpack 'use-samtools-headers
4901 (substitute* '("SAM.cpp"
4903 (("sam.h") "samtools/sam.h"))
4906 (lambda* (#:key outputs #:allow-other-keys)
4907 (let* ((out (assoc-ref outputs "out"))
4908 (lib (string-append out "/lib"))
4909 (include (string-append out "/include/smithlab-cpp")))
4912 (for-each (cut install-file <> lib)
4913 (find-files "." "\\.o$"))
4914 (for-each (cut install-file <> include)
4915 (find-files "." "\\.hpp$")))
4917 (delete 'configure))))
4919 `(("samtools" ,samtools-0.1)
4921 (home-page "https://github.com/smithlabcode/smithlab_cpp")
4922 (synopsis "C++ helper library for functions used in Smith lab projects")
4924 "Smithlab CPP is a C++ library that includes functions used in many of
4925 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
4926 structures, classes for genomic regions, mapped sequencing reads, etc.")
4927 (license license:gpl3+))))
4929 (define-public preseq
4935 (uri (string-append "https://github.com/smithlabcode/"
4936 "preseq/archive/v" version ".tar.gz"))
4937 (file-name (string-append name "-" version ".tar.gz"))
4939 (base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
4940 (modules '((guix build utils)))
4942 ;; Remove bundled samtools.
4943 '(delete-file-recursively "samtools"))))
4944 (build-system gnu-build-system)
4946 `(#:tests? #f ;no "check" target
4948 (modify-phases %standard-phases
4949 (delete 'configure))
4951 (list (string-append "PREFIX="
4952 (assoc-ref %outputs "out"))
4953 (string-append "LIBBAM="
4954 (assoc-ref %build-inputs "samtools")
4956 (string-append "SMITHLAB_CPP="
4957 (assoc-ref %build-inputs "smithlab-cpp")
4960 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
4963 ("samtools" ,samtools-0.1)
4964 ("smithlab-cpp" ,smithlab-cpp)
4966 (home-page "http://smithlabresearch.org/software/preseq/")
4967 (synopsis "Program for analyzing library complexity")
4969 "The preseq package is aimed at predicting and estimating the complexity
4970 of a genomic sequencing library, equivalent to predicting and estimating the
4971 number of redundant reads from a given sequencing depth and how many will be
4972 expected from additional sequencing using an initial sequencing experiment.
4973 The estimates can then be used to examine the utility of further sequencing,
4974 optimize the sequencing depth, or to screen multiple libraries to avoid low
4975 complexity samples.")
4976 (license license:gpl3+)))
4978 (define-public python-screed
4980 (name "python-screed")
4985 (uri (pypi-uri "screed" version))
4988 "18czszp9fkx3j6jr7y5kp6dfialscgddk05mw1zkhh2zhn0jd8i0"))))
4989 (build-system python-build-system)
4992 (modify-phases %standard-phases
4995 (setenv "PYTHONPATH"
4996 (string-append (getenv "PYTHONPATH") ":."))
4997 (zero? (system* "nosetests" "--attr" "!known_failing")))))))
4999 `(("python-nose" ,python-nose)))
5001 `(("python-bz2file" ,python-bz2file)))
5002 (home-page "https://github.com/dib-lab/screed/")
5003 (synopsis "Short read sequence database utilities")
5004 (description "Screed parses FASTA and FASTQ files and generates databases.
5005 Values such as sequence name, sequence description, sequence quality and the
5006 sequence itself can be retrieved from these databases.")
5007 (license license:bsd-3)))
5009 (define-public python2-screed
5010 (package-with-python2 python-screed))
5012 (define-public sra-tools
5020 (string-append "https://github.com/ncbi/sra-tools/archive/"
5022 (file-name (string-append name "-" version ".tar.gz"))
5025 "1camsijmvv2s45mb4iyf44ghl4gkd4rl0viphpcgl3ccchy32a0g"))))
5026 (build-system gnu-build-system)
5028 `(#:parallel-build? #f ; not supported
5029 #:tests? #f ; no "check" target
5031 (list (string-append "DEFAULT_CRT="
5032 (assoc-ref %build-inputs "ncbi-vdb")
5034 (string-append "DEFAULT_KFG="
5035 (assoc-ref %build-inputs "ncbi-vdb")
5037 (string-append "VDB_LIBDIR="
5038 (assoc-ref %build-inputs "ncbi-vdb")
5039 ,(if (string-prefix? "x86_64"
5040 (or (%current-target-system)
5045 (modify-phases %standard-phases
5046 (add-before 'configure 'set-perl-search-path
5048 ;; Work around "dotless @INC" build failure.
5050 (string-append (getcwd) "/setup:"
5051 (getenv "PERL5LIB")))
5054 (lambda* (#:key inputs outputs #:allow-other-keys)
5055 ;; The build system expects a directory containing the sources and
5056 ;; raw build output of ncbi-vdb, including files that are not
5057 ;; installed. Since we are building against an installed version of
5058 ;; ncbi-vdb, the following modifications are needed.
5059 (substitute* "setup/konfigure.perl"
5060 ;; Make the configure script look for the "ilib" directory of
5061 ;; "ncbi-vdb" without first checking for the existence of a
5062 ;; matching library in its "lib" directory.
5063 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5064 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5065 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5066 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5067 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5070 (substitute* "tools/copycat/Makefile"
5071 (("smagic-static") "lmagic"))
5073 ;; The 'configure' script doesn't recognize things like
5074 ;; '--enable-fast-install'.
5077 (string-append "--build-prefix=" (getcwd) "/build")
5078 (string-append "--prefix=" (assoc-ref outputs "out"))
5079 (string-append "--debug")
5080 (string-append "--with-fuse-prefix="
5081 (assoc-ref inputs "fuse"))
5082 (string-append "--with-magic-prefix="
5083 (assoc-ref inputs "libmagic"))
5084 ;; TODO: building with libxml2 fails with linker errors
5085 ;; (string-append "--with-xml2-prefix="
5086 ;; (assoc-ref inputs "libxml2"))
5087 (string-append "--with-ncbi-vdb-sources="
5088 (assoc-ref inputs "ncbi-vdb"))
5089 (string-append "--with-ncbi-vdb-build="
5090 (assoc-ref inputs "ncbi-vdb"))
5091 (string-append "--with-ngs-sdk-prefix="
5092 (assoc-ref inputs "ngs-sdk"))
5093 (string-append "--with-hdf5-prefix="
5094 (assoc-ref inputs "hdf5"))))))
5095 ;; This version of sra-tools fails to build with glibc because of a
5096 ;; naming conflict. glibc-2.25/include/bits/mathcalls.h already
5097 ;; contains a definition of "canonicalize", so we rename it.
5099 ;; See upstream bug report:
5100 ;; https://github.com/ncbi/sra-tools/issues/67
5101 (add-after 'unpack 'patch-away-glibc-conflict
5103 (substitute* "tools/bam-loader/bam.c"
5104 (("canonicalize\\(" line)
5105 (string-append "sra_tools_" line)))
5107 (native-inputs `(("perl" ,perl)))
5109 `(("ngs-sdk" ,ngs-sdk)
5110 ("ncbi-vdb" ,ncbi-vdb)
5115 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5116 (synopsis "Tools and libraries for reading and writing sequencing data")
5118 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5119 reading of sequencing files from the Sequence Read Archive (SRA) database and
5120 writing files into the .sra format.")
5121 (license license:public-domain)))
5123 (define-public seqan
5129 (uri (string-append "http://packages.seqan.de/seqan-library/"
5130 "seqan-library-" version ".tar.bz2"))
5133 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5134 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5135 ;; makes sense to split the outputs.
5136 (outputs '("out" "doc"))
5137 (build-system trivial-build-system)
5139 `(#:modules ((guix build utils))
5142 (use-modules (guix build utils))
5143 (let ((tar (assoc-ref %build-inputs "tar"))
5144 (bzip (assoc-ref %build-inputs "bzip2"))
5145 (out (assoc-ref %outputs "out"))
5146 (doc (assoc-ref %outputs "doc")))
5147 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5148 (system* "tar" "xvf" (assoc-ref %build-inputs "source"))
5149 (chdir (string-append "seqan-library-" ,version))
5150 (copy-recursively "include" (string-append out "/include"))
5151 (copy-recursively "share" (string-append doc "/share"))))))
5153 `(("source" ,source)
5156 (home-page "http://www.seqan.de")
5157 (synopsis "Library for nucleotide sequence analysis")
5159 "SeqAn is a C++ library of efficient algorithms and data structures for
5160 the analysis of sequences with the focus on biological data. It contains
5161 algorithms and data structures for string representation and their
5162 manipulation, online and indexed string search, efficient I/O of
5163 bioinformatics file formats, sequence alignment, and more.")
5164 (license license:bsd-3)))
5166 (define-public seqmagick
5174 "https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
5178 "0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
5179 (build-system python-build-system)
5181 ;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
5182 `(#:python ,python-2
5184 (modify-phases %standard-phases
5185 ;; Current test in setup.py does not work as of 0.6.1,
5186 ;; so use nose to run tests instead for now. See
5187 ;; https://github.com/fhcrc/seqmagick/issues/55
5188 (replace 'check (lambda _ (zero? (system* "nosetests")))))))
5190 ;; biopython-1.66 is required due to
5191 ;; https://github.com/fhcrc/seqmagick/issues/59
5192 ;; When that issue is resolved the 'python2-biopython-1.66' package
5193 ;; should be removed.
5194 `(("python-biopython" ,python2-biopython-1.66)))
5196 `(("python-nose" ,python2-nose)))
5197 (home-page "https://github.com/fhcrc/seqmagick")
5198 (synopsis "Tools for converting and modifying sequence files")
5200 "Bioinformaticians often have to convert sequence files between formats
5201 and do little manipulations on them, and it's not worth writing scripts for
5202 that. Seqmagick is a utility to expose the file format conversion in
5203 BioPython in a convenient way. Instead of having a big mess of scripts, there
5204 is one that takes arguments.")
5205 (license license:gpl3)))
5207 (define-public seqtk
5214 "https://github.com/lh3/seqtk/archive/v"
5216 (file-name (string-append name "-" version ".tar.gz"))
5219 "0ywdyzpmfiz2wp6ampbzqg4y8bj450nfgqarpamg045b8mk32lxx"))
5220 (modules '((guix build utils)))
5223 ;; Remove extraneous header files, as is done in the seqtk
5225 (for-each (lambda (file) (delete-file file))
5226 (list "ksort.h" "kstring.h" "kvec.h"))
5228 (build-system gnu-build-system)
5231 (modify-phases %standard-phases
5234 ;; There are no tests, so we just run a sanity check.
5235 (lambda _ (zero? (system* "./seqtk" "seq"))))
5237 (lambda* (#:key outputs #:allow-other-keys)
5238 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5239 (install-file "seqtk" bin)))))))
5242 (home-page "https://github.com/lh3/seqtk")
5243 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5245 "Seqtk is a fast and lightweight tool for processing sequences in the
5246 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5247 optionally compressed by gzip.")
5248 (license license:expat)))
5250 (define-public snap-aligner
5252 (name "snap-aligner")
5253 (version "1.0beta.18")
5257 "https://github.com/amplab/snap/archive/v"
5259 (file-name (string-append name "-" version ".tar.gz"))
5262 "1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
5263 (build-system gnu-build-system)
5266 (modify-phases %standard-phases
5268 (replace 'check (lambda _ (zero? (system* "./unit_tests"))))
5270 (lambda* (#:key outputs #:allow-other-keys)
5271 (let* ((out (assoc-ref outputs "out"))
5272 (bin (string-append out "/bin")))
5273 (install-file "snap-aligner" bin)
5274 (install-file "SNAPCommand" bin)
5278 (home-page "http://snap.cs.berkeley.edu/")
5279 (synopsis "Short read DNA sequence aligner")
5281 "SNAP is a fast and accurate aligner for short DNA reads. It is
5282 optimized for modern read lengths of 100 bases or higher, and takes advantage
5283 of these reads to align data quickly through a hash-based indexing scheme.")
5284 ;; 32-bit systems are not supported by the unpatched code.
5285 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5286 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5287 ;; systems without a lot of memory cannot make good use of this program.
5288 (supported-systems '("x86_64-linux"))
5289 (license license:asl2.0)))
5291 (define-public sortmerna
5299 "https://github.com/biocore/sortmerna/archive/"
5301 (file-name (string-append name "-" version ".tar.gz"))
5304 "1ghaghvd82af9j5adavxh77g7hm247d1r69m3fbi6f1jdivj5ldk"))))
5305 (build-system gnu-build-system)
5306 (outputs '("out" ;for binaries
5307 "db")) ;for sequence databases
5310 (modify-phases %standard-phases
5312 (lambda* (#:key outputs #:allow-other-keys)
5313 (let* ((out (assoc-ref outputs "out"))
5314 (bin (string-append out "/bin"))
5315 (db (assoc-ref outputs "db"))
5317 (string-append db "/share/sortmerna/rRNA_databases")))
5318 (install-file "sortmerna" bin)
5319 (install-file "indexdb_rna" bin)
5320 (for-each (lambda (file)
5321 (install-file file share))
5322 (find-files "rRNA_databases" ".*fasta"))
5326 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5327 (synopsis "Biological sequence analysis tool for NGS reads")
5329 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5330 and operational taxonomic unit (OTU) picking of next generation
5331 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5332 allows for fast and sensitive analyses of nucleotide sequences. The main
5333 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5334 ;; The source includes x86 specific code
5335 (supported-systems '("x86_64-linux" "i686-linux"))
5336 (license license:lgpl3)))
5344 (uri (string-append "https://github.com/alexdobin/STAR/archive/"
5346 (file-name (string-append name "-" version ".tar.gz"))
5349 "013wirlz8lllgjyagl48l75n1isxyabqb3sj7qlsl0x1rmvqw99a"))
5350 (modules '((guix build utils)))
5353 (substitute* "source/Makefile"
5355 ;; Remove pre-built binaries and bundled htslib sources.
5356 (delete-file-recursively "bin/MacOSX_x86_64")
5357 (delete-file-recursively "bin/Linux_x86_64")
5358 (delete-file-recursively "bin/Linux_x86_64_static")
5359 (delete-file-recursively "source/htslib")
5361 (build-system gnu-build-system)
5363 '(#:tests? #f ;no check target
5364 #:make-flags '("STAR")
5366 (modify-phases %standard-phases
5367 (add-after 'unpack 'enter-source-dir
5368 (lambda _ (chdir "source") #t))
5369 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
5371 (substitute* "Makefile"
5372 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
5374 (substitute* '("BAMfunctions.cpp"
5379 "bamRemoveDuplicates.cpp")
5380 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
5381 (string-append "#include <" header ">")))
5382 (substitute* "IncludeDefine.h"
5383 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
5384 (string-append "<" header ">")))
5387 (lambda* (#:key outputs #:allow-other-keys)
5388 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5389 (install-file "STAR" bin))
5391 (delete 'configure))))
5395 `(("htslib" ,htslib)
5397 (home-page "https://github.com/alexdobin/STAR")
5398 (synopsis "Universal RNA-seq aligner")
5400 "The Spliced Transcripts Alignment to a Reference (STAR) software is
5401 based on a previously undescribed RNA-seq alignment algorithm that uses
5402 sequential maximum mappable seed search in uncompressed suffix arrays followed
5403 by seed clustering and stitching procedure. In addition to unbiased de novo
5404 detection of canonical junctions, STAR can discover non-canonical splices and
5405 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
5407 ;; Only 64-bit systems are supported according to the README.
5408 (supported-systems '("x86_64-linux" "mips64el-linux"))
5409 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
5410 (license license:gpl3+)))
5412 (define-public subread
5418 (uri (string-append "mirror://sourceforge/subread/subread-"
5419 version "/subread-" version "-source.tar.gz"))
5422 "0gn5zhbvllks0mmdg3qlmsbg91p2mpdc2wixwfqpi85yzfrh8hcy"))))
5423 (build-system gnu-build-system)
5425 `(#:tests? #f ;no "check" target
5426 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
5427 ;; optimizations by default, so we override these flags such that x86_64
5428 ;; flags are only added when the build target is an x86_64 system.
5430 (list (let ((system ,(or (%current-target-system)
5432 (flags '("-ggdb" "-fomit-frame-pointer"
5433 "-ffast-math" "-funroll-loops"
5434 "-fmessage-length=0"
5435 "-O9" "-Wall" "-DMAKE_FOR_EXON"
5437 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
5438 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
5439 (if (string-prefix? "x86_64" system)
5440 (string-append "CCFLAGS=" (string-join (append flags flags64)))
5441 (string-append "CCFLAGS=" (string-join flags))))
5442 "-f" "Makefile.Linux"
5443 "CC=gcc ${CCFLAGS}")
5445 (modify-phases %standard-phases
5446 (add-after 'unpack 'enter-dir
5447 (lambda _ (chdir "src") #t))
5449 (lambda* (#:key outputs #:allow-other-keys)
5450 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5452 (copy-recursively "../bin" bin))))
5453 ;; no "configure" script
5454 (delete 'configure))))
5455 (inputs `(("zlib" ,zlib)))
5456 (home-page "http://bioinf.wehi.edu.au/subread-package/")
5457 (synopsis "Tool kit for processing next-gen sequencing data")
5459 "The subread package contains the following tools: subread aligner, a
5460 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
5461 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
5462 features; exactSNP: a SNP caller that discovers SNPs by testing signals
5463 against local background noises.")
5464 (license license:gpl3+)))
5466 (define-public stringtie
5472 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
5473 "stringtie-" version ".tar.gz"))
5476 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
5477 (modules '((guix build utils)))
5480 (delete-file-recursively "samtools-0.1.18")
5482 (build-system gnu-build-system)
5484 `(#:tests? #f ;no test suite
5486 (modify-phases %standard-phases
5487 ;; no configure script
5489 (add-before 'build 'use-system-samtools
5491 (substitute* "Makefile"
5492 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
5494 (substitute* '("gclib/GBam.h"
5496 (("#include \"(bam|sam|kstring).h\"" _ header)
5497 (string-append "#include <samtools/" header ".h>")))
5499 (add-after 'unpack 'remove-duplicate-typedef
5501 ;; This typedef conflicts with the typedef in
5502 ;; glibc-2.25/include/bits/types.h
5503 (substitute* "gclib/GThreads.h"
5504 (("typedef long long __intmax_t;") ""))
5507 (lambda* (#:key outputs #:allow-other-keys)
5508 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5509 (install-file "stringtie" bin)
5512 `(("samtools" ,samtools-0.1)
5514 (home-page "http://ccb.jhu.edu/software/stringtie/")
5515 (synopsis "Transcript assembly and quantification for RNA-Seq data")
5517 "StringTie is a fast and efficient assembler of RNA-Seq sequence
5518 alignments into potential transcripts. It uses a novel network flow algorithm
5519 as well as an optional de novo assembly step to assemble and quantitate
5520 full-length transcripts representing multiple splice variants for each gene
5521 locus. Its input can include not only the alignments of raw reads used by
5522 other transcript assemblers, but also alignments of longer sequences that have
5523 been assembled from those reads. To identify differentially expressed genes
5524 between experiments, StringTie's output can be processed either by the
5525 Cuffdiff or Ballgown programs.")
5526 (license license:artistic2.0)))
5528 (define-public taxtastic
5534 (uri (pypi-uri "taxtastic" version))
5537 "0s79z8kfl853x7l4h8ms05k31q87aw62nrchlk20w9n227j35929"))))
5538 (build-system python-build-system)
5540 `(#:python ,python-2
5542 (modify-phases %standard-phases
5545 (zero? (system* "python" "-m" "unittest" "discover" "-v")))))))
5547 `(("python-sqlalchemy" ,python2-sqlalchemy)
5548 ("python-decorator" ,python2-decorator)
5549 ("python-biopython" ,python2-biopython)
5550 ("python-pandas" ,python2-pandas)))
5551 (home-page "https://github.com/fhcrc/taxtastic")
5552 (synopsis "Tools for taxonomic naming and annotation")
5554 "Taxtastic is software written in python used to build and maintain
5555 reference packages i.e. collections of reference trees, reference alignments,
5556 profiles, and associated taxonomic information.")
5557 (license license:gpl3+)))
5559 (define-public vcftools
5566 "https://github.com/vcftools/vcftools/releases/download/v"
5567 version "/vcftools-" version ".tar.gz"))
5570 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
5571 (build-system gnu-build-system)
5573 `(#:tests? #f ; no "check" target
5575 "CFLAGS=-O2" ; override "-m64" flag
5576 (string-append "PREFIX=" (assoc-ref %outputs "out"))
5577 (string-append "MANDIR=" (assoc-ref %outputs "out")
5578 "/share/man/man1"))))
5580 `(("pkg-config" ,pkg-config)))
5584 (home-page "https://vcftools.github.io/")
5585 (synopsis "Tools for working with VCF files")
5587 "VCFtools is a program package designed for working with VCF files, such
5588 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
5589 provide easily accessible methods for working with complex genetic variation
5590 data in the form of VCF files.")
5591 ;; The license is declared as LGPLv3 in the README and
5592 ;; at https://vcftools.github.io/license.html
5593 (license license:lgpl3)))
5595 (define-public infernal
5601 (uri (string-append "http://eddylab.org/software/infernal/"
5602 "infernal-" version ".tar.gz"))
5605 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
5606 (build-system gnu-build-system)
5608 `(("perl" ,perl))) ; for tests
5609 (home-page "http://eddylab.org/infernal/")
5610 (synopsis "Inference of RNA alignments")
5611 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
5612 searching DNA sequence databases for RNA structure and sequence similarities.
5613 It is an implementation of a special case of profile stochastic context-free
5614 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
5615 profile, but it scores a combination of sequence consensus and RNA secondary
5616 structure consensus, so in many cases, it is more capable of identifying RNA
5617 homologs that conserve their secondary structure more than their primary
5619 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
5620 (supported-systems '("i686-linux" "x86_64-linux"))
5621 (license license:bsd-3)))
5623 (define-public r-centipede
5625 (name "r-centipede")
5629 (uri (string-append "http://download.r-forge.r-project.org/"
5630 "src/contrib/CENTIPEDE_" version ".tar.gz"))
5633 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
5634 (build-system r-build-system)
5635 (home-page "http://centipede.uchicago.edu/")
5636 (synopsis "Predict transcription factor binding sites")
5638 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
5639 of the genome that are bound by particular transcription factors. It starts
5640 by identifying a set of candidate binding sites, and then aims to classify the
5641 sites according to whether each site is bound or not bound by a transcription
5642 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
5643 between two different types of motif instances using as much relevant
5644 information as possible.")
5645 (license (list license:gpl2+ license:gpl3+))))
5647 (define-public r-vegan
5654 (uri (cran-uri "vegan" version))
5657 "1n57dzv2aid6iqd9fkqik401sidqanhzsawyak94qbiyh6dbd1x9"))))
5658 (build-system r-build-system)
5660 `(("gfortran" ,gfortran)))
5662 `(("r-cluster" ,r-cluster)
5663 ("r-lattice" ,r-lattice)
5666 ("r-permute" ,r-permute)))
5667 (home-page "https://cran.r-project.org/web/packages/vegan")
5668 (synopsis "Functions for community ecology")
5670 "The vegan package provides tools for descriptive community ecology. It
5671 has most basic functions of diversity analysis, community ordination and
5672 dissimilarity analysis. Most of its multivariate tools can be used for other
5673 data types as well.")
5674 (license license:gpl2+)))
5676 (define-public r-annotate
5683 (uri (bioconductor-uri "annotate" version))
5686 "0wlrp3v2jxw9is98ap39dfi7z97kmw1wv1xi4h7yfh12zpj2r8l0"))))
5687 (build-system r-build-system)
5689 `(("r-annotationdbi" ,r-annotationdbi)
5690 ("r-biobase" ,r-biobase)
5691 ("r-biocgenerics" ,r-biocgenerics)
5693 ("r-rcurl" ,r-rcurl)
5695 ("r-xtable" ,r-xtable)))
5697 "https://bioconductor.org/packages/annotate")
5698 (synopsis "Annotation for microarrays")
5699 (description "This package provides R environments for the annotation of
5701 (license license:artistic2.0)))
5703 (define-public r-geneplotter
5705 (name "r-geneplotter")
5710 (uri (bioconductor-uri "geneplotter" version))
5713 "1z3g7frc1iviwrsv2dlm4nqvkc0685h4va0388yfxn102ln8wwma"))))
5714 (build-system r-build-system)
5716 `(("r-annotate" ,r-annotate)
5717 ("r-annotationdbi" ,r-annotationdbi)
5718 ("r-biobase" ,r-biobase)
5719 ("r-biocgenerics" ,r-biocgenerics)
5720 ("r-lattice" ,r-lattice)
5721 ("r-rcolorbrewer" ,r-rcolorbrewer)))
5722 (home-page "https://bioconductor.org/packages/geneplotter")
5723 (synopsis "Graphics functions for genomic data")
5725 "This package provides functions for plotting genomic data.")
5726 (license license:artistic2.0)))
5728 (define-public r-genefilter
5730 (name "r-genefilter")
5735 (uri (bioconductor-uri "genefilter" version))
5738 "173swlg6gj4kdllbqvyiw5dggbcxiwlwpqmllsv4dxzn7h25i3g7"))))
5739 (build-system r-build-system)
5741 `(("gfortran" ,gfortran)))
5743 `(("r-annotate" ,r-annotate)
5744 ("r-annotationdbi" ,r-annotationdbi)
5745 ("r-biobase" ,r-biobase)
5746 ("r-s4vectors" ,r-s4vectors)
5747 ("r-survival" ,r-survival)))
5748 (home-page "https://bioconductor.org/packages/genefilter")
5749 (synopsis "Filter genes from high-throughput experiments")
5751 "This package provides basic functions for filtering genes from
5752 high-throughput sequencing experiments.")
5753 (license license:artistic2.0)))
5755 (define-public r-deseq2
5762 (uri (bioconductor-uri "DESeq2" version))
5765 "1hcxnkkjfvz4hj8iqidshwsjq7jnl1z7wj63dvcwlx1zx5aichyh"))))
5766 (properties `((upstream-name . "DESeq2")))
5767 (build-system r-build-system)
5769 `(("r-biobase" ,r-biobase)
5770 ("r-biocgenerics" ,r-biocgenerics)
5771 ("r-biocparallel" ,r-biocparallel)
5772 ("r-genefilter" ,r-genefilter)
5773 ("r-geneplotter" ,r-geneplotter)
5774 ("r-genomicranges" ,r-genomicranges)
5775 ("r-ggplot2" ,r-ggplot2)
5776 ("r-hmisc" ,r-hmisc)
5777 ("r-iranges" ,r-iranges)
5778 ("r-locfit" ,r-locfit)
5780 ("r-rcpparmadillo" ,r-rcpparmadillo)
5781 ("r-s4vectors" ,r-s4vectors)
5782 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5783 (home-page "https://bioconductor.org/packages/DESeq2")
5784 (synopsis "Differential gene expression analysis")
5786 "This package provides functions to estimate variance-mean dependence in
5787 count data from high-throughput nucleotide sequencing assays and test for
5788 differential expression based on a model using the negative binomial
5790 (license license:lgpl3+)))
5792 (define-public r-dexseq
5799 (uri (bioconductor-uri "DEXSeq" version))
5802 "0qxwnz2ffhav9slcn095k206cfza9i3i5l7w1154plf08gpy1d1d"))))
5803 (properties `((upstream-name . "DEXSeq")))
5804 (build-system r-build-system)
5806 `(("r-annotationdbi" ,r-annotationdbi)
5807 ("r-biobase" ,r-biobase)
5808 ("r-biocgenerics" ,r-biocgenerics)
5809 ("r-biocparallel" ,r-biocparallel)
5810 ("r-biomart" ,r-biomart)
5811 ("r-deseq2" ,r-deseq2)
5812 ("r-genefilter" ,r-genefilter)
5813 ("r-geneplotter" ,r-geneplotter)
5814 ("r-genomicranges" ,r-genomicranges)
5815 ("r-hwriter" ,r-hwriter)
5816 ("r-iranges" ,r-iranges)
5817 ("r-rcolorbrewer" ,r-rcolorbrewer)
5818 ("r-rsamtools" ,r-rsamtools)
5819 ("r-s4vectors" ,r-s4vectors)
5820 ("r-statmod" ,r-statmod)
5821 ("r-stringr" ,r-stringr)
5822 ("r-summarizedexperiment" ,r-summarizedexperiment)))
5823 (home-page "https://bioconductor.org/packages/DEXSeq")
5824 (synopsis "Inference of differential exon usage in RNA-Seq")
5826 "This package is focused on finding differential exon usage using RNA-seq
5827 exon counts between samples with different experimental designs. It provides
5828 functions that allows the user to make the necessary statistical tests based
5829 on a model that uses the negative binomial distribution to estimate the
5830 variance between biological replicates and generalized linear models for
5831 testing. The package also provides functions for the visualization and
5832 exploration of the results.")
5833 (license license:gpl3+)))
5835 (define-public r-annotationforge
5837 (name "r-annotationforge")
5842 (uri (bioconductor-uri "AnnotationForge" version))
5845 "01vbrf76vqfvxh6vpfxkjwccxggnha3byqzj333glqz2b6kwx5q1"))))
5847 `((upstream-name . "AnnotationForge")))
5848 (build-system r-build-system)
5850 `(("r-annotationdbi" ,r-annotationdbi)
5851 ("r-biobase" ,r-biobase)
5852 ("r-biocgenerics" ,r-biocgenerics)
5854 ("r-rcurl" ,r-rcurl)
5855 ("r-rsqlite" ,r-rsqlite)
5856 ("r-s4vectors" ,r-s4vectors)
5858 (home-page "https://bioconductor.org/packages/AnnotationForge")
5859 (synopsis "Code for building annotation database packages")
5861 "This package provides code for generating Annotation packages and their
5862 databases. Packages produced are intended to be used with AnnotationDbi.")
5863 (license license:artistic2.0)))
5865 (define-public r-rbgl
5872 (uri (bioconductor-uri "RBGL" version))
5875 "18jad23i3899ypv4bg3l47cvvs3qnj1pqis2p9x0135yv5y6wnv7"))))
5876 (properties `((upstream-name . "RBGL")))
5877 (build-system r-build-system)
5878 (propagated-inputs `(("r-graph" ,r-graph)))
5879 (home-page "https://www.bioconductor.org/packages/RBGL")
5880 (synopsis "Interface to the Boost graph library")
5882 "This package provides a fairly extensive and comprehensive interface to
5883 the graph algorithms contained in the Boost library.")
5884 (license license:artistic2.0)))
5886 (define-public r-gseabase
5893 (uri (bioconductor-uri "GSEABase" version))
5896 "0kpkl6c5lrar6ip7wlhvd5axqlb9lb5l3lgbdb3dlih32c3nz0yq"))))
5897 (properties `((upstream-name . "GSEABase")))
5898 (build-system r-build-system)
5900 `(("r-annotate" ,r-annotate)
5901 ("r-annotationdbi" ,r-annotationdbi)
5902 ("r-biobase" ,r-biobase)
5903 ("r-biocgenerics" ,r-biocgenerics)
5904 ("r-graph" ,r-graph)
5906 (home-page "https://bioconductor.org/packages/GSEABase")
5907 (synopsis "Gene set enrichment data structures and methods")
5909 "This package provides classes and methods to support @dfn{Gene Set
5910 Enrichment Analysis} (GSEA).")
5911 (license license:artistic2.0)))
5913 (define-public r-category
5920 (uri (bioconductor-uri "Category" version))
5923 "0mkav04vbla0xfa0dssxdd0rjs589sxi83xklf5iq5hj3dm8y0i8"))))
5924 (properties `((upstream-name . "Category")))
5925 (build-system r-build-system)
5927 `(("r-annotate" ,r-annotate)
5928 ("r-annotationdbi" ,r-annotationdbi)
5929 ("r-biobase" ,r-biobase)
5930 ("r-biocgenerics" ,r-biocgenerics)
5931 ("r-genefilter" ,r-genefilter)
5932 ("r-graph" ,r-graph)
5933 ("r-gseabase" ,r-gseabase)
5934 ("r-matrix" ,r-matrix)
5937 (home-page "https://bioconductor.org/packages/Category")
5938 (synopsis "Category analysis")
5940 "This package provides a collection of tools for performing category
5942 (license license:artistic2.0)))
5944 (define-public r-gostats
5951 (uri (bioconductor-uri "GOstats" version))
5954 "04gqfdlx9fxf97qf0l28x4aaqvl10n6v58qiz5fiaw05sbj1pf1i"))))
5955 (properties `((upstream-name . "GOstats")))
5956 (build-system r-build-system)
5958 `(("r-annotate" ,r-annotate)
5959 ("r-annotationdbi" ,r-annotationdbi)
5960 ("r-annotationforge" ,r-annotationforge)
5961 ("r-biobase" ,r-biobase)
5962 ("r-category" ,r-category)
5963 ("r-go-db" ,r-go-db)
5964 ("r-graph" ,r-graph)
5965 ("r-rgraphviz" ,r-rgraphviz)
5966 ("r-rbgl" ,r-rbgl)))
5967 (home-page "https://bioconductor.org/packages/GOstats")
5968 (synopsis "Tools for manipulating GO and microarrays")
5970 "This package provides a set of tools for interacting with GO and
5971 microarray data. A variety of basic manipulation tools for graphs, hypothesis
5972 testing and other simple calculations.")
5973 (license license:artistic2.0)))
5975 (define-public r-shortread
5977 (name "r-shortread")
5982 (uri (bioconductor-uri "ShortRead" version))
5985 "06mknlsmd4hnaxzdjapgvp2kgdnf9w103y500dsac5jgsz4vwzcz"))))
5986 (properties `((upstream-name . "ShortRead")))
5987 (build-system r-build-system)
5991 `(("r-biobase" ,r-biobase)
5992 ("r-biocgenerics" ,r-biocgenerics)
5993 ("r-biocparallel" ,r-biocparallel)
5994 ("r-biostrings" ,r-biostrings)
5995 ("r-genomeinfodb" ,r-genomeinfodb)
5996 ("r-genomicalignments" ,r-genomicalignments)
5997 ("r-genomicranges" ,r-genomicranges)
5998 ("r-hwriter" ,r-hwriter)
5999 ("r-iranges" ,r-iranges)
6000 ("r-lattice" ,r-lattice)
6001 ("r-latticeextra" ,r-latticeextra)
6002 ("r-rsamtools" ,r-rsamtools)
6003 ("r-s4vectors" ,r-s4vectors)
6004 ("r-xvector" ,r-xvector)
6005 ("r-zlibbioc" ,r-zlibbioc)))
6006 (home-page "https://bioconductor.org/packages/ShortRead")
6007 (synopsis "FASTQ input and manipulation tools")
6009 "This package implements sampling, iteration, and input of FASTQ files.
6010 It includes functions for filtering and trimming reads, and for generating a
6011 quality assessment report. Data are represented as
6012 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6013 purposes. The package also contains legacy support for early single-end,
6014 ungapped alignment formats.")
6015 (license license:artistic2.0)))
6017 (define-public r-systempiper
6019 (name "r-systempiper")
6024 (uri (bioconductor-uri "systemPipeR" version))
6027 "11mj8pjq5vj25768vmagpzv74fvi3p3kdk5zdlznqyiaggri04cv"))))
6028 (properties `((upstream-name . "systemPipeR")))
6029 (build-system r-build-system)
6031 `(("r-annotate" ,r-annotate)
6032 ("r-batchjobs" ,r-batchjobs)
6033 ("r-biocgenerics" ,r-biocgenerics)
6034 ("r-biostrings" ,r-biostrings)
6035 ("r-deseq2" ,r-deseq2)
6036 ("r-edger" ,r-edger)
6037 ("r-genomicfeatures" ,r-genomicfeatures)
6038 ("r-genomicranges" ,r-genomicranges)
6039 ("r-ggplot2" ,r-ggplot2)
6040 ("r-go-db" ,r-go-db)
6041 ("r-gostats" ,r-gostats)
6042 ("r-limma" ,r-limma)
6043 ("r-pheatmap" ,r-pheatmap)
6044 ("r-rjson" ,r-rjson)
6045 ("r-rsamtools" ,r-rsamtools)
6046 ("r-shortread" ,r-shortread)
6047 ("r-summarizedexperiment" ,r-summarizedexperiment)
6048 ("r-variantannotation" ,r-variantannotation)))
6049 (home-page "https://github.com/tgirke/systemPipeR")
6050 (synopsis "Next generation sequencing workflow and reporting environment")
6052 "This R package provides tools for building and running automated
6053 end-to-end analysis workflows for a wide range of @dfn{next generation
6054 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6055 Important features include a uniform workflow interface across different NGS
6056 applications, automated report generation, and support for running both R and
6057 command-line software, such as NGS aligners or peak/variant callers, on local
6058 computers or compute clusters. Efficient handling of complex sample sets and
6059 experimental designs is facilitated by a consistently implemented sample
6060 annotation infrastructure.")
6061 (license license:artistic2.0)))
6063 (define-public r-grohmm
6070 (uri (bioconductor-uri "groHMM" version))
6073 "0cjkj0ypyc4dfi9s8dh88kh6q4xlpnc0wal7njg4b4gqj0l2hva7"))))
6074 (properties `((upstream-name . "groHMM")))
6075 (build-system r-build-system)
6077 `(("r-genomeinfodb" ,r-genomeinfodb)
6078 ("r-genomicalignments" ,r-genomicalignments)
6079 ("r-genomicranges" ,r-genomicranges)
6080 ("r-iranges" ,r-iranges)
6082 ("r-rtracklayer" ,r-rtracklayer)
6083 ("r-s4vectors" ,r-s4vectors)))
6084 (home-page "https://github.com/Kraus-Lab/groHMM")
6085 (synopsis "GRO-seq analysis pipeline")
6087 "This package provides a pipeline for the analysis of GRO-seq data.")
6088 (license license:gpl3+)))
6090 (define-public r-txdb-hsapiens-ucsc-hg19-knowngene
6092 (name "r-txdb-hsapiens-ucsc-hg19-knowngene")
6096 ;; We cannot use bioconductor-uri here because this tarball is
6097 ;; located under "data/annotation/" instead of "bioc/".
6098 (uri (string-append "https://bioconductor.org/packages/"
6099 "release/data/annotation/src/contrib"
6100 "/TxDb.Hsapiens.UCSC.hg19.knownGene_"
6104 "1sajhcqqwazgz2lqbik7rd935i7kpnh08zxbp2ra10j72yqy4g86"))))
6106 `((upstream-name . "TxDb.Hsapiens.UCSC.hg19.knownGene")))
6107 (build-system r-build-system)
6108 ;; As this package provides little more than a very large data file it
6109 ;; doesn't make sense to build substitutes.
6110 (arguments `(#:substitutable? #f))
6112 `(("r-genomicfeatures" ,r-genomicfeatures)))
6114 "https://bioconductor.org/packages/TxDb.Hsapiens.UCSC.hg19.knownGene/")
6115 (synopsis "Annotation package for human genome in TxDb format")
6117 "This package provides an annotation database of Homo sapiens genome
6118 data. It is derived from the UCSC hg19 genome and based on the \"knownGene\"
6119 track. The database is exposed as a @code{TxDb} object.")
6120 (license license:artistic2.0)))
6122 (define-public r-sparql
6128 (uri (cran-uri "SPARQL" version))
6131 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6132 (properties `((upstream-name . "SPARQL")))
6133 (build-system r-build-system)
6135 `(("r-rcurl" ,r-rcurl)
6137 (home-page "http://cran.r-project.org/web/packages/SPARQL")
6138 (synopsis "SPARQL client for R")
6139 (description "This package provides an interface to use SPARQL to pose
6140 SELECT or UPDATE queries to an end-point.")
6141 ;; The only license indication is found in the DESCRIPTION file,
6142 ;; which states GPL-3. So we cannot assume GPLv3+.
6143 (license license:gpl3)))
6145 (define-public vsearch
6153 "https://github.com/torognes/vsearch/archive/v"
6155 (file-name (string-append name "-" version ".tar.gz"))
6158 "0rplgpvsdkxw0k371ckxrp6i77jn93ckhslaazwbyd85m83nkynr"))
6159 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6162 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6163 ;; for this in the patch.
6164 (delete-file "src/city.h")
6165 (delete-file "src/citycrc.h")
6166 (delete-file "src/city.cc")
6168 (build-system gnu-build-system)
6171 (modify-phases %standard-phases
6172 (add-after 'unpack 'autogen
6173 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
6177 ("cityhash" ,cityhash)))
6179 `(("autoconf" ,autoconf)
6180 ("automake" ,automake)))
6181 (synopsis "Sequence search tools for metagenomics")
6183 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6184 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6185 masking. The tool takes advantage of parallelism in the form of SIMD
6186 vectorization as well as multiple threads to perform accurate alignments at
6187 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6188 Needleman-Wunsch).")
6189 (home-page "https://github.com/torognes/vsearch")
6190 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6192 (supported-systems '("x86_64-linux"))
6193 ;; Dual licensed; also includes public domain source.
6194 (license (list license:gpl3 license:bsd-2))))
6196 (define-public pardre
6199 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6204 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6208 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6209 (build-system gnu-build-system)
6211 `(#:tests? #f ; no tests included
6213 (modify-phases %standard-phases
6216 (lambda* (#:key outputs #:allow-other-keys)
6217 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6218 (install-file "ParDRe" bin)
6221 `(("openmpi" ,openmpi)
6223 (synopsis "Parallel tool to remove duplicate DNA reads")
6225 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6226 Duplicate reads can be seen as identical or nearly identical sequences with
6227 some mismatches. This tool lets users avoid the analysis of unnecessary
6228 reads, reducing the time of subsequent procedures with the
6229 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6230 in order to exploit the parallel capabilities of multicore clusters. It is
6231 faster than multithreaded counterparts (end of 2015) for the same number of
6232 cores and, thanks to the message-passing technology, it can be executed on
6234 (home-page "https://sourceforge.net/projects/pardre/")
6235 (license license:gpl3+)))
6237 (define-public ruby-bio-kseq
6239 (name "ruby-bio-kseq")
6244 (uri (rubygems-uri "bio-kseq" version))
6247 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6248 (build-system ruby-build-system)
6250 `(#:test-target "spec"))
6252 `(("bundler" ,bundler)
6253 ("ruby-rspec" ,ruby-rspec)
6254 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6257 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6259 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6260 FASTQ parsing code. It provides a fast iterator over sequences and their
6262 (home-page "https://github.com/gusevfe/bio-kseq")
6263 (license license:expat)))
6265 (define-public bio-locus
6272 (uri (rubygems-uri "bio-locus" version))
6275 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6276 (build-system ruby-build-system)
6278 `(("ruby-rspec" ,ruby-rspec)))
6279 (synopsis "Tool for fast querying of genome locations")
6281 "Bio-locus is a tabix-like tool for fast querying of genome
6282 locations. Many file formats in bioinformatics contain records that
6283 start with a chromosome name and a position for a SNP, or a start-end
6284 position for indels. Bio-locus allows users to store this chr+pos or
6285 chr+pos+alt information in a database.")
6286 (home-page "https://github.com/pjotrp/bio-locus")
6287 (license license:expat)))
6289 (define-public bio-blastxmlparser
6291 (name "bio-blastxmlparser")
6295 (uri (rubygems-uri "bio-blastxmlparser" version))
6298 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6299 (build-system ruby-build-system)
6301 `(("ruby-bio-logger" ,ruby-bio-logger)
6302 ("ruby-nokogiri" ,ruby-nokogiri)))
6304 `(("ruby-rspec" ,ruby-rspec)))
6305 (synopsis "Fast big data BLAST XML parser and library")
6307 "Very fast parallel big-data BLAST XML file parser which can be used as
6308 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6309 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6310 (home-page "https://github.com/pjotrp/blastxmlparser")
6311 (license license:expat)))
6313 (define-public bioruby
6320 (uri (rubygems-uri "bio" version))
6323 "0hdl0789c9n4mprnx5pgd46bfwl8d000rqpamj5h6kkjgspijv49"))))
6324 (build-system ruby-build-system)
6326 `(("ruby-libxml" ,ruby-libxml)))
6328 `(("which" ,which))) ; required for test phase
6331 (modify-phases %standard-phases
6332 (add-before 'build 'patch-test-command
6334 (substitute* '("test/functional/bio/test_command.rb")
6335 (("/bin/sh") (which "sh")))
6336 (substitute* '("test/functional/bio/test_command.rb")
6337 (("/bin/ls") (which "ls")))
6338 (substitute* '("test/functional/bio/test_command.rb")
6339 (("which") (which "which")))
6340 (substitute* '("test/functional/bio/test_command.rb",
6341 "test/data/command/echoarg2.sh")
6342 (("/bin/echo") (which "echo")))
6344 (synopsis "Ruby library, shell and utilities for bioinformatics")
6345 (description "BioRuby comes with a comprehensive set of Ruby development
6346 tools and libraries for bioinformatics and molecular biology. BioRuby has
6347 components for sequence analysis, pathway analysis, protein modelling and
6348 phylogenetic analysis; it supports many widely used data formats and provides
6349 easy access to databases, external programs and public web services, including
6350 BLAST, KEGG, GenBank, MEDLINE and GO.")
6351 (home-page "http://bioruby.org/")
6352 ;; Code is released under Ruby license, except for setup
6353 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6354 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6356 (define-public r-acsnminer
6358 (name "r-acsnminer")
6359 (version "0.16.8.25")
6362 (uri (cran-uri "ACSNMineR" version))
6365 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6366 (properties `((upstream-name . "ACSNMineR")))
6367 (build-system r-build-system)
6369 `(("r-ggplot2" ,r-ggplot2)
6370 ("r-gridextra" ,r-gridextra)))
6371 (home-page "http://cran.r-project.org/web/packages/ACSNMineR")
6372 (synopsis "Gene enrichment analysis")
6374 "This package provides tools to compute and represent gene set enrichment
6375 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6376 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6377 enrichment can be run with hypergeometric test or Fisher exact test, and can
6378 use multiple corrections. Visualization of data can be done either by
6379 barplots or heatmaps.")
6380 (license license:gpl2+)))
6382 (define-public r-biocgenerics
6384 (name "r-biocgenerics")
6388 (uri (bioconductor-uri "BiocGenerics" version))
6391 "03wxvhxyrhipbgcg83lqlfn7p9gbzzrnl48y0dq7303xgp232zai"))))
6393 `((upstream-name . "BiocGenerics")))
6394 (build-system r-build-system)
6395 (home-page "https://bioconductor.org/packages/BiocGenerics")
6396 (synopsis "S4 generic functions for Bioconductor")
6398 "This package provides S4 generic functions needed by many Bioconductor
6400 (license license:artistic2.0)))
6402 (define-public r-biocinstaller
6404 (name "r-biocinstaller")
6408 (uri (bioconductor-uri "BiocInstaller" version))
6411 "19fga27bv6q9v5mpil74y76lahmnwvpg2h33rdx1r79nvljkd19d"))))
6413 `((upstream-name . "BiocInstaller")))
6414 (build-system r-build-system)
6415 (home-page "https://bioconductor.org/packages/BiocInstaller")
6416 (synopsis "Install Bioconductor packages")
6417 (description "This package is used to install and update R packages from
6418 Bioconductor, CRAN, and Github.")
6419 (license license:artistic2.0)))
6421 (define-public r-biocviews
6423 (name "r-biocviews")
6427 (uri (bioconductor-uri "biocViews" version))
6430 "09zyqj1kqc089lmh9sliy0acanx9zimcasvp71dsrg2bqm08r1md"))))
6432 `((upstream-name . "biocViews")))
6433 (build-system r-build-system)
6435 `(("r-biobase" ,r-biobase)
6436 ("r-graph" ,r-graph)
6438 ("r-rcurl" ,r-rcurl)
6440 ("r-runit" ,r-runit)))
6441 (home-page "https://bioconductor.org/packages/biocViews")
6442 (synopsis "Bioconductor package categorization helper")
6443 (description "The purpose of biocViews is to create HTML pages that
6444 categorize packages in a Bioconductor package repository according to keywords,
6445 also known as views, in a controlled vocabulary.")
6446 (license license:artistic2.0)))
6448 (define-public r-bookdown
6454 (uri (cran-uri "bookdown" version))
6457 "0zm63kr4f4kja4qpwkzl119zzyciqj7ihajfqgfjpgb4dzaiycxp"))))
6458 (build-system r-build-system)
6460 `(("r-htmltools" ,r-htmltools)
6461 ("r-knitr" ,r-knitr)
6462 ("r-rmarkdown" ,r-rmarkdown)
6463 ("r-yaml" ,r-yaml)))
6464 (home-page "https://github.com/rstudio/bookdown")
6465 (synopsis "Authoring books and technical documents with R markdown")
6466 (description "This package provides output formats and utilities for
6467 authoring books and technical documents with R Markdown.")
6468 (license license:gpl3)))
6470 (define-public r-biocstyle
6472 (name "r-biocstyle")
6476 (uri (bioconductor-uri "BiocStyle" version))
6479 "05f2j9fx8s5gh4f8qkl6wcz32ghz04wxhqb3xxcn1bj24qd7x1x8"))))
6481 `((upstream-name . "BiocStyle")))
6482 (build-system r-build-system)
6484 `(("r-bookdown" ,r-bookdown)
6485 ("r-knitr" ,r-knitr)
6486 ("r-rmarkdown" ,r-rmarkdown)
6487 ("r-yaml" ,r-yaml)))
6488 (home-page "https://bioconductor.org/packages/BiocStyle")
6489 (synopsis "Bioconductor formatting styles")
6490 (description "This package provides standard formatting styles for
6491 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
6493 (license license:artistic2.0)))
6495 (define-public r-bioccheck
6497 (name "r-bioccheck")
6501 (uri (bioconductor-uri "BiocCheck" version))
6504 "1nzp8kgw13z9pgf885rplj6k37jcldfhbz0adqclxr2gq0yalmyx"))))
6506 `((upstream-name . "BiocCheck")))
6507 (build-system r-build-system)
6510 (modify-phases %standard-phases
6511 ;; This package can be used by calling BiocCheck(<package>) from
6512 ;; within R, or by running R CMD BiocCheck <package>. This phase
6513 ;; makes sure the latter works. For this to work, the BiocCheck
6514 ;; script must be somewhere on the PATH (not the R bin directory).
6515 (add-after 'install 'install-bioccheck-subcommand
6516 (lambda* (#:key outputs #:allow-other-keys)
6517 (let* ((out (assoc-ref outputs "out"))
6518 (dest-dir (string-append out "/bin"))
6520 (string-append out "/site-library/BiocCheck/script/")))
6522 (symlink (string-append script-dir "/checkBadDeps.R")
6523 (string-append dest-dir "/checkBadDeps.R"))
6524 (symlink (string-append script-dir "/BiocCheck")
6525 (string-append dest-dir "/BiocCheck")))
6528 `(("r-codetools" ,r-codetools)
6529 ("r-graph" ,r-graph)
6531 ("r-optparse" ,r-optparse)
6532 ("r-biocinstaller" ,r-biocinstaller)
6533 ("r-biocviews" ,r-biocviews)
6534 ("r-stringdist" ,r-stringdist)))
6535 (home-page "https://bioconductor.org/packages/BiocCheck")
6536 (synopsis "Executes Bioconductor-specific package checks")
6537 (description "This package contains tools to perform additional quality
6538 checks on R packages that are to be submitted to the Bioconductor repository.")
6539 (license license:artistic2.0)))
6541 (define-public r-getopt
6548 (uri (cran-uri "getopt" version))
6551 "00f57vgnzmg7cz80rjmjz1556xqcmx8nhrlbbhaq4w7gl2ibl87r"))))
6552 (build-system r-build-system)
6553 (home-page "https://github.com/trevorld/getopt")
6554 (synopsis "Command-line option processor for R")
6556 "This package is designed to be used with Rscript to write shebang
6557 scripts that accept short and long options. Many users will prefer to
6558 use the packages @code{optparse} or @code{argparse} which add extra
6559 features like automatically generated help options and usage texts,
6560 support for default values, positional argument support, etc.")
6561 (license license:gpl2+)))
6563 (define-public r-optparse
6570 (uri (cran-uri "optparse" version))
6573 "1ff4wmsszrb3spwfp7ynfs8w11qpy1sdzfxm1wk8dqqvdwris7qb"))))
6574 (build-system r-build-system)
6576 `(("r-getopt" ,r-getopt)))
6578 "https://github.com/trevorld/optparse")
6579 (synopsis "Command line option parser")
6581 "This package provides a command line parser inspired by Python's
6582 @code{optparse} library to be used with Rscript to write shebang scripts
6583 that accept short and long options.")
6584 (license license:gpl2+)))
6586 (define-public r-dnacopy
6592 (uri (bioconductor-uri "DNAcopy" version))
6595 "127il5rlg1hzjlhwhs64x3nm18p00q1pd9ckb2b9ifl0rax95wai"))))
6597 `((upstream-name . "DNAcopy")))
6598 (build-system r-build-system)
6600 `(("gfortran" ,gfortran)))
6601 (home-page "https://bioconductor.org/packages/DNAcopy")
6602 (synopsis "Implementation of a circular binary segmentation algorithm")
6603 (description "This package implements the circular binary segmentation (CBS)
6604 algorithm to segment DNA copy number data and identify genomic regions with
6605 abnormal copy number.")
6606 (license license:gpl2+)))
6608 (define-public r-s4vectors
6610 (name "r-s4vectors")
6614 (uri (bioconductor-uri "S4Vectors" version))
6617 "03s8vz33nl6mivjb7dbvj702dkypi340lji1sjban03fyyls0hw0"))))
6619 `((upstream-name . "S4Vectors")))
6620 (build-system r-build-system)
6622 `(("r-biocgenerics" ,r-biocgenerics)))
6623 (home-page "https://bioconductor.org/packages/S4Vectors")
6624 (synopsis "S4 implementation of vectors and lists")
6626 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
6627 classes and a set of generic functions that extend the semantic of ordinary
6628 vectors and lists in R. Package developers can easily implement vector-like
6629 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
6630 In addition, a few low-level concrete subclasses of general interest (e.g.
6631 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
6632 S4Vectors package itself.")
6633 (license license:artistic2.0)))
6635 (define-public r-seqinr
6642 (uri (cran-uri "seqinr" version))
6645 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
6646 (build-system r-build-system)
6648 `(("r-ade4" ,r-ade4)
6649 ("r-segmented" ,r-segmented)))
6652 (home-page "http://seqinr.r-forge.r-project.org/")
6653 (synopsis "Biological sequences retrieval and analysis")
6655 "This package provides tools for exploratory data analysis and data
6656 visualization of biological sequence (DNA and protein) data. It also includes
6657 utilities for sequence data management under the ACNUC system.")
6658 (license license:gpl2+)))
6660 (define-public r-iranges
6666 (uri (bioconductor-uri "IRanges" version))
6669 "1vqczb9wlxsmpwpqig6j1dmiblcfpq6mgnq8qwzcrvddm4cp47m5"))))
6671 `((upstream-name . "IRanges")))
6672 (build-system r-build-system)
6674 `(("r-biocgenerics" ,r-biocgenerics)
6675 ("r-s4vectors" ,r-s4vectors)))
6676 (home-page "https://bioconductor.org/packages/IRanges")
6677 (synopsis "Infrastructure for manipulating intervals on sequences")
6679 "This package provides efficient low-level and highly reusable S4 classes
6680 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
6681 generally, data that can be organized sequentially (formally defined as
6682 @code{Vector} objects), as well as views on these @code{Vector} objects.
6683 Efficient list-like classes are also provided for storing big collections of
6684 instances of the basic classes. All classes in the package use consistent
6685 naming and share the same rich and consistent \"Vector API\" as much as
6687 (license license:artistic2.0)))
6689 (define-public r-genomeinfodbdata
6691 (name "r-genomeinfodbdata")
6695 ;; We cannot use bioconductor-uri here because this tarball is
6696 ;; located under "data/annotation/" instead of "bioc/".
6697 (uri (string-append "https://bioconductor.org/packages/release/"
6698 "data/annotation/src/contrib/GenomeInfoDbData_"
6702 "120qvhb0pvkzd65lsgja62vyrgc37si6fh68q4cg4w5x9f04jw25"))))
6704 `((upstream-name . "GenomeInfoDbData")))
6705 (build-system r-build-system)
6706 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
6707 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
6708 (description "This package contains data for mapping between NCBI taxonomy
6709 ID and species. It is used by functions in the GenomeInfoDb package.")
6710 (license license:artistic2.0)))
6712 (define-public r-genomeinfodb
6714 (name "r-genomeinfodb")
6718 (uri (bioconductor-uri "GenomeInfoDb" version))
6721 "1jhm0imkac4gvchbjxj408aakk39xdv2fyh818d3lk295bz6bnyp"))))
6723 `((upstream-name . "GenomeInfoDb")))
6724 (build-system r-build-system)
6726 `(("r-biocgenerics" ,r-biocgenerics)
6727 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
6728 ("r-iranges" ,r-iranges)
6729 ("r-rcurl" ,r-rcurl)
6730 ("r-s4vectors" ,r-s4vectors)))
6731 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
6732 (synopsis "Utilities for manipulating chromosome identifiers")
6734 "This package contains data and functions that define and allow
6735 translation between different chromosome sequence naming conventions (e.g.,
6736 \"chr1\" versus \"1\"), including a function that attempts to place sequence
6737 names in their natural, rather than lexicographic, order.")
6738 (license license:artistic2.0)))
6740 (define-public r-edger
6746 (uri (bioconductor-uri "edgeR" version))
6749 "01qnxwr9rmz8r5ga3hvjk632365ga2aygx71mxkk7jiad2pjznsp"))))
6750 (properties `((upstream-name . "edgeR")))
6751 (build-system r-build-system)
6753 `(("r-limma" ,r-limma)
6754 ("r-locfit" ,r-locfit)
6756 ("r-statmod" ,r-statmod))) ;for estimateDisp
6757 (home-page "http://bioinf.wehi.edu.au/edgeR")
6758 (synopsis "EdgeR does empirical analysis of digital gene expression data")
6759 (description "This package can do differential expression analysis of
6760 RNA-seq expression profiles with biological replication. It implements a range
6761 of statistical methodology based on the negative binomial distributions,
6762 including empirical Bayes estimation, exact tests, generalized linear models
6763 and quasi-likelihood tests. It be applied to differential signal analysis of
6764 other types of genomic data that produce counts, including ChIP-seq, SAGE and
6766 (license license:gpl2+)))
6768 (define-public r-variantannotation
6770 (name "r-variantannotation")
6774 (uri (bioconductor-uri "VariantAnnotation" version))
6777 "1lllp2vgyfbrar1yg28ji7am470hfzrzxm1bgdk68xpnrwcgcl25"))))
6779 `((upstream-name . "VariantAnnotation")))
6783 `(("r-annotationdbi" ,r-annotationdbi)
6784 ("r-biobase" ,r-biobase)
6785 ("r-biocgenerics" ,r-biocgenerics)
6786 ("r-biostrings" ,r-biostrings)
6787 ("r-bsgenome" ,r-bsgenome)
6789 ("r-genomeinfodb" ,r-genomeinfodb)
6790 ("r-genomicfeatures" ,r-genomicfeatures)
6791 ("r-genomicranges" ,r-genomicranges)
6792 ("r-iranges" ,r-iranges)
6793 ("r-summarizedexperiment" ,r-summarizedexperiment)
6794 ("r-rsamtools" ,r-rsamtools)
6795 ("r-rtracklayer" ,r-rtracklayer)
6796 ("r-s4vectors" ,r-s4vectors)
6797 ("r-xvector" ,r-xvector)
6798 ("r-zlibbioc" ,r-zlibbioc)))
6799 (build-system r-build-system)
6800 (home-page "https://bioconductor.org/packages/VariantAnnotation")
6801 (synopsis "Package for annotation of genetic variants")
6802 (description "This R package can annotate variants, compute amino acid
6803 coding changes and predict coding outcomes.")
6804 (license license:artistic2.0)))
6806 (define-public r-limma
6812 (uri (bioconductor-uri "limma" version))
6815 "0a15gsaky0hfrkx8wrrmp0labzxpq6m2hrd33zl206wyas8bqzcs"))))
6816 (build-system r-build-system)
6817 (home-page "http://bioinf.wehi.edu.au/limma")
6818 (synopsis "Package for linear models for microarray and RNA-seq data")
6819 (description "This package can be used for the analysis of gene expression
6820 studies, especially the use of linear models for analysing designed experiments
6821 and the assessment of differential expression. The analysis methods apply to
6822 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
6823 (license license:gpl2+)))
6825 (define-public r-xvector
6831 (uri (bioconductor-uri "XVector" version))
6834 "1i4i3kdxr78lr1kcxq657p11ybi7kq10c8kyaqyh6gfc8i9rhvmk"))))
6836 `((upstream-name . "XVector")))
6837 (build-system r-build-system)
6840 (modify-phases %standard-phases
6841 (add-after 'unpack 'use-system-zlib
6843 (substitute* "DESCRIPTION"
6844 (("zlibbioc, ") ""))
6845 (substitute* "NAMESPACE"
6846 (("import\\(zlibbioc\\)") ""))
6851 `(("r-biocgenerics" ,r-biocgenerics)
6852 ("r-iranges" ,r-iranges)
6853 ("r-s4vectors" ,r-s4vectors)))
6854 (home-page "https://bioconductor.org/packages/XVector")
6855 (synopsis "Representation and manpulation of external sequences")
6857 "This package provides memory efficient S4 classes for storing sequences
6858 \"externally\" (behind an R external pointer, or on disk).")
6859 (license license:artistic2.0)))
6861 (define-public r-genomicranges
6863 (name "r-genomicranges")
6867 (uri (bioconductor-uri "GenomicRanges" version))
6870 "10ra2sjn17h6gilm9iz0cygp9ijpgbirljlc4drwrnivnw9cmi2a"))))
6872 `((upstream-name . "GenomicRanges")))
6873 (build-system r-build-system)
6875 `(("r-biocgenerics" ,r-biocgenerics)
6876 ("r-genomeinfodb" ,r-genomeinfodb)
6877 ("r-iranges" ,r-iranges)
6878 ("r-s4vectors" ,r-s4vectors)
6879 ("r-xvector" ,r-xvector)))
6880 (home-page "https://bioconductor.org/packages/GenomicRanges")
6881 (synopsis "Representation and manipulation of genomic intervals")
6883 "This package provides tools to efficiently represent and manipulate
6884 genomic annotations and alignments is playing a central role when it comes to
6885 analyzing high-throughput sequencing data (a.k.a. NGS data). The
6886 GenomicRanges package defines general purpose containers for storing and
6887 manipulating genomic intervals and variables defined along a genome.")
6888 (license license:artistic2.0)))
6890 (define-public r-biobase
6896 (uri (bioconductor-uri "Biobase" version))
6899 "1cgm1ja1kp56zdlzyy9ggbkfn8r2vbsd4hncmz8g4hjd47fg18kg"))))
6901 `((upstream-name . "Biobase")))
6902 (build-system r-build-system)
6904 `(("r-biocgenerics" ,r-biocgenerics)))
6905 (home-page "https://bioconductor.org/packages/Biobase")
6906 (synopsis "Base functions for Bioconductor")
6908 "This package provides functions that are needed by many other packages
6909 on Bioconductor or which replace R functions.")
6910 (license license:artistic2.0)))
6912 (define-public r-annotationdbi
6914 (name "r-annotationdbi")
6918 (uri (bioconductor-uri "AnnotationDbi" version))
6921 "1dh4qs1a757n640gs34lf6z2glc96nan86x0sqaw5csadl2rhnlc"))))
6923 `((upstream-name . "AnnotationDbi")))
6924 (build-system r-build-system)
6926 `(("r-biobase" ,r-biobase)
6927 ("r-biocgenerics" ,r-biocgenerics)
6929 ("r-iranges" ,r-iranges)
6930 ("r-rsqlite" ,r-rsqlite)
6931 ("r-s4vectors" ,r-s4vectors)))
6932 (home-page "https://bioconductor.org/packages/AnnotationDbi")
6933 (synopsis "Annotation database interface")
6935 "This package provides user interface and database connection code for
6936 annotation data packages using SQLite data storage.")
6937 (license license:artistic2.0)))
6939 (define-public r-biomart
6945 (uri (bioconductor-uri "biomaRt" version))
6948 "1dn3ysf0vb3mmg2b3380g0j1ajf88x4rh7fddfp990h2xlnsy2cx"))))
6950 `((upstream-name . "biomaRt")))
6951 (build-system r-build-system)
6953 `(("r-annotationdbi" ,r-annotationdbi)
6954 ("r-progress" ,r-progress)
6955 ("r-rcurl" ,r-rcurl)
6956 ("r-stringr" ,r-stringr)
6958 (home-page "https://bioconductor.org/packages/biomaRt")
6959 (synopsis "Interface to BioMart databases")
6961 "biomaRt provides an interface to a growing collection of databases
6962 implementing the @url{BioMart software suite, http://www.biomart.org}. The
6963 package enables retrieval of large amounts of data in a uniform way without
6964 the need to know the underlying database schemas or write complex SQL queries.
6965 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
6966 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
6967 users direct access to a diverse set of data and enable a wide range of
6968 powerful online queries from gene annotation to database mining.")
6969 (license license:artistic2.0)))
6971 (define-public r-biocparallel
6973 (name "r-biocparallel")
6977 (uri (bioconductor-uri "BiocParallel" version))
6980 "13ng3n2wsgl3fh0v6jnz3vg51k5c1sh44pqdvblcrcd1qyjmmqhd"))))
6982 `((upstream-name . "BiocParallel")))
6983 (build-system r-build-system)
6985 `(("r-futile-logger" ,r-futile-logger)
6988 (home-page "https://bioconductor.org/packages/BiocParallel")
6989 (synopsis "Bioconductor facilities for parallel evaluation")
6991 "This package provides modified versions and novel implementation of
6992 functions for parallel evaluation, tailored to use with Bioconductor
6994 (license (list license:gpl2+ license:gpl3+))))
6996 (define-public r-biostrings
6998 (name "r-biostrings")
7002 (uri (bioconductor-uri "Biostrings" version))
7005 "0vg50qdlxqcm2d6axjnzg8wh8pr4c5gz03l8bdl0llmwzp0zclzk"))))
7007 `((upstream-name . "Biostrings")))
7008 (build-system r-build-system)
7010 `(("r-biocgenerics" ,r-biocgenerics)
7011 ("r-iranges" ,r-iranges)
7012 ("r-s4vectors" ,r-s4vectors)
7013 ("r-xvector" ,r-xvector)))
7014 (home-page "https://bioconductor.org/packages/Biostrings")
7015 (synopsis "String objects and algorithms for biological sequences")
7017 "This package provides memory efficient string containers, string
7018 matching algorithms, and other utilities, for fast manipulation of large
7019 biological sequences or sets of sequences.")
7020 (license license:artistic2.0)))
7022 (define-public r-rsamtools
7024 (name "r-rsamtools")
7028 (uri (bioconductor-uri "Rsamtools" version))
7031 "0pjny5fjvbnfdyhl3bwxin678sha2drvs00sivxh3l772cn6yams"))))
7033 `((upstream-name . "Rsamtools")))
7034 (build-system r-build-system)
7037 (modify-phases %standard-phases
7038 (add-after 'unpack 'use-system-zlib
7040 (substitute* "DESCRIPTION"
7041 (("zlibbioc, ") ""))
7042 (substitute* "NAMESPACE"
7043 (("import\\(zlibbioc\\)") ""))
7048 `(("r-biocgenerics" ,r-biocgenerics)
7049 ("r-biocparallel" ,r-biocparallel)
7050 ("r-biostrings" ,r-biostrings)
7051 ("r-bitops" ,r-bitops)
7052 ("r-genomeinfodb" ,r-genomeinfodb)
7053 ("r-genomicranges" ,r-genomicranges)
7054 ("r-iranges" ,r-iranges)
7055 ("r-s4vectors" ,r-s4vectors)
7056 ("r-xvector" ,r-xvector)))
7057 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7058 (synopsis "Interface to samtools, bcftools, and tabix")
7060 "This package provides an interface to the 'samtools', 'bcftools', and
7061 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7062 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7064 (license license:expat)))
7066 (define-public r-delayedarray
7068 (name "r-delayedarray")
7072 (uri (bioconductor-uri "DelayedArray" version))
7075 "0s7h2giyvz04cg6248kbbzpwhxdrpnsvl2s8k5c8ricisd9aaz4b"))))
7077 `((upstream-name . "DelayedArray")))
7078 (build-system r-build-system)
7080 `(("r-biocgenerics" ,r-biocgenerics)
7081 ("r-s4vectors" ,r-s4vectors)
7082 ("r-iranges" ,r-iranges)
7083 ("r-matrixstats" ,r-matrixstats)))
7084 (home-page "https://bioconductor.org/packages/DelayedArray")
7085 (synopsis "Delayed operations on array-like objects")
7087 "Wrapping an array-like object (typically an on-disk object) in a
7088 @code{DelayedArray} object allows one to perform common array operations on it
7089 without loading the object in memory. In order to reduce memory usage and
7090 optimize performance, operations on the object are either delayed or executed
7091 using a block processing mechanism. Note that this also works on in-memory
7092 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7093 @code{Matrix} objects, and ordinary arrays and data frames.")
7094 (license license:artistic2.0)))
7096 (define-public r-summarizedexperiment
7098 (name "r-summarizedexperiment")
7102 (uri (bioconductor-uri "SummarizedExperiment" version))
7105 "1011r8l0k8420j31bmh4xdcp6ka5bzf4bqhip84v5b6alpkcbvmf"))))
7107 `((upstream-name . "SummarizedExperiment")))
7108 (build-system r-build-system)
7110 `(("r-biobase" ,r-biobase)
7111 ("r-biocgenerics" ,r-biocgenerics)
7112 ("r-delayedarray" ,r-delayedarray)
7113 ("r-genomeinfodb" ,r-genomeinfodb)
7114 ("r-genomicranges" ,r-genomicranges)
7115 ("r-iranges" ,r-iranges)
7116 ("r-matrix" ,r-matrix)
7117 ("r-s4vectors" ,r-s4vectors)))
7118 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7119 (synopsis "Container for representing genomic ranges by sample")
7121 "The SummarizedExperiment container contains one or more assays, each
7122 represented by a matrix-like object of numeric or other mode. The rows
7123 typically represent genomic ranges of interest and the columns represent
7125 (license license:artistic2.0)))
7127 (define-public r-genomicalignments
7129 (name "r-genomicalignments")
7133 (uri (bioconductor-uri "GenomicAlignments" version))
7136 "0sw30lj11wv7ifzypqm04lcah987crqwvj48wz3flaw3biw41zfi"))))
7138 `((upstream-name . "GenomicAlignments")))
7139 (build-system r-build-system)
7141 `(("r-biocgenerics" ,r-biocgenerics)
7142 ("r-biocparallel" ,r-biocparallel)
7143 ("r-biostrings" ,r-biostrings)
7144 ("r-genomeinfodb" ,r-genomeinfodb)
7145 ("r-genomicranges" ,r-genomicranges)
7146 ("r-iranges" ,r-iranges)
7147 ("r-rsamtools" ,r-rsamtools)
7148 ("r-s4vectors" ,r-s4vectors)
7149 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7150 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7151 (synopsis "Representation and manipulation of short genomic alignments")
7153 "This package provides efficient containers for storing and manipulating
7154 short genomic alignments (typically obtained by aligning short reads to a
7155 reference genome). This includes read counting, computing the coverage,
7156 junction detection, and working with the nucleotide content of the
7158 (license license:artistic2.0)))
7160 (define-public r-rtracklayer
7162 (name "r-rtracklayer")
7166 (uri (bioconductor-uri "rtracklayer" version))
7169 "12al1ygzy9p4myxa1fd817m28x2fj6f863znk9bw3hp7knbi98dh"))))
7170 (build-system r-build-system)
7173 (modify-phases %standard-phases
7174 (add-after 'unpack 'use-system-zlib
7176 (substitute* "DESCRIPTION"
7177 ((" zlibbioc,") ""))
7178 (substitute* "NAMESPACE"
7179 (("import\\(zlibbioc\\)") ""))
7184 `(("r-biocgenerics" ,r-biocgenerics)
7185 ("r-biostrings" ,r-biostrings)
7186 ("r-genomeinfodb" ,r-genomeinfodb)
7187 ("r-genomicalignments" ,r-genomicalignments)
7188 ("r-genomicranges" ,r-genomicranges)
7189 ("r-iranges" ,r-iranges)
7190 ("r-rcurl" ,r-rcurl)
7191 ("r-rsamtools" ,r-rsamtools)
7192 ("r-s4vectors" ,r-s4vectors)
7194 ("r-xvector" ,r-xvector)))
7195 (home-page "https://bioconductor.org/packages/rtracklayer")
7196 (synopsis "R interface to genome browsers and their annotation tracks")
7198 "rtracklayer is an extensible framework for interacting with multiple
7199 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7200 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7201 built-in). The user may export/import tracks to/from the supported browsers,
7202 as well as query and modify the browser state, such as the current viewport.")
7203 (license license:artistic2.0)))
7205 (define-public r-genomicfeatures
7207 (name "r-genomicfeatures")
7211 (uri (bioconductor-uri "GenomicFeatures" version))
7214 "1khjvq1ffhqavkwf8n7bilknci60lxbg52icrcf2vnb9k8rlpghs"))))
7216 `((upstream-name . "GenomicFeatures")))
7217 (build-system r-build-system)
7219 `(("r-annotationdbi" ,r-annotationdbi)
7220 ("r-biobase" ,r-biobase)
7221 ("r-biocgenerics" ,r-biocgenerics)
7222 ("r-biomart" ,r-biomart)
7223 ("r-biostrings" ,r-biostrings)
7225 ("r-genomeinfodb" ,r-genomeinfodb)
7226 ("r-genomicranges" ,r-genomicranges)
7227 ("r-iranges" ,r-iranges)
7228 ("r-rcurl" ,r-rcurl)
7229 ("r-rsqlite" ,r-rsqlite)
7230 ("r-rmysql" ,r-rmysql)
7231 ("r-rtracklayer" ,r-rtracklayer)
7232 ("r-s4vectors" ,r-s4vectors)
7233 ("r-xvector" ,r-xvector)))
7234 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7235 (synopsis "Tools for working with transcript centric annotations")
7237 "This package provides a set of tools and methods for making and
7238 manipulating transcript centric annotations. With these tools the user can
7239 easily download the genomic locations of the transcripts, exons and cds of a
7240 given organism, from either the UCSC Genome Browser or a BioMart
7241 database (more sources will be supported in the future). This information is
7242 then stored in a local database that keeps track of the relationship between
7243 transcripts, exons, cds and genes. Flexible methods are provided for
7244 extracting the desired features in a convenient format.")
7245 (license license:artistic2.0)))
7247 (define-public r-go-db
7253 (uri (string-append "https://www.bioconductor.org/packages/"
7254 "release/data/annotation/src/contrib/GO.db_"
7258 "02cj8kqi5w39jwcs8gp1dgj08sah262ppxnkz4h3qd0w191y8yyl"))))
7260 `((upstream-name . "GO.db")))
7261 (build-system r-build-system)
7263 `(("r-annotationdbi" ,r-annotationdbi)))
7264 (home-page "https://bioconductor.org/packages/GO.db")
7265 (synopsis "Annotation maps describing the entire Gene Ontology")
7267 "The purpose of this GO.db annotation package is to provide detailed
7268 information about the latest version of the Gene Ontologies.")
7269 (license license:artistic2.0)))
7271 (define-public r-graph
7277 (uri (bioconductor-uri "graph" version))
7280 "15aajjp8h2z14p80c8hyd4rrmr9vqsm7bvwb989jxjl4k6g52an1"))))
7281 (build-system r-build-system)
7283 `(("r-biocgenerics" ,r-biocgenerics)))
7284 (home-page "https://bioconductor.org/packages/graph")
7285 (synopsis "Handle graph data structures in R")
7287 "This package implements some simple graph handling capabilities for R.")
7288 (license license:artistic2.0)))
7290 (define-public r-topgo
7296 (uri (bioconductor-uri "topGO" version))
7299 "1hqffz5qp7glxdvjp37005g8qk5nam3f9wpf6d1wjnzpar04f3dz"))))
7301 `((upstream-name . "topGO")))
7302 (build-system r-build-system)
7304 `(("r-annotationdbi" ,r-annotationdbi)
7306 ("r-biobase" ,r-biobase)
7307 ("r-biocgenerics" ,r-biocgenerics)
7308 ("r-go-db" ,r-go-db)
7309 ("r-graph" ,r-graph)
7310 ("r-lattice" ,r-lattice)
7311 ("r-matrixstats" ,r-matrixstats)
7312 ("r-sparsem" ,r-sparsem)))
7313 (home-page "https://bioconductor.org/packages/topGO")
7314 (synopsis "Enrichment analysis for gene ontology")
7316 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7317 terms while accounting for the topology of the GO graph. Different test
7318 statistics and different methods for eliminating local similarities and
7319 dependencies between GO terms can be implemented and applied.")
7320 ;; Any version of the LGPL applies.
7321 (license license:lgpl2.1+)))
7323 (define-public r-bsgenome
7329 (uri (bioconductor-uri "BSgenome" version))
7332 "1jbzq7lm2iajajn2bifxnkss0k9fdvgqr30mral17cbhp5f6w4lq"))))
7334 `((upstream-name . "BSgenome")))
7335 (build-system r-build-system)
7337 `(("r-biocgenerics" ,r-biocgenerics)
7338 ("r-biostrings" ,r-biostrings)
7339 ("r-genomeinfodb" ,r-genomeinfodb)
7340 ("r-genomicranges" ,r-genomicranges)
7341 ("r-iranges" ,r-iranges)
7342 ("r-rsamtools" ,r-rsamtools)
7343 ("r-rtracklayer" ,r-rtracklayer)
7344 ("r-s4vectors" ,r-s4vectors)
7345 ("r-xvector" ,r-xvector)))
7346 (home-page "https://bioconductor.org/packages/BSgenome")
7347 (synopsis "Infrastructure for Biostrings-based genome data packages")
7349 "This package provides infrastructure shared by all Biostrings-based
7350 genome data packages and support for efficient SNP representation.")
7351 (license license:artistic2.0)))
7353 (define-public r-bsgenome-hsapiens-1000genomes-hs37d5
7355 (name "r-bsgenome-hsapiens-1000genomes-hs37d5")
7359 ;; We cannot use bioconductor-uri here because this tarball is
7360 ;; located under "data/annotation/" instead of "bioc/".
7361 (uri (string-append "https://www.bioconductor.org/packages/"
7362 "release/data/annotation/src/contrib/"
7363 "BSgenome.Hsapiens.1000genomes.hs37d5_"
7367 "1cg0g5fqmsvwyw2p9hp2yy4ilk21jkbbrnpgqvb5c36ihjwvc7sr"))))
7369 `((upstream-name . "BSgenome.Hsapiens.1000genomes.hs37d5")))
7370 (build-system r-build-system)
7371 ;; As this package provides little more than a very large data file it
7372 ;; doesn't make sense to build substitutes.
7373 (arguments `(#:substitutable? #f))
7375 `(("r-bsgenome" ,r-bsgenome)))
7377 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.1000genomes.hs37d5/")
7378 (synopsis "Full genome sequences for Homo sapiens")
7380 "This package provides full genome sequences for Homo sapiens from
7381 1000genomes phase2 reference genome sequence (hs37d5), based on NCBI GRCh37.")
7382 (license license:artistic2.0)))
7384 (define-public r-impute
7390 (uri (bioconductor-uri "impute" version))
7393 "0b8r4swvyx3cjcc2ky8yn0ncpzlbi1pgfsn3wpbjmhh7sqrffm2n"))))
7395 `(("gfortran" ,gfortran)))
7396 (build-system r-build-system)
7397 (home-page "https://bioconductor.org/packages/impute")
7398 (synopsis "Imputation for microarray data")
7400 "This package provides a function to impute missing gene expression
7401 microarray data, using nearest neighbor averaging.")
7402 (license license:gpl2+)))
7404 (define-public r-seqpattern
7406 (name "r-seqpattern")
7410 (uri (bioconductor-uri "seqPattern" version))
7413 "1kcm5w83q7w0v0vs7nyp4gq5z86c6n6pqy9zmyyhxcrns7f597pm"))))
7415 `((upstream-name . "seqPattern")))
7416 (build-system r-build-system)
7418 `(("r-biostrings" ,r-biostrings)
7419 ("r-genomicranges" ,r-genomicranges)
7420 ("r-iranges" ,r-iranges)
7421 ("r-kernsmooth" ,r-kernsmooth)
7422 ("r-plotrix" ,r-plotrix)))
7423 (home-page "https://bioconductor.org/packages/seqPattern")
7424 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7426 "This package provides tools to visualize oligonucleotide patterns and
7427 sequence motif occurrences across a large set of sequences centred at a common
7428 reference point and sorted by a user defined feature.")
7429 (license license:gpl3+)))
7431 (define-public r-genomation
7433 (name "r-genomation")
7437 (uri (bioconductor-uri "genomation" version))
7440 "1ddd8c9w1f1i1ga9rpbwiic8rsaws1chdxx4j38bpyaiy4zhz1ca"))))
7441 (build-system r-build-system)
7443 `(("r-biostrings" ,r-biostrings)
7444 ("r-bsgenome" ,r-bsgenome)
7445 ("r-data-table" ,r-data-table)
7446 ("r-genomeinfodb" ,r-genomeinfodb)
7447 ("r-genomicalignments" ,r-genomicalignments)
7448 ("r-genomicranges" ,r-genomicranges)
7449 ("r-ggplot2" ,r-ggplot2)
7450 ("r-gridbase" ,r-gridbase)
7451 ("r-impute" ,r-impute)
7452 ("r-iranges" ,r-iranges)
7453 ("r-matrixstats" ,r-matrixstats)
7454 ("r-plotrix" ,r-plotrix)
7457 ("r-readr" ,r-readr)
7458 ("r-reshape2" ,r-reshape2)
7459 ("r-rsamtools" ,r-rsamtools)
7460 ("r-rtracklayer" ,r-rtracklayer)
7461 ("r-runit" ,r-runit)
7462 ("r-s4vectors" ,r-s4vectors)
7463 ("r-seqpattern" ,r-seqpattern)))
7464 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7465 (synopsis "Summary, annotation and visualization of genomic data")
7467 "This package provides a package for summary and annotation of genomic
7468 intervals. Users can visualize and quantify genomic intervals over
7469 pre-defined functional regions, such as promoters, exons, introns, etc. The
7470 genomic intervals represent regions with a defined chromosome position, which
7471 may be associated with a score, such as aligned reads from HT-seq experiments,
7472 TF binding sites, methylation scores, etc. The package can use any tabular
7473 genomic feature data as long as it has minimal information on the locations of
7474 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7475 (license license:artistic2.0)))
7477 (define-public r-genomationdata
7479 (name "r-genomationdata")
7483 ;; We cannot use bioconductor-uri here because this tarball is
7484 ;; located under "data/annotation/" instead of "bioc/".
7485 (uri (string-append "https://bioconductor.org/packages/"
7486 "release/data/experiment/src/contrib/"
7487 "genomationData_" version ".tar.gz"))
7490 "0h7g5x3kyb50qlblz5hc85lfm6n6f5nb68i146way3ggs04sqvla"))))
7491 (build-system r-build-system)
7492 ;; As this package provides little more than large data files, it doesn't
7493 ;; make sense to build substitutes.
7494 (arguments `(#:substitutable? #f))
7496 `(("r-knitr" ,r-knitr)))
7497 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7498 (synopsis "Experimental data for use with the genomation package")
7500 "This package contains experimental genetic data for use with the
7501 genomation package. Included are Chip Seq, Methylation and Cage data,
7502 downloaded from Encode.")
7503 (license license:gpl3+)))
7505 (define-public r-org-hs-eg-db
7507 (name "r-org-hs-eg-db")
7511 ;; We cannot use bioconductor-uri here because this tarball is
7512 ;; located under "data/annotation/" instead of "bioc/".
7513 (uri (string-append "https://www.bioconductor.org/packages/"
7514 "release/data/annotation/src/contrib/"
7515 "org.Hs.eg.db_" version ".tar.gz"))
7518 "1v6wa5613cjq59xd7x1qz8lr9nb2abm9abl2cci1khrnrlpla927"))))
7520 `((upstream-name . "org.Hs.eg.db")))
7521 (build-system r-build-system)
7523 `(("r-annotationdbi" ,r-annotationdbi)))
7524 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
7525 (synopsis "Genome wide annotation for Human")
7527 "This package contains genome-wide annotations for Human, primarily based
7528 on mapping using Entrez Gene identifiers.")
7529 (license license:artistic2.0)))
7531 (define-public r-org-ce-eg-db
7533 (name "r-org-ce-eg-db")
7537 ;; We cannot use bioconductor-uri here because this tarball is
7538 ;; located under "data/annotation/" instead of "bioc/".
7539 (uri (string-append "https://www.bioconductor.org/packages/"
7540 "release/data/annotation/src/contrib/"
7541 "org.Ce.eg.db_" version ".tar.gz"))
7544 "12llfzrrc09kj2wzbisdspv38qzkzgpsbn8kv7qkwg746k3pq436"))))
7546 `((upstream-name . "org.Ce.eg.db")))
7547 (build-system r-build-system)
7549 `(("r-annotationdbi" ,r-annotationdbi)))
7550 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
7551 (synopsis "Genome wide annotation for Worm")
7553 "This package provides mappings from Entrez gene identifiers to various
7554 annotations for the genome of the model worm Caenorhabditis elegans.")
7555 (license license:artistic2.0)))
7557 (define-public r-org-dm-eg-db
7559 (name "r-org-dm-eg-db")
7563 ;; We cannot use bioconductor-uri here because this tarball is
7564 ;; located under "data/annotation/" instead of "bioc/".
7565 (uri (string-append "https://www.bioconductor.org/packages/"
7566 "release/data/annotation/src/contrib/"
7567 "org.Dm.eg.db_" version ".tar.gz"))
7570 "1vzbphbrh1cf7xi5cksia9xy9a9l42js2z2qsajvjxvddiphrb7j"))))
7572 `((upstream-name . "org.Dm.eg.db")))
7573 (build-system r-build-system)
7575 `(("r-annotationdbi" ,r-annotationdbi)))
7576 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
7577 (synopsis "Genome wide annotation for Fly")
7579 "This package provides mappings from Entrez gene identifiers to various
7580 annotations for the genome of the model fruit fly Drosophila melanogaster.")
7581 (license license:artistic2.0)))
7583 (define-public r-org-mm-eg-db
7585 (name "r-org-mm-eg-db")
7589 ;; We cannot use bioconductor-uri here because this tarball is
7590 ;; located under "data/annotation/" instead of "bioc/".
7591 (uri (string-append "https://www.bioconductor.org/packages/"
7592 "release/data/annotation/src/contrib/"
7593 "org.Mm.eg.db_" version ".tar.gz"))
7596 "1lykjqjaf01fmgg3cvfcvwd5xjq6zc5vbxnm5r4l32fzvl89q50c"))))
7598 `((upstream-name . "org.Mm.eg.db")))
7599 (build-system r-build-system)
7601 `(("r-annotationdbi" ,r-annotationdbi)))
7602 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
7603 (synopsis "Genome wide annotation for Mouse")
7605 "This package provides mappings from Entrez gene identifiers to various
7606 annotations for the genome of the model mouse Mus musculus.")
7607 (license license:artistic2.0)))
7609 (define-public r-seqlogo
7616 (uri (bioconductor-uri "seqLogo" version))
7619 "1ql4q4vx0j61a893dqc3c8zxmgs8sqhy3j1qhyfdvbd01vw9w1kq"))))
7620 (properties `((upstream-name . "seqLogo")))
7621 (build-system r-build-system)
7622 (home-page "https://bioconductor.org/packages/seqLogo")
7623 (synopsis "Sequence logos for DNA sequence alignments")
7625 "seqLogo takes the position weight matrix of a DNA sequence motif and
7626 plots the corresponding sequence logo as introduced by Schneider and
7628 (license license:lgpl2.0+)))
7630 (define-public r-bsgenome-hsapiens-ucsc-hg19
7632 (name "r-bsgenome-hsapiens-ucsc-hg19")
7636 ;; We cannot use bioconductor-uri here because this tarball is
7637 ;; located under "data/annotation/" instead of "bioc/".
7638 (uri (string-append "https://www.bioconductor.org/packages/"
7639 "release/data/annotation/src/contrib/"
7640 "BSgenome.Hsapiens.UCSC.hg19_"
7644 "1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
7646 `((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
7647 (build-system r-build-system)
7648 ;; As this package provides little more than a very large data file it
7649 ;; doesn't make sense to build substitutes.
7650 (arguments `(#:substitutable? #f))
7652 `(("r-bsgenome" ,r-bsgenome)))
7654 "https://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
7655 (synopsis "Full genome sequences for Homo sapiens")
7657 "This package provides full genome sequences for Homo sapiens as provided
7658 by UCSC (hg19, February 2009) and stored in Biostrings objects.")
7659 (license license:artistic2.0)))
7661 (define-public r-bsgenome-mmusculus-ucsc-mm9
7663 (name "r-bsgenome-mmusculus-ucsc-mm9")
7667 ;; We cannot use bioconductor-uri here because this tarball is
7668 ;; located under "data/annotation/" instead of "bioc/".
7669 (uri (string-append "https://www.bioconductor.org/packages/"
7670 "release/data/annotation/src/contrib/"
7671 "BSgenome.Mmusculus.UCSC.mm9_"
7675 "1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
7677 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
7678 (build-system r-build-system)
7679 ;; As this package provides little more than a very large data file it
7680 ;; doesn't make sense to build substitutes.
7681 (arguments `(#:substitutable? #f))
7683 `(("r-bsgenome" ,r-bsgenome)))
7685 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
7686 (synopsis "Full genome sequences for Mouse")
7688 "This package provides full genome sequences for Mus musculus (Mouse) as
7689 provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
7690 (license license:artistic2.0)))
7692 (define-public r-bsgenome-mmusculus-ucsc-mm10
7694 (name "r-bsgenome-mmusculus-ucsc-mm10")
7698 ;; We cannot use bioconductor-uri here because this tarball is
7699 ;; located under "data/annotation/" instead of "bioc/".
7700 (uri (string-append "https://www.bioconductor.org/packages/"
7701 "release/data/annotation/src/contrib/"
7702 "BSgenome.Mmusculus.UCSC.mm10_"
7706 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
7708 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
7709 (build-system r-build-system)
7710 ;; As this package provides little more than a very large data file it
7711 ;; doesn't make sense to build substitutes.
7712 (arguments `(#:substitutable? #f))
7714 `(("r-bsgenome" ,r-bsgenome)))
7716 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
7717 (synopsis "Full genome sequences for Mouse")
7719 "This package provides full genome sequences for Mus
7720 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
7721 in Biostrings objects.")
7722 (license license:artistic2.0)))
7724 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
7726 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
7730 ;; We cannot use bioconductor-uri here because this tarball is
7731 ;; located under "data/annotation/" instead of "bioc/".
7732 (uri (string-append "https://www.bioconductor.org/packages/"
7733 "release/data/annotation/src/contrib/"
7734 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
7738 "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
7740 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
7741 (build-system r-build-system)
7742 ;; As this package provides little more than a very large data file it
7743 ;; doesn't make sense to build substitutes.
7744 (arguments `(#:substitutable? #f))
7746 `(("r-bsgenome" ,r-bsgenome)
7747 ("r-genomicfeatures" ,r-genomicfeatures)
7748 ("r-annotationdbi" ,r-annotationdbi)))
7750 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
7751 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
7753 "This package loads a TxDb object, which is an R interface to
7754 prefabricated databases contained in this package. This package provides
7755 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
7756 based on the knownGene track.")
7757 (license license:artistic2.0)))
7759 (define-public r-bsgenome-celegans-ucsc-ce6
7761 (name "r-bsgenome-celegans-ucsc-ce6")
7765 ;; We cannot use bioconductor-uri here because this tarball is
7766 ;; located under "data/annotation/" instead of "bioc/".
7767 (uri (string-append "https://www.bioconductor.org/packages/"
7768 "release/data/annotation/src/contrib/"
7769 "BSgenome.Celegans.UCSC.ce6_"
7773 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
7775 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
7776 (build-system r-build-system)
7777 ;; As this package provides little more than a very large data file it
7778 ;; doesn't make sense to build substitutes.
7779 (arguments `(#:substitutable? #f))
7781 `(("r-bsgenome" ,r-bsgenome)))
7783 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
7784 (synopsis "Full genome sequences for Worm")
7786 "This package provides full genome sequences for Caenorhabditis
7787 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
7789 (license license:artistic2.0)))
7791 (define-public r-bsgenome-celegans-ucsc-ce10
7793 (name "r-bsgenome-celegans-ucsc-ce10")
7797 ;; We cannot use bioconductor-uri here because this tarball is
7798 ;; located under "data/annotation/" instead of "bioc/".
7799 (uri (string-append "https://www.bioconductor.org/packages/"
7800 "release/data/annotation/src/contrib/"
7801 "BSgenome.Celegans.UCSC.ce10_"
7805 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
7807 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
7808 (build-system r-build-system)
7809 ;; As this package provides little more than a very large data file it
7810 ;; doesn't make sense to build substitutes.
7811 (arguments `(#:substitutable? #f))
7813 `(("r-bsgenome" ,r-bsgenome)))
7815 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
7816 (synopsis "Full genome sequences for Worm")
7818 "This package provides full genome sequences for Caenorhabditis
7819 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
7821 (license license:artistic2.0)))
7823 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
7825 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
7829 ;; We cannot use bioconductor-uri here because this tarball is
7830 ;; located under "data/annotation/" instead of "bioc/".
7831 (uri (string-append "https://www.bioconductor.org/packages/"
7832 "release/data/annotation/src/contrib/"
7833 "BSgenome.Dmelanogaster.UCSC.dm3_"
7837 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
7839 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
7840 (build-system r-build-system)
7841 ;; As this package provides little more than a very large data file it
7842 ;; doesn't make sense to build substitutes.
7843 (arguments `(#:substitutable? #f))
7845 `(("r-bsgenome" ,r-bsgenome)))
7847 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
7848 (synopsis "Full genome sequences for Fly")
7850 "This package provides full genome sequences for Drosophila
7851 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
7852 Biostrings objects.")
7853 (license license:artistic2.0)))
7855 (define-public r-motifrg
7862 (uri (bioconductor-uri "motifRG" version))
7865 "193zl2rlzwxv9p9q5i7rilj3w05ndqfyp9bdpvagp5s5cin4hf44"))))
7866 (properties `((upstream-name . "motifRG")))
7867 (build-system r-build-system)
7869 `(("r-biostrings" ,r-biostrings)
7870 ("r-bsgenome" ,r-bsgenome)
7871 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
7872 ("r-iranges" ,r-iranges)
7873 ("r-seqlogo" ,r-seqlogo)
7874 ("r-xvector" ,r-xvector)))
7875 (home-page "https://bioconductor.org/packages/motifRG")
7876 (synopsis "Discover motifs in high throughput sequencing data")
7878 "This package provides tools for discriminative motif discovery in high
7879 throughput genetic sequencing data sets using regression methods.")
7880 (license license:artistic2.0)))
7882 (define-public r-qtl
7889 (uri (string-append "mirror://cran/src/contrib/qtl_"
7893 "067az4v432zxp6lxck8d7vlh9w4r13r0mvw5zsglyaqwsh3d9sad"))))
7894 (build-system r-build-system)
7895 (home-page "http://rqtl.org/")
7896 (synopsis "R package for analyzing QTL experiments in genetics")
7897 (description "R/qtl is an extension library for the R statistics
7898 system. It is used to analyze experimental crosses for identifying
7899 genes contributing to variation in quantitative traits (so-called
7900 quantitative trait loci, QTLs).
7902 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
7903 identify genotyping errors, and to perform single-QTL and two-QTL,
7904 two-dimensional genome scans.")
7905 (license license:gpl3)))
7907 (define-public r-zlibbioc
7913 (uri (bioconductor-uri "zlibbioc" version))
7916 "1zr9hbh55hglfpy15cpxwmddxblhyb0an15953l3rbhmlh2vpy92"))))
7918 `((upstream-name . "zlibbioc")))
7919 (build-system r-build-system)
7920 (home-page "https://bioconductor.org/packages/zlibbioc")
7921 (synopsis "Provider for zlib-1.2.5 to R packages")
7922 (description "This package uses the source code of zlib-1.2.5 to create
7923 libraries for systems that do not have these available via other means.")
7924 (license license:artistic2.0)))
7926 (define-public r-r4rna
7933 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
7937 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
7938 (build-system r-build-system)
7940 `(("r-optparse" ,r-optparse)
7941 ("r-rcolorbrewer" ,r-rcolorbrewer)))
7942 (home-page "http://www.e-rna.org/r-chie/index.cgi")
7943 (synopsis "Analysis framework for RNA secondary structure")
7945 "The R4RNA package aims to be a general framework for the analysis of RNA
7946 secondary structure and comparative analysis in R.")
7947 (license license:gpl3+)))
7949 (define-public r-rhtslib
7956 (uri (bioconductor-uri "Rhtslib" version))
7959 "1dw3p44bfr0m7w39ckc2k37sjcp1zz0b9g12mr8am15jaj6v0q2j"))))
7960 (properties `((upstream-name . "Rhtslib")))
7961 (build-system r-build-system)
7963 `(("r-zlibbioc" ,r-zlibbioc)))
7967 `(("autoconf" ,autoconf)))
7968 (home-page "https://github.com/nhayden/Rhtslib")
7969 (synopsis "High-throughput sequencing library as an R package")
7971 "This package provides the HTSlib C library for high-throughput
7972 nucleotide sequence analysis. The package is primarily useful to developers
7973 of other R packages who wish to make use of HTSlib.")
7974 (license license:lgpl2.0+)))
7976 (define-public r-bamsignals
7978 (name "r-bamsignals")
7983 (uri (bioconductor-uri "bamsignals" version))
7986 "15id6mkj95skb4kfafvfs2j7ylydal60c3pspcl7llhwpq6vcqvl"))))
7987 (build-system r-build-system)
7989 `(("r-biocgenerics" ,r-biocgenerics)
7990 ("r-genomicranges" ,r-genomicranges)
7991 ("r-iranges" ,r-iranges)
7993 ("r-rhtslib" ,r-rhtslib)
7994 ("r-zlibbioc" ,r-zlibbioc)))
7997 (home-page "https://bioconductor.org/packages/bamsignals")
7998 (synopsis "Extract read count signals from bam files")
8000 "This package allows to efficiently obtain count vectors from indexed bam
8001 files. It counts the number of nucleotide sequence reads in given genomic
8002 ranges and it computes reads profiles and coverage profiles. It also handles
8004 (license license:gpl2+)))
8006 (define-public r-rcas
8012 (uri (string-append "https://github.com/BIMSBbioinfo/RCAS/archive/v"
8014 (file-name (string-append name "-" version ".tar.gz"))
8017 "1qgc7vi6fpzl440yg7jhiycg5q336kd4pxqzx10yx2zcq3bq3msg"))))
8018 (build-system r-build-system)
8020 `(("r-knitr" ,r-knitr)
8021 ("r-testthat" ,r-testthat)
8022 ;; During vignette building knitr checks that "pandoc-citeproc"
8024 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)))
8026 `(("r-data-table" ,r-data-table)
8027 ("r-biomart" ,r-biomart)
8028 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8029 ("r-org-ce-eg-db" ,r-org-ce-eg-db)
8030 ("r-org-dm-eg-db" ,r-org-dm-eg-db)
8031 ("r-org-mm-eg-db" ,r-org-mm-eg-db)
8032 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8033 ("r-bsgenome-mmusculus-ucsc-mm9" ,r-bsgenome-mmusculus-ucsc-mm9)
8034 ("r-bsgenome-celegans-ucsc-ce10" ,r-bsgenome-celegans-ucsc-ce10)
8035 ("r-bsgenome-dmelanogaster-ucsc-dm3" ,r-bsgenome-dmelanogaster-ucsc-dm3)
8036 ("r-topgo" ,r-topgo)
8038 ("r-pbapply" ,r-pbapply)
8039 ("r-plotly" ,r-plotly)
8040 ("r-plotrix" ,r-plotrix)
8041 ("r-motifrg" ,r-motifrg)
8042 ("r-genomation" ,r-genomation)
8043 ("r-genomicfeatures" ,r-genomicfeatures)
8044 ("r-rtracklayer" ,r-rtracklayer)
8045 ("r-rmarkdown" ,r-rmarkdown)))
8046 (synopsis "RNA-centric annotation system")
8048 "RCAS aims to be a standalone RNA-centric annotation system that provides
8049 intuitive reports and publication-ready graphics. This package provides the R
8050 library implementing most of the pipeline's features.")
8051 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8052 (license license:artistic2.0)))
8054 (define-public rcas-web
8061 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8062 "releases/download/v" version
8063 "/rcas-web-" version ".tar.gz"))
8066 "1p16frfys41a8yaa4gkm457nzkqhqs2pc3lkac0ds457w9w5j1gm"))))
8067 (build-system gnu-build-system)
8070 (modify-phases %standard-phases
8071 (add-after 'install 'wrap-executable
8072 (lambda* (#:key inputs outputs #:allow-other-keys)
8073 (let* ((out (assoc-ref outputs "out"))
8074 (json (assoc-ref inputs "guile-json"))
8075 (redis (assoc-ref inputs "guile-redis"))
8076 (path (string-append
8077 json "/share/guile/site/2.2:"
8078 redis "/share/guile/site/2.2")))
8079 (wrap-program (string-append out "/bin/rcas-web")
8080 `("GUILE_LOAD_PATH" ":" = (,path))
8081 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8082 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8085 `(("r-minimal" ,r-minimal)
8087 ("guile-next" ,guile-2.2)
8088 ("guile-json" ,guile-json)
8089 ("guile-redis" ,guile2.2-redis)))
8091 `(("pkg-config" ,pkg-config)))
8092 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8093 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8094 (description "This package provides a simple web interface for the
8095 @dfn{RNA-centric annotation system} (RCAS).")
8096 (license license:agpl3+)))
8098 (define-public r-mutationalpatterns
8100 (name "r-mutationalpatterns")
8105 (uri (bioconductor-uri "MutationalPatterns" version))
8108 "0sqbrswg8ylkjb9q3vqcb5ggwixynwj6hyv2n4sk7snyk61z3fq9"))))
8109 (build-system r-build-system)
8111 `(("r-biocgenerics" ,r-biocgenerics)
8112 ("r-biostrings" ,r-biostrings)
8113 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8114 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8115 ("r-genomicranges" ,r-genomicranges)
8116 ("r-genomeinfodb" ,r-genomeinfodb)
8117 ("r-ggplot2" ,r-ggplot2)
8118 ("r-gridextra" ,r-gridextra)
8119 ("r-iranges" ,r-iranges)
8122 ("r-pracma" ,r-pracma)
8123 ("r-reshape2" ,r-reshape2)
8124 ("r-cowplot" ,r-cowplot)
8125 ("r-ggdendro" ,r-ggdendro)
8126 ("r-s4vectors" ,r-s4vectors)
8127 ("r-summarizedexperiment" ,r-summarizedexperiment)
8128 ("r-variantannotation" ,r-variantannotation)))
8129 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8130 (synopsis "Extract and visualize mutational patterns in genomic data")
8131 (description "This package provides an extensive toolset for the
8132 characterization and visualization of a wide range of mutational patterns
8133 in SNV base substitution data.")
8134 (license license:expat)))
8136 (define-public r-wgcna
8143 (uri (cran-uri "WGCNA" version))
8146 "1vrc2k33a196hrrl7k0z534fp96vv0shmigcr65ny1q0v6lq0h6i"))))
8147 (properties `((upstream-name . "WGCNA")))
8148 (build-system r-build-system)
8150 `(("r-annotationdbi" ,r-annotationdbi)
8151 ("r-doparallel" ,r-doparallel)
8152 ("r-dynamictreecut" ,r-dynamictreecut)
8153 ("r-fastcluster" ,r-fastcluster)
8154 ("r-foreach" ,r-foreach)
8155 ("r-go-db" ,r-go-db)
8156 ("r-hmisc" ,r-hmisc)
8157 ("r-impute" ,r-impute)
8159 ("r-robust" ,r-robust)
8160 ("r-survival" ,r-survival)
8161 ("r-matrixstats" ,r-matrixstats)
8162 ("r-preprocesscore" ,r-preprocesscore)))
8164 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8165 (synopsis "Weighted correlation network analysis")
8167 "This package provides functions necessary to perform Weighted
8168 Correlation Network Analysis on high-dimensional data. It includes functions
8169 for rudimentary data cleaning, construction and summarization of correlation
8170 networks, module identification and functions for relating both variables and
8171 modules to sample traits. It also includes a number of utility functions for
8172 data manipulation and visualization.")
8173 (license license:gpl2+)))
8175 (define-public r-chipkernels
8176 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8179 (name "r-chipkernels")
8180 (version (string-append "1.1-" revision "." (string-take commit 9)))
8185 (url "https://github.com/ManuSetty/ChIPKernels.git")
8187 (file-name (string-append name "-" version))
8190 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8191 (build-system r-build-system)
8193 `(("r-iranges" ,r-iranges)
8194 ("r-xvector" ,r-xvector)
8195 ("r-biostrings" ,r-biostrings)
8196 ("r-bsgenome" ,r-bsgenome)
8197 ("r-gtools" ,r-gtools)
8198 ("r-genomicranges" ,r-genomicranges)
8199 ("r-sfsmisc" ,r-sfsmisc)
8200 ("r-kernlab" ,r-kernlab)
8201 ("r-s4vectors" ,r-s4vectors)
8202 ("r-biocgenerics" ,r-biocgenerics)))
8203 (home-page "https://github.com/ManuSetty/ChIPKernels")
8204 (synopsis "Build string kernels for DNA Sequence analysis")
8205 (description "ChIPKernels is an R package for building different string
8206 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8207 must be built and this dictionary can be used for determining kernels for DNA
8209 (license license:gpl2+))))
8211 (define-public r-seqgl
8218 (uri (string-append "https://github.com/ManuSetty/SeqGL/"
8219 "archive/" version ".tar.gz"))
8220 (file-name (string-append name "-" version ".tar.gz"))
8223 "0pnk1p3sci5yipyc8xnb6jbmydpl80fld927xgnbcv104hy8h8yh"))))
8224 (build-system r-build-system)
8226 `(("r-biostrings" ,r-biostrings)
8227 ("r-chipkernels" ,r-chipkernels)
8228 ("r-genomicranges" ,r-genomicranges)
8229 ("r-spams" ,r-spams)
8230 ("r-wgcna" ,r-wgcna)
8231 ("r-fastcluster" ,r-fastcluster)))
8232 (home-page "https://github.com/ManuSetty/SeqGL")
8233 (synopsis "Group lasso for Dnase/ChIP-seq data")
8234 (description "SeqGL is a group lasso based algorithm to extract
8235 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8236 This package presents a method which uses group lasso to discriminate between
8237 bound and non bound genomic regions to accurately identify transcription
8238 factors bound at the specific regions.")
8239 (license license:gpl2+)))
8241 (define-public r-gkmsvm
8248 (uri (cran-uri "gkmSVM" version))
8251 "1zpxgxmf2nd5j5wn00ps6kfxr8wxh7d1swr1rr4spq7sj5z5z0k0"))))
8252 (properties `((upstream-name . "gkmSVM")))
8253 (build-system r-build-system)
8255 `(("r-biocgenerics" ,r-biocgenerics)
8256 ("r-biostrings" ,r-biostrings)
8257 ("r-genomeinfodb" ,r-genomeinfodb)
8258 ("r-genomicranges" ,r-genomicranges)
8259 ("r-iranges" ,r-iranges)
8260 ("r-kernlab" ,r-kernlab)
8263 ("r-rtracklayer" ,r-rtracklayer)
8264 ("r-s4vectors" ,r-s4vectors)
8265 ("r-seqinr" ,r-seqinr)))
8266 (home-page "http://cran.r-project.org/web/packages/gkmSVM")
8267 (synopsis "Gapped-kmer support vector machine")
8269 "This R package provides tools for training gapped-kmer SVM classifiers
8270 for DNA and protein sequences. This package supports several sequence
8271 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8272 (license license:gpl2+)))
8274 (define-public r-tximport
8280 (uri (bioconductor-uri "tximport" version))
8283 "1gyqcm91hxg1kgjqcz2qw1n56yp9pymjzs50rwcpb2893dr8sp2h"))))
8284 (build-system r-build-system)
8285 (home-page "https://bioconductor.org/packages/tximport")
8286 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8288 "This package provides tools to import transcript-level abundance,
8289 estimated counts and transcript lengths, and to summarize them into matrices
8290 for use with downstream gene-level analysis packages. Average transcript
8291 length, weighted by sample-specific transcript abundance estimates, is
8292 provided as a matrix which can be used as an offset for different expression
8293 of gene-level counts.")
8294 (license license:gpl2+)))
8296 (define-public r-rhdf5
8302 (uri (bioconductor-uri "rhdf5" version))
8305 "145858qg1xan6imxcbprzq3yn3mdf532aahdr6cibvdjg47hs4c1"))))
8306 (build-system r-build-system)
8309 (modify-phases %standard-phases
8310 (add-after 'unpack 'unpack-smallhdf5
8311 (lambda* (#:key outputs #:allow-other-keys)
8312 (system* "tar" "-xzvf"
8313 "src/hdf5source/hdf5small.tgz" "-C" "src/" )
8314 (substitute* "src/Makevars"
8315 (("^.*cd hdf5source &&.*$") "")
8316 (("^.*gunzip -dc hdf5small.tgz.*$") "")
8317 (("^.*rm -rf hdf5.*$") "")
8318 (("^.*mv hdf5source/hdf5 ..*$") ""))
8319 (substitute* "src/hdf5/configure"
8323 `(("r-zlibbioc" ,r-zlibbioc)))
8327 (home-page "https://bioconductor.org/packages/rhdf5")
8328 (synopsis "HDF5 interface to R")
8330 "This R/Bioconductor package provides an interface between HDF5 and R.
8331 HDF5's main features are the ability to store and access very large and/or
8332 complex datasets and a wide variety of metadata on mass storage (disk) through
8333 a completely portable file format. The rhdf5 package is thus suited for the
8334 exchange of large and/or complex datasets between R and other software
8335 package, and for letting R applications work on datasets that are larger than
8336 the available RAM.")
8337 (license license:artistic2.0)))
8339 (define-public r-annotationfilter
8341 (name "r-annotationfilter")
8345 (uri (bioconductor-uri "AnnotationFilter" version))
8348 "04zf864c1fvdlaay2r5cn30fc1n5i3czh31fs62qlrvs61wjiscs"))))
8350 `((upstream-name . "AnnotationFilter")))
8351 (build-system r-build-system)
8353 `(("r-genomicranges" ,r-genomicranges)
8354 ("r-lazyeval" ,r-lazyeval)))
8355 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8356 (synopsis "Facilities for filtering Bioconductor annotation resources")
8358 "This package provides classes and other infrastructure to implement
8359 filters for manipulating Bioconductor annotation resources. The filters are
8360 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8361 (license license:artistic2.0)))
8363 (define-public emboss
8369 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8370 (version-major+minor version) ".0/"
8371 "EMBOSS-" version ".tar.gz"))
8374 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8375 (build-system gnu-build-system)
8378 (list (string-append "--with-hpdf="
8379 (assoc-ref %build-inputs "libharu")))
8381 (modify-phases %standard-phases
8382 (add-after 'unpack 'fix-checks
8384 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8385 ;; and zlib, but assume that they are all found at the same
8387 (substitute* "configure.in"
8388 (("CHECK_PNGDRIVER")
8389 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8390 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8391 AM_CONDITIONAL(AMPNG, true)"))
8393 (add-after 'fix-checks 'disable-update-check
8395 ;; At build time there is no connection to the Internet, so
8396 ;; looking for updates will not work.
8397 (substitute* "Makefile.am"
8398 (("\\$\\(bindir\\)/embossupdate") ""))
8400 (add-after 'disable-update-check 'autogen
8401 (lambda _ (zero? (system* "autoreconf" "-vif")))))))
8407 ("libharu" ,libharu)
8410 `(("autoconf" ,autoconf)
8411 ("automake" ,automake)
8412 ("libtool" ,libtool)
8413 ("pkg-config" ,pkg-config)))
8414 (home-page "http://emboss.sourceforge.net")
8415 (synopsis "Molecular biology analysis suite")
8416 (description "EMBOSS is the \"European Molecular Biology Open Software
8417 Suite\". EMBOSS is an analysis package specially developed for the needs of
8418 the molecular biology (e.g. EMBnet) user community. The software
8419 automatically copes with data in a variety of formats and even allows
8420 transparent retrieval of sequence data from the web. It also provides a
8421 number of libraries for the development of software in the field of molecular
8422 biology. EMBOSS also integrates a range of currently available packages and
8423 tools for sequence analysis into a seamless whole.")
8424 (license license:gpl2+)))
8427 (let ((revision "1")
8428 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8431 ;; The version is 2.13.0 even though no release archives have been
8432 ;; published as yet.
8433 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8437 (url "https://github.com/arq5x/bits.git")
8439 (file-name (string-append name "-" version "-checkout"))
8442 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8443 (build-system gnu-build-system)
8445 `(#:tests? #f ;no tests included
8447 (modify-phases %standard-phases
8449 (add-after 'unpack 'remove-cuda
8451 (substitute* "Makefile"
8453 (("(bits_test_intersections) \\\\" _ match) match))
8456 (lambda* (#:key outputs #:allow-other-keys)
8458 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8463 (home-page "https://github.com/arq5x/bits")
8464 (synopsis "Implementation of binary interval search algorithm")
8465 (description "This package provides an implementation of the
8466 BITS (Binary Interval Search) algorithm, an approach to interval set
8467 intersection. It is especially suited for the comparison of diverse genomic
8468 datasets and the exploration of large datasets of genome
8469 intervals (e.g. genes, sequence alignments).")
8470 (license license:gpl2))))
8472 (define-public piranha
8473 ;; There is no release tarball for the latest version. The latest commit is
8474 ;; older than one year at the time of this writing.
8475 (let ((revision "1")
8476 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8479 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8483 (url "https://github.com/smithlabcode/piranha.git")
8487 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8488 (build-system gnu-build-system)
8490 `(#:test-target "test"
8492 (modify-phases %standard-phases
8493 (add-after 'unpack 'copy-smithlab-cpp
8494 (lambda* (#:key inputs #:allow-other-keys)
8495 (for-each (lambda (file)
8496 (install-file file "./src/smithlab_cpp/"))
8497 (find-files (assoc-ref inputs "smithlab-cpp")))
8499 (add-after 'install 'install-to-store
8500 (lambda* (#:key outputs #:allow-other-keys)
8501 (let* ((out (assoc-ref outputs "out"))
8502 (bin (string-append out "/bin")))
8503 (for-each (lambda (file)
8504 (install-file file bin))
8505 (find-files "bin" ".*")))
8508 (list (string-append "--with-bam_tools_headers="
8509 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8510 (string-append "--with-bam_tools_library="
8511 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8513 `(("bamtools" ,bamtools)
8514 ("samtools" ,samtools-0.1)
8517 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8521 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8523 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8526 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8528 `(("python" ,python-2)))
8529 (home-page "https://github.com/smithlabcode/piranha")
8530 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8532 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8533 RIP-seq experiments. It takes input in BED or BAM format and identifies
8534 regions of statistically significant read enrichment. Additional covariates
8535 may optionally be provided to further inform the peak-calling process.")
8536 (license license:gpl3+))))
8544 (uri (string-append "https://pypi.python.org/packages/source/P"
8545 "/PePr/PePr-" version ".tar.gz"))
8548 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8549 (build-system python-build-system)
8551 `(#:python ,python-2 ; python2 only
8552 #:tests? #f)) ; no tests included
8554 `(("python2-numpy" ,python2-numpy)
8555 ("python2-scipy" ,python2-scipy)
8556 ("python2-pysam" ,python2-pysam)))
8557 (home-page "https://github.com/shawnzhangyx/PePr")
8558 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8560 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8561 that is primarily designed for data with biological replicates. It uses a
8562 negative binomial distribution to model the read counts among the samples in
8563 the same group, and look for consistent differences between ChIP and control
8564 group or two ChIP groups run under different conditions.")
8565 (license license:gpl3+)))
8567 (define-public filevercmp
8568 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8571 (version (string-append "0-1." (string-take commit 7)))
8574 (uri (string-append "https://github.com/ekg/filevercmp/archive/"
8576 (file-name (string-append name "-" version ".tar.gz"))
8578 (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
8579 (build-system gnu-build-system)
8581 `(#:tests? #f ; There are no tests to run.
8583 (modify-phases %standard-phases
8584 (delete 'configure) ; There is no configure phase.
8586 (lambda* (#:key outputs #:allow-other-keys)
8587 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8588 (install-file "filevercmp" bin)))))))
8589 (home-page "https://github.com/ekg/filevercmp")
8590 (synopsis "This program compares version strings")
8591 (description "This program compares version strings. It intends to be a
8592 replacement for strverscmp.")
8593 (license license:gpl3+))))
8595 (define-public multiqc
8602 (uri (pypi-uri "multiqc" version))
8605 "0fx1sx53znbgzfhbbiyd8j6cg5llpcsl5q5c45jy2c81d12piqfd"))))
8606 (build-system python-build-system)
8608 `(("python-enum34" ,python-enum34)
8609 ("python-jinja2" ,python-jinja2)
8610 ("python-simplejson" ,python-simplejson)
8611 ("python-pyyaml" ,python-pyyaml)
8612 ("python-click" ,python-click)
8613 ("python-spectra" ,python-spectra)
8614 ("python-requests" ,python-requests)
8615 ("python-markdown" ,python-markdown)
8616 ("python-lzstring" ,python-lzstring)
8617 ("python-matplotlib" ,python-matplotlib)
8618 ("python-numpy" ,python-numpy)
8619 ;; MultQC checks for the presence of nose at runtime.
8620 ("python-nose" ,python-nose)))
8621 (home-page "http://multiqc.info")
8622 (synopsis "Aggregate bioinformatics analysis reports")
8624 "MultiQC is a tool to aggregate bioinformatics results across many
8625 samples into a single report. It contains modules for a large number of
8626 common bioinformatics tools.")
8627 (license license:gpl3+)))
8629 (define-public r-chipseq
8636 (uri (bioconductor-uri "chipseq" version))
8639 "1ymcq77krwjzrkzzcw7i9909cmkqa7c0675z9wzvrrk81hgdssfq"))))
8640 (build-system r-build-system)
8642 `(("r-biocgenerics" ,r-biocgenerics)
8643 ("r-genomicranges" ,r-genomicranges)
8644 ("r-iranges" ,r-iranges)
8645 ("r-lattice" ,r-lattice)
8646 ("r-s4vectors" ,r-s4vectors)
8647 ("r-shortread" ,r-shortread)))
8648 (home-page "https://bioconductor.org/packages/chipseq")
8649 (synopsis "Package for analyzing ChIPseq data")
8651 "This package provides tools for processing short read data from ChIPseq
8653 (license license:artistic2.0)))
8655 (define-public r-copyhelper
8657 (name "r-copyhelper")
8662 (uri (string-append "https://bioconductor.org/packages/release/"
8663 "data/experiment/src/contrib/CopyhelpeR_"
8667 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8668 (properties `((upstream-name . "CopyhelpeR")))
8669 (build-system r-build-system)
8670 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8671 (synopsis "Helper files for CopywriteR")
8673 "This package contains the helper files that are required to run the
8674 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8675 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8676 mm10. In addition, it contains a blacklist filter to remove regions that
8677 display copy number variation. Files are stored as GRanges objects from the
8678 GenomicRanges Bioconductor package.")
8679 (license license:gpl2)))
8681 (define-public r-copywriter
8683 (name "r-copywriter")
8688 (uri (bioconductor-uri "CopywriteR" version))
8691 "17fy2lc5yf3nh6v077kv87h53n263hqz2540lzrl0vjiqrl2plca"))))
8692 (properties `((upstream-name . "CopywriteR")))
8693 (build-system r-build-system)
8695 `(("r-biocparallel" ,r-biocparallel)
8696 ("r-chipseq" ,r-chipseq)
8697 ("r-copyhelper" ,r-copyhelper)
8698 ("r-data-table" ,r-data-table)
8699 ("r-dnacopy" ,r-dnacopy)
8700 ("r-futile-logger" ,r-futile-logger)
8701 ("r-genomeinfodb" ,r-genomeinfodb)
8702 ("r-genomicalignments" ,r-genomicalignments)
8703 ("r-genomicranges" ,r-genomicranges)
8704 ("r-gtools" ,r-gtools)
8705 ("r-iranges" ,r-iranges)
8706 ("r-matrixstats" ,r-matrixstats)
8707 ("r-rsamtools" ,r-rsamtools)
8708 ("r-s4vectors" ,r-s4vectors)))
8709 (home-page "https://github.com/PeeperLab/CopywriteR")
8710 (synopsis "Copy number information from targeted sequencing")
8712 "CopywriteR extracts DNA copy number information from targeted sequencing
8713 by utilizing off-target reads. It allows for extracting uniformly distributed
8714 copy number information, can be used without reference, and can be applied to
8715 sequencing data obtained from various techniques including chromatin
8716 immunoprecipitation and target enrichment on small gene panels. Thereby,
8717 CopywriteR constitutes a widely applicable alternative to available copy
8718 number detection tools.")
8719 (license license:gpl2)))
8721 (define-public r-methylkit
8723 (name "r-methylkit")
8727 (uri (bioconductor-uri "methylKit" version))
8730 "0h53w2mrjrg2n0ndi12k9j6cwclgwcgpy25nz7nyj971aisw02xn"))))
8731 (properties `((upstream-name . "methylKit")))
8732 (build-system r-build-system)
8734 `(("r-data-table" ,r-data-table)
8735 ("r-emdbook" ,r-emdbook)
8736 ("r-fastseg" ,r-fastseg)
8737 ("r-genomeinfodb" ,r-genomeinfodb)
8738 ("r-genomicranges" ,r-genomicranges)
8739 ("r-gtools" ,r-gtools)
8740 ("r-iranges" ,r-iranges)
8741 ("r-kernsmooth" ,r-kernsmooth)
8742 ("r-limma" ,r-limma)
8743 ("r-mclust" ,r-mclust)
8744 ("r-qvalue" ,r-qvalue)
8745 ("r-r-utils" ,r-r-utils)
8747 ("r-rhtslib" ,r-rhtslib)
8748 ("r-rsamtools" ,r-rsamtools)
8749 ("r-rtracklayer" ,r-rtracklayer)
8750 ("r-s4vectors" ,r-s4vectors)
8751 ("r-zlibbioc" ,r-zlibbioc)))
8754 (home-page "https://github.com/al2na/methylKit")
8756 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8758 "MethylKit is an R package for DNA methylation analysis and annotation
8759 from high-throughput bisulfite sequencing. The package is designed to deal
8760 with sequencing data from @dfn{Reduced representation bisulfite
8761 sequencing} (RRBS) and its variants, but also target-capture methods and whole
8762 genome bisulfite sequencing. It also has functions to analyze base-pair
8763 resolution 5hmC data from experimental protocols such as oxBS-Seq and
8765 (license license:artistic2.0)))
8767 (define-public r-sva
8774 (uri (bioconductor-uri "sva" version))
8777 "0q5xb68wfcnchy8rkv5ma67pmz1i91lsnvmwmj8f1c3w4xan3pgw"))))
8778 (build-system r-build-system)
8780 `(("r-genefilter" ,r-genefilter)
8782 ("r-biocparallel" ,r-biocparallel)
8783 ("r-matrixstats" ,r-matrixstats)
8784 ("r-limma" ,r-limma)))
8785 (home-page "https://bioconductor.org/packages/sva")
8786 (synopsis "Surrogate variable analysis")
8788 "This package contains functions for removing batch effects and other
8789 unwanted variation in high-throughput experiment. It also contains functions
8790 for identifying and building surrogate variables for high-dimensional data
8791 sets. Surrogate variables are covariates constructed directly from
8792 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8793 imaging data that can be used in subsequent analyses to adjust for unknown,
8794 unmodeled, or latent sources of noise.")
8795 (license license:artistic2.0)))
8797 (define-public r-seqminer
8804 (uri (cran-uri "seqminer" version))
8807 "057j1l6dip35l1aivilapl2zv9db677b3di2pb3sfgq2sxg0ps3l"))))
8808 (build-system r-build-system)
8811 (home-page "http://seqminer.genomic.codes")
8812 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8814 "This package provides tools to integrate nucleotide sequencing
8815 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8816 ;; Any version of the GPL is acceptable
8817 (license (list license:gpl2+ license:gpl3+))))
8819 (define-public r-raremetals2
8821 (name "r-raremetals2")
8826 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8827 "b/b7/RareMETALS2_" version ".tar.gz"))
8830 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8831 (properties `((upstream-name . "RareMETALS2")))
8832 (build-system r-build-system)
8834 `(("r-seqminer" ,r-seqminer)
8835 ("r-mvtnorm" ,r-mvtnorm)
8837 ("r-compquadform" ,r-compquadform)
8838 ("r-getopt" ,r-getopt)))
8839 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8840 (synopsis "Analyze gene-level association tests for binary trait")
8842 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8843 It was designed to meta-analyze gene-level association tests for binary trait.
8844 While rareMETALS offers a near-complete solution for meta-analysis of
8845 gene-level tests for quantitative trait, it does not offer the optimal
8846 solution for binary trait. The package rareMETALS2 offers improved features
8847 for analyzing gene-level association tests in meta-analyses for binary
8849 (license license:gpl3)))
8851 (define-public r-maldiquant
8853 (name "r-maldiquant")
8858 (uri (cran-uri "MALDIquant" version))
8861 "1pmhsfvd45a44xdiml4zx3zd5fhygqyziqvygahkk9yibnyhv4cv"))))
8862 (properties `((upstream-name . "MALDIquant")))
8863 (build-system r-build-system)
8864 (home-page "http://cran.r-project.org/web/packages/MALDIquant")
8865 (synopsis "Quantitative analysis of mass spectrometry data")
8867 "This package provides a complete analysis pipeline for matrix-assisted
8868 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
8869 two-dimensional mass spectrometry data. In addition to commonly used plotting
8870 and processing methods it includes distinctive features, namely baseline
8871 subtraction methods such as morphological filters (TopHat) or the
8872 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
8873 alignment using warping functions, handling of replicated measurements as well
8874 as allowing spectra with different resolutions.")
8875 (license license:gpl3+)))
8877 (define-public r-protgenerics
8879 (name "r-protgenerics")
8884 (uri (bioconductor-uri "ProtGenerics" version))
8887 "16ijp50448wnabp43klx943rhdvh7x45hvy7cnpq1s4dckxhhyni"))))
8888 (properties `((upstream-name . "ProtGenerics")))
8889 (build-system r-build-system)
8890 (home-page "https://github.com/lgatto/ProtGenerics")
8891 (synopsis "S4 generic functions for proteomics infrastructure")
8893 "This package provides S4 generic functions needed by Bioconductor
8894 proteomics packages.")
8895 (license license:artistic2.0)))
8897 (define-public r-mzr
8904 (uri (bioconductor-uri "mzR" version))
8907 "1x3gp30sfxz2v3k3swih9kff9b2rvk7hzhnlkp6ywlnn2wgb0q8c"))
8908 (modules '((guix build utils)))
8911 (delete-file-recursively "src/boost")
8913 (properties `((upstream-name . "mzR")))
8914 (build-system r-build-system)
8917 (modify-phases %standard-phases
8918 (add-after 'unpack 'use-system-boost
8920 (substitute* "src/Makevars"
8921 (("\\./boost/libs.*") "")
8922 (("ARCH_OBJS=" line)
8924 "\nARCH_LIBS=-lboost_system -lboost_regex \
8925 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
8928 `(("boost" ,boost) ; use this instead of the bundled boost sources
8929 ("netcdf" ,netcdf)))
8931 `(("r-biobase" ,r-biobase)
8932 ("r-biocgenerics" ,r-biocgenerics)
8933 ("r-protgenerics" ,r-protgenerics)
8935 ("r-zlibbioc" ,r-zlibbioc)))
8936 (home-page "https://github.com/sneumann/mzR/")
8937 (synopsis "Parser for mass spectrometry data files")
8939 "The mzR package provides a unified API to the common file formats and
8940 parsers available for mass spectrometry data. It comes with a wrapper for the
8941 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
8942 The package contains the original code written by the ISB, and a subset of the
8943 proteowizard library for mzML and mzIdentML. The netCDF reading code has
8944 previously been used in XCMS.")
8945 (license license:artistic2.0)))
8947 (define-public r-affyio
8954 (uri (bioconductor-uri "affyio" version))
8957 "1pzzp3d3dbmyf34gvivfiprkpscn36rgvhrq853a1d3avcwr5ak9"))))
8958 (build-system r-build-system)
8960 `(("r-zlibbioc" ,r-zlibbioc)))
8963 (home-page "https://github.com/bmbolstad/affyio")
8964 (synopsis "Tools for parsing Affymetrix data files")
8966 "This package provides routines for parsing Affymetrix data files based
8967 upon file format information. The primary focus is on accessing the CEL and
8969 (license license:lgpl2.0+)))
8971 (define-public r-affy
8978 (uri (bioconductor-uri "affy" version))
8981 "0jmbkimma5ffsdkk3xp03g4lpz84gd95nkqakif2nqq6wmx0syrj"))))
8982 (build-system r-build-system)
8984 `(("r-affyio" ,r-affyio)
8985 ("r-biobase" ,r-biobase)
8986 ("r-biocgenerics" ,r-biocgenerics)
8987 ("r-biocinstaller" ,r-biocinstaller)
8988 ("r-preprocesscore" ,r-preprocesscore)
8989 ("r-zlibbioc" ,r-zlibbioc)))
8990 (home-page "https://bioconductor.org/packages/affy")
8991 (synopsis "Methods for affymetrix oligonucleotide arrays")
8993 "This package contains functions for exploratory oligonucleotide array
8995 (license license:lgpl2.0+)))
8997 (define-public r-vsn
9004 (uri (bioconductor-uri "vsn" version))
9007 "18y62phzirj75gg6v5l41jwybmk23ia6w7qhch0kxc4bl2rysw6j"))))
9008 (build-system r-build-system)
9010 `(("r-affy" ,r-affy)
9011 ("r-biobase" ,r-biobase)
9012 ("r-ggplot2" ,r-ggplot2)
9013 ("r-lattice" ,r-lattice)
9014 ("r-limma" ,r-limma)))
9015 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9016 (synopsis "Variance stabilization and calibration for microarray data")
9018 "The package implements a method for normalising microarray intensities,
9019 and works for single- and multiple-color arrays. It can also be used for data
9020 from other technologies, as long as they have similar format. The method uses
9021 a robust variant of the maximum-likelihood estimator for an
9022 additive-multiplicative error model and affine calibration. The model
9023 incorporates data calibration step (a.k.a. normalization), a model for the
9024 dependence of the variance on the mean intensity and a variance stabilizing
9025 data transformation. Differences between transformed intensities are
9026 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9027 their variance is independent of the mean, and they are usually more sensitive
9028 and specific in detecting differential transcription.")
9029 (license license:artistic2.0)))
9031 (define-public r-mzid
9038 (uri (bioconductor-uri "mzID" version))
9041 "0yk70dka56zd8w62f03ggx3mandj91gfa767h9ajj0sd3mjmfqb9"))))
9042 (properties `((upstream-name . "mzID")))
9043 (build-system r-build-system)
9045 `(("r-doparallel" ,r-doparallel)
9046 ("r-foreach" ,r-foreach)
9047 ("r-iterators" ,r-iterators)
9049 ("r-protgenerics" ,r-protgenerics)
9052 (home-page "https://bioconductor.org/packages/mzID")
9053 (synopsis "Parser for mzIdentML files")
9055 "This package provides a parser for mzIdentML files implemented using the
9056 XML package. The parser tries to be general and able to handle all types of
9057 mzIdentML files with the drawback of having less pretty output than a vendor
9059 (license license:gpl2+)))
9061 (define-public r-pcamethods
9063 (name "r-pcamethods")
9068 (uri (bioconductor-uri "pcaMethods" version))
9071 "0ii235g0x0492kh8cfrf28ni0b6vd6fh7kizkqmczzqggd6b1bk8"))))
9072 (properties `((upstream-name . "pcaMethods")))
9073 (build-system r-build-system)
9075 `(("r-biobase" ,r-biobase)
9076 ("r-biocgenerics" ,r-biocgenerics)
9078 ("r-rcpp" ,r-rcpp)))
9079 (home-page "https://github.com/hredestig/pcamethods")
9080 (synopsis "Collection of PCA methods")
9082 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9083 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9084 for missing value estimation is included for comparison. BPCA, PPCA and
9085 NipalsPCA may be used to perform PCA on incomplete data as well as for
9086 accurate missing value estimation. A set of methods for printing and plotting
9087 the results is also provided. All PCA methods make use of the same data
9088 structure (pcaRes) to provide a common interface to the PCA results.")
9089 (license license:gpl3+)))
9091 (define-public r-msnbase
9098 (uri (bioconductor-uri "MSnbase" version))
9101 "0dqfimljhrx3gac8d1k72gppx27lz8yckyb12v4604nbviw7xd3r"))))
9102 (properties `((upstream-name . "MSnbase")))
9103 (build-system r-build-system)
9105 `(("r-affy" ,r-affy)
9106 ("r-biobase" ,r-biobase)
9107 ("r-biocgenerics" ,r-biocgenerics)
9108 ("r-biocparallel" ,r-biocparallel)
9109 ("r-digest" ,r-digest)
9110 ("r-ggplot2" ,r-ggplot2)
9111 ("r-impute" ,r-impute)
9112 ("r-iranges" ,r-iranges)
9113 ("r-lattice" ,r-lattice)
9114 ("r-maldiquant" ,r-maldiquant)
9117 ("r-pcamethods" ,r-pcamethods)
9119 ("r-preprocesscore" ,r-preprocesscore)
9120 ("r-protgenerics" ,r-protgenerics)
9122 ("r-s4vectors" ,r-s4vectors)
9125 (home-page "https://github.com/lgatto/MSnbase")
9126 (synopsis "Base functions and classes for MS-based proteomics")
9128 "This package provides basic plotting, data manipulation and processing
9129 of mass spectrometry based proteomics data.")
9130 (license license:artistic2.0)))
9132 (define-public r-msnid
9139 (uri (bioconductor-uri "MSnID" version))
9142 "1vi4ngwbayrv2jkfb4pbmdp37xn04y07rh1jcklqfh0fcrm1jdig"))))
9143 (properties `((upstream-name . "MSnID")))
9144 (build-system r-build-system)
9146 `(("r-biobase" ,r-biobase)
9147 ("r-data-table" ,r-data-table)
9148 ("r-doparallel" ,r-doparallel)
9149 ("r-dplyr" ,r-dplyr)
9150 ("r-foreach" ,r-foreach)
9151 ("r-iterators" ,r-iterators)
9152 ("r-msnbase" ,r-msnbase)
9155 ("r-protgenerics" ,r-protgenerics)
9156 ("r-r-cache" ,r-r-cache)
9158 ("r-reshape2" ,r-reshape2)))
9159 (home-page "https://bioconductor.org/packages/MSnID")
9160 (synopsis "Utilities for LC-MSn proteomics identifications")
9162 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9163 from mzIdentML (leveraging the mzID package) or text files. After collating
9164 the search results from multiple datasets it assesses their identification
9165 quality and optimize filtering criteria to achieve the maximum number of
9166 identifications while not exceeding a specified false discovery rate. It also
9167 contains a number of utilities to explore the MS/MS results and assess missed
9168 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9169 (license license:artistic2.0)))
9171 (define-public r-seurat
9172 ;; Source releases are only made for new x.0 versions. All newer versions
9173 ;; are only released as pre-built binaries. At the time of this writing the
9174 ;; latest binary release is 1.4.0.12, which is equivalent to this commit.
9175 (let ((commit "fccb77d1452c35ee47e47ebf8e87bddb59f3b08d")
9179 (version (string-append "1.4.0.12-" revision "." (string-take commit 7)))
9183 (url "https://github.com/satijalab/seurat")
9185 (file-name (string-append name "-" version "-checkout"))
9188 "101wq3aqrdmbfi3lqmq4iivk9iwbf10d4z216ss25hf7n9091cyl"))
9189 ;; Delete pre-built jar.
9191 '(begin (delete-file "inst/java/ModularityOptimizer.jar")
9193 (build-system r-build-system)
9196 (modify-phases %standard-phases
9197 (add-after 'unpack 'build-jar
9198 (lambda* (#:key inputs #:allow-other-keys)
9199 (let ((classesdir "tmp-classes"))
9200 (setenv "JAVA_HOME" (assoc-ref inputs "jdk"))
9202 (and (zero? (apply system* `("javac" "-d" ,classesdir
9203 ,@(find-files "java" "\\.java$"))))
9204 (zero? (system* "jar"
9205 "-cf" "inst/java/ModularityOptimizer.jar"
9206 "-C" classesdir ".")))))))))
9208 `(("jdk" ,icedtea "jdk")))
9211 ("r-caret" ,r-caret)
9212 ("r-cowplot" ,r-cowplot)
9213 ("r-dplyr" ,r-dplyr)
9214 ("r-fastica" ,r-fastica)
9217 ("r-gdata" ,r-gdata)
9218 ("r-ggplot2" ,r-ggplot2)
9219 ("r-gplots" ,r-gplots)
9220 ("r-gridextra" ,r-gridextra)
9221 ("r-igraph" ,r-igraph)
9222 ("r-irlba" ,r-irlba)
9224 ("r-mixtools" ,r-mixtools)
9225 ("r-pbapply" ,r-pbapply)
9227 ("r-ranger" ,r-ranger)
9228 ("r-rcolorbrewer" ,r-rcolorbrewer)
9230 ("r-rcppeigen" ,r-rcppeigen)
9231 ("r-rcppprogress" ,r-rcppprogress)
9232 ("r-reshape2" ,r-reshape2)
9234 ("r-rtsne" ,r-rtsne)
9235 ("r-stringr" ,r-stringr)
9236 ("r-tclust" ,r-tclust)
9238 ("r-vgam" ,r-vgam)))
9239 (home-page "http://www.satijalab.org/seurat")
9240 (synopsis "Seurat is an R toolkit for single cell genomics")
9242 "This package is an R package designed for QC, analysis, and
9243 exploration of single cell RNA-seq data. It easily enables widely-used
9244 analytical techniques, including the identification of highly variable genes,
9245 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9246 algorithms; density clustering, hierarchical clustering, k-means, and the
9247 discovery of differentially expressed genes and markers.")
9248 (license license:gpl3))))
9250 (define-public r-aroma-light
9252 (name "r-aroma-light")
9257 (uri (bioconductor-uri "aroma.light" version))
9260 "0crnk6851jwypqr5l5jcbbay0vi5vvdjyisaf6z2d69c39wmr6sc"))))
9261 (properties `((upstream-name . "aroma.light")))
9262 (build-system r-build-system)
9264 `(("r-matrixstats" ,r-matrixstats)
9265 ("r-r-methodss3" ,r-r-methodss3)
9267 ("r-r-utils" ,r-r-utils)))
9268 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9269 (synopsis "Methods for normalization and visualization of microarray data")
9271 "This package provides methods for microarray analysis that take basic
9272 data types such as matrices and lists of vectors. These methods can be used
9273 standalone, be utilized in other packages, or be wrapped up in higher-level
9275 (license license:gpl2+)))
9277 (define-public r-deseq
9284 (uri (bioconductor-uri "DESeq" version))
9287 "0mn5w3cy16iwwk8zxs7za6aa6cnrca75z0g45zd5zh1py5d7nfv9"))))
9288 (properties `((upstream-name . "DESeq")))
9289 (build-system r-build-system)
9291 `(("r-biobase" ,r-biobase)
9292 ("r-biocgenerics" ,r-biocgenerics)
9293 ("r-genefilter" ,r-genefilter)
9294 ("r-geneplotter" ,r-geneplotter)
9295 ("r-lattice" ,r-lattice)
9296 ("r-locfit" ,r-locfit)
9298 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9299 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9300 (synopsis "Differential gene expression analysis")
9302 "This package provides tools for estimating variance-mean dependence in
9303 count data from high-throughput genetic sequencing assays and for testing for
9304 differential expression based on a model using the negative binomial
9306 (license license:gpl3+)))
9308 (define-public r-edaseq
9315 (uri (bioconductor-uri "EDASeq" version))
9318 "07zm89zcivyn2261aq9grqmly8ji482kr9h9dyfknfdfrpv7jpwv"))))
9319 (properties `((upstream-name . "EDASeq")))
9320 (build-system r-build-system)
9322 `(("r-annotationdbi" ,r-annotationdbi)
9323 ("r-aroma-light" ,r-aroma-light)
9324 ("r-biobase" ,r-biobase)
9325 ("r-biocgenerics" ,r-biocgenerics)
9326 ("r-biomart" ,r-biomart)
9327 ("r-biostrings" ,r-biostrings)
9328 ("r-deseq" ,r-deseq)
9329 ("r-genomicfeatures" ,r-genomicfeatures)
9330 ("r-genomicranges" ,r-genomicranges)
9331 ("r-iranges" ,r-iranges)
9332 ("r-rsamtools" ,r-rsamtools)
9333 ("r-shortread" ,r-shortread)))
9334 (home-page "https://github.com/drisso/EDASeq")
9335 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9337 "This package provides support for numerical and graphical summaries of
9338 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9339 adjust for GC-content effect (or other gene-level effects) on read counts:
9340 loess robust local regression, global-scaling, and full-quantile
9341 normalization. Between-lane normalization procedures to adjust for
9342 distributional differences between lanes (e.g., sequencing depth):
9343 global-scaling and full-quantile normalization.")
9344 (license license:artistic2.0)))
9346 (define-public r-interactivedisplaybase
9348 (name "r-interactivedisplaybase")
9353 (uri (bioconductor-uri "interactiveDisplayBase" version))
9356 "01yb945jqqimwjgriza6yy4dnp303cdirxrhl4hjyprfdlmnz5p5"))))
9358 `((upstream-name . "interactiveDisplayBase")))
9359 (build-system r-build-system)
9361 `(("r-biocgenerics" ,r-biocgenerics)
9362 ("r-shiny" ,r-shiny)))
9363 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9364 (synopsis "Base package for web displays of Bioconductor objects")
9366 "This package contains the basic methods needed to generate interactive
9367 Shiny-based display methods for Bioconductor objects.")
9368 (license license:artistic2.0)))
9370 (define-public r-annotationhub
9372 (name "r-annotationhub")
9377 (uri (bioconductor-uri "AnnotationHub" version))
9380 "1arfka3czw8hkv6n2d85bgibq81s2rgkwhmpaxzhy6nw39vv7y8b"))))
9381 (properties `((upstream-name . "AnnotationHub")))
9382 (build-system r-build-system)
9384 `(("r-annotationdbi" ,r-annotationdbi)
9385 ("r-biocgenerics" ,r-biocgenerics)
9386 ("r-biocinstaller" ,r-biocinstaller)
9389 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9390 ("r-rsqlite" ,r-rsqlite)
9391 ("r-s4vectors" ,r-s4vectors)
9392 ("r-yaml" ,r-yaml)))
9393 (home-page "https://bioconductor.org/packages/AnnotationHub")
9394 (synopsis "Client to access AnnotationHub resources")
9396 "This package provides a client for the Bioconductor AnnotationHub web
9397 resource. The AnnotationHub web resource provides a central location where
9398 genomic files (e.g. VCF, bed, wig) and other resources from standard
9399 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9400 metadata about each resource, e.g., a textual description, tags, and date of
9401 modification. The client creates and manages a local cache of files retrieved
9402 by the user, helping with quick and reproducible access.")
9403 (license license:artistic2.0)))
9405 (define-public r-fastseg
9412 (uri (bioconductor-uri "fastseg" version))
9415 "0dd7nr3klwz9ailwshnbynhd62lwb8zbbpj6jf3igpb94yi6x2jp"))))
9416 (build-system r-build-system)
9418 `(("r-biobase" ,r-biobase)
9419 ("r-biocgenerics" ,r-biocgenerics)
9420 ("r-genomicranges" ,r-genomicranges)
9421 ("r-iranges" ,r-iranges)
9422 ("r-s4vectors" ,r-s4vectors)))
9423 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9424 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9426 "Fastseg implements a very fast and efficient segmentation algorithm.
9427 It can segment data from DNA microarrays and data from next generation
9428 sequencing for example to detect copy number segments. Further it can segment
9429 data from RNA microarrays like tiling arrays to identify transcripts. Most
9430 generally, it can segment data given as a matrix or as a vector. Various data
9431 formats can be used as input to fastseg like expression set objects for
9432 microarrays or GRanges for sequencing data.")
9433 (license license:lgpl2.0+)))
9435 (define-public r-keggrest
9442 (uri (bioconductor-uri "KEGGREST" version))
9445 "1i3i88lj57wvpgjf75a23msgfsjv8pr2b4j1faga276p4fsblkhj"))))
9446 (properties `((upstream-name . "KEGGREST")))
9447 (build-system r-build-system)
9449 `(("r-biostrings" ,r-biostrings)
9452 (home-page "https://bioconductor.org/packages/KEGGREST")
9453 (synopsis "Client-side REST access to KEGG")
9455 "This package provides a package that provides a client interface to the
9456 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9457 (license license:artistic2.0)))
9459 (define-public r-gage
9466 (uri (bioconductor-uri "gage" version))
9469 "1r14p88q3y736pkqm4pdimf1izy1xy3xgivmj3cr4dv65kjny1zk"))))
9470 (build-system r-build-system)
9472 `(("r-annotationdbi" ,r-annotationdbi)
9473 ("r-graph" ,r-graph)
9474 ("r-keggrest" ,r-keggrest)))
9475 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9476 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9478 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9479 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9480 data attributes including sample sizes, experimental designs, assay platforms,
9481 and other types of heterogeneity. The gage package provides functions for
9482 basic GAGE analysis, result processing and presentation. In addition, it
9483 provides demo microarray data and commonly used gene set data based on KEGG
9484 pathways and GO terms. These funtions and data are also useful for gene set
9485 analysis using other methods.")
9486 (license license:gpl2+)))
9488 (define-public r-genomicfiles
9490 (name "r-genomicfiles")
9495 (uri (bioconductor-uri "GenomicFiles" version))
9498 "0r0wmrs5jycf1kckhnc2sgjmp336srlcjdkpbb1ymm7kazdd0s9n"))))
9499 (properties `((upstream-name . "GenomicFiles")))
9500 (build-system r-build-system)
9502 `(("r-biocgenerics" ,r-biocgenerics)
9503 ("r-biocparallel" ,r-biocparallel)
9504 ("r-genomeinfodb" ,r-genomeinfodb)
9505 ("r-genomicalignments" ,r-genomicalignments)
9506 ("r-genomicranges" ,r-genomicranges)
9507 ("r-iranges" ,r-iranges)
9508 ("r-rsamtools" ,r-rsamtools)
9509 ("r-rtracklayer" ,r-rtracklayer)
9510 ("r-s4vectors" ,r-s4vectors)
9511 ("r-summarizedexperiment" ,r-summarizedexperiment)
9512 ("r-variantannotation" ,r-variantannotation)))
9513 (home-page "https://bioconductor.org/packages/GenomicFiles")
9514 (synopsis "Distributed computing by file or by range")
9516 "This package provides infrastructure for parallel computations
9517 distributed by file or by range. User defined mapper and reducer functions
9518 provide added flexibility for data combination and manipulation.")
9519 (license license:artistic2.0)))
9521 (define-public r-complexheatmap
9523 (name "r-complexheatmap")
9528 (uri (bioconductor-uri "ComplexHeatmap" version))
9531 "1x6kp55iqqsd8bhdl3qch95nfiy2y46ldbbsx1sj1v8f0b0ywwcy"))))
9533 `((upstream-name . "ComplexHeatmap")))
9534 (build-system r-build-system)
9536 `(("r-circlize" ,r-circlize)
9537 ("r-colorspace" ,r-colorspace)
9538 ("r-getoptlong" ,r-getoptlong)
9539 ("r-globaloptions" ,r-globaloptions)
9540 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9542 "https://github.com/jokergoo/ComplexHeatmap")
9543 (synopsis "Making Complex Heatmaps")
9545 "Complex heatmaps are efficient to visualize associations between
9546 different sources of data sets and reveal potential structures. This package
9547 provides a highly flexible way to arrange multiple heatmaps and supports
9548 self-defined annotation graphics.")
9549 (license license:gpl2+)))
9551 (define-public r-dirichletmultinomial
9553 (name "r-dirichletmultinomial")
9558 (uri (bioconductor-uri "DirichletMultinomial" version))
9561 "1c4s6x0qm20556grcd1xys9kkpnlzpasaai474malwcg6qvgi4x1"))))
9563 `((upstream-name . "DirichletMultinomial")))
9564 (build-system r-build-system)
9568 `(("r-biocgenerics" ,r-biocgenerics)
9569 ("r-iranges" ,r-iranges)
9570 ("r-s4vectors" ,r-s4vectors)))
9571 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9572 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9574 "Dirichlet-multinomial mixture models can be used to describe variability
9575 in microbial metagenomic data. This package is an interface to code
9576 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9578 (license license:lgpl3)))
9580 (define-public r-ensembldb
9582 (name "r-ensembldb")
9587 (uri (bioconductor-uri "ensembldb" version))
9590 "1w0lca3ws5j770bmls91cn93lznvv2pc8s42nybdzz3vdxjvb4m1"))))
9591 (build-system r-build-system)
9593 `(("r-annotationdbi" ,r-annotationdbi)
9594 ("r-annotationfilter" ,r-annotationfilter)
9595 ("r-annotationhub" ,r-annotationhub)
9596 ("r-biobase" ,r-biobase)
9597 ("r-biocgenerics" ,r-biocgenerics)
9598 ("r-biostrings" ,r-biostrings)
9601 ("r-genomeinfodb" ,r-genomeinfodb)
9602 ("r-genomicfeatures" ,r-genomicfeatures)
9603 ("r-genomicranges" ,r-genomicranges)
9604 ("r-iranges" ,r-iranges)
9605 ("r-protgenerics" ,r-protgenerics)
9606 ("r-rsamtools" ,r-rsamtools)
9607 ("r-rsqlite" ,r-rsqlite)
9608 ("r-rtracklayer" ,r-rtracklayer)
9609 ("r-s4vectors" ,r-s4vectors)))
9610 (home-page "https://github.com/jotsetung/ensembldb")
9611 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9613 "The package provides functions to create and use transcript-centric
9614 annotation databases/packages. The annotation for the databases are directly
9615 fetched from Ensembl using their Perl API. The functionality and data is
9616 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9617 but, in addition to retrieve all gene/transcript models and annotations from
9618 the database, the @code{ensembldb} package also provides a filter framework
9619 allowing to retrieve annotations for specific entries like genes encoded on a
9620 chromosome region or transcript models of lincRNA genes.")
9621 ;; No version specified
9622 (license license:lgpl3+)))
9624 (define-public r-organismdbi
9626 (name "r-organismdbi")
9631 (uri (bioconductor-uri "OrganismDbi" version))
9634 "0yxvhwn0m53wfwp0zi81x96argdf7cf1lpymc2as51apvfcnjdl8"))))
9635 (properties `((upstream-name . "OrganismDbi")))
9636 (build-system r-build-system)
9638 `(("r-annotationdbi" ,r-annotationdbi)
9639 ("r-biobase" ,r-biobase)
9640 ("r-biocgenerics" ,r-biocgenerics)
9641 ("r-biocinstaller" ,r-biocinstaller)
9643 ("r-genomicfeatures" ,r-genomicfeatures)
9644 ("r-genomicranges" ,r-genomicranges)
9645 ("r-graph" ,r-graph)
9646 ("r-iranges" ,r-iranges)
9648 ("r-s4vectors" ,r-s4vectors)))
9649 (home-page "https://bioconductor.org/packages/OrganismDbi")
9650 (synopsis "Software to enable the smooth interfacing of database packages")
9651 (description "The package enables a simple unified interface to several
9652 annotation packages each of which has its own schema by taking advantage of
9653 the fact that each of these packages implements a select methods.")
9654 (license license:artistic2.0)))
9656 (define-public r-biovizbase
9658 (name "r-biovizbase")
9663 (uri (bioconductor-uri "biovizBase" version))
9666 "14l4vhj0a4ssr9m9zdzz3qpd4qw1mhgq5bmxq7jhrq3j9kmd6i2f"))))
9667 (properties `((upstream-name . "biovizBase")))
9668 (build-system r-build-system)
9670 `(("r-annotationdbi" ,r-annotationdbi)
9671 ("r-annotationfilter" ,r-annotationfilter)
9672 ("r-biocgenerics" ,r-biocgenerics)
9673 ("r-biostrings" ,r-biostrings)
9674 ("r-dichromat" ,r-dichromat)
9675 ("r-ensembldb" ,r-ensembldb)
9676 ("r-genomeinfodb" ,r-genomeinfodb)
9677 ("r-genomicalignments" ,r-genomicalignments)
9678 ("r-genomicfeatures" ,r-genomicfeatures)
9679 ("r-genomicranges" ,r-genomicranges)
9680 ("r-hmisc" ,r-hmisc)
9681 ("r-iranges" ,r-iranges)
9682 ("r-rcolorbrewer" ,r-rcolorbrewer)
9683 ("r-rsamtools" ,r-rsamtools)
9684 ("r-s4vectors" ,r-s4vectors)
9685 ("r-scales" ,r-scales)
9686 ("r-summarizedexperiment" ,r-summarizedexperiment)
9687 ("r-variantannotation" ,r-variantannotation)))
9688 (home-page "https://bioconductor.org/packages/biovizBase")
9689 (synopsis "Basic graphic utilities for visualization of genomic data")
9691 "The biovizBase package is designed to provide a set of utilities, color
9692 schemes and conventions for genomic data. It serves as the base for various
9693 high-level packages for biological data visualization. This saves development
9694 effort and encourages consistency.")
9695 (license license:artistic2.0)))
9697 (define-public r-ggbio
9704 (uri (bioconductor-uri "ggbio" version))
9707 "1bqxfqy0hff87ax92z4lfbjz01ndrz7x8pzm6dlkdmi52p30krm9"))))
9708 (build-system r-build-system)
9710 `(("r-annotationdbi" ,r-annotationdbi)
9711 ("r-annotationfilter" ,r-annotationfilter)
9712 ("r-biobase" ,r-biobase)
9713 ("r-biocgenerics" ,r-biocgenerics)
9714 ("r-biostrings" ,r-biostrings)
9715 ("r-biovizbase" ,r-biovizbase)
9716 ("r-bsgenome" ,r-bsgenome)
9717 ("r-ensembldb" ,r-ensembldb)
9718 ("r-genomeinfodb" ,r-genomeinfodb)
9719 ("r-genomicalignments" ,r-genomicalignments)
9720 ("r-genomicfeatures" ,r-genomicfeatures)
9721 ("r-genomicranges" ,r-genomicranges)
9722 ("r-ggally" ,r-ggally)
9723 ("r-ggplot2" ,r-ggplot2)
9724 ("r-gridextra" ,r-gridextra)
9725 ("r-gtable" ,r-gtable)
9726 ("r-hmisc" ,r-hmisc)
9727 ("r-iranges" ,r-iranges)
9728 ("r-organismdbi" ,r-organismdbi)
9729 ("r-reshape2" ,r-reshape2)
9730 ("r-rsamtools" ,r-rsamtools)
9731 ("r-rtracklayer" ,r-rtracklayer)
9732 ("r-s4vectors" ,r-s4vectors)
9733 ("r-scales" ,r-scales)
9734 ("r-summarizedexperiment" ,r-summarizedexperiment)
9735 ("r-variantannotation" ,r-variantannotation)))
9736 (home-page "http://www.tengfei.name/ggbio/")
9737 (synopsis "Visualization tools for genomic data")
9739 "The ggbio package extends and specializes the grammar of graphics for
9740 biological data. The graphics are designed to answer common scientific
9741 questions, in particular those often asked of high throughput genomics data.
9742 All core Bioconductor data structures are supported, where appropriate. The
9743 package supports detailed views of particular genomic regions, as well as
9744 genome-wide overviews. Supported overviews include ideograms and grand linear
9745 views. High-level plots include sequence fragment length, edge-linked
9746 interval to data view, mismatch pileup, and several splicing summaries.")
9747 (license license:artistic2.0)))
9749 (define-public r-gprofiler
9751 (name "r-gprofiler")
9756 (uri (cran-uri "gProfileR" version))
9759 "1qix15d0wa9nspdclcawml94mng4qmr2jciv7d24py315wfsvv8p"))))
9760 (properties `((upstream-name . "gProfileR")))
9761 (build-system r-build-system)
9763 `(("r-plyr" ,r-plyr)
9764 ("r-rcurl" ,r-rcurl)))
9765 (home-page "http://cran.r-project.org/web/packages/gProfileR/")
9766 (synopsis "Interface to the g:Profiler toolkit")
9768 "This package provides tools for functional enrichment analysis,
9769 gene identifier conversion and mapping homologous genes across related
9770 organisms via the @code{g:Profiler} toolkit.")
9771 (license license:gpl2+)))
9773 (define-public r-gqtlbase
9780 (uri (bioconductor-uri "gQTLBase" version))
9783 "1756vfcj2dkkgcmfkkg7qdaig36dv9gfvpypn9rbrky56wm1p035"))))
9784 (properties `((upstream-name . "gQTLBase")))
9785 (build-system r-build-system)
9787 `(("r-batchjobs" ,r-batchjobs)
9788 ("r-bbmisc" ,r-bbmisc)
9789 ("r-biocgenerics" ,r-biocgenerics)
9791 ("r-doparallel" ,r-doparallel)
9793 ("r-ffbase" ,r-ffbase)
9794 ("r-foreach" ,r-foreach)
9795 ("r-genomicfiles" ,r-genomicfiles)
9796 ("r-genomicranges" ,r-genomicranges)
9797 ("r-rtracklayer" ,r-rtracklayer)
9798 ("r-s4vectors" ,r-s4vectors)
9799 ("r-summarizedexperiment" ,r-summarizedexperiment)))
9800 (home-page "https://bioconductor.org/packages/gQTLBase")
9801 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
9803 "The purpose of this package is to simplify the storage and interrogation
9804 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
9806 (license license:artistic2.0)))
9808 (define-public r-snpstats
9815 (uri (bioconductor-uri "snpStats" version))
9818 "1x9qwynh2hwl24vq02naf4mchpch7xi2pkdrlgw896k28kx0lvir"))))
9819 (properties `((upstream-name . "snpStats")))
9820 (build-system r-build-system)
9821 (inputs `(("zlib" ,zlib)))
9823 `(("r-biocgenerics" ,r-biocgenerics)
9824 ("r-matrix" ,r-matrix)
9825 ("r-survival" ,r-survival)
9826 ("r-zlibbioc" ,r-zlibbioc)))
9827 (home-page "https://bioconductor.org/packages/snpStats")
9828 (synopsis "Methods for SNP association studies")
9830 "This package provides classes and statistical methods for large
9831 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
9832 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
9833 (license license:gpl3)))
9835 (define-public r-homo-sapiens
9837 (name "r-homo-sapiens")
9841 ;; We cannot use bioconductor-uri here because this tarball is
9842 ;; located under "data/annotation/" instead of "bioc/".
9843 (uri (string-append "http://www.bioconductor.org/packages/"
9844 "release/data/annotation/src/contrib/"
9849 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
9851 `((upstream-name . "Homo.sapiens")))
9852 (build-system r-build-system)
9854 `(("r-genomicfeatures" ,r-genomicfeatures)
9855 ("r-go-db" ,r-go-db)
9856 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
9857 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
9858 ("r-organismdbi" ,r-organismdbi)
9859 ("r-annotationdbi" ,r-annotationdbi)))
9860 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
9861 (synopsis "Annotation package for the Homo.sapiens object")
9863 "This package contains the Homo.sapiens object to access data from
9864 several related annotation packages.")
9865 (license license:artistic2.0)))
9867 (define-public r-erma
9874 (uri (bioconductor-uri "erma" version))
9877 "0gcfs9g8vvdv5vmq9b21kd8sq5mizjj49nfzd4in9zvp4b9v7x1g"))))
9878 (build-system r-build-system)
9880 `(("r-annotationdbi" ,r-annotationdbi)
9881 ("r-biobase" ,r-biobase)
9882 ("r-biocgenerics" ,r-biocgenerics)
9883 ("r-foreach" ,r-foreach)
9884 ("r-genomicfiles" ,r-genomicfiles)
9885 ("r-genomicranges" ,r-genomicranges)
9886 ("r-ggplot2" ,r-ggplot2)
9887 ("r-homo-sapiens" ,r-homo-sapiens)
9888 ("r-rtracklayer" ,r-rtracklayer)
9889 ("r-s4vectors" ,r-s4vectors)
9890 ("r-shiny" ,r-shiny)
9891 ("r-summarizedexperiment" ,r-summarizedexperiment)))
9892 (home-page "https://bioconductor.org/packages/erma")
9893 (synopsis "Epigenomic road map adventures")
9895 "The epigenomics road map describes locations of epigenetic marks in DNA
9896 from a variety of cell types. Of interest are locations of histone
9897 modifications, sites of DNA methylation, and regions of accessible chromatin.
9898 This package presents a selection of elements of the road map including
9899 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
9900 by Ernst and Kellis.")
9901 (license license:artistic2.0)))
9903 (define-public r-ldblock
9910 (uri (bioconductor-uri "ldblock" version))
9913 "18nfsixh6d2wfrb9laqsgly5w1frzihhak683k0p8fdf51h4aqba"))))
9914 (build-system r-build-system)
9916 `(("r-erma" ,r-erma)
9917 ("r-genomeinfodb" ,r-genomeinfodb)
9918 ("r-genomicfiles" ,r-genomicfiles)
9919 ("r-go-db" ,r-go-db)
9920 ("r-homo-sapiens" ,r-homo-sapiens)
9921 ("r-matrix" ,r-matrix)
9922 ("r-rsamtools" ,r-rsamtools)
9923 ("r-snpstats" ,r-snpstats)
9924 ("r-variantannotation" ,r-variantannotation)))
9925 (home-page "https://bioconductor.org/packages/ldblock")
9926 (synopsis "Data structures for linkage disequilibrium measures in populations")
9928 "This package defines data structures for @dfn{linkage
9929 disequilibrium} (LD) measures in populations. Its purpose is to simplify
9930 handling of existing population-level data for the purpose of flexibly
9931 defining LD blocks.")
9932 (license license:artistic2.0)))
9934 (define-public r-gqtlstats
9936 (name "r-gqtlstats")
9941 (uri (bioconductor-uri "gQTLstats" version))
9944 "1cbdqawxzgna8rrgj3siph5sw4d2pb57qc0gn6ibfkhyk45f8gdv"))))
9945 (properties `((upstream-name . "gQTLstats")))
9946 (build-system r-build-system)
9948 `(("r-annotationdbi" ,r-annotationdbi)
9949 ("r-batchjobs" ,r-batchjobs)
9950 ("r-bbmisc" ,r-bbmisc)
9951 ("r-beeswarm" ,r-beeswarm)
9952 ("r-biobase" ,r-biobase)
9953 ("r-biocgenerics" ,r-biocgenerics)
9954 ("r-doparallel" ,r-doparallel)
9955 ("r-dplyr" ,r-dplyr)
9957 ("r-ffbase" ,r-ffbase)
9958 ("r-foreach" ,r-foreach)
9959 ("r-genomeinfodb" ,r-genomeinfodb)
9960 ("r-genomicfeatures" ,r-genomicfeatures)
9961 ("r-genomicfiles" ,r-genomicfiles)
9962 ("r-genomicranges" ,r-genomicranges)
9963 ("r-ggbeeswarm" ,r-ggbeeswarm)
9964 ("r-ggplot2" ,r-ggplot2)
9965 ("r-gqtlbase" ,r-gqtlbase)
9966 ("r-hardyweinberg" ,r-hardyweinberg)
9967 ("r-iranges" ,r-iranges)
9968 ("r-ldblock" ,r-ldblock)
9969 ("r-limma" ,r-limma)
9971 ("r-plotly" ,r-plotly)
9972 ("r-reshape2" ,r-reshape2)
9973 ("r-s4vectors" ,r-s4vectors)
9974 ("r-shiny" ,r-shiny)
9975 ("r-snpstats" ,r-snpstats)
9976 ("r-summarizedexperiment" ,r-summarizedexperiment)
9977 ("r-variantannotation" ,r-variantannotation)))
9978 (home-page "https://bioconductor.org/packages/gQTLstats")
9979 (synopsis "Computationally efficient analysis for eQTL and allied studies")
9981 "This package provides tools for the computationally efficient analysis
9982 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
9983 The software in this package aims to support refinements and functional
9984 interpretation of members of a collection of association statistics on a
9985 family of feature/genome hypotheses.")
9986 (license license:artistic2.0)))
9988 (define-public r-gviz
9995 (uri (bioconductor-uri "Gviz" version))
9998 "1lrw65a8426wpxw975wjcaiacpp6fqa00nif1yxigyankbfs23c8"))))
9999 (properties `((upstream-name . "Gviz")))
10000 (build-system r-build-system)
10002 `(("r-annotationdbi" ,r-annotationdbi)
10003 ("r-biobase" ,r-biobase)
10004 ("r-biocgenerics" ,r-biocgenerics)
10005 ("r-biomart" ,r-biomart)
10006 ("r-biostrings" ,r-biostrings)
10007 ("r-biovizbase" ,r-biovizbase)
10008 ("r-bsgenome" ,r-bsgenome)
10009 ("r-digest" ,r-digest)
10010 ("r-genomeinfodb" ,r-genomeinfodb)
10011 ("r-genomicalignments" ,r-genomicalignments)
10012 ("r-genomicfeatures" ,r-genomicfeatures)
10013 ("r-genomicranges" ,r-genomicranges)
10014 ("r-iranges" ,r-iranges)
10015 ("r-lattice" ,r-lattice)
10016 ("r-latticeextra" ,r-latticeextra)
10017 ("r-matrixstats" ,r-matrixstats)
10018 ("r-rcolorbrewer" ,r-rcolorbrewer)
10019 ("r-rsamtools" ,r-rsamtools)
10020 ("r-rtracklayer" ,r-rtracklayer)
10021 ("r-s4vectors" ,r-s4vectors)
10022 ("r-xvector" ,r-xvector)))
10023 (home-page "https://bioconductor.org/packages/Gviz")
10024 (synopsis "Plotting data and annotation information along genomic coordinates")
10026 "Genomic data analyses requires integrated visualization of known genomic
10027 information and new experimental data. Gviz uses the biomaRt and the
10028 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10029 and translates this to e.g. gene/transcript structures in viewports of the
10030 grid graphics package. This results in genomic information plotted together
10032 (license license:artistic2.0)))
10034 (define-public r-gwascat
10041 (uri (bioconductor-uri "gwascat" version))
10044 "0n5x5i5v6a8wpn5mxmlpkl34b4kyypmymiwww6g61zch7xqrgywi"))))
10045 (build-system r-build-system)
10047 `(("r-annotationdbi" ,r-annotationdbi)
10048 ("r-annotationhub" ,r-annotationhub)
10049 ("r-biocgenerics" ,r-biocgenerics)
10050 ("r-biostrings" ,r-biostrings)
10051 ("r-genomeinfodb" ,r-genomeinfodb)
10052 ("r-genomicfeatures" ,r-genomicfeatures)
10053 ("r-genomicranges" ,r-genomicranges)
10054 ("r-ggbio" ,r-ggbio)
10055 ("r-ggplot2" ,r-ggplot2)
10056 ("r-gqtlstats" ,r-gqtlstats)
10057 ("r-graph" ,r-graph)
10059 ("r-homo-sapiens" ,r-homo-sapiens)
10060 ("r-iranges" ,r-iranges)
10061 ("r-rsamtools" ,r-rsamtools)
10062 ("r-rtracklayer" ,r-rtracklayer)
10063 ("r-s4vectors" ,r-s4vectors)
10064 ("r-snpstats" ,r-snpstats)
10065 ("r-summarizedexperiment" ,r-summarizedexperiment)
10066 ("r-variantannotation" ,r-variantannotation)))
10067 (home-page "https://bioconductor.org/packages/gwascat")
10068 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10070 "This package provides tools for representing and modeling data in the
10071 EMBL-EBI GWAS catalog.")
10072 (license license:artistic2.0)))
10074 (define-public r-sushi
10080 (uri (bioconductor-uri "Sushi" version))
10083 "0axaqm480z8d0b2ldgxwm0swava1p4irc62bpl17p2k8k78g687g"))))
10084 (properties `((upstream-name . "Sushi")))
10085 (build-system r-build-system)
10087 `(("r-biomart" ,r-biomart)
10089 (home-page "https://bioconductor.org/packages/Sushi")
10090 (synopsis "Tools for visualizing genomics data")
10092 "This package provides flexible, quantitative, and integrative genomic
10093 visualizations for publication-quality multi-panel figures.")
10094 (license license:gpl2+)))
10096 (define-public r-fithic
10102 (uri (bioconductor-uri "FitHiC" version))
10105 "12ylhrppi051m7nqsgq95kzd9g9wmp34i0zzfi55cjqawlpx7c6n"))))
10106 (properties `((upstream-name . "FitHiC")))
10107 (build-system r-build-system)
10109 `(("r-data-table" ,r-data-table)
10110 ("r-fdrtool" ,r-fdrtool)
10111 ("r-rcpp" ,r-rcpp)))
10112 (home-page "https://bioconductor.org/packages/FitHiC")
10113 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10115 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10116 intra-chromosomal contact maps produced by genome-wide genome architecture
10117 assays such as Hi-C.")
10118 (license license:gpl2+)))
10120 (define-public r-hitc
10126 (uri (bioconductor-uri "HiTC" version))
10129 "0288xa1jy6nzvz2ha07csmp6dirjw5r7p9vy69q2wsbyzr02ymkp"))))
10130 (properties `((upstream-name . "HiTC")))
10131 (build-system r-build-system)
10133 `(("r-biostrings" ,r-biostrings)
10134 ("r-genomeinfodb" ,r-genomeinfodb)
10135 ("r-genomicranges" ,r-genomicranges)
10136 ("r-iranges" ,r-iranges)
10137 ("r-matrix" ,r-matrix)
10138 ("r-rcolorbrewer" ,r-rcolorbrewer)
10139 ("r-rtracklayer" ,r-rtracklayer)))
10140 (home-page "https://bioconductor.org/packages/HiTC")
10141 (synopsis "High throughput chromosome conformation capture analysis")
10143 "The HiTC package was developed to explore high-throughput \"C\" data
10144 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10145 quality controls, normalization, visualization, and further analysis are also
10147 (license license:artistic2.0)))
10149 (define-public r-qvalue
10156 (uri (bioconductor-uri "qvalue" version))
10159 "1rd9rnf16kh8wc076kahd9hsb9rfwsbzmz3kjmp0pj6rbiq0051i"))))
10160 (build-system r-build-system)
10162 `(("r-ggplot2" ,r-ggplot2)
10163 ("r-reshape2" ,r-reshape2)))
10164 (home-page "http://github.com/jdstorey/qvalue")
10165 (synopsis "Q-value estimation for false discovery rate control")
10167 "This package takes a list of p-values resulting from the simultaneous
10168 testing of many hypotheses and estimates their q-values and local @dfn{false
10169 discovery rate} (FDR) values. The q-value of a test measures the proportion
10170 of false positives incurred when that particular test is called significant.
10171 The local FDR measures the posterior probability the null hypothesis is true
10172 given the test's p-value. Various plots are automatically generated, allowing
10173 one to make sensible significance cut-offs. The software can be applied to
10174 problems in genomics, brain imaging, astrophysics, and data mining.")
10175 ;; Any version of the LGPL.
10176 (license license:lgpl3+)))
10178 (define htslib-for-sambamba
10179 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10182 (name "htslib-for-sambamba")
10183 (version (string-append "1.3.1-1." (string-take commit 9)))
10187 (uri (git-reference
10188 (url "https://github.com/lomereiter/htslib.git")
10190 (file-name (string-append "htslib-" version "-checkout"))
10193 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10195 (substitute-keyword-arguments (package-arguments htslib)
10197 `(modify-phases ,phases
10198 (add-after 'unpack 'bootstrap
10200 (zero? (system* "autoreconf" "-vif"))))))))
10202 `(("autoconf" ,autoconf)
10203 ("automake" ,automake)
10204 ,@(package-native-inputs htslib))))))
10206 (define-public sambamba
10213 (uri (string-append "https://github.com/lomereiter/sambamba/"
10214 "archive/v" version ".tar.gz"))
10215 (file-name (string-append name "-" version ".tar.gz"))
10218 "17076gijd65a3f07zns2gvbgahiz5lriwsa6dq353ss3jl85d8vy"))))
10219 (build-system gnu-build-system)
10221 `(#:tests? #f ; there is no test target
10223 '("D_COMPILER=ldc2"
10224 ;; Override "--compiler" flag only.
10225 "D_FLAGS=--compiler=ldc2 -IBioD -g -d"
10226 "sambamba-ldmd2-64")
10228 (modify-phases %standard-phases
10229 (delete 'configure)
10230 (add-after 'unpack 'place-biod
10231 (lambda* (#:key inputs #:allow-other-keys)
10232 (copy-recursively (assoc-ref inputs "biod") "BioD")
10234 (add-after 'unpack 'unbundle-prerequisites
10236 (substitute* "Makefile"
10237 ((" htslib-static lz4-static") ""))
10240 (lambda* (#:key outputs #:allow-other-keys)
10241 (let* ((out (assoc-ref outputs "out"))
10242 (bin (string-append out "/bin")))
10244 (install-file "build/sambamba" bin)
10250 ,(let ((commit "1248586b54af4bd4dfb28ebfebfc6bf012e7a587"))
10253 (uri (git-reference
10254 (url "https://github.com/biod/BioD.git")
10256 (file-name (string-append "biod-"
10257 (string-take commit 9)
10261 "1m8hi1n7x0ri4l6s9i0x6jg4z4v94xrfdzp7mbizdipfag0m17g3")))))))
10264 ("htslib" ,htslib-for-sambamba)))
10265 (home-page "http://lomereiter.github.io/sambamba")
10266 (synopsis "Tools for working with SAM/BAM data")
10267 (description "Sambamba is a high performance modern robust and
10268 fast tool (and library), written in the D programming language, for
10269 working with SAM and BAM files. Current parallelised functionality is
10270 an important subset of samtools functionality, including view, index,
10271 sort, markdup, and depth.")
10272 (license license:gpl2+)))
10274 (define-public ritornello
10276 (name "ritornello")
10280 (uri (string-append "https://github.com/KlugerLab/"
10281 "Ritornello/archive/v"
10282 version ".tar.gz"))
10283 (file-name (string-append name "-" version ".tar.gz"))
10286 "02nik86gq9ljjriv6pamwlmqnfky3ads1fpklx6mc3hx6k40pg38"))))
10287 (build-system gnu-build-system)
10289 `(#:tests? #f ; there are no tests
10291 (modify-phases %standard-phases
10292 (add-after 'unpack 'patch-samtools-references
10293 (lambda* (#:key inputs #:allow-other-keys)
10294 (substitute* '("src/SamStream.h"
10295 "src/BufferedGenomeReader.h")
10296 (("<sam.h>") "<samtools/sam.h>"))
10298 (delete 'configure)
10300 (lambda* (#:key inputs outputs #:allow-other-keys)
10301 (let* ((out (assoc-ref outputs "out"))
10302 (bin (string-append out "/bin/")))
10304 (install-file "bin/Ritornello" bin)
10307 `(("samtools" ,samtools-0.1)
10311 (home-page "https://github.com/KlugerLab/Ritornello")
10312 (synopsis "Control-free peak caller for ChIP-seq data")
10313 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10314 signal processing that can accurately call binding events without the need to
10315 do a pair total DNA input or IgG control sample. It has been tested for use
10316 with narrow binding events such as transcription factor ChIP-seq.")
10317 (license license:gpl3+)))
10319 (define-public trim-galore
10321 (name "trim-galore")
10326 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
10327 "projects/trim_galore/trim_galore_v"
10331 "0b9qdxi4521gsrjvbhgky8g7kry9b5nx3byzaxkgxz7p4k8bn1mn"))))
10332 (build-system gnu-build-system)
10334 `(#:tests? #f ; no tests
10336 (modify-phases %standard-phases
10337 ;; The archive contains plain files.
10339 (lambda* (#:key source #:allow-other-keys)
10340 (zero? (system* "unzip" source))))
10341 (delete 'configure)
10343 (add-after 'unpack 'hardcode-tool-references
10344 (lambda* (#:key inputs #:allow-other-keys)
10345 (substitute* "trim_galore"
10346 (("\\$path_to_cutadapt = 'cutadapt'")
10347 (string-append "$path_to_cutadapt = '"
10348 (assoc-ref inputs "cutadapt")
10351 (string-append "| "
10352 (assoc-ref inputs "gzip")
10355 (string-append "\""
10356 (assoc-ref inputs "gzip")
10360 (lambda* (#:key outputs #:allow-other-keys)
10361 (let ((bin (string-append (assoc-ref outputs "out")
10364 (install-file "trim_galore" bin)
10369 ("cutadapt" ,cutadapt)))
10371 `(("unzip" ,unzip)))
10372 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10373 (synopsis "Wrapper around Cutadapt and FastQC")
10374 (description "Trim Galore! is a wrapper script to automate quality and
10375 adapter trimming as well as quality control, with some added functionality to
10376 remove biased methylation positions for RRBS sequence files.")
10377 (license license:gpl3+)))
10379 (define-public gess
10385 (uri (string-append "http://compbio.uthscsa.edu/"
10387 "gess-" version ".src.tar.gz"))
10390 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10391 (build-system gnu-build-system)
10393 `(#:tests? #f ; no tests
10395 (modify-phases %standard-phases
10396 (delete 'configure)
10399 (lambda* (#:key inputs outputs #:allow-other-keys)
10400 (let* ((python (assoc-ref inputs "python"))
10401 (out (assoc-ref outputs "out"))
10402 (bin (string-append out "/bin/"))
10403 (target (string-append
10404 out "/lib/python2.7/site-packages/gess/")))
10406 (copy-recursively "." target)
10407 ;; Make GESS.py executable
10408 (chmod (string-append target "GESS.py") #o555)
10409 ;; Add Python shebang to the top and make Matplotlib
10411 (substitute* (string-append target "GESS.py")
10412 (("\"\"\"Description:" line)
10413 (string-append "#!" (which "python") "
10415 matplotlib.use('Agg')
10417 ;; Make sure GESS has all modules in its path
10418 (wrap-program (string-append target "GESS.py")
10419 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
10421 (symlink (string-append target "GESS.py")
10422 (string-append bin "GESS.py"))
10425 `(("python" ,python-2)
10426 ("python2-pysam" ,python2-pysam)
10427 ("python2-scipy" ,python2-scipy)
10428 ("python2-numpy" ,python2-numpy)
10429 ("python2-networkx" ,python2-networkx)
10430 ("python2-biopython" ,python2-biopython)))
10431 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
10432 (synopsis "Detect exon-skipping events from raw RNA-seq data")
10434 "GESS is an implementation of a novel computational method to detect de
10435 novo exon-skipping events directly from raw RNA-seq data without the prior
10436 knowledge of gene annotation information. GESS stands for the graph-based
10437 exon-skipping scanner detection scheme.")
10438 (license license:bsd-3)))
10440 (define-public phylip
10447 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
10448 "download/phylip-" version ".tar.gz"))
10451 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
10452 (build-system gnu-build-system)
10454 `(#:tests? #f ; no check target
10455 #:make-flags (list "-f" "Makefile.unx" "install")
10456 #:parallel-build? #f ; not supported
10458 (modify-phases %standard-phases
10459 (add-after 'unpack 'enter-dir
10460 (lambda _ (chdir "src") #t))
10461 (delete 'configure)
10463 (lambda* (#:key inputs outputs #:allow-other-keys)
10464 (let ((target (string-append (assoc-ref outputs "out")
10467 (for-each (lambda (file)
10468 (install-file file target))
10469 (find-files "../exe" ".*")))
10471 (home-page "http://evolution.genetics.washington.edu/phylip/")
10472 (synopsis "Tools for inferring phylogenies")
10473 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
10474 programs for inferring phylogenies (evolutionary trees).")
10475 (license license:bsd-2)))
10484 (uri (string-append "https://integrativemodeling.org/"
10485 version "/download/imp-" version ".tar.gz"))
10488 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
10489 (build-system cmake-build-system)
10491 `(;; FIXME: Some tests fail because they produce warnings, others fail
10492 ;; because the PYTHONPATH does not include the modeller's directory.
10494 ;; Do not place libraries in an architecture-specific directory.
10496 (list "-DCMAKE_INSTALL_LIBDIR=lib")))
10503 ("python" ,python-2)))
10505 `(("python2-numpy" ,python2-numpy)
10506 ("python2-scipy" ,python2-scipy)
10507 ("python2-pandas" ,python2-pandas)
10508 ("python2-scikit-learn" ,python2-scikit-learn)
10509 ("python2-networkx" ,python2-networkx)))
10510 (home-page "https://integrativemodeling.org")
10511 (synopsis "Integrative modeling platform")
10512 (description "IMP's broad goal is to contribute to a comprehensive
10513 structural characterization of biomolecules ranging in size and complexity
10514 from small peptides to large macromolecular assemblies, by integrating data
10515 from diverse biochemical and biophysical experiments. IMP provides a C++ and
10516 Python toolbox for solving complex modeling problems, and a number of
10517 applications for tackling some common problems in a user-friendly way.")
10518 ;; IMP is largely available under the GNU Lesser GPL; see the file
10519 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
10520 ;; available under the GNU GPL (see the file COPYING.GPL).
10521 (license (list license:lgpl2.1+
10524 (define-public tadbit
10530 (uri (string-append "https://github.com/3DGenomes/TADbit/"
10531 "archive/v" version ".tar.gz"))
10532 (file-name (string-append name "-" version ".tar.gz"))
10535 "1cnfqrl4685zar4nnw94j94nhvl2h29jm448nadqi1h05z6fdk4f"))))
10536 (build-system python-build-system)
10538 `(;; Tests are included and must be run after installation, but
10539 ;; they are incomplete and thus cannot be run.
10543 (modify-phases %standard-phases
10544 (add-after 'unpack 'fix-problems-with-setup.py
10545 (lambda* (#:key outputs #:allow-other-keys)
10546 ;; setup.py opens these files for writing
10547 (chmod "_pytadbit/_version.py" #o664)
10548 (chmod "README.rst" #o664)
10550 ;; Don't attempt to install the bash completions to
10551 ;; the home directory.
10552 (rename-file "extras/.bash_completion"
10554 (substitute* "setup.py"
10555 (("\\(path.expanduser\\('~'\\)")
10556 (string-append "(\""
10557 (assoc-ref outputs "out")
10558 "/etc/bash_completion.d\""))
10559 (("extras/\\.bash_completion")
10563 ;; TODO: add Chimera for visualization
10566 ("python2-scipy" ,python2-scipy)
10567 ("python2-numpy" ,python2-numpy)
10568 ("python2-matplotlib" ,python2-matplotlib)
10569 ("python2-pysam" ,python2-pysam)))
10570 (home-page "http://3dgenomes.github.io/TADbit/")
10571 (synopsis "Analyze, model, and explore 3C-based data")
10573 "TADbit is a complete Python library to deal with all steps to analyze,
10574 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
10575 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
10576 correct interaction matrices, identify and compare the so-called
10577 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
10578 interaction matrices, and finally, extract structural properties from the
10579 models. TADbit is complemented by TADkit for visualizing 3D models.")
10580 (license license:gpl3+)))
10582 (define-public kentutils
10585 ;; 302.1.0 is out, but the only difference is the inclusion of
10586 ;; pre-built binaries.
10587 (version "302.0.0")
10591 (uri (string-append "https://github.com/ENCODE-DCC/kentUtils/"
10592 "archive/v" version ".tar.gz"))
10593 (file-name (string-append name "-" version ".tar.gz"))
10596 "134aja3k1cj32kbk1nnw0q9gxjb2krr15q6sga8qldzvc0585rmm"))
10597 (modules '((guix build utils)
10602 ;; Only the contents of the specified directories are free
10603 ;; for all uses, so we remove the rest. "hg/autoSql" and
10604 ;; "hg/autoXml" are nominally free, but they depend on a
10605 ;; library that is built from the sources in "hg/lib",
10606 ;; which is nonfree.
10607 (let ((free (list "." ".."
10608 "utils" "lib" "inc" "tagStorm"
10609 "parasol" "htslib"))
10610 (directory? (lambda (file)
10611 (eq? 'directory (stat:type (stat file))))))
10612 (for-each (lambda (file)
10613 (and (directory? file)
10614 (delete-file-recursively file)))
10615 (map (cut string-append "src/" <>)
10618 (not (member file free)))))))
10619 ;; Only make the utils target, not the userApps target,
10620 ;; because that requires libraries we won't build.
10621 (substitute* "Makefile"
10622 ((" userApps") " utils"))
10623 ;; Only build libraries that are free.
10624 (substitute* "src/makefile"
10625 (("DIRS =.*") "DIRS =\n")
10626 (("cd jkOwnLib.*") "")
10629 (substitute* "src/utils/makefile"
10630 ;; These tools depend on "jkhgap.a", which is part of the
10631 ;; nonfree "src/hg/lib" directory.
10632 (("raSqlQuery") "")
10633 (("pslLiftSubrangeBlat") "")
10635 ;; Do not build UCSC tools, which may require nonfree
10637 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
10639 (build-system gnu-build-system)
10641 `( ;; There is no global test target and the test target for
10642 ;; individual tools depends on input files that are not
10646 (modify-phases %standard-phases
10647 (add-after 'unpack 'fix-paths
10649 (substitute* "Makefile"
10650 (("/bin/echo") (which "echo")))
10652 (add-after 'unpack 'prepare-samtabix
10653 (lambda* (#:key inputs #:allow-other-keys)
10654 (copy-recursively (assoc-ref inputs "samtabix")
10657 (delete 'configure)
10659 (lambda* (#:key outputs #:allow-other-keys)
10660 (let ((bin (string-append (assoc-ref outputs "out")
10662 (copy-recursively "bin" bin))
10668 (uri (git-reference
10669 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
10670 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
10673 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
10680 ("openssl" ,openssl)))
10681 (home-page "http://genome.cse.ucsc.edu/index.html")
10682 (synopsis "Assorted bioinformatics utilities")
10683 (description "This package provides the kentUtils, a selection of
10684 bioinformatics utilities used in combination with the UCSC genome
10686 ;; Only a subset of the sources are released under a non-copyleft
10687 ;; free software license. All other sources are removed in a
10688 ;; snippet. See this bug report for an explanation of how the
10689 ;; license statements apply:
10690 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
10691 (license (license:non-copyleft
10692 "http://genome.ucsc.edu/license/"
10693 "The contents of this package are free for all uses."))))
10695 (define-public f-seq
10696 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
10700 (version (string-append "1.1-" revision "." (string-take commit 7)))
10703 (uri (git-reference
10704 (url "https://github.com/aboyle/F-seq.git")
10706 (file-name (string-append name "-" version))
10709 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
10710 (modules '((guix build utils)))
10711 ;; Remove bundled Java library archives.
10714 (for-each delete-file (find-files "lib" ".*"))
10716 (build-system ant-build-system)
10718 `(#:tests? #f ; no tests included
10720 (modify-phases %standard-phases
10722 (lambda* (#:key inputs outputs #:allow-other-keys)
10723 (let* ((target (assoc-ref outputs "out"))
10724 (doc (string-append target "/share/doc/f-seq/")))
10727 (substitute* "bin/linux/fseq"
10728 (("java") (which "java"))
10729 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
10730 (string-append (assoc-ref inputs "java-commons-cli")
10731 "/share/java/commons-cli.jar"))
10733 (string-append "REALDIR=" target "/bin\n")))
10734 (install-file "README.txt" doc)
10735 (install-file "bin/linux/fseq" (string-append target "/bin"))
10736 (install-file "build~/fseq.jar" (string-append target "/lib"))
10737 (copy-recursively "lib" (string-append target "/lib"))
10741 ("java-commons-cli" ,java-commons-cli)))
10742 (home-page "http://fureylab.web.unc.edu/software/fseq/")
10743 (synopsis "Feature density estimator for high-throughput sequence tags")
10745 "F-Seq is a software package that generates a continuous tag sequence
10746 density estimation allowing identification of biologically meaningful sites
10747 such as transcription factor binding sites (ChIP-seq) or regions of open
10748 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
10750 (license license:gpl3+))))
10752 (define-public bismark
10759 (uri (string-append "https://github.com/FelixKrueger/Bismark/"
10760 "archive/" version ".tar.gz"))
10761 (file-name (string-append name "-" version ".tar.gz"))
10764 "1204i0pa02ll2jn5pnxypkclnskvv7a2nwh5nxhagmhxk9wfv9sq"))))
10765 (build-system perl-build-system)
10767 `(#:tests? #f ; there are no tests
10769 (modify-phases %standard-phases
10770 (delete 'configure)
10773 (lambda* (#:key outputs #:allow-other-keys)
10774 (let ((bin (string-append (assoc-ref outputs "out")
10776 (docdir (string-append (assoc-ref outputs "out")
10777 "/share/doc/bismark"))
10778 (docs '("Bismark_User_Guide.pdf"
10779 "RELEASE_NOTES.txt"))
10780 (scripts '("bismark"
10781 "bismark_genome_preparation"
10782 "bismark_methylation_extractor"
10785 "coverage2cytosine"
10786 "deduplicate_bismark"
10787 "bismark_sitrep.tpl"
10789 "bismark2summary")))
10792 (for-each (lambda (file) (install-file file bin))
10794 (for-each (lambda (file) (install-file file docdir))
10797 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
10798 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
10799 (description "Bismark is a program to map bisulfite treated sequencing
10800 reads to a genome of interest and perform methylation calls in a single step.
10801 The output can be easily imported into a genome viewer, such as SeqMonk, and
10802 enables a researcher to analyse the methylation levels of their samples
10803 straight away. Its main features are:
10806 @item Bisulfite mapping and methylation calling in one single step
10807 @item Supports single-end and paired-end read alignments
10808 @item Supports ungapped and gapped alignments
10809 @item Alignment seed length, number of mismatches etc are adjustable
10810 @item Output discriminates between cytosine methylation in CpG, CHG
10813 (license license:gpl3+)))
10815 (define-public paml
10821 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
10822 "paml" version ".tgz"))
10825 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
10826 (modules '((guix build utils)))
10827 ;; Remove Windows binaries
10830 (for-each delete-file (find-files "." "\\.exe$"))
10832 (build-system gnu-build-system)
10834 `(#:tests? #f ; there are no tests
10835 #:make-flags '("CC=gcc")
10837 (modify-phases %standard-phases
10838 (replace 'configure
10840 (substitute* "src/BFdriver.c"
10841 (("/bin/bash") (which "bash")))
10845 (lambda* (#:key outputs #:allow-other-keys)
10846 (let ((tools '("baseml" "basemlg" "codeml"
10847 "pamp" "evolver" "yn00" "chi2"))
10848 (bin (string-append (assoc-ref outputs "out") "/bin"))
10849 (docdir (string-append (assoc-ref outputs "out")
10850 "/share/doc/paml")))
10852 (for-each (lambda (file) (install-file file bin)) tools)
10853 (copy-recursively "../doc" docdir)
10855 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
10856 (synopsis "Phylogentic analysis by maximum likelihood")
10857 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
10858 contains a few programs for model fitting and phylogenetic tree reconstruction
10859 using nucleotide or amino-acid sequence data.")
10861 (license license:gpl3)))